diff options
912 files changed, 12909 insertions, 7655 deletions
@@ -19,6 +19,7 @@ Abhinav Kumar <quic_abhinavk@quicinc.com> <abhinavk@codeaurora.org> Ahmad Masri <quic_amasri@quicinc.com> <amasri@codeaurora.org> Adam Oldham <oldhamca@gmail.com> Adam Radford <aradford@gmail.com> +Aditya Garg <gargaditya08@proton.me> <gargaditya08@live.com> Adriana Reus <adi.reus@gmail.com> <adriana.reus@intel.com> Adrian Bunk <bunk@stusta.de> Ajay Kaher <ajay.kaher@broadcom.com> <akaher@vmware.com> @@ -207,6 +208,7 @@ Claudiu Beznea <claudiu.beznea@tuxon.dev> <claudiu.beznea@microchip.com> Colin Ian King <colin.i.king@gmail.com> <colin.king@canonical.com> Corey Minyard <minyard@acm.org> Damian Hobson-Garcia <dhobsong@igel.co.jp> +Dan Carpenter <error27@gmail.com> <dan.carpenter@linaro.org> Dan Carpenter <error27@gmail.com> <dan.carpenter@oracle.com> Dan Williams <djbw@kernel.org> <dan.j.williams@intel.com> Daniel Borkmann <daniel@iogearbox.net> <danborkmann@googlemail.com> @@ -495,6 +497,7 @@ Leon Romanovsky <leon@kernel.org> <leon@leon.nu> Leon Romanovsky <leon@kernel.org> <leonro@mellanox.com> Leon Romanovsky <leon@kernel.org> <leonro@nvidia.com> Leo Yan <leo.yan@linux.dev> <leo.yan@linaro.org> +Liam R. Howlett <liam@infradead.org> <Liam.Howlett@oracle.com> Liam Mark <quic_lmark@quicinc.com> <lmark@codeaurora.org> Linas Vepstas <linas@austin.ibm.com> Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@ascom.ch> @@ -505,6 +508,8 @@ Linus Walleij <linusw@kernel.org> <linus.walleij@stericsson.com> Linus Walleij <linusw@kernel.org> <linus.walleij@linaro.org> Linus Walleij <linusw@kernel.org> <triad@df.lth.se> <linux-hardening@vger.kernel.org> <kernel-hardening@lists.openwall.com> +Li Wang <li.wang@linux.dev> <liwang@redhat.com> +Li Wang <li.wang@linux.dev> <wangli.ahau@gmail.com> Li Yang <leoyang.li@nxp.com> <leoli@freescale.com> Li Yang <leoyang.li@nxp.com> <leo@zh-kernel.org> Lior David <quic_liord@quicinc.com> <liord@codeaurora.org> @@ -687,6 +692,7 @@ Punit Agrawal <punitagrawal@gmail.com> <punit.agrawal@arm.com> Puranjay Mohan <puranjay@kernel.org> <puranjay12@gmail.com> Qais Yousef <qyousef@layalina.io> <qais.yousef@imgtec.com> Qais Yousef <qyousef@layalina.io> <qais.yousef@arm.com> +Qi Zheng <qi.zheng@linux.dev> <zhengqi.arch@bytedance.com> Quentin Monnet <qmo@kernel.org> <quentin.monnet@netronome.com> Quentin Monnet <qmo@kernel.org> <quentin@isovalent.com> Quentin Perret <qperret@qperret.net> <quentin.perret@arm.com> diff --git a/Documentation/ABI/obsolete/sysfs-selinux-user b/Documentation/ABI/removed/sysfs-selinux-user index 8ab7557f283f..8ab7557f283f 100644 --- a/Documentation/ABI/obsolete/sysfs-selinux-user +++ b/Documentation/ABI/removed/sysfs-selinux-user diff --git a/Documentation/admin-guide/cgroup-v1/memcg_test.rst b/Documentation/admin-guide/cgroup-v1/memcg_test.rst index 9f8e27355cba..7c7cd457cf69 100644 --- a/Documentation/admin-guide/cgroup-v1/memcg_test.rst +++ b/Documentation/admin-guide/cgroup-v1/memcg_test.rst @@ -47,21 +47,19 @@ Please note that implementation details can be changed. Called when swp_entry's refcnt goes down to 0. A charge against swap disappears. -3. charge-commit-cancel +3. charge-commit ======================= Memcg pages are charged in two steps: - mem_cgroup_try_charge() - - mem_cgroup_commit_charge() or mem_cgroup_cancel_charge() + - commit_charge() At try_charge(), there are no flags to say "this page is charged". at this point, usage += PAGE_SIZE. At commit(), the page is associated with the memcg. - At cancel(), simply usage -= PAGE_SIZE. - Under below explanation, we assume CONFIG_SWAP=y. 4. Anonymous diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 8ad0b2781317..6efd0095ed99 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -220,7 +220,7 @@ cgroup v2 currently supports the following mount options. memory_hugetlb_accounting Count HugeTLB memory usage towards the cgroup's overall memory usage for the memory controller (for the purpose of - statistics reporting and memory protetion). This is a new + statistics reporting and memory protection). This is a new behavior that could regress existing setups, so it must be explicitly opted in with this mount option. diff --git a/Documentation/devicetree/bindings/mailbox/qcom-ipcc.yaml b/Documentation/devicetree/bindings/mailbox/qcom-ipcc.yaml index 7c4d6170491d..f5c584cf2146 100644 --- a/Documentation/devicetree/bindings/mailbox/qcom-ipcc.yaml +++ b/Documentation/devicetree/bindings/mailbox/qcom-ipcc.yaml @@ -24,6 +24,7 @@ properties: compatible: items: - enum: + - qcom,eliza-ipcc - qcom,glymur-ipcc - qcom,kaanapali-ipcc - qcom,milos-ipcc diff --git a/Documentation/filesystems/isofs.rst b/Documentation/filesystems/isofs.rst index 08fd469091d4..2a30999b024f 100644 --- a/Documentation/filesystems/isofs.rst +++ b/Documentation/filesystems/isofs.rst @@ -57,7 +57,7 @@ Mount options unique to the isofs filesystem. Recommended documents about ISO 9660 standard are located at: - http://www.y-adagio.com/ -- ftp://ftp.ecma.ch/ecma-st/Ecma-119.pdf +- https://ecma-international.org/wp-content/uploads/ECMA-119_2nd_edition_december_1987.pdf Quoting from the PDF "This 2nd Edition of Standard ECMA-119 is technically identical with ISO 9660.", so it is a valid and gratis substitute of the diff --git a/Documentation/netlink/specs/psp.yaml b/Documentation/netlink/specs/psp.yaml index 100c36cda8e5..bfcd6e4ecb85 100644 --- a/Documentation/netlink/specs/psp.yaml +++ b/Documentation/netlink/specs/psp.yaml @@ -188,6 +188,7 @@ operations: name: dev-set doc: Set the configuration of a PSP device. attribute-set: dev + flags: [admin-perm] do: request: attributes: @@ -207,6 +208,7 @@ operations: name: key-rotate doc: Rotate the device key. attribute-set: dev + flags: [admin-perm] do: request: attributes: diff --git a/MAINTAINERS b/MAINTAINERS index 06c00e40999f..e471241229aa 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7077,6 +7077,12 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git core/debugobjec F: include/linux/debugobjects.h F: lib/debugobjects.c +DEC LANCE NETWORK DRIVER +M: "Maciej W. Rozycki" <macro@orcam.me.uk> +L: netdev@vger.kernel.org +S: Maintained +F: drivers/net/ethernet/amd/declance.c + DECSTATION PLATFORM SUPPORT M: "Maciej W. Rozycki" <macro@orcam.me.uk> L: linux-mips@vger.kernel.org @@ -7873,7 +7879,7 @@ F: drivers/gpu/drm/sun4i/sun8i* DRM DRIVER FOR APPLE TOUCH BARS M: Aun-Ali Zaidi <admin@kodeit.net> -M: Aditya Garg <gargaditya08@live.com> +M: Aditya Garg <gargaditya08@proton.me> L: dri-devel@lists.freedesktop.org S: Maintained T: git https://gitlab.freedesktop.org/drm/misc/kernel.git @@ -8193,10 +8199,9 @@ F: include/uapi/drm/nouveau_drm.h CORE DRIVER FOR NVIDIA GPUS [RUST] M: Danilo Krummrich <dakr@kernel.org> M: Alexandre Courbot <acourbot@nvidia.com> -L: nouveau@lists.freedesktop.org +L: nova-gpu@lists.linux.dev S: Supported W: https://rust-for-linux.com/nova-gpu-driver -Q: https://patchwork.freedesktop.org/project/nouveau/ B: https://gitlab.freedesktop.org/drm/nova/-/issues C: irc://irc.oftc.net/nouveau T: git https://gitlab.freedesktop.org/drm/rust/kernel.git drm-rust-next @@ -8205,10 +8210,9 @@ F: drivers/gpu/nova-core/ DRM DRIVER FOR NVIDIA GPUS [RUST] M: Danilo Krummrich <dakr@kernel.org> -L: nouveau@lists.freedesktop.org +L: nova-gpu@lists.linux.dev S: Supported W: https://rust-for-linux.com/nova-gpu-driver -Q: https://patchwork.freedesktop.org/project/nouveau/ B: https://gitlab.freedesktop.org/drm/nova/-/issues C: irc://irc.oftc.net/nouveau T: git https://gitlab.freedesktop.org/drm/rust/kernel.git drm-rust-next @@ -13860,7 +13864,6 @@ M: Pratyush Yadav <pratyush@kernel.org> R: Dave Young <ruirui.yang@linux.dev> L: kexec@lists.infradead.org S: Maintained -W: http://lse.sourceforge.net/kdump/ F: Documentation/admin-guide/kdump/ F: fs/proc/vmcore.c F: include/linux/crash_core.h @@ -15252,7 +15255,7 @@ M: Andrea Cervesato <andrea.cervesato@suse.com> M: Cyril Hrubis <chrubis@suse.cz> M: Jan Stancek <jstancek@redhat.com> M: Petr Vorel <pvorel@suse.cz> -M: Li Wang <liwang@redhat.com> +M: Li Wang <li.wang@linux.dev> M: Yang Xu <xuyang2018.jy@fujitsu.com> M: Xiao Yang <yangx.jy@fujitsu.com> L: ltp@lists.linux.it (subscribers-only) @@ -15399,7 +15402,7 @@ F: include/net/netns/mctp.h F: net/mctp/ MAPLE TREE -M: Liam R. Howlett <Liam.Howlett@oracle.com> +M: Liam R. Howlett <liam@infradead.org> R: Alice Ryhl <aliceryhl@google.com> R: Andrew Ballance <andrewjballance@gmail.com> L: maple-tree@lists.infradead.org @@ -16759,7 +16762,7 @@ MEMORY MANAGEMENT - CORE M: Andrew Morton <akpm@linux-foundation.org> M: David Hildenbrand <david@kernel.org> R: Lorenzo Stoakes <ljs@kernel.org> -R: Liam R. Howlett <Liam.Howlett@oracle.com> +R: Liam R. Howlett <liam@infradead.org> R: Vlastimil Babka <vbabka@kernel.org> R: Mike Rapoport <rppt@kernel.org> R: Suren Baghdasaryan <surenb@google.com> @@ -16805,7 +16808,7 @@ F: mm/sparse.c F: mm/util.c F: mm/vmpressure.c F: mm/vmstat.c -N: include/linux/page[-_]* +N: include\/linux\/page[-_][a-zA-Z]* MEMORY MANAGEMENT - EXECMEM M: Andrew Morton <akpm@linux-foundation.org> @@ -16895,7 +16898,7 @@ MEMORY MANAGEMENT - MISC M: Andrew Morton <akpm@linux-foundation.org> M: David Hildenbrand <david@kernel.org> R: Lorenzo Stoakes <ljs@kernel.org> -R: Liam R. Howlett <Liam.Howlett@oracle.com> +R: Liam R. Howlett <liam@infradead.org> R: Vlastimil Babka <vbabka@kernel.org> R: Mike Rapoport <rppt@kernel.org> R: Suren Baghdasaryan <surenb@google.com> @@ -16962,6 +16965,7 @@ S: Maintained F: include/linux/compaction.h F: include/linux/gfp.h F: include/linux/page-isolation.h +F: include/linux/pageblock-flags.h F: mm/compaction.c F: mm/debug_page_alloc.c F: mm/debug_page_ref.c @@ -16983,7 +16987,7 @@ M: Andrew Morton <akpm@linux-foundation.org> M: Johannes Weiner <hannes@cmpxchg.org> R: David Hildenbrand <david@kernel.org> R: Michal Hocko <mhocko@kernel.org> -R: Qi Zheng <zhengqi.arch@bytedance.com> +R: Qi Zheng <qi.zheng@linux.dev> R: Shakeel Butt <shakeel.butt@linux.dev> R: Lorenzo Stoakes <ljs@kernel.org> L: linux-mm@kvack.org @@ -16996,7 +17000,7 @@ M: Andrew Morton <akpm@linux-foundation.org> M: David Hildenbrand <david@kernel.org> M: Lorenzo Stoakes <ljs@kernel.org> R: Rik van Riel <riel@surriel.com> -R: Liam R. Howlett <Liam.Howlett@oracle.com> +R: Liam R. Howlett <liam@infradead.org> R: Vlastimil Babka <vbabka@kernel.org> R: Harry Yoo <harry@kernel.org> R: Jann Horn <jannh@google.com> @@ -17043,7 +17047,7 @@ M: David Hildenbrand <david@kernel.org> M: Lorenzo Stoakes <ljs@kernel.org> R: Zi Yan <ziy@nvidia.com> R: Baolin Wang <baolin.wang@linux.alibaba.com> -R: Liam R. Howlett <Liam.Howlett@oracle.com> +R: Liam R. Howlett <liam@infradead.org> R: Nico Pache <npache@redhat.com> R: Ryan Roberts <ryan.roberts@arm.com> R: Dev Jain <dev.jain@arm.com> @@ -17081,7 +17085,7 @@ F: tools/testing/selftests/mm/uffd-*.[ch] MEMORY MANAGEMENT - RUST M: Alice Ryhl <aliceryhl@google.com> R: Lorenzo Stoakes <ljs@kernel.org> -R: Liam R. Howlett <Liam.Howlett@oracle.com> +R: Liam R. Howlett <liam@infradead.org> L: linux-mm@kvack.org L: rust-for-linux@vger.kernel.org S: Maintained @@ -17095,7 +17099,7 @@ F: rust/kernel/page.rs MEMORY MAPPING M: Andrew Morton <akpm@linux-foundation.org> -M: Liam R. Howlett <Liam.Howlett@oracle.com> +M: Liam R. Howlett <liam@infradead.org> M: Lorenzo Stoakes <ljs@kernel.org> R: Vlastimil Babka <vbabka@kernel.org> R: Jann Horn <jannh@google.com> @@ -17127,7 +17131,7 @@ F: tools/testing/vma/ MEMORY MAPPING - LOCKING M: Andrew Morton <akpm@linux-foundation.org> M: Suren Baghdasaryan <surenb@google.com> -M: Liam R. Howlett <Liam.Howlett@oracle.com> +M: Liam R. Howlett <liam@infradead.org> M: Lorenzo Stoakes <ljs@kernel.org> R: Vlastimil Babka <vbabka@kernel.org> R: Shakeel Butt <shakeel.butt@linux.dev> @@ -17142,7 +17146,7 @@ F: mm/mmap_lock.c MEMORY MAPPING - MADVISE (MEMORY ADVICE) M: Andrew Morton <akpm@linux-foundation.org> -M: Liam R. Howlett <Liam.Howlett@oracle.com> +M: Liam R. Howlett <liam@infradead.org> M: Lorenzo Stoakes <ljs@kernel.org> M: David Hildenbrand <david@kernel.org> R: Vlastimil Babka <vbabka@kernel.org> @@ -18672,19 +18676,59 @@ F: net/xfrm/ F: tools/testing/selftests/net/ipsec.c NETWORKING [IPv4/IPv6] -M: "David S. Miller" <davem@davemloft.net> M: David Ahern <dsahern@kernel.org> +M: Ido Schimmel <idosch@nvidia.com> L: netdev@vger.kernel.org S: Maintained -T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git -F: arch/x86/net/* -F: include/linux/ip.h -F: include/linux/ipv6* +F: Documentation/netlink/specs/rt-addr.yaml +F: Documentation/netlink/specs/rt-neigh.yaml +F: Documentation/netlink/specs/rt-route.yaml +F: Documentation/netlink/specs/rt-rule.yaml +F: include/linux/inetdevice.h +F: include/linux/mroute* +F: include/net/addrconf.h +F: include/net/arp.h F: include/net/fib* +F: include/net/if_inet6.h +F: include/net/inetpeer.h F: include/net/ip* +F: include/net/lwtunnel.h +F: include/net/ndisc.h +F: include/net/netns/nexthop.h +F: include/net/nexthop.h F: include/net/route.h -F: net/ipv4/ -F: net/ipv6/ +F: include/uapi/linux/fib_rules.h +F: include/uapi/linux/in_route.h +F: include/uapi/linux/mroute* +F: include/uapi/linux/nexthop.h +F: net/core/fib* +F: net/core/lwtunnel.c +F: net/ipv4/arp.c +F: net/ipv4/devinet.c +F: net/ipv4/fib* +F: net/ipv4/icmp.c +F: net/ipv4/igmp.c +F: net/ipv4/inet_fragment.c +F: net/ipv4/inetpeer.c +F: net/ipv4/ip* +F: net/ipv4/metrics.c +F: net/ipv4/netlink.c +F: net/ipv4/nexthop.c +F: net/ipv4/route.c +F: net/ipv6/addr* +F: net/ipv6/anycast.c +F: net/ipv6/exthdrs.c +F: net/ipv6/exthdrs_core.c +F: net/ipv6/fib* +F: net/ipv6/icmp.c +F: net/ipv6/ip* +F: net/ipv6/mcast* +F: net/ipv6/ndisc.c +F: net/ipv6/output_core.c +F: net/ipv6/reassembly.c +F: net/ipv6/route.c +F: tools/testing/selftests/net/fib* +F: tools/testing/selftests/net/forwarding/ NETWORKING [LABELED] (NetLabel, Labeled IPsec, SECMARK) M: Paul Moore <paul@paul-moore.com> @@ -18819,18 +18863,11 @@ F: Documentation/networking/net_failover.rst F: drivers/net/net_failover.c F: include/net/net_failover.h -NEXTHOP -M: David Ahern <dsahern@kernel.org> -L: netdev@vger.kernel.org -S: Maintained -F: include/net/netns/nexthop.h -F: include/net/nexthop.h -F: include/uapi/linux/nexthop.h -F: net/ipv4/nexthop.c - NFC SUBSYSTEM -L: netdev@vger.kernel.org -S: Orphan +M: David Heidelberg <david+nfc@ixit.cz> +L: oe-linux-nfc@lists.linux.dev +S: Maintained +T: git https://codeberg.org/linux-nfc/linux.git F: Documentation/devicetree/bindings/net/nfc/ F: drivers/nfc/ F: include/net/nfc/ @@ -20774,6 +20811,7 @@ M: Dominik Brodowski <linux@dominikbrodowski.net> S: Odd Fixes T: git git://git.kernel.org/pub/scm/linux/kernel/git/brodo/linux.git F: Documentation/pcmcia/ +F: drivers/net/ethernet/8390/pcnet_cs.c F: drivers/pcmcia/ F: include/pcmcia/ F: tools/pcmcia/ @@ -23369,7 +23407,7 @@ RUST [ALLOC] M: Danilo Krummrich <dakr@kernel.org> R: Lorenzo Stoakes <ljs@kernel.org> R: Vlastimil Babka <vbabka@kernel.org> -R: Liam R. Howlett <Liam.Howlett@oracle.com> +R: Liam R. Howlett <liam@infradead.org> R: Uladzislau Rezki <urezki@gmail.com> L: rust-for-linux@vger.kernel.org S: Maintained @@ -23521,7 +23559,7 @@ F: drivers/s390/net/ S390 PCI SUBSYSTEM M: Niklas Schnelle <schnelle@linux.ibm.com> -M: Gerald Schaefer <gerald.schaefer@linux.ibm.com> +M: Gerd Bayer <gbayer@linux.ibm.com> L: linux-s390@vger.kernel.org S: Supported F: Documentation/arch/s390/pci.rst @@ -24314,7 +24352,7 @@ F: include/media/i2c/rj54n1cb0c.h SHRINKER M: Andrew Morton <akpm@linux-foundation.org> M: Dave Chinner <david@fromorbit.com> -R: Qi Zheng <zhengqi.arch@bytedance.com> +R: Qi Zheng <qi.zheng@linux.dev> R: Roman Gushchin <roman.gushchin@linux.dev> R: Muchun Song <muchun.song@linux.dev> L: linux-mm@kvack.org @@ -24616,6 +24654,7 @@ S: Maintained F: fs/smb/client/smbdirect.* F: fs/smb/smbdirect/ F: fs/smb/server/transport_rdma.* +F: include/linux/smbdirect.h SMC91x ETHERNET DRIVER M: Nicolas Pitre <nico@fluxnic.net> @@ -2,7 +2,7 @@ VERSION = 7 PATCHLEVEL = 1 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc2 NAME = Baby Opossum Posse # *DOCUMENTATION* diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h index d4d7451c2c12..a8cb5a5c93b7 100644 --- a/arch/arm64/include/asm/irqflags.h +++ b/arch/arm64/include/asm/irqflags.h @@ -40,7 +40,7 @@ static __always_inline void __pmr_local_irq_enable(void) barrier(); } -static inline void arch_local_irq_enable(void) +static __always_inline void arch_local_irq_enable(void) { if (system_uses_irq_prio_masking()) { __pmr_local_irq_enable(); @@ -68,7 +68,7 @@ static __always_inline void __pmr_local_irq_disable(void) barrier(); } -static inline void arch_local_irq_disable(void) +static __always_inline void arch_local_irq_disable(void) { if (system_uses_irq_prio_masking()) { __pmr_local_irq_disable(); @@ -90,7 +90,7 @@ static __always_inline unsigned long __pmr_local_save_flags(void) /* * Save the current interrupt enable state. */ -static inline unsigned long arch_local_save_flags(void) +static __always_inline unsigned long arch_local_save_flags(void) { if (system_uses_irq_prio_masking()) { return __pmr_local_save_flags(); @@ -109,7 +109,7 @@ static __always_inline bool __pmr_irqs_disabled_flags(unsigned long flags) return flags != GIC_PRIO_IRQON; } -static inline bool arch_irqs_disabled_flags(unsigned long flags) +static __always_inline bool arch_irqs_disabled_flags(unsigned long flags) { if (system_uses_irq_prio_masking()) { return __pmr_irqs_disabled_flags(flags); @@ -128,7 +128,7 @@ static __always_inline bool __pmr_irqs_disabled(void) return __pmr_irqs_disabled_flags(__pmr_local_save_flags()); } -static inline bool arch_irqs_disabled(void) +static __always_inline bool arch_irqs_disabled(void) { if (system_uses_irq_prio_masking()) { return __pmr_irqs_disabled(); @@ -160,7 +160,7 @@ static __always_inline unsigned long __pmr_local_irq_save(void) return flags; } -static inline unsigned long arch_local_irq_save(void) +static __always_inline unsigned long arch_local_irq_save(void) { if (system_uses_irq_prio_masking()) { return __pmr_local_irq_save(); @@ -187,7 +187,7 @@ static __always_inline void __pmr_local_irq_restore(unsigned long flags) /* * restore saved IRQ state */ -static inline void arch_local_irq_restore(unsigned long flags) +static __always_inline void arch_local_irq_restore(unsigned long flags) { if (system_uses_irq_prio_masking()) { __pmr_local_irq_restore(flags); diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h index 74a4f738c5f5..229ee7976f69 100644 --- a/arch/arm64/include/asm/kernel-pgtable.h +++ b/arch/arm64/include/asm/kernel-pgtable.h @@ -68,7 +68,12 @@ #define KERNEL_SEGMENT_COUNT 5 #if SWAPPER_BLOCK_SIZE > SEGMENT_ALIGN -#define EARLY_SEGMENT_EXTRA_PAGES (KERNEL_SEGMENT_COUNT + 1) +/* + * KERNEL_SEGMENT_COUNT counts the permanent kernel VMAs. The early mapping + * has one additional split, [_text, _stext). Reserve one more page for the + * SWAPPER_BLOCK_SIZE-unaligned boundaries. + */ +#define EARLY_SEGMENT_EXTRA_PAGES (KERNEL_SEGMENT_COUNT + 2) /* * The initial ID map consists of the kernel image, mapped as two separate * segments, and may appear misaligned wrt the swapper block size. This means diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index 37414440cee7..043495f7fc78 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -50,6 +50,9 @@ #include <linux/mm.h> +#define MARKER(m) \ + m, __after_##m = m - 1 + enum __kvm_host_smccc_func { /* Hypercalls that are unavailable once pKVM has finalised. */ /* __KVM_HOST_SMCCC_FUNC___kvm_hyp_init */ @@ -59,8 +62,10 @@ enum __kvm_host_smccc_func { __KVM_HOST_SMCCC_FUNC___kvm_enable_ssbs, __KVM_HOST_SMCCC_FUNC___vgic_v3_init_lrs, __KVM_HOST_SMCCC_FUNC___vgic_v3_get_gic_config, + + MARKER(__KVM_HOST_SMCCC_FUNC_MIN_PKVM), + __KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize, - __KVM_HOST_SMCCC_FUNC_MIN_PKVM = __KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize, /* Hypercalls that are always available and common to [nh]VHE/pKVM. */ __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc, @@ -72,11 +77,20 @@ enum __kvm_host_smccc_func { __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_range, __KVM_HOST_SMCCC_FUNC___kvm_flush_cpu_context, __KVM_HOST_SMCCC_FUNC___kvm_timer_set_cntvoff, + __KVM_HOST_SMCCC_FUNC___tracing_load, + __KVM_HOST_SMCCC_FUNC___tracing_unload, + __KVM_HOST_SMCCC_FUNC___tracing_enable, + __KVM_HOST_SMCCC_FUNC___tracing_swap_reader, + __KVM_HOST_SMCCC_FUNC___tracing_update_clock, + __KVM_HOST_SMCCC_FUNC___tracing_reset, + __KVM_HOST_SMCCC_FUNC___tracing_enable_event, + __KVM_HOST_SMCCC_FUNC___tracing_write_event, __KVM_HOST_SMCCC_FUNC___vgic_v3_save_aprs, __KVM_HOST_SMCCC_FUNC___vgic_v3_restore_vmcr_aprs, __KVM_HOST_SMCCC_FUNC___vgic_v5_save_apr, __KVM_HOST_SMCCC_FUNC___vgic_v5_restore_vmcr_apr, - __KVM_HOST_SMCCC_FUNC_MAX_NO_PKVM = __KVM_HOST_SMCCC_FUNC___vgic_v5_restore_vmcr_apr, + + MARKER(__KVM_HOST_SMCCC_FUNC_PKVM_ONLY), /* Hypercalls that are available only when pKVM has finalised. */ __KVM_HOST_SMCCC_FUNC___pkvm_host_share_hyp, @@ -100,14 +114,8 @@ enum __kvm_host_smccc_func { __KVM_HOST_SMCCC_FUNC___pkvm_vcpu_load, __KVM_HOST_SMCCC_FUNC___pkvm_vcpu_put, __KVM_HOST_SMCCC_FUNC___pkvm_tlb_flush_vmid, - __KVM_HOST_SMCCC_FUNC___tracing_load, - __KVM_HOST_SMCCC_FUNC___tracing_unload, - __KVM_HOST_SMCCC_FUNC___tracing_enable, - __KVM_HOST_SMCCC_FUNC___tracing_swap_reader, - __KVM_HOST_SMCCC_FUNC___tracing_update_clock, - __KVM_HOST_SMCCC_FUNC___tracing_reset, - __KVM_HOST_SMCCC_FUNC___tracing_enable_event, - __KVM_HOST_SMCCC_FUNC___tracing_write_event, + + MARKER(__KVM_HOST_SMCCC_FUNC_MAX) }; #define DECLARE_KVM_VHE_SYM(sym) extern char sym[] diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 851f6171751c..65eead8362e0 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -450,9 +450,6 @@ struct kvm_vcpu_fault_info { r = __VNCR_START__ + ((VNCR_ ## r) / 8), \ __after_##r = __MAX__(__before_##r - 1, r) -#define MARKER(m) \ - m, __after_##m = m - 1 - enum vcpu_sysreg { __INVALID_SYSREG__, /* 0 is reserved as an invalid value */ MPIDR_EL1, /* MultiProcessor Affinity Register */ @@ -1548,7 +1545,7 @@ static inline bool __vcpu_has_feature(const struct kvm_arch *ka, int feature) #define kvm_vcpu_has_feature(k, f) __vcpu_has_feature(&(k)->arch, (f)) #define vcpu_has_feature(v, f) __vcpu_has_feature(&(v)->kvm->arch, (f)) -#define kvm_vcpu_initialized(v) vcpu_get_flag(vcpu, VCPU_INITIALIZED) +#define kvm_vcpu_initialized(v) vcpu_get_flag(v, VCPU_INITIALIZED) int kvm_trng_call(struct kvm_vcpu *vcpu); #ifdef CONFIG_KVM diff --git a/arch/arm64/kernel/pi/patch-scs.c b/arch/arm64/kernel/pi/patch-scs.c index dac568e4a54f..3944ad899021 100644 --- a/arch/arm64/kernel/pi/patch-scs.c +++ b/arch/arm64/kernel/pi/patch-scs.c @@ -196,9 +196,9 @@ static int scs_handle_fde_frame(const struct eh_frame *frame, loc += *opcode++ * code_alignment_factor; loc += (*opcode++ << 8) * code_alignment_factor; loc += (*opcode++ << 16) * code_alignment_factor; - loc += (*opcode++ << 24) * code_alignment_factor; + loc += ((u64)*opcode++ << 24) * code_alignment_factor; size -= 4; - break; + break; case DW_CFA_def_cfa: case DW_CFA_offset_extended: diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 08ffc5a5aea4..38e6fa204c17 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -67,6 +67,9 @@ struct rt_sigframe_user_layout { unsigned long end_offset; }; +#define TERMINATOR_SIZE round_up(sizeof(struct _aarch64_ctx), 16) +#define EXTRA_CONTEXT_SIZE round_up(sizeof(struct extra_context), 16) + /* * Holds any EL0-controlled state that influences unprivileged memory accesses. * This includes both accesses done in userspace and uaccess done in the kernel. @@ -74,13 +77,35 @@ struct rt_sigframe_user_layout { * This state needs to be carefully managed to ensure that it doesn't cause * uaccess to fail when setting up the signal frame, and the signal handler * itself also expects a well-defined state when entered. + * + * The struct should be zero-initialised. Its members should only be accessed + * via the accessors below. __valid_fields tracks which of the fields are valid + * (have been set to some value). */ struct user_access_state { - u64 por_el0; + unsigned int __valid_fields; + u64 __por_el0; }; -#define TERMINATOR_SIZE round_up(sizeof(struct _aarch64_ctx), 16) -#define EXTRA_CONTEXT_SIZE round_up(sizeof(struct extra_context), 16) +#define UA_STATE_HAS_POR_EL0 BIT(0) + +static void set_ua_state_por_el0(struct user_access_state *ua_state, + u64 por_el0) +{ + ua_state->__por_el0 = por_el0; + ua_state->__valid_fields |= UA_STATE_HAS_POR_EL0; +} + +static int get_ua_state_por_el0(const struct user_access_state *ua_state, + u64 *por_el0) +{ + if (ua_state->__valid_fields & UA_STATE_HAS_POR_EL0) { + *por_el0 = ua_state->__por_el0; + return 0; + } + + return -ENOENT; +} /* * Save the user access state into ua_state and reset it to disable any @@ -94,7 +119,7 @@ static void save_reset_user_access_state(struct user_access_state *ua_state) for (int pkey = 0; pkey < arch_max_pkey(); pkey++) por_enable_all |= POR_ELx_PERM_PREP(pkey, POE_RWX); - ua_state->por_el0 = read_sysreg_s(SYS_POR_EL0); + set_ua_state_por_el0(ua_state, read_sysreg_s(SYS_POR_EL0)); write_sysreg_s(por_enable_all, SYS_POR_EL0); /* * No ISB required as we can tolerate spurious Overlay faults - @@ -122,8 +147,10 @@ static void set_handler_user_access_state(void) */ static void restore_user_access_state(const struct user_access_state *ua_state) { - if (system_supports_poe()) - write_sysreg_s(ua_state->por_el0, SYS_POR_EL0); + u64 por_el0; + + if (get_ua_state_por_el0(ua_state, &por_el0) == 0) + write_sysreg_s(por_el0, SYS_POR_EL0); } static void init_user_layout(struct rt_sigframe_user_layout *user) @@ -333,11 +360,16 @@ static int restore_fpmr_context(struct user_ctxs *user) static int preserve_poe_context(struct poe_context __user *ctx, const struct user_access_state *ua_state) { - int err = 0; + int err; + u64 por_el0; + + err = get_ua_state_por_el0(ua_state, &por_el0); + if (WARN_ON_ONCE(err)) + return err; __put_user_error(POE_MAGIC, &ctx->head.magic, err); __put_user_error(sizeof(*ctx), &ctx->head.size, err); - __put_user_error(ua_state->por_el0, &ctx->por_el0, err); + __put_user_error(por_el0, &ctx->por_el0, err); return err; } @@ -353,7 +385,7 @@ static int restore_poe_context(struct user_ctxs *user, __get_user_error(por_el0, &(user->poe->por_el0), err); if (!err) - ua_state->por_el0 = por_el0; + set_ua_state_por_el0(ua_state, por_el0); return err; } @@ -1095,7 +1127,7 @@ SYSCALL_DEFINE0(rt_sigreturn) { struct pt_regs *regs = current_pt_regs(); struct rt_sigframe __user *frame; - struct user_access_state ua_state; + struct user_access_state ua_state = {}; /* Always make any pending restarted system calls return -EINTR */ current->restart_block.fn = do_no_restart_syscall; @@ -1507,7 +1539,7 @@ static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set, { struct rt_sigframe_user_layout user; struct rt_sigframe __user *frame; - struct user_access_state ua_state; + struct user_access_state ua_state = {}; int err = 0; fpsimd_save_and_flush_current_state(); diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 176cbe8baad3..8bb2c7422cc8 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -824,6 +824,10 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *v) { bool irq_lines = *vcpu_hcr(v) & (HCR_VI | HCR_VF | HCR_VSE); + irq_lines |= (!irqchip_in_kernel(v->kvm) && + (kvm_timer_should_notify_user(v) || + kvm_pmu_should_notify_user(v))); + return ((irq_lines || kvm_vgic_vcpu_pending_irq(v)) && !kvm_arm_vcpu_stopped(v) && !v->arch.pause); } diff --git a/arch/arm64/kvm/config.c b/arch/arm64/kvm/config.c index f35b8dddd7c1..0622162b089e 100644 --- a/arch/arm64/kvm/config.c +++ b/arch/arm64/kvm/config.c @@ -131,7 +131,6 @@ struct reg_feat_map_desc { } #define FEAT_SPE ID_AA64DFR0_EL1, PMSVer, IMP -#define FEAT_SPE_FnE ID_AA64DFR0_EL1, PMSVer, V1P2 #define FEAT_BRBE ID_AA64DFR0_EL1, BRBE, IMP #define FEAT_TRC_SR ID_AA64DFR0_EL1, TraceVer, IMP #define FEAT_PMUv3 ID_AA64DFR0_EL1, PMUVer, IMP @@ -192,7 +191,7 @@ struct reg_feat_map_desc { #define FEAT_SRMASK ID_AA64MMFR4_EL1, SRMASK, IMP #define FEAT_PoPS ID_AA64MMFR4_EL1, PoPS, IMP #define FEAT_PFAR ID_AA64PFR1_EL1, PFAR, IMP -#define FEAT_Debugv8p9 ID_AA64DFR0_EL1, PMUVer, V3P9 +#define FEAT_Debugv8p9 ID_AA64DFR0_EL1, DebugVer, V8P9 #define FEAT_PMUv3_SS ID_AA64DFR0_EL1, PMSS, IMP #define FEAT_SEBEP ID_AA64DFR0_EL1, SEBEP, IMP #define FEAT_EBEP ID_AA64DFR1_EL1, EBEP, IMP @@ -283,7 +282,7 @@ static bool feat_anerr(struct kvm *kvm) static bool feat_sme_smps(struct kvm *kvm) { /* - * Revists this if KVM ever supports SME -- this really should + * Revisit this if KVM ever supports SME -- this really should * look at the guest's view of SMIDR_EL1. Funnily enough, this * is not captured in the JSON file, but only as a note in the * ARM ARM. @@ -295,17 +294,27 @@ static bool feat_sme_smps(struct kvm *kvm) static bool feat_spe_fds(struct kvm *kvm) { /* - * Revists this if KVM ever supports SPE -- this really should + * Revisit this if KVM ever supports SPE -- this really should * look at the guest's view of PMSIDR_EL1. */ return (kvm_has_feat(kvm, FEAT_SPEv1p4) && (read_sysreg_s(SYS_PMSIDR_EL1) & PMSIDR_EL1_FDS)); } +static bool feat_spe_fne(struct kvm *kvm) +{ + /* + * Revisit this if KVM ever supports SPE -- this really should + * look at the guest's view of PMSIDR_EL1. + */ + return (kvm_has_feat(kvm, FEAT_SPEv1p2) && + (read_sysreg_s(SYS_PMSIDR_EL1) & PMSIDR_EL1_FnE)); +} + static bool feat_trbe_mpam(struct kvm *kvm) { /* - * Revists this if KVM ever supports both MPAM and TRBE -- + * Revisit this if KVM ever supports both MPAM and TRBE -- * this really should look at the guest's view of TRBIDR_EL1. */ return (kvm_has_feat(kvm, FEAT_TRBE) && @@ -537,7 +546,7 @@ static const struct reg_bits_to_feat_map hdfgrtr_feat_map[] = { HDFGRTR_EL2_PMBPTR_EL1 | HDFGRTR_EL2_PMBLIMITR_EL1, FEAT_SPE), - NEEDS_FEAT(HDFGRTR_EL2_nPMSNEVFR_EL1, FEAT_SPE_FnE), + NEEDS_FEAT(HDFGRTR_EL2_nPMSNEVFR_EL1, feat_spe_fne), NEEDS_FEAT(HDFGRTR_EL2_nBRBDATA | HDFGRTR_EL2_nBRBCTL | HDFGRTR_EL2_nBRBIDR, @@ -605,7 +614,7 @@ static const struct reg_bits_to_feat_map hdfgwtr_feat_map[] = { HDFGWTR_EL2_PMBPTR_EL1 | HDFGWTR_EL2_PMBLIMITR_EL1, FEAT_SPE), - NEEDS_FEAT(HDFGWTR_EL2_nPMSNEVFR_EL1, FEAT_SPE_FnE), + NEEDS_FEAT(HDFGWTR_EL2_nPMSNEVFR_EL1, feat_spe_fne), NEEDS_FEAT(HDFGWTR_EL2_nBRBDATA | HDFGWTR_EL2_nBRBCTL, FEAT_BRBE), diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index 73f2e0221e70..06db299c37a8 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -709,6 +709,14 @@ static const hcall_t host_hcall[] = { HANDLE_FUNC(__kvm_tlb_flush_vmid_range), HANDLE_FUNC(__kvm_flush_cpu_context), HANDLE_FUNC(__kvm_timer_set_cntvoff), + HANDLE_FUNC(__tracing_load), + HANDLE_FUNC(__tracing_unload), + HANDLE_FUNC(__tracing_enable), + HANDLE_FUNC(__tracing_swap_reader), + HANDLE_FUNC(__tracing_update_clock), + HANDLE_FUNC(__tracing_reset), + HANDLE_FUNC(__tracing_enable_event), + HANDLE_FUNC(__tracing_write_event), HANDLE_FUNC(__vgic_v3_save_aprs), HANDLE_FUNC(__vgic_v3_restore_vmcr_aprs), HANDLE_FUNC(__vgic_v5_save_apr), @@ -735,22 +743,16 @@ static const hcall_t host_hcall[] = { HANDLE_FUNC(__pkvm_vcpu_load), HANDLE_FUNC(__pkvm_vcpu_put), HANDLE_FUNC(__pkvm_tlb_flush_vmid), - HANDLE_FUNC(__tracing_load), - HANDLE_FUNC(__tracing_unload), - HANDLE_FUNC(__tracing_enable), - HANDLE_FUNC(__tracing_swap_reader), - HANDLE_FUNC(__tracing_update_clock), - HANDLE_FUNC(__tracing_reset), - HANDLE_FUNC(__tracing_enable_event), - HANDLE_FUNC(__tracing_write_event), }; static void handle_host_hcall(struct kvm_cpu_context *host_ctxt) { DECLARE_REG(unsigned long, id, host_ctxt, 0); - unsigned long hcall_min = 0, hcall_max = -1; + unsigned long hcall_min = 0, hcall_max = __KVM_HOST_SMCCC_FUNC_MAX; hcall_t hfn; + BUILD_BUG_ON(ARRAY_SIZE(host_hcall) != __KVM_HOST_SMCCC_FUNC_MAX); + /* * If pKVM has been initialised then reject any calls to the * early "privileged" hypercalls. Note that we cannot reject @@ -763,16 +765,14 @@ static void handle_host_hcall(struct kvm_cpu_context *host_ctxt) if (static_branch_unlikely(&kvm_protected_mode_initialized)) { hcall_min = __KVM_HOST_SMCCC_FUNC_MIN_PKVM; } else { - hcall_max = __KVM_HOST_SMCCC_FUNC_MAX_NO_PKVM; + hcall_max = __KVM_HOST_SMCCC_FUNC_PKVM_ONLY; } id &= ~ARM_SMCCC_CALL_HINTS; id -= KVM_HOST_SMCCC_ID(0); - if (unlikely(id < hcall_min || id > hcall_max || - id >= ARRAY_SIZE(host_hcall))) { + if (unlikely(id < hcall_min || id >= hcall_max)) goto inval; - } hfn = host_hcall[id]; if (unlikely(!hfn)) @@ -805,6 +805,10 @@ static void handle_host_smc(struct kvm_cpu_context *host_ctxt) } func_id &= ~ARM_SMCCC_CALL_HINTS; + if (upper_32_bits(func_id)) { + cpu_reg(host_ctxt, 0) = SMCCC_RET_NOT_SUPPORTED; + goto exit_skip_instr; + } handled = kvm_host_psci_handler(host_ctxt, func_id); if (!handled) diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c index 7ed96d64d611..e7496eb85628 100644 --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c @@ -266,7 +266,8 @@ struct pkvm_hyp_vcpu *pkvm_load_hyp_vcpu(pkvm_handle_t handle, if (hyp_vm->kvm.created_vcpus <= vcpu_idx) goto unlock; - hyp_vcpu = hyp_vm->vcpus[vcpu_idx]; + /* Pairs with smp_store_release() in register_hyp_vcpu(). */ + hyp_vcpu = smp_load_acquire(&hyp_vm->vcpus[vcpu_idx]); if (!hyp_vcpu) goto unlock; @@ -860,12 +861,30 @@ err_unpin_kvm: * the page-aligned size of 'struct pkvm_hyp_vcpu'. * Return 0 on success, negative error code on failure. */ +static int register_hyp_vcpu(struct pkvm_hyp_vm *hyp_vm, + struct pkvm_hyp_vcpu *hyp_vcpu) +{ + unsigned int idx = hyp_vcpu->vcpu.vcpu_idx; + + if (idx >= hyp_vm->kvm.created_vcpus) + return -EINVAL; + + if (hyp_vm->vcpus[idx]) + return -EINVAL; + + /* + * Ensure the hyp_vcpu is initialised before publishing it to + * the vCPU-load path via 'hyp_vm->vcpus[]'. + */ + smp_store_release(&hyp_vm->vcpus[idx], hyp_vcpu); + return 0; +} + int __pkvm_init_vcpu(pkvm_handle_t handle, struct kvm_vcpu *host_vcpu, unsigned long vcpu_hva) { struct pkvm_hyp_vcpu *hyp_vcpu; struct pkvm_hyp_vm *hyp_vm; - unsigned int idx; int ret; hyp_vcpu = map_donated_memory(vcpu_hva, sizeof(*hyp_vcpu)); @@ -884,18 +903,11 @@ int __pkvm_init_vcpu(pkvm_handle_t handle, struct kvm_vcpu *host_vcpu, if (ret) goto unlock; - idx = hyp_vcpu->vcpu.vcpu_idx; - if (idx >= hyp_vm->kvm.created_vcpus) { - ret = -EINVAL; - goto unlock; - } - - if (hyp_vm->vcpus[idx]) { - ret = -EINVAL; - goto unlock; + ret = register_hyp_vcpu(hyp_vm, hyp_vcpu); + if (ret) { + unpin_host_vcpu(host_vcpu); + unpin_host_sve_state(hyp_vcpu); } - - hyp_vm->vcpus[idx] = hyp_vcpu; unlock: hyp_spin_unlock(&vm_table_lock); diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c index d8e5b563fd3d..d461981616d9 100644 --- a/arch/arm64/kvm/hyp/nvhe/setup.c +++ b/arch/arm64/kvm/hyp/nvhe/setup.c @@ -312,15 +312,15 @@ void __noreturn __pkvm_init_finalise(void) }; pkvm_pgtable.mm_ops = &pkvm_pgtable_mm_ops; - ret = fix_host_ownership(); + ret = fix_hyp_pgtable_refcnt(); if (ret) goto out; - ret = fix_hyp_pgtable_refcnt(); + ret = hyp_create_fixmap(); if (ret) goto out; - ret = hyp_create_fixmap(); + ret = fix_host_ownership(); if (ret) goto out; diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v2.c b/arch/arm64/kvm/vgic/vgic-mmio-v2.c index 406845b3117c..0643e333db35 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v2.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v2.c @@ -91,7 +91,7 @@ static int vgic_mmio_uaccess_write_v2_misc(struct kvm_vcpu *vcpu, * migration from old kernels to new kernels with legacy * userspace. */ - reg = FIELD_GET(GICD_IIDR_REVISION_MASK, reg); + reg = FIELD_GET(GICD_IIDR_REVISION_MASK, val); switch (reg) { case KVM_VGIC_IMP_REV_2: case KVM_VGIC_IMP_REV_3: diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c index 89edb84d1ac6..5913a20d8301 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c @@ -194,7 +194,7 @@ static int vgic_mmio_uaccess_write_v3_misc(struct kvm_vcpu *vcpu, if ((reg ^ val) & ~GICD_IIDR_REVISION_MASK) return -EINVAL; - reg = FIELD_GET(GICD_IIDR_REVISION_MASK, reg); + reg = FIELD_GET(GICD_IIDR_REVISION_MASK, val); switch (reg) { case KVM_VGIC_IMP_REV_2: case KVM_VGIC_IMP_REV_3: diff --git a/arch/loongarch/Kbuild b/arch/loongarch/Kbuild index beb8499dd8ed..1c7a0dbe5e72 100644 --- a/arch/loongarch/Kbuild +++ b/arch/loongarch/Kbuild @@ -3,7 +3,7 @@ obj-y += mm/ obj-y += net/ obj-y += vdso/ -obj-$(CONFIG_KVM) += kvm/ +obj-$(subst m,y,$(CONFIG_KVM)) += kvm/ # for cleaning subdir- += boot diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index 3b042dbb2c41..606597da46b8 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -220,6 +220,7 @@ menu "Kernel type and options" choice prompt "Kernel type" + default 64BIT # Keep existing behavior config 32BIT bool "32-bit kernel" diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile index 47516aeea9d2..54fcfa1eac1f 100644 --- a/arch/loongarch/Makefile +++ b/arch/loongarch/Makefile @@ -55,9 +55,11 @@ endif ifdef CONFIG_32BIT tool-archpref = $(32bit-tool-archpref) UTS_MACHINE := loongarch32 +cflags-y += $(call cc-option,-m32) else tool-archpref = $(64bit-tool-archpref) UTS_MACHINE := loongarch64 +cflags-y += $(call cc-option,-m64) endif ifneq ($(SUBARCH),$(ARCH)) diff --git a/arch/loongarch/include/asm/asm-prototypes.h b/arch/loongarch/include/asm/asm-prototypes.h index 704066b4f736..de0c17f3f49c 100644 --- a/arch/loongarch/include/asm/asm-prototypes.h +++ b/arch/loongarch/include/asm/asm-prototypes.h @@ -20,3 +20,23 @@ asmlinkage void noinstr __no_stack_protector ret_from_kernel_thread(struct task_ struct pt_regs *regs, int (*fn)(void *), void *fn_arg); + +struct kvm_run; +struct kvm_vcpu; +struct loongarch_fpu; + +void kvm_exc_entry(void); +int kvm_enter_guest(struct kvm_run *run, struct kvm_vcpu *vcpu); + +void kvm_save_fpu(struct loongarch_fpu *fpu); +void kvm_restore_fpu(struct loongarch_fpu *fpu); + +#ifdef CONFIG_CPU_HAS_LSX +void kvm_save_lsx(struct loongarch_fpu *fpu); +void kvm_restore_lsx(struct loongarch_fpu *fpu); +#endif + +#ifdef CONFIG_CPU_HAS_LASX +void kvm_save_lasx(struct loongarch_fpu *fpu); +void kvm_restore_lasx(struct loongarch_fpu *fpu); +#endif diff --git a/arch/loongarch/include/asm/kvm_host.h b/arch/loongarch/include/asm/kvm_host.h index 130cedbb6b39..776bc487a705 100644 --- a/arch/loongarch/include/asm/kvm_host.h +++ b/arch/loongarch/include/asm/kvm_host.h @@ -87,7 +87,6 @@ struct kvm_context { struct kvm_world_switch { int (*exc_entry)(void); int (*enter_guest)(struct kvm_run *run, struct kvm_vcpu *vcpu); - unsigned long page_order; }; #define MAX_PGTABLE_LEVELS 4 @@ -359,8 +358,6 @@ void kvm_exc_entry(void); int kvm_enter_guest(struct kvm_run *run, struct kvm_vcpu *vcpu); extern unsigned long vpid_mask; -extern const unsigned long kvm_exception_size; -extern const unsigned long kvm_enter_guest_size; extern struct kvm_world_switch *kvm_loongarch_ops; #define SW_GCSR (1 << 0) diff --git a/arch/loongarch/include/asm/linkage.h b/arch/loongarch/include/asm/linkage.h index a1bd6a3ee03a..ae937d1708b2 100644 --- a/arch/loongarch/include/asm/linkage.h +++ b/arch/loongarch/include/asm/linkage.h @@ -69,7 +69,7 @@ 9, 10, 11, 12, 13, 14, 15, 16, \ 17, 18, 19, 20, 21, 22, 23, 24, \ 25, 26, 27, 28, 29, 30, 31; \ - .cfi_offset \num, SC_REGS + \num * SZREG; \ + .cfi_offset \num, SC_REGS + \num * 8; \ .endr; \ \ nop; \ diff --git a/arch/loongarch/include/asm/vdso/gettimeofday.h b/arch/loongarch/include/asm/vdso/gettimeofday.h index bae76767c693..18ba403e1ed9 100644 --- a/arch/loongarch/include/asm/vdso/gettimeofday.h +++ b/arch/loongarch/include/asm/vdso/gettimeofday.h @@ -85,12 +85,6 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode, return count; } -static inline bool loongarch_vdso_hres_capable(void) -{ - return true; -} -#define __arch_vdso_hres_capable loongarch_vdso_hres_capable - #endif /* CONFIG_GENERIC_GETTIMEOFDAY */ #endif /* !__ASSEMBLER__ */ diff --git a/arch/loongarch/kvm/Makefile b/arch/loongarch/kvm/Makefile index ae469edec99c..a4d044da3aa7 100644 --- a/arch/loongarch/kvm/Makefile +++ b/arch/loongarch/kvm/Makefile @@ -7,11 +7,12 @@ include $(srctree)/virt/kvm/Makefile.kvm obj-$(CONFIG_KVM) += kvm.o +obj-y += switch.o + kvm-y += exit.o kvm-y += interrupt.o kvm-y += main.o kvm-y += mmu.o -kvm-y += switch.o kvm-y += timer.o kvm-y += tlb.o kvm-y += vcpu.o diff --git a/arch/loongarch/kvm/exit.c b/arch/loongarch/kvm/exit.c index da0ad89f2eb7..3b95cd0f989b 100644 --- a/arch/loongarch/kvm/exit.c +++ b/arch/loongarch/kvm/exit.c @@ -390,6 +390,7 @@ int kvm_emu_mmio_read(struct kvm_vcpu *vcpu, larch_inst inst) run->mmio.len = 8; break; default: + ret = EMULATE_FAIL; break; } break; diff --git a/arch/loongarch/kvm/interrupt.c b/arch/loongarch/kvm/interrupt.c index 32930959f7c2..a18c60dffbba 100644 --- a/arch/loongarch/kvm/interrupt.c +++ b/arch/loongarch/kvm/interrupt.c @@ -28,23 +28,29 @@ static unsigned int priority_to_irq[EXCCODE_INT_NUM] = { static int kvm_irq_deliver(struct kvm_vcpu *vcpu, unsigned int priority) { unsigned int irq = 0; + unsigned long old, new; clear_bit(priority, &vcpu->arch.irq_pending); if (priority < EXCCODE_INT_NUM) irq = priority_to_irq[priority]; - if (kvm_guest_has_msgint(&vcpu->arch) && (priority == INT_AVEC)) { - dmsintc_inject_irq(vcpu); - set_gcsr_estat(irq); - return 1; - } - switch (priority) { + case INT_AVEC: + if (!kvm_guest_has_msgint(&vcpu->arch)) + break; + dmsintc_inject_irq(vcpu); + fallthrough; case INT_TI: case INT_IPI: case INT_SWI0: case INT_SWI1: + old = kvm_read_hw_gcsr(LOONGARCH_CSR_TVAL); set_gcsr_estat(irq); + new = kvm_read_hw_gcsr(LOONGARCH_CSR_TVAL); + + /* Inject TI if TVAL inverted */ + if (new > old) + set_gcsr_estat(CPU_TIMER); break; case INT_HWI0 ... INT_HWI7: @@ -61,22 +67,28 @@ static int kvm_irq_deliver(struct kvm_vcpu *vcpu, unsigned int priority) static int kvm_irq_clear(struct kvm_vcpu *vcpu, unsigned int priority) { unsigned int irq = 0; + unsigned long old, new; clear_bit(priority, &vcpu->arch.irq_clear); if (priority < EXCCODE_INT_NUM) irq = priority_to_irq[priority]; - if (kvm_guest_has_msgint(&vcpu->arch) && (priority == INT_AVEC)) { - clear_gcsr_estat(irq); - return 1; - } - switch (priority) { + case INT_AVEC: + if (!kvm_guest_has_msgint(&vcpu->arch)) + break; + fallthrough; case INT_TI: case INT_IPI: case INT_SWI0: case INT_SWI1: + old = kvm_read_hw_gcsr(LOONGARCH_CSR_TVAL); clear_gcsr_estat(irq); + new = kvm_read_hw_gcsr(LOONGARCH_CSR_TVAL); + + /* Inject TI if TVAL inverted */ + if (new > old) + set_gcsr_estat(CPU_TIMER); break; case INT_HWI0 ... INT_HWI7: diff --git a/arch/loongarch/kvm/main.c b/arch/loongarch/kvm/main.c index 76ebff2faedd..f105a86143f5 100644 --- a/arch/loongarch/kvm/main.c +++ b/arch/loongarch/kvm/main.c @@ -348,8 +348,7 @@ void kvm_arch_disable_virtualization_cpu(void) static int kvm_loongarch_env_init(void) { - int cpu, order, ret; - void *addr; + int cpu, ret; struct kvm_context *context; vmcs = alloc_percpu(struct kvm_context); @@ -365,30 +364,8 @@ static int kvm_loongarch_env_init(void) return -ENOMEM; } - /* - * PGD register is shared between root kernel and kvm hypervisor. - * So world switch entry should be in DMW area rather than TLB area - * to avoid page fault reenter. - * - * In future if hardware pagetable walking is supported, we won't - * need to copy world switch code to DMW area. - */ - order = get_order(kvm_exception_size + kvm_enter_guest_size); - addr = (void *)__get_free_pages(GFP_KERNEL, order); - if (!addr) { - free_percpu(vmcs); - vmcs = NULL; - kfree(kvm_loongarch_ops); - kvm_loongarch_ops = NULL; - return -ENOMEM; - } - - memcpy(addr, kvm_exc_entry, kvm_exception_size); - memcpy(addr + kvm_exception_size, kvm_enter_guest, kvm_enter_guest_size); - flush_icache_range((unsigned long)addr, (unsigned long)addr + kvm_exception_size + kvm_enter_guest_size); - kvm_loongarch_ops->exc_entry = addr; - kvm_loongarch_ops->enter_guest = addr + kvm_exception_size; - kvm_loongarch_ops->page_order = order; + kvm_loongarch_ops->exc_entry = (void *)kvm_exc_entry; + kvm_loongarch_ops->enter_guest = (void *)kvm_enter_guest; vpid_mask = read_csr_gstat(); vpid_mask = (vpid_mask & CSR_GSTAT_GIDBIT) >> CSR_GSTAT_GIDBIT_SHIFT; @@ -428,16 +405,10 @@ static int kvm_loongarch_env_init(void) static void kvm_loongarch_env_exit(void) { - unsigned long addr; - if (vmcs) free_percpu(vmcs); if (kvm_loongarch_ops) { - if (kvm_loongarch_ops->exc_entry) { - addr = (unsigned long)kvm_loongarch_ops->exc_entry; - free_pages(addr, kvm_loongarch_ops->page_order); - } kfree(kvm_loongarch_ops); } diff --git a/arch/loongarch/kvm/mmu.c b/arch/loongarch/kvm/mmu.c index a7fa458e3360..e104897aa532 100644 --- a/arch/loongarch/kvm/mmu.c +++ b/arch/loongarch/kvm/mmu.c @@ -95,7 +95,7 @@ static int kvm_flush_pte(kvm_pte_t *pte, phys_addr_t addr, kvm_ptw_ctx *ctx) else kvm->stat.pages--; - *pte = ctx->invalid_entry; + kvm_set_pte(pte, ctx->invalid_entry); return 1; } diff --git a/arch/loongarch/kvm/switch.S b/arch/loongarch/kvm/switch.S index f1768b7a6194..936e4ae3e408 100644 --- a/arch/loongarch/kvm/switch.S +++ b/arch/loongarch/kvm/switch.S @@ -4,9 +4,11 @@ */ #include <linux/linkage.h> +#include <linux/kvm_types.h> #include <asm/asm.h> #include <asm/asmmacro.h> #include <asm/loongarch.h> +#include <asm/page.h> #include <asm/regdef.h> #include <asm/unwind_hints.h> @@ -100,11 +102,16 @@ * - is still in guest mode, such as pgd table/vmid registers etc, * - will fix with hw page walk enabled in future * load kvm_vcpu from reserved CSR KVM_VCPU_KS, and save a2 to KVM_TEMP_KS + * + * PGD register is shared between root kernel and kvm hypervisor. + * So world switch entry should be in DMW area rather than TLB area + * to avoid page fault re-enter. */ .text + .p2align PAGE_SHIFT .cfi_sections .debug_frame SYM_CODE_START(kvm_exc_entry) - UNWIND_HINT_UNDEFINED + UNWIND_HINT_END_OF_STACK csrwr a2, KVM_TEMP_KS csrrd a2, KVM_VCPU_KS addi.d a2, a2, KVM_VCPU_ARCH @@ -190,8 +197,8 @@ ret_to_host: kvm_restore_host_gpr a2 jr ra -SYM_INNER_LABEL(kvm_exc_entry_end, SYM_L_LOCAL) SYM_CODE_END(kvm_exc_entry) +EXPORT_SYMBOL_FOR_KVM(kvm_exc_entry) /* * int kvm_enter_guest(struct kvm_run *run, struct kvm_vcpu *vcpu) @@ -215,8 +222,8 @@ SYM_FUNC_START(kvm_enter_guest) /* Save kvm_vcpu to kscratch */ csrwr a1, KVM_VCPU_KS kvm_switch_to_guest -SYM_INNER_LABEL(kvm_enter_guest_end, SYM_L_LOCAL) SYM_FUNC_END(kvm_enter_guest) +EXPORT_SYMBOL_FOR_KVM(kvm_enter_guest) SYM_FUNC_START(kvm_save_fpu) fpu_save_csr a0 t1 @@ -224,6 +231,7 @@ SYM_FUNC_START(kvm_save_fpu) fpu_save_cc a0 t1 t2 jr ra SYM_FUNC_END(kvm_save_fpu) +EXPORT_SYMBOL_FOR_KVM(kvm_save_fpu) SYM_FUNC_START(kvm_restore_fpu) fpu_restore_double a0 t1 @@ -231,6 +239,7 @@ SYM_FUNC_START(kvm_restore_fpu) fpu_restore_cc a0 t1 t2 jr ra SYM_FUNC_END(kvm_restore_fpu) +EXPORT_SYMBOL_FOR_KVM(kvm_restore_fpu) #ifdef CONFIG_CPU_HAS_LSX SYM_FUNC_START(kvm_save_lsx) @@ -239,6 +248,7 @@ SYM_FUNC_START(kvm_save_lsx) lsx_save_data a0 t1 jr ra SYM_FUNC_END(kvm_save_lsx) +EXPORT_SYMBOL_FOR_KVM(kvm_save_lsx) SYM_FUNC_START(kvm_restore_lsx) lsx_restore_data a0 t1 @@ -246,6 +256,7 @@ SYM_FUNC_START(kvm_restore_lsx) fpu_restore_csr a0 t1 t2 jr ra SYM_FUNC_END(kvm_restore_lsx) +EXPORT_SYMBOL_FOR_KVM(kvm_restore_lsx) #endif #ifdef CONFIG_CPU_HAS_LASX @@ -255,6 +266,7 @@ SYM_FUNC_START(kvm_save_lasx) lasx_save_data a0 t1 jr ra SYM_FUNC_END(kvm_save_lasx) +EXPORT_SYMBOL_FOR_KVM(kvm_save_lasx) SYM_FUNC_START(kvm_restore_lasx) lasx_restore_data a0 t1 @@ -262,10 +274,8 @@ SYM_FUNC_START(kvm_restore_lasx) fpu_restore_csr a0 t1 t2 jr ra SYM_FUNC_END(kvm_restore_lasx) +EXPORT_SYMBOL_FOR_KVM(kvm_restore_lasx) #endif - .section ".rodata" -SYM_DATA(kvm_exception_size, .quad kvm_exc_entry_end - kvm_exc_entry) -SYM_DATA(kvm_enter_guest_size, .quad kvm_enter_guest_end - kvm_enter_guest) #ifdef CONFIG_CPU_HAS_LBT STACK_FRAME_NON_STANDARD kvm_restore_fpu diff --git a/arch/loongarch/kvm/timer.c b/arch/loongarch/kvm/timer.c index 29c2aaba63c3..8356fce0043f 100644 --- a/arch/loongarch/kvm/timer.c +++ b/arch/loongarch/kvm/timer.c @@ -96,15 +96,21 @@ void kvm_restore_timer(struct kvm_vcpu *vcpu) * and set CSR TVAL with -1 */ write_gcsr_timertick(0); - __delay(2); /* Wait cycles until timer interrupt injected */ /* * Writing CSR_TINTCLR_TI to LOONGARCH_CSR_TINTCLR will clear * timer interrupt, and CSR TVAL keeps unchanged with -1, it * avoids spurious timer interrupt */ - if (!(estat & CPU_TIMER)) + if (!(estat & CPU_TIMER)) { + __delay(2); /* Wait cycles until timer interrupt injected */ + + /* Write TVAL with max value if no TI shot */ + estat = kvm_read_hw_gcsr(LOONGARCH_CSR_ESTAT); + if (!(estat & CPU_TIMER)) + write_gcsr_timertick(CSR_TCFG_VAL); gcsr_write(CSR_TINTCLR_TI, LOONGARCH_CSR_TINTCLR); + } return; } diff --git a/arch/loongarch/kvm/vm.c b/arch/loongarch/kvm/vm.c index 8cc5ee1c53ef..1317c718f896 100644 --- a/arch/loongarch/kvm/vm.c +++ b/arch/loongarch/kvm/vm.c @@ -125,7 +125,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = 1; break; case KVM_CAP_NR_VCPUS: - r = num_online_cpus(); + r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS); break; case KVM_CAP_MAX_VCPUS: r = KVM_MAX_VCPUS; diff --git a/arch/loongarch/pci/acpi.c b/arch/loongarch/pci/acpi.c index 0dde3ddcd544..b02698a338ee 100644 --- a/arch/loongarch/pci/acpi.c +++ b/arch/loongarch/pci/acpi.c @@ -61,11 +61,16 @@ static void acpi_release_root_info(struct acpi_pci_root_info *ci) static int acpi_prepare_root_resources(struct acpi_pci_root_info *ci) { int status; + unsigned long long pci_h = 0; struct resource_entry *entry, *tmp; struct acpi_device *device = ci->bridge; status = acpi_pci_probe_root_resources(ci); if (status > 0) { + acpi_evaluate_integer(device->handle, "PCIH", NULL, &pci_h); + if (pci_h) + return status; + resource_list_for_each_entry_safe(entry, tmp, &ci->resources) { if (entry->res->flags & IORESOURCE_MEM) { entry->offset = ci->root->mcfg_addr & GENMASK_ULL(63, 40); diff --git a/arch/loongarch/pci/pci.c b/arch/loongarch/pci/pci.c index d233ea2218fe..f33c7ea1443d 100644 --- a/arch/loongarch/pci/pci.c +++ b/arch/loongarch/pci/pci.c @@ -132,6 +132,9 @@ static void loongson_gpu_fixup_dma_hang(struct pci_dev *pdev, bool on) crtc_reg = regbase; crtc_offset = 0x400; break; + default: + iounmap(regbase); + return; } for (i = 0; i < CRTC_NUM_MAX; i++, crtc_reg += crtc_offset) { diff --git a/arch/loongarch/vdso/Makefile b/arch/loongarch/vdso/Makefile index 42aa96249828..9c9181bb4071 100644 --- a/arch/loongarch/vdso/Makefile +++ b/arch/loongarch/vdso/Makefile @@ -12,6 +12,8 @@ obj-vdso-$(CONFIG_GENERIC_GETTIMEOFDAY) += vgettimeofday.o ccflags-vdso := \ $(filter -I%,$(KBUILD_CFLAGS)) \ $(filter -E%,$(KBUILD_CFLAGS)) \ + $(filter -m32,$(KBUILD_CFLAGS)) \ + $(filter -m64,$(KBUILD_CFLAGS)) \ $(filter -march=%,$(KBUILD_CFLAGS)) \ $(filter -m%-float,$(KBUILD_CFLAGS)) \ $(CLANG_FLAGS) \ diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile index edab2a948352..4391783521bd 100644 --- a/arch/parisc/Makefile +++ b/arch/parisc/Makefile @@ -174,15 +174,21 @@ ifeq ($(KBUILD_EXTMOD),) # this hack. prepare: vdso_prepare vdso_prepare: prepare0 - $(if $(CONFIG_64BIT),$(Q)$(MAKE) \ - $(build)=arch/parisc/kernel/vdso64 include/generated/vdso64-offsets.h) - $(if $(CONFIG_PA11)$(CONFIG_COMPAT),$(Q)$(MAKE) \ +ifdef CONFIG_64BIT + $(Q)$(MAKE) $(build)=arch/parisc/kernel/vdso64 include/generated/vdso64-offsets.h + $(if $(CONFIG_COMPAT),$(Q)$(MAKE) \ $(build)=arch/parisc/kernel/vdso32 include/generated/vdso32-offsets.h) +else + $(Q)$(MAKE) $(build)=arch/parisc/kernel/vdso32 include/generated/vdso32-offsets.h +endif endif -vdso-install-$(CONFIG_PA11) += arch/parisc/kernel/vdso32/vdso32.so +ifdef CONFIG_64BIT +vdso-install-y += arch/parisc/kernel/vdso64/vdso64.so vdso-install-$(CONFIG_COMPAT) += arch/parisc/kernel/vdso32/vdso32.so -vdso-install-$(CONFIG_64BIT) += arch/parisc/kernel/vdso64/vdso64.so +else +vdso-install-y += arch/parisc/kernel/vdso32/vdso32.so +endif install: KBUILD_IMAGE := vmlinux zinstall: KBUILD_IMAGE := vmlinuz diff --git a/arch/parisc/include/asm/vdso.h b/arch/parisc/include/asm/vdso.h index 5501560f5ffe..e5cca3c9c8e7 100644 --- a/arch/parisc/include/asm/vdso.h +++ b/arch/parisc/include/asm/vdso.h @@ -6,13 +6,14 @@ #ifdef CONFIG_64BIT #include <generated/vdso64-offsets.h> +#define VDSO64_SYMBOL(tsk, name) ((tsk)->mm->context.vdso_base + (vdso64_offset_##name)) #endif #if !defined(CONFIG_64BIT) || defined(CONFIG_COMPAT) #include <generated/vdso32-offsets.h> -#endif - -#define VDSO64_SYMBOL(tsk, name) ((tsk)->mm->context.vdso_base + (vdso64_offset_##name)) #define VDSO32_SYMBOL(tsk, name) ((tsk)->mm->context.vdso_base + (vdso32_offset_##name)) +#else +#define VDSO32_SYMBOL(tsk, name) 0UL +#endif #endif /* __ASSEMBLER__ */ diff --git a/arch/parisc/kernel/Makefile b/arch/parisc/kernel/Makefile index 2f3441769ac5..49f937c2abbe 100644 --- a/arch/parisc/kernel/Makefile +++ b/arch/parisc/kernel/Makefile @@ -46,6 +46,9 @@ obj-$(CONFIG_KEXEC_FILE) += kexec_file.o # vdso obj-y += vdso.o -obj-$(CONFIG_64BIT) += vdso64/ -obj-$(CONFIG_PA11) += vdso32/ +ifdef CONFIG_64BIT +obj-y += vdso64/ obj-$(CONFIG_COMPAT) += vdso32/ +else +obj-y += vdso32/ +endif diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c index bc47bbe3026e..b52ad704ec8a 100644 --- a/arch/parisc/kernel/drivers.c +++ b/arch/parisc/kernel/drivers.c @@ -41,9 +41,7 @@ const struct dma_map_ops *hppa_dma_ops __ro_after_init; EXPORT_SYMBOL(hppa_dma_ops); -static struct device root = { - .init_name = "parisc", -}; +static struct device *root; static inline int check_dev(struct device *dev) { @@ -89,7 +87,7 @@ static int for_each_padev(int (*fn)(struct device *, void *), void * data) .obj = data, .fn = fn, }; - return device_for_each_child(&root, &recurse_data, descend_children); + return device_for_each_child(root, &recurse_data, descend_children); } /** @@ -290,7 +288,7 @@ const struct parisc_device * find_pa_parent_type(const struct parisc_device *padev, int type) { const struct device *dev = &padev->dev; - while (dev != &root) { + while (dev != root) { struct parisc_device *candidate = to_parisc_device(dev); if (candidate->id.hw_type == type) return candidate; @@ -319,7 +317,7 @@ static void get_node_path(struct device *dev, struct hardware_path *path) dev = dev->parent; } - while (dev != &root) { + while (dev != root) { if (dev_is_pci(dev)) { unsigned int devfn = to_pci_dev(dev)->devfn; path->bc[i--] = PCI_SLOT(devfn) | (PCI_FUNC(devfn)<< 5); @@ -482,7 +480,7 @@ static struct parisc_device * __init alloc_tree_node( static struct parisc_device *create_parisc_device(struct hardware_path *modpath) { int i; - struct device *parent = &root; + struct device *parent = root; for (i = 0; i < 6; i++) { if (modpath->bc[i] == -1) continue; @@ -755,7 +753,7 @@ parse_tree_node(struct device *parent, int index, struct hardware_path *modpath) struct device *hwpath_to_device(struct hardware_path *modpath) { int i; - struct device *parent = &root; + struct device *parent = root; for (i = 0; i < 6; i++) { if (modpath->bc[i] == -1) continue; @@ -880,7 +878,7 @@ void __init walk_central_bus(void) { walk_native_bus(CENTRAL_BUS_ADDR, CENTRAL_BUS_ADDR + (MAX_NATIVE_DEVICES * NATIVE_DEVICE_OFFSET), - &root); + root); } static __init void print_parisc_device(struct parisc_device *dev) @@ -907,9 +905,10 @@ void __init init_parisc_bus(void) { if (bus_register(&parisc_bus_type)) panic("Could not register PA-RISC bus type\n"); - if (device_register(&root)) + + root = root_device_register("parisc"); + if (IS_ERR(root)) panic("Could not register PA-RISC root device\n"); - get_device(&root); } static __init void qemu_header(void) diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index 31430e9bcfdd..7650f2adb5cf 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -1414,6 +1414,9 @@ static inline char *debug_get_user_string(const char __user *user_buf, { char *buffer; + if (!user_len) + return ERR_PTR(-EINVAL); + buffer = memdup_user_nul(user_buf, user_len); if (IS_ERR(buffer)) return buffer; @@ -1584,6 +1587,11 @@ static int debug_input_flush_fn(debug_info_t *id, struct debug_view *view, char input_buf[1]; int rc = user_len; + if (!user_len) { + rc = -EINVAL; + goto out; + } + if (user_len > 0x10000) user_len = 0x10000; if (*offset != 0) { diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 191cc53caead..028aeb9c48d6 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -438,7 +438,7 @@ void do_secure_storage_access(struct pt_regs *regs) panic("Unexpected PGM 0x3d with TEID bit 61=0"); } if (is_kernel_fault(regs)) { - folio = phys_to_folio(addr); + folio = virt_to_folio((void *)addr); if (unlikely(!folio_try_get(folio))) return; rc = uv_convert_from_secure(folio_to_phys(folio)); diff --git a/arch/sh/include/asm/setup.h b/arch/sh/include/asm/setup.h index 63c9efc06348..8488f76b48b4 100644 --- a/arch/sh/include/asm/setup.h +++ b/arch/sh/include/asm/setup.h @@ -7,7 +7,7 @@ /* * This is set up by the setup-routine at boot-time */ -extern unsigned char *boot_params_page; +extern unsigned char boot_params_page[]; #define PARAM boot_params_page #define MOUNT_ROOT_RDONLY (*(unsigned long *) (PARAM+0x000)) diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index dc8fe1361c18..be58b7f5c806 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -137,7 +137,8 @@ extern void __init efi_dump_pagetable(void); extern void __init efi_apply_memmap_quirks(void); extern int __init efi_reuse_config(u64 tables, int nr_tables); extern void efi_delete_dummy_variable(void); -extern void efi_crash_gracefully_on_page_fault(unsigned long phys_addr); +extern void efi_crash_gracefully_on_page_fault(unsigned long phys_addr, + const struct pt_regs *regs); extern void efi_unmap_boot_services(void); void arch_efi_call_virt_setup(void); diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 9b140bbdc1d8..4438ecac9a89 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -2040,7 +2040,7 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) * flush). Translate the address here so the memory can be uniformly * read with kvm_read_guest(). */ - if (!hc->fast && is_guest_mode(vcpu)) { + if (!hc->fast && mmu_is_nested(vcpu)) { hc->ingpa = translate_nested_gpa(vcpu, hc->ingpa, 0, NULL); if (unlikely(hc->ingpa == INVALID_GPA)) return HV_STATUS_INVALID_HYPERCALL_INPUT; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index e3ec4d8607c1..4078e624ca66 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -667,13 +667,15 @@ bool __kvm_apic_update_irr(unsigned long *pir, void *regs, int *max_irr) u32 *__pir = (void *)pir_vals; u32 i, vec; u32 irr_val, prev_irr_val; - int max_updated_irr; + int max_new_irr; - max_updated_irr = -1; - *max_irr = -1; - - if (!pi_harvest_pir(pir, pir_vals)) + if (!pi_harvest_pir(pir, pir_vals)) { + *max_irr = apic_find_highest_vector(regs + APIC_IRR); return false; + } + + max_new_irr = -1; + *max_irr = -1; for (i = vec = 0; i <= 7; i++, vec += 32) { u32 *p_irr = (u32 *)(regs + APIC_IRR + i * 0x10); @@ -688,25 +690,25 @@ bool __kvm_apic_update_irr(unsigned long *pir, void *regs, int *max_irr) !try_cmpxchg(p_irr, &prev_irr_val, irr_val)); if (prev_irr_val != irr_val) - max_updated_irr = __fls(irr_val ^ prev_irr_val) + vec; + max_new_irr = __fls(irr_val ^ prev_irr_val) + vec; } if (irr_val) *max_irr = __fls(irr_val) + vec; } - return ((max_updated_irr != -1) && - (max_updated_irr == *max_irr)); + return max_new_irr != -1 && max_new_irr == *max_irr; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(__kvm_apic_update_irr); bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, unsigned long *pir, int *max_irr) { struct kvm_lapic *apic = vcpu->arch.apic; - bool irr_updated = __kvm_apic_update_irr(pir, apic->regs, max_irr); + bool max_irr_is_from_pir; - if (unlikely(!apic->apicv_active && irr_updated)) + max_irr_is_from_pir = __kvm_apic_update_irr(pir, apic->regs, max_irr); + if (unlikely(!apic->apicv_active && max_irr_is_from_pir)) apic->irr_pending = true; - return irr_updated; + return max_irr_is_from_pir; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_apic_update_irr); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 24fbc9ea502a..892246204435 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -182,6 +182,8 @@ static struct kmem_cache *pte_list_desc_cache; struct kmem_cache *mmu_page_header_cache; static void mmu_spte_set(u64 *sptep, u64 spte); +static int mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp, + u64 *spte, struct list_head *invalid_list); struct kvm_mmu_role_regs { const unsigned long cr0; @@ -1287,19 +1289,6 @@ static void drop_spte(struct kvm *kvm, u64 *sptep) rmap_remove(kvm, sptep); } -static void drop_large_spte(struct kvm *kvm, u64 *sptep, bool flush) -{ - struct kvm_mmu_page *sp; - - sp = sptep_to_sp(sptep); - WARN_ON_ONCE(sp->role.level == PG_LEVEL_4K); - - drop_spte(kvm, sptep); - - if (flush) - kvm_flush_remote_tlbs_sptep(kvm, sptep); -} - /* * Write-protect on the specified @sptep, @pt_protect indicates whether * spte write-protection is caused by protecting shadow page table. @@ -2466,7 +2455,8 @@ static struct kvm_mmu_page *kvm_mmu_get_child_sp(struct kvm_vcpu *vcpu, { union kvm_mmu_page_role role; - if (is_shadow_present_pte(*sptep) && !is_large_pte(*sptep)) + if (is_shadow_present_pte(*sptep) && !is_large_pte(*sptep) && + spte_to_child_sp(*sptep) && spte_to_child_sp(*sptep)->gfn == gfn) return ERR_PTR(-EEXIST); role = kvm_mmu_child_role(sptep, direct, access); @@ -2544,13 +2534,16 @@ static void __link_shadow_page(struct kvm *kvm, BUILD_BUG_ON(VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK); - /* - * If an SPTE is present already, it must be a leaf and therefore - * a large one. Drop it, and flush the TLB if needed, before - * installing sp. - */ - if (is_shadow_present_pte(*sptep)) - drop_large_spte(kvm, sptep, flush); + if (is_shadow_present_pte(*sptep)) { + struct kvm_mmu_page *parent_sp; + LIST_HEAD(invalid_list); + + parent_sp = sptep_to_sp(sptep); + WARN_ON_ONCE(parent_sp->role.level == PG_LEVEL_4K); + + mmu_page_zap_pte(kvm, parent_sp, sptep, &invalid_list); + kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, true); + } spte = make_nonleaf_spte(sp->spt, sp_ad_disabled(sp)); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index a29896a9ef14..5c2c33a5f7dc 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -7029,8 +7029,8 @@ static void vmx_set_rvi(int vector) int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) { struct vcpu_vt *vt = to_vt(vcpu); + bool max_irr_is_from_pir; int max_irr; - bool got_posted_interrupt; if (KVM_BUG_ON(!enable_apicv, vcpu->kvm)) return -EIO; @@ -7042,17 +7042,22 @@ int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) * But on x86 this is just a compiler barrier anyway. */ smp_mb__after_atomic(); - got_posted_interrupt = - kvm_apic_update_irr(vcpu, vt->pi_desc.pir, &max_irr); + max_irr_is_from_pir = kvm_apic_update_irr(vcpu, vt->pi_desc.pir, + &max_irr); } else { max_irr = kvm_lapic_find_highest_irr(vcpu); - got_posted_interrupt = false; + max_irr_is_from_pir = false; } /* - * Newly recognized interrupts are injected via either virtual interrupt - * delivery (RVI) or KVM_REQ_EVENT. Virtual interrupt delivery is - * disabled in two cases: + * If APICv is enabled and L2 is not active, then update the Requesting + * Virtual Interrupt (RVI) portion of vmcs01.GUEST_INTR_STATUS with the + * highest priority IRR to deliver the IRQ via Virtual Interrupt + * Delivery. Note, this is required even if the highest priority IRQ + * was already pending in the IRR, as RVI isn't updated in lockstep with + * the IRR (unlike apic->irr_pending). + * + * For the cases where Virtual Interrupt Delivery can't be used: * * 1) If L2 is running and the vCPU has a new pending interrupt. If L1 * wants to exit on interrupts, KVM_REQ_EVENT is needed to synthesize a @@ -7063,10 +7068,29 @@ int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) * 2) If APICv is disabled for this vCPU, assigned devices may still * attempt to post interrupts. The posted interrupt vector will cause * a VM-Exit and the subsequent entry will call sync_pir_to_irr. + * + * In both cases, set KVM_REQ_EVENT if and only if the highest priority + * pending IRQ came from the PIR, as setting KVM_REQ_EVENT if any IRQ + * is pending may put the vCPU into an infinite loop, e.g. if the IRQ + * is blocked, then it will stay pending until an IRQ window is opened. + * + * Note! It's possible that one or more IRQs were moved from the PIR + * to the IRR _without_ max_irr_is_from_pir being true! I.e. if there + * was a higher priority IRQ already pending in the IRR. Not setting + * KVM_REQ_EVENT in this case is intentional and safe. If APICv is + * inactive, or L2 is running with exit-on-interrupt off (in vmcs12), + * i.e. without nested virtual interrupt delivery, then there's no need + * to request an IRQ window as the lower priority IRQ only needs to be + * delivered when the higher priority IRQ is dismissed from the ISR, + * i.e. on the next EOI, and EOIs are always intercepted if APICv is + * disabled or if L2 is running without nested VID. If L2 is running + * exit-on-interrupt on (in vmcs12), then the higher priority IRQ will + * trigger a nested VM-Exit, at which point KVM will re-evaluate L1's + * pending IRQs. */ if (!is_guest_mode(vcpu) && kvm_vcpu_apicv_active(vcpu)) vmx_set_rvi(max_irr); - else if (got_posted_interrupt) + else if (max_irr_is_from_pir) kvm_make_request(KVM_REQ_EVENT, vcpu); return max_irr; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index f0e77e084482..63de8e8684f2 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -686,7 +686,7 @@ page_fault_oops(struct pt_regs *regs, unsigned long error_code, * avoid hanging the system. */ if (IS_ENABLED(CONFIG_EFI)) - efi_crash_gracefully_on_page_fault(address); + efi_crash_gracefully_on_page_fault(address, regs); /* Only not-present faults should be handled by KFENCE. */ if (!(error_code & X86_PF_PROT) && diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index df24ffc6105d..90a065fcb1fa 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -761,7 +761,8 @@ int efi_capsule_setup_info(struct capsule_info *cap_info, void *kbuff, * @return: Returns, if the page fault is not handled. This function * will never return if the page fault is handled successfully. */ -void efi_crash_gracefully_on_page_fault(unsigned long phys_addr) +void efi_crash_gracefully_on_page_fault(unsigned long phys_addr, + const struct pt_regs *regs) { if (!IS_ENABLED(CONFIG_X86_64)) return; @@ -770,7 +771,7 @@ void efi_crash_gracefully_on_page_fault(unsigned long phys_addr) * If we get an interrupt/NMI while processing an EFI runtime service * then this is a regular OOPS, not an EFI failure. */ - if (in_interrupt()) + if (!in_task()) return; /* @@ -811,6 +812,14 @@ void efi_crash_gracefully_on_page_fault(unsigned long phys_addr) } /* + * The API does not permit entering a kernel mode FPU section with + * interrupts enabled and leaving it with interrupts disabled. So + * re-enable interrupts now if they were enabled when the page fault + * occurred. + */ + local_irq_restore(regs->flags); + + /* * Before calling EFI Runtime Service, the kernel has switched the * calling process to efi_mm. Hence, switch back to task_mm. */ diff --git a/crypto/authencesn.c b/crypto/authencesn.c index af3d584e584f..522df41365d8 100644 --- a/crypto/authencesn.c +++ b/crypto/authencesn.c @@ -390,6 +390,11 @@ static int crypto_authenc_esn_create(struct crypto_template *tmpl, auth = crypto_spawn_ahash_alg(&ctx->auth); auth_base = &auth->base; + if (auth->digestsize > 0 && auth->digestsize < 4) { + err = -EINVAL; + goto err_free_inst; + } + err = crypto_grab_skcipher(&ctx->enc, aead_crypto_instance(inst), crypto_attr_alg_name(tb[2]), 0, mask); if (err) diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c index 2801378e3e19..3b7b008bccfe 100644 --- a/drivers/accel/ivpu/ivpu_drv.c +++ b/drivers/accel/ivpu/ivpu_drv.c @@ -537,6 +537,26 @@ static const struct file_operations ivpu_fops = { #endif }; +static int ivpu_gem_prime_handle_to_fd(struct drm_device *dev, struct drm_file *file_priv, + u32 handle, u32 flags, int *prime_fd) +{ + struct drm_gem_object *obj; + + obj = drm_gem_object_lookup(file_priv, handle); + if (!obj) + return -ENOENT; + + if (drm_gem_is_imported(obj)) { + /* Do not allow re-exporting */ + drm_gem_object_put(obj); + return -EOPNOTSUPP; + } + + drm_gem_object_put(obj); + + return drm_gem_prime_handle_to_fd(dev, file_priv, handle, flags, prime_fd); +} + static const struct drm_driver driver = { .driver_features = DRIVER_GEM | DRIVER_COMPUTE_ACCEL, @@ -545,6 +565,7 @@ static const struct drm_driver driver = { .gem_create_object = ivpu_gem_create_object, .gem_prime_import = ivpu_gem_prime_import, + .prime_handle_to_fd = ivpu_gem_prime_handle_to_fd, .ioctls = ivpu_drm_ioctls, .num_ioctls = ARRAY_SIZE(ivpu_drm_ioctls), diff --git a/drivers/accel/qaic/qaic_ras.c b/drivers/accel/qaic/qaic_ras.c index cc0b75461e1a..6791af366cba 100644 --- a/drivers/accel/qaic/qaic_ras.c +++ b/drivers/accel/qaic/qaic_ras.c @@ -497,11 +497,11 @@ static void decode_ras_msg(struct qaic_device *qdev, struct ras_data *msg) qdev->ce_count++; break; case UE: - if (qdev->ce_count != UINT_MAX) + if (qdev->ue_count != UINT_MAX) qdev->ue_count++; break; case UE_NF: - if (qdev->ce_count != UINT_MAX) + if (qdev->ue_nf_count != UINT_MAX) qdev->ue_nf_count++; break; default: diff --git a/drivers/acpi/acpi_tad.c b/drivers/acpi/acpi_tad.c index b406d7a98996..cac07e997028 100644 --- a/drivers/acpi/acpi_tad.c +++ b/drivers/acpi/acpi_tad.c @@ -605,15 +605,12 @@ static umode_t acpi_tad_attr_is_visible(struct kobject *kobj, return 0; } -static const struct attribute_group acpi_tad_attr_group = { +static const struct attribute_group acpi_tad_group = { .attrs = acpi_tad_attrs, .is_visible = acpi_tad_attr_is_visible, }; -static const struct attribute_group *acpi_tad_attr_groups[] = { - &acpi_tad_attr_group, - NULL, -}; +__ATTRIBUTE_GROUPS(acpi_tad); #ifdef CONFIG_RTC_CLASS /* RTC class device interface */ @@ -683,9 +680,8 @@ static int acpi_tad_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *t) acpi_tad_rt_to_tm(&rt, &tm_now); - value = ktime_divns(ktime_sub(rtc_tm_to_ktime(t->time), - rtc_tm_to_ktime(tm_now)), NSEC_PER_SEC); - if (value <= 0 || value > U32_MAX) + value = rtc_tm_to_time64(&t->time) - rtc_tm_to_time64(&tm_now); + if (value <= 0 || value >= U32_MAX) return -EINVAL; } @@ -748,8 +744,7 @@ static int acpi_tad_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *t) if (retval != ACPI_TAD_WAKE_DISABLED) { t->enabled = 1; - t->time = rtc_ktime_to_tm(ktime_add_ns(rtc_tm_to_ktime(tm_now), - (u64)retval * NSEC_PER_SEC)); + rtc_time64_to_tm(rtc_tm_to_time64(&tm_now) + retval, &t->time); } else { t->enabled = 0; t->time = tm_now; @@ -795,9 +790,9 @@ static int acpi_tad_disable_timer(struct device *dev, u32 timer_id) return acpi_tad_wake_set(dev, "_STV", timer_id, ACPI_TAD_WAKE_DISABLED); } -static void acpi_tad_remove(struct platform_device *pdev) +static void acpi_tad_remove(void *data) { - struct device *dev = &pdev->dev; + struct device *dev = data; struct acpi_tad_driver_data *dd = dev_get_drvdata(dev); device_init_wakeup(dev, false); @@ -824,6 +819,7 @@ static int acpi_tad_probe(struct platform_device *pdev) struct acpi_tad_driver_data *dd; acpi_status status; unsigned long long caps; + int ret; /* * Initialization failure messages are mostly about firmware issues, so @@ -863,13 +859,21 @@ static int acpi_tad_probe(struct platform_device *pdev) } /* - * The platform bus type layer tells the ACPI PM domain powers up the - * device, so set the runtime PM status of it to "active". + * The platform bus type probe callback tells the ACPI PM domain to + * power up the device, so set the runtime PM status of it to "active". */ pm_runtime_set_active(dev); pm_runtime_enable(dev); pm_runtime_suspend(dev); + /* + * acpi_tad_remove() needs to run after unregistering the RTC class + * device to avoid racing with the latter's callbacks. + */ + ret = devm_add_action_or_reset(&pdev->dev, acpi_tad_remove, &pdev->dev); + if (ret) + return ret; + if (caps & ACPI_TAD_RT) acpi_tad_register_rtc(dev, caps); @@ -885,10 +889,9 @@ static struct platform_driver acpi_tad_driver = { .driver = { .name = "acpi-tad", .acpi_match_table = acpi_tad_ids, - .dev_groups = acpi_tad_attr_groups, + .dev_groups = acpi_tad_groups, }, .probe = acpi_tad_probe, - .remove = acpi_tad_remove, }; MODULE_DEVICE_TABLE(acpi, acpi_tad_ids); diff --git a/drivers/acpi/apei/einj-core.c b/drivers/acpi/apei/einj-core.c index a9248af078f6..1f3fa2278584 100644 --- a/drivers/acpi/apei/einj-core.c +++ b/drivers/acpi/apei/einj-core.c @@ -401,8 +401,18 @@ static struct acpi_generic_address *einj_get_trigger_parameter_region( return NULL; } + +static bool is_memory_injection(u32 type, u32 flags) +{ + if (flags & SETWA_FLAGS_EINJV2) + return !!(type & ACPI_EINJV2_MEMORY); + if (type & ACPI5_VENDOR_BIT) + return !!(vendor_flags & SETWA_FLAGS_MEM); + return !!(type & MEM_ERROR_MASK) || !!(flags & SETWA_FLAGS_MEM); +} + /* Execute instructions in trigger error action table */ -static int __einj_error_trigger(u64 trigger_paddr, u32 type, +static int __einj_error_trigger(u64 trigger_paddr, u32 type, u32 flags, u64 param1, u64 param2) { struct acpi_einj_trigger trigger_tab; @@ -480,7 +490,7 @@ static int __einj_error_trigger(u64 trigger_paddr, u32 type, * This will cause resource conflict with regular memory. So * remove it from trigger table resources. */ - if ((param_extension || acpi5) && (type & MEM_ERROR_MASK) && param2) { + if ((param_extension || acpi5) && is_memory_injection(type, flags)) { struct apei_resources addr_resources; apei_resources_init(&addr_resources); @@ -660,7 +670,7 @@ static int __einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2, return rc; trigger_paddr = apei_exec_ctx_get_output(&ctx); if (notrigger == 0) { - rc = __einj_error_trigger(trigger_paddr, type, param1, param2); + rc = __einj_error_trigger(trigger_paddr, type, flags, param1, param2); if (rc) return rc; } @@ -718,35 +728,30 @@ int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2, u64 param3, SETWA_FLAGS_PCIE_SBDF | SETWA_FLAGS_EINJV2))) return -EINVAL; + /* + * Injections targeting a CXL 1.0/1.1 port have to be injected + * via the einj_cxl_rch_error_inject() path as that does the proper + * validation of the given RCRB base (MMIO) address. + */ + if (einj_is_cxl_error_type(type) && (flags & SETWA_FLAGS_MEM)) + return -EINVAL; + /* check if type is a valid EINJv2 error type */ if (is_v2) { if (!(type & available_error_type_v2)) return -EINVAL; } - /* - * We need extra sanity checks for memory errors. - * Other types leap directly to injection. - */ /* ensure param1/param2 existed */ if (!(param_extension || acpi5)) goto inject; - /* ensure injection is memory related */ - if (type & ACPI5_VENDOR_BIT) { - if (vendor_flags != SETWA_FLAGS_MEM) - goto inject; - } else if (!(type & MEM_ERROR_MASK) && !(flags & SETWA_FLAGS_MEM)) { - goto inject; - } - /* - * Injections targeting a CXL 1.0/1.1 port have to be injected - * via the einj_cxl_rch_error_inject() path as that does the proper - * validation of the given RCRB base (MMIO) address. + * We need extra sanity checks for memory errors. + * Other types leap directly to injection. */ - if (einj_is_cxl_error_type(type) && (flags & SETWA_FLAGS_MEM)) - return -EINVAL; + if (!is_memory_injection(type, flags)) + goto inject; /* * Disallow crazy address masks that give BIOS leeway to pick diff --git a/drivers/acpi/arm64/cpuidle.c b/drivers/acpi/arm64/cpuidle.c index 801f9c450142..c68a5db8ebba 100644 --- a/drivers/acpi/arm64/cpuidle.c +++ b/drivers/acpi/arm64/cpuidle.c @@ -16,7 +16,7 @@ static int psci_acpi_cpu_init_idle(unsigned int cpu) { - int i, count; + int i; struct acpi_lpi_state *lpi; struct acpi_processor *pr = per_cpu(processors, cpu); @@ -30,14 +30,10 @@ static int psci_acpi_cpu_init_idle(unsigned int cpu) if (!psci_ops.cpu_suspend) return -EOPNOTSUPP; - count = pr->power.count - 1; - if (count <= 0) - return -ENODEV; - - for (i = 0; i < count; i++) { + for (i = 1; i < pr->power.count; i++) { u32 state; - lpi = &pr->power.lpi_states[i + 1]; + lpi = &pr->power.lpi_states[i]; /* * Only bits[31:0] represent a PSCI power_state while * bits[63:32] must be 0x0 as per ARM ACPI FFH Specification diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index 2e91c5a97761..f370be8715ae 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -362,7 +362,7 @@ static int send_pcc_cmd(int pcc_ss_id, u16 cmd) end: if (cmd == CMD_WRITE) { if (unlikely(ret)) { - for_each_online_cpu(i) { + for_each_possible_cpu(i) { struct cpc_desc *desc = per_cpu(cpc_desc_ptr, i); if (!desc) @@ -524,13 +524,13 @@ int acpi_get_psd_map(unsigned int cpu, struct cppc_cpudata *cpu_data) else if (pdomain->coord_type == DOMAIN_COORD_TYPE_SW_ANY) cpu_data->shared_type = CPUFREQ_SHARED_TYPE_ANY; - for_each_online_cpu(i) { + for_each_possible_cpu(i) { if (i == cpu) continue; match_cpc_ptr = per_cpu(cpc_desc_ptr, i); if (!match_cpc_ptr) - goto err_fault; + continue; match_pdomain = &(match_cpc_ptr->domain_info); if (match_pdomain->domain != pdomain->domain) diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index 0a3c8232d15d..458efa4fe9d4 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -916,6 +916,14 @@ static const struct dmi_system_id video_detect_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "82K8"), }, }, + { + .callback = video_detect_force_native, + /* HP OMEN Gaming Laptop 16-n0xxx */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "HP"), + DMI_MATCH(DMI_PRODUCT_NAME, "OMEN by HP Gaming Laptop 16-n0xxx"), + }, + }, /* * x86 android tablets which directly control the backlight through diff --git a/drivers/ata/pata_parport/pata_parport.c b/drivers/ata/pata_parport/pata_parport.c index a5b959891cb7..40baeac594a9 100644 --- a/drivers/ata/pata_parport/pata_parport.c +++ b/drivers/ata/pata_parport/pata_parport.c @@ -459,19 +459,11 @@ static void pata_parport_dev_release(struct device *dev) kfree(pi); } -static void pata_parport_bus_release(struct device *dev) -{ - /* nothing to do here but required to avoid warning on device removal */ -} - static const struct bus_type pata_parport_bus_type = { .name = DRV_NAME, }; -static struct device pata_parport_bus = { - .init_name = DRV_NAME, - .release = pata_parport_bus_release, -}; +static struct device *pata_parport_bus; static const struct scsi_host_template pata_parport_sht = { PATA_PARPORT_SHT("pata_parport") @@ -518,7 +510,7 @@ static struct pi_adapter *pi_init_one(struct parport *parport, } /* set up pi->dev before pi_probe_unit() so it can use dev_printk() */ - pi->dev.parent = &pata_parport_bus; + pi->dev.parent = pata_parport_bus; pi->dev.bus = &pata_parport_bus_type; pi->dev.driver = &pr->driver; pi->dev.release = pata_parport_dev_release; @@ -780,8 +772,9 @@ static __init int pata_parport_init(void) return error; } - error = device_register(&pata_parport_bus); - if (error) { + pata_parport_bus = root_device_register(DRV_NAME); + if (IS_ERR(pata_parport_bus)) { + error = PTR_ERR(pata_parport_bus); pr_err("failed to register pata_parport bus, error: %d\n", error); goto out_unregister_bus; } @@ -811,7 +804,7 @@ out_remove_del: out_remove_new: bus_remove_file(&pata_parport_bus_type, &bus_attr_new_device); out_unregister_dev: - device_unregister(&pata_parport_bus); + root_device_unregister(pata_parport_bus); out_unregister_bus: bus_unregister(&pata_parport_bus_type); return error; @@ -822,7 +815,7 @@ static __exit void pata_parport_exit(void) parport_unregister_driver(&pata_parport_driver); bus_remove_file(&pata_parport_bus_type, &bus_attr_new_device); bus_remove_file(&pata_parport_bus_type, &bus_attr_delete_device); - device_unregister(&pata_parport_bus); + root_device_unregister(pata_parport_bus); bus_unregister(&pata_parport_bus_type); } diff --git a/drivers/base/regmap/regmap-sdw-mbq.c b/drivers/base/regmap/regmap-sdw-mbq.c index 4533fe793c5f..2585933d4946 100644 --- a/drivers/base/regmap/regmap-sdw-mbq.c +++ b/drivers/base/regmap/regmap-sdw-mbq.c @@ -172,7 +172,7 @@ static int regmap_sdw_mbq_read(void *context, unsigned int reg, unsigned int *va ret = regmap_sdw_mbq_read_impl(slave, reg, val, mbq_size); if (ret == -ENODATA) { if (!deferrable) - dev_warn(dev, "Defer on undeferable control: %x\n", reg); + dev_warn(dev, "Defer on undeferrable control: %x\n", reg); ret = regmap_sdw_mbq_poll_busy(slave, reg, ctx); if (ret) diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c index 2f59c0d6f9ec..a3643e67b33f 100644 --- a/drivers/bluetooth/btintel_pcie.c +++ b/drivers/bluetooth/btintel_pcie.c @@ -289,6 +289,9 @@ static inline void btintel_pcie_dump_debug_registers(struct hci_dev *hdev) skb_put_data(skb, buf, strlen(buf)); data->boot_stage_cache = reg; + if (reg & BTINTEL_PCIE_CSR_BOOT_STAGE_DEVICE_WARNING) + bt_dev_warn(hdev, "Controller device warning (boot_stage: 0x%8.8x)", reg); + reg = btintel_pcie_rd_reg32(data, BTINTEL_PCIE_CSR_IPC_STATUS_REG); snprintf(buf, sizeof(buf), "ipc status: 0x%8.8x", reg); skb_put_data(skb, buf, strlen(buf)); @@ -880,8 +883,11 @@ static inline bool btintel_pcie_in_lockdown(struct btintel_pcie_data *data) static inline bool btintel_pcie_in_error(struct btintel_pcie_data *data) { - return (data->boot_stage_cache & BTINTEL_PCIE_CSR_BOOT_STAGE_DEVICE_ERR) || - (data->boot_stage_cache & BTINTEL_PCIE_CSR_BOOT_STAGE_ABORT_HANDLER); + if (data->boot_stage_cache & BTINTEL_PCIE_CSR_BOOT_STAGE_DEVICE_WARNING) + bt_dev_warn(data->hdev, "Controller device warning (boot_stage: 0x%8.8x)", + data->boot_stage_cache); + + return data->boot_stage_cache & BTINTEL_PCIE_CSR_BOOT_STAGE_ABORT_HANDLER; } static void btintel_pcie_msix_gp1_handler(struct btintel_pcie_data *data) @@ -914,7 +920,8 @@ static void btintel_pcie_msix_gp0_handler(struct btintel_pcie_data *data) data->img_resp_cache = reg; if (btintel_pcie_in_error(data)) { - bt_dev_err(data->hdev, "Controller in error state"); + bt_dev_err(data->hdev, "Controller in error state (boot_stage: 0x%8.8x)", + data->boot_stage_cache); btintel_pcie_dump_debug_registers(data->hdev); return; } diff --git a/drivers/bluetooth/btintel_pcie.h b/drivers/bluetooth/btintel_pcie.h index 3c7bb708362d..f922abd1e7d8 100644 --- a/drivers/bluetooth/btintel_pcie.h +++ b/drivers/bluetooth/btintel_pcie.h @@ -48,7 +48,7 @@ #define BTINTEL_PCIE_CSR_BOOT_STAGE_OPFW (BIT(2)) #define BTINTEL_PCIE_CSR_BOOT_STAGE_ROM_LOCKDOWN (BIT(10)) #define BTINTEL_PCIE_CSR_BOOT_STAGE_IML_LOCKDOWN (BIT(11)) -#define BTINTEL_PCIE_CSR_BOOT_STAGE_DEVICE_ERR (BIT(12)) +#define BTINTEL_PCIE_CSR_BOOT_STAGE_DEVICE_WARNING (BIT(12)) #define BTINTEL_PCIE_CSR_BOOT_STAGE_ABORT_HANDLER (BIT(13)) #define BTINTEL_PCIE_CSR_BOOT_STAGE_DEVICE_HALTED (BIT(14)) #define BTINTEL_PCIE_CSR_BOOT_STAGE_MAC_ACCESS_ON (BIT(16)) diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c index 6fb6ca274808..f70c1b0f8990 100644 --- a/drivers/bluetooth/btmtk.c +++ b/drivers/bluetooth/btmtk.c @@ -695,8 +695,13 @@ static int btmtk_usb_hci_wmt_sync(struct hci_dev *hdev, if (data->evt_skb == NULL) goto err_free_wc; - /* Parse and handle the return WMT event */ - wmt_evt = (struct btmtk_hci_wmt_evt *)data->evt_skb->data; + wmt_evt = skb_pull_data(data->evt_skb, sizeof(*wmt_evt)); + if (!wmt_evt) { + bt_dev_err(hdev, "WMT event too short (%u bytes)", + data->evt_skb->len); + err = -EINVAL; + goto err_free_skb; + } if (wmt_evt->whdr.op != hdr->op) { bt_dev_err(hdev, "Wrong op received %d expected %d", wmt_evt->whdr.op, hdr->op); @@ -712,6 +717,12 @@ static int btmtk_usb_hci_wmt_sync(struct hci_dev *hdev, status = BTMTK_WMT_PATCH_DONE; break; case BTMTK_WMT_FUNC_CTRL: + if (!skb_pull_data(data->evt_skb, + sizeof(wmt_evt_funcc->status))) { + err = -EINVAL; + goto err_free_skb; + } + wmt_evt_funcc = (struct btmtk_hci_wmt_evt_funcc *)wmt_evt; if (be16_to_cpu(wmt_evt_funcc->status) == 0x404) status = BTMTK_WMT_ON_DONE; diff --git a/drivers/bluetooth/hci_ath.c b/drivers/bluetooth/hci_ath.c index fa679ad0acdf..8201fa7f61e8 100644 --- a/drivers/bluetooth/hci_ath.c +++ b/drivers/bluetooth/hci_ath.c @@ -191,6 +191,9 @@ static int ath_recv(struct hci_uart *hu, const void *data, int count) { struct ath_struct *ath = hu->priv; + if (!ath) + return -ENODEV; + ath->rx_skb = h4_recv_buf(hu, ath->rx_skb, data, count, ath_recv_pkts, ARRAY_SIZE(ath_recv_pkts)); if (IS_ERR(ath->rx_skb)) { diff --git a/drivers/bluetooth/hci_bcsp.c b/drivers/bluetooth/hci_bcsp.c index b386f91d8b46..db56eead27ce 100644 --- a/drivers/bluetooth/hci_bcsp.c +++ b/drivers/bluetooth/hci_bcsp.c @@ -585,6 +585,9 @@ static int bcsp_recv(struct hci_uart *hu, const void *data, int count) if (!test_bit(HCI_UART_REGISTERED, &hu->flags)) return -EUNATCH; + if (!bcsp) + return -ENODEV; + BT_DBG("hu %p count %d rx_state %d rx_count %ld", hu, count, bcsp->rx_state, bcsp->rx_count); diff --git a/drivers/bluetooth/hci_h4.c b/drivers/bluetooth/hci_h4.c index a889a66a326f..767372707498 100644 --- a/drivers/bluetooth/hci_h4.c +++ b/drivers/bluetooth/hci_h4.c @@ -109,6 +109,9 @@ static int h4_recv(struct hci_uart *hu, const void *data, int count) { struct h4_struct *h4 = hu->priv; + if (!h4) + return -ENODEV; + h4->rx_skb = h4_recv_buf(hu, h4->rx_skb, data, count, h4_recv_pkts, ARRAY_SIZE(h4_recv_pkts)); if (IS_ERR(h4->rx_skb)) { diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c index cfdf75dc2847..d35383718212 100644 --- a/drivers/bluetooth/hci_h5.c +++ b/drivers/bluetooth/hci_h5.c @@ -587,6 +587,9 @@ static int h5_recv(struct hci_uart *hu, const void *data, int count) struct h5 *h5 = hu->priv; const unsigned char *ptr = data; + if (!h5) + return -ENODEV; + BT_DBG("%s pending %zu count %d", hu->hdev->name, h5->rx_pending, count); diff --git a/drivers/bluetooth/virtio_bt.c b/drivers/bluetooth/virtio_bt.c index 76d61af8a275..140ab55c9fc5 100644 --- a/drivers/bluetooth/virtio_bt.c +++ b/drivers/bluetooth/virtio_bt.c @@ -12,6 +12,7 @@ #include <net/bluetooth/hci_core.h> #define VERSION "0.1" +#define VIRTBT_RX_BUF_SIZE 1000 enum { VIRTBT_VQ_TX, @@ -33,11 +34,11 @@ static int virtbt_add_inbuf(struct virtio_bluetooth *vbt) struct sk_buff *skb; int err; - skb = alloc_skb(1000, GFP_KERNEL); + skb = alloc_skb(VIRTBT_RX_BUF_SIZE, GFP_KERNEL); if (!skb) return -ENOMEM; - sg_init_one(sg, skb->data, 1000); + sg_init_one(sg, skb->data, VIRTBT_RX_BUF_SIZE); err = virtqueue_add_inbuf(vq, sg, 1, skb, GFP_KERNEL); if (err < 0) { @@ -197,6 +198,7 @@ static int virtbt_shutdown_generic(struct hci_dev *hdev) static void virtbt_rx_handle(struct virtio_bluetooth *vbt, struct sk_buff *skb) { + size_t min_hdr; __u8 pkt_type; pkt_type = *((__u8 *) skb->data); @@ -204,16 +206,32 @@ static void virtbt_rx_handle(struct virtio_bluetooth *vbt, struct sk_buff *skb) switch (pkt_type) { case HCI_EVENT_PKT: + min_hdr = sizeof(struct hci_event_hdr); + break; case HCI_ACLDATA_PKT: + min_hdr = sizeof(struct hci_acl_hdr); + break; case HCI_SCODATA_PKT: + min_hdr = sizeof(struct hci_sco_hdr); + break; case HCI_ISODATA_PKT: - hci_skb_pkt_type(skb) = pkt_type; - hci_recv_frame(vbt->hdev, skb); + min_hdr = sizeof(struct hci_iso_hdr); break; default: kfree_skb(skb); - break; + return; + } + + if (skb->len < min_hdr) { + bt_dev_err_ratelimited(vbt->hdev, + "rx pkt_type 0x%02x payload %u < hdr %zu\n", + pkt_type, skb->len, min_hdr); + kfree_skb(skb); + return; } + + hci_skb_pkt_type(skb) = pkt_type; + hci_recv_frame(vbt->hdev, skb); } static void virtbt_rx_work(struct work_struct *work) @@ -227,8 +245,15 @@ static void virtbt_rx_work(struct work_struct *work) if (!skb) return; - skb_put(skb, len); - virtbt_rx_handle(vbt, skb); + if (!len || len > VIRTBT_RX_BUF_SIZE) { + bt_dev_err_ratelimited(vbt->hdev, + "rx reply len %u outside [1, %u]\n", + len, VIRTBT_RX_BUF_SIZE); + kfree_skb(skb); + } else { + skb_put(skb, len); + virtbt_rx_handle(vbt, skb); + } if (virtbt_add_inbuf(vbt) < 0) return; diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c index 4a9e9de4d684..9a9d12be9bf7 100644 --- a/drivers/char/ipmi/ipmi_si_intf.c +++ b/drivers/char/ipmi/ipmi_si_intf.c @@ -168,6 +168,10 @@ struct smi_info { OEM2_DATA_AVAIL) unsigned char msg_flags; + /* When requesting events and messages, don't do it forever. */ + unsigned int num_requests_in_a_row; + bool last_was_flag_fetch; + /* Does the BMC have an event buffer? */ bool has_event_buffer; @@ -410,7 +414,10 @@ static void start_getting_msg_queue(struct smi_info *smi_info) start_new_msg(smi_info, smi_info->curr_msg->data, smi_info->curr_msg->data_size); - smi_info->si_state = SI_GETTING_MESSAGES; + if (smi_info->si_state != SI_GETTING_MESSAGES) { + smi_info->num_requests_in_a_row = 0; + smi_info->si_state = SI_GETTING_MESSAGES; + } } static void start_getting_events(struct smi_info *smi_info) @@ -421,7 +428,10 @@ static void start_getting_events(struct smi_info *smi_info) start_new_msg(smi_info, smi_info->curr_msg->data, smi_info->curr_msg->data_size); - smi_info->si_state = SI_GETTING_EVENTS; + if (smi_info->si_state != SI_GETTING_EVENTS) { + smi_info->num_requests_in_a_row = 0; + smi_info->si_state = SI_GETTING_EVENTS; + } } /* @@ -487,15 +497,19 @@ retry: } else if (smi_info->msg_flags & RECEIVE_MSG_AVAIL) { /* Messages available. */ smi_info->curr_msg = alloc_msg_handle_irq(smi_info); - if (!smi_info->curr_msg) + if (!smi_info->curr_msg) { + smi_info->si_state = SI_NORMAL; return; + } start_getting_msg_queue(smi_info); } else if (smi_info->msg_flags & EVENT_MSG_BUFFER_FULL) { /* Events available. */ smi_info->curr_msg = alloc_msg_handle_irq(smi_info); - if (!smi_info->curr_msg) + if (!smi_info->curr_msg) { + smi_info->si_state = SI_NORMAL; return; + } start_getting_events(smi_info); } else if (smi_info->msg_flags & OEM_DATA_AVAIL && @@ -595,6 +609,7 @@ static void handle_transaction_done(struct smi_info *smi_info) smi_info->si_state = SI_NORMAL; } else { smi_info->msg_flags = msg[3]; + smi_info->last_was_flag_fetch = true; handle_flags(smi_info); } break; @@ -630,7 +645,13 @@ static void handle_transaction_done(struct smi_info *smi_info) */ msg = smi_info->curr_msg; smi_info->curr_msg = NULL; - if (msg->rsp[2] != 0) { + /* + * It appears some BMCs, with no event data, return no + * data in the message and not a 0x80 error as the + * spec says they should. Shut down processing if + * the data is not the right length. + */ + if (msg->rsp[2] != 0 || msg->rsp_size != 19) { /* Error getting event, probably done. */ msg->done(msg); @@ -640,6 +661,11 @@ static void handle_transaction_done(struct smi_info *smi_info) } else { smi_inc_stat(smi_info, events); + smi_info->num_requests_in_a_row++; + if (smi_info->num_requests_in_a_row > 10) + /* Stop if we do this too many times. */ + smi_info->msg_flags &= ~EVENT_MSG_BUFFER_FULL; + /* * Do this before we deliver the message * because delivering the message releases the @@ -678,6 +704,11 @@ static void handle_transaction_done(struct smi_info *smi_info) } else { smi_inc_stat(smi_info, incoming_messages); + smi_info->num_requests_in_a_row++; + if (smi_info->num_requests_in_a_row > 10) + /* Stop if we do this too many times. */ + smi_info->msg_flags &= ~RECEIVE_MSG_AVAIL; + /* * Do this before we deliver the message * because delivering the message releases the @@ -820,6 +851,26 @@ restart: } /* + * If we are currently idle, or if the last thing that was + * done was a flag fetch and there is a message pending, try + * to start the next message. + * + * We do the waiting message check to avoid a stuck flag + * completely wedging the driver. Let a message through + * in between flag operations if that happens. + */ + if (si_sm_result == SI_SM_IDLE || + (si_sm_result == SI_SM_ATTN && smi_info->waiting_msg && + smi_info->last_was_flag_fetch)) { + smi_info->last_was_flag_fetch = false; + smi_inc_stat(smi_info, idles); + + si_sm_result = start_next_msg(smi_info); + if (si_sm_result != SI_SM_IDLE) + goto restart; + } + + /* * We prefer handling attn over new messages. But don't do * this if there is not yet an upper layer to handle anything. */ @@ -846,15 +897,6 @@ restart: } } - /* If we are currently idle, try to start the next message. */ - if (si_sm_result == SI_SM_IDLE) { - smi_inc_stat(smi_info, idles); - - si_sm_result = start_next_msg(smi_info); - if (si_sm_result != SI_SM_IDLE) - goto restart; - } - if ((si_sm_result == SI_SM_IDLE) && (atomic_read(&smi_info->req_events))) { /* diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c index b49500a1bd36..f419b46bf002 100644 --- a/drivers/char/ipmi/ipmi_ssif.c +++ b/drivers/char/ipmi/ipmi_ssif.c @@ -225,6 +225,9 @@ struct ssif_info { bool has_event_buffer; bool supports_alert; + /* When requesting events and messages, don't do it forever. */ + unsigned int num_requests_in_a_row; + /* * Used to tell what we should do with alerts. If we are * waiting on a response, read the data immediately. @@ -413,7 +416,10 @@ static void start_event_fetch(struct ssif_info *ssif_info, unsigned long *flags) } ssif_info->curr_msg = msg; - ssif_info->ssif_state = SSIF_GETTING_EVENTS; + if (ssif_info->ssif_state != SSIF_GETTING_EVENTS) { + ssif_info->num_requests_in_a_row = 0; + ssif_info->ssif_state = SSIF_GETTING_EVENTS; + } ipmi_ssif_unlock_cond(ssif_info, flags); msg->data[0] = (IPMI_NETFN_APP_REQUEST << 2); @@ -436,7 +442,10 @@ static void start_recv_msg_fetch(struct ssif_info *ssif_info, } ssif_info->curr_msg = msg; - ssif_info->ssif_state = SSIF_GETTING_MESSAGES; + if (ssif_info->ssif_state != SSIF_GETTING_MESSAGES) { + ssif_info->num_requests_in_a_row = 0; + ssif_info->ssif_state = SSIF_GETTING_MESSAGES; + } ipmi_ssif_unlock_cond(ssif_info, flags); msg->data[0] = (IPMI_NETFN_APP_REQUEST << 2); @@ -843,6 +852,11 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result, ssif_info->msg_flags &= ~EVENT_MSG_BUFFER_FULL; handle_flags(ssif_info, flags); } else { + ssif_info->num_requests_in_a_row++; + if (ssif_info->num_requests_in_a_row > 10) + /* Stop if we do this too many times. */ + ssif_info->msg_flags &= ~EVENT_MSG_BUFFER_FULL; + handle_flags(ssif_info, flags); ssif_inc_stat(ssif_info, events); deliver_recv_msg(ssif_info, msg); @@ -876,6 +890,11 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result, ssif_info->msg_flags &= ~RECEIVE_MSG_AVAIL; handle_flags(ssif_info, flags); } else { + ssif_info->num_requests_in_a_row++; + if (ssif_info->num_requests_in_a_row > 10) + /* Stop if we do this too many times. */ + ssif_info->msg_flags &= ~RECEIVE_MSG_AVAIL; + ssif_inc_stat(ssif_info, incoming_messages); handle_flags(ssif_info, flags); deliver_recv_msg(ssif_info, msg); @@ -1886,6 +1905,7 @@ static int ssif_probe(struct i2c_client *client) "kssif%4.4x", thread_num); if (IS_ERR(ssif_info->thread)) { rv = PTR_ERR(ssif_info->thread); + ssif_info->thread = NULL; dev_notice(&ssif_info->client->dev, "Could not start kernel thread: error %d\n", rv); diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c index af7ce62ec55c..0ff1658c2dc1 100644 --- a/drivers/dpll/dpll_netlink.c +++ b/drivers/dpll/dpll_netlink.c @@ -900,11 +900,21 @@ int dpll_pin_delete_ntf(struct dpll_pin *pin) return dpll_pin_event_send(DPLL_CMD_PIN_DELETE_NTF, pin); } +/** + * __dpll_pin_change_ntf - notify that the pin has been changed + * @pin: registered pin pointer + * + * Context: caller must hold dpll_lock. Suitable for use inside pin + * callbacks which are already invoked under dpll_lock. + * Return: 0 if succeeds, error code otherwise. + */ int __dpll_pin_change_ntf(struct dpll_pin *pin) { + lockdep_assert_held(&dpll_lock); dpll_pin_notify(pin, DPLL_PIN_CHANGED); return dpll_pin_event_send(DPLL_CMD_PIN_CHANGE_NTF, pin); } +EXPORT_SYMBOL_GPL(__dpll_pin_change_ntf); /** * dpll_pin_change_ntf - notify that the pin has been changed diff --git a/drivers/dpll/dpll_netlink.h b/drivers/dpll/dpll_netlink.h index dd28b56d27c5..a9cfd55f57fc 100644 --- a/drivers/dpll/dpll_netlink.h +++ b/drivers/dpll/dpll_netlink.h @@ -11,5 +11,3 @@ int dpll_device_delete_ntf(struct dpll_device *dpll); int dpll_pin_create_ntf(struct dpll_pin *pin); int dpll_pin_delete_ntf(struct dpll_pin *pin); - -int __dpll_pin_change_ntf(struct dpll_pin *pin); diff --git a/drivers/firmware/efi/efi-pstore.c b/drivers/firmware/efi/efi-pstore.c index a253b6144945..a5db3534f0a6 100644 --- a/drivers/firmware/efi/efi-pstore.c +++ b/drivers/firmware/efi/efi-pstore.c @@ -60,8 +60,10 @@ static int efi_pstore_open(struct pstore_info *psi) return err; psi->data = kzalloc(record_size, GFP_KERNEL); - if (!psi->data) + if (!psi->data) { + efivar_unlock(); return -ENOMEM; + } return 0; } diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile index 983a438e35f3..cfedb3025c26 100644 --- a/drivers/firmware/efi/libstub/Makefile +++ b/drivers/firmware/efi/libstub/Makefile @@ -66,7 +66,7 @@ KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ lib-y := efi-stub-helper.o gop.o secureboot.o tpm.o \ file.o mem.o random.o randomalloc.o pci.o \ skip_spaces.o lib-cmdline.o lib-ctype.o \ - alignedmem.o relocate.o printk.o vsprintf.o + alignedmem.o printk.o vsprintf.o # include the stub's libfdt dependencies from lib/ when needed libfdt-deps := fdt_rw.c fdt_ro.c fdt_wip.c fdt.c \ diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h index 979a21818cc1..fd91fc15ec81 100644 --- a/drivers/firmware/efi/libstub/efistub.h +++ b/drivers/firmware/efi/libstub/efistub.h @@ -1104,13 +1104,6 @@ efi_status_t efi_allocate_pages_aligned(unsigned long size, unsigned long *addr, efi_status_t efi_low_alloc_above(unsigned long size, unsigned long align, unsigned long *addr, unsigned long min); -efi_status_t efi_relocate_kernel(unsigned long *image_addr, - unsigned long image_size, - unsigned long alloc_size, - unsigned long preferred_addr, - unsigned long alignment, - unsigned long min_addr); - efi_status_t efi_parse_options(char const *cmdline); void efi_parse_option_graphics(char *option); diff --git a/drivers/firmware/efi/libstub/loongarch-stub.c b/drivers/firmware/efi/libstub/loongarch-stub.c index 736b6aae323d..c87ac7025107 100644 --- a/drivers/firmware/efi/libstub/loongarch-stub.c +++ b/drivers/firmware/efi/libstub/loongarch-stub.c @@ -14,6 +14,86 @@ extern int kernel_asize; extern int kernel_fsize; extern int kernel_entry; +/** + * efi_relocate_kernel() - copy memory area + * @image_addr: pointer to address of memory area to copy + * @image_size: size of memory area to copy + * @alloc_size: minimum size of memory to allocate, must be greater or + * equal to image_size + * @preferred_addr: preferred target address + * @alignment: minimum alignment of the allocated memory area. It + * should be a power of two. + * @min_addr: minimum target address + * + * Copy a memory area to a newly allocated memory area aligned according + * to @alignment but at least EFI_ALLOC_ALIGN. If the preferred address + * is not available, the allocated address will not be below @min_addr. + * On exit, @image_addr is updated to the target copy address that was used. + * + * This function is used to copy the Linux kernel verbatim. It does not apply + * any relocation changes. + * + * Return: status code + */ +static +efi_status_t efi_relocate_kernel(unsigned long *image_addr, + unsigned long image_size, + unsigned long alloc_size, + unsigned long preferred_addr, + unsigned long alignment, + unsigned long min_addr) +{ + unsigned long cur_image_addr; + unsigned long new_addr = 0; + efi_status_t status; + unsigned long nr_pages; + efi_physical_addr_t efi_addr = preferred_addr; + + if (!image_addr || !image_size || !alloc_size) + return EFI_INVALID_PARAMETER; + if (alloc_size < image_size) + return EFI_INVALID_PARAMETER; + + cur_image_addr = *image_addr; + + /* + * The EFI firmware loader could have placed the kernel image + * anywhere in memory, but the kernel has restrictions on the + * max physical address it can run at. Some architectures + * also have a preferred address, so first try to relocate + * to the preferred address. If that fails, allocate as low + * as possible while respecting the required alignment. + */ + nr_pages = round_up(alloc_size, EFI_ALLOC_ALIGN) / EFI_PAGE_SIZE; + status = efi_bs_call(allocate_pages, EFI_ALLOCATE_ADDRESS, + EFI_LOADER_DATA, nr_pages, &efi_addr); + new_addr = efi_addr; + /* + * If preferred address allocation failed allocate as low as + * possible. + */ + if (status != EFI_SUCCESS) { + status = efi_low_alloc_above(alloc_size, alignment, &new_addr, + min_addr); + } + if (status != EFI_SUCCESS) { + efi_err("Failed to allocate usable memory for kernel.\n"); + return status; + } + + /* + * We know source/dest won't overlap since both memory ranges + * have been allocated by UEFI, so we can safely use memcpy. + */ + memcpy((void *)new_addr, (void *)cur_image_addr, image_size); + efi_cache_sync_image(new_addr, image_size); + + /* Return the new address of the relocated image. */ + *image_addr = new_addr; + + return status; +} + efi_status_t handle_kernel_image(unsigned long *image_addr, unsigned long *image_size, unsigned long *reserve_addr, diff --git a/drivers/firmware/efi/libstub/loongarch.c b/drivers/firmware/efi/libstub/loongarch.c index 9825f5218137..f7938d5c196a 100644 --- a/drivers/firmware/efi/libstub/loongarch.c +++ b/drivers/firmware/efi/libstub/loongarch.c @@ -18,6 +18,11 @@ efi_status_t check_platform_features(void) return EFI_SUCCESS; } +void efi_cache_sync_image(unsigned long image_base, unsigned long alloc_size) +{ + asm volatile ("ibar 0" ::: "memory"); +} + struct exit_boot_struct { efi_memory_desc_t *runtime_map; int runtime_entry_count; diff --git a/drivers/firmware/efi/libstub/mem.c b/drivers/firmware/efi/libstub/mem.c index 9c82259eea81..59f3f83de50c 100644 --- a/drivers/firmware/efi/libstub/mem.c +++ b/drivers/firmware/efi/libstub/mem.c @@ -124,3 +124,85 @@ void efi_free(unsigned long size, unsigned long addr) nr_pages = round_up(size, EFI_ALLOC_ALIGN) / EFI_PAGE_SIZE; efi_bs_call(free_pages, addr, nr_pages); } + +/** + * efi_low_alloc_above() - allocate pages at or above given address + * @size: size of the memory area to allocate + * @align: minimum alignment of the allocated memory area. It should + * a power of two. + * @addr: on exit the address of the allocated memory + * @min: minimum address to used for the memory allocation + * + * Allocate at the lowest possible address that is not below @min as + * EFI_LOADER_DATA. The allocated pages are aligned according to @align but at + * least EFI_ALLOC_ALIGN. The first allocated page will not below the address + * given by @min. + * + * Return: status code + */ +efi_status_t efi_low_alloc_above(unsigned long size, unsigned long align, + unsigned long *addr, unsigned long min) +{ + struct efi_boot_memmap *map __free(efi_pool) = NULL; + efi_status_t status; + unsigned long nr_pages; + int i; + + status = efi_get_memory_map(&map, false); + if (status != EFI_SUCCESS) + return status; + + /* + * Enforce minimum alignment that EFI or Linux requires when + * requesting a specific address. We are doing page-based (or + * larger) allocations, and both the address and size must meet + * alignment constraints. + */ + if (align < EFI_ALLOC_ALIGN) + align = EFI_ALLOC_ALIGN; + + size = round_up(size, EFI_ALLOC_ALIGN); + nr_pages = size / EFI_PAGE_SIZE; + for (i = 0; i < map->map_size / map->desc_size; i++) { + efi_memory_desc_t *desc; + unsigned long m = (unsigned long)map->map; + u64 start, end; + + desc = efi_memdesc_ptr(m, map->desc_size, i); + + if (desc->type != EFI_CONVENTIONAL_MEMORY) + continue; + + if (desc->attribute & EFI_MEMORY_HOT_PLUGGABLE) + continue; + + if (efi_soft_reserve_enabled() && + (desc->attribute & EFI_MEMORY_SP)) + continue; + + if (desc->num_pages < nr_pages) + continue; + + start = desc->phys_addr; + end = start + desc->num_pages * EFI_PAGE_SIZE; + + if (start < min) + start = min; + + start = round_up(start, align); + if ((start + size) > end) + continue; + + status = efi_bs_call(allocate_pages, EFI_ALLOCATE_ADDRESS, + EFI_LOADER_DATA, nr_pages, &start); + if (status == EFI_SUCCESS) { + *addr = start; + break; + } + } + + if (i == map->map_size / map->desc_size) + return EFI_NOT_FOUND; + + return EFI_SUCCESS; +} diff --git a/drivers/firmware/efi/libstub/relocate.c b/drivers/firmware/efi/libstub/relocate.c deleted file mode 100644 index d4264bfb6dc1..000000000000 --- a/drivers/firmware/efi/libstub/relocate.c +++ /dev/null @@ -1,166 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -#include <linux/efi.h> -#include <asm/efi.h> - -#include "efistub.h" - -/** - * efi_low_alloc_above() - allocate pages at or above given address - * @size: size of the memory area to allocate - * @align: minimum alignment of the allocated memory area. It should - * a power of two. - * @addr: on exit the address of the allocated memory - * @min: minimum address to used for the memory allocation - * - * Allocate at the lowest possible address that is not below @min as - * EFI_LOADER_DATA. The allocated pages are aligned according to @align but at - * least EFI_ALLOC_ALIGN. The first allocated page will not below the address - * given by @min. - * - * Return: status code - */ -efi_status_t efi_low_alloc_above(unsigned long size, unsigned long align, - unsigned long *addr, unsigned long min) -{ - struct efi_boot_memmap *map __free(efi_pool) = NULL; - efi_status_t status; - unsigned long nr_pages; - int i; - - status = efi_get_memory_map(&map, false); - if (status != EFI_SUCCESS) - return status; - - /* - * Enforce minimum alignment that EFI or Linux requires when - * requesting a specific address. We are doing page-based (or - * larger) allocations, and both the address and size must meet - * alignment constraints. - */ - if (align < EFI_ALLOC_ALIGN) - align = EFI_ALLOC_ALIGN; - - size = round_up(size, EFI_ALLOC_ALIGN); - nr_pages = size / EFI_PAGE_SIZE; - for (i = 0; i < map->map_size / map->desc_size; i++) { - efi_memory_desc_t *desc; - unsigned long m = (unsigned long)map->map; - u64 start, end; - - desc = efi_memdesc_ptr(m, map->desc_size, i); - - if (desc->type != EFI_CONVENTIONAL_MEMORY) - continue; - - if (desc->attribute & EFI_MEMORY_HOT_PLUGGABLE) - continue; - - if (efi_soft_reserve_enabled() && - (desc->attribute & EFI_MEMORY_SP)) - continue; - - if (desc->num_pages < nr_pages) - continue; - - start = desc->phys_addr; - end = start + desc->num_pages * EFI_PAGE_SIZE; - - if (start < min) - start = min; - - start = round_up(start, align); - if ((start + size) > end) - continue; - - status = efi_bs_call(allocate_pages, EFI_ALLOCATE_ADDRESS, - EFI_LOADER_DATA, nr_pages, &start); - if (status == EFI_SUCCESS) { - *addr = start; - break; - } - } - - if (i == map->map_size / map->desc_size) - return EFI_NOT_FOUND; - - return EFI_SUCCESS; -} - -/** - * efi_relocate_kernel() - copy memory area - * @image_addr: pointer to address of memory area to copy - * @image_size: size of memory area to copy - * @alloc_size: minimum size of memory to allocate, must be greater or - * equal to image_size - * @preferred_addr: preferred target address - * @alignment: minimum alignment of the allocated memory area. It - * should be a power of two. - * @min_addr: minimum target address - * - * Copy a memory area to a newly allocated memory area aligned according - * to @alignment but at least EFI_ALLOC_ALIGN. If the preferred address - * is not available, the allocated address will not be below @min_addr. - * On exit, @image_addr is updated to the target copy address that was used. - * - * This function is used to copy the Linux kernel verbatim. It does not apply - * any relocation changes. - * - * Return: status code - */ -efi_status_t efi_relocate_kernel(unsigned long *image_addr, - unsigned long image_size, - unsigned long alloc_size, - unsigned long preferred_addr, - unsigned long alignment, - unsigned long min_addr) -{ - unsigned long cur_image_addr; - unsigned long new_addr = 0; - efi_status_t status; - unsigned long nr_pages; - efi_physical_addr_t efi_addr = preferred_addr; - - if (!image_addr || !image_size || !alloc_size) - return EFI_INVALID_PARAMETER; - if (alloc_size < image_size) - return EFI_INVALID_PARAMETER; - - cur_image_addr = *image_addr; - - /* - * The EFI firmware loader could have placed the kernel image - * anywhere in memory, but the kernel has restrictions on the - * max physical address it can run at. Some architectures - * also have a preferred address, so first try to relocate - * to the preferred address. If that fails, allocate as low - * as possible while respecting the required alignment. - */ - nr_pages = round_up(alloc_size, EFI_ALLOC_ALIGN) / EFI_PAGE_SIZE; - status = efi_bs_call(allocate_pages, EFI_ALLOCATE_ADDRESS, - EFI_LOADER_DATA, nr_pages, &efi_addr); - new_addr = efi_addr; - /* - * If preferred address allocation failed allocate as low as - * possible. - */ - if (status != EFI_SUCCESS) { - status = efi_low_alloc_above(alloc_size, alignment, &new_addr, - min_addr); - } - if (status != EFI_SUCCESS) { - efi_err("Failed to allocate usable memory for kernel.\n"); - return status; - } - - /* - * We know source/dest won't overlap since both memory ranges - * have been allocated by UEFI, so we can safely use memcpy. - */ - memcpy((void *)new_addr, (void *)cur_image_addr, image_size); - - /* Return the new address of the relocated image. */ - *image_addr = new_addr; - - return status; -} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 737ef1ef96a5..66ca043658ff 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2839,8 +2839,12 @@ static int amdgpu_device_ip_fini_early(struct amdgpu_device *adev) * that checks whether the PSP is running. A solution for those issues * in the APU is to trigger a GPU reset, but this should be done during * the unload phase to avoid adding boot latency and screen flicker. + * GFX V11 has GC block as default off IP. Every time AMDGPU driver sends + * a request to PMFW to unload MP1, PMFW will put GC in reset and power down + * the voltage. Hence, skipping reset for APUs with GFX V11 or later. */ - if ((adev->flags & AMD_IS_APU) && !adev->gmc.is_app_apu) { + if ((adev->flags & AMD_IS_APU) && !adev->gmc.is_app_apu && + amdgpu_ip_version(adev, GC_HWIP, 0) < IP_VERSION(11, 0, 0)) { r = amdgpu_asic_reset(adev); if (r) dev_err(adev->dev, "asic reset on %s failed\n", __func__); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index fcad7daaa41b..8d99bfaa498f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -3090,10 +3090,8 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) case IP_VERSION(11, 5, 1): case IP_VERSION(11, 5, 2): case IP_VERSION(11, 5, 3): - adev->family = AMDGPU_FAMILY_GC_11_5_0; - break; case IP_VERSION(11, 5, 4): - adev->family = AMDGPU_FAMILY_GC_11_5_4; + adev->family = AMDGPU_FAMILY_GC_11_5_0; break; case IP_VERSION(12, 0, 0): case IP_VERSION(12, 0, 1): diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index e47921e2a9af..60debd543e44 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -3149,17 +3149,15 @@ static int __init amdgpu_init(void) r = amdgpu_sync_init(); if (r) - goto error_sync; - - r = amdgpu_userq_fence_slab_init(); - if (r) - goto error_fence; + return r; amdgpu_register_atpx_handler(); amdgpu_acpi_detect(); - /* Ignore KFD init failures. Normal when CONFIG_HSA_AMD is not set. */ - amdgpu_amdkfd_init(); + /* Ignore KFD init failures when CONFIG_HSA_AMD is not set. */ + r = amdgpu_amdkfd_init(); + if (r && r != -ENOENT) + goto error_fini_sync; if (amdgpu_pp_feature_mask & PP_OVERDRIVE_MASK) { add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK); @@ -3170,10 +3168,8 @@ static int __init amdgpu_init(void) /* let modprobe override vga console setting */ return pci_register_driver(&amdgpu_kms_pci_driver); -error_fence: +error_fini_sync: amdgpu_sync_fini(); - -error_sync: return r; } @@ -3184,7 +3180,6 @@ static void __exit amdgpu_exit(void) amdgpu_unregister_atpx_handler(); amdgpu_acpi_release(); amdgpu_sync_fini(); - amdgpu_userq_fence_slab_fini(); mmu_notifier_synchronize(); amdgpu_xcp_drv_release(); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c index bc772ca3dab7..b6f849d51c2e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c @@ -262,12 +262,19 @@ void amdgpu_gart_table_ram_free(struct amdgpu_device *adev) */ int amdgpu_gart_table_vram_alloc(struct amdgpu_device *adev) { + int r; + if (adev->gart.bo != NULL) return 0; - return amdgpu_bo_create_kernel(adev, adev->gart.table_size, PAGE_SIZE, - AMDGPU_GEM_DOMAIN_VRAM, &adev->gart.bo, - NULL, (void *)&adev->gart.ptr); + r = amdgpu_bo_create_kernel(adev, adev->gart.table_size, PAGE_SIZE, + AMDGPU_GEM_DOMAIN_VRAM, &adev->gart.bo, + NULL, (void *)&adev->gart.ptr); + if (r) + return r; + + memset_io(adev->gart.ptr, adev->gart.gart_pte_flags, adev->gart.table_size); + return 0; } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index 285e217fba04..3d9497d121ca 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -314,7 +314,10 @@ void amdgpu_gmc_gart_location(struct amdgpu_device *adev, struct amdgpu_gmc *mc, mc->gart_start = max_mc_address - mc->gart_size + 1; break; case AMDGPU_GART_PLACEMENT_LOW: - mc->gart_start = 0; + if (size_bf >= mc->gart_size) + mc->gart_start = 0; + else + mc->gart_start = ALIGN(mc->fb_end, four_gb); break; case AMDGPU_GART_PLACEMENT_BEST_FIT: default: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 06efce38f323..71272f40feef 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -873,68 +873,59 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) ? -EFAULT : 0; } case AMDGPU_INFO_READ_MMR_REG: { - int ret = 0; - unsigned int n, alloc_size; - uint32_t *regs; unsigned int se_num = (info->read_mmr_reg.instance >> AMDGPU_INFO_MMR_SE_INDEX_SHIFT) & AMDGPU_INFO_MMR_SE_INDEX_MASK; unsigned int sh_num = (info->read_mmr_reg.instance >> AMDGPU_INFO_MMR_SH_INDEX_SHIFT) & AMDGPU_INFO_MMR_SH_INDEX_MASK; - - if (!down_read_trylock(&adev->reset_domain->sem)) - return -ENOENT; + unsigned int alloc_size; + uint32_t *regs; + int ret; /* set full masks if the userspace set all bits * in the bitfields */ - if (se_num == AMDGPU_INFO_MMR_SE_INDEX_MASK) { + if (se_num == AMDGPU_INFO_MMR_SE_INDEX_MASK) se_num = 0xffffffff; - } else if (se_num >= AMDGPU_GFX_MAX_SE) { - ret = -EINVAL; - goto out; - } + else if (se_num >= AMDGPU_GFX_MAX_SE) + return -EINVAL; - if (sh_num == AMDGPU_INFO_MMR_SH_INDEX_MASK) { + if (sh_num == AMDGPU_INFO_MMR_SH_INDEX_MASK) sh_num = 0xffffffff; - } else if (sh_num >= AMDGPU_GFX_MAX_SH_PER_SE) { - ret = -EINVAL; - goto out; - } + else if (sh_num >= AMDGPU_GFX_MAX_SH_PER_SE) + return -EINVAL; - if (info->read_mmr_reg.count > 128) { - ret = -EINVAL; - goto out; - } + if (info->read_mmr_reg.count > 128) + return -EINVAL; - regs = kmalloc_array(info->read_mmr_reg.count, sizeof(*regs), GFP_KERNEL); - if (!regs) { - ret = -ENOMEM; - goto out; - } + regs = kmalloc_array(info->read_mmr_reg.count, sizeof(*regs), + GFP_KERNEL); + if (!regs) + return -ENOMEM; + down_read(&adev->reset_domain->sem); alloc_size = info->read_mmr_reg.count * sizeof(*regs); - amdgpu_gfx_off_ctrl(adev, false); + ret = 0; for (i = 0; i < info->read_mmr_reg.count; i++) { if (amdgpu_asic_read_register(adev, se_num, sh_num, info->read_mmr_reg.dword_offset + i, ®s[i])) { DRM_DEBUG_KMS("unallowed offset %#x\n", info->read_mmr_reg.dword_offset + i); - kfree(regs); - amdgpu_gfx_off_ctrl(adev, true); ret = -EFAULT; - goto out; + break; } } amdgpu_gfx_off_ctrl(adev, true); - n = copy_to_user(out, regs, min(size, alloc_size)); - kfree(regs); - ret = (n ? -EFAULT : 0); -out: up_read(&adev->reset_domain->sem); + + if (!ret) { + ret = copy_to_user(out, regs, min(size, alloc_size)) + ? -EFAULT : 0; + } + kfree(regs); return ret; } case AMDGPU_INFO_DEV_INFO: { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c index cdf4909592d2..0c57fe259894 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c @@ -1950,7 +1950,7 @@ void amdgpu_ras_check_bad_page_status(struct amdgpu_device *adev) if (!control || amdgpu_bad_page_threshold == 0) return; - if (control->ras_num_bad_pages >= ras->bad_page_cnt_threshold) { + if (control->ras_num_bad_pages > ras->bad_page_cnt_threshold) { if (amdgpu_dpm_send_rma_reason(adev)) dev_warn(adev->dev, "Unable to send out-of-band RMA CPER"); else diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 0dc68fb9d88e..3d2e00efc741 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -75,6 +75,9 @@ static int amdgpu_ttm_init_on_chip(struct amdgpu_device *adev, unsigned int type, uint64_t size_in_page) { + if (!size_in_page) + return 0; + return ttm_range_man_init(&adev->mman.bdev, type, false, size_in_page); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c index d5abf785ca17..de140a8ed135 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c @@ -205,6 +205,19 @@ void amdgpu_userq_start_hang_detect_work(struct amdgpu_usermode_queue *queue) msecs_to_jiffies(timeout_ms)); } +void amdgpu_userq_process_fence_irq(struct amdgpu_device *adev, u32 doorbell) +{ + struct xarray *xa = &adev->userq_doorbell_xa; + struct amdgpu_usermode_queue *queue; + unsigned long flags; + + xa_lock_irqsave(xa, flags); + queue = xa_load(xa, doorbell); + if (queue) + amdgpu_userq_fence_driver_process(queue->fence_drv); + xa_unlock_irqrestore(xa, flags); +} + static void amdgpu_userq_init_hang_detect_work(struct amdgpu_usermode_queue *queue) { INIT_DELAYED_WORK(&queue->hang_detect_work, amdgpu_userq_hang_detect_work); @@ -643,12 +656,6 @@ amdgpu_userq_destroy(struct amdgpu_userq_mgr *uq_mgr, struct amdgpu_usermode_que #endif amdgpu_userq_detect_and_reset_queues(uq_mgr); r = amdgpu_userq_unmap_helper(queue); - /*TODO: It requires a reset for userq hw unmap error*/ - if (r) { - drm_warn(adev_to_drm(uq_mgr->adev), "trying to destroy a HW mapping userq\n"); - queue->state = AMDGPU_USERQ_STATE_HUNG; - } - atomic_dec(&uq_mgr->userq_count[queue->queue_type]); amdgpu_userq_cleanup(queue); mutex_unlock(&uq_mgr->userq_mutex); @@ -1187,7 +1194,7 @@ retry_lock: bo = range->bo; ret = amdgpu_ttm_tt_get_user_pages(bo, range); if (ret) - goto unlock_all; + goto free_ranges; } invalidated = true; @@ -1214,6 +1221,7 @@ retry_lock: unlock_all: drm_exec_fini(&exec); +free_ranges: xa_for_each(&xa, tmp_key, range) { if (!range) continue; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h index 675fe6395ac8..8b8f345b60b6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h @@ -156,6 +156,7 @@ void amdgpu_userq_reset_work(struct work_struct *work); void amdgpu_userq_pre_reset(struct amdgpu_device *adev); int amdgpu_userq_post_reset(struct amdgpu_device *adev, bool vram_lost); void amdgpu_userq_start_hang_detect_work(struct amdgpu_usermode_queue *queue); +void amdgpu_userq_process_fence_irq(struct amdgpu_device *adev, u32 doorbell); int amdgpu_userq_input_va_validate(struct amdgpu_device *adev, struct amdgpu_usermode_queue *queue, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c index da39ac862f37..e2d5f04296e1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c @@ -32,29 +32,9 @@ #include "amdgpu.h" #include "amdgpu_userq_fence.h" -static const struct dma_fence_ops amdgpu_userq_fence_ops; -static struct kmem_cache *amdgpu_userq_fence_slab; - #define AMDGPU_USERQ_MAX_HANDLES (1U << 16) -int amdgpu_userq_fence_slab_init(void) -{ - amdgpu_userq_fence_slab = kmem_cache_create("amdgpu_userq_fence", - sizeof(struct amdgpu_userq_fence), - 0, - SLAB_HWCACHE_ALIGN, - NULL); - if (!amdgpu_userq_fence_slab) - return -ENOMEM; - - return 0; -} - -void amdgpu_userq_fence_slab_fini(void) -{ - rcu_barrier(); - kmem_cache_destroy(amdgpu_userq_fence_slab); -} +static const struct dma_fence_ops amdgpu_userq_fence_ops; static inline struct amdgpu_userq_fence *to_amdgpu_userq_fence(struct dma_fence *f) { @@ -231,7 +211,7 @@ void amdgpu_userq_fence_driver_put(struct amdgpu_userq_fence_driver *fence_drv) static int amdgpu_userq_fence_alloc(struct amdgpu_userq_fence **userq_fence) { - *userq_fence = kmem_cache_alloc(amdgpu_userq_fence_slab, GFP_ATOMIC); + *userq_fence = kmalloc(sizeof(**userq_fence), GFP_KERNEL); return *userq_fence ? 0 : -ENOMEM; } @@ -342,7 +322,7 @@ static void amdgpu_userq_fence_free(struct rcu_head *rcu) amdgpu_userq_fence_driver_put(fence_drv); kvfree(userq_fence->fence_drv_array); - kmem_cache_free(amdgpu_userq_fence_slab, userq_fence); + kfree(userq_fence); } static void amdgpu_userq_fence_release(struct dma_fence *f) @@ -545,7 +525,7 @@ int amdgpu_userq_signal_ioctl(struct drm_device *dev, void *data, r = amdgpu_userq_fence_create(queue, userq_fence, wptr, &fence); if (r) { mutex_unlock(&userq_mgr->userq_mutex); - kmem_cache_free(amdgpu_userq_fence_slab, userq_fence); + kfree(userq_fence); goto put_gobj_write; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.h index d56246ad8c26..d355a0eecc07 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.h @@ -58,9 +58,6 @@ struct amdgpu_userq_fence_driver { char timeline_name[TASK_COMM_LEN]; }; -int amdgpu_userq_fence_slab_init(void); -void amdgpu_userq_fence_slab_fini(void); - void amdgpu_userq_fence_driver_get(struct amdgpu_userq_fence_driver *fence_drv); void amdgpu_userq_fence_driver_put(struct amdgpu_userq_fence_driver *fence_drv); int amdgpu_userq_fence_driver_alloc(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 115a7b269af3..9ba9de16a27a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -3023,11 +3023,22 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid, is_compute_context = vm->is_compute_context; - if (is_compute_context && !svm_range_restore_pages(adev, pasid, vmid, - node_id, addr >> PAGE_SHIFT, ts, write_fault)) { + if (is_compute_context) { + /* Unreserve root since svm_range_restore_pages might try to reserve it. */ + /* TODO: rework svm_range_restore_pages so that this isn't necessary. */ amdgpu_bo_unreserve(root); + + if (!svm_range_restore_pages(adev, pasid, vmid, + node_id, addr >> PAGE_SHIFT, ts, write_fault)) { + amdgpu_bo_unref(&root); + return true; + } amdgpu_bo_unref(&root); - return true; + + /* Re-acquire the VM lock, could be that the VM was freed in between. */ + vm = amdgpu_vm_lock_by_pasid(adev, &root, pasid); + if (!vm) + return false; } addr /= AMDGPU_GPU_PAGE_SIZE; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index 8c82e90f871b..d40ab1e95480 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -6523,15 +6523,7 @@ static int gfx_v11_0_eop_irq(struct amdgpu_device *adev, DRM_DEBUG("IH: CP EOP\n"); if (adev->enable_mes && doorbell_offset) { - struct amdgpu_usermode_queue *queue; - struct xarray *xa = &adev->userq_doorbell_xa; - unsigned long flags; - - xa_lock_irqsave(xa, flags); - queue = xa_load(xa, doorbell_offset); - if (queue) - amdgpu_userq_fence_driver_process(queue->fence_drv); - xa_unlock_irqrestore(xa, flags); + amdgpu_userq_process_fence_irq(adev, doorbell_offset); } else { me_id = (entry->ring_id & 0x0c) >> 2; pipe_id = (entry->ring_id & 0x03) >> 0; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c index 65c33823a688..0e0b1e5b88fc 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c @@ -4854,15 +4854,7 @@ static int gfx_v12_0_eop_irq(struct amdgpu_device *adev, DRM_DEBUG("IH: CP EOP\n"); if (adev->enable_mes && doorbell_offset) { - struct xarray *xa = &adev->userq_doorbell_xa; - struct amdgpu_usermode_queue *queue; - unsigned long flags; - - xa_lock_irqsave(xa, flags); - queue = xa_load(xa, doorbell_offset); - if (queue) - amdgpu_userq_fence_driver_process(queue->fence_drv); - xa_unlock_irqrestore(xa, flags); + amdgpu_userq_process_fence_irq(adev, doorbell_offset); } else { me_id = (entry->ring_id & 0x0c) >> 2; pipe_id = (entry->ring_id & 0x03) >> 0; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c index 68fd3c04134d..68db1bc73bc7 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c @@ -3643,16 +3643,7 @@ static int gfx_v12_1_eop_irq(struct amdgpu_device *adev, DRM_DEBUG("IH: CP EOP\n"); if (adev->enable_mes && doorbell_offset) { - struct xarray *xa = &adev->userq_doorbell_xa; - struct amdgpu_usermode_queue *queue; - unsigned long flags; - - xa_lock_irqsave(xa, flags); - queue = xa_load(xa, doorbell_offset); - if (queue) - amdgpu_userq_fence_driver_process(queue->fence_drv); - - xa_unlock_irqrestore(xa, flags); + amdgpu_userq_process_fence_irq(adev, doorbell_offset); } else { me_id = (entry->ring_id & 0x0c) >> 2; pipe_id = (entry->ring_id & 0x03) >> 0; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c index 73223d97a87f..ac90d8e9d86a 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c @@ -1571,6 +1571,71 @@ static void gfx_v6_0_setup_spi(struct amdgpu_device *adev) mutex_unlock(&adev->grbm_idx_mutex); } +/** + * gfx_v6_0_setup_tcc() - setup which TCCs are used + * + * @adev: amdgpu_device pointer + * + * Verify whether the current GPU has any TCCs disabled, + * which can happen when the GPU is harvested and some + * memory channels are disabled, reducing the memory bus width. + * For example, on the Radeon HD 7870 XT (Tahiti LE). + * + * If some TCCs are disabled, we need to make sure that + * the disabled TCCs are not used, and the remaining TCCs + * are used optimally. + * + * TCP_CHAN_STEER_LO/HI control which TCC is used by TCP channels. + * TCP_ADDR_CONFIG.NUM_TCC_BANKS controls how many channels are used. + * + * For optimal performance: + * - Rely on the CHAN_STEER from the golden registers table, + * only skip disabled TCCs but keep the mapping order. + * - Limit NUM_TCC_BANKS to number of active TCCs to avoid thrashing, + * which performs better than using the same TCC twice. + */ +static void gfx_v6_0_setup_tcc(struct amdgpu_device *adev) +{ + u32 i, tcc, tcp_addr_config, num_active_tcc = 0; + u64 chan_steer, patched_chan_steer = 0; + const u32 num_max_tcc = adev->gfx.config.max_texture_channel_caches; + const u32 dis_tcc_mask = + amdgpu_gfx_create_bitmask(num_max_tcc) & + (REG_GET_FIELD(RREG32(mmCGTS_TCC_DISABLE), + CGTS_TCC_DISABLE, TCC_DISABLE) | + REG_GET_FIELD(RREG32(mmCGTS_USER_TCC_DISABLE), + CGTS_USER_TCC_DISABLE, TCC_DISABLE)); + + /* When no TCC is disabled, the golden registers table already has optimal TCC setup */ + if (!dis_tcc_mask) + return; + + /* Each 4-bit nibble contains the index of a TCC used by all TCPs */ + chan_steer = RREG32(mmTCP_CHAN_STEER_LO) | ((u64)RREG32(mmTCP_CHAN_STEER_HI) << 32ull); + + /* Patch the TCP to TCC mapping to skip disabled TCCs */ + for (i = 0; i < num_max_tcc; ++i) { + tcc = (chan_steer >> (u64)(4 * i)) & 0xf; + + if (!((1 << tcc) & dis_tcc_mask)) { + /* Copy enabled TCC indices to the patched register value. */ + patched_chan_steer |= (u64)tcc << (u64)(4 * num_active_tcc); + ++num_active_tcc; + } + } + + WARN_ON(num_active_tcc != num_max_tcc - hweight32(dis_tcc_mask)); + + /* Patch number of TCCs used by TCPs */ + tcp_addr_config = REG_SET_FIELD(RREG32(mmTCP_ADDR_CONFIG), + TCP_ADDR_CONFIG, NUM_TCC_BANKS, + num_active_tcc - 1); + + WREG32(mmTCP_ADDR_CONFIG, tcp_addr_config); + WREG32(mmTCP_CHAN_STEER_HI, upper_32_bits(patched_chan_steer)); + WREG32(mmTCP_CHAN_STEER_LO, lower_32_bits(patched_chan_steer)); +} + static void gfx_v6_0_config_init(struct amdgpu_device *adev) { adev->gfx.config.double_offchip_lds_buf = 0; @@ -1729,6 +1794,7 @@ static void gfx_v6_0_constants_init(struct amdgpu_device *adev) gfx_v6_0_tiling_mode_table_init(adev); gfx_v6_0_setup_rb(adev); + gfx_v6_0_setup_tcc(adev); gfx_v6_0_setup_spi(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 95be105671ec..86c7c2a429b7 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -5660,9 +5660,6 @@ static void gfx_v9_0_ring_emit_fence_kiq(struct amdgpu_ring *ring, u64 addr, { struct amdgpu_device *adev = ring->adev; - /* we only allocate 32bit for each seq wb address */ - BUG_ON(flags & AMDGPU_FENCE_FLAG_64BIT); - /* write fence seq to the "addr" */ amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3)); amdgpu_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) | diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c index 9fe8d10ab270..cffb1e6bab35 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c @@ -802,6 +802,7 @@ static const struct amd_ip_funcs jpeg_v2_0_ip_funcs = { static const struct amdgpu_ring_funcs jpeg_v2_0_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_JPEG, .align_mask = 0xf, + .no_user_fence = true, .get_rptr = jpeg_v2_0_dec_ring_get_rptr, .get_wptr = jpeg_v2_0_dec_ring_get_wptr, .set_wptr = jpeg_v2_0_dec_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c index 20983f126b49..13a6e24c624a 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c @@ -693,6 +693,7 @@ static const struct amd_ip_funcs jpeg_v2_6_ip_funcs = { static const struct amdgpu_ring_funcs jpeg_v2_5_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_JPEG, .align_mask = 0xf, + .no_user_fence = true, .get_rptr = jpeg_v2_5_dec_ring_get_rptr, .get_wptr = jpeg_v2_5_dec_ring_get_wptr, .set_wptr = jpeg_v2_5_dec_ring_set_wptr, @@ -724,6 +725,7 @@ static const struct amdgpu_ring_funcs jpeg_v2_5_dec_ring_vm_funcs = { static const struct amdgpu_ring_funcs jpeg_v2_6_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_JPEG, .align_mask = 0xf, + .no_user_fence = true, .get_rptr = jpeg_v2_5_dec_ring_get_rptr, .get_wptr = jpeg_v2_5_dec_ring_get_wptr, .set_wptr = jpeg_v2_5_dec_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c index 98f5e0622bc5..d0445df39d2c 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c @@ -594,6 +594,7 @@ static const struct amd_ip_funcs jpeg_v3_0_ip_funcs = { static const struct amdgpu_ring_funcs jpeg_v3_0_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_JPEG, .align_mask = 0xf, + .no_user_fence = true, .get_rptr = jpeg_v3_0_dec_ring_get_rptr, .get_wptr = jpeg_v3_0_dec_ring_get_wptr, .set_wptr = jpeg_v3_0_dec_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c index 0bd83820dd20..6fd4238a8471 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c @@ -759,6 +759,7 @@ static const struct amd_ip_funcs jpeg_v4_0_ip_funcs = { static const struct amdgpu_ring_funcs jpeg_v4_0_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_JPEG, .align_mask = 0xf, + .no_user_fence = true, .get_rptr = jpeg_v4_0_dec_ring_get_rptr, .get_wptr = jpeg_v4_0_dec_ring_get_wptr, .set_wptr = jpeg_v4_0_dec_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c index 82abe181c730..0c746580de11 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c @@ -1219,6 +1219,7 @@ static const struct amd_ip_funcs jpeg_v4_0_3_ip_funcs = { static const struct amdgpu_ring_funcs jpeg_v4_0_3_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_JPEG, .align_mask = 0xf, + .no_user_fence = true, .get_rptr = jpeg_v4_0_3_dec_ring_get_rptr, .get_wptr = jpeg_v4_0_3_dec_ring_get_wptr, .set_wptr = jpeg_v4_0_3_dec_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c index 54fd9c800c40..a43582b9c876 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c @@ -804,6 +804,7 @@ static const struct amd_ip_funcs jpeg_v4_0_5_ip_funcs = { static const struct amdgpu_ring_funcs jpeg_v4_0_5_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_JPEG, .align_mask = 0xf, + .no_user_fence = true, .get_rptr = jpeg_v4_0_5_dec_ring_get_rptr, .get_wptr = jpeg_v4_0_5_dec_ring_get_wptr, .set_wptr = jpeg_v4_0_5_dec_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c index 46bf15dce2bd..72a4b2d0676f 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c @@ -680,6 +680,7 @@ static const struct amd_ip_funcs jpeg_v5_0_0_ip_funcs = { static const struct amdgpu_ring_funcs jpeg_v5_0_0_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_JPEG, .align_mask = 0xf, + .no_user_fence = true, .get_rptr = jpeg_v5_0_0_dec_ring_get_rptr, .get_wptr = jpeg_v5_0_0_dec_ring_get_wptr, .set_wptr = jpeg_v5_0_0_dec_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c index edecbfe66c79..250316704dfa 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c @@ -884,6 +884,7 @@ static const struct amd_ip_funcs jpeg_v5_0_1_ip_funcs = { static const struct amdgpu_ring_funcs jpeg_v5_0_1_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_JPEG, .align_mask = 0xf, + .no_user_fence = true, .get_rptr = jpeg_v5_0_1_dec_ring_get_rptr, .get_wptr = jpeg_v5_0_1_dec_ring_get_wptr, .set_wptr = jpeg_v5_0_1_dec_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_2.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_2.c index 285c459379c4..7a4ecea6b39a 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_2.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_2.c @@ -703,6 +703,7 @@ static const struct amd_ip_funcs jpeg_v5_0_2_ip_funcs = { static const struct amdgpu_ring_funcs jpeg_v5_0_2_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_JPEG, .align_mask = 0xf, + .no_user_fence = true, .get_rptr = jpeg_v5_0_2_dec_ring_get_rptr, .get_wptr = jpeg_v5_0_2_dec_ring_get_wptr, .set_wptr = jpeg_v5_0_2_dec_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_3_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_3_0.c index 1821dced936f..e7546816baba 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_3_0.c @@ -661,6 +661,7 @@ static const struct amd_ip_funcs jpeg_v5_3_0_ip_funcs = { static const struct amdgpu_ring_funcs jpeg_v5_3_0_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_JPEG, .align_mask = 0xf, + .no_user_fence = true, .get_rptr = jpeg_v5_3_0_dec_ring_get_rptr, .get_wptr = jpeg_v5_3_0_dec_ring_get_wptr, .set_wptr = jpeg_v5_3_0_dec_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c b/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c index 2fc39a6938f6..5b4121ddc78c 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c @@ -31,89 +31,68 @@ #define AMDGPU_USERQ_GANG_CTX_SZ PAGE_SIZE static int -mes_userq_map_gtt_bo_to_gart(struct amdgpu_bo *bo) -{ - int ret; - - ret = amdgpu_bo_reserve(bo, true); - if (ret) { - DRM_ERROR("Failed to reserve bo. ret %d\n", ret); - goto err_reserve_bo_failed; - } - - ret = amdgpu_ttm_alloc_gart(&bo->tbo); - if (ret) { - DRM_ERROR("Failed to bind bo to GART. ret %d\n", ret); - goto err_map_bo_gart_failed; - } - - amdgpu_bo_unreserve(bo); - bo = amdgpu_bo_ref(bo); - - return 0; - -err_map_bo_gart_failed: - amdgpu_bo_unreserve(bo); -err_reserve_bo_failed: - return ret; -} - -static int mes_userq_create_wptr_mapping(struct amdgpu_device *adev, struct amdgpu_userq_mgr *uq_mgr, struct amdgpu_usermode_queue *queue, uint64_t wptr) { struct amdgpu_bo_va_mapping *wptr_mapping; - struct amdgpu_vm *wptr_vm; struct amdgpu_userq_obj *wptr_obj = &queue->wptr_obj; + struct amdgpu_bo *obj; + struct amdgpu_vm *vm = queue->vm; + struct drm_exec exec; int ret; - wptr_vm = queue->vm; - ret = amdgpu_bo_reserve(wptr_vm->root.bo, false); - if (ret) - return ret; - wptr &= AMDGPU_GMC_HOLE_MASK; - wptr_mapping = amdgpu_vm_bo_lookup_mapping(wptr_vm, wptr >> PAGE_SHIFT); - amdgpu_bo_unreserve(wptr_vm->root.bo); - if (!wptr_mapping) { - DRM_ERROR("Failed to lookup wptr bo\n"); - return -EINVAL; - } - wptr_obj->obj = wptr_mapping->bo_va->base.bo; - if (wptr_obj->obj->tbo.base.size > PAGE_SIZE) { - DRM_ERROR("Requested GART mapping for wptr bo larger than one page\n"); - return -EINVAL; - } + drm_exec_init(&exec, DRM_EXEC_IGNORE_DUPLICATES, 2); + drm_exec_until_all_locked(&exec) { + ret = amdgpu_vm_lock_pd(vm, &exec, 1); + drm_exec_retry_on_contention(&exec); + if (unlikely(ret)) + goto fail_lock; + + wptr_mapping = amdgpu_vm_bo_lookup_mapping(vm, wptr >> PAGE_SHIFT); + if (!wptr_mapping) { + ret = -EINVAL; + goto fail_lock; + } - ret = mes_userq_map_gtt_bo_to_gart(wptr_obj->obj); - if (ret) { - DRM_ERROR("Failed to map wptr bo to GART\n"); - return ret; + obj = wptr_mapping->bo_va->base.bo; + ret = drm_exec_lock_obj(&exec, &obj->tbo.base); + drm_exec_retry_on_contention(&exec); + if (unlikely(ret)) + goto fail_lock; } - ret = amdgpu_bo_reserve(wptr_obj->obj, true); - if (ret) { - DRM_ERROR("Failed to reserve wptr bo\n"); - return ret; + wptr_obj->obj = amdgpu_bo_ref(wptr_mapping->bo_va->base.bo); + if (wptr_obj->obj->tbo.base.size > PAGE_SIZE) { + ret = -EINVAL; + goto fail_map; } /* TODO use eviction fence instead of pinning. */ ret = amdgpu_bo_pin(wptr_obj->obj, AMDGPU_GEM_DOMAIN_GTT); if (ret) { - drm_file_err(uq_mgr->file, "[Usermode queues] Failed to pin wptr bo\n"); - goto unresv_bo; + DRM_ERROR("Failed to pin wptr bo. ret %d\n", ret); + goto fail_map; + } + + ret = amdgpu_ttm_alloc_gart(&wptr_obj->obj->tbo); + if (ret) { + DRM_ERROR("Failed to bind bo to GART. ret %d\n", ret); + goto fail_map; } queue->wptr_obj.gpu_addr = amdgpu_bo_gpu_offset(wptr_obj->obj); - amdgpu_bo_unreserve(wptr_obj->obj); + drm_exec_fini(&exec); return 0; -unresv_bo: - amdgpu_bo_unreserve(wptr_obj->obj); +fail_map: + amdgpu_bo_unref(&wptr_obj->obj); +fail_lock: + drm_exec_fini(&exec); return ret; } diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index 44f0f23e1148..e64f2f6df9a9 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -889,7 +889,7 @@ static void sdma_v4_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 se /* write the fence */ amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_FENCE)); /* zero in first two bits */ - BUG_ON(addr & 0x3); + WARN_ON(addr & 0x3); amdgpu_ring_write(ring, lower_32_bits(addr)); amdgpu_ring_write(ring, upper_32_bits(addr)); amdgpu_ring_write(ring, lower_32_bits(seq)); @@ -899,7 +899,7 @@ static void sdma_v4_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 se addr += 4; amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_FENCE)); /* zero in first two bits */ - BUG_ON(addr & 0x3); + WARN_ON(addr & 0x3); amdgpu_ring_write(ring, lower_32_bits(addr)); amdgpu_ring_write(ring, upper_32_bits(addr)); amdgpu_ring_write(ring, upper_32_bits(seq)); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c index 0f530bb8a9a3..8ca46e1e474e 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c @@ -1662,17 +1662,8 @@ static int sdma_v6_0_process_fence_irq(struct amdgpu_device *adev, u32 doorbell_offset = entry->src_data[0]; if (adev->enable_mes && doorbell_offset) { - struct amdgpu_usermode_queue *queue; - struct xarray *xa = &adev->userq_doorbell_xa; - unsigned long flags; - doorbell_offset >>= SDMA0_QUEUE0_DOORBELL_OFFSET__OFFSET__SHIFT; - - xa_lock_irqsave(xa, flags); - queue = xa_load(xa, doorbell_offset); - if (queue) - amdgpu_userq_fence_driver_process(queue->fence_drv); - xa_unlock_irqrestore(xa, flags); + amdgpu_userq_process_fence_irq(adev, doorbell_offset); } return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c index 9ed817b69a3b..37191e2918d4 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c @@ -1594,17 +1594,8 @@ static int sdma_v7_0_process_fence_irq(struct amdgpu_device *adev, u32 doorbell_offset = entry->src_data[0]; if (adev->enable_mes && doorbell_offset) { - struct xarray *xa = &adev->userq_doorbell_xa; - struct amdgpu_usermode_queue *queue; - unsigned long flags; - doorbell_offset >>= SDMA0_QUEUE0_DOORBELL_OFFSET__OFFSET__SHIFT; - - xa_lock_irqsave(xa, flags); - queue = xa_load(xa, doorbell_offset); - if (queue) - amdgpu_userq_fence_driver_process(queue->fence_drv); - xa_unlock_irqrestore(xa, flags); + amdgpu_userq_process_fence_irq(adev, doorbell_offset); } return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c b/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c index fea576a7f397..efb3fde919ee 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c @@ -242,6 +242,10 @@ static void uvd_v3_1_mc_resume(struct amdgpu_device *adev) uint64_t addr; uint32_t size; + /* When the keyselect is already set, don't perturb it. */ + if (RREG32(mmUVD_FW_START)) + return; + /* program the VCPU memory controller bits 0-27 */ addr = (adev->uvd.inst->gpu_addr + AMDGPU_UVD_FIRMWARE_OFFSET) >> 3; size = AMDGPU_UVD_FIRMWARE_SIZE(adev) >> 3; @@ -284,6 +288,12 @@ static int uvd_v3_1_fw_validate(struct amdgpu_device *adev) int i; uint32_t keysel = adev->uvd.keyselect; + if (RREG32(mmUVD_FW_START) & UVD_FW_STATUS__PASS_MASK) { + dev_dbg(adev->dev, "UVD keyselect already set: 0x%x (on CPU: 0x%x)\n", + RREG32(mmUVD_FW_START), adev->uvd.keyselect); + return 0; + } + WREG32(mmUVD_FW_START, keysel); for (i = 0; i < 10; ++i) { diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c index e35fae9cdaf6..0442bfcfd384 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c @@ -2113,6 +2113,7 @@ static const struct amd_ip_funcs vcn_v2_0_ip_funcs = { static const struct amdgpu_ring_funcs vcn_v2_0_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_DEC, .align_mask = 0xf, + .no_user_fence = true, .secure_submission_supported = true, .get_rptr = vcn_v2_0_dec_ring_get_rptr, .get_wptr = vcn_v2_0_dec_ring_get_wptr, @@ -2145,6 +2146,7 @@ static const struct amdgpu_ring_funcs vcn_v2_0_enc_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_ENC, .align_mask = 0x3f, .nop = VCN_ENC_CMD_NO_OP, + .no_user_fence = true, .get_rptr = vcn_v2_0_enc_ring_get_rptr, .get_wptr = vcn_v2_0_enc_ring_get_wptr, .set_wptr = vcn_v2_0_enc_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c index 006a15451197..8b8184fe6764 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c @@ -1778,6 +1778,7 @@ static void vcn_v2_5_dec_ring_set_wptr(struct amdgpu_ring *ring) static const struct amdgpu_ring_funcs vcn_v2_5_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_DEC, .align_mask = 0xf, + .no_user_fence = true, .secure_submission_supported = true, .get_rptr = vcn_v2_5_dec_ring_get_rptr, .get_wptr = vcn_v2_5_dec_ring_get_wptr, @@ -1879,6 +1880,7 @@ static const struct amdgpu_ring_funcs vcn_v2_5_enc_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_ENC, .align_mask = 0x3f, .nop = VCN_ENC_CMD_NO_OP, + .no_user_fence = true, .get_rptr = vcn_v2_5_enc_ring_get_rptr, .get_wptr = vcn_v2_5_enc_ring_get_wptr, .set_wptr = vcn_v2_5_enc_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index 6fb4fcdbba4f..81bba3ec2a93 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -1856,6 +1856,7 @@ static const struct amdgpu_ring_funcs vcn_v3_0_dec_sw_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_DEC, .align_mask = 0x3f, .nop = VCN_DEC_SW_CMD_NO_OP, + .no_user_fence = true, .secure_submission_supported = true, .get_rptr = vcn_v3_0_dec_ring_get_rptr, .get_wptr = vcn_v3_0_dec_ring_get_wptr, @@ -1972,6 +1973,7 @@ static int vcn_v3_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job, for (i = 0, msg = &msg[6]; i < num_buffers; ++i, msg += 4) { uint32_t offset, size, *create; + uint64_t buf_end; if (msg[0] != RDECODE_MESSAGE_CREATE) continue; @@ -1979,7 +1981,8 @@ static int vcn_v3_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job, offset = msg[1]; size = msg[2]; - if (size < 4 || offset + size > end - addr) { + if (size < 4 || check_add_overflow(offset, size, &buf_end) || + buf_end > end - addr) { DRM_ERROR("VCN message buffer exceeds BO bounds!\n"); r = -EINVAL; goto out; @@ -2036,6 +2039,7 @@ static int vcn_v3_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, static const struct amdgpu_ring_funcs vcn_v3_0_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_DEC, .align_mask = 0xf, + .no_user_fence = true, .secure_submission_supported = true, .get_rptr = vcn_v3_0_dec_ring_get_rptr, .get_wptr = vcn_v3_0_dec_ring_get_wptr, @@ -2138,6 +2142,7 @@ static const struct amdgpu_ring_funcs vcn_v3_0_enc_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_ENC, .align_mask = 0x3f, .nop = VCN_ENC_CMD_NO_OP, + .no_user_fence = true, .get_rptr = vcn_v3_0_enc_ring_get_rptr, .get_wptr = vcn_v3_0_enc_ring_get_wptr, .set_wptr = vcn_v3_0_enc_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c index 5dec92691f73..ff7269bafae8 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c @@ -1889,6 +1889,7 @@ static int vcn_v4_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job, for (i = 0, msg = &msg[6]; i < num_buffers; ++i, msg += 4) { uint32_t offset, size, *create; + uint64_t buf_end; if (msg[0] != RDECODE_MESSAGE_CREATE) continue; @@ -1896,7 +1897,8 @@ static int vcn_v4_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job, offset = msg[1]; size = msg[2]; - if (size < 4 || offset + size > end - addr) { + if (size < 4 || check_add_overflow(offset, size, &buf_end) || + buf_end > end - addr) { DRM_ERROR("VCN message buffer exceeds BO bounds!\n"); r = -EINVAL; goto out; @@ -1994,6 +1996,7 @@ static struct amdgpu_ring_funcs vcn_v4_0_unified_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_ENC, .align_mask = 0x3f, .nop = VCN_ENC_CMD_NO_OP, + .no_user_fence = true, .extra_bytes = sizeof(struct amdgpu_vcn_rb_metadata), .get_rptr = vcn_v4_0_unified_ring_get_rptr, .get_wptr = vcn_v4_0_unified_ring_get_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c index ff3013b97abd..10e8fc2821f3 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c @@ -1775,6 +1775,7 @@ static const struct amdgpu_ring_funcs vcn_v4_0_3_unified_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_ENC, .align_mask = 0x3f, .nop = VCN_ENC_CMD_NO_OP, + .no_user_fence = true, .get_rptr = vcn_v4_0_3_unified_ring_get_rptr, .get_wptr = vcn_v4_0_3_unified_ring_get_wptr, .set_wptr = vcn_v4_0_3_unified_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c index 1f6a22983c0d..1571cc5a148c 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c @@ -1483,6 +1483,7 @@ static struct amdgpu_ring_funcs vcn_v4_0_5_unified_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_ENC, .align_mask = 0x3f, .nop = VCN_ENC_CMD_NO_OP, + .no_user_fence = true, .get_rptr = vcn_v4_0_5_unified_ring_get_rptr, .get_wptr = vcn_v4_0_5_unified_ring_get_wptr, .set_wptr = vcn_v4_0_5_unified_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c index 6109124f852e..d5f49fa33bee 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c @@ -1207,6 +1207,7 @@ static const struct amdgpu_ring_funcs vcn_v5_0_0_unified_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_ENC, .align_mask = 0x3f, .nop = VCN_ENC_CMD_NO_OP, + .no_user_fence = true, .get_rptr = vcn_v5_0_0_unified_ring_get_rptr, .get_wptr = vcn_v5_0_0_unified_ring_get_wptr, .set_wptr = vcn_v5_0_0_unified_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c index c28c6aff17aa..54fbf8d73ca6 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c @@ -1419,6 +1419,7 @@ static const struct amdgpu_ring_funcs vcn_v5_0_1_unified_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_ENC, .align_mask = 0x3f, .nop = VCN_ENC_CMD_NO_OP, + .no_user_fence = true, .get_rptr = vcn_v5_0_1_unified_ring_get_rptr, .get_wptr = vcn_v5_0_1_unified_ring_get_wptr, .set_wptr = vcn_v5_0_1_unified_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_2.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_2.c index c3d3cc023058..bbc172db91a1 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_2.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_2.c @@ -994,6 +994,7 @@ static const struct amdgpu_ring_funcs vcn_v5_0_2_unified_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_ENC, .align_mask = 0x3f, .nop = VCN_ENC_CMD_NO_OP, + .no_user_fence = true, .get_rptr = vcn_v5_0_2_unified_ring_get_rptr, .get_wptr = vcn_v5_0_2_unified_ring_get_wptr, .set_wptr = vcn_v5_0_2_unified_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 55ea5145a28a..f95bf6d95534 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -25,6 +25,7 @@ #include <linux/err.h> #include <linux/fs.h> #include <linux/file.h> +#include <linux/overflow.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/uaccess.h> @@ -1359,7 +1360,7 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep, peer_pdd = kfd_process_device_data_by_id(p, devices_arr[i]); if (WARN_ON_ONCE(!peer_pdd)) continue; - kfd_flush_tlb(peer_pdd, TLB_FLUSH_LEGACY); + kfd_flush_tlb(peer_pdd); } kfree(devices_arr); @@ -1454,7 +1455,7 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep, if (WARN_ON_ONCE(!peer_pdd)) continue; if (flush_tlb) - kfd_flush_tlb(peer_pdd, TLB_FLUSH_HEAVYWEIGHT); + kfd_flush_tlb(peer_pdd); /* Remove dma mapping after tlb flush to avoid IO_PAGE_FAULT */ err = amdgpu_amdkfd_gpuvm_dmaunmap_mem(mem, peer_pdd->drm_priv); @@ -1695,6 +1696,16 @@ static int kfd_ioctl_smi_events(struct file *filep, return kfd_smi_event_open(pdd->dev, &args->anon_fd); } +static int kfd_ioctl_svm_validate(void *kdata, unsigned int usize) +{ + struct kfd_ioctl_svm_args *args = kdata; + size_t expected = struct_size(args, attrs, args->nattr); + + if (expected == SIZE_MAX || usize < expected) + return -EINVAL; + return 0; +} + #if IS_ENABLED(CONFIG_HSA_AMD_SVM) static int kfd_ioctl_set_xnack_mode(struct file *filep, @@ -3209,7 +3220,11 @@ static int kfd_ioctl_create_process(struct file *filep, struct kfd_process *p, v #define AMDKFD_IOCTL_DEF(ioctl, _func, _flags) \ [_IOC_NR(ioctl)] = {.cmd = ioctl, .func = _func, .flags = _flags, \ - .cmd_drv = 0, .name = #ioctl} + .validate = NULL, .cmd_drv = 0, .name = #ioctl} + +#define AMDKFD_IOCTL_DEF_V(ioctl, _func, _validate, _flags) \ + [_IOC_NR(ioctl)] = {.cmd = ioctl, .func = _func, .flags = _flags, \ + .validate = _validate, .cmd_drv = 0, .name = #ioctl} /** Ioctl table */ static const struct amdkfd_ioctl_desc amdkfd_ioctls[] = { @@ -3306,7 +3321,8 @@ static const struct amdkfd_ioctl_desc amdkfd_ioctls[] = { AMDKFD_IOCTL_DEF(AMDKFD_IOC_SMI_EVENTS, kfd_ioctl_smi_events, 0), - AMDKFD_IOCTL_DEF(AMDKFD_IOC_SVM, kfd_ioctl_svm, 0), + AMDKFD_IOCTL_DEF_V(AMDKFD_IOC_SVM, kfd_ioctl_svm, + kfd_ioctl_svm_validate, 0), AMDKFD_IOCTL_DEF(AMDKFD_IOC_SET_XNACK_MODE, kfd_ioctl_set_xnack_mode, 0), @@ -3431,6 +3447,12 @@ static long kfd_ioctl(struct file *filep, unsigned int cmd, unsigned long arg) memset(kdata, 0, usize); } + if (ioctl->validate) { + retcode = ioctl->validate(kdata, usize); + if (retcode) + goto err_i1; + } + retcode = func(filep, process, kdata); if (cmd & IOC_OUT) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 8ff97bf7d95a..b7f8f7ff8198 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -1737,37 +1737,6 @@ bool kgd2kfd_vmfault_fast_path(struct amdgpu_device *adev, struct amdgpu_iv_entr return false; } -/* check if there is kfd process still uses adev */ -static bool kgd2kfd_check_device_idle(struct amdgpu_device *adev) -{ - struct kfd_process *p; - struct hlist_node *p_temp; - unsigned int temp; - struct kfd_node *dev; - - mutex_lock(&kfd_processes_mutex); - - if (hash_empty(kfd_processes_table)) { - mutex_unlock(&kfd_processes_mutex); - return true; - } - - /* check if there is device still use adev */ - hash_for_each_safe(kfd_processes_table, temp, p_temp, p, kfd_processes) { - for (int i = 0; i < p->n_pdds; i++) { - dev = p->pdds[i]->dev; - if (dev->adev == adev) { - mutex_unlock(&kfd_processes_mutex); - return false; - } - } - } - - mutex_unlock(&kfd_processes_mutex); - - return true; -} - /** kgd2kfd_teardown_processes - gracefully tear down existing * kfd processes that use adev * @@ -1800,7 +1769,7 @@ void kgd2kfd_teardown_processes(struct amdgpu_device *adev) mutex_unlock(&kfd_processes_mutex); /* wait all kfd processes use adev terminate */ - while (!kgd2kfd_check_device_idle(adev)) + while (!!atomic_read(&adev->kfd.dev->kfd_processes_count)) cond_resched(); } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index ab3b2e7be9bd..9185ebe4c079 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -572,7 +572,7 @@ static int allocate_vmid(struct device_queue_manager *dqm, qpd->vmid, qpd->page_table_base); /* invalidate the VM context after pasid and vmid mapping is set up */ - kfd_flush_tlb(qpd_to_pdd(qpd), TLB_FLUSH_LEGACY); + kfd_flush_tlb(qpd_to_pdd(qpd)); if (dqm->dev->kfd2kgd->set_scratch_backing_va) dqm->dev->kfd2kgd->set_scratch_backing_va(dqm->dev->adev, @@ -610,7 +610,7 @@ static void deallocate_vmid(struct device_queue_manager *dqm, if (flush_texture_cache_nocpsch(q->device, qpd)) dev_err(dev, "Failed to flush TC\n"); - kfd_flush_tlb(qpd_to_pdd(qpd), TLB_FLUSH_LEGACY); + kfd_flush_tlb(qpd_to_pdd(qpd)); /* Release the vmid mapping */ set_pasid_vmid_mapping(dqm, 0, qpd->vmid); @@ -1284,7 +1284,7 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm, dqm->dev->adev, qpd->vmid, qpd->page_table_base); - kfd_flush_tlb(pdd, TLB_FLUSH_LEGACY); + kfd_flush_tlb(pdd); } /* Take a safe reference to the mm_struct, which may otherwise diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 6e333bfa17d6..7b5b12206919 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -1047,10 +1047,13 @@ extern struct srcu_struct kfd_processes_srcu; typedef int amdkfd_ioctl_t(struct file *filep, struct kfd_process *p, void *data); +typedef int amdkfd_ioctl_validate_t(void *kdata, unsigned int usize); + struct amdkfd_ioctl_desc { unsigned int cmd; int flags; amdkfd_ioctl_t *func; + amdkfd_ioctl_validate_t *validate; unsigned int cmd_drv; const char *name; }; @@ -1551,13 +1554,13 @@ void kfd_signal_reset_event(struct kfd_node *dev); void kfd_signal_poison_consumed_event(struct kfd_node *dev, u32 pasid); void kfd_signal_process_terminate_event(struct kfd_process *p); -static inline void kfd_flush_tlb(struct kfd_process_device *pdd, - enum TLB_FLUSH_TYPE type) +static inline void kfd_flush_tlb(struct kfd_process_device *pdd) { struct amdgpu_device *adev = pdd->dev->adev; struct amdgpu_vm *vm = drm_priv_to_vm(pdd->drm_priv); - amdgpu_vm_flush_compute_tlb(adev, vm, type, pdd->dev->xcc_mask); + amdgpu_vm_flush_compute_tlb(adev, vm, TLB_FLUSH_HEAVYWEIGHT, + pdd->dev->xcc_mask); } static inline bool kfd_flush_tlb_after_unmap(struct kfd_dev *dev) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index b120fdb0ef77..35ec67d9739b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -1366,6 +1366,12 @@ svm_range_unmap_from_gpu(struct amdgpu_device *adev, struct amdgpu_vm *vm, pr_debug("CPU[0x%llx 0x%llx] -> GPU[0x%llx 0x%llx]\n", start, last, gpu_start, gpu_end); + + if (!amdgpu_vm_ready(vm)) { + pr_debug("VM not ready, canceling unmap\n"); + return -EINVAL; + } + return amdgpu_vm_update_range(adev, vm, false, true, true, false, NULL, gpu_start, gpu_end, init_pte_value, 0, 0, NULL, NULL, fence); @@ -1418,7 +1424,7 @@ svm_range_unmap_from_gpus(struct svm_range *prange, unsigned long start, if (r) break; } - kfd_flush_tlb(pdd, TLB_FLUSH_HEAVYWEIGHT); + kfd_flush_tlb(pdd); } return r; @@ -1443,6 +1449,11 @@ svm_range_map_to_gpu(struct kfd_process_device *pdd, struct svm_range *prange, pr_debug("svms 0x%p [0x%lx 0x%lx] readonly %d\n", prange->svms, last_start, last_start + npages - 1, readonly); + if (!amdgpu_vm_ready(vm)) { + pr_debug("VM not ready, canceling map\n"); + return -EINVAL; + } + for (i = offset; i < offset + npages; i++) { uint64_t gpu_start; uint64_t gpu_end; @@ -1560,7 +1571,7 @@ svm_range_map_to_gpus(struct svm_range *prange, unsigned long offset, } } - kfd_flush_tlb(pdd, TLB_FLUSH_LEGACY); + kfd_flush_tlb(pdd); } return r; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index e96a12ff2d31..5fc5d5608506 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1903,7 +1903,11 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) goto error; } - init_data.asic_id.chip_family = adev->family; + /* special handling for early revisions of GC 11.5.4 */ + if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(11, 5, 4)) + init_data.asic_id.chip_family = AMDGPU_FAMILY_GC_11_5_4; + else + init_data.asic_id.chip_family = adev->family; init_data.asic_id.pci_revision_id = adev->pdev->revision; init_data.asic_id.hw_internal_rev = adev->external_rev_id; @@ -9404,9 +9408,21 @@ static void manage_dm_interrupts(struct amdgpu_device *adev, if (acrtc_state) { timing = &acrtc_state->stream->timing; - if (amdgpu_ip_version(adev, DCE_HWIP, 0) < - IP_VERSION(3, 5, 0) || - !(adev->flags & AMD_IS_APU)) { + if (amdgpu_ip_version(adev, DCE_HWIP, 0) >= + IP_VERSION(3, 2, 0) && + !(adev->flags & AMD_IS_APU)) { + /* + * DGPUs NV3x and newer that support idle optimizations + * experience intermittent flip-done timeouts on cursor + * updates. Restore 5s offdelay behavior for now. + * + * Discussion on the issue: + * https://lore.kernel.org/amd-gfx/20260217191632.1243826-1-sysdadmin@m1k.cloud/ + */ + config.offdelay_ms = 5000; + config.disable_immediate = false; + } else if (amdgpu_ip_version(adev, DCE_HWIP, 0) < + IP_VERSION(3, 5, 0)) { /* * Older HW and DGPU have issues with instant off; * use a 2 frame offdelay. diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index 3b8ae7798a93..a3cb05490dc9 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -1032,6 +1032,45 @@ dm_helpers_read_acpi_edid(struct amdgpu_dm_connector *aconnector) return drm_edid_read_custom(connector, dm_helpers_probe_acpi_edid, connector); } +static const struct drm_edid * +dm_helpers_read_vbios_hardcoded_edid(struct dc_link *link, struct amdgpu_dm_connector *aconnector) +{ + struct dc_bios *bios = link->ctx->dc_bios; + struct embedded_panel_info info; + const struct drm_edid *edid; + enum bp_result r; + + if (!dc_is_embedded_signal(link->connector_signal) || + !bios->funcs->get_embedded_panel_info) + return NULL; + + memset(&info, 0, sizeof(info)); + r = bios->funcs->get_embedded_panel_info(bios, &info); + + if (r != BP_RESULT_OK) { + dm_error("Error when reading embedded panel info: %u\n", r); + return NULL; + } + + if (!info.fake_edid || !info.fake_edid_size) { + dm_error("Embedded panel info doesn't contain an EDID\n"); + return NULL; + } + + edid = drm_edid_alloc(info.fake_edid, info.fake_edid_size); + + if (!drm_edid_valid(edid)) { + dm_error("EDID from embedded panel info is invalid\n"); + drm_edid_free(edid); + return NULL; + } + + aconnector->base.display_info.width_mm = info.panel_width_mm; + aconnector->base.display_info.height_mm = info.panel_height_mm; + + return edid; +} + void populate_hdmi_info_from_connector(struct drm_hdmi_info *hdmi, struct dc_edid_caps *edid_caps) { edid_caps->scdc_present = hdmi->scdc.supported; @@ -1052,6 +1091,9 @@ enum dc_edid_status dm_helpers_read_local_edid( if (link->aux_mode) ddc = &aconnector->dm_dp_aux.aux.ddc; + else if (link->ddc_hw_inst == GPIO_DDC_LINE_UNKNOWN && + dc_is_embedded_signal(link->connector_signal)) + ddc = NULL; else ddc = &aconnector->i2c->base; @@ -1065,6 +1107,8 @@ enum dc_edid_status dm_helpers_read_local_edid( drm_edid = dm_helpers_read_acpi_edid(aconnector); if (drm_edid) drm_info(connector->dev, "Using ACPI provided EDID for %s\n", connector->name); + else if (!ddc) + drm_edid = dm_helpers_read_vbios_hardcoded_edid(link, aconnector); else drm_edid = drm_edid_read_ddc(connector, ddc); drm_edid_connector_update(connector, drm_edid); diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c index dd362071a6c9..c307f42fe0b9 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c @@ -794,11 +794,13 @@ static enum bp_result bios_parser_external_encoder_control( static enum bp_result bios_parser_dac_load_detection( struct dc_bios *dcb, - enum engine_id engine_id) + enum engine_id engine_id, + struct graphics_object_id ext_enc_id) { struct bios_parser *bp = BP_FROM_DCB(dcb); struct dc_context *ctx = dcb->ctx; struct bp_load_detection_parameters bp_params = {0}; + struct bp_external_encoder_control ext_cntl = {0}; enum bp_result bp_result = BP_RESULT_UNSUPPORTED; uint32_t bios_0_scratch; uint32_t device_id_mask = 0; @@ -824,6 +826,13 @@ static enum bp_result bios_parser_dac_load_detection( bp_params.engine_id = engine_id; bp_result = bp->cmd_tbl.dac_load_detection(bp, &bp_params); + } else if (ext_enc_id.id) { + if (!bp->cmd_tbl.external_encoder_control) + return BP_RESULT_UNSUPPORTED; + + ext_cntl.action = EXTERNAL_ENCODER_CONTROL_DAC_LOAD_DETECT; + ext_cntl.encoder_id = ext_enc_id; + bp_result = bp->cmd_tbl.external_encoder_control(bp, &ext_cntl); } if (bp_result != BP_RESULT_OK) @@ -1304,6 +1313,60 @@ static enum bp_result bios_parser_get_embedded_panel_info( return BP_RESULT_FAILURE; } +static enum bp_result get_embedded_panel_extra_info( + struct bios_parser *bp, + struct embedded_panel_info *info, + const uint32_t table_offset) +{ + uint8_t *record = bios_get_image(&bp->base, table_offset, 1); + ATOM_PANEL_RESOLUTION_PATCH_RECORD *panel_res_record; + ATOM_FAKE_EDID_PATCH_RECORD *fake_edid_record; + + while (*record != ATOM_RECORD_END_TYPE) { + switch (*record) { + case LCD_MODE_PATCH_RECORD_MODE_TYPE: + record += sizeof(ATOM_PATCH_RECORD_MODE); + break; + case LCD_RTS_RECORD_TYPE: + record += sizeof(ATOM_LCD_RTS_RECORD); + break; + case LCD_CAP_RECORD_TYPE: + record += sizeof(ATOM_LCD_MODE_CONTROL_CAP); + break; + case LCD_FAKE_EDID_PATCH_RECORD_TYPE: + fake_edid_record = (ATOM_FAKE_EDID_PATCH_RECORD *)record; + if (fake_edid_record->ucFakeEDIDLength) { + if (fake_edid_record->ucFakeEDIDLength == 128) + info->fake_edid_size = + fake_edid_record->ucFakeEDIDLength; + else + info->fake_edid_size = + fake_edid_record->ucFakeEDIDLength * 128; + + info->fake_edid = fake_edid_record->ucFakeEDIDString; + + record += struct_size(fake_edid_record, + ucFakeEDIDString, + info->fake_edid_size); + } else { + /* empty fake edid record must be 3 bytes long */ + record += sizeof(ATOM_FAKE_EDID_PATCH_RECORD) + 1; + } + break; + case LCD_PANEL_RESOLUTION_RECORD_TYPE: + panel_res_record = (ATOM_PANEL_RESOLUTION_PATCH_RECORD *)record; + info->panel_width_mm = panel_res_record->usHSize; + info->panel_height_mm = panel_res_record->usVSize; + record += sizeof(ATOM_PANEL_RESOLUTION_PATCH_RECORD); + break; + default: + return BP_RESULT_BADBIOSTABLE; + } + } + + return BP_RESULT_OK; +} + static enum bp_result get_embedded_panel_info_v1_2( struct bios_parser *bp, struct embedded_panel_info *info) @@ -1420,6 +1483,10 @@ static enum bp_result get_embedded_panel_info_v1_2( if (ATOM_PANEL_MISC_API_ENABLED & lvds->ucLVDS_Misc) info->lcd_timing.misc_info.API_ENABLED = true; + if (lvds->usExtInfoTableOffset) + return get_embedded_panel_extra_info(bp, info, + le16_to_cpu(lvds->usExtInfoTableOffset) + DATA_TABLES(LCD_Info)); + return BP_RESULT_OK; } @@ -1545,6 +1612,10 @@ static enum bp_result get_embedded_panel_info_v1_3( (uint32_t) (ATOM_PANEL_MISC_V13_GREY_LEVEL & lvds->ucLCD_Misc) >> ATOM_PANEL_MISC_V13_GREY_LEVEL_SHIFT; + if (lvds->usExtInfoTableOffset) + return get_embedded_panel_extra_info(bp, info, + le16_to_cpu(lvds->usExtInfoTableOffset) + DATA_TABLES(LCD_Info)); + return BP_RESULT_OK; } diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 7f55ba09b191..37714d4371fb 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -1682,7 +1682,7 @@ struct dc_scratch_space { struct dc_link_training_overrides preferred_training_settings; struct dp_audio_test_data audio_test_data; - uint8_t ddc_hw_inst; + enum gpio_ddc_line ddc_hw_inst; uint8_t hpd_src; diff --git a/drivers/gpu/drm/amd/display/dc/dc_bios_types.h b/drivers/gpu/drm/amd/display/dc/dc_bios_types.h index 6f96c5cf39fe..526f71616f94 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_bios_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_bios_types.h @@ -102,7 +102,8 @@ struct dc_vbios_funcs { struct bp_external_encoder_control *cntl); enum bp_result (*dac_load_detection)( struct dc_bios *bios, - enum engine_id engine_id); + enum engine_id engine_id, + struct graphics_object_id ext_enc_id); enum bp_result (*transmitter_control)( struct dc_bios *bios, struct bp_transmitter_control *cntl); diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c index 5f40ae9e3120..e15fd1454d3b 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c @@ -1102,7 +1102,9 @@ void dce110_link_encoder_hw_init( ASSERT(result == BP_RESULT_OK); } - aux_initialize(enc110); + + if (enc110->aux_regs) + aux_initialize(enc110); /* reinitialize HPD. * hpd_initialize() will pass DIG_FE id to HW context. diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mmhubbub.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mmhubbub.c index 6f2a0d5d963b..62fe5c3b18dc 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mmhubbub.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mmhubbub.c @@ -40,8 +40,8 @@ #define FN(reg_name, field_name) \ mcif_wb30->mcif_wb_shift->field_name, mcif_wb30->mcif_wb_mask->field_name -#define MCIF_ADDR(addr) (((unsigned long long)addr & 0xffffffffff) + 0xFE) >> 8 -#define MCIF_ADDR_HIGH(addr) (unsigned long long)addr >> 40 +#define MCIF_ADDR(addr) ((uint32_t)((((unsigned long long)(addr) & 0xffffffffffULL) + 0xFEULL) >> 8)) +#define MCIF_ADDR_HIGH(addr) ((uint32_t)(((unsigned long long)(addr)) >> 40)) /* wbif programming guide: * 1. set up wbif parameter: diff --git a/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c b/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c index a2c46350e44e..95f8b7c7d657 100644 --- a/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c +++ b/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c @@ -646,6 +646,9 @@ failure: enum gpio_ddc_line dal_ddc_get_line( const struct ddc *ddc) { + if (!ddc) + return GPIO_DDC_LINE_UNKNOWN; + return (enum gpio_ddc_line)dal_gpio_get_enum(ddc->pin_data); } diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c index 5273ca09fe12..f0abbb7c2cb2 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c @@ -665,16 +665,45 @@ void dce110_update_info_frame(struct pipe_ctx *pipe_ctx) } static void -dce110_dac_encoder_control(struct pipe_ctx *pipe_ctx, bool enable) +dce110_external_encoder_control(enum bp_external_encoder_control_action action, + struct dc_link *link, + struct dc_crtc_timing *timing) { - struct dc_link *link = pipe_ctx->stream->link; + struct dc *dc = link->ctx->dc; struct dc_bios *bios = link->ctx->dc_bios; - struct bp_encoder_control encoder_control = {0}; + const struct dc_link_settings *link_settings = &link->cur_link_settings; + enum bp_result bp_result = BP_RESULT_OK; + struct bp_external_encoder_control ext_cntl = { + .action = action, + .connector_obj_id = link->link_enc->connector, + .encoder_id = link->ext_enc_id, + .lanes_number = link_settings->lane_count, + .link_rate = link_settings->link_rate, + + /* Use signal type of the real link encoder, ie. DP */ + .signal = link->connector_signal, + + /* We don't know the timing yet when executing the SETUP action, + * so use a reasonably high default value. It seems that ENABLE + * can change the actual pixel clock but doesn't work with higher + * pixel clocks than what SETUP was called with. + */ + .pixel_clock = timing ? timing->pix_clk_100hz / 10 : 300000, + .color_depth = timing ? timing->display_color_depth : COLOR_DEPTH_888, + }; + DC_LOGGER_INIT(dc->ctx); - encoder_control.action = enable ? ENCODER_CONTROL_ENABLE : ENCODER_CONTROL_DISABLE; - encoder_control.engine_id = link->link_enc->analog_engine; - encoder_control.pixel_clock = pipe_ctx->stream->timing.pix_clk_100hz / 10; - bios->funcs->encoder_control(bios, &encoder_control); + bp_result = bios->funcs->external_encoder_control(bios, &ext_cntl); + + if (bp_result != BP_RESULT_OK) + DC_LOG_ERROR("Failed to execute external encoder action: 0x%x\n", action); +} + +static void +dce110_prepare_ddc(struct dc_link *link) +{ + if (link->ext_enc_id.id) + dce110_external_encoder_control(EXTERNAL_ENCODER_CONTROL_DDC_SETUP, link, NULL); } static bool @@ -684,7 +713,8 @@ dce110_dac_load_detect(struct dc_link *link) struct link_encoder *link_enc = link->link_enc; enum bp_result bp_result; - bp_result = bios->funcs->dac_load_detection(bios, link_enc->analog_engine); + bp_result = bios->funcs->dac_load_detection( + bios, link_enc->analog_engine, link->ext_enc_id); return bp_result == BP_RESULT_OK; } @@ -700,7 +730,6 @@ void dce110_enable_stream(struct pipe_ctx *pipe_ctx) uint32_t early_control = 0; struct timing_generator *tg = pipe_ctx->stream_res.tg; - link_hwss->setup_stream_attribute(pipe_ctx); link_hwss->setup_stream_encoder(pipe_ctx); dc->hwss.update_info_frame(pipe_ctx); @@ -719,8 +748,8 @@ void dce110_enable_stream(struct pipe_ctx *pipe_ctx) tg->funcs->set_early_control(tg, early_control); - if (dc_is_rgb_signal(pipe_ctx->stream->signal)) - dce110_dac_encoder_control(pipe_ctx, true); + if (link->ext_enc_id.id) + dce110_external_encoder_control(EXTERNAL_ENCODER_CONTROL_ENABLE, link, timing); } static enum bp_result link_transmitter_control( @@ -1219,8 +1248,8 @@ void dce110_disable_stream(struct pipe_ctx *pipe_ctx) link_enc->transmitter - TRANSMITTER_UNIPHY_A); } - if (dc_is_rgb_signal(pipe_ctx->stream->signal)) - dce110_dac_encoder_control(pipe_ctx, false); + if (link->ext_enc_id.id) + dce110_external_encoder_control(EXTERNAL_ENCODER_CONTROL_DISABLE, link, NULL); } void dce110_unblank_stream(struct pipe_ctx *pipe_ctx, @@ -1603,22 +1632,6 @@ static enum dc_status dce110_enable_stream_timing( return DC_OK; } -static void -dce110_select_crtc_source(struct pipe_ctx *pipe_ctx) -{ - struct dc_link *link = pipe_ctx->stream->link; - struct dc_bios *bios = link->ctx->dc_bios; - struct bp_crtc_source_select crtc_source_select = {0}; - enum engine_id engine_id = link->link_enc->preferred_engine; - - if (dc_is_rgb_signal(pipe_ctx->stream->signal)) - engine_id = link->link_enc->analog_engine; - crtc_source_select.controller_id = CONTROLLER_ID_D0 + pipe_ctx->stream_res.tg->inst; - crtc_source_select.color_depth = pipe_ctx->stream->timing.display_color_depth; - crtc_source_select.engine_id = engine_id; - crtc_source_select.sink_signal = pipe_ctx->stream->signal; - bios->funcs->select_crtc_source(bios, &crtc_source_select); -} enum dc_status dce110_apply_single_controller_ctx_to_hw( struct pipe_ctx *pipe_ctx, @@ -1639,10 +1652,6 @@ enum dc_status dce110_apply_single_controller_ctx_to_hw( hws->funcs.disable_stream_gating(dc, pipe_ctx); } - if (pipe_ctx->stream->signal == SIGNAL_TYPE_RGB) { - dce110_select_crtc_source(pipe_ctx); - } - if (pipe_ctx->stream_res.audio != NULL) { struct audio_output audio_output = {0}; @@ -1722,8 +1731,7 @@ enum dc_status dce110_apply_single_controller_ctx_to_hw( pipe_ctx->stream_res.tg->funcs->set_static_screen_control( pipe_ctx->stream_res.tg, event_triggers, 2); - if (!dc_is_virtual_signal(pipe_ctx->stream->signal) && - !dc_is_rgb_signal(pipe_ctx->stream->signal)) + if (!dc_is_virtual_signal(pipe_ctx->stream->signal)) pipe_ctx->stream_res.stream_enc->funcs->dig_connect_to_otg( pipe_ctx->stream_res.stream_enc, pipe_ctx->stream_res.tg->inst); @@ -3376,6 +3384,15 @@ void dce110_enable_tmds_link_output(struct dc_link *link, link->phy_state.symclk_state = SYMCLK_ON_TX_ON; } +static void dce110_enable_analog_link_output( + struct dc_link *link, + uint32_t pix_clk_100hz) +{ + link->link_enc->funcs->enable_analog_output( + link->link_enc, + pix_clk_100hz); +} + void dce110_enable_dp_link_output( struct dc_link *link, const struct link_resource *link_res, @@ -3423,6 +3440,11 @@ void dce110_enable_dp_link_output( } } + if (link->ext_enc_id.id) { + dce110_external_encoder_control(EXTERNAL_ENCODER_CONTROL_INIT, link, NULL); + dce110_external_encoder_control(EXTERNAL_ENCODER_CONTROL_SETUP, link, NULL); + } + if (dc->link_srv->dp_get_encoding_format(link_settings) == DP_8b_10b_ENCODING) { if (dc->clk_mgr->funcs->notify_link_rate_change) dc->clk_mgr->funcs->notify_link_rate_change(dc->clk_mgr, link); @@ -3513,8 +3535,10 @@ static const struct hw_sequencer_funcs dce110_funcs = { .enable_lvds_link_output = dce110_enable_lvds_link_output, .enable_tmds_link_output = dce110_enable_tmds_link_output, .enable_dp_link_output = dce110_enable_dp_link_output, + .enable_analog_link_output = dce110_enable_analog_link_output, .disable_link_output = dce110_disable_link_output, .dac_load_detect = dce110_dac_load_detect, + .prepare_ddc = dce110_prepare_ddc, }; static const struct hwseq_private_funcs dce110_private_funcs = { diff --git a/drivers/gpu/drm/amd/display/dc/link/link_factory.c b/drivers/gpu/drm/amd/display/dc/link/link_factory.c index 7e7682d7dfc8..ae4c4ad05baa 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_factory.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_factory.c @@ -568,7 +568,9 @@ static bool construct_phy(struct dc_link *link, goto ddc_create_fail; } - if (!link->ddc->ddc_pin) { + /* Embedded display connectors such as LVDS may not have DDC. */ + if (!link->ddc->ddc_pin && + !dc_is_embedded_signal(link->connector_signal)) { DC_ERROR("Failed to get I2C info for connector!\n"); goto ddc_create_fail; } diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c index 6a25dcfcdf17..d2d56a1c4b8b 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c @@ -753,7 +753,8 @@ static struct link_encoder *dce60_link_encoder_create( enc_init_data, &link_enc_feature, &link_enc_regs[link_regs_id], - &link_enc_aux_regs[enc_init_data->channel - 1], + enc_init_data->channel == CHANNEL_ID_UNKNOWN ? + NULL : &link_enc_aux_regs[enc_init_data->channel - 1], enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs) ? NULL : &link_enc_hpd_regs[enc_init_data->hpd_source]); return &enc110->base; diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c index 33be49b3c1b1..6c00497e9a01 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c @@ -760,7 +760,8 @@ static struct link_encoder *dce80_link_encoder_create( enc_init_data, &link_enc_feature, &link_enc_regs[link_regs_id], - &link_enc_aux_regs[enc_init_data->channel - 1], + enc_init_data->channel == CHANNEL_ID_UNKNOWN ? + NULL : &link_enc_aux_regs[enc_init_data->channel - 1], enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs) ? NULL : &link_enc_hpd_regs[enc_init_data->hpd_source]); return &enc110->base; diff --git a/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h b/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h index 38a77fa9b4af..a0f03fb67605 100644 --- a/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h +++ b/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h @@ -153,6 +153,10 @@ struct embedded_panel_info { uint32_t drr_enabled; uint32_t min_drr_refresh_rate; bool realtek_eDPToLVDS; + uint16_t panel_width_mm; + uint16_t panel_height_mm; + uint16_t fake_edid_size; + const uint8_t *fake_edid; }; struct dc_firmware_info { diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c index 731355bdb9bc..3650e7beeb67 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c @@ -1333,12 +1333,13 @@ static int ci_populate_all_memory_levels(struct pp_hwmgr *hwmgr) dev_id = adev->pdev->device; - if ((dpm_table->mclk_table.count >= 2) - && ((dev_id == 0x67B0) || (dev_id == 0x67B1))) { - smu_data->smc_state_table.MemoryLevel[1].MinVddci = - smu_data->smc_state_table.MemoryLevel[0].MinVddci; - smu_data->smc_state_table.MemoryLevel[1].MinMvdd = - smu_data->smc_state_table.MemoryLevel[0].MinMvdd; + if ((dpm_table->mclk_table.count >= 2) && + ((dev_id == 0x67B0) || (dev_id == 0x67B1)) && + (adev->pdev->revision == 0)) { + smu_data->smc_state_table.MemoryLevel[1].MinVddc = + smu_data->smc_state_table.MemoryLevel[0].MinVddc; + smu_data->smc_state_table.MemoryLevel[1].MinVddcPhases = + smu_data->smc_state_table.MemoryLevel[0].MinVddcPhases; } smu_data->smc_state_table.MemoryLevel[0].ActivityLevel = 0x1F; CONVERT_FROM_HOST_TO_SMC_US(smu_data->smc_state_table.MemoryLevel[0].ActivityLevel); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c index 7f386ff0c872..9d8b1227388f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c @@ -425,6 +425,7 @@ static int aldebaran_set_default_dpm_table(struct smu_context *smu) dpm_table->dpm_levels[0].enabled = true; dpm_table->dpm_levels[1].value = pptable->GfxclkFmax; dpm_table->dpm_levels[1].enabled = true; + dpm_table->flags |= SMU_DPM_TABLE_FINE_GRAINED; } else { dpm_table->count = 1; dpm_table->dpm_levels[0].value = smu->smu_table.boot_values.gfxclk / 100; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c index cd0a23f432ff..0df8c05a7fce 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c @@ -1129,6 +1129,7 @@ static int smu_v13_0_6_set_default_dpm_table(struct smu_context *smu) /* gfxclk dpm table setup */ dpm_table = &dpm_context->dpm_tables.gfx_table; dpm_table->clk_type = SMU_GFXCLK; + dpm_table->flags = SMU_DPM_TABLE_FINE_GRAINED; if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_DPM_GFXCLK_BIT)) { /* In the case of gfxclk, only fine-grained dpm is honored. * Get min/max values from FW. diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c index 3d49e58794d2..90c7127beabf 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c @@ -1370,7 +1370,7 @@ int smu_cmn_print_dpm_clk_levels(struct smu_context *smu, level_index = 1; } - if (!is_fine_grained) { + if (!is_fine_grained || count == 1) { for (i = 0; i < count; i++) { freq_match = !is_deep_sleep && smu_cmn_freqs_match( diff --git a/drivers/gpu/drm/bridge/tda998x_drv.c b/drivers/gpu/drm/bridge/tda998x_drv.c index d9b388165de1..6c427bc75896 100644 --- a/drivers/gpu/drm/bridge/tda998x_drv.c +++ b/drivers/gpu/drm/bridge/tda998x_drv.c @@ -1293,7 +1293,7 @@ static const struct drm_edid *tda998x_edid_read(struct tda998x_priv *priv, * can't handle signals gracefully. */ if (tda998x_edid_delay_wait(priv)) - return 0; + return NULL; if (priv->rev == TDA19988) reg_clear(priv, REG_TX4, TX4_PD_RAM); @@ -1762,7 +1762,7 @@ static const struct drm_bridge_funcs tda998x_bridge_funcs = { static int tda998x_get_audio_ports(struct tda998x_priv *priv, struct device_node *np) { - const u32 *port_data; + const __be32 *port_data; u32 size; int i; diff --git a/drivers/gpu/drm/drm_color_mgmt.c b/drivers/gpu/drm/drm_color_mgmt.c index c598b99673fc..e7db4e4ea700 100644 --- a/drivers/gpu/drm/drm_color_mgmt.c +++ b/drivers/gpu/drm/drm_color_mgmt.c @@ -831,7 +831,7 @@ static void fill_palette_332(struct drm_crtc *crtc, u16 r, u16 g, u16 b, } /** - * drm_crtc_fill_palette_332 - Programs a default palette for R332-like formats + * drm_crtc_fill_palette_332 - Programs a default palette for RGB332-like formats * @crtc: The displaying CRTC * @set_palette: Callback for programming the hardware gamma LUT * diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index a80a335f4148..1541fc8a9ac2 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -490,7 +490,7 @@ static void drm_fb_helper_memory_range_to_clip(struct fb_info *info, off_t off, * the number of horizontal pixels that need an update. */ off_t bit_off = (off % line_length) * 8; - off_t bit_end = (end % line_length) * 8; + off_t bit_end = bit_off + len * 8; x1 = bit_off / info->var.bits_per_pixel; x2 = DIV_ROUND_UP(bit_end, info->var.bits_per_pixel); diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index d6424267260b..51a887cc7fd7 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -1019,7 +1019,7 @@ int drm_gem_change_handle_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_gem_change_handle *args = data; - struct drm_gem_object *obj; + struct drm_gem_object *obj, *idrobj; int handle, ret; if (!drm_core_check_feature(dev, DRIVER_GEM)) @@ -1042,8 +1042,29 @@ int drm_gem_change_handle_ioctl(struct drm_device *dev, void *data, mutex_lock(&file_priv->prime.lock); spin_lock(&file_priv->table_lock); + + /* When create_tail allocs an obj idr, it needs to first alloc as NULL, + * then later replace with the correct object. This is not necessary + * here, because the only operations that could race are drm_prime + * bookkeeping, and we hold the prime lock. + */ ret = idr_alloc(&file_priv->object_idr, obj, handle, handle + 1, GFP_NOWAIT); + + if (ret < 0) { + spin_unlock(&file_priv->table_lock); + goto out_unlock; + } + + idrobj = idr_replace(&file_priv->object_idr, NULL, handle); + if (idrobj != obj) { + idr_replace(&file_priv->object_idr, idrobj, handle); + idr_remove(&file_priv->object_idr, args->new_handle); + spin_unlock(&file_priv->table_lock); + ret = -ENOENT; + goto out_unlock; + } + spin_unlock(&file_priv->table_lock); if (ret < 0) @@ -1055,6 +1076,8 @@ int drm_gem_change_handle_ioctl(struct drm_device *dev, void *data, if (ret < 0) { spin_lock(&file_priv->table_lock); idr_remove(&file_priv->object_idr, handle); + idrobj = idr_replace(&file_priv->object_idr, obj, handle); + WARN_ON(idrobj != NULL); spin_unlock(&file_priv->table_lock); goto out_unlock; } diff --git a/drivers/gpu/drm/drm_gem_framebuffer_helper.c b/drivers/gpu/drm/drm_gem_framebuffer_helper.c index 9166c353f131..88808e972cc1 100644 --- a/drivers/gpu/drm/drm_gem_framebuffer_helper.c +++ b/drivers/gpu/drm/drm_gem_framebuffer_helper.c @@ -172,8 +172,8 @@ int drm_gem_fb_init_with_funcs(struct drm_device *dev, } for (i = 0; i < info->num_planes; i++) { - unsigned int width = mode_cmd->width / (i ? info->hsub : 1); - unsigned int height = mode_cmd->height / (i ? info->vsub : 1); + unsigned int width = drm_format_info_plane_width(info, mode_cmd->width, i); + unsigned int height = drm_format_info_plane_height(info, mode_cmd->height, i); unsigned int min_size; objs[i] = drm_gem_object_lookup(file, mode_cmd->handles[i]); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c index df4232d7e135..3cc50d697c89 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c @@ -116,16 +116,18 @@ int etnaviv_sched_push_job(struct etnaviv_gem_submit *submit) */ mutex_lock(&gpu->sched_lock); + ret = xa_alloc_cyclic(&gpu->user_fences, &submit->out_fence_id, + NULL, xa_limit_32b, &gpu->next_user_fence, + GFP_KERNEL); + if (ret < 0) + goto out_unlock; + drm_sched_job_arm(&submit->sched_job); submit->out_fence = dma_fence_get(&submit->sched_job.s_fence->finished); - ret = xa_alloc_cyclic(&gpu->user_fences, &submit->out_fence_id, - submit->out_fence, xa_limit_32b, - &gpu->next_user_fence, GFP_KERNEL); - if (ret < 0) { - drm_sched_job_cleanup(&submit->sched_job); - goto out_unlock; - } + + xa_store(&gpu->user_fences, submit->out_fence_id, + submit->out_fence, GFP_KERNEL); /* the scheduler holds on to the job now */ kref_get(&submit->refcount); diff --git a/drivers/gpu/drm/exynos/exynos_drm_mic.c b/drivers/gpu/drm/exynos/exynos_drm_mic.c index 29a8366513fa..e68c954ec3e6 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_mic.c +++ b/drivers/gpu/drm/exynos/exynos_drm_mic.c @@ -423,7 +423,9 @@ static int exynos_mic_probe(struct platform_device *pdev) mic->bridge.of_node = dev->of_node; - drm_bridge_add(&mic->bridge); + ret = devm_drm_bridge_add(dev, &mic->bridge); + if (ret) + goto err; pm_runtime_enable(dev); @@ -443,12 +445,8 @@ err: static void exynos_mic_remove(struct platform_device *pdev) { - struct exynos_mic *mic = platform_get_drvdata(pdev); - component_del(&pdev->dev, &exynos_mic_component_ops); pm_runtime_disable(&pdev->dev); - - drm_bridge_remove(&mic->bridge); } static const struct of_device_id exynos_mic_of_match[] = { diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c index 385a634c3ed0..d9be7a5a239c 100644 --- a/drivers/gpu/drm/i915/i915_driver.c +++ b/drivers/gpu/drm/i915/i915_driver.c @@ -750,9 +750,8 @@ static bool has_auxccs(struct drm_device *drm) { struct drm_i915_private *i915 = to_i915(drm); - return IS_GRAPHICS_VER(i915, 9, 12) || - IS_ALDERLAKE_P(i915) || - IS_METEORLAKE(i915); + return IS_GRAPHICS_VER(i915, 9, 12) && + !HAS_FLAT_CCS(i915); } static bool has_fenced_regions(struct drm_device *drm) diff --git a/drivers/gpu/drm/imagination/pvr_fw_trace.c b/drivers/gpu/drm/imagination/pvr_fw_trace.c index e154cb35f604..6193811ef7be 100644 --- a/drivers/gpu/drm/imagination/pvr_fw_trace.c +++ b/drivers/gpu/drm/imagination/pvr_fw_trace.c @@ -558,6 +558,6 @@ pvr_fw_trace_debugfs_init(struct pvr_device *pvr_dev, struct dentry *dir) &pvr_fw_trace_fops); } - debugfs_create_file("trace_mask", 0600, dir, fw_trace, + debugfs_create_file("trace_mask", 0600, dir, pvr_dev, &pvr_fw_trace_mask_fops); } diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c index 72848ed80df7..b101e14f841e 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c @@ -2513,6 +2513,7 @@ static const struct nvkm_device_chip nv170_chipset = { .name = "GA100", .bar = { 0x00000001, tu102_bar_new }, + .bios = { 0x00000001, nvkm_bios_new }, .devinit = { 0x00000001, ga100_devinit_new }, .fault = { 0x00000001, tu102_fault_new }, .fb = { 0x00000001, ga100_fb_new }, @@ -2529,7 +2530,6 @@ nv170_chipset = { .vfn = { 0x00000001, ga100_vfn_new }, .ce = { 0x000003ff, ga100_ce_new }, .fifo = { 0x00000001, ga100_fifo_new }, - .sec2 = { 0x00000001, tu102_sec2_new }, }; static const struct nvkm_device_chip @@ -3341,7 +3341,6 @@ nvkm_device_ctor(const struct nvkm_device_func *func, case 0x166: device->chip = &nv166_chipset; break; case 0x167: device->chip = &nv167_chipset; break; case 0x168: device->chip = &nv168_chipset; break; - case 0x170: device->chip = &nv170_chipset; break; case 0x172: device->chip = &nv172_chipset; break; case 0x173: device->chip = &nv173_chipset; break; case 0x174: device->chip = &nv174_chipset; break; @@ -3361,6 +3360,14 @@ nvkm_device_ctor(const struct nvkm_device_func *func, case 0x1b6: device->chip = &nv1b6_chipset; break; case 0x1b7: device->chip = &nv1b7_chipset; break; default: + if (nvkm_boolopt(device->cfgopt, "NvEnableUnsupportedChipsets", false)) { + switch (device->chipset) { + case 0x170: device->chip = &nv170_chipset; break; + default: + break; + } + } + if (!device->chip) { nvdev_error(device, "unknown chipset (%08x)\n", boot0); ret = -ENODEV; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga100.c index fdd820eeef81..27a13aeccd3c 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga100.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga100.c @@ -41,11 +41,15 @@ ga100_gsp_flcn = { static const struct nvkm_gsp_func ga100_gsp = { .flcn = &ga100_gsp_flcn, + .fwsec = &tu102_gsp_fwsec, .sig_section = ".fwsignature_ga100", .booter.ctor = tu102_gsp_booter_ctor, + .fwsec_sb.ctor = tu102_gsp_fwsec_sb_ctor, + .fwsec_sb.dtor = tu102_gsp_fwsec_sb_dtor, + .dtor = r535_gsp_dtor, .oneinit = tu102_gsp_oneinit, .init = tu102_gsp_init, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu102.c index dd82c76b8b9a..19cb269e7a26 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu102.c @@ -318,13 +318,8 @@ tu102_gsp_oneinit(struct nvkm_gsp *gsp) if (ret) return ret; - /* - * Calculate FB layout. FRTS is a memory region created by the FWSEC-FRTS firmware. - * FWSEC comes from VBIOS. So on systems with no VBIOS (e.g. GA100), the FRTS does - * not exist. Therefore, use the existence of VBIOS to determine whether to reserve - * an FRTS region. - */ - gsp->fb.wpr2.frts.size = device->bios ? 0x100000 : 0; + /* Calculate FB layout. */ + gsp->fb.wpr2.frts.size = 0x100000; gsp->fb.wpr2.frts.addr = ALIGN_DOWN(gsp->fb.bios.addr, 0x20000) - gsp->fb.wpr2.frts.size; gsp->fb.wpr2.boot.size = gsp->boot.fw.size; @@ -348,12 +343,9 @@ tu102_gsp_oneinit(struct nvkm_gsp *gsp) if (ret) return ret; - /* Only boot FWSEC-FRTS if it actually exists */ - if (gsp->fb.wpr2.frts.size) { - ret = nvkm_gsp_fwsec_frts(gsp); - if (WARN_ON(ret)) - return ret; - } + ret = nvkm_gsp_fwsec_frts(gsp); + if (WARN_ON(ret)) + return ret; /* Reset GSP into RISC-V mode. */ ret = gsp->func->reset(gsp); diff --git a/drivers/gpu/drm/panel/Kconfig b/drivers/gpu/drm/panel/Kconfig index d6863b28ddc5..d592f4f4b939 100644 --- a/drivers/gpu/drm/panel/Kconfig +++ b/drivers/gpu/drm/panel/Kconfig @@ -208,6 +208,7 @@ config DRM_PANEL_HIMAX_HX83121A depends on OF depends on DRM_MIPI_DSI depends on BACKLIGHT_CLASS_DEVICE + select DRM_DISPLAY_DSC_HELPER select DRM_KMS_HELPER help Say Y here if you want to enable support for Himax HX83121A-based diff --git a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c index d5fe105bdbdd..658ce64c71eb 100644 --- a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c +++ b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c @@ -1324,6 +1324,8 @@ static int boe_panel_disable(struct drm_panel *panel) mipi_dsi_dcs_set_display_off_multi(&ctx); mipi_dsi_dcs_enter_sleep_mode_multi(&ctx); + boe->dsi->mode_flags |= MIPI_DSI_MODE_LPM; + mipi_dsi_msleep(&ctx, 150); return ctx.accum_err; diff --git a/drivers/gpu/drm/panel/panel-feiyang-fy07024di26a30d.c b/drivers/gpu/drm/panel/panel-feiyang-fy07024di26a30d.c index 4f8d6d8c07e4..dbdb7e3cb7b6 100644 --- a/drivers/gpu/drm/panel/panel-feiyang-fy07024di26a30d.c +++ b/drivers/gpu/drm/panel/panel-feiyang-fy07024di26a30d.c @@ -98,9 +98,7 @@ static int feiyang_enable(struct drm_panel *panel) /* T12 (video & logic signal rise + backlight rise) T12 >= 200ms */ msleep(200); - mipi_dsi_dcs_set_display_on(ctx->dsi); - - return 0; + return mipi_dsi_dcs_set_display_on(ctx->dsi); } static int feiyang_disable(struct drm_panel *panel) diff --git a/drivers/gpu/drm/panel/panel-himax-hx83102.c b/drivers/gpu/drm/panel/panel-himax-hx83102.c index 8b2a68ee851e..a5e5c9ea7a73 100644 --- a/drivers/gpu/drm/panel/panel-himax-hx83102.c +++ b/drivers/gpu/drm/panel/panel-himax-hx83102.c @@ -937,6 +937,8 @@ static int hx83102_disable(struct drm_panel *panel) mipi_dsi_dcs_set_display_off_multi(&dsi_ctx); mipi_dsi_dcs_enter_sleep_mode_multi(&dsi_ctx); + dsi->mode_flags |= MIPI_DSI_MODE_LPM; + mipi_dsi_msleep(&dsi_ctx, 150); return dsi_ctx.accum_err; diff --git a/drivers/gpu/drm/panel/panel-himax-hx83121a.c b/drivers/gpu/drm/panel/panel-himax-hx83121a.c index ebe643ba4184..bed79aa06f46 100644 --- a/drivers/gpu/drm/panel/panel-himax-hx83121a.c +++ b/drivers/gpu/drm/panel/panel-himax-hx83121a.c @@ -596,8 +596,8 @@ static int himax_probe(struct mipi_dsi_device *dsi) ctx = devm_drm_panel_alloc(dev, struct himax, panel, &himax_panel_funcs, DRM_MODE_CONNECTOR_DSI); - if (!ctx) - return -ENOMEM; + if (IS_ERR(ctx)) + return PTR_ERR(ctx); ret = devm_regulator_bulk_get_const(&dsi->dev, ARRAY_SIZE(himax_supplies), diff --git a/drivers/gpu/drm/qxl/qxl_drv.c b/drivers/gpu/drm/qxl/qxl_drv.c index 2bbb1168a3ff..1e6a2392d7c6 100644 --- a/drivers/gpu/drm/qxl/qxl_drv.c +++ b/drivers/gpu/drm/qxl/qxl_drv.c @@ -118,12 +118,13 @@ qxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Complete initialization. */ ret = drm_dev_register(&qdev->ddev, ent->driver_data); if (ret) - goto modeset_cleanup; + goto poll_fini; drm_client_setup(&qdev->ddev, NULL); return 0; -modeset_cleanup: +poll_fini: + drm_kms_helper_poll_fini(&qdev->ddev); qxl_modeset_fini(qdev); unload: qxl_device_fini(qdev); @@ -154,6 +155,7 @@ qxl_pci_remove(struct pci_dev *pdev) { struct drm_device *dev = pci_get_drvdata(pdev); + drm_kms_helper_poll_fini(dev); drm_dev_unregister(dev); drm_atomic_helper_shutdown(dev); if (pci_is_vga(pdev) && pdev->revision < 5) diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c index 22321eb95b7d..703848fac189 100644 --- a/drivers/gpu/drm/radeon/ci_dpm.c +++ b/drivers/gpu/drm/radeon/ci_dpm.c @@ -2461,7 +2461,8 @@ static void ci_register_patching_mc_arb(struct radeon_device *rdev, if (patch && ((rdev->pdev->device == 0x67B0) || - (rdev->pdev->device == 0x67B1))) { + (rdev->pdev->device == 0x67B1)) && + (rdev->pdev->revision == 0)) { if ((memory_clock > 100000) && (memory_clock <= 125000)) { tmp2 = (((0x31 * engine_clock) / 125000) - 1) & 0xff; *dram_timimg2 &= ~0x00ff0000; @@ -3304,7 +3305,8 @@ static int ci_populate_all_memory_levels(struct radeon_device *rdev) pi->smc_state_table.MemoryLevel[0].EnabledForActivity = 1; if ((dpm_table->mclk_table.count >= 2) && - ((rdev->pdev->device == 0x67B0) || (rdev->pdev->device == 0x67B1))) { + ((rdev->pdev->device == 0x67B0) || (rdev->pdev->device == 0x67B1)) && + (rdev->pdev->revision == 0)) { pi->smc_state_table.MemoryLevel[1].MinVddc = pi->smc_state_table.MemoryLevel[0].MinVddc; pi->smc_state_table.MemoryLevel[1].MinVddcPhases = @@ -4493,7 +4495,8 @@ static int ci_register_patching_mc_seq(struct radeon_device *rdev, if (patch && ((rdev->pdev->device == 0x67B0) || - (rdev->pdev->device == 0x67B1))) { + (rdev->pdev->device == 0x67B1)) && + (rdev->pdev->revision == 0)) { for (i = 0; i < table->last; i++) { if (table->last >= SMU7_DISCRETE_MC_REGISTER_ARRAY_SIZE) return -EINVAL; diff --git a/drivers/gpu/drm/sti/sti_hda.c b/drivers/gpu/drm/sti/sti_hda.c index b7397827889c..360a88ca8f0c 100644 --- a/drivers/gpu/drm/sti/sti_hda.c +++ b/drivers/gpu/drm/sti/sti_hda.c @@ -741,6 +741,7 @@ static int sti_hda_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct sti_hda *hda; struct resource *res; + int ret; DRM_INFO("%s\n", __func__); @@ -779,7 +780,9 @@ static int sti_hda_probe(struct platform_device *pdev) return PTR_ERR(hda->clk_hddac); } - drm_bridge_add(&hda->bridge); + ret = devm_drm_bridge_add(dev, &hda->bridge); + if (ret) + return ret; platform_set_drvdata(pdev, hda); @@ -788,10 +791,7 @@ static int sti_hda_probe(struct platform_device *pdev) static void sti_hda_remove(struct platform_device *pdev) { - struct sti_hda *hda = platform_get_drvdata(pdev); - component_del(&pdev->dev, &sti_hda_ops); - drm_bridge_remove(&hda->bridge); } static const struct of_device_id hda_of_match[] = { diff --git a/drivers/gpu/drm/sysfb/ofdrm.c b/drivers/gpu/drm/sysfb/ofdrm.c index d38ba70f4e0d..247cf13c80a0 100644 --- a/drivers/gpu/drm/sysfb/ofdrm.c +++ b/drivers/gpu/drm/sysfb/ofdrm.c @@ -350,6 +350,7 @@ static void ofdrm_pci_release(void *data) struct pci_dev *pcidev = data; pci_disable_device(pcidev); + pci_dev_put(pcidev); } static int ofdrm_device_init_pci(struct ofdrm_device *odev) @@ -375,6 +376,7 @@ static int ofdrm_device_init_pci(struct ofdrm_device *odev) if (ret) { drm_err(dev, "pci_enable_device(%s) failed: %d\n", dev_name(&pcidev->dev), ret); + pci_dev_put(pcidev); return ret; } ret = devm_add_action_or_reset(&pdev->dev, ofdrm_pci_release, pcidev); diff --git a/drivers/gpu/drm/tiny/appletbdrm.c b/drivers/gpu/drm/tiny/appletbdrm.c index 3bae91d7eefe..278bb23fe4c8 100644 --- a/drivers/gpu/drm/tiny/appletbdrm.c +++ b/drivers/gpu/drm/tiny/appletbdrm.c @@ -353,7 +353,7 @@ static int appletbdrm_primary_plane_helper_atomic_check(struct drm_plane *plane, frames_size + sizeof(struct appletbdrm_fb_request_footer), 16); - appletbdrm_state->request = kzalloc(request_size, GFP_KERNEL); + appletbdrm_state->request = kvzalloc(request_size, GFP_KERNEL); if (!appletbdrm_state->request) return -ENOMEM; @@ -543,7 +543,7 @@ static void appletbdrm_primary_plane_destroy_state(struct drm_plane *plane, { struct appletbdrm_plane_state *appletbdrm_state = to_appletbdrm_plane_state(state); - kfree(appletbdrm_state->request); + kvfree(appletbdrm_state->request); kfree(appletbdrm_state->response); __drm_gem_destroy_shadow_plane_state(&appletbdrm_state->base); diff --git a/drivers/gpu/drm/tiny/bochs.c b/drivers/gpu/drm/tiny/bochs.c index 222e4ae1abbd..5d8dc5efec77 100644 --- a/drivers/gpu/drm/tiny/bochs.c +++ b/drivers/gpu/drm/tiny/bochs.c @@ -761,25 +761,21 @@ static int bochs_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent ret = pcim_enable_device(pdev); if (ret) - goto err_free_dev; + return ret; pci_set_drvdata(pdev, dev); ret = bochs_load(bochs); if (ret) - goto err_free_dev; + return ret; ret = drm_dev_register(dev, 0); if (ret) - goto err_free_dev; + return ret; drm_client_setup(dev, NULL); return ret; - -err_free_dev: - drm_dev_put(dev); - return ret; } static void bochs_pci_remove(struct pci_dev *pdev) diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c index 26a3689e5fd9..278bbe7a11ad 100644 --- a/drivers/gpu/drm/ttm/ttm_pool.c +++ b/drivers/gpu/drm/ttm/ttm_pool.c @@ -206,6 +206,14 @@ error_free: return NULL; } +static void __free_pages_gpu_account(struct page *p, unsigned int order, + bool reclaim) +{ + mod_lruvec_page_state(p, reclaim ? NR_GPU_RECLAIM : NR_GPU_ACTIVE, + -(1 << order)); + __free_pages(p, order); +} + /* Reset the caching and pages of size 1 << order */ static void ttm_pool_free_page(struct ttm_pool *pool, enum ttm_caching caching, unsigned int order, struct page *p, bool reclaim) @@ -223,9 +231,7 @@ static void ttm_pool_free_page(struct ttm_pool *pool, enum ttm_caching caching, #endif if (!pool || !ttm_pool_uses_dma_alloc(pool)) { - mod_lruvec_page_state(p, reclaim ? NR_GPU_RECLAIM : NR_GPU_ACTIVE, - -(1 << order)); - __free_pages(p, order); + __free_pages_gpu_account(p, order, reclaim); return; } @@ -606,7 +612,7 @@ static int ttm_pool_restore_commit(struct ttm_pool_tt_restore *restore, */ ttm_pool_split_for_swap(restore->pool, p); copy_highpage(restore->alloced_page + i, p); - __free_pages(p, 0); + __free_pages_gpu_account(p, 0, false); } restore->restored_pages++; @@ -1068,7 +1074,7 @@ long ttm_pool_backup(struct ttm_pool *pool, struct ttm_tt *tt, if (flags->purge) { shrunken += num_pages; page->private = 0; - __free_pages(page, order); + __free_pages_gpu_account(page, order, false); memset(tt->pages + i, 0, num_pages * sizeof(*tt->pages)); } @@ -1109,7 +1115,7 @@ long ttm_pool_backup(struct ttm_pool *pool, struct ttm_tt *tt, } handle = shandle; tt->pages[i] = ttm_backup_handle_to_page_ptr(handle); - put_page(page); + __free_pages_gpu_account(page, 0, false); shrunken++; } diff --git a/drivers/gpu/drm/udl/udl_main.c b/drivers/gpu/drm/udl/udl_main.c index 08a0e9480d70..17950fe3a0ec 100644 --- a/drivers/gpu/drm/udl/udl_main.c +++ b/drivers/gpu/drm/udl/udl_main.c @@ -285,13 +285,12 @@ static struct urb *udl_get_urb_locked(struct udl_device *udl, long timeout) return unode->urb; } -#define GET_URB_TIMEOUT HZ struct urb *udl_get_urb(struct udl_device *udl) { struct urb *urb; spin_lock_irq(&udl->urbs.lock); - urb = udl_get_urb_locked(udl, GET_URB_TIMEOUT); + urb = udl_get_urb_locked(udl, HZ * 2); spin_unlock_irq(&udl->urbs.lock); return urb; } diff --git a/drivers/gpu/drm/udl/udl_modeset.c b/drivers/gpu/drm/udl/udl_modeset.c index 231e829bd709..1ca073a4ecb2 100644 --- a/drivers/gpu/drm/udl/udl_modeset.c +++ b/drivers/gpu/drm/udl/udl_modeset.c @@ -21,6 +21,7 @@ #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_gem_shmem_helper.h> #include <drm/drm_modeset_helper_vtables.h> +#include <drm/drm_print.h> #include <drm/drm_probe_helper.h> #include <drm/drm_vblank.h> @@ -342,8 +343,10 @@ static void udl_crtc_helper_atomic_enable(struct drm_crtc *crtc, struct drm_atom return; urb = udl_get_urb(udl); - if (!urb) + if (!urb) { + drm_err_ratelimited(dev, "get urb failed when enabling crtc\n"); goto out; + } buf = (char *)urb->transfer_buffer; buf = udl_vidreg_lock(buf); diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile index 49de1c22a469..03242e8b3d87 100644 --- a/drivers/gpu/drm/xe/Makefile +++ b/drivers/gpu/drm/xe/Makefile @@ -88,6 +88,7 @@ xe-y += xe_bb.o \ xe_irq.o \ xe_late_bind_fw.o \ xe_lrc.o \ + xe_mem_pool.o \ xe_migrate.o \ xe_mmio.o \ xe_mmio_gem.o \ diff --git a/drivers/gpu/drm/xe/display/xe_hdcp_gsc.c b/drivers/gpu/drm/xe/display/xe_hdcp_gsc.c index 29c72aa4b0d2..33494b86205d 100644 --- a/drivers/gpu/drm/xe/display/xe_hdcp_gsc.c +++ b/drivers/gpu/drm/xe/display/xe_hdcp_gsc.c @@ -37,9 +37,17 @@ static bool intel_hdcp_gsc_check_status(struct drm_device *drm) struct xe_device *xe = to_xe_device(drm); struct xe_tile *tile = xe_device_get_root_tile(xe); struct xe_gt *gt = tile->media_gt; - struct xe_gsc *gsc = >->uc.gsc; + struct xe_gsc *gsc; + + if (!gt) { + drm_dbg_kms(&xe->drm, + "not checking GSC status for HDCP2.x: media GT not present or disabled\n"); + return false; + } + + gsc = >->uc.gsc; - if (!gsc || !xe_uc_fw_is_available(&gsc->fw)) { + if (!xe_uc_fw_is_available(&gsc->fw)) { drm_dbg_kms(&xe->drm, "GSC Components not ready for HDCP2.x\n"); return false; diff --git a/drivers/gpu/drm/xe/regs/xe_gt_regs.h b/drivers/gpu/drm/xe/regs/xe_gt_regs.h index 4ebaa0888a43..9c88ca3ce768 100644 --- a/drivers/gpu/drm/xe/regs/xe_gt_regs.h +++ b/drivers/gpu/drm/xe/regs/xe_gt_regs.h @@ -583,7 +583,7 @@ #define DISABLE_128B_EVICTION_COMMAND_UDW REG_BIT(36 - 32) #define LSCFE_SAME_ADDRESS_ATOMICS_COALESCING_DISABLE REG_BIT(35 - 32) -#define ROW_CHICKEN5 XE_REG_MCR(0xe7f0) +#define ROW_CHICKEN5 XE_REG_MCR(0xe7f0, XE_REG_OPTION_MASKED) #define CPSS_AWARE_DIS REG_BIT(3) #define SARB_CHICKEN1 XE_REG_MCR(0xe90c) diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index a7c2dc7f224c..4075edf97421 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -2322,8 +2322,10 @@ struct xe_bo *xe_bo_init_locked(struct xe_device *xe, struct xe_bo *bo, } /* XE_BO_FLAG_GGTTx requires XE_BO_FLAG_GGTT also be set */ - if ((flags & XE_BO_FLAG_GGTT_ALL) && !(flags & XE_BO_FLAG_GGTT)) + if ((flags & XE_BO_FLAG_GGTT_ALL) && !(flags & XE_BO_FLAG_GGTT)) { + xe_bo_free(bo); return ERR_PTR(-EINVAL); + } if (flags & (XE_BO_FLAG_VRAM_MASK | XE_BO_FLAG_STOLEN) && !(flags & XE_BO_FLAG_IGNORE_MIN_PAGE_SIZE) && @@ -2342,8 +2344,10 @@ struct xe_bo *xe_bo_init_locked(struct xe_device *xe, struct xe_bo *bo, alignment = SZ_4K >> PAGE_SHIFT; } - if (type == ttm_bo_type_device && aligned_size != size) + if (type == ttm_bo_type_device && aligned_size != size) { + xe_bo_free(bo); return ERR_PTR(-EINVAL); + } if (!bo) { bo = xe_bo_alloc(); diff --git a/drivers/gpu/drm/xe/xe_bo_types.h b/drivers/gpu/drm/xe/xe_bo_types.h index ff8317bfc1ae..9d19940b8fc0 100644 --- a/drivers/gpu/drm/xe/xe_bo_types.h +++ b/drivers/gpu/drm/xe/xe_bo_types.h @@ -18,6 +18,7 @@ #include "xe_ggtt_types.h" struct xe_device; +struct xe_mem_pool_node; struct xe_vm; #define XE_BO_MAX_PLACEMENTS 3 @@ -88,7 +89,7 @@ struct xe_bo { bool ccs_cleared; /** @bb_ccs: BB instructions of CCS read/write. Valid only for VF */ - struct xe_bb *bb_ccs[XE_SRIOV_VF_CCS_CTX_COUNT]; + struct xe_mem_pool_node *bb_ccs[XE_SRIOV_VF_CCS_CTX_COUNT]; /** * @cpu_caching: CPU caching mode. Currently only used for userspace diff --git a/drivers/gpu/drm/xe/xe_dma_buf.c b/drivers/gpu/drm/xe/xe_dma_buf.c index 7f9602b3363d..b9828da15897 100644 --- a/drivers/gpu/drm/xe/xe_dma_buf.c +++ b/drivers/gpu/drm/xe/xe_dma_buf.c @@ -258,6 +258,13 @@ out_unlock: return ERR_PTR(ret); } +/* + * Takes ownership of @storage: on success it is transferred to the returned + * drm_gem_object; on failure it is freed before returning the error. + * This matches the contract of xe_bo_init_locked() which frees @storage on + * its error paths, so callers need not (and must not) free @storage after + * this call. + */ static struct drm_gem_object * xe_dma_buf_init_obj(struct drm_device *dev, struct xe_bo *storage, struct dma_buf *dma_buf) @@ -271,8 +278,10 @@ xe_dma_buf_init_obj(struct drm_device *dev, struct xe_bo *storage, int ret = 0; dummy_obj = drm_gpuvm_resv_object_alloc(&xe->drm); - if (!dummy_obj) + if (!dummy_obj) { + xe_bo_free(storage); return ERR_PTR(-ENOMEM); + } dummy_obj->resv = resv; xe_validation_guard(&ctx, &xe->val, &exec, (struct xe_val_flags) {}, ret) { @@ -281,6 +290,7 @@ xe_dma_buf_init_obj(struct drm_device *dev, struct xe_bo *storage, if (ret) break; + /* xe_bo_init_locked() frees storage on error */ bo = xe_bo_init_locked(xe, storage, NULL, resv, NULL, dma_buf->size, 0, /* Will require 1way or 2way for vm_bind */ ttm_bo_type_sg, XE_BO_FLAG_SYSTEM, &exec); @@ -368,12 +378,15 @@ struct drm_gem_object *xe_gem_prime_import(struct drm_device *dev, goto out_err; } - /* Errors here will take care of freeing the bo. */ + /* + * xe_dma_buf_init_obj() takes ownership of bo on both success + * and failure, so we must not touch bo after this call. + */ obj = xe_dma_buf_init_obj(dev, bo, dma_buf); - if (IS_ERR(obj)) + if (IS_ERR(obj)) { + dma_buf_detach(dma_buf, attach); return obj; - - + } get_dma_buf(dma_buf); obj->import_attach = attach; return obj; diff --git a/drivers/gpu/drm/xe/xe_eu_stall.c b/drivers/gpu/drm/xe/xe_eu_stall.c index c34408cfd292..dddcdd0bb7a3 100644 --- a/drivers/gpu/drm/xe/xe_eu_stall.c +++ b/drivers/gpu/drm/xe/xe_eu_stall.c @@ -869,14 +869,14 @@ static int xe_eu_stall_stream_close(struct inode *inode, struct file *file) struct xe_eu_stall_data_stream *stream = file->private_data; struct xe_gt *gt = stream->gt; - drm_dev_put(>->tile->xe->drm); - mutex_lock(>->eu_stall->stream_lock); xe_eu_stall_disable_locked(stream); xe_eu_stall_data_buf_destroy(stream); xe_eu_stall_stream_free(stream); mutex_unlock(>->eu_stall->stream_lock); + drm_dev_put(>->tile->xe->drm); + return 0; } diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c index b287d0e0e60a..071b8c41df43 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.c +++ b/drivers/gpu/drm/xe/xe_exec_queue.c @@ -1405,7 +1405,7 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data, if (q->vm && q->hwe->hw_engine_group) { err = xe_hw_engine_group_add_exec_queue(q->hwe->hw_engine_group, q); if (err) - goto put_exec_queue; + goto kill_exec_queue; } } @@ -1416,12 +1416,15 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data, /* user id alloc must always be last in ioctl to prevent UAF */ err = xa_alloc(&xef->exec_queue.xa, &id, q, xa_limit_32b, GFP_KERNEL); if (err) - goto kill_exec_queue; + goto del_hw_engine_group; args->exec_queue_id = id; return 0; +del_hw_engine_group: + if (q->vm && q->hwe && q->hwe->hw_engine_group) + xe_hw_engine_group_del_exec_queue(q->hwe->hw_engine_group, q); kill_exec_queue: xe_exec_queue_kill(q); delete_queue_group: @@ -1760,7 +1763,7 @@ void xe_exec_queue_tlb_inval_last_fence_put(struct xe_exec_queue *q, void xe_exec_queue_tlb_inval_last_fence_put_unlocked(struct xe_exec_queue *q, unsigned int type) { - xe_assert(q->vm->xe, type == XE_EXEC_QUEUE_TLB_INVAL_MEDIA_GT || + xe_assert(gt_to_xe(q->gt), type == XE_EXEC_QUEUE_TLB_INVAL_MEDIA_GT || type == XE_EXEC_QUEUE_TLB_INVAL_PRIMARY_GT); dma_fence_put(q->tlb_inval[type].last_fence); diff --git a/drivers/gpu/drm/xe/xe_gsc.c b/drivers/gpu/drm/xe/xe_gsc.c index e5c234f3d795..0d13e357fb43 100644 --- a/drivers/gpu/drm/xe/xe_gsc.c +++ b/drivers/gpu/drm/xe/xe_gsc.c @@ -166,7 +166,7 @@ static int query_compatibility_version(struct xe_gsc *gsc) &rd_offset); if (err) { xe_gt_err(gt, "HuC: invalid GSC reply for version query (err=%d)\n", err); - return err; + goto out_bo; } compat->major = version_query_rd(xe, &bo->vmap, rd_offset, proj_major); diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c index 87a164efcc33..01fe03b9efe8 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c @@ -385,10 +385,10 @@ static int pf_migration_mmio_save(struct xe_gt *gt, unsigned int vfid, void *buf if (xe_gt_is_media_type(gt)) for (n = 0; n < MED_VF_SW_FLAG_COUNT; n++) - regs[n] = xe_mmio_read32(>->mmio, MED_VF_SW_FLAG(n)); + regs[n] = xe_mmio_read32(&mmio, MED_VF_SW_FLAG(n)); else for (n = 0; n < VF_SW_FLAG_COUNT; n++) - regs[n] = xe_mmio_read32(>->mmio, VF_SW_FLAG(n)); + regs[n] = xe_mmio_read32(&mmio, VF_SW_FLAG(n)); return 0; } @@ -407,10 +407,10 @@ static int pf_migration_mmio_restore(struct xe_gt *gt, unsigned int vfid, if (xe_gt_is_media_type(gt)) for (n = 0; n < MED_VF_SW_FLAG_COUNT; n++) - xe_mmio_write32(>->mmio, MED_VF_SW_FLAG(n), regs[n]); + xe_mmio_write32(&mmio, MED_VF_SW_FLAG(n), regs[n]); else for (n = 0; n < VF_SW_FLAG_COUNT; n++) - xe_mmio_write32(>->mmio, VF_SW_FLAG(n), regs[n]); + xe_mmio_write32(&mmio, VF_SW_FLAG(n), regs[n]); return 0; } diff --git a/drivers/gpu/drm/xe/xe_guc_ads.c b/drivers/gpu/drm/xe/xe_guc_ads.c index 81b5f01b1f65..2b835d48b565 100644 --- a/drivers/gpu/drm/xe/xe_guc_ads.c +++ b/drivers/gpu/drm/xe/xe_guc_ads.c @@ -512,12 +512,9 @@ static void guc_golden_lrc_init(struct xe_guc_ads *ads) * that starts after the execlists LRC registers. This is * required to allow the GuC to restore just the engine state * when a watchdog reset occurs. - * We calculate the engine state size by removing the size of - * what comes before it in the context image (which is identical - * on all engines). */ ads_blob_write(ads, ads.eng_state_size[guc_class], - real_size - xe_lrc_skip_size(xe)); + xe_lrc_engine_state_size(gt, class)); ads_blob_write(ads, ads.golden_context_lrca[guc_class], addr_ggtt); diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c index a145234f662b..10556156eaad 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.c +++ b/drivers/gpu/drm/xe/xe_guc_submit.c @@ -261,22 +261,10 @@ static void guc_submit_sw_fini(struct drm_device *drm, void *arg) static void guc_submit_fini(void *arg) { struct xe_guc *guc = arg; - - /* Forcefully kill any remaining exec queues */ - xe_guc_ct_stop(&guc->ct); - guc_submit_reset_prepare(guc); - xe_guc_softreset(guc); - xe_guc_submit_stop(guc); - xe_uc_fw_sanitize(&guc->fw); - xe_guc_submit_pause_abort(guc); -} - -static void guc_submit_wedged_fini(void *arg) -{ - struct xe_guc *guc = arg; struct xe_exec_queue *q; unsigned long index; + /* Drop any wedged queue refs */ mutex_lock(&guc->submission_state.lock); xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) { if (exec_queue_wedged(q)) { @@ -286,6 +274,14 @@ static void guc_submit_wedged_fini(void *arg) } } mutex_unlock(&guc->submission_state.lock); + + /* Forcefully kill any remaining exec queues */ + xe_guc_ct_stop(&guc->ct); + guc_submit_reset_prepare(guc); + xe_guc_softreset(guc); + xe_guc_submit_stop(guc); + xe_uc_fw_sanitize(&guc->fw); + xe_guc_submit_pause_abort(guc); } static const struct xe_exec_queue_ops guc_exec_queue_ops; @@ -1320,10 +1316,8 @@ static void disable_scheduling_deregister(struct xe_guc *guc, void xe_guc_submit_wedge(struct xe_guc *guc) { struct xe_device *xe = guc_to_xe(guc); - struct xe_gt *gt = guc_to_gt(guc); struct xe_exec_queue *q; unsigned long index; - int err; xe_gt_assert(guc_to_gt(guc), guc_to_xe(guc)->wedged.mode); @@ -1335,15 +1329,6 @@ void xe_guc_submit_wedge(struct xe_guc *guc) return; if (xe->wedged.mode == XE_WEDGED_MODE_UPON_ANY_HANG_NO_RESET) { - err = devm_add_action_or_reset(guc_to_xe(guc)->drm.dev, - guc_submit_wedged_fini, guc); - if (err) { - xe_gt_err(gt, "Failed to register clean-up on wedged.mode=%s; " - "Although device is wedged.\n", - xe_wedged_mode_to_string(XE_WEDGED_MODE_UPON_ANY_HANG_NO_RESET)); - return; - } - mutex_lock(&guc->submission_state.lock); xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) if (xe_exec_queue_get_unless_zero(q)) diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c index 9d12a0d2f0b5..4af9f0d7c6f3 100644 --- a/drivers/gpu/drm/xe/xe_lrc.c +++ b/drivers/gpu/drm/xe/xe_lrc.c @@ -746,9 +746,16 @@ size_t xe_lrc_reg_size(struct xe_device *xe) return 80 * sizeof(u32); } -size_t xe_lrc_skip_size(struct xe_device *xe) +/** + * xe_lrc_engine_state_size() - Get size of the engine state within LRC + * @gt: the &xe_gt struct instance + * @class: Hardware engine class + * + * Returns: Size of the engine state + */ +size_t xe_lrc_engine_state_size(struct xe_gt *gt, enum xe_engine_class class) { - return LRC_PPHWSP_SIZE + xe_lrc_reg_size(xe); + return xe_gt_lrc_hang_replay_size(gt, class) - xe_lrc_reg_size(gt_to_xe(gt)); } static inline u32 __xe_lrc_seqno_offset(struct xe_lrc *lrc) @@ -1214,7 +1221,7 @@ static ssize_t setup_invalidate_state_cache_wa(struct xe_lrc *lrc, if (xe_gt_WARN_ON(lrc->gt, max_len < 3)) return -ENOSPC; - *cmd++ = MI_LOAD_REGISTER_IMM | MI_LRI_NUM_REGS(1); + *cmd++ = MI_LOAD_REGISTER_IMM | MI_LRI_LRM_CS_MMIO | MI_LRI_NUM_REGS(1); *cmd++ = CS_DEBUG_MODE2(0).addr; *cmd++ = REG_MASKED_FIELD_ENABLE(INSTRUCTION_STATE_CACHE_INVALIDATE); diff --git a/drivers/gpu/drm/xe/xe_lrc.h b/drivers/gpu/drm/xe/xe_lrc.h index e7c975f9e2d9..5440663183f6 100644 --- a/drivers/gpu/drm/xe/xe_lrc.h +++ b/drivers/gpu/drm/xe/xe_lrc.h @@ -130,7 +130,7 @@ u32 xe_lrc_parallel_ggtt_addr(struct xe_lrc *lrc); struct iosys_map xe_lrc_parallel_map(struct xe_lrc *lrc); size_t xe_lrc_reg_size(struct xe_device *xe); -size_t xe_lrc_skip_size(struct xe_device *xe); +size_t xe_lrc_engine_state_size(struct xe_gt *gt, enum xe_engine_class class); void xe_lrc_dump_default(struct drm_printer *p, struct xe_gt *gt, diff --git a/drivers/gpu/drm/xe/xe_mem_pool.c b/drivers/gpu/drm/xe/xe_mem_pool.c new file mode 100644 index 000000000000..d5e24d6aa88d --- /dev/null +++ b/drivers/gpu/drm/xe/xe_mem_pool.c @@ -0,0 +1,403 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2026 Intel Corporation + */ + +#include <linux/kernel.h> + +#include <drm/drm_managed.h> + +#include "instructions/xe_mi_commands.h" +#include "xe_bo.h" +#include "xe_device_types.h" +#include "xe_map.h" +#include "xe_mem_pool.h" +#include "xe_mem_pool_types.h" +#include "xe_tile_printk.h" + +/** + * struct xe_mem_pool - DRM MM pool for sub-allocating memory from a BO on an + * XE tile. + * + * The XE memory pool is a DRM MM manager that provides sub-allocation of memory + * from a backing buffer object (BO) on a specific XE tile. It is designed to + * manage memory for GPU workloads, allowing for efficient allocation and + * deallocation of memory regions within the BO. + * + * The memory pool maintains a primary BO that is pinned in the GGTT and mapped + * into the CPU address space for direct access. Optionally, it can also maintain + * a shadow BO that can be used for atomic updates to the primary BO's contents. + * + * The API provided by the memory pool allows clients to allocate and free memory + * regions, retrieve GPU and CPU addresses, and synchronize data between the + * primary and shadow BOs as needed. + */ +struct xe_mem_pool { + /** @base: Range allocator over [0, @size) in bytes */ + struct drm_mm base; + /** @bo: Active pool BO (GGTT-pinned, CPU-mapped). */ + struct xe_bo *bo; + /** @shadow: Shadow BO for atomic command updates. */ + struct xe_bo *shadow; + /** @swap_guard: Timeline guard updating @bo and @shadow */ + struct mutex swap_guard; + /** @cpu_addr: CPU virtual address of the active BO. */ + void *cpu_addr; + /** @is_iomem: Indicates if the BO mapping is I/O memory. */ + bool is_iomem; +}; + +static struct xe_mem_pool *node_to_pool(struct xe_mem_pool_node *node) +{ + return container_of(node->sa_node.mm, struct xe_mem_pool, base); +} + +static struct xe_tile *pool_to_tile(struct xe_mem_pool *pool) +{ + return pool->bo->tile; +} + +static void fini_pool_action(struct drm_device *drm, void *arg) +{ + struct xe_mem_pool *pool = arg; + + if (pool->is_iomem) + kvfree(pool->cpu_addr); + + drm_mm_takedown(&pool->base); +} + +static int pool_shadow_init(struct xe_mem_pool *pool) +{ + struct xe_tile *tile = pool->bo->tile; + struct xe_device *xe = tile_to_xe(tile); + struct xe_bo *shadow; + int ret; + + xe_assert(xe, !pool->shadow); + + ret = drmm_mutex_init(&xe->drm, &pool->swap_guard); + if (ret) + return ret; + + if (IS_ENABLED(CONFIG_PROVE_LOCKING)) { + fs_reclaim_acquire(GFP_KERNEL); + might_lock(&pool->swap_guard); + fs_reclaim_release(GFP_KERNEL); + } + shadow = xe_managed_bo_create_pin_map(xe, tile, + xe_bo_size(pool->bo), + XE_BO_FLAG_VRAM_IF_DGFX(tile) | + XE_BO_FLAG_GGTT | + XE_BO_FLAG_GGTT_INVALIDATE | + XE_BO_FLAG_PINNED_NORESTORE); + if (IS_ERR(shadow)) + return PTR_ERR(shadow); + + pool->shadow = shadow; + + return 0; +} + +/** + * xe_mem_pool_init() - Initialize memory pool. + * @tile: the &xe_tile where allocate. + * @size: number of bytes to allocate. + * @guard: the size of the guard region at the end of the BO that is not + * sub-allocated, in bytes. + * @flags: flags to use to create shadow pool. + * + * Initializes a memory pool for sub-allocating memory from a backing BO on the + * specified XE tile. The backing BO is pinned in the GGTT and mapped into + * the CPU address space for direct access. Optionally, a shadow BO can also be + * initialized for atomic updates to the primary BO's contents. + * + * Returns: a pointer to the &xe_mem_pool, or an error pointer on failure. + */ +struct xe_mem_pool *xe_mem_pool_init(struct xe_tile *tile, u32 size, + u32 guard, int flags) +{ + struct xe_device *xe = tile_to_xe(tile); + struct xe_mem_pool *pool; + struct xe_bo *bo; + u32 managed_size; + int ret; + + xe_tile_assert(tile, size > guard); + managed_size = size - guard; + + pool = drmm_kzalloc(&xe->drm, sizeof(*pool), GFP_KERNEL); + if (!pool) + return ERR_PTR(-ENOMEM); + + bo = xe_managed_bo_create_pin_map(xe, tile, size, + XE_BO_FLAG_VRAM_IF_DGFX(tile) | + XE_BO_FLAG_GGTT | + XE_BO_FLAG_GGTT_INVALIDATE | + XE_BO_FLAG_PINNED_NORESTORE); + if (IS_ERR(bo)) { + xe_tile_err(tile, "Failed to prepare %uKiB BO for mem pool (%pe)\n", + size / SZ_1K, bo); + return ERR_CAST(bo); + } + pool->bo = bo; + pool->is_iomem = bo->vmap.is_iomem; + + if (pool->is_iomem) { + pool->cpu_addr = kvzalloc(size, GFP_KERNEL); + if (!pool->cpu_addr) + return ERR_PTR(-ENOMEM); + } else { + pool->cpu_addr = bo->vmap.vaddr; + } + + if (flags & XE_MEM_POOL_BO_FLAG_INIT_SHADOW_COPY) { + ret = pool_shadow_init(pool); + + if (ret) + goto out_err; + } + + drm_mm_init(&pool->base, 0, managed_size); + ret = drmm_add_action_or_reset(&xe->drm, fini_pool_action, pool); + if (ret) + return ERR_PTR(ret); + + return pool; + +out_err: + if (flags & XE_MEM_POOL_BO_FLAG_INIT_SHADOW_COPY) + xe_tile_err(tile, + "Failed to initialize shadow BO for mem pool (%d)\n", ret); + if (bo->vmap.is_iomem) + kvfree(pool->cpu_addr); + return ERR_PTR(ret); +} + +/** + * xe_mem_pool_sync() - Copy the entire contents of the main pool to shadow pool. + * @pool: the memory pool containing the primary and shadow BOs. + * + * Copies the entire contents of the primary pool to the shadow pool. This must + * be done after xe_mem_pool_init() with the XE_MEM_POOL_BO_FLAG_INIT_SHADOW_COPY + * flag to ensure that the shadow pool has the same initial contents as the primary + * pool. After this initial synchronization, clients can choose to synchronize the + * shadow pool with the primary pool on a node basis using + * xe_mem_pool_sync_shadow_locked() as needed. + * + * Return: None. + */ +void xe_mem_pool_sync(struct xe_mem_pool *pool) +{ + struct xe_tile *tile = pool_to_tile(pool); + struct xe_device *xe = tile_to_xe(tile); + + xe_tile_assert(tile, pool->shadow); + + xe_map_memcpy_to(xe, &pool->shadow->vmap, 0, + pool->cpu_addr, xe_bo_size(pool->bo)); +} + +/** + * xe_mem_pool_swap_shadow_locked() - Swap the primary BO with the shadow BO. + * @pool: the memory pool containing the primary and shadow BOs. + * + * Swaps the primary buffer object with the shadow buffer object in the mem + * pool. This allows for atomic updates to the contents of the primary BO + * by first writing to the shadow BO and then swapping it with the primary BO. + * Swap_guard must be held to ensure synchronization with any concurrent swap + * operations. + * + * Return: None. + */ +void xe_mem_pool_swap_shadow_locked(struct xe_mem_pool *pool) +{ + struct xe_tile *tile = pool_to_tile(pool); + + xe_tile_assert(tile, pool->shadow); + lockdep_assert_held(&pool->swap_guard); + + swap(pool->bo, pool->shadow); + if (!pool->bo->vmap.is_iomem) + pool->cpu_addr = pool->bo->vmap.vaddr; +} + +/** + * xe_mem_pool_sync_shadow_locked() - Copy node from primary pool to shadow pool. + * @node: the node allocated in the memory pool. + * + * Copies the specified batch buffer from the primary pool to the shadow pool. + * Swap_guard must be held to ensure synchronization with any concurrent swap + * operations. + * + * Return: None. + */ +void xe_mem_pool_sync_shadow_locked(struct xe_mem_pool_node *node) +{ + struct xe_mem_pool *pool = node_to_pool(node); + struct xe_tile *tile = pool_to_tile(pool); + struct xe_device *xe = tile_to_xe(tile); + struct drm_mm_node *sa_node = &node->sa_node; + + xe_tile_assert(tile, pool->shadow); + lockdep_assert_held(&pool->swap_guard); + + xe_map_memcpy_to(xe, &pool->shadow->vmap, + sa_node->start, + pool->cpu_addr + sa_node->start, + sa_node->size); +} + +/** + * xe_mem_pool_gpu_addr() - Retrieve GPU address of memory pool. + * @pool: the memory pool + * + * Returns: GGTT address of the memory pool. + */ +u64 xe_mem_pool_gpu_addr(struct xe_mem_pool *pool) +{ + return xe_bo_ggtt_addr(pool->bo); +} + +/** + * xe_mem_pool_cpu_addr() - Retrieve CPU address of manager pool. + * @pool: the memory pool + * + * Returns: CPU virtual address of memory pool. + */ +void *xe_mem_pool_cpu_addr(struct xe_mem_pool *pool) +{ + return pool->cpu_addr; +} + +/** + * xe_mem_pool_bo_swap_guard() - Retrieve the mutex used to guard swap + * operations on a memory pool. + * @pool: the memory pool + * + * Returns: Swap guard mutex or NULL if shadow pool is not created. + */ +struct mutex *xe_mem_pool_bo_swap_guard(struct xe_mem_pool *pool) +{ + if (!pool->shadow) + return NULL; + + return &pool->swap_guard; +} + +/** + * xe_mem_pool_bo_flush_write() - Copy the data from the sub-allocation + * to the GPU memory. + * @node: the node allocated in the memory pool to flush. + */ +void xe_mem_pool_bo_flush_write(struct xe_mem_pool_node *node) +{ + struct xe_mem_pool *pool = node_to_pool(node); + struct xe_tile *tile = pool_to_tile(pool); + struct xe_device *xe = tile_to_xe(tile); + struct drm_mm_node *sa_node = &node->sa_node; + + if (!pool->bo->vmap.is_iomem) + return; + + xe_map_memcpy_to(xe, &pool->bo->vmap, sa_node->start, + pool->cpu_addr + sa_node->start, + sa_node->size); +} + +/** + * xe_mem_pool_bo_sync_read() - Copy the data from GPU memory to the + * sub-allocation. + * @node: the node allocated in the memory pool to read back. + */ +void xe_mem_pool_bo_sync_read(struct xe_mem_pool_node *node) +{ + struct xe_mem_pool *pool = node_to_pool(node); + struct xe_tile *tile = pool_to_tile(pool); + struct xe_device *xe = tile_to_xe(tile); + struct drm_mm_node *sa_node = &node->sa_node; + + if (!pool->bo->vmap.is_iomem) + return; + + xe_map_memcpy_from(xe, pool->cpu_addr + sa_node->start, + &pool->bo->vmap, sa_node->start, sa_node->size); +} + +/** + * xe_mem_pool_alloc_node() - Allocate a new node for use with xe_mem_pool. + * + * Returns: node structure or an ERR_PTR(-ENOMEM). + */ +struct xe_mem_pool_node *xe_mem_pool_alloc_node(void) +{ + struct xe_mem_pool_node *node = kzalloc_obj(*node); + + if (!node) + return ERR_PTR(-ENOMEM); + + return node; +} + +/** + * xe_mem_pool_insert_node() - Insert a node into the memory pool. + * @pool: the memory pool to insert into + * @node: the node to insert + * @size: the size of the node to be allocated in bytes. + * + * Inserts a node into the specified memory pool using drm_mm for + * allocation. + * + * Returns: 0 on success or a negative error code on failure. + */ +int xe_mem_pool_insert_node(struct xe_mem_pool *pool, + struct xe_mem_pool_node *node, u32 size) +{ + if (!pool) + return -EINVAL; + + return drm_mm_insert_node(&pool->base, &node->sa_node, size); +} + +/** + * xe_mem_pool_free_node() - Free a node allocated from the memory pool. + * @node: the node to free + * + * Returns: None. + */ +void xe_mem_pool_free_node(struct xe_mem_pool_node *node) +{ + if (!node) + return; + + drm_mm_remove_node(&node->sa_node); + kfree(node); +} + +/** + * xe_mem_pool_node_cpu_addr() - Retrieve CPU address of the node. + * @node: the node allocated in the memory pool + * + * Returns: CPU virtual address of the node. + */ +void *xe_mem_pool_node_cpu_addr(struct xe_mem_pool_node *node) +{ + struct xe_mem_pool *pool = node_to_pool(node); + + return xe_mem_pool_cpu_addr(pool) + node->sa_node.start; +} + +/** + * xe_mem_pool_dump() - Dump the state of the DRM MM manager for debugging. + * @pool: the memory pool info be dumped. + * @p: The DRM printer to use for output. + * + * Only the drm managed region is dumped, not the state of the BOs or any other + * pool information. + * + * Returns: None. + */ +void xe_mem_pool_dump(struct xe_mem_pool *pool, struct drm_printer *p) +{ + drm_mm_print(&pool->base, p); +} diff --git a/drivers/gpu/drm/xe/xe_mem_pool.h b/drivers/gpu/drm/xe/xe_mem_pool.h new file mode 100644 index 000000000000..89cd2555fe91 --- /dev/null +++ b/drivers/gpu/drm/xe/xe_mem_pool.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2026 Intel Corporation + */ +#ifndef _XE_MEM_POOL_H_ +#define _XE_MEM_POOL_H_ + +#include <linux/sizes.h> +#include <linux/types.h> + +#include <drm/drm_mm.h> +#include "xe_mem_pool_types.h" + +struct drm_printer; +struct xe_mem_pool; +struct xe_tile; + +struct xe_mem_pool *xe_mem_pool_init(struct xe_tile *tile, u32 size, + u32 guard, int flags); +void xe_mem_pool_sync(struct xe_mem_pool *pool); +void xe_mem_pool_swap_shadow_locked(struct xe_mem_pool *pool); +void xe_mem_pool_sync_shadow_locked(struct xe_mem_pool_node *node); +u64 xe_mem_pool_gpu_addr(struct xe_mem_pool *pool); +void *xe_mem_pool_cpu_addr(struct xe_mem_pool *pool); +struct mutex *xe_mem_pool_bo_swap_guard(struct xe_mem_pool *pool); +void xe_mem_pool_bo_flush_write(struct xe_mem_pool_node *node); +void xe_mem_pool_bo_sync_read(struct xe_mem_pool_node *node); +struct xe_mem_pool_node *xe_mem_pool_alloc_node(void); +int xe_mem_pool_insert_node(struct xe_mem_pool *pool, + struct xe_mem_pool_node *node, u32 size); +void xe_mem_pool_free_node(struct xe_mem_pool_node *node); +void *xe_mem_pool_node_cpu_addr(struct xe_mem_pool_node *node); +void xe_mem_pool_dump(struct xe_mem_pool *pool, struct drm_printer *p); + +#endif diff --git a/drivers/gpu/drm/xe/xe_mem_pool_types.h b/drivers/gpu/drm/xe/xe_mem_pool_types.h new file mode 100644 index 000000000000..d5e926c93351 --- /dev/null +++ b/drivers/gpu/drm/xe/xe_mem_pool_types.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2026 Intel Corporation + */ + +#ifndef _XE_MEM_POOL_TYPES_H_ +#define _XE_MEM_POOL_TYPES_H_ + +#include <drm/drm_mm.h> + +#define XE_MEM_POOL_BO_FLAG_INIT_SHADOW_COPY BIT(0) + +/** + * struct xe_mem_pool_node - Sub-range allocations from mem pool. + */ +struct xe_mem_pool_node { + /** @sa_node: drm_mm_node for this allocation. */ + struct drm_mm_node sa_node; +}; + +#endif diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c index fc918b4fba54..5fdc89ed5256 100644 --- a/drivers/gpu/drm/xe/xe_migrate.c +++ b/drivers/gpu/drm/xe/xe_migrate.c @@ -29,6 +29,7 @@ #include "xe_hw_engine.h" #include "xe_lrc.h" #include "xe_map.h" +#include "xe_mem_pool.h" #include "xe_mocs.h" #include "xe_printk.h" #include "xe_pt.h" @@ -1166,11 +1167,12 @@ int xe_migrate_ccs_rw_copy(struct xe_tile *tile, struct xe_exec_queue *q, u32 batch_size, batch_size_allocated; struct xe_device *xe = gt_to_xe(gt); struct xe_res_cursor src_it, ccs_it; + struct xe_mem_pool *bb_pool; struct xe_sriov_vf_ccs_ctx *ctx; - struct xe_sa_manager *bb_pool; u64 size = xe_bo_size(src_bo); - struct xe_bb *bb = NULL; + struct xe_mem_pool_node *bb; u64 src_L0, src_L0_ofs; + struct xe_bb xe_bb_tmp; u32 src_L0_pt; int err; @@ -1208,18 +1210,18 @@ int xe_migrate_ccs_rw_copy(struct xe_tile *tile, struct xe_exec_queue *q, size -= src_L0; } - bb = xe_bb_alloc(gt); + bb = xe_mem_pool_alloc_node(); if (IS_ERR(bb)) return PTR_ERR(bb); bb_pool = ctx->mem.ccs_bb_pool; - scoped_guard(mutex, xe_sa_bo_swap_guard(bb_pool)) { - xe_sa_bo_swap_shadow(bb_pool); + scoped_guard(mutex, xe_mem_pool_bo_swap_guard(bb_pool)) { + xe_mem_pool_swap_shadow_locked(bb_pool); - err = xe_bb_init(bb, bb_pool, batch_size); + err = xe_mem_pool_insert_node(bb_pool, bb, batch_size * sizeof(u32)); if (err) { xe_gt_err(gt, "BB allocation failed.\n"); - xe_bb_free(bb, NULL); + kfree(bb); return err; } @@ -1227,6 +1229,7 @@ int xe_migrate_ccs_rw_copy(struct xe_tile *tile, struct xe_exec_queue *q, size = xe_bo_size(src_bo); batch_size = 0; + xe_bb_tmp = (struct xe_bb){ .cs = xe_mem_pool_node_cpu_addr(bb), .len = 0 }; /* * Emit PTE and copy commands here. * The CCS copy command can only support limited size. If the size to be @@ -1255,24 +1258,27 @@ int xe_migrate_ccs_rw_copy(struct xe_tile *tile, struct xe_exec_queue *q, xe_assert(xe, IS_ALIGNED(ccs_it.start, PAGE_SIZE)); batch_size += EMIT_COPY_CCS_DW; - emit_pte(m, bb, src_L0_pt, false, true, &src_it, src_L0, src); + emit_pte(m, &xe_bb_tmp, src_L0_pt, false, true, &src_it, src_L0, src); - emit_pte(m, bb, ccs_pt, false, false, &ccs_it, ccs_size, src); + emit_pte(m, &xe_bb_tmp, ccs_pt, false, false, &ccs_it, ccs_size, src); - bb->len = emit_flush_invalidate(bb->cs, bb->len, flush_flags); - flush_flags = xe_migrate_ccs_copy(m, bb, src_L0_ofs, src_is_pltt, + xe_bb_tmp.len = emit_flush_invalidate(xe_bb_tmp.cs, xe_bb_tmp.len, + flush_flags); + flush_flags = xe_migrate_ccs_copy(m, &xe_bb_tmp, src_L0_ofs, src_is_pltt, src_L0_ofs, dst_is_pltt, src_L0, ccs_ofs, true); - bb->len = emit_flush_invalidate(bb->cs, bb->len, flush_flags); + xe_bb_tmp.len = emit_flush_invalidate(xe_bb_tmp.cs, xe_bb_tmp.len, + flush_flags); size -= src_L0; } - xe_assert(xe, (batch_size_allocated == bb->len)); + xe_assert(xe, (batch_size_allocated == xe_bb_tmp.len)); + xe_assert(xe, bb->sa_node.size == xe_bb_tmp.len * sizeof(u32)); src_bo->bb_ccs[read_write] = bb; xe_sriov_vf_ccs_rw_update_bb_addr(ctx); - xe_sa_bo_sync_shadow(bb->bo); + xe_mem_pool_sync_shadow_locked(bb); } return 0; @@ -1297,10 +1303,10 @@ int xe_migrate_ccs_rw_copy(struct xe_tile *tile, struct xe_exec_queue *q, void xe_migrate_ccs_rw_copy_clear(struct xe_bo *src_bo, enum xe_sriov_vf_ccs_rw_ctxs read_write) { - struct xe_bb *bb = src_bo->bb_ccs[read_write]; + struct xe_mem_pool_node *bb = src_bo->bb_ccs[read_write]; struct xe_device *xe = xe_bo_device(src_bo); + struct xe_mem_pool *bb_pool; struct xe_sriov_vf_ccs_ctx *ctx; - struct xe_sa_manager *bb_pool; u32 *cs; xe_assert(xe, IS_SRIOV_VF(xe)); @@ -1308,17 +1314,17 @@ void xe_migrate_ccs_rw_copy_clear(struct xe_bo *src_bo, ctx = &xe->sriov.vf.ccs.contexts[read_write]; bb_pool = ctx->mem.ccs_bb_pool; - guard(mutex) (xe_sa_bo_swap_guard(bb_pool)); - xe_sa_bo_swap_shadow(bb_pool); - - cs = xe_sa_bo_cpu_addr(bb->bo); - memset(cs, MI_NOOP, bb->len * sizeof(u32)); - xe_sriov_vf_ccs_rw_update_bb_addr(ctx); + scoped_guard(mutex, xe_mem_pool_bo_swap_guard(bb_pool)) { + xe_mem_pool_swap_shadow_locked(bb_pool); - xe_sa_bo_sync_shadow(bb->bo); + cs = xe_mem_pool_node_cpu_addr(bb); + memset(cs, MI_NOOP, bb->sa_node.size); + xe_sriov_vf_ccs_rw_update_bb_addr(ctx); - xe_bb_free(bb, NULL); - src_bo->bb_ccs[read_write] = NULL; + xe_mem_pool_sync_shadow_locked(bb); + xe_mem_pool_free_node(bb); + src_bo->bb_ccs[read_write] = NULL; + } } /** diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c index 01673d2b2464..9f98d0334164 100644 --- a/drivers/gpu/drm/xe/xe_pci.c +++ b/drivers/gpu/drm/xe/xe_pci.c @@ -118,6 +118,7 @@ static const struct xe_graphics_desc graphics_xe2 = { static const struct xe_graphics_desc graphics_xe3p_lpg = { XE2_GFX_FEATURES, + .has_indirect_ring_state = 1, .multi_queue_engine_class_mask = BIT(XE_ENGINE_CLASS_COPY) | BIT(XE_ENGINE_CLASS_COMPUTE), .num_geometry_xecore_fuse_regs = 3, .num_compute_xecore_fuse_regs = 3, diff --git a/drivers/gpu/drm/xe/xe_reg_whitelist.c b/drivers/gpu/drm/xe/xe_reg_whitelist.c index 80577e4b7437..8cc313182968 100644 --- a/drivers/gpu/drm/xe/xe_reg_whitelist.c +++ b/drivers/gpu/drm/xe/xe_reg_whitelist.c @@ -226,7 +226,7 @@ void xe_reg_whitelist_print_entry(struct drm_printer *p, unsigned int indent, } range_start = reg & REG_GENMASK(25, range_bit); - range_end = range_start | REG_GENMASK(range_bit, 0); + range_end = range_start | REG_GENMASK(range_bit - 1, 0); switch (val & RING_FORCE_TO_NONPRIV_ACCESS_MASK) { case RING_FORCE_TO_NONPRIV_ACCESS_RW: diff --git a/drivers/gpu/drm/xe/xe_sriov_pf_migration.c b/drivers/gpu/drm/xe/xe_sriov_pf_migration.c index 6c4b16409cc9..150a241110fb 100644 --- a/drivers/gpu/drm/xe/xe_sriov_pf_migration.c +++ b/drivers/gpu/drm/xe/xe_sriov_pf_migration.c @@ -149,10 +149,11 @@ pf_migration_consume(struct xe_device *xe, unsigned int vfid) for_each_gt(gt, xe, gt_id) { data = xe_gt_sriov_pf_migration_save_consume(gt, vfid); - if (data && PTR_ERR(data) != EAGAIN) + if (!data) + continue; + if (!IS_ERR(data) || PTR_ERR(data) != -EAGAIN) return data; - if (PTR_ERR(data) == -EAGAIN) - more_data = true; + more_data = true; } if (!more_data) diff --git a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c index db023fb66a27..09b99fb2608b 100644 --- a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c +++ b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c @@ -14,9 +14,9 @@ #include "xe_guc.h" #include "xe_guc_submit.h" #include "xe_lrc.h" +#include "xe_mem_pool.h" #include "xe_migrate.h" #include "xe_pm.h" -#include "xe_sa.h" #include "xe_sriov_printk.h" #include "xe_sriov_vf.h" #include "xe_sriov_vf_ccs.h" @@ -141,43 +141,47 @@ static u64 get_ccs_bb_pool_size(struct xe_device *xe) static int alloc_bb_pool(struct xe_tile *tile, struct xe_sriov_vf_ccs_ctx *ctx) { + struct xe_mem_pool *pool; struct xe_device *xe = tile_to_xe(tile); - struct xe_sa_manager *sa_manager; + u32 *pool_cpu_addr, *last_dw_addr; u64 bb_pool_size; - int offset, err; + int err; bb_pool_size = get_ccs_bb_pool_size(xe); xe_sriov_info(xe, "Allocating %s CCS BB pool size = %lldMB\n", ctx->ctx_id ? "Restore" : "Save", bb_pool_size / SZ_1M); - sa_manager = __xe_sa_bo_manager_init(tile, bb_pool_size, SZ_4K, SZ_16, - XE_SA_BO_MANAGER_FLAG_SHADOW); - - if (IS_ERR(sa_manager)) { - xe_sriov_err(xe, "Suballocator init failed with error: %pe\n", - sa_manager); - err = PTR_ERR(sa_manager); + pool = xe_mem_pool_init(tile, bb_pool_size, sizeof(u32), + XE_MEM_POOL_BO_FLAG_INIT_SHADOW_COPY); + if (IS_ERR(pool)) { + xe_sriov_err(xe, "xe_mem_pool_init failed with error: %pe\n", + pool); + err = PTR_ERR(pool); return err; } - offset = 0; - xe_map_memset(xe, &sa_manager->bo->vmap, offset, MI_NOOP, - bb_pool_size); - xe_map_memset(xe, &sa_manager->shadow->vmap, offset, MI_NOOP, - bb_pool_size); + pool_cpu_addr = xe_mem_pool_cpu_addr(pool); + memset(pool_cpu_addr, 0, bb_pool_size); - offset = bb_pool_size - sizeof(u32); - xe_map_wr(xe, &sa_manager->bo->vmap, offset, u32, MI_BATCH_BUFFER_END); - xe_map_wr(xe, &sa_manager->shadow->vmap, offset, u32, MI_BATCH_BUFFER_END); + last_dw_addr = pool_cpu_addr + (bb_pool_size / sizeof(u32)) - 1; + *last_dw_addr = MI_BATCH_BUFFER_END; - ctx->mem.ccs_bb_pool = sa_manager; + /** + * Sync the main copy and shadow copy so that the shadow copy is + * replica of main copy. We sync only BBs after init part. So, we + * need to make sure the main pool and shadow copy are in sync after + * this point. This is needed as GuC may read the BB commands from + * shadow copy. + */ + xe_mem_pool_sync(pool); + ctx->mem.ccs_bb_pool = pool; return 0; } static void ccs_rw_update_ring(struct xe_sriov_vf_ccs_ctx *ctx) { - u64 addr = xe_sa_manager_gpu_addr(ctx->mem.ccs_bb_pool); + u64 addr = xe_mem_pool_gpu_addr(ctx->mem.ccs_bb_pool); struct xe_lrc *lrc = xe_exec_queue_lrc(ctx->mig_q); u32 dw[10], i = 0; @@ -388,7 +392,7 @@ err_ret: #define XE_SRIOV_VF_CCS_RW_BB_ADDR_OFFSET (2 * sizeof(u32)) void xe_sriov_vf_ccs_rw_update_bb_addr(struct xe_sriov_vf_ccs_ctx *ctx) { - u64 addr = xe_sa_manager_gpu_addr(ctx->mem.ccs_bb_pool); + u64 addr = xe_mem_pool_gpu_addr(ctx->mem.ccs_bb_pool); struct xe_lrc *lrc = xe_exec_queue_lrc(ctx->mig_q); struct xe_device *xe = gt_to_xe(ctx->mig_q->gt); @@ -412,8 +416,8 @@ int xe_sriov_vf_ccs_attach_bo(struct xe_bo *bo) struct xe_device *xe = xe_bo_device(bo); enum xe_sriov_vf_ccs_rw_ctxs ctx_id; struct xe_sriov_vf_ccs_ctx *ctx; + struct xe_mem_pool_node *bb; struct xe_tile *tile; - struct xe_bb *bb; int err = 0; xe_assert(xe, IS_VF_CCS_READY(xe)); @@ -445,7 +449,7 @@ int xe_sriov_vf_ccs_detach_bo(struct xe_bo *bo) { struct xe_device *xe = xe_bo_device(bo); enum xe_sriov_vf_ccs_rw_ctxs ctx_id; - struct xe_bb *bb; + struct xe_mem_pool_node *bb; xe_assert(xe, IS_VF_CCS_READY(xe)); @@ -471,8 +475,8 @@ int xe_sriov_vf_ccs_detach_bo(struct xe_bo *bo) */ void xe_sriov_vf_ccs_print(struct xe_device *xe, struct drm_printer *p) { - struct xe_sa_manager *bb_pool; enum xe_sriov_vf_ccs_rw_ctxs ctx_id; + struct xe_mem_pool *bb_pool; if (!IS_VF_CCS_READY(xe)) return; @@ -485,7 +489,7 @@ void xe_sriov_vf_ccs_print(struct xe_device *xe, struct drm_printer *p) drm_printf(p, "ccs %s bb suballoc info\n", ctx_id ? "write" : "read"); drm_printf(p, "-------------------------\n"); - drm_suballoc_dump_debug_info(&bb_pool->base, p, xe_sa_manager_gpu_addr(bb_pool)); + xe_mem_pool_dump(bb_pool, p); drm_puts(p, "\n"); } } diff --git a/drivers/gpu/drm/xe/xe_sriov_vf_ccs_types.h b/drivers/gpu/drm/xe/xe_sriov_vf_ccs_types.h index 22c499943d2a..6fc8f97ef3f4 100644 --- a/drivers/gpu/drm/xe/xe_sriov_vf_ccs_types.h +++ b/drivers/gpu/drm/xe/xe_sriov_vf_ccs_types.h @@ -17,9 +17,6 @@ enum xe_sriov_vf_ccs_rw_ctxs { XE_SRIOV_VF_CCS_CTX_COUNT }; -struct xe_migrate; -struct xe_sa_manager; - /** * struct xe_sriov_vf_ccs_ctx - VF CCS migration context data. */ @@ -33,7 +30,7 @@ struct xe_sriov_vf_ccs_ctx { /** @mem: memory data */ struct { /** @mem.ccs_bb_pool: Pool from which batch buffers are allocated. */ - struct xe_sa_manager *ccs_bb_pool; + struct xe_mem_pool *ccs_bb_pool; } mem; }; diff --git a/drivers/gpu/drm/xe/xe_tuning.c b/drivers/gpu/drm/xe/xe_tuning.c index f8de6a4bf189..0b78ec2bc6a4 100644 --- a/drivers/gpu/drm/xe/xe_tuning.c +++ b/drivers/gpu/drm/xe/xe_tuning.c @@ -97,7 +97,7 @@ static const struct xe_rtp_entry_sr gt_tunings[] = { { XE_RTP_NAME("Tuning: Set STLB Bank Hash Mode to 4KB"), XE_RTP_RULES(GRAPHICS_VERSION_RANGE(3510, XE_RTP_END_VERSION_UNDEFINED), IS_INTEGRATED), - XE_RTP_ACTIONS(FIELD_SET(XEHP_GAMSTLB_CTRL, BANK_HASH_MODE, + XE_RTP_ACTIONS(FIELD_SET(GAMSTLB_CTRL, BANK_HASH_MODE, BANK_HASH_4KB_MODE)) }, }; diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index 56e2db50bb36..a717a2b8dea3 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -3658,6 +3658,8 @@ static int vm_bind_ioctl_check_args(struct xe_device *xe, struct xe_vm *vm, op == DRM_XE_VM_BIND_OP_MAP_USERPTR) || XE_IOCTL_DBG(xe, coh_mode == XE_COH_NONE && op == DRM_XE_VM_BIND_OP_MAP_USERPTR) || + XE_IOCTL_DBG(xe, !IS_DGFX(xe) && coh_mode == XE_COH_NONE && + is_cpu_addr_mirror) || XE_IOCTL_DBG(xe, xe_device_is_l2_flush_optimized(xe) && (op == DRM_XE_VM_BIND_OP_MAP_USERPTR || is_cpu_addr_mirror) && @@ -4156,7 +4158,8 @@ int xe_vm_get_property_ioctl(struct drm_device *drm, void *data, int ret = 0; if (XE_IOCTL_DBG(xe, (args->reserved[0] || args->reserved[1] || - args->reserved[2]))) + args->reserved[2] || args->extensions || + args->pad))) return -EINVAL; vm = xe_vm_lookup(xef, args->vm_id); diff --git a/drivers/gpu/drm/xe/xe_vm_madvise.c b/drivers/gpu/drm/xe/xe_vm_madvise.c index 66f00d3f5c07..c78906dea82b 100644 --- a/drivers/gpu/drm/xe/xe_vm_madvise.c +++ b/drivers/gpu/drm/xe/xe_vm_madvise.c @@ -621,6 +621,45 @@ static int xe_madvise_purgeable_retained_to_user(const struct xe_madvise_details return 0; } +static bool check_pat_args_are_sane(struct xe_device *xe, + struct xe_vmas_in_madvise_range *madvise_range, + u16 pat_index) +{ + u16 coh_mode = xe_pat_index_get_coh_mode(xe, pat_index); + int i; + + /* + * Using coh_none with CPU cached buffers is not allowed on iGPU. + * On iGPU the GPU shares the LLC with the CPU, so with coh_none + * the GPU bypasses CPU caches and reads directly from DRAM, + * potentially seeing stale sensitive data from previously freed + * pages. On dGPU this restriction does not apply, because the + * platform does not provide a non-coherent system memory access + * path that would violate the DMA coherency contract. + */ + if (coh_mode != XE_COH_NONE || IS_DGFX(xe)) + return true; + + for (i = 0; i < madvise_range->num_vmas; i++) { + struct xe_vma *vma = madvise_range->vmas[i]; + struct xe_bo *bo = xe_vma_bo(vma); + + if (bo) { + /* BO with WB caching + COH_NONE is not allowed */ + if (XE_IOCTL_DBG(xe, bo->cpu_caching == DRM_XE_GEM_CPU_CACHING_WB)) + return false; + /* Imported dma-buf without caching info, assume cached */ + if (XE_IOCTL_DBG(xe, !bo->cpu_caching)) + return false; + } else if (XE_IOCTL_DBG(xe, xe_vma_is_cpu_addr_mirror(vma) || + xe_vma_is_userptr(vma))) + /* System memory (userptr/SVM) is always CPU cached */ + return false; + } + + return true; +} + static bool check_bo_args_are_sane(struct xe_vm *vm, struct xe_vma **vmas, int num_vmas, u32 atomic_val) { @@ -750,6 +789,14 @@ int xe_vm_madvise_ioctl(struct drm_device *dev, void *data, struct drm_file *fil } } + if (args->type == DRM_XE_MEM_RANGE_ATTR_PAT) { + if (!check_pat_args_are_sane(xe, &madvise_range, + args->pat_index.val)) { + err = -EINVAL; + goto free_vmas; + } + } + if (madvise_range.has_bo_vmas) { if (args->type == DRM_XE_MEM_RANGE_ATTR_ATOMIC) { if (!check_bo_args_are_sane(vm, madvise_range.vmas, diff --git a/drivers/gpu/drm/xe/xe_wa.c b/drivers/gpu/drm/xe/xe_wa.c index 546296f0220b..4b1cbced06be 100644 --- a/drivers/gpu/drm/xe/xe_wa.c +++ b/drivers/gpu/drm/xe/xe_wa.c @@ -743,14 +743,6 @@ static const struct xe_rtp_entry_sr lrc_was[] = { XE_RTP_RULES(GRAPHICS_VERSION(2001), ENGINE_CLASS(RENDER)), XE_RTP_ACTIONS(SET(WM_CHICKEN3, HIZ_PLANE_COMPRESSION_DIS)) }, - { XE_RTP_NAME("14019988906"), - XE_RTP_RULES(GRAPHICS_VERSION_RANGE(2001, 2002), ENGINE_CLASS(RENDER)), - XE_RTP_ACTIONS(SET(XEHP_PSS_CHICKEN, FLSH_IGNORES_PSD)) - }, - { XE_RTP_NAME("14019877138"), - XE_RTP_RULES(GRAPHICS_VERSION_RANGE(2001, 2002), ENGINE_CLASS(RENDER)), - XE_RTP_ACTIONS(SET(XEHP_PSS_CHICKEN, FD_END_COLLECT)) - }, { XE_RTP_NAME("14021490052"), XE_RTP_RULES(GRAPHICS_VERSION(2001), ENGINE_CLASS(RENDER)), XE_RTP_ACTIONS(SET(FF_MODE, diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c index a40a765f0307..27992c38ad90 100644 --- a/drivers/infiniband/core/addr.c +++ b/drivers/infiniband/core/addr.c @@ -149,7 +149,7 @@ static int ib_nl_ip_send_msg(struct rdma_dev_addr *dev_addr, attrtype = RDMA_NLA_F_MANDATORY | LS_NLA_TYPE_IPV6; } - len = nla_total_size(sizeof(size)); + len = nla_total_size(size); len += NLMSG_ALIGN(sizeof(*header)); skb = nlmsg_new(len, GFP_KERNEL); diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index a768436ba468..91a62d2ade4d 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -778,6 +778,7 @@ static int ib_uverbs_rereg_mr(struct uverbs_attr_bundle *attrs) struct ib_pd *orig_pd; struct ib_pd *new_pd; struct ib_mr *new_mr; + u32 lkey, rkey; ret = uverbs_request(attrs, &cmd, sizeof(cmd)); if (ret) @@ -846,6 +847,8 @@ static int ib_uverbs_rereg_mr(struct uverbs_attr_bundle *attrs) new_mr->uobject = uobj; atomic_inc(&new_pd->usecnt); new_uobj->object = new_mr; + lkey = new_mr->lkey; + rkey = new_mr->rkey; rdma_restrack_new(&new_mr->res, RDMA_RESTRACK_MR); rdma_restrack_set_name(&new_mr->res, NULL); @@ -871,11 +874,13 @@ static int ib_uverbs_rereg_mr(struct uverbs_attr_bundle *attrs) mr->iova = cmd.hca_va; mr->length = cmd.length; } + lkey = mr->lkey; + rkey = mr->rkey; } memset(&resp, 0, sizeof(resp)); - resp.lkey = mr->lkey; - resp.rkey = mr->rkey; + resp.lkey = lkey; + resp.rkey = rkey; ret = uverbs_response(attrs, &resp, sizeof(resp)); diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c index 51afaac88c72..9121d83bf88a 100644 --- a/drivers/infiniband/hw/hfi1/pio.c +++ b/drivers/infiniband/hw/hfi1/pio.c @@ -1942,13 +1942,16 @@ bail: void free_pio_map(struct hfi1_devdata *dd) { + struct pio_vl_map *map; + /* Free PIO map if allocated */ if (rcu_access_pointer(dd->pio_map)) { spin_lock_irq(&dd->pio_map_lock); - pio_map_free(rcu_access_pointer(dd->pio_map)); + map = rcu_access_pointer(dd->pio_map); RCU_INIT_POINTER(dd->pio_map, NULL); spin_unlock_irq(&dd->pio_map_lock); synchronize_rcu(); + pio_map_free(map); } kfree(dd->kernel_send_context); dd->kernel_send_context = NULL; diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c index e5f442938177..cfd9dd0f7e81 100644 --- a/drivers/infiniband/hw/hfi1/sdma.c +++ b/drivers/infiniband/hw/hfi1/sdma.c @@ -1255,6 +1255,7 @@ void sdma_clean(struct hfi1_devdata *dd, size_t num_engines) { size_t i; struct sdma_engine *sde; + struct sdma_vl_map *map; if (dd->sdma_pad_dma) { dma_free_coherent(&dd->pcidev->dev, SDMA_PAD, @@ -1291,10 +1292,11 @@ void sdma_clean(struct hfi1_devdata *dd, size_t num_engines) } if (rcu_access_pointer(dd->sdma_map)) { spin_lock_irq(&dd->sde_map_lock); - sdma_map_free(rcu_access_pointer(dd->sdma_map)); + map = rcu_access_pointer(dd->sdma_map); RCU_INIT_POINTER(dd->sdma_map, NULL); spin_unlock_irq(&dd->sde_map_lock); synchronize_rcu(); + sdma_map_free(map); } kfree(dd->per_sdma); dd->per_sdma = NULL; diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c index a27ea85bb063..bf04ee84a943 100644 --- a/drivers/infiniband/hw/hns/hns_roce_qp.c +++ b/drivers/infiniband/hw/hns/hns_roce_qp.c @@ -47,8 +47,8 @@ static struct hns_roce_qp *hns_roce_qp_lookup(struct hns_roce_dev *hr_dev, xa_lock_irqsave(&hr_dev->qp_table_xa, flags); qp = __hns_roce_qp_lookup(hr_dev, qpn); - if (qp) - refcount_inc(&qp->refcount); + if (qp && !refcount_inc_not_zero(&qp->refcount)) + qp = NULL; xa_unlock_irqrestore(&hr_dev->qp_table_xa, flags); if (!qp) @@ -1171,6 +1171,7 @@ static int hns_roce_create_qp_common(struct hns_roce_dev *hr_dev, struct hns_roce_ib_create_qp_resp resp = {}; struct ib_device *ibdev = &hr_dev->ib_dev; struct hns_roce_ib_create_qp ucmd = {}; + unsigned long flags; int ret; mutex_init(&hr_qp->mutex); @@ -1251,13 +1252,19 @@ static int hns_roce_create_qp_common(struct hns_roce_dev *hr_dev, hr_qp->ibqp.qp_num = hr_qp->qpn; hr_qp->event = hns_roce_ib_qp_event; - refcount_set(&hr_qp->refcount, 1); init_completion(&hr_qp->free); + refcount_set_release(&hr_qp->refcount, 1); return 0; err_flow_ctrl: + spin_lock_irqsave(&hr_dev->qp_list_lock, flags); + hns_roce_lock_cqs(init_attr->send_cq ? to_hr_cq(init_attr->send_cq) : NULL, + init_attr->recv_cq ? to_hr_cq(init_attr->recv_cq) : NULL); hns_roce_qp_remove(hr_dev, hr_qp); + hns_roce_unlock_cqs(init_attr->send_cq ? to_hr_cq(init_attr->send_cq) : NULL, + init_attr->recv_cq ? to_hr_cq(init_attr->recv_cq) : NULL); + spin_unlock_irqrestore(&hr_dev->qp_list_lock, flags); err_store: free_qpc(hr_dev, hr_qp); err_qpc: diff --git a/drivers/infiniband/hw/hns/hns_roce_srq.c b/drivers/infiniband/hw/hns/hns_roce_srq.c index cb848e8e6bbd..8b94cbdfa54d 100644 --- a/drivers/infiniband/hw/hns/hns_roce_srq.c +++ b/drivers/infiniband/hw/hns/hns_roce_srq.c @@ -16,8 +16,8 @@ void hns_roce_srq_event(struct hns_roce_dev *hr_dev, u32 srqn, int event_type) xa_lock(&srq_table->xa); srq = xa_load(&srq_table->xa, srqn & (hr_dev->caps.num_srqs - 1)); - if (srq) - refcount_inc(&srq->refcount); + if (srq && !refcount_inc_not_zero(&srq->refcount)) + srq = NULL; xa_unlock(&srq_table->xa); if (!srq) { @@ -470,6 +470,10 @@ int hns_roce_create_srq(struct ib_srq *ib_srq, if (ret) goto err_srqn; + srq->event = hns_roce_ib_srq_event; + init_completion(&srq->free); + refcount_set_release(&srq->refcount, 1); + if (udata) { resp.cap_flags = srq->cap_flags; resp.srqn = srq->srqn; @@ -480,10 +484,6 @@ int hns_roce_create_srq(struct ib_srq *ib_srq, } } - srq->event = hns_roce_ib_srq_event; - refcount_set(&srq->refcount, 1); - init_completion(&srq->free); - return 0; err_srqc: diff --git a/drivers/infiniband/hw/ionic/ionic_ibdev.c b/drivers/infiniband/hw/ionic/ionic_ibdev.c index 0382a64839d2..73a616ae3502 100644 --- a/drivers/infiniband/hw/ionic/ionic_ibdev.c +++ b/drivers/infiniband/hw/ionic/ionic_ibdev.c @@ -185,7 +185,7 @@ static ssize_t hca_type_show(struct device *device, struct ionic_ibdev *dev = rdma_device_to_drv_device(device, struct ionic_ibdev, ibdev); - return sysfs_emit(buf, "%s.64\n", dev->ibdev.node_desc); + return sysfs_emit(buf, "%.64s\n", dev->ibdev.node_desc); } static DEVICE_ATTR_RO(hca_type); diff --git a/drivers/infiniband/hw/mana/cq.c b/drivers/infiniband/hw/mana/cq.c index f4cbe21763bf..2d682428ef20 100644 --- a/drivers/infiniband/hw/mana/cq.c +++ b/drivers/infiniband/hw/mana/cq.c @@ -137,8 +137,9 @@ int mana_ib_install_cq_cb(struct mana_ib_dev *mdev, struct mana_ib_cq *cq) if (cq->queue.id >= gc->max_num_cqs) return -EINVAL; - /* Create CQ table entry */ - WARN_ON(gc->cq_table[cq->queue.id]); + /* Create CQ table entry, sharing a CQ between WQs is not supported */ + if (gc->cq_table[cq->queue.id]) + return -EINVAL; if (cq->queue.kmem) gdma_cq = cq->queue.kmem; else diff --git a/drivers/infiniband/hw/mana/qp.c b/drivers/infiniband/hw/mana/qp.c index 645581359cee..0fbcf449c134 100644 --- a/drivers/infiniband/hw/mana/qp.c +++ b/drivers/infiniband/hw/mana/qp.c @@ -21,6 +21,9 @@ static int mana_ib_cfg_vport_steering(struct mana_ib_dev *dev, gc = mdev_to_gc(dev); + if (rx_hash_key_len > sizeof(req->hashkey)) + return -EINVAL; + req_buf_size = struct_size(req, indir_tab, MANA_INDIRECT_TABLE_DEF_SIZE); req = kzalloc(req_buf_size, GFP_KERNEL); if (!req) @@ -173,11 +176,8 @@ static int mana_ib_create_qp_rss(struct ib_qp *ibqp, struct ib_pd *pd, ret = mana_create_wq_obj(mpc, mpc->port_handle, GDMA_RQ, &wq_spec, &cq_spec, &wq->rx_object); - if (ret) { - /* Do cleanup starting with index i-1 */ - i--; + if (ret) goto fail; - } /* The GDMA regions are now owned by the WQ object */ wq->queue.gdma_region = GDMA_INVALID_DMA_REGION; @@ -197,8 +197,10 @@ static int mana_ib_create_qp_rss(struct ib_qp *ibqp, struct ib_pd *pd, /* Create CQ table entry */ ret = mana_ib_install_cq_cb(mdev, cq); - if (ret) + if (ret) { + mana_destroy_wq_obj(mpc, GDMA_RQ, wq->rx_object); goto fail; + } } resp.num_entries = i; @@ -215,13 +217,15 @@ static int mana_ib_create_qp_rss(struct ib_qp *ibqp, struct ib_pd *pd, ibdev_dbg(&mdev->ib_dev, "Failed to copy to udata create rss-qp, %d\n", ret); - goto fail; + goto err_disable_vport_rx; } kfree(mana_ind_table); return 0; +err_disable_vport_rx: + mana_disable_vport_rx(mpc); fail: while (i-- > 0) { ibwq = ind_tbl->ind_tbl[i]; diff --git a/drivers/infiniband/hw/mlx4/srq.c b/drivers/infiniband/hw/mlx4/srq.c index 5b23e5f8b84a..767840736d58 100644 --- a/drivers/infiniband/hw/mlx4/srq.c +++ b/drivers/infiniband/hw/mlx4/srq.c @@ -194,13 +194,15 @@ int mlx4_ib_create_srq(struct ib_srq *ib_srq, if (udata) if (ib_copy_to_udata(udata, &srq->msrq.srqn, sizeof (__u32))) { err = -EFAULT; - goto err_wrid; + goto err_srq; } init_attr->attr.max_wr = srq->msrq.max - 1; return 0; +err_srq: + mlx4_srq_free(dev->dev, &srq->msrq); err_wrid: if (udata) mlx4_ib_db_unmap_user(ucontext, &srq->db); diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 109661c2ac12..61078281953d 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -3310,7 +3310,7 @@ int mlx5_ib_dev_res_cq_init(struct mlx5_ib_dev *dev) * devr->c0 is set once, never changed until device unload. * Avoid taking the mutex if initialization is already done. */ - if (devr->c0) + if (smp_load_acquire(&devr->c0)) return 0; mutex_lock(&devr->cq_lock); @@ -3336,7 +3336,7 @@ int mlx5_ib_dev_res_cq_init(struct mlx5_ib_dev *dev) } devr->p0 = pd; - devr->c0 = cq; + smp_store_release(&devr->c0, cq); unlock: mutex_unlock(&devr->cq_lock); @@ -3354,7 +3354,7 @@ int mlx5_ib_dev_res_srq_init(struct mlx5_ib_dev *dev) * devr->s1 is set once, never changed until device unload. * Avoid taking the mutex if initialization is already done. */ - if (devr->s1) + if (smp_load_acquire(&devr->s1)) return 0; mutex_lock(&devr->srq_lock); @@ -3392,10 +3392,11 @@ int mlx5_ib_dev_res_srq_init(struct mlx5_ib_dev *dev) "Couldn't create SRQ 1 for res init, err=%pe\n", s1); ib_destroy_srq(s0); + goto unlock; } devr->s0 = s0; - devr->s1 = s1; + smp_store_release(&devr->s1, s1); unlock: mutex_unlock(&devr->srq_lock); diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 8f50e7342a76..8fd05532c09c 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -1603,6 +1603,11 @@ static int create_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, } if (qp->rq.wqe_cnt) { + if (!rq->base.ubuffer.umem) { + err = -EINVAL; + goto err_destroy_sq; + } + rq->base.container_mibqp = qp; if (qp->flags & IB_QP_CREATE_CVLAN_STRIPPING) @@ -4692,7 +4697,7 @@ int mlx5_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, struct mlx5_ib_dev *dev = to_mdev(ibqp->device); struct mlx5_ib_modify_qp_resp resp = {}; struct mlx5_ib_qp *qp = to_mqp(ibqp); - struct mlx5_ib_modify_qp ucmd; + struct mlx5_ib_modify_qp ucmd = {}; enum ib_qp_type qp_type; enum ib_qp_state cur_state, new_state; int err = -EINVAL; diff --git a/drivers/infiniband/hw/mlx5/qpc.c b/drivers/infiniband/hw/mlx5/qpc.c index 146d03ae40bd..a7a4f9420271 100644 --- a/drivers/infiniband/hw/mlx5/qpc.c +++ b/drivers/infiniband/hw/mlx5/qpc.c @@ -314,7 +314,14 @@ destroy: xa_cmpxchg_irq(&table->dct_xa, dct->mqp.qpn, XA_ZERO_ENTRY, dct, 0); return err; } - xa_erase_irq(&table->dct_xa, dct->mqp.qpn); + + /* + * A race can occur where a concurrent create gets the same dctn + * (after hardware released it) and overwrites XA_ZERO_ENTRY with + * its new DCT before we reach here. In that case, we must not erase + * the entry as it now belongs to the new DCT. + */ + xa_cmpxchg_irq(&table->dct_xa, dct->mqp.qpn, XA_ZERO_ENTRY, NULL, 0); return 0; } diff --git a/drivers/infiniband/hw/mlx5/srq_cmd.c b/drivers/infiniband/hw/mlx5/srq_cmd.c index 8b3385396599..c1a088120915 100644 --- a/drivers/infiniband/hw/mlx5/srq_cmd.c +++ b/drivers/infiniband/hw/mlx5/srq_cmd.c @@ -683,7 +683,14 @@ int mlx5_cmd_destroy_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq) xa_cmpxchg_irq(&table->array, srq->srqn, XA_ZERO_ENTRY, srq, 0); return err; } - xa_erase_irq(&table->array, srq->srqn); + + /* + * A race can occur where a concurrent create gets the same srqn + * (after hardware released it) and overwrites XA_ZERO_ENTRY with + * its new SRQ before we reach here. In that case, we must not erase + * the entry as it now belongs to the new SRQ. + */ + xa_cmpxchg_irq(&table->array, srq->srqn, XA_ZERO_ENTRY, NULL, 0); mlx5_core_res_put(&srq->common); wait_for_completion(&srq->common.free); diff --git a/drivers/infiniband/hw/mlx5/umr.c b/drivers/infiniband/hw/mlx5/umr.c index 29488fba21a0..f2139474be37 100644 --- a/drivers/infiniband/hw/mlx5/umr.c +++ b/drivers/infiniband/hw/mlx5/umr.c @@ -147,7 +147,7 @@ int mlx5r_umr_resource_init(struct mlx5_ib_dev *dev) * UMR qp is set once, never changed until device unload. * Avoid taking the mutex if initialization is already done. */ - if (dev->umrc.qp) + if (smp_load_acquire(&dev->umrc.qp)) return 0; mutex_lock(&dev->umrc.init_lock); @@ -185,7 +185,7 @@ int mlx5r_umr_resource_init(struct mlx5_ib_dev *dev) sema_init(&dev->umrc.sem, MAX_UMR_WR); mutex_init(&dev->umrc.lock); dev->umrc.state = MLX5_UMR_STATE_ACTIVE; - dev->umrc.qp = qp; + smp_store_release(&dev->umrc.qp, qp); mutex_unlock(&dev->umrc.init_lock); return 0; diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c index c17e2a54dbca..a88cc5d84af8 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c @@ -215,7 +215,7 @@ static void ocrdma_del_mmap(struct ocrdma_ucontext *uctx, u64 phy_addr, mutex_lock(&uctx->mm_list_lock); list_for_each_entry_safe(mm, tmp, &uctx->mm_head, entry) { - if (len != mm->key.len && phy_addr != mm->key.phy_addr) + if (len != mm->key.len || phy_addr != mm->key.phy_addr) continue; list_del(&mm->entry); @@ -233,7 +233,7 @@ static bool ocrdma_search_mmap(struct ocrdma_ucontext *uctx, u64 phy_addr, mutex_lock(&uctx->mm_list_lock); list_for_each_entry(mm, &uctx->mm_head, entry) { - if (len != mm->key.len && phy_addr != mm->key.phy_addr) + if (len != mm->key.len || phy_addr != mm->key.phy_addr) continue; found = true; @@ -620,9 +620,9 @@ static int ocrdma_copy_pd_uresp(struct ocrdma_dev *dev, struct ocrdma_pd *pd, ucopy_err: if (pd->dpp_enabled) - ocrdma_del_mmap(pd->uctx, dpp_page_addr, PAGE_SIZE); + ocrdma_del_mmap(uctx, dpp_page_addr, PAGE_SIZE); dpp_map_err: - ocrdma_del_mmap(pd->uctx, db_page_addr, db_page_size); + ocrdma_del_mmap(uctx, db_page_addr, db_page_size); return status; } diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c index bcd43dc30e21..c7c2b41060e5 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c @@ -322,7 +322,7 @@ int pvrdma_alloc_ucontext(struct ib_ucontext *uctx, struct ib_udata *udata) uresp.qp_tab_size = vdev->dsr->caps.max_qp; ret = ib_copy_to_udata(udata, &uresp, sizeof(uresp)); if (ret) { - pvrdma_uar_free(vdev, &context->uar); + /* pvrdma_dealloc_ucontext() also frees the UAR */ pvrdma_dealloc_ucontext(&context->ibucontext); return -EFAULT; } diff --git a/drivers/infiniband/sw/rxe/rxe_recv.c b/drivers/infiniband/sw/rxe/rxe_recv.c index f79214738c2b..2d5e701ff961 100644 --- a/drivers/infiniband/sw/rxe/rxe_recv.c +++ b/drivers/infiniband/sw/rxe/rxe_recv.c @@ -330,6 +330,17 @@ void rxe_rcv(struct sk_buff *skb) pkt->qp = NULL; pkt->mask |= rxe_opcode[pkt->opcode].mask; + /* + * Unknown opcodes have a zero-initialized rxe_opcode[] entry, so + * both mask and length are 0. Reject them before any length math: + * rxe_icrc_hdr() would otherwise compute length - RXE_BTH_BYTES + * and pass the underflowed value to rxe_crc32(), producing an + * out-of-bounds read. + */ + if (unlikely(!rxe_opcode[pkt->opcode].mask || + !rxe_opcode[pkt->opcode].length)) + goto drop; + if (unlikely(pkt->paylen < header_size(pkt) + bth_pad(pkt) + RXE_ICRC_SIZE)) goto drop; diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c index 9faf8c09aa8e..9cb2f6fbf2dd 100644 --- a/drivers/infiniband/sw/rxe/rxe_resp.c +++ b/drivers/infiniband/sw/rxe/rxe_resp.c @@ -540,7 +540,19 @@ static enum resp_states check_rkey(struct rxe_qp *qp, } skip_check_range: - if (pkt->mask & (RXE_WRITE_MASK | RXE_ATOMIC_WRITE_MASK)) { + if (pkt->mask & RXE_ATOMIC_WRITE_MASK) { + /* IBA oA19-28: ATOMIC_WRITE payload is exactly 8 bytes. + * Reject any other length before the responder reads + * sizeof(u64) bytes from payload_addr(pkt); a shorter + * payload would read past the logical end of the packet + * into skb->head tailroom. + */ + if (resid != sizeof(u64) || pktlen != sizeof(u64) || + bth_pad(pkt)) { + state = RESPST_ERR_LENGTH; + goto err; + } + } else if (pkt->mask & RXE_WRITE_MASK) { if (resid > mtu) { if (pktlen != mtu || bth_pad(pkt)) { state = RESPST_ERR_LENGTH; diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h index 1342e764a548..834d8fabfba3 100644 --- a/drivers/iommu/amd/amd_iommu.h +++ b/drivers/iommu/amd/amd_iommu.h @@ -11,6 +11,9 @@ #include "amd_iommu_types.h" +extern int amd_iommu_evtlog_size; +extern int amd_iommu_pprlog_size; + irqreturn_t amd_iommu_int_thread(int irq, void *data); irqreturn_t amd_iommu_int_thread_evtlog(int irq, void *data); irqreturn_t amd_iommu_int_thread_pprlog(int irq, void *data); diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index c685d3771436..f9f718087893 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -15,6 +15,7 @@ #include <linux/mutex.h> #include <linux/msi.h> #include <linux/list.h> +#include <linux/sizes.h> #include <linux/spinlock.h> #include <linux/pci.h> #include <linux/iommufd.h> @@ -141,7 +142,6 @@ #define MMIO_STATUS_GALOG_INT_MASK BIT(10) /* event logging constants */ -#define EVENT_ENTRY_SIZE 0x10 #define EVENT_TYPE_SHIFT 28 #define EVENT_TYPE_MASK 0xf #define EVENT_TYPE_ILL_DEV 0x1 @@ -259,15 +259,20 @@ #define MMIO_CMD_BUFFER_TAIL(x) FIELD_GET(MMIO_CMD_TAIL_MASK, (x)) /* constants for event buffer handling */ -#define EVT_BUFFER_SIZE 8192 /* 512 entries */ -#define EVT_LEN_MASK (0x9ULL << 56) +#define EVTLOG_ENTRY_SIZE 0x10 +#define EVTLOG_SIZE_SHIFT 56 +#define EVTLOG_SIZE_DEF SZ_8K /* 512 entries */ +#define EVTLOG_LEN_MASK_DEF (0x9ULL << EVTLOG_SIZE_SHIFT) +#define EVTLOG_SIZE_MAX SZ_512K /* 32K entries */ +#define EVTLOG_LEN_MASK_MAX (0xFULL << EVTLOG_SIZE_SHIFT) /* Constants for PPR Log handling */ -#define PPR_LOG_ENTRIES 512 -#define PPR_LOG_SIZE_SHIFT 56 -#define PPR_LOG_SIZE_512 (0x9ULL << PPR_LOG_SIZE_SHIFT) -#define PPR_ENTRY_SIZE 16 -#define PPR_LOG_SIZE (PPR_ENTRY_SIZE * PPR_LOG_ENTRIES) +#define PPRLOG_ENTRY_SIZE 0x10 +#define PPRLOG_SIZE_SHIFT 56 +#define PPRLOG_SIZE_DEF SZ_8K /* 512 entries */ +#define PPRLOG_LEN_MASK_DEF (0x9ULL << PPRLOG_SIZE_SHIFT) +#define PPRLOG_SIZE_MAX SZ_512K /* 32K entries */ +#define PPRLOG_LEN_MASK_MAX (0xFULL << PPRLOG_SIZE_SHIFT) /* PAGE_SERVICE_REQUEST PPR Log Buffer Entry flags */ #define PPR_FLAG_EXEC 0x002 /* Execute permission requested */ diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 56ad020df494..3bdb380d23e9 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -132,6 +132,9 @@ struct ivhd_entry { u8 uid; } __attribute__((packed)); +int amd_iommu_evtlog_size = EVTLOG_SIZE_DEF; +int amd_iommu_pprlog_size = PPRLOG_SIZE_DEF; + /* * An AMD IOMMU memory definition structure. It defines things like exclusion * ranges for devices and regions that should be unity mapped. @@ -865,35 +868,47 @@ void *__init iommu_alloc_4k_pages(struct amd_iommu *iommu, gfp_t gfp, } /* allocates the memory where the IOMMU will log its events to */ -static int __init alloc_event_buffer(struct amd_iommu *iommu) +static int __init alloc_event_buffer(void) { - iommu->evt_buf = iommu_alloc_4k_pages(iommu, GFP_KERNEL, - EVT_BUFFER_SIZE); + struct amd_iommu *iommu; - return iommu->evt_buf ? 0 : -ENOMEM; + for_each_iommu(iommu) { + iommu->evt_buf = iommu_alloc_4k_pages(iommu, GFP_KERNEL, + amd_iommu_evtlog_size); + if (!iommu->evt_buf) + return -ENOMEM; + } + + return 0; } -static void iommu_enable_event_buffer(struct amd_iommu *iommu) +static void iommu_enable_event_buffer(void) { + struct amd_iommu *iommu; u64 entry; - BUG_ON(iommu->evt_buf == NULL); + for_each_iommu(iommu) { + BUG_ON(iommu->evt_buf == NULL); - if (!is_kdump_kernel()) { - /* - * Event buffer is re-used for kdump kernel and setting - * of MMIO register is not required. - */ - entry = iommu_virt_to_phys(iommu->evt_buf) | EVT_LEN_MASK; - memcpy_toio(iommu->mmio_base + MMIO_EVT_BUF_OFFSET, - &entry, sizeof(entry)); - } + if (!is_kdump_kernel()) { + /* + * Event buffer is re-used for kdump kernel and setting + * of MMIO register is not required. + */ + entry = iommu_virt_to_phys(iommu->evt_buf); + entry |= (amd_iommu_evtlog_size == EVTLOG_SIZE_DEF) ? + EVTLOG_LEN_MASK_DEF : EVTLOG_LEN_MASK_MAX; - /* set head and tail to zero manually */ - writel(0x00, iommu->mmio_base + MMIO_EVT_HEAD_OFFSET); - writel(0x00, iommu->mmio_base + MMIO_EVT_TAIL_OFFSET); + memcpy_toio(iommu->mmio_base + MMIO_EVT_BUF_OFFSET, + &entry, sizeof(entry)); + } - iommu_feature_enable(iommu, CONTROL_EVT_LOG_EN); + /* set head and tail to zero manually */ + writel(0x00, iommu->mmio_base + MMIO_EVT_HEAD_OFFSET); + writel(0x00, iommu->mmio_base + MMIO_EVT_TAIL_OFFSET); + + iommu_feature_enable(iommu, CONTROL_EVT_LOG_EN); + } } /* @@ -984,15 +999,20 @@ static int __init alloc_cwwb_sem(struct amd_iommu *iommu) return 0; } -static int __init remap_event_buffer(struct amd_iommu *iommu) +static int __init remap_event_buffer(void) { + struct amd_iommu *iommu; u64 paddr; pr_info_once("Re-using event buffer from the previous kernel\n"); - paddr = readq(iommu->mmio_base + MMIO_EVT_BUF_OFFSET) & PM_ADDR_MASK; - iommu->evt_buf = iommu_memremap(paddr, EVT_BUFFER_SIZE); + for_each_iommu(iommu) { + paddr = readq(iommu->mmio_base + MMIO_EVT_BUF_OFFSET) & PM_ADDR_MASK; + iommu->evt_buf = iommu_memremap(paddr, amd_iommu_evtlog_size); + if (!iommu->evt_buf) + return -ENOMEM; + } - return iommu->evt_buf ? 0 : -ENOMEM; + return 0; } static int __init remap_command_buffer(struct amd_iommu *iommu) @@ -1044,10 +1064,6 @@ static int __init alloc_iommu_buffers(struct amd_iommu *iommu) ret = remap_command_buffer(iommu); if (ret) return ret; - - ret = remap_event_buffer(iommu); - if (ret) - return ret; } else { ret = alloc_cwwb_sem(iommu); if (ret) @@ -1056,10 +1072,6 @@ static int __init alloc_iommu_buffers(struct amd_iommu *iommu) ret = alloc_command_buffer(iommu); if (ret) return ret; - - ret = alloc_event_buffer(iommu); - if (ret) - return ret; } return 0; @@ -2893,7 +2905,6 @@ static void early_enable_iommu(struct amd_iommu *iommu) iommu_init_flags(iommu); iommu_set_device_table(iommu); iommu_enable_command_buffer(iommu); - iommu_enable_event_buffer(iommu); iommu_set_exclusion_range(iommu); iommu_enable_gt(iommu); iommu_enable_ga(iommu); @@ -2957,7 +2968,6 @@ static void early_enable_iommus(void) iommu_disable_event_buffer(iommu); iommu_disable_irtcachedis(iommu); iommu_enable_command_buffer(iommu); - iommu_enable_event_buffer(iommu); iommu_enable_ga(iommu); iommu_enable_xt(iommu); iommu_enable_irtcachedis(iommu); @@ -3070,6 +3080,7 @@ static void amd_iommu_resume(void *data) for_each_iommu(iommu) early_enable_iommu(iommu); + iommu_enable_event_buffer(); amd_iommu_enable_interrupts(); } @@ -3399,6 +3410,33 @@ disable_snp: #endif } +static void amd_iommu_apply_erratum_snp(void) +{ +#ifdef CONFIG_KVM_AMD_SEV + if (!amd_iommu_snp_en) + return; + + /* Errata fix for Family 0x19 */ + if (boot_cpu_data.x86 != 0x19) + return; + + /* Set event log buffer size to max */ + amd_iommu_evtlog_size = EVTLOG_SIZE_MAX; + pr_info("Applying erratum: Increase Event log size to 0x%x\n", + amd_iommu_evtlog_size); + + /* + * Set PPR log buffer size to max. + * (Family 0x19, model < 0x10 doesn't support PPR when SNP is enabled). + */ + if (boot_cpu_data.x86_model >= 0x10) { + amd_iommu_pprlog_size = PPRLOG_SIZE_MAX; + pr_info("Applying erratum: Increase PPR log size to 0x%x\n", + amd_iommu_pprlog_size); + } +#endif +} + /**************************************************************************** * * AMD IOMMU Initialization State Machine @@ -3435,6 +3473,21 @@ static int __init state_next(void) case IOMMU_ENABLED: register_syscore(&amd_iommu_syscore); iommu_snp_enable(); + + amd_iommu_apply_erratum_snp(); + + /* Allocate/enable event log buffer */ + if (is_kdump_kernel()) + ret = remap_event_buffer(); + else + ret = alloc_event_buffer(); + + if (ret) { + init_state = IOMMU_INIT_ERROR; + break; + } + iommu_enable_event_buffer(); + ret = amd_iommu_init_pci(); init_state = ret ? IOMMU_INIT_ERROR : IOMMU_PCI_INIT; break; @@ -4037,11 +4090,11 @@ int amd_iommu_snp_disable(void) return 0; for_each_iommu(iommu) { - ret = iommu_make_shared(iommu->evt_buf, EVT_BUFFER_SIZE); + ret = iommu_make_shared(iommu->evt_buf, amd_iommu_evtlog_size); if (ret) return ret; - ret = iommu_make_shared(iommu->ppr_log, PPR_LOG_SIZE); + ret = iommu_make_shared(iommu->ppr_log, amd_iommu_pprlog_size); if (ret) return ret; diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 01171361f9bc..f78e23f03938 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -1010,7 +1010,7 @@ static void iommu_poll_events(struct amd_iommu *iommu) iommu_print_event(iommu, iommu->evt_buf + head); /* Update head pointer of hardware ring-buffer */ - head = (head + EVENT_ENTRY_SIZE) % EVT_BUFFER_SIZE; + head = (head + EVTLOG_ENTRY_SIZE) % amd_iommu_evtlog_size; writel(head, iommu->mmio_base + MMIO_EVT_HEAD_OFFSET); } @@ -2149,7 +2149,8 @@ static void set_dte_passthrough(struct iommu_dev_data *dev_data, new->data[0] |= DTE_FLAG_TV | DTE_FLAG_IR | DTE_FLAG_IW; new->data[1] |= FIELD_PREP(DTE_DOMID_MASK, domain->id) | - (dev_data->ats_enabled) ? DTE_FLAG_IOTLB : 0; + (dev_data->ats_enabled ? DTE_FLAG_IOTLB : 0); + } static void set_dte_entry(struct amd_iommu *iommu, diff --git a/drivers/iommu/amd/ppr.c b/drivers/iommu/amd/ppr.c index e6767c057d01..1f8d2823bea4 100644 --- a/drivers/iommu/amd/ppr.c +++ b/drivers/iommu/amd/ppr.c @@ -20,7 +20,7 @@ int __init amd_iommu_alloc_ppr_log(struct amd_iommu *iommu) { iommu->ppr_log = iommu_alloc_4k_pages(iommu, GFP_KERNEL | __GFP_ZERO, - PPR_LOG_SIZE); + amd_iommu_pprlog_size); return iommu->ppr_log ? 0 : -ENOMEM; } @@ -33,7 +33,9 @@ void amd_iommu_enable_ppr_log(struct amd_iommu *iommu) iommu_feature_enable(iommu, CONTROL_PPR_EN); - entry = iommu_virt_to_phys(iommu->ppr_log) | PPR_LOG_SIZE_512; + entry = iommu_virt_to_phys(iommu->ppr_log); + entry |= (amd_iommu_pprlog_size == PPRLOG_SIZE_DEF) ? + PPRLOG_LEN_MASK_DEF : PPRLOG_LEN_MASK_MAX; memcpy_toio(iommu->mmio_base + MMIO_PPR_LOG_OFFSET, &entry, sizeof(entry)); @@ -201,7 +203,7 @@ void amd_iommu_poll_ppr_log(struct amd_iommu *iommu) raw[0] = raw[1] = 0UL; /* Update head pointer of hardware ring-buffer */ - head = (head + PPR_ENTRY_SIZE) % PPR_LOG_SIZE; + head = (head + PPRLOG_ENTRY_SIZE) % amd_iommu_pprlog_size; writel(head, iommu->mmio_base + MMIO_PPR_HEAD_OFFSET); /* Handle PPR entry */ diff --git a/drivers/iommu/iommu-pages.h b/drivers/iommu/iommu-pages.h index ae9da4f571f6..e9e605b5fa3a 100644 --- a/drivers/iommu/iommu-pages.h +++ b/drivers/iommu/iommu-pages.h @@ -137,7 +137,7 @@ static inline void iommu_pages_flush_incoherent(struct device *dma_dev, void *virt, size_t offset, size_t len) { - dma_sync_single_for_device(dma_dev, (uintptr_t)virt + offset, len, + dma_sync_single_for_device(dma_dev, virt_to_phys(virt) + offset, len, DMA_TO_DEVICE); } void iommu_pages_stop_incoherent_list(struct iommu_pages_list *list, diff --git a/drivers/mailbox/cix-mailbox.c b/drivers/mailbox/cix-mailbox.c index 443620e8ae37..43c76cdab24a 100644 --- a/drivers/mailbox/cix-mailbox.c +++ b/drivers/mailbox/cix-mailbox.c @@ -12,8 +12,6 @@ #include <linux/module.h> #include <linux/platform_device.h> -#include "mailbox.h" - /* * The maximum transmission size is 32 words or 128 bytes. */ @@ -405,7 +403,7 @@ static int cix_mbox_startup(struct mbox_chan *chan) int index = cp->index, ret; u32 val; - ret = request_irq(priv->irq, cix_mbox_isr, 0, + ret = request_irq(priv->irq, cix_mbox_isr, IRQF_NO_SUSPEND, dev_name(priv->dev), chan); if (ret) { dev_err(priv->dev, "Unable to acquire IRQ %d\n", priv->irq); @@ -415,7 +413,7 @@ static int cix_mbox_startup(struct mbox_chan *chan) switch (cp->type) { case CIX_MBOX_TYPE_DB: /* Overwrite txdone_method for DB channel */ - chan->txdone_method = TXDONE_BY_ACK; + chan->txdone_method = MBOX_TXDONE_BY_ACK; fallthrough; case CIX_MBOX_TYPE_REG: if (priv->dir == CIX_MBOX_TX) { diff --git a/drivers/mailbox/exynos-mailbox.c b/drivers/mailbox/exynos-mailbox.c index 5f2d3b81c1db..d2355b128ba4 100644 --- a/drivers/mailbox/exynos-mailbox.c +++ b/drivers/mailbox/exynos-mailbox.c @@ -99,7 +99,6 @@ static int exynos_mbox_probe(struct platform_device *pdev) struct mbox_controller *mbox; struct mbox_chan *chans; struct clk *pclk; - int i; exynos_mbox = devm_kzalloc(dev, sizeof(*exynos_mbox), GFP_KERNEL); if (!exynos_mbox) @@ -129,9 +128,6 @@ static int exynos_mbox_probe(struct platform_device *pdev) mbox->ops = &exynos_mbox_chan_ops; mbox->of_xlate = exynos_mbox_of_xlate; - for (i = 0; i < EXYNOS_MBOX_CHAN_COUNT; i++) - chans[i].mbox = mbox; - exynos_mbox->mbox = mbox; platform_set_drvdata(pdev, exynos_mbox); diff --git a/drivers/mailbox/hi3660-mailbox.c b/drivers/mailbox/hi3660-mailbox.c index 17c29e960fbf..9b727a2b54a5 100644 --- a/drivers/mailbox/hi3660-mailbox.c +++ b/drivers/mailbox/hi3660-mailbox.c @@ -15,8 +15,6 @@ #include <linux/platform_device.h> #include <linux/slab.h> -#include "mailbox.h" - #define MBOX_CHAN_MAX 32 #define MBOX_RX 0x0 diff --git a/drivers/mailbox/hi6220-mailbox.c b/drivers/mailbox/hi6220-mailbox.c index f77741ce42e7..69d15b6283e9 100644 --- a/drivers/mailbox/hi6220-mailbox.c +++ b/drivers/mailbox/hi6220-mailbox.c @@ -79,12 +79,12 @@ struct hi6220_mbox { /* region for mailbox */ void __iomem *base; - unsigned int chan_num; - struct hi6220_mbox_chan *mchan; - void *irq_map_chan[MBOX_CHAN_MAX]; struct mbox_chan *chan; struct mbox_controller controller; + + unsigned int chan_num; + struct hi6220_mbox_chan mchan[] __counted_by(chan_num); }; static void mbox_set_state(struct hi6220_mbox *mbox, @@ -267,16 +267,12 @@ static int hi6220_mbox_probe(struct platform_device *pdev) struct hi6220_mbox *mbox; int i, err; - mbox = devm_kzalloc(dev, sizeof(*mbox), GFP_KERNEL); + mbox = devm_kzalloc(dev, struct_size(mbox, mchan, MBOX_CHAN_MAX), GFP_KERNEL); if (!mbox) return -ENOMEM; - mbox->dev = dev; mbox->chan_num = MBOX_CHAN_MAX; - mbox->mchan = devm_kcalloc(dev, - mbox->chan_num, sizeof(*mbox->mchan), GFP_KERNEL); - if (!mbox->mchan) - return -ENOMEM; + mbox->dev = dev; mbox->chan = devm_kcalloc(dev, mbox->chan_num, sizeof(*mbox->chan), GFP_KERNEL); diff --git a/drivers/mailbox/imx-mailbox.c b/drivers/mailbox/imx-mailbox.c index 003f9236c35e..246a9a9e3952 100644 --- a/drivers/mailbox/imx-mailbox.c +++ b/drivers/mailbox/imx-mailbox.c @@ -23,8 +23,6 @@ #include <linux/slab.h> #include <linux/workqueue.h> -#include "mailbox.h" - #define IMX_MU_CHANS 24 /* TX0/RX0/RXDB[0-3] */ #define IMX_MU_SCU_CHANS 6 @@ -734,7 +732,7 @@ static struct mbox_chan * imx_mu_xlate(struct mbox_controller *mbox, p_chan = &mbox->chans[chan]; if (type == IMX_MU_TYPE_TXDB_V2) - p_chan->txdone_method = TXDONE_BY_ACK; + p_chan->txdone_method = MBOX_TXDONE_BY_ACK; return p_chan; } diff --git a/drivers/mailbox/mailbox-sti.c b/drivers/mailbox/mailbox-sti.c index b4b5bdd503cf..b6c9ecbbc8ec 100644 --- a/drivers/mailbox/mailbox-sti.c +++ b/drivers/mailbox/mailbox-sti.c @@ -21,8 +21,6 @@ #include <linux/property.h> #include <linux/slab.h> -#include "mailbox.h" - #define STI_MBOX_INST_MAX 4 /* RAM saving: Max supported instances */ #define STI_MBOX_CHAN_MAX 20 /* RAM saving: Max supported channels */ diff --git a/drivers/mailbox/mailbox-test.c b/drivers/mailbox/mailbox-test.c index 3a28ab5c42e5..7b6ef033e77a 100644 --- a/drivers/mailbox/mailbox-test.c +++ b/drivers/mailbox/mailbox-test.c @@ -28,8 +28,6 @@ #define MBOX_HEXDUMP_MAX_LEN (MBOX_HEXDUMP_LINE_LEN * \ (MBOX_MAX_MSG_LEN / MBOX_BYTES_PER_LINE)) -static bool mbox_data_ready; - struct mbox_test_device { struct device *dev; void __iomem *tx_mmio; @@ -42,6 +40,7 @@ struct mbox_test_device { spinlock_t lock; struct mutex mutex; wait_queue_head_t waitq; + bool data_ready; struct fasync_struct *async_queue; struct dentry *root_debugfs_dir; }; @@ -162,7 +161,7 @@ static bool mbox_test_message_data_ready(struct mbox_test_device *tdev) unsigned long flags; spin_lock_irqsave(&tdev->lock, flags); - data_ready = mbox_data_ready; + data_ready = tdev->data_ready; spin_unlock_irqrestore(&tdev->lock, flags); return data_ready; @@ -227,7 +226,7 @@ static ssize_t mbox_test_message_read(struct file *filp, char __user *userbuf, *(touser + l) = '\0'; memset(tdev->rx_buffer, 0, MBOX_MAX_MSG_LEN); - mbox_data_ready = false; + tdev->data_ready = false; spin_unlock_irqrestore(&tdev->lock, flags); @@ -297,7 +296,7 @@ static void mbox_test_receive_message(struct mbox_client *client, void *message) message, MBOX_MAX_MSG_LEN); memcpy(tdev->rx_buffer, message, MBOX_MAX_MSG_LEN); } - mbox_data_ready = true; + tdev->data_ready = true; spin_unlock_irqrestore(&tdev->lock, flags); wake_up_interruptible(&tdev->waitq); @@ -336,7 +335,7 @@ mbox_test_request_channel(struct platform_device *pdev, const char *name) client = devm_kzalloc(&pdev->dev, sizeof(*client), GFP_KERNEL); if (!client) - return ERR_PTR(-ENOMEM); + return NULL; client->dev = &pdev->dev; client->rx_callback = mbox_test_receive_message; @@ -355,67 +354,80 @@ mbox_test_request_channel(struct platform_device *pdev, const char *name) return channel; } +static void __iomem *mbox_test_ioremap(struct platform_device *pdev, unsigned int res_num) +{ + struct resource *res; + void __iomem *mmio; + + res = platform_get_resource(pdev, IORESOURCE_MEM, res_num); + if (!res) + return NULL; + + mmio = devm_ioremap_resource(&pdev->dev, res); + if (PTR_ERR(mmio) == -EBUSY) { + dev_info(&pdev->dev, "trying workaround with plain ioremap\n"); + return devm_ioremap(&pdev->dev, res->start, resource_size(res)); + } + + return IS_ERR(mmio) ? NULL : mmio; +} + static int mbox_test_probe(struct platform_device *pdev) { struct mbox_test_device *tdev; - struct resource *res; - resource_size_t size; int ret; tdev = devm_kzalloc(&pdev->dev, sizeof(*tdev), GFP_KERNEL); if (!tdev) return -ENOMEM; + tdev->dev = &pdev->dev; + spin_lock_init(&tdev->lock); + mutex_init(&tdev->mutex); + init_waitqueue_head(&tdev->waitq); + platform_set_drvdata(pdev, tdev); + /* It's okay for MMIO to be NULL */ - tdev->tx_mmio = devm_platform_get_and_ioremap_resource(pdev, 0, &res); - if (PTR_ERR(tdev->tx_mmio) == -EBUSY) { - /* if reserved area in SRAM, try just ioremap */ - size = resource_size(res); - tdev->tx_mmio = devm_ioremap(&pdev->dev, res->start, size); - } else if (IS_ERR(tdev->tx_mmio)) { - tdev->tx_mmio = NULL; - } + tdev->tx_mmio = mbox_test_ioremap(pdev, 0); /* If specified, second reg entry is Rx MMIO */ - tdev->rx_mmio = devm_platform_get_and_ioremap_resource(pdev, 1, &res); - if (PTR_ERR(tdev->rx_mmio) == -EBUSY) { - size = resource_size(res); - tdev->rx_mmio = devm_ioremap(&pdev->dev, res->start, size); - } else if (IS_ERR(tdev->rx_mmio)) { + tdev->rx_mmio = mbox_test_ioremap(pdev, 1); + if (!tdev->rx_mmio) tdev->rx_mmio = tdev->tx_mmio; - } tdev->tx_channel = mbox_test_request_channel(pdev, "tx"); tdev->rx_channel = mbox_test_request_channel(pdev, "rx"); - if (IS_ERR_OR_NULL(tdev->tx_channel) && IS_ERR_OR_NULL(tdev->rx_channel)) + if (!tdev->tx_channel && !tdev->rx_channel) return -EPROBE_DEFER; /* If Rx is not specified but has Rx MMIO, then Rx = Tx */ if (!tdev->rx_channel && (tdev->rx_mmio != tdev->tx_mmio)) tdev->rx_channel = tdev->tx_channel; - tdev->dev = &pdev->dev; - platform_set_drvdata(pdev, tdev); - - spin_lock_init(&tdev->lock); - mutex_init(&tdev->mutex); - if (tdev->rx_channel) { tdev->rx_buffer = devm_kzalloc(&pdev->dev, MBOX_MAX_MSG_LEN, GFP_KERNEL); - if (!tdev->rx_buffer) - return -ENOMEM; + if (!tdev->rx_buffer) { + ret = -ENOMEM; + goto err_free_chans; + } } ret = mbox_test_add_debugfs(pdev, tdev); if (ret) - return ret; + goto err_free_chans; - init_waitqueue_head(&tdev->waitq); dev_info(&pdev->dev, "Successfully registered\n"); return 0; + +err_free_chans: + if (tdev->tx_channel) + mbox_free_channel(tdev->tx_channel); + if (tdev->rx_channel && tdev->rx_channel != tdev->tx_channel) + mbox_free_channel(tdev->rx_channel); + return ret; } static void mbox_test_remove(struct platform_device *pdev) @@ -426,7 +438,7 @@ static void mbox_test_remove(struct platform_device *pdev) if (tdev->tx_channel) mbox_free_channel(tdev->tx_channel); - if (tdev->rx_channel) + if (tdev->rx_channel && tdev->rx_channel != tdev->tx_channel) mbox_free_channel(tdev->rx_channel); } diff --git a/drivers/mailbox/mailbox.c b/drivers/mailbox/mailbox.c index 617ba505691d..bbc9fd75a95f 100644 --- a/drivers/mailbox/mailbox.c +++ b/drivers/mailbox/mailbox.c @@ -18,8 +18,6 @@ #include <linux/property.h> #include <linux/spinlock.h> -#include "mailbox.h" - static LIST_HEAD(mbox_cons); static DEFINE_MUTEX(con_mutex); @@ -52,7 +50,7 @@ static void msg_submit(struct mbox_chan *chan) int err = -EBUSY; scoped_guard(spinlock_irqsave, &chan->lock) { - if (!chan->msg_count || chan->active_req) + if (!chan->msg_count || chan->active_req != MBOX_NO_MSG) break; count = chan->msg_count; @@ -74,7 +72,7 @@ static void msg_submit(struct mbox_chan *chan) } } - if (!err && (chan->txdone_method & TXDONE_BY_POLL)) { + if (!err && (chan->txdone_method & MBOX_TXDONE_BY_POLL)) { /* kick start the timer immediately to avoid delays */ scoped_guard(spinlock_irqsave, &chan->mbox->poll_hrt_lock) hrtimer_start(&chan->mbox->poll_hrt, 0, HRTIMER_MODE_REL); @@ -87,13 +85,13 @@ static void tx_tick(struct mbox_chan *chan, int r) scoped_guard(spinlock_irqsave, &chan->lock) { mssg = chan->active_req; - chan->active_req = NULL; + chan->active_req = MBOX_NO_MSG; } /* Submit next message */ msg_submit(chan); - if (!mssg) + if (mssg == MBOX_NO_MSG) return; /* Notify the client */ @@ -114,7 +112,7 @@ static enum hrtimer_restart txdone_hrtimer(struct hrtimer *hrtimer) for (i = 0; i < mbox->num_chans; i++) { struct mbox_chan *chan = &mbox->chans[i]; - if (chan->active_req && chan->cl) { + if (chan->active_req != MBOX_NO_MSG && chan->cl) { txdone = chan->mbox->ops->last_tx_done(chan); if (txdone) tx_tick(chan, 0); @@ -164,7 +162,7 @@ EXPORT_SYMBOL_GPL(mbox_chan_received_data); */ void mbox_chan_txdone(struct mbox_chan *chan, int r) { - if (unlikely(!(chan->txdone_method & TXDONE_BY_IRQ))) { + if (unlikely(!(chan->txdone_method & MBOX_TXDONE_BY_IRQ))) { dev_err(chan->mbox->dev, "Controller can't run the TX ticker\n"); return; @@ -185,7 +183,7 @@ EXPORT_SYMBOL_GPL(mbox_chan_txdone); */ void mbox_client_txdone(struct mbox_chan *chan, int r) { - if (unlikely(!(chan->txdone_method & TXDONE_BY_ACK))) { + if (unlikely(!(chan->txdone_method & MBOX_TXDONE_BY_ACK))) { dev_err(chan->mbox->dev, "Client can't run the TX ticker\n"); return; } @@ -219,6 +217,29 @@ bool mbox_client_peek_data(struct mbox_chan *chan) EXPORT_SYMBOL_GPL(mbox_client_peek_data); /** + * mbox_chan_tx_slots_available - Query the number of available TX queue slots. + * @chan: Mailbox channel to query. + * + * Clients may call this to check how many messages can be queued via + * mbox_send_message() before the channel's TX queue is full. This helps + * clients avoid the -ENOBUFS error without needing to increase + * MBOX_TX_QUEUE_LEN. + * This can be called from atomic context. + * + * Return: Number of available slots in the channel's TX queue. + */ +unsigned int mbox_chan_tx_slots_available(struct mbox_chan *chan) +{ + unsigned int ret; + + guard(spinlock_irqsave)(&chan->lock); + ret = MBOX_TX_QUEUE_LEN - chan->msg_count; + + return ret; +} +EXPORT_SYMBOL_GPL(mbox_chan_tx_slots_available); + +/** * mbox_send_message - For client to submit a message to be * sent to the remote. * @chan: Mailbox channel assigned to this client. @@ -246,7 +267,7 @@ int mbox_send_message(struct mbox_chan *chan, void *mssg) { int t; - if (!chan || !chan->cl) + if (!chan || !chan->cl || mssg == MBOX_NO_MSG) return -EINVAL; t = add_to_rbuf(chan, mssg); @@ -319,12 +340,12 @@ static int __mbox_bind_client(struct mbox_chan *chan, struct mbox_client *cl) scoped_guard(spinlock_irqsave, &chan->lock) { chan->msg_free = 0; chan->msg_count = 0; - chan->active_req = NULL; + chan->active_req = MBOX_NO_MSG; chan->cl = cl; init_completion(&chan->tx_complete); - if (chan->txdone_method == TXDONE_BY_POLL && cl->knows_txdone) - chan->txdone_method = TXDONE_BY_ACK; + if (chan->txdone_method == MBOX_TXDONE_BY_POLL && cl->knows_txdone) + chan->txdone_method = MBOX_TXDONE_BY_ACK; } if (chan->mbox->ops->startup) { @@ -341,7 +362,7 @@ static int __mbox_bind_client(struct mbox_chan *chan, struct mbox_client *cl) } /** - * mbox_bind_client - Request a mailbox channel. + * mbox_bind_client - Bind client to a mailbox channel. * @chan: The mailbox channel to bind the client to. * @cl: Identity of the client requesting the channel. * @@ -477,9 +498,9 @@ void mbox_free_channel(struct mbox_chan *chan) /* The queued TX requests are simply aborted, no callbacks are made */ scoped_guard(spinlock_irqsave, &chan->lock) { chan->cl = NULL; - chan->active_req = NULL; - if (chan->txdone_method == TXDONE_BY_ACK) - chan->txdone_method = TXDONE_BY_POLL; + chan->active_req = MBOX_NO_MSG; + if (chan->txdone_method == MBOX_TXDONE_BY_ACK) + chan->txdone_method = MBOX_TXDONE_BY_POLL; } module_put(chan->mbox->dev->driver->owner); @@ -505,18 +526,17 @@ int mbox_controller_register(struct mbox_controller *mbox) { int i, txdone; - /* Sanity check */ - if (!mbox || !mbox->dev || !mbox->ops || !mbox->num_chans) + if (!mbox || !mbox->dev || !mbox->ops || !mbox->chans || !mbox->num_chans) return -EINVAL; if (mbox->txdone_irq) - txdone = TXDONE_BY_IRQ; + txdone = MBOX_TXDONE_BY_IRQ; else if (mbox->txdone_poll) - txdone = TXDONE_BY_POLL; + txdone = MBOX_TXDONE_BY_POLL; else /* It has to be ACK then */ - txdone = TXDONE_BY_ACK; + txdone = MBOX_TXDONE_BY_ACK; - if (txdone == TXDONE_BY_POLL) { + if (txdone == MBOX_TXDONE_BY_POLL) { if (!mbox->ops->last_tx_done) { dev_err(mbox->dev, "last_tx_done method is absent\n"); @@ -532,6 +552,7 @@ int mbox_controller_register(struct mbox_controller *mbox) chan->cl = NULL; chan->mbox = mbox; + chan->active_req = MBOX_NO_MSG; chan->txdone_method = txdone; spin_lock_init(&chan->lock); } diff --git a/drivers/mailbox/mailbox.h b/drivers/mailbox/mailbox.h deleted file mode 100644 index e1ec4efab693..000000000000 --- a/drivers/mailbox/mailbox.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ - -#ifndef __MAILBOX_H -#define __MAILBOX_H - -#include <linux/bits.h> - -#define TXDONE_BY_IRQ BIT(0) /* controller has remote RTR irq */ -#define TXDONE_BY_POLL BIT(1) /* controller can read status of last TX */ -#define TXDONE_BY_ACK BIT(2) /* S/W ACK received by Client ticks the TX */ - -#endif /* __MAILBOX_H */ diff --git a/drivers/mailbox/mtk-cmdq-mailbox.c b/drivers/mailbox/mtk-cmdq-mailbox.c index d7c6b38888a3..e523c84b4808 100644 --- a/drivers/mailbox/mtk-cmdq-mailbox.c +++ b/drivers/mailbox/mtk-cmdq-mailbox.c @@ -493,14 +493,14 @@ static int cmdq_mbox_send_data(struct mbox_chan *chan, void *data) if (curr_pa == end_pa - CMDQ_INST_SIZE || curr_pa == end_pa) { /* set to this task directly */ - writel(task->pa_base >> cmdq->pdata->shift, - thread->base + CMDQ_THR_CURR_ADDR); + gce_addr = cmdq_convert_gce_addr(task->pa_base, cmdq->pdata); + writel(gce_addr, thread->base + CMDQ_THR_CURR_ADDR); } else { cmdq_task_insert_into_thread(task); smp_mb(); /* modify jump before enable thread */ } - writel((task->pa_base + pkt->cmd_buf_size) >> cmdq->pdata->shift, - thread->base + CMDQ_THR_END_ADDR); + gce_addr = cmdq_convert_gce_addr(task->pa_base + pkt->cmd_buf_size, cmdq->pdata); + writel(gce_addr, thread->base + CMDQ_THR_END_ADDR); cmdq_thread_resume(thread); } list_move_tail(&task->list_entry, &thread->task_busy_list); @@ -728,7 +728,7 @@ static int cmdq_probe(struct platform_device *pdev) cmdq->mbox.ops = &cmdq_mbox_chan_ops; cmdq->mbox.of_xlate = cmdq_xlate; - /* make use of TXDONE_BY_ACK */ + /* make use of MBOX_TXDONE_BY_ACK */ cmdq->mbox.txdone_irq = false; cmdq->mbox.txdone_poll = false; diff --git a/drivers/mailbox/mtk-vcp-mailbox.c b/drivers/mailbox/mtk-vcp-mailbox.c index cedad575528f..1b291b8ea15a 100644 --- a/drivers/mailbox/mtk-vcp-mailbox.c +++ b/drivers/mailbox/mtk-vcp-mailbox.c @@ -50,7 +50,7 @@ static struct mbox_chan *mtk_vcp_mbox_xlate(struct mbox_controller *mbox, const struct of_phandle_args *sp) { if (sp->args_count) - return NULL; + return ERR_PTR(-EINVAL); return &mbox->chans[0]; } diff --git a/drivers/mailbox/omap-mailbox.c b/drivers/mailbox/omap-mailbox.c index d9f100c18895..535ca8020877 100644 --- a/drivers/mailbox/omap-mailbox.c +++ b/drivers/mailbox/omap-mailbox.c @@ -22,8 +22,6 @@ #include <linux/pm_runtime.h> #include <linux/mailbox_controller.h> -#include "mailbox.h" - #define MAILBOX_REVISION 0x000 #define MAILBOX_MESSAGE(m) (0x040 + 4 * (m)) #define MAILBOX_FIFOSTATUS(m) (0x080 + 4 * (m)) @@ -240,7 +238,7 @@ static int omap_mbox_startup(struct omap_mbox *mbox) } if (mbox->send_no_irq) - mbox->chan->txdone_method = TXDONE_BY_ACK; + mbox->chan->txdone_method = MBOX_TXDONE_BY_ACK; omap_mbox_enable_irq(mbox, IRQ_RX); diff --git a/drivers/mailbox/pcc.c b/drivers/mailbox/pcc.c index 22e70af1ae5d..636879ae1db7 100644 --- a/drivers/mailbox/pcc.c +++ b/drivers/mailbox/pcc.c @@ -59,8 +59,6 @@ #include <linux/io-64-nonatomic-lo-hi.h> #include <acpi/pcc.h> -#include "mailbox.h" - #define MBOX_IRQ_NAME "pcc-mbox" /** diff --git a/drivers/mailbox/rockchip-mailbox.c b/drivers/mailbox/rockchip-mailbox.c index 4d966cb2ed03..a1a7dee64356 100644 --- a/drivers/mailbox/rockchip-mailbox.c +++ b/drivers/mailbox/rockchip-mailbox.c @@ -46,7 +46,7 @@ struct rockchip_mbox { /* The maximum size of buf for each channel */ u32 buf_size; - struct rockchip_mbox_chan *chans; + struct rockchip_mbox_chan chans[]; }; static int rockchip_mbox_send_data(struct mbox_chan *chan, void *data) @@ -173,15 +173,10 @@ static int rockchip_mbox_probe(struct platform_device *pdev) drv_data = (const struct rockchip_mbox_data *) device_get_match_data(&pdev->dev); - mb = devm_kzalloc(&pdev->dev, sizeof(*mb), GFP_KERNEL); + mb = devm_kzalloc(&pdev->dev, struct_size(mb, chans, drv_data->num_chans), GFP_KERNEL); if (!mb) return -ENOMEM; - mb->chans = devm_kcalloc(&pdev->dev, drv_data->num_chans, - sizeof(*mb->chans), GFP_KERNEL); - if (!mb->chans) - return -ENOMEM; - mb->mbox.chans = devm_kcalloc(&pdev->dev, drv_data->num_chans, sizeof(*mb->mbox.chans), GFP_KERNEL); if (!mb->mbox.chans) diff --git a/drivers/mailbox/tegra-hsp.c b/drivers/mailbox/tegra-hsp.c index ed9a0bb2bcd8..500fa77c7d53 100644 --- a/drivers/mailbox/tegra-hsp.c +++ b/drivers/mailbox/tegra-hsp.c @@ -16,8 +16,6 @@ #include <dt-bindings/mailbox/tegra186-hsp.h> -#include "mailbox.h" - #define HSP_INT_IE(x) (0x100 + ((x) * 4)) #define HSP_INT_IV 0x300 #define HSP_INT_IR 0x304 @@ -497,7 +495,7 @@ static int tegra_hsp_mailbox_flush(struct mbox_chan *chan, mbox_chan_txdone(chan, 0); /* Wait until channel is empty */ - if (chan->active_req != NULL) + if (chan->active_req != MBOX_NO_MSG) continue; return 0; @@ -516,7 +514,7 @@ static int tegra_hsp_mailbox_startup(struct mbox_chan *chan) struct tegra_hsp *hsp = mb->channel.hsp; unsigned long flags; - chan->txdone_method = TXDONE_BY_IRQ; + chan->txdone_method = MBOX_TXDONE_BY_IRQ; /* * Shared mailboxes start out as consumers by default. FULL and EMPTY diff --git a/drivers/md/persistent-data/dm-btree-remove.c b/drivers/md/persistent-data/dm-btree-remove.c index 942cd47eb52d..aeec5b9a1dd5 100644 --- a/drivers/md/persistent-data/dm-btree-remove.c +++ b/drivers/md/persistent-data/dm-btree-remove.c @@ -490,12 +490,20 @@ static int rebalance_children(struct shadow_spine *s, if (le32_to_cpu(n->header.nr_entries) == 1) { struct dm_block *child; + int is_shared; dm_block_t b = value64(n, 0); + r = dm_tm_block_is_shared(info->tm, b, &is_shared); + if (r) + return r; + r = dm_tm_read_lock(info->tm, b, &btree_node_validator, &child); if (r) return r; + if (is_shared) + inc_children(info->tm, dm_block_data(child), vt); + memcpy(n, dm_block_data(child), dm_bm_block_size(dm_tm_get_bm(info->tm))); diff --git a/drivers/media/platform/qcom/camss/camss-csid-gen3.c b/drivers/media/platform/qcom/camss/camss-csid-gen3.c index 664245cf6eb0..bd059243790e 100644 --- a/drivers/media/platform/qcom/camss/camss-csid-gen3.c +++ b/drivers/media/platform/qcom/camss/camss-csid-gen3.c @@ -48,9 +48,9 @@ #define IS_CSID_690(csid) ((csid->camss->res->version == CAMSS_8775P) \ || (csid->camss->res->version == CAMSS_8300)) #define CSID_BUF_DONE_IRQ_STATUS 0x8C -#define BUF_DONE_IRQ_STATUS_RDI_OFFSET (csid_is_lite(csid) ?\ - 1 : (IS_CSID_690(csid) ?\ - 13 : 14)) +#define BUF_DONE_IRQ_STATUS_RDI_OFFSET (csid_is_lite(csid) ? \ + ((IS_CSID_690(csid) ? 0 : 1)) : \ + ((IS_CSID_690(csid) ? 13 : 14))) #define CSID_BUF_DONE_IRQ_MASK 0x90 #define CSID_BUF_DONE_IRQ_CLEAR 0x94 #define CSID_BUF_DONE_IRQ_SET 0x98 diff --git a/drivers/media/platform/qcom/camss/camss-csiphy.c b/drivers/media/platform/qcom/camss/camss-csiphy.c index 62623393f414..78a1b568dbae 100644 --- a/drivers/media/platform/qcom/camss/camss-csiphy.c +++ b/drivers/media/platform/qcom/camss/camss-csiphy.c @@ -558,12 +558,16 @@ static int csiphy_init_formats(struct v4l2_subdev *sd, return csiphy_set_format(sd, fh ? fh->state : NULL, &format); } -static bool csiphy_match_clock_name(const char *clock_name, const char *format, - int index) +static bool __printf(2, 3) +csiphy_match_clock_name(const char *clock_name, const char *format, ...) { char name[16]; /* csiphyXXX_timer\0 */ + va_list args; + + va_start(args, format); + vsnprintf(name, sizeof(name), format, args); + va_end(args); - snprintf(name, sizeof(name), format, index); return !strcmp(clock_name, name); } diff --git a/drivers/media/platform/qcom/camss/camss.c b/drivers/media/platform/qcom/camss/camss.c index 00b87fd9afbd..9335636d7c4d 100644 --- a/drivers/media/platform/qcom/camss/camss.c +++ b/drivers/media/platform/qcom/camss/camss.c @@ -3598,12 +3598,10 @@ static const struct camss_subdev_resources csid_res_8775p[] = { /* CSID2 (lite) */ { .regulators = {}, - .clock = { "cpas_vfe_lite", "vfe_lite_ahb", - "vfe_lite_csid", "vfe_lite_cphy_rx", - "vfe_lite"}, + .clock = { "vfe_lite_csid", "vfe_lite_cphy_rx" }, .clock_rate = { - { 0, 0, 400000000, 400000000, 0}, - { 0, 0, 400000000, 480000000, 0} + { 400000000, 480000000 }, + { 400000000, 480000000 } }, .reg = { "csid_lite0" }, .interrupt = { "csid_lite0" }, @@ -3617,12 +3615,10 @@ static const struct camss_subdev_resources csid_res_8775p[] = { /* CSID3 (lite) */ { .regulators = {}, - .clock = { "cpas_vfe_lite", "vfe_lite_ahb", - "vfe_lite_csid", "vfe_lite_cphy_rx", - "vfe_lite"}, + .clock = { "vfe_lite_csid", "vfe_lite_cphy_rx" }, .clock_rate = { - { 0, 0, 400000000, 400000000, 0}, - { 0, 0, 400000000, 480000000, 0} + { 400000000, 480000000 }, + { 400000000, 480000000 } }, .reg = { "csid_lite1" }, .interrupt = { "csid_lite1" }, @@ -3636,12 +3632,10 @@ static const struct camss_subdev_resources csid_res_8775p[] = { /* CSID4 (lite) */ { .regulators = {}, - .clock = { "cpas_vfe_lite", "vfe_lite_ahb", - "vfe_lite_csid", "vfe_lite_cphy_rx", - "vfe_lite"}, + .clock = { "vfe_lite_csid", "vfe_lite_cphy_rx" }, .clock_rate = { - { 0, 0, 400000000, 400000000, 0}, - { 0, 0, 400000000, 480000000, 0} + { 400000000, 480000000 }, + { 400000000, 480000000 } }, .reg = { "csid_lite2" }, .interrupt = { "csid_lite2" }, @@ -3655,12 +3649,10 @@ static const struct camss_subdev_resources csid_res_8775p[] = { /* CSID5 (lite) */ { .regulators = {}, - .clock = { "cpas_vfe_lite", "vfe_lite_ahb", - "vfe_lite_csid", "vfe_lite_cphy_rx", - "vfe_lite"}, + .clock = { "vfe_lite_csid", "vfe_lite_cphy_rx" }, .clock_rate = { - { 0, 0, 400000000, 400000000, 0}, - { 0, 0, 400000000, 480000000, 0} + { 400000000, 480000000 }, + { 400000000, 480000000 } }, .reg = { "csid_lite3" }, .interrupt = { "csid_lite3" }, @@ -3674,12 +3666,10 @@ static const struct camss_subdev_resources csid_res_8775p[] = { /* CSID6 (lite) */ { .regulators = {}, - .clock = { "cpas_vfe_lite", "vfe_lite_ahb", - "vfe_lite_csid", "vfe_lite_cphy_rx", - "vfe_lite"}, + .clock = { "vfe_lite_csid", "vfe_lite_cphy_rx" }, .clock_rate = { - { 0, 0, 400000000, 400000000, 0}, - { 0, 0, 400000000, 480000000, 0} + { 400000000, 480000000 }, + { 400000000, 480000000 } }, .reg = { "csid_lite4" }, .interrupt = { "csid_lite4" }, @@ -3752,15 +3742,17 @@ static const struct camss_subdev_resources vfe_res_8775p[] = { /* VFE2 (lite) */ { .regulators = {}, - .clock = { "cpas_vfe_lite", "vfe_lite_ahb", + .clock = { "cpas_ahb", "cpas_vfe_lite", "vfe_lite_ahb", "vfe_lite_csid", "vfe_lite_cphy_rx", - "vfe_lite"}, + "vfe_lite", "camnoc_axi"}, .clock_rate = { - { 0, 0, 0, 0 }, + { 0 }, + { 0 }, { 300000000, 400000000, 400000000, 400000000 }, { 400000000, 400000000, 400000000, 400000000 }, { 400000000, 400000000, 400000000, 400000000 }, { 480000000, 600000000, 600000000, 600000000 }, + { 400000000 }, }, .reg = { "vfe_lite0" }, .interrupt = { "vfe_lite0" }, @@ -3775,15 +3767,17 @@ static const struct camss_subdev_resources vfe_res_8775p[] = { /* VFE3 (lite) */ { .regulators = {}, - .clock = { "cpas_vfe_lite", "vfe_lite_ahb", + .clock = { "cpas_ahb", "cpas_vfe_lite", "vfe_lite_ahb", "vfe_lite_csid", "vfe_lite_cphy_rx", - "vfe_lite"}, + "vfe_lite", "camnoc_axi"}, .clock_rate = { - { 0, 0, 0, 0 }, + { 0 }, + { 0 }, { 300000000, 400000000, 400000000, 400000000 }, { 400000000, 400000000, 400000000, 400000000 }, { 400000000, 400000000, 400000000, 400000000 }, { 480000000, 600000000, 600000000, 600000000 }, + { 400000000 }, }, .reg = { "vfe_lite1" }, .interrupt = { "vfe_lite1" }, @@ -3798,15 +3792,17 @@ static const struct camss_subdev_resources vfe_res_8775p[] = { /* VFE4 (lite) */ { .regulators = {}, - .clock = { "cpas_vfe_lite", "vfe_lite_ahb", + .clock = { "cpas_ahb", "cpas_vfe_lite", "vfe_lite_ahb", "vfe_lite_csid", "vfe_lite_cphy_rx", - "vfe_lite"}, + "vfe_lite", "camnoc_axi"}, .clock_rate = { - { 0, 0, 0, 0 }, + { 0 }, + { 0 }, { 300000000, 400000000, 400000000, 400000000 }, { 400000000, 400000000, 400000000, 400000000 }, { 400000000, 400000000, 400000000, 400000000 }, { 480000000, 600000000, 600000000, 600000000 }, + { 400000000 }, }, .reg = { "vfe_lite2" }, .interrupt = { "vfe_lite2" }, @@ -3821,15 +3817,17 @@ static const struct camss_subdev_resources vfe_res_8775p[] = { /* VFE5 (lite) */ { .regulators = {}, - .clock = { "cpas_vfe_lite", "vfe_lite_ahb", + .clock = { "cpas_ahb", "cpas_vfe_lite", "vfe_lite_ahb", "vfe_lite_csid", "vfe_lite_cphy_rx", - "vfe_lite"}, + "vfe_lite", "camnoc_axi"}, .clock_rate = { - { 0, 0, 0, 0 }, + { 0 }, + { 0 }, { 300000000, 400000000, 400000000, 400000000 }, { 400000000, 400000000, 400000000, 400000000 }, { 400000000, 400000000, 400000000, 400000000 }, { 480000000, 600000000, 600000000, 600000000 }, + { 400000000 }, }, .reg = { "vfe_lite3" }, .interrupt = { "vfe_lite3" }, @@ -3844,15 +3842,17 @@ static const struct camss_subdev_resources vfe_res_8775p[] = { /* VFE6 (lite) */ { .regulators = {}, - .clock = { "cpas_vfe_lite", "vfe_lite_ahb", + .clock = { "cpas_ahb", "cpas_vfe_lite", "vfe_lite_ahb", "vfe_lite_csid", "vfe_lite_cphy_rx", - "vfe_lite"}, + "vfe_lite", "camnoc_axi"}, .clock_rate = { - { 0, 0, 0, 0 }, + { 0 }, + { 0 }, { 300000000, 400000000, 400000000, 400000000 }, { 400000000, 400000000, 400000000, 400000000 }, { 400000000, 400000000, 400000000, 400000000 }, { 480000000, 600000000, 600000000, 600000000 }, + { 400000000 }, }, .reg = { "vfe_lite4" }, .interrupt = { "vfe_lite4" }, diff --git a/drivers/media/platform/qcom/iris/Kconfig b/drivers/media/platform/qcom/iris/Kconfig index 3c803a05305a..5498f48362d1 100644 --- a/drivers/media/platform/qcom/iris/Kconfig +++ b/drivers/media/platform/qcom/iris/Kconfig @@ -3,7 +3,7 @@ config VIDEO_QCOM_IRIS depends on VIDEO_DEV depends on ARCH_QCOM || COMPILE_TEST select V4L2_MEM2MEM_DEV - select QCOM_MDT_LOADER if ARCH_QCOM + select QCOM_MDT_LOADER select QCOM_SCM select VIDEOBUF2_DMA_CONTIG help diff --git a/drivers/media/platform/qcom/iris/iris_buffer.c b/drivers/media/platform/qcom/iris/iris_buffer.c index 9151f43bc6b9..1d53c7414b75 100644 --- a/drivers/media/platform/qcom/iris/iris_buffer.c +++ b/drivers/media/platform/qcom/iris/iris_buffer.c @@ -582,10 +582,12 @@ static int iris_release_internal_buffers(struct iris_inst *inst, continue; if (!(buffer->attr & BUF_ATTR_QUEUED)) continue; + buffer->attr |= BUF_ATTR_PENDING_RELEASE; ret = hfi_ops->session_release_buf(inst, buffer); - if (ret) + if (ret) { + buffer->attr &= ~BUF_ATTR_PENDING_RELEASE; return ret; - buffer->attr |= BUF_ATTR_PENDING_RELEASE; + } } return 0; diff --git a/drivers/media/platform/qcom/iris/iris_core.c b/drivers/media/platform/qcom/iris/iris_core.c index 8406c48d635b..dbaac01eb15a 100644 --- a/drivers/media/platform/qcom/iris/iris_core.c +++ b/drivers/media/platform/qcom/iris/iris_core.c @@ -75,6 +75,10 @@ int iris_core_init(struct iris_core *core) if (ret) goto error_unload_fw; + ret = iris_vpu_switch_to_hwmode(core); + if (ret) + goto error_unload_fw; + ret = iris_hfi_core_init(core); if (ret) goto error_unload_fw; diff --git a/drivers/media/platform/qcom/iris/iris_hfi_common.c b/drivers/media/platform/qcom/iris/iris_hfi_common.c index 92112eb16c11..621c66593d88 100644 --- a/drivers/media/platform/qcom/iris/iris_hfi_common.c +++ b/drivers/media/platform/qcom/iris/iris_hfi_common.c @@ -159,6 +159,10 @@ int iris_hfi_pm_resume(struct iris_core *core) if (ret) goto err_suspend_hw; + ret = iris_vpu_switch_to_hwmode(core); + if (ret) + goto err_suspend_hw; + ret = ops->sys_interframe_powercollapse(core); if (ret) goto err_suspend_hw; diff --git a/drivers/media/platform/qcom/iris/iris_hfi_queue.c b/drivers/media/platform/qcom/iris/iris_hfi_queue.c index b3ed06297953..bf6db23b53e2 100644 --- a/drivers/media/platform/qcom/iris/iris_hfi_queue.c +++ b/drivers/media/platform/qcom/iris/iris_hfi_queue.c @@ -263,7 +263,7 @@ int iris_hfi_queues_init(struct iris_core *core) GFP_KERNEL, DMA_ATTR_WRITE_COMBINE); if (!core->sfr_vaddr) { dev_err(core->dev, "sfr alloc and map failed\n"); - dma_free_attrs(core->dev, sizeof(*q_tbl_hdr), core->iface_q_table_vaddr, + dma_free_attrs(core->dev, queue_size, core->iface_q_table_vaddr, core->iface_q_table_daddr, DMA_ATTR_WRITE_COMBINE); return -ENOMEM; } diff --git a/drivers/media/platform/qcom/iris/iris_vdec.c b/drivers/media/platform/qcom/iris/iris_vdec.c index 719217399a30..99d544e2af4f 100644 --- a/drivers/media/platform/qcom/iris/iris_vdec.c +++ b/drivers/media/platform/qcom/iris/iris_vdec.c @@ -61,12 +61,6 @@ int iris_vdec_inst_init(struct iris_inst *inst) return iris_ctrls_init(inst); } -void iris_vdec_inst_deinit(struct iris_inst *inst) -{ - kfree(inst->fmt_dst); - kfree(inst->fmt_src); -} - static const struct iris_fmt iris_vdec_formats_cap[] = { [IRIS_FMT_NV12] = { .pixfmt = V4L2_PIX_FMT_NV12, diff --git a/drivers/media/platform/qcom/iris/iris_vdec.h b/drivers/media/platform/qcom/iris/iris_vdec.h index ec1ce55d1375..5123d2a340e1 100644 --- a/drivers/media/platform/qcom/iris/iris_vdec.h +++ b/drivers/media/platform/qcom/iris/iris_vdec.h @@ -9,7 +9,6 @@ struct iris_inst; int iris_vdec_inst_init(struct iris_inst *inst); -void iris_vdec_inst_deinit(struct iris_inst *inst); int iris_vdec_enum_fmt(struct iris_inst *inst, struct v4l2_fmtdesc *f); int iris_vdec_try_fmt(struct iris_inst *inst, struct v4l2_format *f); int iris_vdec_s_fmt(struct iris_inst *inst, struct v4l2_format *f); diff --git a/drivers/media/platform/qcom/iris/iris_venc.c b/drivers/media/platform/qcom/iris/iris_venc.c index aa27b22704eb..4d886769d958 100644 --- a/drivers/media/platform/qcom/iris/iris_venc.c +++ b/drivers/media/platform/qcom/iris/iris_venc.c @@ -79,12 +79,6 @@ int iris_venc_inst_init(struct iris_inst *inst) return iris_ctrls_init(inst); } -void iris_venc_inst_deinit(struct iris_inst *inst) -{ - kfree(inst->fmt_dst); - kfree(inst->fmt_src); -} - static const struct iris_fmt iris_venc_formats_cap[] = { [IRIS_FMT_H264] = { .pixfmt = V4L2_PIX_FMT_H264, diff --git a/drivers/media/platform/qcom/iris/iris_venc.h b/drivers/media/platform/qcom/iris/iris_venc.h index c4db7433da53..00c1716b2747 100644 --- a/drivers/media/platform/qcom/iris/iris_venc.h +++ b/drivers/media/platform/qcom/iris/iris_venc.h @@ -9,7 +9,6 @@ struct iris_inst; int iris_venc_inst_init(struct iris_inst *inst); -void iris_venc_inst_deinit(struct iris_inst *inst); int iris_venc_enum_fmt(struct iris_inst *inst, struct v4l2_fmtdesc *f); int iris_venc_try_fmt(struct iris_inst *inst, struct v4l2_format *f); int iris_venc_s_fmt(struct iris_inst *inst, struct v4l2_format *f); diff --git a/drivers/media/platform/qcom/iris/iris_vidc.c b/drivers/media/platform/qcom/iris/iris_vidc.c index bd38d84c9cc7..5eb1786b0737 100644 --- a/drivers/media/platform/qcom/iris/iris_vidc.c +++ b/drivers/media/platform/qcom/iris/iris_vidc.c @@ -289,10 +289,6 @@ int iris_close(struct file *filp) v4l2_m2m_ctx_release(inst->m2m_ctx); v4l2_m2m_release(inst->m2m_dev); mutex_lock(&inst->lock); - if (inst->domain == DECODER) - iris_vdec_inst_deinit(inst); - else if (inst->domain == ENCODER) - iris_venc_inst_deinit(inst); iris_session_close(inst); iris_inst_change_state(inst, IRIS_INST_DEINIT); iris_v4l2_fh_deinit(inst, filp); @@ -304,6 +300,8 @@ int iris_close(struct file *filp) mutex_unlock(&inst->lock); mutex_destroy(&inst->ctx_q_lock); mutex_destroy(&inst->lock); + kfree(inst->fmt_src); + kfree(inst->fmt_dst); kfree(inst); return 0; diff --git a/drivers/media/platform/qcom/iris/iris_vpu2.c b/drivers/media/platform/qcom/iris/iris_vpu2.c index 9c103a2e4e4e..01ef40f38957 100644 --- a/drivers/media/platform/qcom/iris/iris_vpu2.c +++ b/drivers/media/platform/qcom/iris/iris_vpu2.c @@ -44,4 +44,5 @@ const struct vpu_ops iris_vpu2_ops = { .power_off_controller = iris_vpu_power_off_controller, .power_on_controller = iris_vpu_power_on_controller, .calc_freq = iris_vpu2_calc_freq, + .set_hwmode = iris_vpu_set_hwmode, }; diff --git a/drivers/media/platform/qcom/iris/iris_vpu3x.c b/drivers/media/platform/qcom/iris/iris_vpu3x.c index fe4423b951b1..3dad47be78b5 100644 --- a/drivers/media/platform/qcom/iris/iris_vpu3x.c +++ b/drivers/media/platform/qcom/iris/iris_vpu3x.c @@ -234,14 +234,8 @@ static int iris_vpu35_power_on_hw(struct iris_core *core) if (ret) goto err_disable_hw_free_clk; - ret = dev_pm_genpd_set_hwmode(core->pmdomain_tbl->pd_devs[IRIS_HW_POWER_DOMAIN], true); - if (ret) - goto err_disable_hw_clk; - return 0; -err_disable_hw_clk: - iris_disable_unprepare_clock(core, IRIS_HW_CLK); err_disable_hw_free_clk: iris_disable_unprepare_clock(core, IRIS_HW_FREERUN_CLK); err_disable_axi_clk: @@ -266,6 +260,7 @@ const struct vpu_ops iris_vpu3_ops = { .power_off_controller = iris_vpu_power_off_controller, .power_on_controller = iris_vpu_power_on_controller, .calc_freq = iris_vpu3x_vpu4x_calculate_frequency, + .set_hwmode = iris_vpu_set_hwmode, }; const struct vpu_ops iris_vpu33_ops = { @@ -274,6 +269,7 @@ const struct vpu_ops iris_vpu33_ops = { .power_off_controller = iris_vpu33_power_off_controller, .power_on_controller = iris_vpu_power_on_controller, .calc_freq = iris_vpu3x_vpu4x_calculate_frequency, + .set_hwmode = iris_vpu_set_hwmode, }; const struct vpu_ops iris_vpu35_ops = { @@ -283,4 +279,5 @@ const struct vpu_ops iris_vpu35_ops = { .power_on_controller = iris_vpu35_vpu4x_power_on_controller, .program_bootup_registers = iris_vpu35_vpu4x_program_bootup_registers, .calc_freq = iris_vpu3x_vpu4x_calculate_frequency, + .set_hwmode = iris_vpu_set_hwmode, }; diff --git a/drivers/media/platform/qcom/iris/iris_vpu4x.c b/drivers/media/platform/qcom/iris/iris_vpu4x.c index a8db02ce5c5e..02e100a4045f 100644 --- a/drivers/media/platform/qcom/iris/iris_vpu4x.c +++ b/drivers/media/platform/qcom/iris/iris_vpu4x.c @@ -252,21 +252,10 @@ static int iris_vpu4x_power_on_hardware(struct iris_core *core) ret = iris_vpu4x_power_on_apv(core); if (ret) goto disable_hw_clocks; - - iris_vpu4x_ahb_sync_reset_apv(core); } - iris_vpu4x_ahb_sync_reset_hardware(core); - - ret = iris_vpu4x_genpd_set_hwmode(core, true, efuse_value); - if (ret) - goto disable_apv_power_domain; - return 0; -disable_apv_power_domain: - if (!(efuse_value & DISABLE_VIDEO_APV_BIT)) - iris_vpu4x_power_off_apv(core); disable_hw_clocks: iris_vpu4x_disable_hardware_clocks(core, efuse_value); disable_vpp1_power_domain: @@ -359,6 +348,18 @@ disable_clocks_and_power: iris_disable_power_domains(core, core->pmdomain_tbl->pd_devs[IRIS_HW_POWER_DOMAIN]); } +static int iris_vpu4x_set_hwmode(struct iris_core *core) +{ + u32 efuse_value = readl(core->reg_base + WRAPPER_EFUSE_MONITOR); + + if (!(efuse_value & DISABLE_VIDEO_APV_BIT)) + iris_vpu4x_ahb_sync_reset_apv(core); + + iris_vpu4x_ahb_sync_reset_hardware(core); + + return iris_vpu4x_genpd_set_hwmode(core, true, efuse_value); +} + const struct vpu_ops iris_vpu4x_ops = { .power_off_hw = iris_vpu4x_power_off_hardware, .power_on_hw = iris_vpu4x_power_on_hardware, @@ -366,4 +367,5 @@ const struct vpu_ops iris_vpu4x_ops = { .power_on_controller = iris_vpu35_vpu4x_power_on_controller, .program_bootup_registers = iris_vpu35_vpu4x_program_bootup_registers, .calc_freq = iris_vpu3x_vpu4x_calculate_frequency, + .set_hwmode = iris_vpu4x_set_hwmode, }; diff --git a/drivers/media/platform/qcom/iris/iris_vpu_buffer.h b/drivers/media/platform/qcom/iris/iris_vpu_buffer.h index 12640eb5ed8c..8c0d6b7b5de8 100644 --- a/drivers/media/platform/qcom/iris/iris_vpu_buffer.h +++ b/drivers/media/platform/qcom/iris/iris_vpu_buffer.h @@ -67,7 +67,7 @@ struct iris_inst; #define SIZE_DOLBY_RPU_METADATA (41 * 1024) #define H264_CABAC_HDR_RATIO_HD_TOT 1 #define H264_CABAC_RES_RATIO_HD_TOT 3 -#define H265D_MAX_SLICE 1200 +#define H265D_MAX_SLICE 3600 #define SIZE_H265D_HW_PIC_T SIZE_H264D_HW_PIC_T #define H265_CABAC_HDR_RATIO_HD_TOT 2 #define H265_CABAC_RES_RATIO_HD_TOT 2 diff --git a/drivers/media/platform/qcom/iris/iris_vpu_common.c b/drivers/media/platform/qcom/iris/iris_vpu_common.c index 548e5f1727fd..69e6126dc4d9 100644 --- a/drivers/media/platform/qcom/iris/iris_vpu_common.c +++ b/drivers/media/platform/qcom/iris/iris_vpu_common.c @@ -292,14 +292,8 @@ int iris_vpu_power_on_hw(struct iris_core *core) if (ret && ret != -ENOENT) goto err_disable_hw_clock; - ret = dev_pm_genpd_set_hwmode(core->pmdomain_tbl->pd_devs[IRIS_HW_POWER_DOMAIN], true); - if (ret) - goto err_disable_hw_ahb_clock; - return 0; -err_disable_hw_ahb_clock: - iris_disable_unprepare_clock(core, IRIS_HW_AHB_CLK); err_disable_hw_clock: iris_disable_unprepare_clock(core, IRIS_HW_CLK); err_disable_power: @@ -308,6 +302,16 @@ err_disable_power: return ret; } +int iris_vpu_set_hwmode(struct iris_core *core) +{ + return dev_pm_genpd_set_hwmode(core->pmdomain_tbl->pd_devs[IRIS_HW_POWER_DOMAIN], true); +} + +int iris_vpu_switch_to_hwmode(struct iris_core *core) +{ + return core->iris_platform_data->vpu_ops->set_hwmode(core); +} + int iris_vpu35_vpu4x_power_off_controller(struct iris_core *core) { u32 clk_rst_tbl_size = core->iris_platform_data->clk_rst_tbl_size; diff --git a/drivers/media/platform/qcom/iris/iris_vpu_common.h b/drivers/media/platform/qcom/iris/iris_vpu_common.h index f6dffc613b82..dee3b1349c5e 100644 --- a/drivers/media/platform/qcom/iris/iris_vpu_common.h +++ b/drivers/media/platform/qcom/iris/iris_vpu_common.h @@ -21,6 +21,7 @@ struct vpu_ops { int (*power_on_controller)(struct iris_core *core); void (*program_bootup_registers)(struct iris_core *core); u64 (*calc_freq)(struct iris_inst *inst, size_t data_size); + int (*set_hwmode)(struct iris_core *core); }; int iris_vpu_boot_firmware(struct iris_core *core); @@ -30,6 +31,8 @@ int iris_vpu_watchdog(struct iris_core *core, u32 intr_status); int iris_vpu_prepare_pc(struct iris_core *core); int iris_vpu_power_on_controller(struct iris_core *core); int iris_vpu_power_on_hw(struct iris_core *core); +int iris_vpu_set_hwmode(struct iris_core *core); +int iris_vpu_switch_to_hwmode(struct iris_core *core); int iris_vpu_power_on(struct iris_core *core); int iris_vpu_power_off_controller(struct iris_core *core); void iris_vpu_power_off_hw(struct iris_core *core); diff --git a/drivers/media/platform/qcom/venus/Kconfig b/drivers/media/platform/qcom/venus/Kconfig index ffb731ecd48c..63ee8c78dc6d 100644 --- a/drivers/media/platform/qcom/venus/Kconfig +++ b/drivers/media/platform/qcom/venus/Kconfig @@ -4,7 +4,7 @@ config VIDEO_QCOM_VENUS depends on VIDEO_DEV && QCOM_SMEM depends on (ARCH_QCOM && ARM64 && IOMMU_API) || COMPILE_TEST select OF_DYNAMIC if ARCH_QCOM - select QCOM_MDT_LOADER if ARCH_QCOM + select QCOM_MDT_LOADER select QCOM_SCM select VIDEOBUF2_DMA_CONTIG select V4L2_MEM2MEM_DEV diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c index 8aa3753aaaa1..0b076790bd9d 100644 --- a/drivers/mtd/nand/spi/core.c +++ b/drivers/mtd/nand/spi/core.c @@ -100,6 +100,17 @@ spinand_fill_page_read_op(struct spinand_device *spinand, u64 addr) return op; } +static struct spi_mem_op +spinand_fill_page_read_packed_op(struct spinand_device *spinand, u64 addr) +{ + struct spi_mem_op op = spinand->op_templates->page_read; + + op.cmd.opcode |= addr >> 16; + op.addr.val = addr & 0xFFFF; + + return op; +} + struct spi_mem_op spinand_fill_prog_exec_op(struct spinand_device *spinand, u64 addr) { @@ -453,7 +464,10 @@ static int spinand_load_page_op(struct spinand_device *spinand, { struct nand_device *nand = spinand_to_nand(spinand); unsigned int row = nanddev_pos_to_row(nand, &req->pos); - struct spi_mem_op op = SPINAND_OP(spinand, page_read, row); + bool packed = spinand->flags & SPINAND_ODTR_PACKED_PAGE_READ; + struct spi_mem_op op = packed ? + SPINAND_OP(spinand, page_read_packed, row) : + SPINAND_OP(spinand, page_read, row); return spi_mem_exec_op(spinand->spimem, &op); } @@ -1489,9 +1503,13 @@ static int spinand_init_odtr_instruction_set(struct spinand_device *spinand) if (!spi_mem_supports_op(spinand->spimem, &tmpl->blk_erase)) return -EOPNOTSUPP; - tmpl->page_read = (struct spi_mem_op)SPINAND_PAGE_READ_8D_8D_0_OP(0); - if (!spi_mem_supports_op(spinand->spimem, &tmpl->page_read)) + if (spinand->flags & SPINAND_ODTR_PACKED_PAGE_READ) + tmpl->page_read = (struct spi_mem_op)SPINAND_PAGE_READ_PACKED_8D_8D_0_OP(0); + else + tmpl->page_read = (struct spi_mem_op)SPINAND_PAGE_READ_8D_8D_0_OP(0); + if (!spi_mem_supports_op(spinand->spimem, &tmpl->page_read)) { return -EOPNOTSUPP; + } tmpl->prog_exec = (struct spi_mem_op)SPINAND_PROG_EXEC_8D_8D_0_OP(0); if (!spi_mem_supports_op(spinand->spimem, &tmpl->prog_exec)) diff --git a/drivers/mtd/nand/spi/winbond.c b/drivers/mtd/nand/spi/winbond.c index ad22774096e6..7cc0f0091430 100644 --- a/drivers/mtd/nand/spi/winbond.c +++ b/drivers/mtd/nand/spi/winbond.c @@ -99,7 +99,7 @@ static SPINAND_OP_VARIANTS(update_cache_variants, #define SPINAND_WINBOND_WRITE_VCR_8D_8D_8D(reg, buf) \ SPI_MEM_OP(SPI_MEM_DTR_OP_RPT_CMD(0x81, 8), \ - SPI_MEM_DTR_OP_ADDR(4, reg, 8), \ + SPI_MEM_DTR_OP_ADDR(4, reg << 8, 8), \ SPI_MEM_OP_NO_DUMMY, \ SPI_MEM_DTR_OP_DATA_OUT(2, buf, 8)) @@ -518,7 +518,7 @@ static const struct spinand_info winbond_spinand_table[] = { SPINAND_INFO_OP_VARIANTS(&read_cache_octal_variants, &write_cache_octal_variants, &update_cache_octal_variants), - 0, + SPINAND_ODTR_PACKED_PAGE_READ, SPINAND_INFO_VENDOR_OPS(&winbond_w35_ops), SPINAND_ECCINFO(&w35n01jw_ooblayout, NULL), SPINAND_CONFIGURE_CHIP(w35n0xjw_vcr_cfg)), @@ -529,7 +529,7 @@ static const struct spinand_info winbond_spinand_table[] = { SPINAND_INFO_OP_VARIANTS(&read_cache_octal_variants, &write_cache_octal_variants, &update_cache_octal_variants), - 0, + SPINAND_ODTR_PACKED_PAGE_READ, SPINAND_INFO_VENDOR_OPS(&winbond_w35_ops), SPINAND_ECCINFO(&w35n01jw_ooblayout, NULL), SPINAND_CONFIGURE_CHIP(w35n0xjw_vcr_cfg)), diff --git a/drivers/mtd/spi-nor/debugfs.c b/drivers/mtd/spi-nor/debugfs.c index fa6956144d2e..14ba1680c315 100644 --- a/drivers/mtd/spi-nor/debugfs.c +++ b/drivers/mtd/spi-nor/debugfs.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 +#include <linux/array_size.h> #include <linux/debugfs.h> #include <linux/mtd/spi-nor.h> #include <linux/spi/spi.h> @@ -92,7 +93,8 @@ static int spi_nor_params_show(struct seq_file *s, void *data) seq_printf(s, "address nbytes\t%u\n", nor->addr_nbytes); seq_puts(s, "flags\t\t"); - spi_nor_print_flags(s, nor->flags, snor_f_names, sizeof(snor_f_names)); + spi_nor_print_flags(s, nor->flags, snor_f_names, + ARRAY_SIZE(snor_f_names)); seq_puts(s, "\n"); seq_puts(s, "\nopcodes\n"); diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c index 0df3208783ad..da5866ba0699 100644 --- a/drivers/net/bareudp.c +++ b/drivers/net/bareudp.c @@ -529,6 +529,9 @@ static int bareudp_fill_metadata_dst(struct net_device *dev, struct in6_addr saddr; struct socket *sock = rcu_dereference(bareudp->sock); + if (!sock) + return -ESHUTDOWN; + dst = udp_tunnel6_dst_lookup(skb, dev, bareudp->net, sock, 0, &saddr, &info->key, sport, bareudp->port, info->key.tos, diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index af7f74cfdc08..f0aa7d2f2171 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -1029,6 +1029,7 @@ static void ad_cond_set_peer_notif(struct port *port) static void ad_mux_machine(struct port *port, bool *update_slave_arr) { struct bonding *bond = __get_bond_by_port(port); + struct aggregator *aggregator; mux_states_t last_state; /* keep current State Machine state to compare later if it was @@ -1036,6 +1037,7 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) */ last_state = port->sm_mux_state; + aggregator = rcu_dereference(port->aggregator); if (port->sm_vars & AD_PORT_BEGIN) { port->sm_mux_state = AD_MUX_DETACHED; } else { @@ -1055,7 +1057,7 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) * cycle to update ready variable, we check * READY_N and update READY here */ - __set_agg_ports_ready(port->aggregator, __agg_ports_are_ready(port->aggregator)); + __set_agg_ports_ready(aggregator, __agg_ports_are_ready(aggregator)); port->sm_mux_state = AD_MUX_DETACHED; break; } @@ -1070,7 +1072,7 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) * update ready variable, we check READY_N and update * READY here */ - __set_agg_ports_ready(port->aggregator, __agg_ports_are_ready(port->aggregator)); + __set_agg_ports_ready(aggregator, __agg_ports_are_ready(aggregator)); /* if the wait_while_timer expired, and the port is * in READY state, move to ATTACHED state @@ -1086,7 +1088,7 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) if ((port->sm_vars & AD_PORT_SELECTED) && (port->partner_oper.port_state & LACP_STATE_SYNCHRONIZATION) && !__check_agg_selection_timer(port)) { - if (port->aggregator->is_active) { + if (aggregator->is_active) { int state = AD_MUX_COLLECTING_DISTRIBUTING; if (!bond->params.coupled_control) @@ -1102,9 +1104,9 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) * cycle to update ready variable, we check * READY_N and update READY here */ - __set_agg_ports_ready(port->aggregator, __agg_ports_are_ready(port->aggregator)); + __set_agg_ports_ready(aggregator, __agg_ports_are_ready(aggregator)); port->sm_mux_state = AD_MUX_DETACHED; - } else if (port->aggregator->is_active) { + } else if (aggregator->is_active) { port->actor_oper_port_state |= LACP_STATE_SYNCHRONIZATION; } @@ -1115,7 +1117,7 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) * sure that a collecting distributing * port in an active aggregator is enabled */ - if (port->aggregator->is_active && + if (aggregator->is_active && !__port_is_collecting_distributing(port)) { __enable_port(port); *update_slave_arr = true; @@ -1134,7 +1136,7 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) */ struct slave *slave = port->slave; - if (port->aggregator->is_active && + if (aggregator->is_active && bond_is_slave_rx_disabled(slave)) { ad_enable_collecting(port); *update_slave_arr = true; @@ -1154,8 +1156,8 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) * sure that a collecting distributing * port in an active aggregator is enabled */ - if (port->aggregator && - port->aggregator->is_active && + if (aggregator && + aggregator->is_active && !__port_is_collecting_distributing(port)) { __enable_port(port); *update_slave_arr = true; @@ -1187,7 +1189,7 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) port->sm_mux_timer_counter = __ad_timer_to_ticks(AD_WAIT_WHILE_TIMER, 0); break; case AD_MUX_ATTACHED: - if (port->aggregator->is_active) + if (aggregator->is_active) port->actor_oper_port_state |= LACP_STATE_SYNCHRONIZATION; else @@ -1561,9 +1563,9 @@ static void ad_port_selection_logic(struct port *port, bool *update_slave_arr) bond = __get_bond_by_port(port); /* if the port is connected to other aggregator, detach it */ - if (port->aggregator) { + temp_aggregator = rcu_dereference(port->aggregator); + if (temp_aggregator) { /* detach the port from its former aggregator */ - temp_aggregator = port->aggregator; for (curr_port = temp_aggregator->lag_ports; curr_port; last_port = curr_port, curr_port = curr_port->next_port_in_aggregator) { @@ -1586,7 +1588,7 @@ static void ad_port_selection_logic(struct port *port, bool *update_slave_arr) /* clear the port's relations to this * aggregator */ - port->aggregator = NULL; + RCU_INIT_POINTER(port->aggregator, NULL); port->next_port_in_aggregator = NULL; port->actor_port_aggregator_identifier = 0; @@ -1609,7 +1611,7 @@ static void ad_port_selection_logic(struct port *port, bool *update_slave_arr) port->slave->bond->dev->name, port->slave->dev->name, port->actor_port_number, - port->aggregator->aggregator_identifier); + temp_aggregator->aggregator_identifier); } } /* search on all aggregators for a suitable aggregator for this port */ @@ -1633,15 +1635,15 @@ static void ad_port_selection_logic(struct port *port, bool *update_slave_arr) ) ) { /* attach to the founded aggregator */ - port->aggregator = aggregator; + rcu_assign_pointer(port->aggregator, aggregator); port->actor_port_aggregator_identifier = - port->aggregator->aggregator_identifier; + aggregator->aggregator_identifier; port->next_port_in_aggregator = aggregator->lag_ports; - port->aggregator->num_of_ports++; + aggregator->num_of_ports++; aggregator->lag_ports = port; slave_dbg(bond->dev, slave->dev, "Port %d joined LAG %d (existing LAG)\n", port->actor_port_number, - port->aggregator->aggregator_identifier); + aggregator->aggregator_identifier); /* mark this port as selected */ port->sm_vars |= AD_PORT_SELECTED; @@ -1656,39 +1658,40 @@ static void ad_port_selection_logic(struct port *port, bool *update_slave_arr) if (!found) { if (free_aggregator) { /* assign port a new aggregator */ - port->aggregator = free_aggregator; port->actor_port_aggregator_identifier = - port->aggregator->aggregator_identifier; + free_aggregator->aggregator_identifier; /* update the new aggregator's parameters * if port was responsed from the end-user */ if (port->actor_oper_port_key & AD_DUPLEX_KEY_MASKS) /* if port is full duplex */ - port->aggregator->is_individual = false; + free_aggregator->is_individual = false; else - port->aggregator->is_individual = true; + free_aggregator->is_individual = true; - port->aggregator->actor_admin_aggregator_key = + free_aggregator->actor_admin_aggregator_key = port->actor_admin_port_key; - port->aggregator->actor_oper_aggregator_key = + free_aggregator->actor_oper_aggregator_key = port->actor_oper_port_key; - port->aggregator->partner_system = + free_aggregator->partner_system = port->partner_oper.system; - port->aggregator->partner_system_priority = + free_aggregator->partner_system_priority = port->partner_oper.system_priority; - port->aggregator->partner_oper_aggregator_key = port->partner_oper.key; - port->aggregator->receive_state = 1; - port->aggregator->transmit_state = 1; - port->aggregator->lag_ports = port; - port->aggregator->num_of_ports++; + free_aggregator->partner_oper_aggregator_key = port->partner_oper.key; + free_aggregator->receive_state = 1; + free_aggregator->transmit_state = 1; + free_aggregator->lag_ports = port; + free_aggregator->num_of_ports++; + + rcu_assign_pointer(port->aggregator, free_aggregator); /* mark this port as selected */ port->sm_vars |= AD_PORT_SELECTED; slave_dbg(bond->dev, port->slave->dev, "Port %d joined LAG %d (new LAG)\n", port->actor_port_number, - port->aggregator->aggregator_identifier); + free_aggregator->aggregator_identifier); } else { slave_err(bond->dev, port->slave->dev, "Port %d did not find a suitable aggregator\n", @@ -1700,13 +1703,12 @@ static void ad_port_selection_logic(struct port *port, bool *update_slave_arr) * in all aggregator's ports, else set ready=FALSE in all * aggregator's ports */ - __set_agg_ports_ready(port->aggregator, - __agg_ports_are_ready(port->aggregator)); + aggregator = rcu_dereference(port->aggregator); + __set_agg_ports_ready(aggregator, __agg_ports_are_ready(aggregator)); - aggregator = __get_first_agg(port); - ad_agg_selection_logic(aggregator, update_slave_arr); + ad_agg_selection_logic(__get_first_agg(port), update_slave_arr); - if (!port->aggregator->is_active) + if (!aggregator->is_active) port->actor_oper_port_state &= ~LACP_STATE_SYNCHRONIZATION; } @@ -2075,13 +2077,15 @@ static void ad_initialize_port(struct port *port, const struct bond_params *bond */ static void ad_enable_collecting(struct port *port) { - if (port->aggregator->is_active) { + struct aggregator *aggregator = rcu_dereference(port->aggregator); + + if (aggregator->is_active) { struct slave *slave = port->slave; slave_dbg(slave->bond->dev, slave->dev, "Enabling collecting on port %d (LAG %d)\n", port->actor_port_number, - port->aggregator->aggregator_identifier); + aggregator->aggregator_identifier); __enable_collecting_port(port); } } @@ -2093,11 +2097,13 @@ static void ad_enable_collecting(struct port *port) */ static void ad_disable_distributing(struct port *port, bool *update_slave_arr) { - if (port->aggregator && __agg_has_partner(port->aggregator)) { + struct aggregator *aggregator = rcu_dereference(port->aggregator); + + if (aggregator && __agg_has_partner(aggregator)) { slave_dbg(port->slave->bond->dev, port->slave->dev, "Disabling distributing on port %d (LAG %d)\n", port->actor_port_number, - port->aggregator->aggregator_identifier); + aggregator->aggregator_identifier); __disable_distributing_port(port); /* Slave array needs an update */ *update_slave_arr = true; @@ -2114,11 +2120,13 @@ static void ad_disable_distributing(struct port *port, bool *update_slave_arr) static void ad_enable_collecting_distributing(struct port *port, bool *update_slave_arr) { - if (port->aggregator->is_active) { + struct aggregator *aggregator = rcu_dereference(port->aggregator); + + if (aggregator->is_active) { slave_dbg(port->slave->bond->dev, port->slave->dev, "Enabling port %d (LAG %d)\n", port->actor_port_number, - port->aggregator->aggregator_identifier); + aggregator->aggregator_identifier); __enable_port(port); /* Slave array needs update */ *update_slave_arr = true; @@ -2135,11 +2143,13 @@ static void ad_enable_collecting_distributing(struct port *port, static void ad_disable_collecting_distributing(struct port *port, bool *update_slave_arr) { - if (port->aggregator && __agg_has_partner(port->aggregator)) { + struct aggregator *aggregator = rcu_dereference(port->aggregator); + + if (aggregator && __agg_has_partner(aggregator)) { slave_dbg(port->slave->bond->dev, port->slave->dev, "Disabling port %d (LAG %d)\n", port->actor_port_number, - port->aggregator->aggregator_identifier); + aggregator->aggregator_identifier); __disable_port(port); /* Slave array needs an update */ *update_slave_arr = true; @@ -2379,7 +2389,7 @@ void bond_3ad_unbind_slave(struct slave *slave) */ for (temp_port = aggregator->lag_ports; temp_port; temp_port = temp_port->next_port_in_aggregator) { - temp_port->aggregator = new_aggregator; + rcu_assign_pointer(temp_port->aggregator, new_aggregator); temp_port->actor_port_aggregator_identifier = new_aggregator->aggregator_identifier; } @@ -2848,15 +2858,16 @@ out: int __bond_3ad_get_active_agg_info(struct bonding *bond, struct ad_info *ad_info) { - struct aggregator *aggregator = NULL; + struct aggregator *aggregator = NULL, *tmp; struct list_head *iter; struct slave *slave; struct port *port; bond_for_each_slave_rcu(bond, slave, iter) { port = &(SLAVE_AD_INFO(slave)->port); - if (port->aggregator && port->aggregator->is_active) { - aggregator = port->aggregator; + tmp = rcu_dereference(port->aggregator); + if (tmp && tmp->is_active) { + aggregator = tmp; break; } } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index c7baa5c4bf40..af82a3df2c5d 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1433,7 +1433,7 @@ static void bond_poll_controller(struct net_device *bond_dev) if (BOND_MODE(bond) == BOND_MODE_8023AD) { struct aggregator *agg = - SLAVE_AD_INFO(slave)->port.aggregator; + rcu_dereference(SLAVE_AD_INFO(slave)->port.aggregator); if (agg && agg->aggregator_identifier != ad_info.aggregator_id) @@ -5179,15 +5179,16 @@ int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave) spin_unlock_bh(&bond->mode_lock); agg_id = ad_info.aggregator_id; } + rcu_read_lock(); bond_for_each_slave(bond, slave, iter) { if (skipslave == slave) continue; all_slaves->arr[all_slaves->count++] = slave; if (BOND_MODE(bond) == BOND_MODE_8023AD) { - struct aggregator *agg; + const struct aggregator *agg; - agg = SLAVE_AD_INFO(slave)->port.aggregator; + agg = rcu_dereference(SLAVE_AD_INFO(slave)->port.aggregator); if (!agg || agg->aggregator_identifier != agg_id) continue; } @@ -5199,6 +5200,7 @@ int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave) usable_slaves->arr[usable_slaves->count++] = slave; } + rcu_read_unlock(); bond_set_slave_arr(bond, usable_slaves, all_slaves); return ret; diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index ea1a80e658ae..c7d3e0602c83 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -66,27 +66,29 @@ static int bond_fill_slave_info(struct sk_buff *skb, const struct port *ad_port; ad_port = &SLAVE_AD_INFO(slave)->port; - agg = SLAVE_AD_INFO(slave)->port.aggregator; + rcu_read_lock(); + agg = rcu_dereference(SLAVE_AD_INFO(slave)->port.aggregator); if (agg) { if (nla_put_u16(skb, IFLA_BOND_SLAVE_AD_AGGREGATOR_ID, agg->aggregator_identifier)) - goto nla_put_failure; + goto nla_put_failure_rcu; if (nla_put_u8(skb, IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE, ad_port->actor_oper_port_state)) - goto nla_put_failure; + goto nla_put_failure_rcu; if (nla_put_u16(skb, IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE, ad_port->partner_oper.port_state)) - goto nla_put_failure; + goto nla_put_failure_rcu; if (nla_put_u8(skb, IFLA_BOND_SLAVE_AD_CHURN_ACTOR_STATE, ad_port->sm_churn_actor_state)) - goto nla_put_failure; + goto nla_put_failure_rcu; if (nla_put_u8(skb, IFLA_BOND_SLAVE_AD_CHURN_PARTNER_STATE, ad_port->sm_churn_partner_state)) - goto nla_put_failure; + goto nla_put_failure_rcu; } + rcu_read_unlock(); if (nla_put_u16(skb, IFLA_BOND_SLAVE_ACTOR_PORT_PRIO, SLAVE_AD_INFO(slave)->port_priority)) @@ -95,6 +97,8 @@ static int bond_fill_slave_info(struct sk_buff *skb, return 0; +nla_put_failure_rcu: + rcu_read_unlock(); nla_put_failure: return -EMSGSIZE; } diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c index e34f80305191..3714aab1a3d9 100644 --- a/drivers/net/bonding/bond_procfs.c +++ b/drivers/net/bonding/bond_procfs.c @@ -188,6 +188,7 @@ static void bond_info_show_master(struct seq_file *seq) } } +/* Note: runs under rcu_read_lock() */ static void bond_info_show_slave(struct seq_file *seq, const struct slave *slave) { @@ -214,7 +215,7 @@ static void bond_info_show_slave(struct seq_file *seq, if (BOND_MODE(bond) == BOND_MODE_8023AD) { const struct port *port = &SLAVE_AD_INFO(slave)->port; - const struct aggregator *agg = port->aggregator; + const struct aggregator *agg = rcu_dereference(port->aggregator); if (agg) { seq_printf(seq, "Aggregator ID: %d\n", diff --git a/drivers/net/bonding/bond_sysfs_slave.c b/drivers/net/bonding/bond_sysfs_slave.c index 36d0e8440b5b..fc6fe7181789 100644 --- a/drivers/net/bonding/bond_sysfs_slave.c +++ b/drivers/net/bonding/bond_sysfs_slave.c @@ -62,10 +62,15 @@ static ssize_t ad_aggregator_id_show(struct slave *slave, char *buf) const struct aggregator *agg; if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) { - agg = SLAVE_AD_INFO(slave)->port.aggregator; - if (agg) - return sysfs_emit(buf, "%d\n", - agg->aggregator_identifier); + rcu_read_lock(); + agg = rcu_dereference(SLAVE_AD_INFO(slave)->port.aggregator); + if (agg) { + ssize_t res = sysfs_emit(buf, "%d\n", + agg->aggregator_identifier); + rcu_read_unlock(); + return res; + } + rcu_read_unlock(); } return sysfs_emit(buf, "N/A\n"); @@ -78,7 +83,7 @@ static ssize_t ad_actor_oper_port_state_show(struct slave *slave, char *buf) if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) { ad_port = &SLAVE_AD_INFO(slave)->port; - if (ad_port->aggregator) + if (rcu_access_pointer(ad_port->aggregator)) return sysfs_emit(buf, "%u\n", ad_port->actor_oper_port_state); } @@ -93,7 +98,7 @@ static ssize_t ad_partner_oper_port_state_show(struct slave *slave, char *buf) if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) { ad_port = &SLAVE_AD_INFO(slave)->port; - if (ad_port->aggregator) + if (rcu_access_pointer(ad_port->aggregator)) return sysfs_emit(buf, "%u\n", ad_port->partner_oper.port_state); } diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index b9423389c2ef..44d670904ad8 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -25,6 +25,9 @@ #include "mt7530.h" +#define MT7530_STATS_POLL_INTERVAL (1 * HZ) +#define MT7530_STATS_RATE_LIMIT (HZ / 10) + static struct mt753x_pcs *pcs_to_mt753x_pcs(struct phylink_pcs *pcs) { return container_of(pcs, struct mt753x_pcs, pcs); @@ -906,10 +909,9 @@ static void mt7530_get_rmon_stats(struct dsa_switch *ds, int port, *ranges = mt7530_rmon_ranges; } -static void mt7530_get_stats64(struct dsa_switch *ds, int port, - struct rtnl_link_stats64 *storage) +static void mt7530_read_port_stats64(struct mt7530_priv *priv, int port, + struct rtnl_link_stats64 *storage) { - struct mt7530_priv *priv = ds->priv; uint64_t data; /* MIB counter doesn't provide a FramesTransmittedOK but instead @@ -951,6 +953,54 @@ static void mt7530_get_stats64(struct dsa_switch *ds, int port, &storage->rx_crc_errors); } +static void mt7530_stats_refresh(struct mt7530_priv *priv) +{ + struct rtnl_link_stats64 stats = {}; + struct dsa_port *dp; + int port; + + dsa_switch_for_each_user_port(dp, priv->ds) { + port = dp->index; + + mt7530_read_port_stats64(priv, port, &stats); + + spin_lock_bh(&priv->stats_lock); + priv->ports[port].stats = stats; + priv->stats_last = jiffies; + spin_unlock_bh(&priv->stats_lock); + } +} + +static void mt7530_stats_poll(struct work_struct *work) +{ + struct mt7530_priv *priv = container_of(work, struct mt7530_priv, + stats_work.work); + + mt7530_stats_refresh(priv); + schedule_delayed_work(&priv->stats_work, + MT7530_STATS_POLL_INTERVAL); +} + +static void mt7530_get_stats64(struct dsa_switch *ds, int port, + struct rtnl_link_stats64 *storage) +{ + struct mt7530_priv *priv = ds->priv; + bool refresh; + + if (priv->bus) { + spin_lock_bh(&priv->stats_lock); + *storage = priv->ports[port].stats; + refresh = time_after(jiffies, priv->stats_last + + MT7530_STATS_RATE_LIMIT); + spin_unlock_bh(&priv->stats_lock); + if (refresh) + mod_delayed_work(system_percpu_wq, + &priv->stats_work, 0); + } else { + mt7530_read_port_stats64(priv, port, storage); + } +} + static void mt7530_get_eth_ctrl_stats(struct dsa_switch *ds, int port, struct ethtool_eth_ctrl_stats *ctrl_stats) { @@ -3137,9 +3187,24 @@ mt753x_setup(struct dsa_switch *ds) if (ret && priv->irq_domain) mt7530_free_mdio_irq(priv); + if (!ret && priv->bus) { + mt7530_stats_refresh(priv); + schedule_delayed_work(&priv->stats_work, + MT7530_STATS_POLL_INTERVAL); + } + return ret; } +static void +mt753x_teardown(struct dsa_switch *ds) +{ + struct mt7530_priv *priv = ds->priv; + + if (priv->bus) + cancel_delayed_work_sync(&priv->stats_work); +} + static int mt753x_set_mac_eee(struct dsa_switch *ds, int port, struct ethtool_keee *e) { @@ -3257,6 +3322,7 @@ static int mt7988_setup(struct dsa_switch *ds) static const struct dsa_switch_ops mt7530_switch_ops = { .get_tag_protocol = mtk_get_tag_protocol, .setup = mt753x_setup, + .teardown = mt753x_teardown, .preferred_default_local_cpu_port = mt753x_preferred_default_local_cpu_port, .get_strings = mt7530_get_strings, .get_ethtool_stats = mt7530_get_ethtool_stats, @@ -3395,6 +3461,9 @@ mt7530_probe_common(struct mt7530_priv *priv) priv->ds->ops = &mt7530_switch_ops; priv->ds->phylink_mac_ops = &mt753x_phylink_mac_ops; mutex_init(&priv->reg_mutex); + spin_lock_init(&priv->stats_lock); + INIT_DELAYED_WORK(&priv->stats_work, mt7530_stats_poll); + dev_set_drvdata(dev, priv); return 0; diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h index 3e0090bed298..dd33b0df3419 100644 --- a/drivers/net/dsa/mt7530.h +++ b/drivers/net/dsa/mt7530.h @@ -796,6 +796,7 @@ struct mt7530_fdb { * @pvid: The VLAN specified is to be considered a PVID at ingress. Any * untagged frames will be assigned to the related VLAN. * @sgmii_pcs: Pointer to PCS instance for SerDes ports + * @stats: Cached port statistics for MDIO-connected switches */ struct mt7530_port { bool enable; @@ -803,6 +804,7 @@ struct mt7530_port { u32 pm; u16 pvid; struct phylink_pcs *sgmii_pcs; + struct rtnl_link_stats64 stats; }; /* Port 5 mode definitions of the MT7530 switch */ @@ -875,6 +877,9 @@ struct mt753x_info { * @create_sgmii: Pointer to function creating SGMII PCS instance(s) * @active_cpu_ports: Holding the active CPU ports * @mdiodev: The pointer to the MDIO device structure + * @stats_lock: Protects cached per-port stats from concurrent access + * @stats_work: Delayed work for polling MIB counters on MDIO switches + * @stats_last: Jiffies timestamp of last MIB counter poll */ struct mt7530_priv { struct device *dev; @@ -900,6 +905,9 @@ struct mt7530_priv { int (*create_sgmii)(struct mt7530_priv *priv); u8 active_cpu_ports; struct mdio_device *mdiodev; + spinlock_t stats_lock; /* protects cached stats counters */ + struct delayed_work stats_work; + unsigned long stats_last; }; struct mt7530_hw_vlan_entry { diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index 2bb0a3ff9810..d0c0c0ec8a80 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -847,13 +847,24 @@ static void airoha_qdma_wake_netdev_txqs(struct airoha_queue *q) { struct airoha_qdma *qdma = q->qdma; struct airoha_eth *eth = qdma->eth; - int i; + int i, qid = q - &qdma->q_tx[0]; for (i = 0; i < ARRAY_SIZE(eth->ports); i++) { struct airoha_gdm_port *port = eth->ports[i]; + int j; + + if (!port) + continue; + + if (port->qdma != qdma) + continue; - if (port && port->qdma == qdma) - netif_tx_wake_all_queues(port->dev); + for (j = 0; j < port->dev->num_tx_queues; j++) { + if (airoha_qdma_get_txq(qdma, j) != qid) + continue; + + netif_wake_subqueue(port->dev, j); + } } q->txq_stopped = false; } @@ -929,10 +940,9 @@ static int airoha_qdma_tx_napi_poll(struct napi_struct *napi, int budget) q->queued--; if (skb) { - u16 queue = skb_get_queue_mapping(skb); struct netdev_queue *txq; - txq = netdev_get_tx_queue(skb->dev, queue); + txq = skb_get_tx_queue(skb->dev, skb); netdev_tx_completed_queue(txq, 1, skb->len); dev_kfree_skb_any(skb); } @@ -1737,14 +1747,11 @@ static int airoha_dev_stop(struct net_device *dev) { struct airoha_gdm_port *port = netdev_priv(dev); struct airoha_qdma *qdma = port->qdma; - int i, err; + int i; netif_tx_disable(dev); - err = airoha_set_vip_for_gdm_port(port, false); - if (err) - return err; - - for (i = 0; i < ARRAY_SIZE(qdma->q_tx); i++) + airoha_set_vip_for_gdm_port(port, false); + for (i = 0; i < dev->num_tx_queues; i++) netdev_tx_reset_subqueue(dev, i); airoha_set_gdm_port_fwd_cfg(qdma->eth, REG_GDM_FWD_CFG(port->id), @@ -1997,12 +2004,12 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, struct netdev_queue *txq; struct airoha_queue *q; LIST_HEAD(tx_list); + int i = 0, qid; void *data; - int i, qid; u16 index; u8 fport; - qid = skb_get_queue_mapping(skb) % ARRAY_SIZE(qdma->q_tx); + qid = airoha_qdma_get_txq(qdma, skb_get_queue_mapping(skb)); tag = airoha_get_dsa_tag(skb, dev); msg0 = FIELD_PREP(QDMA_ETH_TXMSG_CHAN_MASK, @@ -2039,7 +2046,7 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, spin_lock_bh(&q->lock); - txq = netdev_get_tx_queue(dev, qid); + txq = skb_get_tx_queue(dev, skb); nr_frags = 1 + skb_shinfo(skb)->nr_frags; if (q->queued + nr_frags >= q->ndesc) { @@ -2057,7 +2064,7 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, list); index = e - q->entry; - for (i = 0; i < nr_frags; i++) { + while (true) { struct airoha_qdma_desc *desc = &q->desc[index]; skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; dma_addr_t addr; @@ -2069,7 +2076,7 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, goto error_unmap; list_move_tail(&e->list, &tx_list); - e->skb = i ? NULL : skb; + e->skb = i == nr_frags - 1 ? skb : NULL; e->dma_addr = addr; e->dma_len = len; @@ -2088,6 +2095,9 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, WRITE_ONCE(desc->msg1, cpu_to_le32(msg1)); WRITE_ONCE(desc->msg2, cpu_to_le32(0xffff)); + if (++i == nr_frags) + break; + data = skb_frag_address(frag); len = skb_frag_size(frag); } @@ -2095,30 +2105,27 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, skb_tx_timestamp(skb); netdev_tx_sent_queue(txq, skb->len); + if (q->ndesc - q->queued < q->free_thr) { + netif_tx_stop_queue(txq); + q->txq_stopped = true; + } if (netif_xmit_stopped(txq) || !netdev_xmit_more()) airoha_qdma_rmw(qdma, REG_TX_CPU_IDX(qid), TX_RING_CPU_IDX_MASK, FIELD_PREP(TX_RING_CPU_IDX_MASK, index)); - if (q->ndesc - q->queued < q->free_thr) { - netif_tx_stop_queue(txq); - q->txq_stopped = true; - } - spin_unlock_bh(&q->lock); return NETDEV_TX_OK; error_unmap: - while (!list_empty(&tx_list)) { - e = list_first_entry(&tx_list, struct airoha_queue_entry, - list); + list_for_each_entry(e, &tx_list, list) { dma_unmap_single(dev->dev.parent, e->dma_addr, e->dma_len, DMA_TO_DEVICE); e->dma_addr = 0; - list_move_tail(&e->list, &q->tx_list); } + list_splice(&tx_list, &q->tx_list); spin_unlock_bh(&q->lock); error: diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h index e389d2fe3b86..4fad3acc3ccf 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.h +++ b/drivers/net/ethernet/airoha/airoha_eth.h @@ -631,6 +631,11 @@ u32 airoha_rmw(void __iomem *base, u32 offset, u32 mask, u32 val); #define airoha_qdma_clear(qdma, offset, val) \ airoha_rmw((qdma)->regs, (offset), (val), 0) +static inline u16 airoha_qdma_get_txq(struct airoha_qdma *qdma, u16 qid) +{ + return qid % ARRAY_SIZE(qdma->q_tx); +} + static inline bool airoha_is_lan_gdm_port(struct airoha_gdm_port *port) { /* GDM1 port on EN7581 SoC is connected to the lan dsa switch. diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h index 60b7e53206d1..3d3b09010d48 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe.h @@ -135,11 +135,11 @@ */ #define XGBE_TSTAMP_SSINC 20 #define XGBE_TSTAMP_SNSINC 0 -#define XGBE_PTP_ACT_CLK_FREQ 500000000 +#define XGBE_PTP_ACT_CLK_FREQ (NSEC_PER_SEC / XGBE_TSTAMP_SSINC) #define XGBE_V2_TSTAMP_SSINC 0xA #define XGBE_V2_TSTAMP_SNSINC 0 -#define XGBE_V2_PTP_ACT_CLK_FREQ 1000000000 +#define XGBE_V2_PTP_ACT_CLK_FREQ (NSEC_PER_SEC / XGBE_V2_TSTAMP_SSINC) /* Define maximum supported values */ #define XGBE_MAX_PPS_OUT 4 diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 8c55874f44ca..008c34cff7b4 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -3825,7 +3825,10 @@ static int bnxt_alloc_tpa_info(struct bnxt *bp) if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) { if (!bp->max_tpa_v2) return 0; - bp->max_tpa = max_t(u16, bp->max_tpa_v2, MAX_TPA_P5); + bp->max_tpa = min_t(u16, bp->max_tpa_v2, MAX_TPA_P5); + /* Older P5 FW sets max_tpa_v2 low by mistake except NPAR */ + if (bp->max_tpa <= 32 && BNXT_CHIP_P5(bp) && !BNXT_NPAR(bp)) + bp->max_tpa = MAX_TPA_P5; } for (i = 0; i < bp->rx_nr_rings; i++) { @@ -17360,9 +17363,14 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev) netdev_info(bp->dev, "PCI Slot Reset\n"); - if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS) && - test_bit(BNXT_STATE_PCI_CHANNEL_IO_FROZEN, &bp->state)) - msleep(900); + if (test_bit(BNXT_STATE_PCI_CHANNEL_IO_FROZEN, &bp->state)) { + /* After DPC, the chip should return CRS when the vendor ID + * config register is read until it is ready. On all chips, + * this is not happening reliably so add a 5-second delay as a + * workaround. + */ + msleep(5000); + } netdev_lock(netdev); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c index 53f336db4fcc..5d41dc1bc782 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c @@ -419,31 +419,13 @@ void bnxt_ptp_reapply_pps(struct bnxt *bp) } } -static int bnxt_get_target_cycles(struct bnxt_ptp_cfg *ptp, u64 target_ns, - u64 *cycles_delta) -{ - u64 cycles_now; - u64 nsec_now, nsec_delta; - int rc; - - rc = bnxt_refclk_read(ptp->bp, NULL, &cycles_now); - if (rc) - return rc; - - nsec_now = bnxt_timecounter_cyc2time(ptp, cycles_now); - - nsec_delta = target_ns - nsec_now; - *cycles_delta = div64_u64(nsec_delta << ptp->cc.shift, ptp->cc.mult); - return 0; -} - static int bnxt_ptp_perout_cfg(struct bnxt_ptp_cfg *ptp, struct ptp_clock_request *rq) { struct hwrm_func_ptp_cfg_input *req; struct bnxt *bp = ptp->bp; struct timespec64 ts; - u64 target_ns, delta; + u64 target_ns; u16 enables; int rc; @@ -451,10 +433,6 @@ static int bnxt_ptp_perout_cfg(struct bnxt_ptp_cfg *ptp, ts.tv_nsec = rq->perout.start.nsec; target_ns = timespec64_to_ns(&ts); - rc = bnxt_get_target_cycles(ptp, target_ns, &delta); - if (rc) - return rc; - rc = hwrm_req_init(bp, req, HWRM_FUNC_PTP_CFG); if (rc) return rc; @@ -468,7 +446,10 @@ static int bnxt_ptp_perout_cfg(struct bnxt_ptp_cfg *ptp, req->ptp_freq_adj_dll_phase = 0; req->ptp_freq_adj_ext_period = cpu_to_le32(NSEC_PER_SEC); req->ptp_freq_adj_ext_up = 0; - req->ptp_freq_adj_ext_phase_lower = cpu_to_le32(delta); + req->ptp_freq_adj_ext_phase_lower = + cpu_to_le32(lower_32_bits(target_ns)); + req->ptp_freq_adj_ext_phase_upper = + cpu_to_le32(upper_32_bits(target_ns)); return hwrm_req_send(bp, req); } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c index 052bf69cfa4c..5c751933da6a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c @@ -175,8 +175,14 @@ int bnxt_register_dev(struct bnxt_en_dev *edev, ulp->handle = handle; rcu_assign_pointer(ulp->ulp_ops, ulp_ops); - if (test_bit(BNXT_STATE_OPEN, &bp->state)) - bnxt_hwrm_vnic_cfg(bp, &bp->vnic_info[BNXT_VNIC_DEFAULT]); + if (test_bit(BNXT_STATE_OPEN, &bp->state)) { + rc = bnxt_hwrm_vnic_cfg(bp, &bp->vnic_info[BNXT_VNIC_DEFAULT]); + if (rc) { + netdev_err(dev, "Failed to configure dual VNIC mode\n"); + RCU_INIT_POINTER(ulp->ulp_ops, NULL); + goto exit; + } + } edev->ulp_tbl->msix_requested = bnxt_get_ulp_msix_num(bp); diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 4824232f4890..065cbbf52686 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -1491,6 +1491,11 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) gpage = gmac_get_queue_page(geth, port, mapping + PAGE_SIZE); if (!gpage) { dev_err(geth->dev, "could not find mapping\n"); + if (skb) { + napi_free_frags(&port->napi); + port->stats.rx_dropped++; + skb = NULL; + } continue; } page = gpage->page; diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h index e663bb5e614e..e691144e8756 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.h +++ b/drivers/net/ethernet/freescale/enetc/enetc.h @@ -330,6 +330,7 @@ struct enetc_si { struct workqueue_struct *workqueue; struct work_struct rx_mode_task; struct dentry *debugfs_root; + struct enetc_msg_swbd msg; /* Only valid for VSI */ }; #define ENETC_SI_ALIGN 32 diff --git a/drivers/net/ethernet/freescale/enetc/enetc_vf.c b/drivers/net/ethernet/freescale/enetc/enetc_vf.c index 6c4b374bcb0e..df8e95cc47d0 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_vf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_vf.c @@ -17,11 +17,36 @@ static void enetc_msg_vsi_write_msg(struct enetc_hw *hw, enetc_wr(hw, ENETC_VSIMSGSNDAR0, val); } +static void enetc_msg_dma_free(struct device *dev, struct enetc_msg_swbd *msg) +{ + if (msg->vaddr) { + dma_free_coherent(dev, msg->size, msg->vaddr, msg->dma); + msg->vaddr = NULL; + } +} + static int enetc_msg_vsi_send(struct enetc_si *si, struct enetc_msg_swbd *msg) { + struct device *dev = &si->pdev->dev; int timeout = 100; u32 vsimsgsr; + /* The VSI mailbox may be busy if last message was not yet processed + * by PSI. So need to check the mailbox status before sending. + */ + vsimsgsr = enetc_rd(&si->hw, ENETC_VSIMSGSR); + if (vsimsgsr & ENETC_VSIMSGSR_MB) { + /* It is safe to free the DMA buffer here, the caller does + * not access the DMA buffer if enetc_msg_vsi_send() fails. + */ + enetc_msg_dma_free(dev, msg); + dev_err(dev, "VSI mailbox is busy\n"); + return -EIO; + } + + /* Free the DMA buffer of the last message */ + enetc_msg_dma_free(dev, &si->msg); + si->msg = *msg; enetc_msg_vsi_write_msg(&si->hw, msg); do { @@ -32,12 +57,15 @@ static int enetc_msg_vsi_send(struct enetc_si *si, struct enetc_msg_swbd *msg) usleep_range(1000, 2000); } while (--timeout); - if (!timeout) + if (!timeout) { + dev_err(dev, "VSI mailbox timeout\n"); + return -ETIMEDOUT; + } /* check for message delivery error */ if (vsimsgsr & ENETC_VSIMSGSR_MS) { - dev_err(&si->pdev->dev, "VSI command execute error: %d\n", + dev_err(dev, "VSI command execute error: %d\n", ENETC_SIMSGSR_GET_MC(vsimsgsr)); return -EIO; } @@ -50,7 +78,6 @@ static int enetc_msg_vsi_set_primary_mac_addr(struct enetc_ndev_priv *priv, { struct enetc_msg_cmd_set_primary_mac *cmd; struct enetc_msg_swbd msg; - int err; msg.size = ALIGN(sizeof(struct enetc_msg_cmd_set_primary_mac), 64); msg.vaddr = dma_alloc_coherent(priv->dev, msg.size, &msg.dma, @@ -67,11 +94,7 @@ static int enetc_msg_vsi_set_primary_mac_addr(struct enetc_ndev_priv *priv, memcpy(&cmd->mac, saddr, sizeof(struct sockaddr)); /* send the command and wait */ - err = enetc_msg_vsi_send(priv->si, &msg); - - dma_free_coherent(priv->dev, msg.size, msg.vaddr, msg.dma); - - return err; + return enetc_msg_vsi_send(priv->si, &msg); } static int enetc_vf_set_mac_addr(struct net_device *ndev, void *addr) @@ -259,6 +282,7 @@ static void enetc_vf_remove(struct pci_dev *pdev) { struct enetc_si *si = pci_get_drvdata(pdev); struct enetc_ndev_priv *priv; + struct enetc_msg_swbd msg; priv = netdev_priv(si->ndev); unregister_netdev(si->ndev); @@ -270,7 +294,9 @@ static void enetc_vf_remove(struct pci_dev *pdev) free_netdev(si->ndev); + msg = si->msg; enetc_pci_remove(pdev); + enetc_msg_dma_free(&pdev->dev, &msg); } static const struct pci_device_id enetc_vf_id_table[] = { diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 58cc3147afe2..73e051d26b9d 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -1756,6 +1756,27 @@ static int ibmveth_set_mac_addr(struct net_device *dev, void *p) return 0; } +static netdev_features_t ibmveth_features_check(struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features) +{ + /* Some physical adapters do not support segmentation offload with + * MSS < 224. Disable GSO for such packets to avoid adapter freeze. + * Note: Single-segment packets (gso_segs == 1) don't need this check + * as they bypass the LSO path and are transmitted without segmentation. + */ + if (skb_is_gso(skb)) { + if (skb_shinfo(skb)->gso_size < IBMVETH_MIN_LSO_MSS) { + netdev_warn_once(dev, + "MSS %u too small for LSO, disabling GSO\n", + skb_shinfo(skb)->gso_size); + features &= ~NETIF_F_GSO_MASK; + } + } + + return vlan_features_check(skb, features); +} + static const struct net_device_ops ibmveth_netdev_ops = { .ndo_open = ibmveth_open, .ndo_stop = ibmveth_close, @@ -1767,6 +1788,7 @@ static const struct net_device_ops ibmveth_netdev_ops = { .ndo_set_features = ibmveth_set_features, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = ibmveth_set_mac_addr, + .ndo_features_check = ibmveth_features_check, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = ibmveth_poll_controller, #endif diff --git a/drivers/net/ethernet/ibm/ibmveth.h b/drivers/net/ethernet/ibm/ibmveth.h index 068f99df133e..d87713668ed3 100644 --- a/drivers/net/ethernet/ibm/ibmveth.h +++ b/drivers/net/ethernet/ibm/ibmveth.h @@ -37,6 +37,7 @@ #define IBMVETH_ILLAN_IPV4_TCP_CSUM 0x0000000000000002UL #define IBMVETH_ILLAN_ACTIVE_TRUNK 0x0000000000000001UL +#define IBMVETH_MIN_LSO_MSS 224 /* Minimum MSS for LSO */ /* hcall macros */ #define h_register_logical_lan(ua, buflst, rxq, fltlst, mac) \ plpar_hcall_norets(H_REGISTER_LOGICAL_LAN, ua, buflst, rxq, fltlst, mac) diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index e9fb0a0919e3..050f8241ef5e 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -158,11 +158,10 @@ struct iavf_vlan { enum iavf_vlan_state_t { IAVF_VLAN_INVALID, IAVF_VLAN_ADD, /* filter needs to be added */ - IAVF_VLAN_IS_NEW, /* filter is new, wait for PF answer */ - IAVF_VLAN_ACTIVE, /* filter is accepted by PF */ - IAVF_VLAN_DISABLE, /* filter needs to be deleted by PF, then marked INACTIVE */ - IAVF_VLAN_INACTIVE, /* filter is inactive, we are in IFF_DOWN */ - IAVF_VLAN_REMOVE, /* filter needs to be removed from list */ + IAVF_VLAN_ADDING, /* ADD sent to PF, waiting for response */ + IAVF_VLAN_ACTIVE, /* PF confirmed, filter is in HW */ + IAVF_VLAN_REMOVE, /* filter queued for DEL from PF */ + IAVF_VLAN_REMOVING, /* DEL sent to PF, waiting for response */ }; struct iavf_vlan_filter { diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 3c1465cf0515..d2914c511e1e 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -757,10 +757,10 @@ iavf_vlan_filter *iavf_add_vlan(struct iavf_adapter *adapter, adapter->num_vlan_filters++; iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_VLAN_FILTER); } else if (f->state == IAVF_VLAN_REMOVE) { - /* Re-add the filter since we cannot tell whether the - * pending delete has already been processed by the PF. - * A duplicate add is harmless. - */ + /* DEL not yet sent to PF, cancel it */ + f->state = IAVF_VLAN_ACTIVE; + } else if (f->state == IAVF_VLAN_REMOVING) { + /* DEL already sent to PF, re-add after completion */ f->state = IAVF_VLAN_ADD; iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_VLAN_FILTER); @@ -791,37 +791,19 @@ static void iavf_del_vlan(struct iavf_adapter *adapter, struct iavf_vlan vlan) list_del(&f->list); kfree(f); adapter->num_vlan_filters--; - } else { + } else if (f->state != IAVF_VLAN_REMOVING) { f->state = IAVF_VLAN_REMOVE; iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_DEL_VLAN_FILTER); } + /* If REMOVING, DEL is already sent to PF; completion + * handler will free the filter when PF confirms. + */ } spin_unlock_bh(&adapter->mac_vlan_list_lock); } -/** - * iavf_restore_filters - * @adapter: board private structure - * - * Restore existing non MAC filters when VF netdev comes back up - **/ -static void iavf_restore_filters(struct iavf_adapter *adapter) -{ - struct iavf_vlan_filter *f; - - /* re-add all VLAN filters */ - spin_lock_bh(&adapter->mac_vlan_list_lock); - - list_for_each_entry(f, &adapter->vlan_filter_list, list) { - if (f->state == IAVF_VLAN_INACTIVE) - f->state = IAVF_VLAN_ADD; - } - - spin_unlock_bh(&adapter->mac_vlan_list_lock); - adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; -} /** * iavf_get_num_vlans_added - get number of VLANs added @@ -1246,13 +1228,12 @@ static void iavf_up_complete(struct iavf_adapter *adapter) } /** - * iavf_clear_mac_vlan_filters - Remove mac and vlan filters not sent to PF - * yet and mark other to be removed. + * iavf_clear_mac_filters - Remove MAC filters not sent to PF yet and mark + * others to be removed. * @adapter: board private structure **/ -static void iavf_clear_mac_vlan_filters(struct iavf_adapter *adapter) +static void iavf_clear_mac_filters(struct iavf_adapter *adapter) { - struct iavf_vlan_filter *vlf, *vlftmp; struct iavf_mac_filter *f, *ftmp; spin_lock_bh(&adapter->mac_vlan_list_lock); @@ -1271,11 +1252,6 @@ static void iavf_clear_mac_vlan_filters(struct iavf_adapter *adapter) } } - /* disable all VLAN filters */ - list_for_each_entry_safe(vlf, vlftmp, &adapter->vlan_filter_list, - list) - vlf->state = IAVF_VLAN_DISABLE; - spin_unlock_bh(&adapter->mac_vlan_list_lock); } @@ -1371,7 +1347,7 @@ void iavf_down(struct iavf_adapter *adapter) iavf_napi_disable_all(adapter); iavf_irq_disable(adapter); - iavf_clear_mac_vlan_filters(adapter); + iavf_clear_mac_filters(adapter); iavf_clear_cloud_filters(adapter); iavf_clear_fdir_filters(adapter); iavf_clear_adv_rss_conf(adapter); @@ -1388,8 +1364,6 @@ void iavf_down(struct iavf_adapter *adapter) */ if (!list_empty(&adapter->mac_filter_list)) adapter->aq_required |= IAVF_FLAG_AQ_DEL_MAC_FILTER; - if (!list_empty(&adapter->vlan_filter_list)) - adapter->aq_required |= IAVF_FLAG_AQ_DEL_VLAN_FILTER; if (!list_empty(&adapter->cloud_filter_list)) adapter->aq_required |= IAVF_FLAG_AQ_DEL_CLOUD_FILTER; if (!list_empty(&adapter->fdir_list_head)) @@ -4494,8 +4468,6 @@ static int iavf_open(struct net_device *netdev) iavf_add_filter(adapter, adapter->hw.mac.addr); spin_unlock_bh(&adapter->mac_vlan_list_lock); - /* Restore filters that were removed with IFF_DOWN */ - iavf_restore_filters(adapter); iavf_restore_fdir_filters(adapter); iavf_configure(adapter); diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index a52c100dcbc5..4f2defd2331b 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -746,7 +746,7 @@ static void iavf_vlan_add_reject(struct iavf_adapter *adapter) spin_lock_bh(&adapter->mac_vlan_list_lock); list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { - if (f->state == IAVF_VLAN_IS_NEW) { + if (f->state == IAVF_VLAN_ADDING) { list_del(&f->list); kfree(f); adapter->num_vlan_filters--; @@ -812,7 +812,7 @@ void iavf_add_vlans(struct iavf_adapter *adapter) if (f->state == IAVF_VLAN_ADD) { vvfl->vlan_id[i] = f->vlan.vid; i++; - f->state = IAVF_VLAN_IS_NEW; + f->state = IAVF_VLAN_ADDING; if (i == count) break; } @@ -874,7 +874,7 @@ void iavf_add_vlans(struct iavf_adapter *adapter) vlan->tpid = f->vlan.tpid; i++; - f->state = IAVF_VLAN_IS_NEW; + f->state = IAVF_VLAN_ADDING; } } @@ -911,22 +911,12 @@ void iavf_del_vlans(struct iavf_adapter *adapter) spin_lock_bh(&adapter->mac_vlan_list_lock); list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { - /* since VLAN capabilities are not allowed, we dont want to send - * a VLAN delete request because it will most likely fail and - * create unnecessary errors/noise, so just free the VLAN - * filters marked for removal to enable bailing out before - * sending a virtchnl message - */ if (f->state == IAVF_VLAN_REMOVE && !VLAN_FILTERING_ALLOWED(adapter)) { list_del(&f->list); kfree(f); adapter->num_vlan_filters--; - } else if (f->state == IAVF_VLAN_DISABLE && - !VLAN_FILTERING_ALLOWED(adapter)) { - f->state = IAVF_VLAN_INACTIVE; - } else if (f->state == IAVF_VLAN_REMOVE || - f->state == IAVF_VLAN_DISABLE) { + } else if (f->state == IAVF_VLAN_REMOVE) { count++; } } @@ -958,18 +948,10 @@ void iavf_del_vlans(struct iavf_adapter *adapter) vvfl->vsi_id = adapter->vsi_res->vsi_id; vvfl->num_elements = count; - list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { - if (f->state == IAVF_VLAN_DISABLE) { - vvfl->vlan_id[i] = f->vlan.vid; - f->state = IAVF_VLAN_INACTIVE; - i++; - if (i == count) - break; - } else if (f->state == IAVF_VLAN_REMOVE) { + list_for_each_entry(f, &adapter->vlan_filter_list, list) { + if (f->state == IAVF_VLAN_REMOVE) { vvfl->vlan_id[i] = f->vlan.vid; - list_del(&f->list); - kfree(f); - adapter->num_vlan_filters--; + f->state = IAVF_VLAN_REMOVING; i++; if (i == count) break; @@ -1006,9 +988,8 @@ void iavf_del_vlans(struct iavf_adapter *adapter) vvfl_v2->vport_id = adapter->vsi_res->vsi_id; vvfl_v2->num_elements = count; - list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { - if (f->state == IAVF_VLAN_DISABLE || - f->state == IAVF_VLAN_REMOVE) { + list_for_each_entry(f, &adapter->vlan_filter_list, list) { + if (f->state == IAVF_VLAN_REMOVE) { struct virtchnl_vlan_supported_caps *filtering_support = &adapter->vlan_v2_caps.filtering.filtering_support; struct virtchnl_vlan *vlan; @@ -1022,13 +1003,7 @@ void iavf_del_vlans(struct iavf_adapter *adapter) vlan->tci = f->vlan.vid; vlan->tpid = f->vlan.tpid; - if (f->state == IAVF_VLAN_DISABLE) { - f->state = IAVF_VLAN_INACTIVE; - } else { - list_del(&f->list); - kfree(f); - adapter->num_vlan_filters--; - } + f->state = IAVF_VLAN_REMOVING; i++; if (i == count) break; @@ -2391,10 +2366,6 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, ether_addr_copy(adapter->hw.mac.addr, netdev->dev_addr); wake_up(&adapter->vc_waitqueue); break; - case VIRTCHNL_OP_DEL_VLAN: - dev_err(&adapter->pdev->dev, "Failed to delete VLAN filter, error %s\n", - iavf_stat_str(&adapter->hw, v_retval)); - break; case VIRTCHNL_OP_DEL_ETH_ADDR: dev_err(&adapter->pdev->dev, "Failed to delete MAC filter, error %s\n", iavf_stat_str(&adapter->hw, v_retval)); @@ -2905,17 +2876,42 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, spin_unlock_bh(&adapter->adv_rss_lock); } break; + case VIRTCHNL_OP_ADD_VLAN: case VIRTCHNL_OP_ADD_VLAN_V2: { struct iavf_vlan_filter *f; + if (v_retval) + break; + spin_lock_bh(&adapter->mac_vlan_list_lock); list_for_each_entry(f, &adapter->vlan_filter_list, list) { - if (f->state == IAVF_VLAN_IS_NEW) + if (f->state == IAVF_VLAN_ADDING) f->state = IAVF_VLAN_ACTIVE; } spin_unlock_bh(&adapter->mac_vlan_list_lock); } break; + case VIRTCHNL_OP_DEL_VLAN: + case VIRTCHNL_OP_DEL_VLAN_V2: { + struct iavf_vlan_filter *f, *ftmp; + + spin_lock_bh(&adapter->mac_vlan_list_lock); + list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, + list) { + if (f->state == IAVF_VLAN_REMOVING) { + if (v_retval) { + /* PF rejected DEL, keep filter */ + f->state = IAVF_VLAN_ACTIVE; + } else { + list_del(&f->list); + kfree(f); + adapter->num_vlan_filters--; + } + } + } + spin_unlock_bh(&adapter->mac_vlan_list_lock); + } + break; case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING: /* PF enabled vlan strip on this VF. * Update netdev->features if needed to be in sync with ethtool. diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c index 6144cee8034d..641d6e289d5c 100644 --- a/drivers/net/ethernet/intel/ice/devlink/devlink.c +++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c @@ -1245,6 +1245,8 @@ static int ice_devlink_reinit_up(struct ice_pf *pf) return err; } + ice_init_dev_hw(pf); + /* load MSI-X values */ ice_set_min_max_msix(pf); diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index ce11fea122d0..b617a6bff891 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -1126,8 +1126,6 @@ int ice_init_hw(struct ice_hw *hw) if (status) goto err_unroll_fltr_mgmt_struct; - ice_init_dev_hw(hw->back); - mutex_init(&hw->tnl_lock); ice_init_chk_recipe_reuse_support(hw); diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c index 62f75701d652..27b460926bac 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.c +++ b/drivers/net/ethernet/intel/ice/ice_dpll.c @@ -1155,6 +1155,32 @@ ice_dpll_input_state_get(const struct dpll_pin *pin, void *pin_priv, } /** + * ice_dpll_sw_pin_notify_peer - notify the paired SW pin after a state change + * @d: pointer to dplls struct + * @changed: the SW pin that was explicitly changed (already notified by dpll core) + * + * SMA and U.FL pins share physical signal paths in pairs (SMA1/U.FL1 and + * SMA2/U.FL2). When one pin's routing changes via the PCA9575 GPIO + * expander, the paired pin's state may also change. Send a change + * notification for the peer pin so userspace consumers monitoring the + * peer via dpll netlink learn about the update. + * + * Context: Called from dpll_pin_ops callbacks after pf->dplls.lock is + * released. Uses __dpll_pin_change_ntf() because dpll_lock is + * still held by the dpll netlink layer. + */ +static void ice_dpll_sw_pin_notify_peer(struct ice_dplls *d, + struct ice_dpll_pin *changed) +{ + struct ice_dpll_pin *peer; + + peer = (changed >= d->sma && changed < d->sma + ICE_DPLL_PIN_SW_NUM) ? + &d->ufl[changed->idx] : &d->sma[changed->idx]; + if (peer->pin) + __dpll_pin_change_ntf(peer->pin); +} + +/** * ice_dpll_sma_direction_set - set direction of SMA pin * @p: pointer to a pin * @direction: requested direction of the pin @@ -1171,6 +1197,8 @@ static int ice_dpll_sma_direction_set(struct ice_dpll_pin *p, enum dpll_pin_direction direction, struct netlink_ext_ack *extack) { + struct ice_dplls *d = &p->pf->dplls; + struct ice_dpll_pin *peer; u8 data; int ret; @@ -1189,8 +1217,9 @@ static int ice_dpll_sma_direction_set(struct ice_dpll_pin *p, case ICE_DPLL_PIN_SW_2_IDX: if (direction == DPLL_PIN_DIRECTION_INPUT) { data &= ~ICE_SMA2_DIR_EN; + data |= ICE_SMA2_UFL2_RX_DIS; } else { - data &= ~ICE_SMA2_TX_EN; + data &= ~(ICE_SMA2_TX_EN | ICE_SMA2_UFL2_RX_DIS); data |= ICE_SMA2_DIR_EN; } break; @@ -1202,6 +1231,34 @@ static int ice_dpll_sma_direction_set(struct ice_dpll_pin *p, ret = ice_dpll_pin_state_update(p->pf, p, ICE_DPLL_PIN_TYPE_SOFTWARE, extack); + if (ret) + return ret; + + /* When a direction change activates the paired U.FL pin, enable + * its backing CGU pin so the pin reports as connected. Without + * this the U.FL routing is correct but the CGU pin stays disabled + * and userspace sees the pin as disconnected. Do not disable the + * backing pin when U.FL becomes inactive because the SMA pin may + * still be using it. + */ + peer = &d->ufl[p->idx]; + if (peer->active) { + struct ice_dpll_pin *target; + enum ice_dpll_pin_type type; + + if (peer->output) { + target = peer->output; + type = ICE_DPLL_PIN_TYPE_OUTPUT; + } else { + target = peer->input; + type = ICE_DPLL_PIN_TYPE_INPUT; + } + ret = ice_dpll_pin_enable(&p->pf->hw, target, + d->eec.dpll_idx, type, extack); + if (!ret) + ret = ice_dpll_pin_state_update(p->pf, target, + type, extack); + } return ret; } @@ -1253,6 +1310,14 @@ ice_dpll_ufl_pin_state_set(const struct dpll_pin *pin, void *pin_priv, data &= ~ICE_SMA1_MASK; enable = true; } else if (state == DPLL_PIN_STATE_DISCONNECTED) { + /* Skip if U.FL1 is not active, setting TX_EN + * while DIR_EN is set would also deactivate + * the paired SMA1 output. + */ + if (data & (ICE_SMA1_DIR_EN | ICE_SMA1_TX_EN)) { + ret = 0; + goto unlock; + } data |= ICE_SMA1_TX_EN; enable = false; } else { @@ -1267,6 +1332,15 @@ ice_dpll_ufl_pin_state_set(const struct dpll_pin *pin, void *pin_priv, data &= ~ICE_SMA2_UFL2_RX_DIS; enable = true; } else if (state == DPLL_PIN_STATE_DISCONNECTED) { + /* Skip if U.FL2 is not active, setting + * UFL2_RX_DIS could also disable the paired + * SMA2 input. + */ + if (!(data & ICE_SMA2_DIR_EN) || + (data & ICE_SMA2_UFL2_RX_DIS)) { + ret = 0; + goto unlock; + } data |= ICE_SMA2_UFL2_RX_DIS; enable = false; } else { @@ -1296,6 +1370,8 @@ ice_dpll_ufl_pin_state_set(const struct dpll_pin *pin, void *pin_priv, unlock: mutex_unlock(&pf->dplls.lock); + if (!ret) + ice_dpll_sw_pin_notify_peer(&pf->dplls, p); return ret; } @@ -1414,6 +1490,8 @@ ice_dpll_sma_pin_state_set(const struct dpll_pin *pin, void *pin_priv, unlock: mutex_unlock(&pf->dplls.lock); + if (!ret) + ice_dpll_sw_pin_notify_peer(&pf->dplls, sma); return ret; } @@ -1609,6 +1687,8 @@ ice_dpll_pin_sma_direction_set(const struct dpll_pin *pin, void *pin_priv, mutex_lock(&pf->dplls.lock); ret = ice_dpll_sma_direction_set(p, direction, extack); mutex_unlock(&pf->dplls.lock); + if (!ret) + ice_dpll_sw_pin_notify_peer(&pf->dplls, p); return ret; } @@ -1915,7 +1995,10 @@ ice_dpll_phase_offset_get(const struct dpll_pin *pin, void *pin_priv, d->active_input == p->input->pin)) *phase_offset = d->phase_offset * ICE_DPLL_PHASE_OFFSET_FACTOR; else if (d->phase_offset_monitor_period) - *phase_offset = p->phase_offset * ICE_DPLL_PHASE_OFFSET_FACTOR; + *phase_offset = (p->input && + p->direction == DPLL_PIN_DIRECTION_INPUT ? + p->input->phase_offset : + p->phase_offset) * ICE_DPLL_PHASE_OFFSET_FACTOR; else *phase_offset = 0; mutex_unlock(&pf->dplls.lock); @@ -2610,6 +2693,27 @@ static u64 ice_generate_clock_id(struct ice_pf *pf) } /** + * ice_dpll_pin_ntf - notify pin change including any SW pin wrappers + * @dplls: pointer to dplls struct + * @pin: the dpll_pin that changed + * + * Send a change notification for @pin and for any registered SMA/U.FL pin + * whose backing CGU input matches @pin. + */ +static void ice_dpll_pin_ntf(struct ice_dplls *dplls, struct dpll_pin *pin) +{ + dpll_pin_change_ntf(pin); + for (int i = 0; i < ICE_DPLL_PIN_SW_NUM; i++) { + if (dplls->sma[i].pin && dplls->sma[i].input && + dplls->sma[i].input->pin == pin) + dpll_pin_change_ntf(dplls->sma[i].pin); + if (dplls->ufl[i].pin && dplls->ufl[i].input && + dplls->ufl[i].input->pin == pin) + dpll_pin_change_ntf(dplls->ufl[i].pin); + } +} + +/** * ice_dpll_notify_changes - notify dpll subsystem about changes * @d: pointer do dpll * @@ -2617,6 +2721,7 @@ static u64 ice_generate_clock_id(struct ice_pf *pf) */ static void ice_dpll_notify_changes(struct ice_dpll *d) { + struct ice_dplls *dplls = &d->pf->dplls; bool pin_notified = false; if (d->prev_dpll_state != d->dpll_state) { @@ -2625,17 +2730,17 @@ static void ice_dpll_notify_changes(struct ice_dpll *d) } if (d->prev_input != d->active_input) { if (d->prev_input) - dpll_pin_change_ntf(d->prev_input); + ice_dpll_pin_ntf(dplls, d->prev_input); d->prev_input = d->active_input; if (d->active_input) { - dpll_pin_change_ntf(d->active_input); + ice_dpll_pin_ntf(dplls, d->active_input); pin_notified = true; } } if (d->prev_phase_offset != d->phase_offset) { d->prev_phase_offset = d->phase_offset; if (!pin_notified && d->active_input) - dpll_pin_change_ntf(d->active_input); + ice_dpll_pin_ntf(dplls, d->active_input); } } @@ -2664,6 +2769,7 @@ static bool ice_dpll_is_pps_phase_monitor(struct ice_pf *pf) /** * ice_dpll_pins_notify_mask - notify dpll subsystem about bulk pin changes + * @dplls: pointer to dplls struct * @pins: array of ice_dpll_pin pointers registered within dpll subsystem * @pin_num: number of pins * @phase_offset_ntf_mask: bitmask of pin indexes to notify @@ -2673,15 +2779,14 @@ static bool ice_dpll_is_pps_phase_monitor(struct ice_pf *pf) * * Context: Must be called while pf->dplls.lock is released. */ -static void ice_dpll_pins_notify_mask(struct ice_dpll_pin *pins, +static void ice_dpll_pins_notify_mask(struct ice_dplls *dplls, + struct ice_dpll_pin *pins, u8 pin_num, u32 phase_offset_ntf_mask) { - int i = 0; - - for (i = 0; i < pin_num; i++) - if (phase_offset_ntf_mask & (1 << i)) - dpll_pin_change_ntf(pins[i].pin); + for (int i = 0; i < pin_num; i++) + if (phase_offset_ntf_mask & BIT(i)) + ice_dpll_pin_ntf(dplls, pins[i].pin); } /** @@ -2857,7 +2962,7 @@ static void ice_dpll_periodic_work(struct kthread_work *work) ice_dpll_notify_changes(de); ice_dpll_notify_changes(dp); if (phase_offset_ntf) - ice_dpll_pins_notify_mask(d->inputs, d->num_inputs, + ice_dpll_pins_notify_mask(d, d->inputs, d->num_inputs, phase_offset_ntf); resched: @@ -4014,6 +4119,7 @@ static int ice_dpll_init_info_sw_pins(struct ice_pf *pf) struct ice_dpll_pin *pin; u32 phase_adj_max, caps; int i, ret; + u8 data; if (pf->hw.device_id == ICE_DEV_ID_E810C_QSFP) input_idx_offset = ICE_E810_RCLK_PINS_NUM; @@ -4073,6 +4179,22 @@ static int ice_dpll_init_info_sw_pins(struct ice_pf *pf) } ice_dpll_phase_range_set(&pin->prop.phase_range, phase_adj_max); } + + /* Initialize the SMA control register to a known-good default state. + * Without this write the PCA9575 GPIO expander retains its power-on + * default (all outputs high) which makes all SW pins appear inactive. + * Set SMA1 and SMA2 as active inputs, disable U.FL1 output and + * U.FL2 input. + */ + ret = ice_read_sma_ctrl(&pf->hw, &data); + if (ret) + return ret; + data &= ~ICE_ALL_SMA_MASK; + data |= ICE_SMA1_TX_EN | ICE_SMA2_TX_EN | ICE_SMA2_UFL2_RX_DIS; + ret = ice_write_sma_ctrl(&pf->hw, data); + if (ret) + return ret; + ret = ice_dpll_pin_state_update(pf, pin, ICE_DPLL_PIN_TYPE_SOFTWARE, NULL); if (ret) diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 5f92377d4dfc..1d1947a7fe11 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -5245,6 +5245,8 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) return err; } + ice_init_dev_hw(pf); + adapter = ice_adapter_get(pdev); if (IS_ERR(adapter)) { err = PTR_ERR(adapter); diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index 772f6b07340d..b1f46707dcc0 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c @@ -804,7 +804,12 @@ void ice_reset_all_vfs(struct ice_pf *pf) ice_vf_ctrl_invalidate_vsi(vf); ice_vf_pre_vsi_rebuild(vf); - ice_vf_rebuild_vsi(vf); + if (ice_vf_rebuild_vsi(vf)) { + dev_err(dev, "VF %u VSI rebuild failed, leaving VF disabled\n", + vf->vf_id); + mutex_unlock(&vf->cfg_lock); + continue; + } ice_vf_post_vsi_rebuild(vf); ice_eswitch_attach_vf(pf, vf); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/debugfs.c index 3debf2fae1a4..6f13296303cb 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/debugfs.c @@ -249,34 +249,21 @@ DEFINE_SHOW_ATTRIBUTE(npc_defrag); int npc_cn20k_debugfs_init(struct rvu *rvu) { struct npc_priv_t *npc_priv = npc_priv_get(); - struct dentry *npc_dentry; - npc_dentry = debugfs_create_file("mcam_layout", 0444, rvu->rvu_dbg.npc, - npc_priv, &npc_mcam_layout_fops); + debugfs_create_file("mcam_layout", 0444, rvu->rvu_dbg.npc, + npc_priv, &npc_mcam_layout_fops); - if (!npc_dentry) - return -EFAULT; + debugfs_create_file("mcam_default", 0444, rvu->rvu_dbg.npc, + rvu, &npc_mcam_default_fops); - npc_dentry = debugfs_create_file("mcam_default", 0444, rvu->rvu_dbg.npc, - rvu, &npc_mcam_default_fops); + debugfs_create_file("vidx2idx", 0444, rvu->rvu_dbg.npc, + npc_priv, &npc_vidx2idx_map_fops); - if (!npc_dentry) - return -EFAULT; + debugfs_create_file("idx2vidx", 0444, rvu->rvu_dbg.npc, + npc_priv, &npc_idx2vidx_map_fops); - npc_dentry = debugfs_create_file("vidx2idx", 0444, rvu->rvu_dbg.npc, - npc_priv, &npc_vidx2idx_map_fops); - if (!npc_dentry) - return -EFAULT; - - npc_dentry = debugfs_create_file("idx2vidx", 0444, rvu->rvu_dbg.npc, - npc_priv, &npc_idx2vidx_map_fops); - if (!npc_dentry) - return -EFAULT; - - npc_dentry = debugfs_create_file("defrag", 0444, rvu->rvu_dbg.npc, - npc_priv, &npc_defrag_fops); - if (!npc_dentry) - return -EFAULT; + debugfs_create_file("defrag", 0444, rvu->rvu_dbg.npc, + npc_priv, &npc_defrag_fops); return 0; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c index 7291fdb89b03..6b3f453fd500 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c @@ -798,7 +798,7 @@ program_mkex_extr: iounmap(mkex_prfl_addr); } -void +int npc_cn20k_enable_mcam_entry(struct rvu *rvu, int blkaddr, int index, bool enable) { @@ -808,7 +808,12 @@ npc_cn20k_enable_mcam_entry(struct rvu *rvu, int blkaddr, u64 cfg, hw_prio; u8 kw_type; - npc_mcam_idx_2_key_type(rvu, index, &kw_type); + if (index < 0 || index >= mcam->total_entries) + return -EINVAL; + + if (npc_mcam_idx_2_key_type(rvu, index, &kw_type)) + return -EINVAL; + if (kw_type == NPC_MCAM_KEY_X2) { cfg = rvu_read64(rvu, blkaddr, NPC_AF_CN20K_MCAMEX_BANKX_CFG_EXT(mcam_idx, @@ -819,7 +824,7 @@ npc_cn20k_enable_mcam_entry(struct rvu *rvu, int blkaddr, rvu_write64(rvu, blkaddr, NPC_AF_CN20K_MCAMEX_BANKX_CFG_EXT(mcam_idx, bank), cfg); - return; + return 0; } /* For NPC_CN20K_MCAM_KEY_X4 keys, both the banks @@ -836,10 +841,12 @@ npc_cn20k_enable_mcam_entry(struct rvu *rvu, int blkaddr, NPC_AF_CN20K_MCAMEX_BANKX_CFG_EXT(mcam_idx, bank), cfg); } + + return 0; } -void -npc_cn20k_clear_mcam_entry(struct rvu *rvu, int blkaddr, int bank, int index) +static void +npc_clear_x2_entry(struct rvu *rvu, int blkaddr, int bank, int index) { rvu_write64(rvu, blkaddr, NPC_AF_CN20K_MCAMEX_BANKX_CAMX_INTF_EXT(index, bank, 1), @@ -873,6 +880,33 @@ npc_cn20k_clear_mcam_entry(struct rvu *rvu, int blkaddr, int bank, int index) NPC_AF_CN20K_MCAMEX_BANKX_STAT_EXT(index, bank), 0); } +int +npc_cn20k_clear_mcam_entry(struct rvu *rvu, int blkaddr, int mcam_idx) +{ + struct npc_mcam *mcam = &rvu->hw->mcam; + int bank = npc_get_bank(mcam, mcam_idx); + u8 kw_type; + int index; + + if (npc_mcam_idx_2_key_type(rvu, mcam_idx, &kw_type)) + return -EINVAL; + + index = mcam_idx & (mcam->banksize - 1); + + if (kw_type == NPC_MCAM_KEY_X2) { + npc_clear_x2_entry(rvu, blkaddr, bank, index); + return 0; + } + + /* For NPC_MCAM_KEY_X4 keys, both the banks + * need to be programmed with the same value. + */ + for (bank = 0; bank < mcam->banks_per_entry; bank++) + npc_clear_x2_entry(rvu, blkaddr, bank, index); + + return 0; +} + static void npc_cn20k_get_keyword(struct cn20k_mcam_entry *entry, int idx, u64 *cam0, u64 *cam1) { @@ -1014,48 +1048,27 @@ static void npc_cn20k_config_kw_x4(struct rvu *rvu, struct npc_mcam *mcam, kw, req_kw_type); } -static void -npc_cn20k_set_mcam_bank_cfg(struct rvu *rvu, int blkaddr, int mcam_idx, - int bank, u8 kw_type, bool enable, u8 hw_prio) -{ - struct npc_mcam *mcam = &rvu->hw->mcam; - u64 bank_cfg; - - bank_cfg = (u64)hw_prio << 24; - if (enable) - bank_cfg |= 0x1; - - if (kw_type == NPC_MCAM_KEY_X2) { - rvu_write64(rvu, blkaddr, - NPC_AF_CN20K_MCAMEX_BANKX_CFG_EXT(mcam_idx, bank), - bank_cfg); - return; - } - - /* For NPC_MCAM_KEY_X4 keys, both the banks - * need to be programmed with the same value. - */ - for (bank = 0; bank < mcam->banks_per_entry; bank++) { - rvu_write64(rvu, blkaddr, - NPC_AF_CN20K_MCAMEX_BANKX_CFG_EXT(mcam_idx, bank), - bank_cfg); - } -} - -void npc_cn20k_config_mcam_entry(struct rvu *rvu, int blkaddr, int index, - u8 intf, struct cn20k_mcam_entry *entry, - bool enable, u8 hw_prio, u8 req_kw_type) +int npc_cn20k_config_mcam_entry(struct rvu *rvu, int blkaddr, int index, + u8 intf, struct cn20k_mcam_entry *entry, + bool enable, u8 hw_prio, u8 req_kw_type) { struct npc_mcam *mcam = &rvu->hw->mcam; int mcam_idx = index % mcam->banksize; int bank = index / mcam->banksize; + u64 bank_cfg = (u64)hw_prio << 24; int kw = 0; u8 kw_type; + if (index < 0 || index >= mcam->total_entries) + return -EINVAL; + + if (npc_mcam_idx_2_key_type(rvu, index, &kw_type)) + return -EINVAL; + /* Disable before mcam entry update */ - npc_cn20k_enable_mcam_entry(rvu, blkaddr, index, false); + if (npc_cn20k_enable_mcam_entry(rvu, blkaddr, index, false)) + return -EINVAL; - npc_mcam_idx_2_key_type(rvu, index, &kw_type); /* CAM1 takes the comparison value and * CAM0 specifies match for a bit in key being '0' or '1' or 'dontcare'. * CAM1<n> = 0 & CAM0<n> = 1 => match if key<n> = 0 @@ -1064,7 +1077,7 @@ void npc_cn20k_config_mcam_entry(struct rvu *rvu, int blkaddr, int index, */ if (kw_type == NPC_MCAM_KEY_X2) { /* Clear mcam entry to avoid writes being suppressed by NPC */ - npc_cn20k_clear_mcam_entry(rvu, blkaddr, bank, mcam_idx); + npc_clear_x2_entry(rvu, blkaddr, bank, mcam_idx); npc_cn20k_config_kw_x2(rvu, mcam, blkaddr, mcam_idx, intf, entry, bank, kw_type, kw, req_kw_type); @@ -1085,44 +1098,55 @@ void npc_cn20k_config_mcam_entry(struct rvu *rvu, int blkaddr, int index, NPC_AF_CN20K_MCAMEX_BANKX_ACTIONX_EXT(mcam_idx, bank, 1), entry->vtag_action); - goto set_cfg; - } - - /* Clear mcam entry to avoid writes being suppressed by NPC */ - npc_cn20k_clear_mcam_entry(rvu, blkaddr, 0, mcam_idx); - npc_cn20k_clear_mcam_entry(rvu, blkaddr, 1, mcam_idx); - npc_cn20k_config_kw_x4(rvu, mcam, blkaddr, - mcam_idx, intf, entry, - kw_type, req_kw_type); - for (bank = 0; bank < mcam->banks_per_entry; bank++) { - /* Set 'action' */ + /* Set HW priority */ rvu_write64(rvu, blkaddr, - NPC_AF_CN20K_MCAMEX_BANKX_ACTIONX_EXT(mcam_idx, - bank, 0), - entry->action); + NPC_AF_CN20K_MCAMEX_BANKX_CFG_EXT(mcam_idx, bank), + bank_cfg); - /* Set TAG 'action' */ - rvu_write64(rvu, blkaddr, - NPC_AF_CN20K_MCAMEX_BANKX_ACTIONX_EXT(mcam_idx, - bank, 1), - entry->vtag_action); + } else { + /* Clear mcam entry to avoid writes being suppressed by NPC */ + npc_clear_x2_entry(rvu, blkaddr, 0, mcam_idx); + npc_clear_x2_entry(rvu, blkaddr, 1, mcam_idx); - /* Set 'action2' for inline receive */ - rvu_write64(rvu, blkaddr, - NPC_AF_CN20K_MCAMEX_BANKX_ACTIONX_EXT(mcam_idx, - bank, 2), - entry->action2); + npc_cn20k_config_kw_x4(rvu, mcam, blkaddr, + mcam_idx, intf, entry, + kw_type, req_kw_type); + for (bank = 0; bank < mcam->banks_per_entry; bank++) { + /* Set 'action' */ + rvu_write64(rvu, blkaddr, + NPC_AF_CN20K_MCAMEX_BANKX_ACTIONX_EXT(mcam_idx, + bank, 0), + entry->action); + + /* Set TAG 'action' */ + rvu_write64(rvu, blkaddr, + NPC_AF_CN20K_MCAMEX_BANKX_ACTIONX_EXT(mcam_idx, + bank, 1), + entry->vtag_action); + + /* Set 'action2' for inline receive */ + rvu_write64(rvu, blkaddr, + NPC_AF_CN20K_MCAMEX_BANKX_ACTIONX_EXT(mcam_idx, + bank, 2), + entry->action2); + + /* Set HW priority */ + rvu_write64(rvu, blkaddr, + NPC_AF_CN20K_MCAMEX_BANKX_CFG_EXT(mcam_idx, bank), + bank_cfg); + } } -set_cfg: /* TODO: */ /* PF installing VF rule */ - npc_cn20k_set_mcam_bank_cfg(rvu, blkaddr, mcam_idx, bank, - kw_type, enable, hw_prio); + if (npc_cn20k_enable_mcam_entry(rvu, blkaddr, index, enable)) + return -EINVAL; + + return 0; } -void npc_cn20k_copy_mcam_entry(struct rvu *rvu, int blkaddr, u16 src, u16 dest) +int npc_cn20k_copy_mcam_entry(struct rvu *rvu, int blkaddr, u16 src, u16 dest) { struct npc_mcam *mcam = &rvu->hw->mcam; u64 cfg, sreg, dreg, soff, doff; @@ -1130,12 +1154,20 @@ void npc_cn20k_copy_mcam_entry(struct rvu *rvu, int blkaddr, u16 src, u16 dest) int bank, i, sb, db; int dbank, sbank; + if (src >= mcam->total_entries || dest >= mcam->total_entries) + return -EINVAL; + dbank = npc_get_bank(mcam, dest); sbank = npc_get_bank(mcam, src); - npc_mcam_idx_2_key_type(rvu, src, &src_kwtype); - npc_mcam_idx_2_key_type(rvu, dest, &dest_kwtype); + + if (npc_mcam_idx_2_key_type(rvu, src, &src_kwtype)) + return -EINVAL; + + if (npc_mcam_idx_2_key_type(rvu, dest, &dest_kwtype)) + return -EINVAL; + if (src_kwtype != dest_kwtype) - return; + return -EINVAL; src &= (mcam->banksize - 1); dest &= (mcam->banksize - 1); @@ -1170,6 +1202,8 @@ void npc_cn20k_copy_mcam_entry(struct rvu *rvu, int blkaddr, u16 src, u16 dest) if (src_kwtype == NPC_MCAM_KEY_X2) break; } + + return 0; } static void npc_cn20k_fill_entryword(struct cn20k_mcam_entry *entry, int idx, @@ -1179,21 +1213,37 @@ static void npc_cn20k_fill_entryword(struct cn20k_mcam_entry *entry, int idx, entry->kw_mask[idx] = cam1 ^ cam0; } -void npc_cn20k_read_mcam_entry(struct rvu *rvu, int blkaddr, u16 index, - struct cn20k_mcam_entry *entry, - u8 *intf, u8 *ena, u8 *hw_prio) +int npc_cn20k_read_mcam_entry(struct rvu *rvu, int blkaddr, u16 index, + struct cn20k_mcam_entry *entry, + u8 *intf, u8 *ena, u8 *hw_prio) { struct npc_mcam *mcam = &rvu->hw->mcam; u64 cam0, cam1, bank_cfg, cfg; int kw = 0, bank; u8 kw_type; - npc_mcam_idx_2_key_type(rvu, index, &kw_type); + if (index >= mcam->total_entries) + return -EINVAL; + + if (npc_mcam_idx_2_key_type(rvu, index, &kw_type)) + return -EINVAL; bank = npc_get_bank(mcam, index); index &= (mcam->banksize - 1); cfg = rvu_read64(rvu, blkaddr, + NPC_AF_CN20K_MCAMEX_BANKX_ACTIONX_EXT(index, bank, 0)); + entry->action = cfg; + + cfg = rvu_read64(rvu, blkaddr, + NPC_AF_CN20K_MCAMEX_BANKX_ACTIONX_EXT(index, bank, 1)); + entry->vtag_action = cfg; + + cfg = rvu_read64(rvu, blkaddr, + NPC_AF_CN20K_MCAMEX_BANKX_ACTIONX_EXT(index, bank, 2)); + entry->action2 = cfg; + + cfg = rvu_read64(rvu, blkaddr, NPC_AF_CN20K_MCAMEX_BANKX_CAMX_INTF_EXT(index, bank, 1)) & 3; *intf = cfg; @@ -1242,7 +1292,7 @@ void npc_cn20k_read_mcam_entry(struct rvu *rvu, int blkaddr, u16 index, bank, 0)); npc_cn20k_fill_entryword(entry, kw + 3, cam0, cam1); - goto read_action; + return 0; } for (bank = 0; bank < mcam->banks_per_entry; bank++, kw = kw + 4) { @@ -1287,17 +1337,7 @@ void npc_cn20k_read_mcam_entry(struct rvu *rvu, int blkaddr, u16 index, npc_cn20k_fill_entryword(entry, kw + 3, cam0, cam1); } -read_action: - /* 'action' is set to same value for both bank '0' and '1'. - * Hence, reading bank '0' should be enough. - */ - cfg = rvu_read64(rvu, blkaddr, - NPC_AF_CN20K_MCAMEX_BANKX_ACTIONX_EXT(index, 0, 0)); - entry->action = cfg; - - cfg = rvu_read64(rvu, blkaddr, - NPC_AF_CN20K_MCAMEX_BANKX_ACTIONX_EXT(index, 0, 1)); - entry->vtag_action = cfg; + return 0; } int rvu_mbox_handler_npc_cn20k_mcam_write_entry(struct rvu *rvu, @@ -1335,11 +1375,10 @@ int rvu_mbox_handler_npc_cn20k_mcam_write_entry(struct rvu *rvu, if (is_pffunc_af(req->hdr.pcifunc)) nix_intf = req->intf; - npc_cn20k_config_mcam_entry(rvu, blkaddr, req->entry, nix_intf, - &req->entry_data, req->enable_entry, - req->hw_prio, req->req_kw_type); + rc = npc_cn20k_config_mcam_entry(rvu, blkaddr, req->entry, nix_intf, + &req->entry_data, req->enable_entry, + req->hw_prio, req->req_kw_type); - rc = 0; exit: mutex_unlock(&mcam->lock); return rc; @@ -1361,11 +1400,13 @@ int rvu_mbox_handler_npc_cn20k_mcam_read_entry(struct rvu *rvu, mutex_lock(&mcam->lock); rc = npc_mcam_verify_entry(mcam, pcifunc, req->entry); - if (!rc) - npc_cn20k_read_mcam_entry(rvu, blkaddr, req->entry, - &rsp->entry_data, &rsp->intf, - &rsp->enable, &rsp->hw_prio); + if (rc) + goto fail; + rc = npc_cn20k_read_mcam_entry(rvu, blkaddr, req->entry, + &rsp->entry_data, &rsp->intf, + &rsp->enable, &rsp->hw_prio); +fail: mutex_unlock(&mcam->lock); return rc; } @@ -1375,11 +1416,13 @@ int rvu_mbox_handler_npc_cn20k_mcam_alloc_and_write_entry(struct rvu *rvu, struct npc_mcam_alloc_and_write_entry_rsp *rsp) { struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, req->hdr.pcifunc); + struct npc_mcam_free_entry_req free_req = { 0 }; struct npc_mcam_alloc_entry_req entry_req; struct npc_mcam_alloc_entry_rsp entry_rsp; struct npc_mcam *mcam = &rvu->hw->mcam; u16 entry = NPC_MCAM_ENTRY_INVALID; - int blkaddr, rc; + struct msg_rsp free_rsp; + int blkaddr, rc, err; u8 nix_intf; blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0); @@ -1415,12 +1458,23 @@ int rvu_mbox_handler_npc_cn20k_mcam_alloc_and_write_entry(struct rvu *rvu, else nix_intf = pfvf->nix_rx_intf; - npc_cn20k_config_mcam_entry(rvu, blkaddr, entry, nix_intf, - &req->entry_data, req->enable_entry, - req->hw_prio, req->req_kw_type); + rc = npc_cn20k_config_mcam_entry(rvu, blkaddr, entry, nix_intf, + &req->entry_data, req->enable_entry, + req->hw_prio, req->req_kw_type); mutex_unlock(&mcam->lock); + if (rc) { + free_req.hdr.pcifunc = req->hdr.pcifunc; + free_req.entry = entry_rsp.entry; + err = rvu_mbox_handler_npc_mcam_free_entry(rvu, &free_req, &free_rsp); + if (err) + dev_err(rvu->dev, + "%s: Error to free mcam idx %u\n", + __func__, entry_rsp.entry); + return rc; + } + rsp->entry = entry_rsp.entry; return 0; } @@ -1480,9 +1534,9 @@ int rvu_mbox_handler_npc_cn20k_read_base_steer_rule(struct rvu *rvu, read_entry: /* Read the mcam entry */ - npc_cn20k_read_mcam_entry(rvu, blkaddr, index, - &rsp->entry, &intf, - &enable, &hw_prio); + rc = npc_cn20k_read_mcam_entry(rvu, blkaddr, index, + &rsp->entry, &intf, + &enable, &hw_prio); mutex_unlock(&mcam->lock); out: return rc; @@ -2305,6 +2359,7 @@ err2: __npc_subbank_mark_free(rvu, sb); err1: kfree(save); + *alloc_cnt = 0; return rc; } @@ -3482,7 +3537,7 @@ static int npc_defrag_alloc_free_slots(struct rvu *rvu, { int alloc_cnt1, alloc_cnt2; struct npc_subbank *sb; - int rc, sb_off, i; + int rc, sb_off, i, err; bool deleted; sb = &npc_priv.sb[f->idx]; @@ -3496,6 +3551,7 @@ static int npc_defrag_alloc_free_slots(struct rvu *rvu, NPC_MCAM_LOWER_PRIO, false, cnt, save, cnt, true, &alloc_cnt1); + if (alloc_cnt1 < cnt) { rc = __npc_subbank_alloc(rvu, sb, NPC_MCAM_KEY_X2, sb->b1b, @@ -3511,15 +3567,17 @@ static int npc_defrag_alloc_free_slots(struct rvu *rvu, dev_err(rvu->dev, "%s: Failed to alloc cnt=%u alloc_cnt1=%u alloc_cnt2=%u\n", __func__, cnt, alloc_cnt1, alloc_cnt2); + rc = -ENOSPC; goto fail_free_alloc; } + return 0; fail_free_alloc: for (i = 0; i < alloc_cnt1 + alloc_cnt2; i++) { - rc = npc_mcam_idx_2_subbank_idx(rvu, save[i], - &sb, &sb_off); - if (rc) { + err = npc_mcam_idx_2_subbank_idx(rvu, save[i], + &sb, &sb_off); + if (err) { dev_err(rvu->dev, "%s: Error to find subbank for mcam idx=%u\n", __func__, save[i]); @@ -3565,9 +3623,10 @@ int npc_defrag_move_vdx_to_free(struct rvu *rvu, struct npc_defrag_node *v, int cnt, u16 *save) { + u16 new_midx, old_midx, vidx, target_pf; struct npc_mcam *mcam = &rvu->hw->mcam; + struct rvu_npc_mcam_rule *rule, *tmp; int i, vidx_cnt, rc, sb_off; - u16 new_midx, old_midx, vidx; struct npc_subbank *sb; bool deleted; u16 pcifunc; @@ -3607,9 +3666,30 @@ int npc_defrag_move_vdx_to_free(struct rvu *rvu, NPC_AF_CN20K_MCAMEX_BANKX_STAT_EXT(midx, bank)); - npc_cn20k_enable_mcam_entry(rvu, blkaddr, old_midx, false); - npc_cn20k_copy_mcam_entry(rvu, blkaddr, old_midx, new_midx); - npc_cn20k_enable_mcam_entry(rvu, blkaddr, new_midx, true); + /* If bug happened during copy/enable mcam, then there is a bug in allocation + * algorithm itself. There is no point in rewinding and returning, as it + * will face further issue. Return error after printing error + */ + if (npc_cn20k_enable_mcam_entry(rvu, blkaddr, old_midx, false)) { + dev_err(rvu->dev, + "%s: Error happened while disabling old_mid=%u\n", + __func__, old_midx); + return -EFAULT; + } + + if (npc_cn20k_copy_mcam_entry(rvu, blkaddr, old_midx, new_midx)) { + dev_err(rvu->dev, + "%s: Error happened while copying old_midx=%u new_midx=%u\n", + __func__, old_midx, new_midx); + return -EFAULT; + } + + if (npc_cn20k_enable_mcam_entry(rvu, blkaddr, new_midx, true)) { + dev_err(rvu->dev, + "%s: Error happened while enabling new_mid=%u\n", + __func__, new_midx); + return -EFAULT; + } midx = new_midx % mcam->banksize; bank = new_midx / mcam->banksize; @@ -3665,8 +3745,21 @@ int npc_defrag_move_vdx_to_free(struct rvu *rvu, mcam->entry2pfvf_map[new_midx] = pcifunc; /* Counter is not preserved */ mcam->entry2cntr_map[new_midx] = new_midx; + target_pf = mcam->entry2target_pffunc[old_midx]; + mcam->entry2target_pffunc[new_midx] = target_pf; + mcam->entry2target_pffunc[old_midx] = NPC_MCAM_INVALID_MAP; + npc_mcam_set_bit(mcam, new_midx); + /* Note: list order is not functionally required for mcam_rules */ + list_for_each_entry_safe(rule, tmp, &mcam->mcam_rules, list) { + if (rule->entry != old_midx) + continue; + + rule->entry = new_midx; + break; + } + /* Mark as invalid */ v->vidx[vidx_cnt - i - 1] = -1; save[cnt - i - 1] = -1; @@ -3935,6 +4028,13 @@ int npc_cn20k_dft_rules_idx_get(struct rvu *rvu, u16 pcifunc, u16 *bcast, void *val; int i, j; + for (i = 0; i < ARRAY_SIZE(ptr); i++) { + if (!ptr[i]) + continue; + + *ptr[i] = USHRT_MAX; + } + if (!npc_priv.init_done) return 0; @@ -3950,7 +4050,6 @@ int npc_cn20k_dft_rules_idx_get(struct rvu *rvu, u16 pcifunc, u16 *bcast, npc_dft_rule_name[NPC_DFT_RULE_PROMISC_ID], pcifunc); - *ptr[0] = USHRT_MAX; return -ESRCH; } @@ -3970,7 +4069,6 @@ int npc_cn20k_dft_rules_idx_get(struct rvu *rvu, u16 pcifunc, u16 *bcast, npc_dft_rule_name[NPC_DFT_RULE_UCAST_ID], pcifunc); - *ptr[3] = USHRT_MAX; return -ESRCH; } @@ -3990,7 +4088,6 @@ int npc_cn20k_dft_rules_idx_get(struct rvu *rvu, u16 pcifunc, u16 *bcast, __func__, npc_dft_rule_name[i], pcifunc); - *ptr[j] = USHRT_MAX; continue; } @@ -4085,7 +4182,7 @@ int rvu_mbox_handler_npc_get_dft_rl_idxs(struct rvu *rvu, struct msg_req *req, return 0; } -static bool npc_is_cgx_or_lbk(struct rvu *rvu, u16 pcifunc) +bool npc_is_cgx_or_lbk(struct rvu *rvu, u16 pcifunc) { return is_pf_cgxmapped(rvu, rvu_get_pf(rvu->pdev, pcifunc)) || is_lbk_vf(rvu, pcifunc); @@ -4093,11 +4190,11 @@ static bool npc_is_cgx_or_lbk(struct rvu *rvu, u16 pcifunc) void npc_cn20k_dft_rules_free(struct rvu *rvu, u16 pcifunc) { - struct npc_mcam_free_entry_req free_req = { 0 }; + struct npc_mcam *mcam = &rvu->hw->mcam; + u16 ptr[4] = {[0 ... 3] = USHRT_MAX}; + struct rvu_npc_mcam_rule *rule, *tmp; unsigned long index; - struct msg_rsp rsp; - u16 ptr[4]; - int rc, i; + int blkaddr, rc, i; void *map; if (!npc_priv.init_done) @@ -4155,14 +4252,43 @@ void npc_cn20k_dft_rules_free(struct rvu *rvu, u16 pcifunc) } free_rules: + blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0); + if (blkaddr < 0) + return; + for (int i = 0; i < 4; i++) { + if (ptr[i] == USHRT_MAX) + continue; - free_req.hdr.pcifunc = pcifunc; - free_req.all = 1; - rc = rvu_mbox_handler_npc_mcam_free_entry(rvu, &free_req, &rsp); - if (rc) - dev_err(rvu->dev, - "%s: Error deleting default entries (pcifunc=%#x\n", - __func__, pcifunc); + mutex_lock(&mcam->lock); + npc_mcam_clear_bit(mcam, ptr[i]); + mcam->entry2pfvf_map[ptr[i]] = NPC_MCAM_INVALID_MAP; + npc_cn20k_enable_mcam_entry(rvu, blkaddr, ptr[i], false); + mcam->entry2target_pffunc[ptr[i]] = 0x0; + mutex_unlock(&mcam->lock); + + rc = npc_cn20k_idx_free(rvu, &ptr[i], 1); + if (rc) { + /* Non recoverable error. Let us WARN and return. Keep system alive to + * enable debugging + */ + WARN(1, "%s Error deleting default entries (pcifunc=%#x) mcam_idx=%u\n", + __func__, pcifunc, ptr[i]); + return; + } + } + + mutex_lock(&mcam->lock); + list_for_each_entry_safe(rule, tmp, &mcam->mcam_rules, list) { + for (int i = 0; i < 4; i++) { + if (ptr[i] != rule->entry) + continue; + + list_del(&rule->list); + kfree(rule); + break; + } + } + mutex_unlock(&mcam->lock); } int npc_cn20k_dft_rules_alloc(struct rvu *rvu, u16 pcifunc) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.h index 815d0b257a7e..3d5eb952cc07 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.h @@ -320,21 +320,21 @@ void npc_cn20k_dft_rules_free(struct rvu *rvu, u16 pcifunc); int npc_cn20k_dft_rules_idx_get(struct rvu *rvu, u16 pcifunc, u16 *bcast, u16 *mcast, u16 *promisc, u16 *ucast); -void npc_cn20k_config_mcam_entry(struct rvu *rvu, int blkaddr, int index, - u8 intf, struct cn20k_mcam_entry *entry, - bool enable, u8 hw_prio, u8 req_kw_type); -void npc_cn20k_enable_mcam_entry(struct rvu *rvu, int blkaddr, - int index, bool enable); -void npc_cn20k_copy_mcam_entry(struct rvu *rvu, int blkaddr, - u16 src, u16 dest); -void npc_cn20k_read_mcam_entry(struct rvu *rvu, int blkaddr, u16 index, - struct cn20k_mcam_entry *entry, u8 *intf, - u8 *ena, u8 *hw_prio); -void npc_cn20k_clear_mcam_entry(struct rvu *rvu, int blkaddr, - int bank, int index); +int npc_cn20k_config_mcam_entry(struct rvu *rvu, int blkaddr, int index, + u8 intf, struct cn20k_mcam_entry *entry, + bool enable, u8 hw_prio, u8 req_kw_type); +int npc_cn20k_enable_mcam_entry(struct rvu *rvu, int blkaddr, + int index, bool enable); +int npc_cn20k_copy_mcam_entry(struct rvu *rvu, int blkaddr, + u16 src, u16 dest); +int npc_cn20k_read_mcam_entry(struct rvu *rvu, int blkaddr, u16 index, + struct cn20k_mcam_entry *entry, u8 *intf, + u8 *ena, u8 *hw_prio); +int npc_cn20k_clear_mcam_entry(struct rvu *rvu, int blkaddr, int index); int npc_mcam_idx_2_key_type(struct rvu *rvu, u16 mcam_idx, u8 *key_type); u16 npc_cn20k_vidx2idx(u16 index); u16 npc_cn20k_idx2vidx(u16 idx); int npc_cn20k_defrag(struct rvu *rvu); +bool npc_is_cgx_or_lbk(struct rvu *rvu, u16 pcifunc); #endif /* NPC_CN20K_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index ef5b081162eb..f977734ae712 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -3577,6 +3577,9 @@ static int nix_update_mce_rule(struct rvu *rvu, u16 pcifunc, mcam_index = npc_get_nixlf_mcam_index(mcam, pcifunc & ~RVU_PFVF_FUNC_MASK, nixlf, type); + if (mcam_index < 0) + return -EINVAL; + err = nix_update_mce_list(rvu, pcifunc, mce_list, mce_idx, mcam_index, add); return err; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index c2ca5ed1d028..3c814d157ab9 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -163,14 +163,35 @@ int npc_get_nixlf_mcam_index(struct npc_mcam *mcam, if (rc) return -EFAULT; + if (is_lbk_vf(rvu, pcifunc)) { + if (promisc == USHRT_MAX) + return -EINVAL; + return promisc; + } + + if (is_cgx_vf(rvu, pcifunc)) { + if (ucast == USHRT_MAX) + return -EINVAL; + + return ucast; + } + switch (type) { case NIXLF_BCAST_ENTRY: + if (bcast == USHRT_MAX) + return -EINVAL; return bcast; case NIXLF_ALLMULTI_ENTRY: + if (mcast == USHRT_MAX) + return -EINVAL; return mcast; case NIXLF_PROMISC_ENTRY: + if (promisc == USHRT_MAX) + return -EINVAL; return promisc; case NIXLF_UCAST_ENTRY: + if (ucast == USHRT_MAX) + return -EINVAL; return ucast; default: return -EINVAL; @@ -238,10 +259,10 @@ void npc_enable_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam, int actbank = bank; if (is_cn20k(rvu->pdev)) { - if (index < 0 || index >= mcam->banksize * mcam->banks) - return; - - return npc_cn20k_enable_mcam_entry(rvu, blkaddr, index, enable); + if (npc_cn20k_enable_mcam_entry(rvu, blkaddr, index, enable)) + dev_err(rvu->dev, "Error to %s mcam %u entry\n", + enable ? "enable" : "disable", index); + return; } index &= (mcam->banksize - 1); @@ -258,6 +279,13 @@ static void npc_clear_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam, int bank = npc_get_bank(mcam, index); int actbank = bank; + if (is_cn20k(rvu->pdev)) { + if (npc_cn20k_clear_mcam_entry(rvu, blkaddr, index)) + dev_err(rvu->dev, "%s Failed to clear mcam %u\n", + __func__, index); + return; + } + index &= (mcam->banksize - 1); for (; bank < (actbank + mcam->banks_per_entry); bank++) { rvu_write64(rvu, blkaddr, @@ -424,6 +452,15 @@ static u64 npc_get_default_entry_action(struct rvu *rvu, struct npc_mcam *mcam, index = npc_get_nixlf_mcam_index(mcam, pf_func, nixlf, NIXLF_UCAST_ENTRY); + + if (index < 0) { + dev_err(rvu->dev, + "%s: failed to get ucast entry pcifunc:0x%x\n", + __func__, pf_func); + /* Action 0 is drop */ + return 0; + } + bank = npc_get_bank(mcam, index); index &= (mcam->banksize - 1); @@ -589,8 +626,8 @@ void npc_read_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam, NPC_AF_MCAMEX_BANKX_CFG(src, sbank)) & 1; } -static void npc_copy_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam, - int blkaddr, u16 src, u16 dest) +static int npc_copy_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam, + int blkaddr, u16 src, u16 dest) { int dbank = npc_get_bank(mcam, dest); int sbank = npc_get_bank(mcam, src); @@ -630,6 +667,7 @@ static void npc_copy_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam, NPC_AF_MCAMEX_BANKX_CFG(src, sbank)); rvu_write64(rvu, blkaddr, NPC_AF_MCAMEX_BANKX_CFG(dest, dbank), cfg); + return 0; } u64 npc_get_mcam_action(struct rvu *rvu, struct npc_mcam *mcam, @@ -689,6 +727,12 @@ void rvu_npc_install_ucast_entry(struct rvu *rvu, u16 pcifunc, index = npc_get_nixlf_mcam_index(mcam, pcifunc, nixlf, NIXLF_UCAST_ENTRY); + if (index < 0) { + dev_err(rvu->dev, + "%s: Error to get ucast entry for pcifunc=%#x\n", + __func__, pcifunc); + return; + } /* Don't change the action if entry is already enabled * Otherwise RSS action may get overwritten. @@ -744,16 +788,38 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc, index = npc_get_nixlf_mcam_index(mcam, pcifunc, nixlf, NIXLF_PROMISC_ENTRY); + /* In cn20k, default indexes are installed only for CGX mapped + * and lbk interfaces + */ if (is_cgx_vf(rvu, pcifunc)) index = npc_get_nixlf_mcam_index(mcam, pcifunc & ~RVU_PFVF_FUNC_MASK, nixlf, NIXLF_PROMISC_ENTRY); + if (index < 0) { + dev_err(rvu->dev, + "%s: Error to get promisc entry for pcifunc=%#x\n", + __func__, pcifunc); + return; + } + /* If the corresponding PF's ucast action is RSS, * use the same action for promisc also + * Please note that for lbk(s) "index" and "ucast_idx" + * will be same. */ - ucast_idx = npc_get_nixlf_mcam_index(mcam, pcifunc, - nixlf, NIXLF_UCAST_ENTRY); + if (is_lbk_vf(rvu, pcifunc)) + ucast_idx = index; + else + ucast_idx = npc_get_nixlf_mcam_index(mcam, pcifunc, + nixlf, NIXLF_UCAST_ENTRY); + if (ucast_idx < 0) { + dev_err(rvu->dev, + "%s: Error to get ucast/promisc entry for pcifunc=%#x\n", + __func__, pcifunc); + return; + } + if (is_mcam_entry_enabled(rvu, mcam, blkaddr, ucast_idx)) *(u64 *)&action = npc_get_mcam_action(rvu, mcam, blkaddr, ucast_idx); @@ -827,6 +893,14 @@ void rvu_npc_enable_promisc_entry(struct rvu *rvu, u16 pcifunc, index = npc_get_nixlf_mcam_index(mcam, pcifunc, nixlf, NIXLF_PROMISC_ENTRY); + + if (index < 0) { + dev_err(rvu->dev, + "%s: Error to get promisc entry for pcifunc=%#x\n", + __func__, pcifunc); + return; + } + npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable); } @@ -867,6 +941,12 @@ void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc, index = npc_get_nixlf_mcam_index(mcam, pcifunc, nixlf, NIXLF_BCAST_ENTRY); + if (index < 0) { + dev_err(rvu->dev, + "%s: Error to get bcast entry for pcifunc=%#x\n", + __func__, pcifunc); + return; + } if (!hw->cap.nix_rx_multicast) { /* Early silicon doesn't support pkt replication, @@ -931,12 +1011,25 @@ void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf, index = npc_get_nixlf_mcam_index(mcam, pcifunc, nixlf, NIXLF_ALLMULTI_ENTRY); + if (index < 0) { + dev_err(rvu->dev, + "%s: Error to get mcast entry for pcifunc=%#x\n", + __func__, pcifunc); + return; + } /* If the corresponding PF's ucast action is RSS, * use the same action for multicast entry also */ ucast_idx = npc_get_nixlf_mcam_index(mcam, pcifunc, nixlf, NIXLF_UCAST_ENTRY); + if (ucast_idx < 0) { + dev_err(rvu->dev, + "%s: Error to get ucast entry for pcifunc=%#x\n", + __func__, pcifunc); + return; + } + if (is_mcam_entry_enabled(rvu, mcam, blkaddr, ucast_idx)) *(u64 *)&action = npc_get_mcam_action(rvu, mcam, blkaddr, ucast_idx); @@ -1001,6 +1094,13 @@ void rvu_npc_enable_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf, index = npc_get_nixlf_mcam_index(mcam, pcifunc, nixlf, NIXLF_ALLMULTI_ENTRY); + if (index < 0) { + dev_err(rvu->dev, + "%s: Error to get mcast entry for pcifunc=%#x\n", + __func__, pcifunc); + return; + } + npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable); } @@ -1113,8 +1213,12 @@ void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf, index = mcam_index; } - if (index >= mcam->total_entries) + if (index < 0 || index >= mcam->total_entries) { + dev_err(rvu->dev, + "%s: Invalid mcam index, pcifunc=%#x\n", + __func__, pcifunc); return; + } bank = npc_get_bank(mcam, index); index &= (mcam->banksize - 1); @@ -1158,16 +1262,18 @@ void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf, /* If PF's promiscuous entry is enabled, * Set RSS action for that entry as well */ - npc_update_rx_action_with_alg_idx(rvu, action, pfvf, index, - blkaddr, alg_idx); + if (index >= 0) + npc_update_rx_action_with_alg_idx(rvu, action, pfvf, index, + blkaddr, alg_idx); index = npc_get_nixlf_mcam_index(mcam, pcifunc, nixlf, NIXLF_ALLMULTI_ENTRY); /* If PF's allmulti entry is enabled, * Set RSS action for that entry as well */ - npc_update_rx_action_with_alg_idx(rvu, action, pfvf, index, - blkaddr, alg_idx); + if (index >= 0) + npc_update_rx_action_with_alg_idx(rvu, action, pfvf, index, + blkaddr, alg_idx); } } @@ -1180,12 +1286,22 @@ void npc_enadis_default_mce_entry(struct rvu *rvu, u16 pcifunc, int index, blkaddr, mce_idx; struct rvu_pfvf *pfvf; + /* multicast pkt replication is not enabled for AF's VFs & SDP links */ + if (is_lbk_vf(rvu, pcifunc) || is_sdp_pfvf(rvu, pcifunc)) + return; + blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0); if (blkaddr < 0) return; index = npc_get_nixlf_mcam_index(mcam, pcifunc & ~RVU_PFVF_FUNC_MASK, nixlf, type); + if (index < 0) { + dev_err(rvu->dev, + "%s: Error to get entry for pcifunc=%#x, type=%u\n", + __func__, pcifunc, type); + return; + } /* disable MCAM entry when packet replication is not supported by hw */ if (!hw->cap.nix_rx_multicast && !is_vf(pcifunc)) { @@ -1214,6 +1330,10 @@ static void npc_enadis_default_entries(struct rvu *rvu, u16 pcifunc, struct npc_mcam *mcam = &rvu->hw->mcam; int index, blkaddr; + /* only CGX or LBK interfaces have default entries */ + if (is_cn20k(rvu->pdev) && !npc_is_cgx_or_lbk(rvu, pcifunc)) + return; + blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0); if (blkaddr < 0) return; @@ -1223,6 +1343,12 @@ static void npc_enadis_default_entries(struct rvu *rvu, u16 pcifunc, pfvf->nix_rx_intf)) { index = npc_get_nixlf_mcam_index(mcam, pcifunc, nixlf, NIXLF_UCAST_ENTRY); + if (index < 0) { + dev_err(rvu->dev, + "%s: Error to get ucast entry for pcifunc=%#x\n", + __func__, pcifunc); + return; + } npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable); } @@ -2504,33 +2630,58 @@ void npc_mcam_clear_bit(struct npc_mcam *mcam, u16 index) static void npc_mcam_free_all_entries(struct rvu *rvu, struct npc_mcam *mcam, int blkaddr, u16 pcifunc) { + u16 dft_idxs[NPC_DFT_RULE_MAX_ID] = {[0 ... NPC_DFT_RULE_MAX_ID - 1] = USHRT_MAX}; + bool cn20k_dft_rl; u16 index, cntr; int rc; + npc_cn20k_dft_rules_idx_get(rvu, pcifunc, + &dft_idxs[NPC_DFT_RULE_BCAST_ID], + &dft_idxs[NPC_DFT_RULE_MCAST_ID], + &dft_idxs[NPC_DFT_RULE_PROMISC_ID], + &dft_idxs[NPC_DFT_RULE_UCAST_ID]); + /* Scan all MCAM entries and free the ones mapped to 'pcifunc' */ for (index = 0; index < mcam->bmap_entries; index++) { - if (mcam->entry2pfvf_map[index] == pcifunc) { + if (mcam->entry2pfvf_map[index] != pcifunc) + continue; + + cn20k_dft_rl = false; + + if (is_cn20k(rvu->pdev)) { + if (dft_idxs[NPC_DFT_RULE_BCAST_ID] == index || + dft_idxs[NPC_DFT_RULE_MCAST_ID] == index || + dft_idxs[NPC_DFT_RULE_PROMISC_ID] == index || + dft_idxs[NPC_DFT_RULE_UCAST_ID] == index) { + cn20k_dft_rl = true; + } + } + + /* Disable the entry */ + npc_enable_mcam_entry(rvu, mcam, blkaddr, index, false); + + if (!cn20k_dft_rl) { mcam->entry2pfvf_map[index] = NPC_MCAM_INVALID_MAP; /* Free the entry in bitmap */ npc_mcam_clear_bit(mcam, index); - /* Disable the entry */ - npc_enable_mcam_entry(rvu, mcam, blkaddr, index, false); - - /* Update entry2counter mapping */ - cntr = mcam->entry2cntr_map[index]; - if (cntr != NPC_MCAM_INVALID_MAP) - npc_unmap_mcam_entry_and_cntr(rvu, mcam, - blkaddr, index, - cntr); mcam->entry2target_pffunc[index] = 0x0; - if (is_cn20k(rvu->pdev)) { - rc = npc_cn20k_idx_free(rvu, &index, 1); - if (rc) - dev_err(rvu->dev, - "Failed to free mcam idx=%u pcifunc=%#x\n", - index, pcifunc); - } } + + /* Update entry2counter mapping */ + cntr = mcam->entry2cntr_map[index]; + if (cntr != NPC_MCAM_INVALID_MAP) + npc_unmap_mcam_entry_and_cntr(rvu, mcam, + blkaddr, index, + cntr); + + if (!is_cn20k(rvu->pdev) || cn20k_dft_rl) + continue; + + rc = npc_cn20k_idx_free(rvu, &index, 1); + if (rc) + dev_err(rvu->dev, + "Failed to free mcam idx=%u pcifunc=%#x\n", + index, pcifunc); } } @@ -3266,7 +3417,10 @@ int rvu_mbox_handler_npc_mcam_shift_entry(struct rvu *rvu, npc_enable_mcam_entry(rvu, mcam, blkaddr, new_entry, false); /* Copy rule from old entry to new entry */ - npc_copy_mcam_entry(rvu, mcam, blkaddr, old_entry, new_entry); + if (npc_copy_mcam_entry(rvu, mcam, blkaddr, old_entry, new_entry)) { + rc = NPC_MCAM_INVALID_REQ; + break; + } /* Copy counter mapping, if any */ cntr = mcam->entry2cntr_map[old_entry]; @@ -3284,7 +3438,8 @@ int rvu_mbox_handler_npc_mcam_shift_entry(struct rvu *rvu, /* If shift has failed then report the failed index */ if (index != req->shift_count) { - rc = NPC_MCAM_PERM_DENIED; + if (!rc) + rc = NPC_MCAM_PERM_DENIED; rsp->failed_entry_idx = index; } @@ -3851,6 +4006,12 @@ int rvu_mbox_handler_npc_read_base_steer_rule(struct rvu *rvu, /* Read the default ucast entry if there is no pkt steering rule */ index = npc_get_nixlf_mcam_index(mcam, pcifunc, nixlf, NIXLF_UCAST_ENTRY); + if (index < 0) { + mutex_unlock(&mcam->lock); + rc = NIX_AF_ERR_AF_LF_INVALID; + goto out; + } + read_entry: /* Read the mcam entry */ npc_read_mcam_entry(rvu, mcam, blkaddr, index, &rsp->entry, &intf, @@ -3924,6 +4085,12 @@ void rvu_npc_clear_ucast_entry(struct rvu *rvu, int pcifunc, int nixlf) ucast_idx = npc_get_nixlf_mcam_index(mcam, pcifunc, nixlf, NIXLF_UCAST_ENTRY); + if (ucast_idx < 0) { + dev_err(rvu->dev, + "%s: Error to get ucast entry for pcifunc=%#x\n", + __func__, pcifunc); + return; + } npc_enable_mcam_entry(rvu, mcam, blkaddr, ucast_idx, false); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c index b45798d9fdab..6ae9cdcb608b 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c @@ -1444,7 +1444,7 @@ static int npc_install_flow(struct rvu *rvu, int blkaddr, u16 target, struct msg_rsp write_rsp; struct mcam_entry *entry; bool new = false; - u16 entry_index; + int entry_index; int err; installed_features = req->features; @@ -1477,6 +1477,14 @@ static int npc_install_flow(struct rvu *rvu, int blkaddr, u16 target, if (req->default_rule) { entry_index = npc_get_nixlf_mcam_index(mcam, target, nixlf, NIXLF_UCAST_ENTRY); + + if (entry_index < 0) { + dev_err(rvu->dev, + "%s: Error to get ucast entry for target=%#x\n", + __func__, target); + return -EINVAL; + } + enable = is_mcam_entry_enabled(rvu, mcam, blkaddr, entry_index); } @@ -1980,13 +1988,15 @@ static int npc_update_dmac_value(struct rvu *rvu, int npcblkaddr, ether_addr_copy(rule->packet.dmac, pfvf->mac_addr); - if (is_cn20k(rvu->pdev)) - npc_cn20k_read_mcam_entry(rvu, npcblkaddr, rule->entry, - cn20k_entry, &intf, - &enable, &hw_prio); - else + if (is_cn20k(rvu->pdev)) { + if (npc_cn20k_read_mcam_entry(rvu, npcblkaddr, rule->entry, + cn20k_entry, &intf, + &enable, &hw_prio)) + return -EINVAL; + } else { npc_read_mcam_entry(rvu, mcam, npcblkaddr, rule->entry, entry, &intf, &enable); + } npc_update_entry(rvu, NPC_DMAC, &mdata, ether_addr_to_u64(pfvf->mac_addr), 0, @@ -2038,8 +2048,12 @@ void npc_mcam_enable_flows(struct rvu *rvu, u16 target) continue; } - if (rule->vfvlan_cfg) - npc_update_dmac_value(rvu, blkaddr, rule, pfvf); + if (rule->vfvlan_cfg) { + if (npc_update_dmac_value(rvu, blkaddr, rule, pfvf)) + dev_err(rvu->dev, + "Update dmac failed for %u, target=%#x\n", + rule->entry, target); + } if (rule->rx_action.op == NIX_RX_ACTION_DEFAULT) { if (!def_ucast_rule) diff --git a/drivers/net/ethernet/mellanox/mlx4/srq.c b/drivers/net/ethernet/mellanox/mlx4/srq.c index dd890f5d7b72..8711689120f3 100644 --- a/drivers/net/ethernet/mellanox/mlx4/srq.c +++ b/drivers/net/ethernet/mellanox/mlx4/srq.c @@ -44,13 +44,14 @@ void mlx4_srq_event(struct mlx4_dev *dev, u32 srqn, int event_type) { struct mlx4_srq_table *srq_table = &mlx4_priv(dev)->srq_table; struct mlx4_srq *srq; + unsigned long flags; - rcu_read_lock(); + spin_lock_irqsave(&srq_table->lock, flags); srq = radix_tree_lookup(&srq_table->tree, srqn & (dev->caps.num_srqs - 1)); - rcu_read_unlock(); - if (srq) - refcount_inc(&srq->refcount); - else { + if (!srq || !refcount_inc_not_zero(&srq->refcount)) + srq = NULL; + spin_unlock_irqrestore(&srq_table->lock, flags); + if (!srq) { mlx4_warn(dev, "Async event for bogus SRQ %08x\n", srqn); return; } @@ -203,8 +204,8 @@ int mlx4_srq_alloc(struct mlx4_dev *dev, u32 pdn, u32 cqn, u16 xrcd, if (err) goto err_radix; - refcount_set(&srq->refcount, 1); init_completion(&srq->free); + refcount_set_release(&srq->refcount, 1); return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.c index 6a50b6dec0fa..d9adb993e64d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.c @@ -1070,29 +1070,37 @@ static struct psp_dev_ops mlx5_psp_ops = { void mlx5e_psp_unregister(struct mlx5e_priv *priv) { - if (!priv->psp || !priv->psp->psp) + struct mlx5e_psp *psp = priv->psp; + + if (!psp || !psp->psp) return; - psp_dev_unregister(priv->psp->psp); + psp_dev_unregister(psp->psp); + psp->psp = NULL; } void mlx5e_psp_register(struct mlx5e_priv *priv) { + struct mlx5e_psp *psp = priv->psp; + struct psp_dev *psd; + /* FW Caps missing */ if (!priv->psp) return; - priv->psp->caps.assoc_drv_spc = sizeof(u32); - priv->psp->caps.versions = 1 << PSP_VERSION_HDR0_AES_GCM_128; + psp->caps.assoc_drv_spc = sizeof(u32); + psp->caps.versions = 1 << PSP_VERSION_HDR0_AES_GCM_128; if (MLX5_CAP_PSP(priv->mdev, psp_crypto_esp_aes_gcm_256_encrypt) && MLX5_CAP_PSP(priv->mdev, psp_crypto_esp_aes_gcm_256_decrypt)) - priv->psp->caps.versions |= 1 << PSP_VERSION_HDR0_AES_GCM_256; + psp->caps.versions |= 1 << PSP_VERSION_HDR0_AES_GCM_256; - priv->psp->psp = psp_dev_create(priv->netdev, &mlx5_psp_ops, - &priv->psp->caps, NULL); - if (IS_ERR(priv->psp->psp)) + psd = psp_dev_create(priv->netdev, &mlx5_psp_ops, &psp->caps, NULL); + if (IS_ERR(psd)) { mlx5_core_err(priv->mdev, "PSP failed to register due to %pe\n", - priv->psp->psp); + psd); + return; + } + psp->psp = psd; } int mlx5e_psp_init(struct mlx5e_priv *priv) @@ -1131,22 +1139,18 @@ int mlx5e_psp_init(struct mlx5e_priv *priv) if (!psp) return -ENOMEM; - priv->psp = psp; fs = mlx5e_accel_psp_fs_init(priv); if (IS_ERR(fs)) { err = PTR_ERR(fs); - goto out_err; + kfree(psp); + return err; } psp->fs = fs; + priv->psp = psp; mlx5_core_dbg(priv->mdev, "PSP attached to netdevice\n"); return 0; - -out_err: - priv->psp = NULL; - kfree(psp); - return err; } void mlx5e_psp_cleanup(struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 5a46870c4b74..8f2b3abe0092 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -6023,7 +6023,6 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev, if (take_rtnl) rtnl_lock(); - mlx5e_psp_register(priv); /* update XDP supported features */ mlx5e_set_xdp_feature(priv); @@ -6036,7 +6035,6 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev, static void mlx5e_nic_cleanup(struct mlx5e_priv *priv) { mlx5e_health_destroy_reporters(priv); - mlx5e_psp_unregister(priv); mlx5e_ktls_cleanup(priv); mlx5e_psp_cleanup(priv); mlx5e_fs_cleanup(priv->fs); @@ -6160,6 +6158,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv) mlx5e_fs_init_l2_addr(priv->fs, netdev); mlx5e_ipsec_init(priv); + mlx5e_psp_register(priv); err = mlx5e_macsec_init(priv); if (err) @@ -6230,6 +6229,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv) mlx5_lag_remove_netdev(mdev, priv->netdev); mlx5_vxlan_reset_to_default(mdev->vxlan); mlx5e_macsec_cleanup(priv); + mlx5e_psp_unregister(priv); mlx5e_ipsec_cleanup(priv); } @@ -6774,9 +6774,11 @@ static int mlx5e_resume(struct auxiliary_device *adev) return err; actual_adev = mlx5_sd_get_adev(mdev, adev, edev->idx); - if (actual_adev) - return _mlx5e_resume(actual_adev); - return 0; + if (actual_adev) { + err = _mlx5e_resume(actual_adev); + mlx5_sd_put_adev(actual_adev, adev); + } + return err; } static int _mlx5e_suspend(struct auxiliary_device *adev, bool pre_netdev_reg) @@ -6815,6 +6817,8 @@ static int mlx5e_suspend(struct auxiliary_device *adev, pm_message_t state) err = _mlx5e_suspend(actual_adev, false); mlx5_sd_cleanup(mdev); + if (actual_adev) + mlx5_sd_put_adev(actual_adev, adev); return err; } @@ -6912,9 +6916,19 @@ static int mlx5e_probe(struct auxiliary_device *adev, return err; actual_adev = mlx5_sd_get_adev(mdev, adev, edev->idx); - if (actual_adev) - return _mlx5e_probe(actual_adev); + if (actual_adev) { + err = _mlx5e_probe(actual_adev); + if (err) + goto sd_cleanup; + mlx5_sd_put_adev(actual_adev, adev); + } return 0; + +sd_cleanup: + mlx5_sd_cleanup(mdev); + if (actual_adev) + mlx5_sd_put_adev(actual_adev, adev); + return err; } static void _mlx5e_remove(struct auxiliary_device *adev) @@ -6966,6 +6980,8 @@ static void mlx5e_remove(struct auxiliary_device *adev) _mlx5e_remove(actual_adev); mlx5_sd_cleanup(mdev); + if (actual_adev) + mlx5_sd_put_adev(actual_adev, adev); } static const struct auxiliary_device_id mlx5e_id_table[] = { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c index 762c783156b4..6e199161b008 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c @@ -18,6 +18,7 @@ struct mlx5_sd { u8 host_buses; struct mlx5_devcom_comp_dev *devcom; struct dentry *dfs; + u8 state; bool primary; union { struct { /* primary */ @@ -31,6 +32,11 @@ struct mlx5_sd { }; }; +enum mlx5_sd_state { + MLX5_SD_STATE_DOWN = 0, + MLX5_SD_STATE_UP, +}; + static int mlx5_sd_get_host_buses(struct mlx5_core_dev *dev) { struct mlx5_sd *sd = mlx5_get_sd(dev); @@ -270,9 +276,6 @@ static void sd_unregister(struct mlx5_core_dev *dev) { struct mlx5_sd *sd = mlx5_get_sd(dev); - mlx5_devcom_comp_lock(sd->devcom); - mlx5_devcom_comp_set_ready(sd->devcom, false); - mlx5_devcom_comp_unlock(sd->devcom); mlx5_devcom_unregister_component(sd->devcom); } @@ -426,6 +429,7 @@ int mlx5_sd_init(struct mlx5_core_dev *dev) struct mlx5_core_dev *primary, *pos, *to; struct mlx5_sd *sd = mlx5_get_sd(dev); u8 alias_key[ACCESS_KEY_LEN]; + struct mlx5_sd *primary_sd; int err, i; err = sd_init(dev); @@ -440,10 +444,17 @@ int mlx5_sd_init(struct mlx5_core_dev *dev) if (err) goto err_sd_cleanup; + mlx5_devcom_comp_lock(sd->devcom); if (!mlx5_devcom_comp_is_ready(sd->devcom)) - return 0; + goto out; primary = mlx5_sd_get_primary(dev); + if (!primary) + goto out; + + primary_sd = mlx5_get_sd(primary); + if (primary_sd->state != MLX5_SD_STATE_DOWN) + goto out; for (i = 0; i < ACCESS_KEY_LEN; i++) alias_key[i] = get_random_u8(); @@ -452,9 +463,13 @@ int mlx5_sd_init(struct mlx5_core_dev *dev) if (err) goto err_sd_unregister; - sd->dfs = debugfs_create_dir("multi-pf", mlx5_debugfs_get_dev_root(primary)); - debugfs_create_x32("group_id", 0400, sd->dfs, &sd->group_id); - debugfs_create_file("primary", 0400, sd->dfs, primary, &dev_fops); + primary_sd->dfs = + debugfs_create_dir("multi-pf", + mlx5_debugfs_get_dev_root(primary)); + debugfs_create_x32("group_id", 0400, primary_sd->dfs, + &primary_sd->group_id); + debugfs_create_file("primary", 0400, primary_sd->dfs, primary, + &dev_fops); mlx5_sd_for_each_secondary(i, primary, pos) { char name[32]; @@ -464,7 +479,8 @@ int mlx5_sd_init(struct mlx5_core_dev *dev) goto err_unset_secondaries; snprintf(name, sizeof(name), "secondary_%d", i - 1); - debugfs_create_file(name, 0400, sd->dfs, pos, &dev_fops); + debugfs_create_file(name, 0400, primary_sd->dfs, pos, + &dev_fops); } @@ -472,6 +488,9 @@ int mlx5_sd_init(struct mlx5_core_dev *dev) sd->group_id, mlx5_devcom_comp_get_size(sd->devcom)); sd_print_group(primary); + primary_sd->state = MLX5_SD_STATE_UP; +out: + mlx5_devcom_comp_unlock(sd->devcom); return 0; err_unset_secondaries: @@ -479,8 +498,18 @@ err_unset_secondaries: mlx5_sd_for_each_secondary_to(i, primary, to, pos) sd_cmd_unset_secondary(pos); sd_cmd_unset_primary(primary); - debugfs_remove_recursive(sd->dfs); + debugfs_remove_recursive(primary_sd->dfs); + primary_sd->dfs = NULL; err_sd_unregister: + mlx5_sd_for_each_secondary(i, primary, pos) { + struct mlx5_sd *peer_sd = mlx5_get_sd(pos); + + primary_sd->secondaries[i - 1] = NULL; + peer_sd->primary_dev = NULL; + } + primary_sd->primary = false; + mlx5_devcom_comp_set_ready(sd->devcom, false); + mlx5_devcom_comp_unlock(sd->devcom); sd_unregister(dev); err_sd_cleanup: sd_cleanup(dev); @@ -491,42 +520,97 @@ void mlx5_sd_cleanup(struct mlx5_core_dev *dev) { struct mlx5_sd *sd = mlx5_get_sd(dev); struct mlx5_core_dev *primary, *pos; + struct mlx5_sd *primary_sd; int i; if (!sd) return; + mlx5_devcom_comp_lock(sd->devcom); if (!mlx5_devcom_comp_is_ready(sd->devcom)) - goto out; + goto out_unlock; primary = mlx5_sd_get_primary(dev); + if (!primary) + goto out_ready_false; + + primary_sd = mlx5_get_sd(primary); + if (primary_sd->state != MLX5_SD_STATE_UP) + goto out_clear_peers; + mlx5_sd_for_each_secondary(i, primary, pos) sd_cmd_unset_secondary(pos); sd_cmd_unset_primary(primary); - debugfs_remove_recursive(sd->dfs); + debugfs_remove_recursive(primary_sd->dfs); + primary_sd->dfs = NULL; sd_info(primary, "group id %#x, uncombined\n", sd->group_id); -out: + primary_sd->state = MLX5_SD_STATE_DOWN; +out_clear_peers: + mlx5_sd_for_each_secondary(i, primary, pos) { + struct mlx5_sd *peer_sd = mlx5_get_sd(pos); + + primary_sd->secondaries[i - 1] = NULL; + peer_sd->primary_dev = NULL; + } + primary_sd->primary = false; +out_ready_false: + mlx5_devcom_comp_set_ready(sd->devcom, false); +out_unlock: + mlx5_devcom_comp_unlock(sd->devcom); sd_unregister(dev); sd_cleanup(dev); } +/* Lock order: + * primary: actual_adev_lock -> SD devcom comp lock + * secondary: SD devcom comp lock -> (drop) -> actual_adev_lock + * The two locks are never held together, so no ABBA. + */ struct auxiliary_device *mlx5_sd_get_adev(struct mlx5_core_dev *dev, struct auxiliary_device *adev, int idx) { struct mlx5_sd *sd = mlx5_get_sd(dev); struct mlx5_core_dev *primary; + struct mlx5_adev *primary_adev; if (!sd) return adev; - if (!mlx5_devcom_comp_is_ready(sd->devcom)) + mlx5_devcom_comp_lock(sd->devcom); + if (!mlx5_devcom_comp_is_ready(sd->devcom)) { + mlx5_devcom_comp_unlock(sd->devcom); return NULL; + } primary = mlx5_sd_get_primary(dev); - if (dev == primary) + if (!primary || dev == primary) { + mlx5_devcom_comp_unlock(sd->devcom); return adev; + } + + primary_adev = primary->priv.adev[idx]; + get_device(&primary_adev->adev.dev); + mlx5_devcom_comp_unlock(sd->devcom); + + device_lock(&primary_adev->adev.dev); + /* Primary may have completed remove between dropping devcom and + * acquiring device_lock; recheck. + */ + if (!mlx5_devcom_comp_is_ready(sd->devcom)) { + device_unlock(&primary_adev->adev.dev); + put_device(&primary_adev->adev.dev); + return NULL; + } + return &primary_adev->adev; +} - return &primary->priv.adev[idx]->adev; +void mlx5_sd_put_adev(struct auxiliary_device *actual_adev, + struct auxiliary_device *adev) +{ + if (actual_adev != adev) { + device_unlock(&actual_adev->dev); + put_device(&actual_adev->dev); + } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.h index 137efaf9aabc..9bfd5b9756b5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.h @@ -15,6 +15,8 @@ struct mlx5_core_dev *mlx5_sd_ch_ix_get_dev(struct mlx5_core_dev *primary, int c struct auxiliary_device *mlx5_sd_get_adev(struct mlx5_core_dev *dev, struct auxiliary_device *adev, int idx); +void mlx5_sd_put_adev(struct auxiliary_device *actual_adev, + struct auxiliary_device *adev); int mlx5_sd_init(struct mlx5_core_dev *dev); void mlx5_sd_cleanup(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c index c406a3b56b37..4dea2bb58d2f 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c @@ -826,7 +826,8 @@ struct net_device *fbnic_netdev_alloc(struct fbnic_dev *fbd) netif_tx_stop_all_queues(netdev); if (fbnic_phylink_create(netdev)) { - fbnic_netdev_free(fbd); + free_netdev(netdev); + fbd->netdev = NULL; return NULL; } diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h index 6a745bb71b5c..eb57b86fbe22 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h @@ -31,11 +31,11 @@ enum spx5_target_chiptype { SPX5_TARGET_CT_7552 = 0x7552, /* SparX-5-128 Enterprise */ SPX5_TARGET_CT_7556 = 0x7556, /* SparX-5-160 Enterprise */ SPX5_TARGET_CT_7558 = 0x7558, /* SparX-5-200 Enterprise */ - SPX5_TARGET_CT_7546TSN = 0x47546, /* SparX-5-64i Industrial */ - SPX5_TARGET_CT_7549TSN = 0x47549, /* SparX-5-90i Industrial */ - SPX5_TARGET_CT_7552TSN = 0x47552, /* SparX-5-128i Industrial */ - SPX5_TARGET_CT_7556TSN = 0x47556, /* SparX-5-160i Industrial */ - SPX5_TARGET_CT_7558TSN = 0x47558, /* SparX-5-200i Industrial */ + SPX5_TARGET_CT_7546TSN = 0x0546, /* SparX-5-64i Industrial */ + SPX5_TARGET_CT_7549TSN = 0x0549, /* SparX-5-90i Industrial */ + SPX5_TARGET_CT_7552TSN = 0x0552, /* SparX-5-128i Industrial */ + SPX5_TARGET_CT_7556TSN = 0x0556, /* SparX-5-160i Industrial */ + SPX5_TARGET_CT_7558TSN = 0x0558, /* SparX-5-200i Industrial */ SPX5_TARGET_CT_LAN9694 = 0x9694, /* lan969x-40 */ SPX5_TARGET_CT_LAN9691VAO = 0x9691, /* lan969x-40-VAO */ SPX5_TARGET_CT_LAN9694TSN = 0x9695, /* lan969x-40-TSN */ diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_port.c b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c index 04bc8fffaf96..62c49893de3c 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_port.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c @@ -1128,7 +1128,8 @@ int sparx5_port_init(struct sparx5 *sparx5, DEV2G5_PCS1G_SD_CFG(port->portno)); if (conf->portmode == PHY_INTERFACE_MODE_QSGMII || - conf->portmode == PHY_INTERFACE_MODE_SGMII) { + conf->portmode == PHY_INTERFACE_MODE_SGMII || + conf->portmode == PHY_INTERFACE_MODE_1000BASEX) { err = sparx5_serdes_set(sparx5, port, conf); if (err) return err; diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index 098fbda0d128..d8e816882f02 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -43,8 +43,9 @@ static u64 mana_gd_r64(struct gdma_context *g, u64 offset) static int mana_gd_init_pf_regs(struct pci_dev *pdev) { struct gdma_context *gc = pci_get_drvdata(pdev); - void __iomem *sriov_base_va; + u64 remaining_barsize; u64 sriov_base_off; + u64 sriov_shm_off; gc->db_page_size = mana_gd_r32(gc, GDMA_PF_REG_DB_PAGE_SIZE) & 0xFFFF; @@ -73,10 +74,28 @@ static int mana_gd_init_pf_regs(struct pci_dev *pdev) gc->phys_db_page_base = gc->bar0_pa + gc->db_page_off; sriov_base_off = mana_gd_r64(gc, GDMA_SRIOV_REG_CFG_BASE_OFF); + if (sriov_base_off >= gc->bar0_size || + gc->bar0_size - sriov_base_off < + GDMA_PF_REG_SHM_OFF + sizeof(u64) || + !IS_ALIGNED(sriov_base_off, sizeof(u64))) { + dev_err(gc->dev, + "SRIOV base offset 0x%llx out of range or unaligned (BAR0 size 0x%llx)\n", + sriov_base_off, (u64)gc->bar0_size); + return -EPROTO; + } - sriov_base_va = gc->bar0_va + sriov_base_off; - gc->shm_base = sriov_base_va + - mana_gd_r64(gc, sriov_base_off + GDMA_PF_REG_SHM_OFF); + remaining_barsize = gc->bar0_size - sriov_base_off; + sriov_shm_off = mana_gd_r64(gc, sriov_base_off + GDMA_PF_REG_SHM_OFF); + if (sriov_shm_off >= remaining_barsize || + remaining_barsize - sriov_shm_off < SMC_APERTURE_SIZE || + !IS_ALIGNED(sriov_shm_off, sizeof(u32))) { + dev_err(gc->dev, + "SRIOV SHM offset 0x%llx out of range or unaligned (BAR0 size 0x%llx)\n", + sriov_shm_off, (u64)gc->bar0_size); + return -EPROTO; + } + + gc->shm_base = gc->bar0_va + sriov_base_off + sriov_shm_off; return 0; } @@ -84,6 +103,7 @@ static int mana_gd_init_pf_regs(struct pci_dev *pdev) static int mana_gd_init_vf_regs(struct pci_dev *pdev) { struct gdma_context *gc = pci_get_drvdata(pdev); + u64 shm_off; gc->db_page_size = mana_gd_r32(gc, GDMA_REG_DB_PAGE_SIZE) & 0xFFFF; @@ -111,7 +131,17 @@ static int mana_gd_init_vf_regs(struct pci_dev *pdev) gc->db_page_base = gc->bar0_va + gc->db_page_off; gc->phys_db_page_base = gc->bar0_pa + gc->db_page_off; - gc->shm_base = gc->bar0_va + mana_gd_r64(gc, GDMA_REG_SHM_OFFSET); + shm_off = mana_gd_r64(gc, GDMA_REG_SHM_OFFSET); + if (shm_off >= gc->bar0_size || + gc->bar0_size - shm_off < SMC_APERTURE_SIZE || + !IS_ALIGNED(shm_off, sizeof(u32))) { + dev_err(gc->dev, + "SHM offset 0x%llx out of range or unaligned (BAR0 size 0x%llx)\n", + shm_off, (u64)gc->bar0_size); + return -EPROTO; + } + + gc->shm_base = gc->bar0_va + shm_off; return 0; } diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index a654b3699c4c..9afc786b297a 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -2520,9 +2520,12 @@ static void mana_destroy_rxq(struct mana_port_context *apc, napi_disable_locked(napi); netif_napi_del_locked(napi); } - xdp_rxq_info_unreg(&rxq->xdp_rxq); - mana_destroy_wq_obj(apc, GDMA_RQ, rxq->rxobj); + if (xdp_rxq_info_is_reg(&rxq->xdp_rxq)) + xdp_rxq_info_unreg(&rxq->xdp_rxq); + + if (rxq->rxobj != INVALID_MANA_HANDLE) + mana_destroy_wq_obj(apc, GDMA_RQ, rxq->rxobj); mana_deinit_cq(apc, &rxq->rx_cq); @@ -2796,9 +2799,6 @@ out: mana_destroy_rxq(apc, rxq, false); - if (cq) - mana_deinit_cq(apc, cq); - return NULL; } diff --git a/drivers/net/ethernet/microsoft/mana/shm_channel.c b/drivers/net/ethernet/microsoft/mana/shm_channel.c index 0f1679ebad96..d21b5db06e50 100644 --- a/drivers/net/ethernet/microsoft/mana/shm_channel.c +++ b/drivers/net/ethernet/microsoft/mana/shm_channel.c @@ -61,11 +61,6 @@ union smc_proto_hdr { }; }; /* HW DATA */ -#define SMC_APERTURE_BITS 256 -#define SMC_BASIC_UNIT (sizeof(u32)) -#define SMC_APERTURE_DWORDS (SMC_APERTURE_BITS / (SMC_BASIC_UNIT * 8)) -#define SMC_LAST_DWORD (SMC_APERTURE_DWORDS - 1) - static int mana_smc_poll_register(void __iomem *base, bool reset) { void __iomem *ptr = base + SMC_LAST_DWORD * SMC_BASIC_UNIT; diff --git a/drivers/net/ethernet/renesas/rtsn.c b/drivers/net/ethernet/renesas/rtsn.c index 03a2669f0518..ee8381b60b8d 100644 --- a/drivers/net/ethernet/renesas/rtsn.c +++ b/drivers/net/ethernet/renesas/rtsn.c @@ -797,11 +797,11 @@ static int rtsn_mdio_alloc(struct rtsn_private *priv) /* Enter config mode before registering the MDIO bus */ ret = rtsn_reset(priv); if (ret) - goto out_free_bus; + goto out_put_node; ret = rtsn_change_mode(priv, OCR_OPC_CONFIG); if (ret) - goto out_free_bus; + goto out_put_node; rtsn_modify(priv, MPIC, MPIC_PSMCS_MASK | MPIC_PSMHT_MASK, MPIC_PSMCS_DEFAULT | MPIC_PSMHT_DEFAULT); @@ -824,6 +824,8 @@ static int rtsn_mdio_alloc(struct rtsn_private *priv) return 0; +out_put_node: + of_node_put(mdio_node); out_free_bus: mdiobus_free(mii); return ret; diff --git a/drivers/net/ethernet/sfc/efx_devlink.c b/drivers/net/ethernet/sfc/efx_devlink.c index d842c60dfc10..e5c6f81af48b 100644 --- a/drivers/net/ethernet/sfc/efx_devlink.c +++ b/drivers/net/ethernet/sfc/efx_devlink.c @@ -531,7 +531,7 @@ static int efx_devlink_info_running_versions(struct efx_nic *efx, if (rc || outlength < MC_CMD_GET_VERSION_OUT_LEN) { netif_err(efx, drv, efx->net_dev, "mcdi MC_CMD_GET_VERSION failed\n"); - return rc; + return rc ?: -EIO; } /* Handle previous output */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-nuvoton.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-nuvoton.c index e2240b68ad98..2ab6ecac6422 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-nuvoton.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-nuvoton.c @@ -100,6 +100,8 @@ static int nvt_gmac_probe(struct platform_device *pdev) if (!priv) return dev_err_probe(dev, -ENOMEM, "Failed to allocate private data\n"); + priv->dev = dev; + priv->regmap = syscon_regmap_lookup_by_phandle_args(dev->of_node, "nuvoton,sys", 1, &priv->macid); if (IS_ERR(priv->regmap)) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index ca68248dbc78..3591755ea30b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -5549,9 +5549,12 @@ read_again: break; /* Prefetch the next RX descriptor */ - rx_q->cur_rx = STMMAC_NEXT_ENTRY(rx_q->cur_rx, - priv->dma_conf.dma_rx_size); - next_entry = rx_q->cur_rx; + next_entry = STMMAC_NEXT_ENTRY(rx_q->cur_rx, + priv->dma_conf.dma_rx_size); + if (unlikely(next_entry == rx_q->dirty_rx)) + break; + + rx_q->cur_rx = next_entry; np = stmmac_get_rx_desc(priv, rx_q, next_entry); @@ -5686,7 +5689,6 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) dma_dir = page_pool_get_dma_dir(rx_q->page_pool); bufsz = DIV_ROUND_UP(priv->dma_conf.dma_buf_sz, PAGE_SIZE) * PAGE_SIZE; - limit = min(priv->dma_conf.dma_rx_size - 1, (unsigned int)limit); if (netif_msg_rx_status(priv)) { void *rx_head = stmmac_get_rx_desc(priv, rx_q, 0); @@ -5733,9 +5735,12 @@ read_again: if (unlikely(status & dma_own)) break; - rx_q->cur_rx = STMMAC_NEXT_ENTRY(rx_q->cur_rx, - priv->dma_conf.dma_rx_size); - next_entry = rx_q->cur_rx; + next_entry = STMMAC_NEXT_ENTRY(rx_q->cur_rx, + priv->dma_conf.dma_rx_size); + if (unlikely(next_entry == rx_q->dirty_rx)) + break; + + rx_q->cur_rx = next_entry; np = stmmac_get_rx_desc(priv, rx_q, next_entry); diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c index d3772d01e00b..2451f6b20b11 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c @@ -2480,8 +2480,11 @@ int wx_sw_init(struct wx *wx) wx->oem_svid = pdev->subsystem_vendor; wx->oem_ssid = pdev->subsystem_device; wx->bus.device = PCI_SLOT(pdev->devfn); - wx->bus.func = FIELD_GET(WX_CFG_PORT_ST_LANID, - rd32(wx, WX_CFG_PORT_ST)); + if (pdev->is_virtfn) + wx->bus.func = PCI_FUNC(pdev->devfn); + else + wx->bus.func = FIELD_GET(WX_CFG_PORT_ST_LANID, + rd32(wx, WX_CFG_PORT_ST)); if (wx->oem_svid == PCI_VENDOR_ID_WANGXUN || pdev->is_virtfn) { diff --git a/drivers/net/ethernet/wangxun/libwx/wx_vf_common.c b/drivers/net/ethernet/wangxun/libwx/wx_vf_common.c index 29cdbed2e5ec..94ff8f5f0b4c 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_vf_common.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_vf_common.c @@ -99,8 +99,8 @@ int wx_request_msix_irqs_vf(struct wx *wx) } } - err = request_threaded_irq(wx->msix_entry->vector, wx_msix_misc_vf, - NULL, IRQF_ONESHOT, netdev->name, wx); + err = request_irq(wx->msix_entry->vector, wx_msix_misc_vf, + 0, netdev->name, wx); if (err) { wx_err(wx, "request_irq for msix_other failed: %d\n", err); goto free_queue_irqs; diff --git a/drivers/net/mctp/mctp-i2c.c b/drivers/net/mctp/mctp-i2c.c index 15fe4d1163c1..ee2913758e54 100644 --- a/drivers/net/mctp/mctp-i2c.c +++ b/drivers/net/mctp/mctp-i2c.c @@ -496,8 +496,6 @@ static void mctp_i2c_xmit(struct mctp_i2c_dev *midev, struct sk_buff *skb) u8 *pecp; int rc; - fs = mctp_i2c_get_tx_flow_state(midev, skb); - hdr = (void *)skb_mac_header(skb); /* Sanity check that packet contents matches skb length, * and can't exceed MCTP_I2C_BUFSZ @@ -509,6 +507,8 @@ static void mctp_i2c_xmit(struct mctp_i2c_dev *midev, struct sk_buff *skb) return; } + fs = mctp_i2c_get_tx_flow_state(midev, skb); + if (skb_tailroom(skb) >= 1) { /* Linear case with space, we can just append the PEC */ skb_put(skb, 1); diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index 205384dab89a..57dd6821a8aa 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -752,7 +752,7 @@ static ssize_t enabled_store(struct config_item *item, unregister_netcons_consoles(); } - ret = strnlen(buf, count); + ret = count; /* Deferred cleanup */ netconsole_process_cleanups(); out_unlock: @@ -781,7 +781,7 @@ static ssize_t release_store(struct config_item *item, const char *buf, nt->release = release; - ret = strnlen(buf, count); + ret = count; out_unlock: dynamic_netconsole_mutex_unlock(); return ret; @@ -807,7 +807,7 @@ static ssize_t extended_store(struct config_item *item, const char *buf, goto out_unlock; nt->extended = extended; - ret = strnlen(buf, count); + ret = count; out_unlock: dynamic_netconsole_mutex_unlock(); return ret; @@ -817,6 +817,13 @@ static ssize_t dev_name_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); + size_t len = count; + + /* Account for a trailing newline appended by tools like echo */ + if (len && buf[len - 1] == '\n') + len--; + if (len >= IFNAMSIZ) + return -ENAMETOOLONG; dynamic_netconsole_mutex_lock(); if (nt->state == STATE_ENABLED) { @@ -830,7 +837,7 @@ static ssize_t dev_name_store(struct config_item *item, const char *buf, trim_newline(nt->np.dev_name, IFNAMSIZ); dynamic_netconsole_mutex_unlock(); - return strnlen(buf, count); + return count; } static ssize_t local_port_store(struct config_item *item, const char *buf, @@ -849,7 +856,7 @@ static ssize_t local_port_store(struct config_item *item, const char *buf, ret = kstrtou16(buf, 10, &nt->np.local_port); if (ret < 0) goto out_unlock; - ret = strnlen(buf, count); + ret = count; out_unlock: dynamic_netconsole_mutex_unlock(); return ret; @@ -871,7 +878,7 @@ static ssize_t remote_port_store(struct config_item *item, ret = kstrtou16(buf, 10, &nt->np.remote_port); if (ret < 0) goto out_unlock; - ret = strnlen(buf, count); + ret = count; out_unlock: dynamic_netconsole_mutex_unlock(); return ret; @@ -896,7 +903,7 @@ static ssize_t local_ip_store(struct config_item *item, const char *buf, goto out_unlock; nt->np.ipv6 = !!ipv6; - ret = strnlen(buf, count); + ret = count; out_unlock: dynamic_netconsole_mutex_unlock(); return ret; @@ -921,7 +928,7 @@ static ssize_t remote_ip_store(struct config_item *item, const char *buf, goto out_unlock; nt->np.ipv6 = !!ipv6; - ret = strnlen(buf, count); + ret = count; out_unlock: dynamic_netconsole_mutex_unlock(); return ret; @@ -957,7 +964,7 @@ static ssize_t remote_mac_store(struct config_item *item, const char *buf, goto out_unlock; memcpy(nt->np.remote_mac, remote_mac, ETH_ALEN); - ret = strnlen(buf, count); + ret = count; out_unlock: dynamic_netconsole_mutex_unlock(); return ret; @@ -1072,26 +1079,30 @@ static ssize_t userdatum_value_store(struct config_item *item, const char *buf, size_t count) { struct userdatum *udm = to_userdatum(item); + char old_value[MAX_EXTRADATA_VALUE_LEN]; struct netconsole_target *nt; struct userdata *ud; ssize_t ret; - if (count > MAX_EXTRADATA_VALUE_LEN) + if (count >= MAX_EXTRADATA_VALUE_LEN) return -EMSGSIZE; mutex_lock(&netconsole_subsys.su_mutex); dynamic_netconsole_mutex_lock(); - - ret = strscpy(udm->value, buf, sizeof(udm->value)); - if (ret < 0) - goto out_unlock; + /* Snapshot for rollback if update_userdata() fails below */ + strscpy(old_value, udm->value, sizeof(old_value)); + /* count is bounded above, so strscpy() cannot truncate here */ + strscpy(udm->value, buf, sizeof(udm->value)); trim_newline(udm->value, sizeof(udm->value)); ud = to_userdata(item->ci_parent); nt = userdata_to_target(ud); ret = update_userdata(nt); - if (ret < 0) + if (ret < 0) { + /* Restore the previous value so it matches the live payload */ + strscpy(udm->value, old_value, sizeof(udm->value)); goto out_unlock; + } ret = count; out_unlock: dynamic_netconsole_mutex_unlock(); @@ -1133,7 +1144,7 @@ static ssize_t sysdata_msgid_enabled_store(struct config_item *item, disable_sysdata_feature(nt, SYSDATA_MSGID); unlock_ok: - ret = strnlen(buf, count); + ret = count; dynamic_netconsole_mutex_unlock(); mutex_unlock(&netconsole_subsys.su_mutex); return ret; @@ -1162,7 +1173,7 @@ static ssize_t sysdata_release_enabled_store(struct config_item *item, disable_sysdata_feature(nt, SYSDATA_RELEASE); unlock_ok: - ret = strnlen(buf, count); + ret = count; dynamic_netconsole_mutex_unlock(); mutex_unlock(&netconsole_subsys.su_mutex); return ret; @@ -1191,7 +1202,7 @@ static ssize_t sysdata_taskname_enabled_store(struct config_item *item, disable_sysdata_feature(nt, SYSDATA_TASKNAME); unlock_ok: - ret = strnlen(buf, count); + ret = count; dynamic_netconsole_mutex_unlock(); mutex_unlock(&netconsole_subsys.su_mutex); return ret; @@ -1225,7 +1236,7 @@ static ssize_t sysdata_cpu_nr_enabled_store(struct config_item *item, disable_sysdata_feature(nt, SYSDATA_CPU_NR); unlock_ok: - ret = strnlen(buf, count); + ret = count; dynamic_netconsole_mutex_unlock(); mutex_unlock(&netconsole_subsys.su_mutex); return ret; diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index 1e06e781c835..f00fc2f9ebde 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -829,7 +829,7 @@ static struct sk_buff *nsim_dev_trap_skb_build(void) skb->protocol = htons(ETH_P_IP); skb_set_network_header(skb, skb->len); - iph = skb_put(skb, sizeof(struct iphdr)); + iph = skb_put_zero(skb, sizeof(struct iphdr)); iph->protocol = IPPROTO_UDP; iph->saddr = in_aton("192.0.2.1"); iph->daddr = in_aton("198.51.100.1"); diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index a05af192caf3..a750768912b5 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -1182,7 +1182,8 @@ void nsim_destroy(struct netdevsim *ns) unregister_netdevice_notifier_dev_net(ns->netdev, &ns->nb, &ns->nn); - nsim_psp_uninit(ns); + if (nsim_dev_port_is_pf(ns->nsim_dev_port)) + nsim_psp_uninit(ns); rtnl_lock(); peer = rtnl_dereference(ns->peer); diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index 7e129dddbbe7..d909c4160ea1 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -120,7 +120,9 @@ struct netdevsim { u64_stats_t tx_packets; u64_stats_t tx_bytes; struct u64_stats_sync syncp; - struct psp_dev *dev; + struct psp_dev __rcu *dev; + struct dentry *rereg; + struct mutex rereg_lock; u32 spi; u32 assoc_cnt; } psp; diff --git a/drivers/net/netdevsim/psp.c b/drivers/net/netdevsim/psp.c index 0b4d717253b0..6936ecb8173e 100644 --- a/drivers/net/netdevsim/psp.c +++ b/drivers/net/netdevsim/psp.c @@ -19,6 +19,7 @@ nsim_do_psp(struct sk_buff *skb, struct netdevsim *ns, struct netdevsim *peer_ns, struct skb_ext **psp_ext) { enum skb_drop_reason rc = 0; + struct psp_dev *peer_psd; struct psp_assoc *pas; struct net *net; void **ptr; @@ -48,7 +49,8 @@ nsim_do_psp(struct sk_buff *skb, struct netdevsim *ns, } /* Now pretend we just received this frame */ - if (peer_ns->psp.dev->config.versions & (1 << pas->version)) { + peer_psd = rcu_dereference(peer_ns->psp.dev); + if (peer_psd && peer_psd->config.versions & (1 << pas->version)) { bool strip_icv = false; u8 generation; @@ -61,8 +63,7 @@ nsim_do_psp(struct sk_buff *skb, struct netdevsim *ns, skb_ext_reset(skb); skb->mac_len = ETH_HLEN; - if (psp_dev_rcv(skb, peer_ns->psp.dev->id, generation, - strip_icv)) { + if (psp_dev_rcv(skb, peer_psd->id, generation, strip_icv)) { rc = SKB_DROP_REASON_PSP_OUTPUT; goto out_unlock; } @@ -209,26 +210,50 @@ static struct psp_dev_caps nsim_psp_caps = { .assoc_drv_spc = sizeof(void *), }; -void nsim_psp_uninit(struct netdevsim *ns) +static void __nsim_psp_uninit(struct netdevsim *ns, bool teardown) { - if (!IS_ERR(ns->psp.dev)) - psp_dev_unregister(ns->psp.dev); + struct psp_dev *psd; + + psd = rcu_dereference_protected(ns->psp.dev, + teardown || + lockdep_is_held(&ns->psp.rereg_lock)); + if (psd) { + rcu_assign_pointer(ns->psp.dev, NULL); + synchronize_rcu(); + psp_dev_unregister(psd); + } WARN_ON(ns->psp.assoc_cnt); } +void nsim_psp_uninit(struct netdevsim *ns) +{ + debugfs_remove(ns->psp.rereg); + mutex_destroy(&ns->psp.rereg_lock); + __nsim_psp_uninit(ns, true); +} + static ssize_t nsim_psp_rereg_write(struct file *file, const char __user *data, size_t count, loff_t *ppos) { struct netdevsim *ns = file->private_data; - int err; + struct psp_dev *psd; + ssize_t ret; + + mutex_lock(&ns->psp.rereg_lock); + __nsim_psp_uninit(ns, false); - nsim_psp_uninit(ns); + psd = psp_dev_create(ns->netdev, &nsim_psp_ops, &nsim_psp_caps, ns); + if (IS_ERR(psd)) { + ret = PTR_ERR(psd); + goto out; + } - ns->psp.dev = psp_dev_create(ns->netdev, &nsim_psp_ops, - &nsim_psp_caps, ns); - err = PTR_ERR_OR_ZERO(ns->psp.dev); - return err ?: count; + rcu_assign_pointer(ns->psp.dev, psd); + ret = count; +out: + mutex_unlock(&ns->psp.rereg_lock); + return ret; } static const struct file_operations nsim_psp_rereg_fops = { @@ -241,14 +266,16 @@ static const struct file_operations nsim_psp_rereg_fops = { int nsim_psp_init(struct netdevsim *ns) { struct dentry *ddir = ns->nsim_dev_port->ddir; - int err; + struct psp_dev *psd; + + psd = psp_dev_create(ns->netdev, &nsim_psp_ops, &nsim_psp_caps, ns); + if (IS_ERR(psd)) + return PTR_ERR(psd); - ns->psp.dev = psp_dev_create(ns->netdev, &nsim_psp_ops, - &nsim_psp_caps, ns); - err = PTR_ERR_OR_ZERO(ns->psp.dev); - if (err) - return err; + rcu_assign_pointer(ns->psp.dev, psd); - debugfs_create_file("psp_rereg", 0200, ddir, ns, &nsim_psp_rereg_fops); + mutex_init(&ns->psp.rereg_lock); + ns->psp.rereg = debugfs_create_file("psp_rereg", 0200, ddir, ns, + &nsim_psp_rereg_fops); return 0; } diff --git a/drivers/net/ovpn/io.c b/drivers/net/ovpn/io.c index db43a1f8a07a..22c555dd962e 100644 --- a/drivers/net/ovpn/io.c +++ b/drivers/net/ovpn/io.c @@ -85,17 +85,24 @@ static void ovpn_netdev_write(struct ovpn_peer *peer, struct sk_buff *skb) skb_scrub_packet(skb, true); /* network header reset in ovpn_decrypt_post() */ + skb_reset_mac_header(skb); skb_reset_transport_header(skb); skb_reset_inner_headers(skb); /* cause packet to be "received" by the interface */ pkt_len = skb->len; + /* we may get here in process context in case of TCP connections, + * therefore we have to disable BHs to ensure gro_cells_receive() + * and dev_dstats_rx_add() do not get corrupted or enter deadlock + */ + local_bh_disable(); ret = gro_cells_receive(&peer->ovpn->gro_cells, skb); if (likely(ret == NET_RX_SUCCESS)) { /* update RX stats with the size of decrypted packet */ ovpn_peer_stats_increment_rx(&peer->vpn_stats, pkt_len); dev_dstats_rx_add(peer->ovpn->dev, pkt_len); } + local_bh_enable(); } void ovpn_decrypt_post(void *data, int ret) diff --git a/drivers/net/phy/bcm-phy-lib.c b/drivers/net/phy/bcm-phy-lib.c index 5198d66dbbc0..b64beade8dd9 100644 --- a/drivers/net/phy/bcm-phy-lib.c +++ b/drivers/net/phy/bcm-phy-lib.c @@ -563,6 +563,15 @@ void bcm_phy_get_stats(struct phy_device *phydev, u64 *shadow, } EXPORT_SYMBOL_GPL(bcm_phy_get_stats); +void bcm_phy_update_stats_shadow(struct phy_device *phydev, u64 *shadow) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(bcm_phy_hw_stats); i++) + bcm_phy_get_stat(phydev, shadow, i); +} +EXPORT_SYMBOL_GPL(bcm_phy_update_stats_shadow); + void bcm_phy_r_rc_cal_reset(struct phy_device *phydev) { /* Reset R_CAL/RC_CAL Engine */ diff --git a/drivers/net/phy/bcm-phy-lib.h b/drivers/net/phy/bcm-phy-lib.h index bceddbc860eb..bba94ce96195 100644 --- a/drivers/net/phy/bcm-phy-lib.h +++ b/drivers/net/phy/bcm-phy-lib.h @@ -85,6 +85,7 @@ int bcm_phy_get_sset_count(struct phy_device *phydev); void bcm_phy_get_strings(struct phy_device *phydev, u8 *data); void bcm_phy_get_stats(struct phy_device *phydev, u64 *shadow, struct ethtool_stats *stats, u64 *data); +void bcm_phy_update_stats_shadow(struct phy_device *phydev, u64 *shadow); void bcm_phy_r_rc_cal_reset(struct phy_device *phydev); int bcm_phy_28nm_a0b0_afe_config_init(struct phy_device *phydev); int bcm_phy_enable_jumbo(struct phy_device *phydev); diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c index 00e8fa14aa77..71a163f62c0e 100644 --- a/drivers/net/phy/bcm7xxx.c +++ b/drivers/net/phy/bcm7xxx.c @@ -807,6 +807,17 @@ static void bcm7xxx_28nm_get_phy_stats(struct phy_device *phydev, bcm_phy_get_stats(phydev, priv->stats, stats, data); } +static int bcm7xxx_28nm_suspend(struct phy_device *phydev) +{ + struct bcm7xxx_phy_priv *priv = phydev->priv; + + mutex_lock(&phydev->lock); + bcm_phy_update_stats_shadow(phydev, priv->stats); + mutex_unlock(&phydev->lock); + + return genphy_suspend(phydev); +} + static int bcm7xxx_28nm_probe(struct phy_device *phydev) { struct bcm7xxx_phy_priv *priv; @@ -849,6 +860,7 @@ static int bcm7xxx_28nm_probe(struct phy_device *phydev) .flags = PHY_IS_INTERNAL, \ .config_init = bcm7xxx_28nm_config_init, \ .resume = bcm7xxx_28nm_resume, \ + .suspend = bcm7xxx_28nm_suspend, \ .get_tunable = bcm7xxx_28nm_get_tunable, \ .set_tunable = bcm7xxx_28nm_set_tunable, \ .get_sset_count = bcm_phy_get_sset_count, \ @@ -866,6 +878,7 @@ static int bcm7xxx_28nm_probe(struct phy_device *phydev) .flags = PHY_IS_INTERNAL, \ .config_init = bcm7xxx_28nm_ephy_config_init, \ .resume = bcm7xxx_28nm_ephy_resume, \ + .suspend = bcm7xxx_28nm_suspend, \ .get_sset_count = bcm_phy_get_sset_count, \ .get_strings = bcm_phy_get_strings, \ .get_stats = bcm7xxx_28nm_get_phy_stats, \ @@ -902,6 +915,7 @@ static int bcm7xxx_28nm_probe(struct phy_device *phydev) .config_aneg = genphy_config_aneg, \ .read_status = genphy_read_status, \ .resume = bcm7xxx_16nm_ephy_resume, \ + .suspend = bcm7xxx_28nm_suspend, \ } static struct phy_driver bcm7xxx_driver[] = { diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index bf0c6a04481e..d1a4edb34ad2 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -592,8 +592,13 @@ static int bcm54xx_set_wakeup_irq(struct phy_device *phydev, bool state) static int bcm54xx_suspend(struct phy_device *phydev) { + struct bcm54xx_phy_priv *priv = phydev->priv; int ret = 0; + mutex_lock(&phydev->lock); + bcm_phy_update_stats_shadow(phydev, priv->stats); + mutex_unlock(&phydev->lock); + bcm54xx_ptp_stop(phydev); /* Acknowledge any Wake-on-LAN interrupt prior to suspend */ diff --git a/drivers/net/phy/dp83869.c b/drivers/net/phy/dp83869.c index 1f381d7b13ff..96a7d255f50f 100644 --- a/drivers/net/phy/dp83869.c +++ b/drivers/net/phy/dp83869.c @@ -31,6 +31,7 @@ #define DP83869_RGMIICTL 0x0032 #define DP83869_STRAP_STS1 0x006e #define DP83869_RGMIIDCTL 0x0086 +#define DP83869_ANA_PLL_PROG_PI 0x00c6 #define DP83869_RXFCFG 0x0134 #define DP83869_RXFPMD1 0x0136 #define DP83869_RXFPMD2 0x0137 @@ -826,12 +827,22 @@ static int dp83869_config_init(struct phy_device *phydev) dp83869_config_port_mirroring(phydev); /* Clock output selection if muxing property is set */ - if (dp83869->clk_output_sel != DP83869_CLK_O_SEL_REF_CLK) + if (dp83869->clk_output_sel != DP83869_CLK_O_SEL_REF_CLK) { + /* + * Table 7-121 in datasheet says we have to set register 0xc6 + * to value 0x10 before CLK_O_SEL can be modified. + */ + ret = phy_write_mmd(phydev, DP83869_DEVADDR, + DP83869_ANA_PLL_PROG_PI, 0x10); + if (ret) + return ret; + ret = phy_modify_mmd(phydev, DP83869_DEVADDR, DP83869_IO_MUX_CFG, DP83869_IO_MUX_CFG_CLK_O_SEL_MASK, dp83869->clk_output_sel << DP83869_IO_MUX_CFG_CLK_O_SEL_SHIFT); + } if (phy_interface_is_rgmii(phydev)) { ret = phy_write_mmd(phydev, DP83869_DEVADDR, DP83869_RGMIIDCTL, diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 2aa1dedd21b8..e211a523c258 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -4548,6 +4548,13 @@ static int lan8814_config_init(struct phy_device *phydev) struct kszphy_priv *lan8814 = phydev->priv; int ret; + if (phy_package_init_once(phydev)) + /* Reset the PHY */ + lanphy_modify_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + LAN8814_QSGMII_SOFT_RESET, + LAN8814_QSGMII_SOFT_RESET_BIT, + LAN8814_QSGMII_SOFT_RESET_BIT); + /* Based on the interface type select how the advertise ability is * encoded, to set as SGMII or as USGMII. */ @@ -4655,13 +4662,7 @@ static int lan8814_probe(struct phy_device *phydev) priv->is_ptp_available = err == LAN8814_REV_LAN8814 || err == LAN8814_REV_LAN8818; - if (phy_package_init_once(phydev)) { - /* Reset the PHY */ - lanphy_modify_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, - LAN8814_QSGMII_SOFT_RESET, - LAN8814_QSGMII_SOFT_RESET_BIT, - LAN8814_QSGMII_SOFT_RESET_BIT); - + if (phy_package_probe_once(phydev)) { err = lan8814_release_coma_mode(phydev); if (err) return err; diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c index df0bcfedddbc..293ef80c4e30 100644 --- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -756,6 +756,7 @@ static void ax88772_mac_link_down(struct phylink_config *config, struct usbnet *dev = netdev_priv(to_net_dev(config->dev)); asix_write_medium_mode(dev, 0, 0); + usbnet_link_change(dev, false, false); } static void ax88772_mac_link_up(struct phylink_config *config, @@ -786,6 +787,7 @@ static void ax88772_mac_link_up(struct phylink_config *config, m |= AX_MEDIUM_RFC; asix_write_medium_mode(dev, m, 0); + usbnet_link_change(dev, true, false); } static const struct phylink_mac_ops ax88772_phylink_mac_ops = { diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index bb9929727eb9..0223a172851e 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -2012,6 +2012,14 @@ static const struct usb_device_id cdc_devs[] = { .driver_info = (unsigned long)&apple_private_interface_info, }, + /* Mac */ + { USB_DEVICE_INTERFACE_NUMBER(0x05ac, 0x1905, 0), + .driver_info = (unsigned long)&apple_private_interface_info, + }, + { USB_DEVICE_INTERFACE_NUMBER(0x05ac, 0x1905, 2), + .driver_info = (unsigned long)&apple_private_interface_info, + }, + /* Ericsson MBM devices like F5521gw */ { .match_flags = USB_DEVICE_ID_MATCH_INT_INFO | USB_DEVICE_ID_MATCH_VENDOR, diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 7337bf1b7d6a..1ace1d2398c9 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -10138,6 +10138,7 @@ static const struct usb_device_id rtl8152_table[] = { { USB_DEVICE(VENDOR_ID_DELL, 0xb097) }, { USB_DEVICE(VENDOR_ID_ASUS, 0x1976) }, { USB_DEVICE(VENDOR_ID_TRENDNET, 0xe02b) }, + { USB_DEVICE(VENDOR_ID_TRENDNET, 0xe02c) }, {} }; diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c index 4cda0643afb6..c880c95c41a5 100644 --- a/drivers/net/usb/rtl8150.c +++ b/drivers/net/usb/rtl8150.c @@ -683,6 +683,7 @@ static netdev_tx_t rtl8150_start_xmit(struct sk_buff *skb, struct net_device *netdev) { rtl8150_t *dev = netdev_priv(netdev); + unsigned int skb_len; int count, res; /* pad the frame and ensure terminating USB packet, datasheet 9.2.3 */ @@ -694,6 +695,8 @@ static netdev_tx_t rtl8150_start_xmit(struct sk_buff *skb, return NETDEV_TX_OK; } + skb_len = skb->len; + netif_stop_queue(netdev); dev->tx_skb = skb; usb_fill_bulk_urb(dev->tx_urb, dev->udev, usb_sndbulkpipe(dev->udev, 2), @@ -707,9 +710,16 @@ static netdev_tx_t rtl8150_start_xmit(struct sk_buff *skb, netdev->stats.tx_errors++; netif_start_queue(netdev); } + /* + * The URB was not submitted, so write_bulk_callback() will + * never run to free dev->tx_skb. Drop the skb here and + * clear tx_skb to avoid leaving a stale pointer. + */ + dev->tx_skb = NULL; + dev_kfree_skb_any(skb); } else { netdev->stats.tx_packets++; - netdev->stats.tx_bytes += skb->len; + netdev->stats.tx_bytes += skb_len; netif_trans_update(netdev); } diff --git a/drivers/net/veth.c b/drivers/net/veth.c index e35df717e65e..0cfb19b760dd 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -972,7 +972,8 @@ static int veth_poll(struct napi_struct *napi, int budget) /* NAPI functions as RCU section */ peer_dev = rcu_dereference_check(priv->peer, rcu_read_lock_bh_held()); - peer_txq = peer_dev ? netdev_get_tx_queue(peer_dev, queue_idx) : NULL; + peer_txq = (peer_dev && queue_idx < peer_dev->real_num_tx_queues) ? + netdev_get_tx_queue(peer_dev, queue_idx) : NULL; xdp_set_return_frame_no_direct(); done = veth_xdp_rcv(rq, budget, &bq, &stats); diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 2cf2dbd1c12f..46209917ae4d 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -1034,6 +1034,7 @@ static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev, err: port_dev->priv_flags &= ~IFF_L3MDEV_SLAVE; + synchronize_net(); return ret; } @@ -1053,10 +1054,16 @@ static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev, } /* inverse of do_vrf_add_slave */ -static int do_vrf_del_slave(struct net_device *dev, struct net_device *port_dev) +static int do_vrf_del_slave(struct net_device *dev, struct net_device *port_dev, + bool needs_sync) { netdev_upper_dev_unlink(port_dev, dev); port_dev->priv_flags &= ~IFF_L3MDEV_SLAVE; + /* Make sure that concurrent RCU readers that identified the device + * as a VRF port see a VRF master or no master at all. + */ + if (needs_sync) + synchronize_net(); cycle_netdev(port_dev, NULL); @@ -1065,7 +1072,7 @@ static int do_vrf_del_slave(struct net_device *dev, struct net_device *port_dev) static int vrf_del_slave(struct net_device *dev, struct net_device *port_dev) { - return do_vrf_del_slave(dev, port_dev); + return do_vrf_del_slave(dev, port_dev, true); } static void vrf_dev_uninit(struct net_device *dev) @@ -1619,7 +1626,7 @@ static void vrf_dellink(struct net_device *dev, struct list_head *head) struct list_head *iter; netdev_for_each_lower_dev(dev, port_dev, iter) - vrf_del_slave(dev, port_dev); + do_vrf_del_slave(dev, port_dev, false); vrf_map_unregister_dev(dev); @@ -1751,7 +1758,7 @@ static int vrf_device_event(struct notifier_block *unused, goto out; vrf_dev = netdev_master_upper_dev_get(dev); - vrf_del_slave(vrf_dev, dev); + do_vrf_del_slave(vrf_dev, dev, false); } out: return NOTIFY_DONE; diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c index 3bd57527b1be..15bfb78381d4 100644 --- a/drivers/net/wan/fsl_ucc_hdlc.c +++ b/drivers/net/wan/fsl_ucc_hdlc.c @@ -773,11 +773,6 @@ static void uhdlc_memclean(struct ucc_hdlc_private *priv) kfree(priv->tx_skbuff); priv->tx_skbuff = NULL; - if (priv->uf_regs) { - iounmap(priv->uf_regs); - priv->uf_regs = NULL; - } - if (priv->uccf) { ucc_fast_free(priv->uccf); priv->uccf = NULL; @@ -1255,12 +1250,12 @@ static void ucc_hdlc_remove(struct platform_device *pdev) uhdlc_memclean(priv); - if (priv->utdm->si_regs) { + if (priv->utdm && priv->utdm->si_regs) { iounmap(priv->utdm->si_regs); priv->utdm->si_regs = NULL; } - if (priv->utdm->siram) { + if (priv->utdm && priv->utdm->siram) { iounmap(priv->utdm->siram); priv->utdm->siram = NULL; } diff --git a/drivers/net/wireless/ath/ath10k/Kconfig b/drivers/net/wireless/ath/ath10k/Kconfig index 876aed765833..efb9f022d8c6 100644 --- a/drivers/net/wireless/ath/ath10k/Kconfig +++ b/drivers/net/wireless/ath/ath10k/Kconfig @@ -46,6 +46,7 @@ config ATH10K_SNOC depends on ARCH_QCOM || COMPILE_TEST depends on QCOM_SMEM depends on QCOM_RPROC_COMMON || QCOM_RPROC_COMMON=n + select POWER_SEQUENCING select QCOM_SCM select QCOM_QMI_HELPERS help diff --git a/drivers/net/wireless/ath/ath12k/core.c b/drivers/net/wireless/ath/ath12k/core.c index 2519e2400d58..980a12fb2c6e 100644 --- a/drivers/net/wireless/ath/ath12k/core.c +++ b/drivers/net/wireless/ath/ath12k/core.c @@ -1838,10 +1838,22 @@ static struct ath12k_hw_group *ath12k_core_hw_group_alloc(struct ath12k_base *ab return ag; } +static void ath12k_core_free_wsi_info(struct ath12k_hw_group *ag) +{ + int i; + + for (i = 0; i < ag->num_devices; i++) { + of_node_put(ag->wsi_node[i]); + ag->wsi_node[i] = NULL; + } + ag->num_devices = 0; +} + static void ath12k_core_hw_group_free(struct ath12k_hw_group *ag) { mutex_lock(&ath12k_hw_group_mutex); + ath12k_core_free_wsi_info(ag); list_del(&ag->list); kfree(ag); @@ -1867,52 +1879,59 @@ static struct ath12k_hw_group *ath12k_core_hw_group_find_by_dt(struct ath12k_bas static int ath12k_core_get_wsi_info(struct ath12k_hw_group *ag, struct ath12k_base *ab) { - struct device_node *wsi_dev = ab->dev->of_node, *next_wsi_dev; - struct device_node *tx_endpoint, *next_rx_endpoint; - int device_count = 0; - - next_wsi_dev = wsi_dev; + struct device_node *next_wsi_dev; + int device_count = 0, ret = 0; + struct device_node *wsi_dev; - if (!next_wsi_dev) + wsi_dev = of_node_get(ab->dev->of_node); + if (!wsi_dev) return -ENODEV; do { - ag->wsi_node[device_count] = next_wsi_dev; + if (device_count >= ATH12K_MAX_DEVICES) { + ath12k_warn(ab, "device count in DT %d is more than limit %d\n", + device_count, ATH12K_MAX_DEVICES); + ret = -EINVAL; + break; + } + + ag->wsi_node[device_count++] = of_node_get(wsi_dev); - tx_endpoint = of_graph_get_endpoint_by_regs(next_wsi_dev, 0, -1); + struct device_node *tx_endpoint __free(device_node) = + of_graph_get_endpoint_by_regs(wsi_dev, 0, -1); if (!tx_endpoint) { - of_node_put(next_wsi_dev); - return -ENODEV; + ret = -ENODEV; + break; } - next_rx_endpoint = of_graph_get_remote_endpoint(tx_endpoint); + struct device_node *next_rx_endpoint __free(device_node) = + of_graph_get_remote_endpoint(tx_endpoint); if (!next_rx_endpoint) { - of_node_put(next_wsi_dev); - of_node_put(tx_endpoint); - return -ENODEV; + ret = -ENODEV; + break; } - of_node_put(tx_endpoint); - of_node_put(next_wsi_dev); - next_wsi_dev = of_graph_get_port_parent(next_rx_endpoint); if (!next_wsi_dev) { - of_node_put(next_rx_endpoint); - return -ENODEV; + ret = -ENODEV; + break; } - of_node_put(next_rx_endpoint); + of_node_put(wsi_dev); + wsi_dev = next_wsi_dev; + } while (ab->dev->of_node != wsi_dev); - device_count++; - if (device_count > ATH12K_MAX_DEVICES) { - ath12k_warn(ab, "device count in DT %d is more than limit %d\n", - device_count, ATH12K_MAX_DEVICES); - of_node_put(next_wsi_dev); - return -EINVAL; + if (ret) { + while (--device_count >= 0) { + of_node_put(ag->wsi_node[device_count]); + ag->wsi_node[device_count] = NULL; } - } while (wsi_dev != next_wsi_dev); - of_node_put(next_wsi_dev); + of_node_put(wsi_dev); + return ret; + } + + of_node_put(wsi_dev); ag->num_devices = device_count; return 0; @@ -1983,9 +2002,9 @@ static struct ath12k_hw_group *ath12k_core_hw_group_assign(struct ath12k_base *a ath12k_core_get_wsi_index(ag, ab)) { ath12k_dbg(ab, ATH12K_DBG_BOOT, "unable to get wsi info from dt, grouping single device"); + ath12k_core_free_wsi_info(ag); ag->id = ATH12K_INVALID_GROUP_ID; ag->num_devices = 1; - memset(ag->wsi_node, 0, sizeof(ag->wsi_node)); wsi->index = 0; } diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.c b/drivers/net/wireless/ath/ath12k/dp_rx.c index 250459facff3..b108ccd0f637 100644 --- a/drivers/net/wireless/ath/ath12k/dp_rx.c +++ b/drivers/net/wireless/ath/ath12k/dp_rx.c @@ -565,6 +565,9 @@ static int ath12k_dp_prepare_reo_update_elem(struct ath12k_dp *dp, lockdep_assert_held(&dp->dp_lock); + if (!peer->primary_link) + return 0; + elem = kzalloc_obj(*elem, GFP_ATOMIC); if (!elem) return -ENOMEM; @@ -1337,7 +1340,7 @@ void ath12k_dp_rx_deliver_msdu(struct ath12k_pdev_dp *dp_pdev, struct napi_struc bool is_mcbc = rxcb->is_mcbc; bool is_eapol = rxcb->is_eapol; - peer = ath12k_dp_peer_find_by_peerid(dp_pdev, rx_info->peer_id); + peer = ath12k_dp_peer_find_by_peerid(dp_pdev, rxcb->peer_id); pubsta = peer ? peer->sta : NULL; diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c index fbdfe6424fd7..df2334f3bad6 100644 --- a/drivers/net/wireless/ath/ath12k/mac.c +++ b/drivers/net/wireless/ath/ath12k/mac.c @@ -788,7 +788,7 @@ struct ath12k_link_vif *ath12k_mac_get_arvif(struct ath12k *ar, u32 vdev_id) /* To use the arvif returned, caller must have held rcu read lock. */ - WARN_ON(!rcu_read_lock_any_held()); + lockdep_assert_in_rcu_read_lock(); arvif_iter.vdev_id = vdev_id; arvif_iter.ar = ar; diff --git a/drivers/net/wireless/ath/ath12k/p2p.c b/drivers/net/wireless/ath/ath12k/p2p.c index 59589748f1a8..19ebcd1d8eb2 100644 --- a/drivers/net/wireless/ath/ath12k/p2p.c +++ b/drivers/net/wireless/ath/ath12k/p2p.c @@ -123,7 +123,7 @@ static void ath12k_p2p_noa_update_vdev_iter(void *data, u8 *mac, struct ath12k_p2p_noa_arg *arg = data; struct ath12k_link_vif *arvif; - WARN_ON(!rcu_read_lock_any_held()); + lockdep_assert_in_rcu_read_lock(); arvif = &ahvif->deflink; if (!arvif->is_created || arvif->ar != arg->ar || arvif->vdev_id != arg->vdev_id) return; diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c index 65a05a9520ff..b5e904a55aea 100644 --- a/drivers/net/wireless/ath/ath12k/wmi.c +++ b/drivers/net/wireless/ath/ath12k/wmi.c @@ -9778,7 +9778,7 @@ static void ath12k_wmi_rssi_dbm_conversion_params_info_event(struct ath12k_base *ab, struct sk_buff *skb) { - struct ath12k_wmi_rssi_dbm_conv_info_arg rssi_info; + struct ath12k_wmi_rssi_dbm_conv_info_arg rssi_info = {}; struct ath12k *ar; s32 noise_floor; u32 pdev_id; @@ -10251,7 +10251,7 @@ int ath12k_wmi_hw_data_filter_cmd(struct ath12k *ar, struct wmi_hw_data_filter_a { struct wmi_hw_data_filter_cmd *cmd; struct sk_buff *skb; - int len; + int ret, len; len = sizeof(*cmd); skb = ath12k_wmi_alloc_skb(ar->wmi->wmi_ab, len); @@ -10275,7 +10275,13 @@ int ath12k_wmi_hw_data_filter_cmd(struct ath12k *ar, struct wmi_hw_data_filter_a "wmi hw data filter enable %d filter_bitmap 0x%x\n", arg->enable, arg->hw_filter_bitmap); - return ath12k_wmi_cmd_send(ar->wmi, skb, WMI_HW_DATA_FILTER_CMDID); + ret = ath12k_wmi_cmd_send(ar->wmi, skb, WMI_HW_DATA_FILTER_CMDID); + if (ret) { + ath12k_warn(ar->ab, "failed to send WMI_HW_DATA_FILTER_CMDID\n"); + dev_kfree_skb(skb); + } + + return ret; } int ath12k_wmi_wow_host_wakeup_ind(struct ath12k *ar) @@ -10283,6 +10289,7 @@ int ath12k_wmi_wow_host_wakeup_ind(struct ath12k *ar) struct wmi_wow_host_wakeup_cmd *cmd; struct sk_buff *skb; size_t len; + int ret; len = sizeof(*cmd); skb = ath12k_wmi_alloc_skb(ar->wmi->wmi_ab, len); @@ -10295,14 +10302,20 @@ int ath12k_wmi_wow_host_wakeup_ind(struct ath12k *ar) ath12k_dbg(ar->ab, ATH12K_DBG_WMI, "wmi tlv wow host wakeup ind\n"); - return ath12k_wmi_cmd_send(ar->wmi, skb, WMI_WOW_HOSTWAKEUP_FROM_SLEEP_CMDID); + ret = ath12k_wmi_cmd_send(ar->wmi, skb, WMI_WOW_HOSTWAKEUP_FROM_SLEEP_CMDID); + if (ret) { + ath12k_warn(ar->ab, "failed to send WMI_WOW_HOSTWAKEUP_FROM_SLEEP_CMDID\n"); + dev_kfree_skb(skb); + } + + return ret; } int ath12k_wmi_wow_enable(struct ath12k *ar) { struct wmi_wow_enable_cmd *cmd; struct sk_buff *skb; - int len; + int ret, len; len = sizeof(*cmd); skb = ath12k_wmi_alloc_skb(ar->wmi->wmi_ab, len); @@ -10317,7 +10330,13 @@ int ath12k_wmi_wow_enable(struct ath12k *ar) cmd->pause_iface_config = cpu_to_le32(WOW_IFACE_PAUSE_ENABLED); ath12k_dbg(ar->ab, ATH12K_DBG_WMI, "wmi tlv wow enable\n"); - return ath12k_wmi_cmd_send(ar->wmi, skb, WMI_WOW_ENABLE_CMDID); + ret = ath12k_wmi_cmd_send(ar->wmi, skb, WMI_WOW_ENABLE_CMDID); + if (ret) { + ath12k_warn(ar->ab, "failed to send WMI_WOW_ENABLE_CMDID\n"); + dev_kfree_skb(skb); + } + + return ret; } int ath12k_wmi_wow_add_wakeup_event(struct ath12k *ar, u32 vdev_id, @@ -10327,6 +10346,7 @@ int ath12k_wmi_wow_add_wakeup_event(struct ath12k *ar, u32 vdev_id, struct wmi_wow_add_del_event_cmd *cmd; struct sk_buff *skb; size_t len; + int ret; len = sizeof(*cmd); skb = ath12k_wmi_alloc_skb(ar->wmi->wmi_ab, len); @@ -10343,7 +10363,13 @@ int ath12k_wmi_wow_add_wakeup_event(struct ath12k *ar, u32 vdev_id, ath12k_dbg(ar->ab, ATH12K_DBG_WMI, "wmi tlv wow add wakeup event %s enable %d vdev_id %d\n", wow_wakeup_event(event), enable, vdev_id); - return ath12k_wmi_cmd_send(ar->wmi, skb, WMI_WOW_ENABLE_DISABLE_WAKE_EVENT_CMDID); + ret = ath12k_wmi_cmd_send(ar->wmi, skb, WMI_WOW_ENABLE_DISABLE_WAKE_EVENT_CMDID); + if (ret) { + ath12k_warn(ar->ab, "failed to send WMI_WOW_ENABLE_DISABLE_WAKE_EVENT_CMDID\n"); + dev_kfree_skb(skb); + } + + return ret; } int ath12k_wmi_wow_add_pattern(struct ath12k *ar, u32 vdev_id, u32 pattern_id, @@ -10356,6 +10382,7 @@ int ath12k_wmi_wow_add_pattern(struct ath12k *ar, u32 vdev_id, u32 pattern_id, struct sk_buff *skb; void *ptr; size_t len; + int ret; len = sizeof(*cmd) + sizeof(*tlv) + /* array struct */ @@ -10435,7 +10462,13 @@ int ath12k_wmi_wow_add_pattern(struct ath12k *ar, u32 vdev_id, u32 pattern_id, ath12k_dbg_dump(ar->ab, ATH12K_DBG_WMI, NULL, "wow bitmask: ", bitmap->bitmaskbuf, pattern_len); - return ath12k_wmi_cmd_send(ar->wmi, skb, WMI_WOW_ADD_WAKE_PATTERN_CMDID); + ret = ath12k_wmi_cmd_send(ar->wmi, skb, WMI_WOW_ADD_WAKE_PATTERN_CMDID); + if (ret) { + ath12k_warn(ar->ab, "failed to send WMI_WOW_ADD_WAKE_PATTERN_CMDID\n"); + dev_kfree_skb(skb); + } + + return ret; } int ath12k_wmi_wow_del_pattern(struct ath12k *ar, u32 vdev_id, u32 pattern_id) @@ -10443,6 +10476,7 @@ int ath12k_wmi_wow_del_pattern(struct ath12k *ar, u32 vdev_id, u32 pattern_id) struct wmi_wow_del_pattern_cmd *cmd; struct sk_buff *skb; size_t len; + int ret; len = sizeof(*cmd); skb = ath12k_wmi_alloc_skb(ar->wmi->wmi_ab, len); @@ -10459,7 +10493,13 @@ int ath12k_wmi_wow_del_pattern(struct ath12k *ar, u32 vdev_id, u32 pattern_id) ath12k_dbg(ar->ab, ATH12K_DBG_WMI, "wmi tlv wow del pattern vdev_id %d pattern_id %d\n", vdev_id, pattern_id); - return ath12k_wmi_cmd_send(ar->wmi, skb, WMI_WOW_DEL_WAKE_PATTERN_CMDID); + ret = ath12k_wmi_cmd_send(ar->wmi, skb, WMI_WOW_DEL_WAKE_PATTERN_CMDID); + if (ret) { + ath12k_warn(ar->ab, "failed to send WMI_WOW_DEL_WAKE_PATTERN_CMDID\n"); + dev_kfree_skb(skb); + } + + return ret; } static struct sk_buff * @@ -10595,6 +10635,7 @@ int ath12k_wmi_wow_config_pno(struct ath12k *ar, u32 vdev_id, struct wmi_pno_scan_req_arg *pno_scan) { struct sk_buff *skb; + int ret; if (pno_scan->enable) skb = ath12k_wmi_op_gen_config_pno_start(ar, vdev_id, pno_scan); @@ -10604,7 +10645,13 @@ int ath12k_wmi_wow_config_pno(struct ath12k *ar, u32 vdev_id, if (IS_ERR_OR_NULL(skb)) return -ENOMEM; - return ath12k_wmi_cmd_send(ar->wmi, skb, WMI_NETWORK_LIST_OFFLOAD_CONFIG_CMDID); + ret = ath12k_wmi_cmd_send(ar->wmi, skb, WMI_NETWORK_LIST_OFFLOAD_CONFIG_CMDID); + if (ret) { + ath12k_warn(ar->ab, "failed to send WMI_NETWORK_LIST_OFFLOAD_CONFIG_CMDID\n"); + dev_kfree_skb(skb); + } + + return ret; } static void ath12k_wmi_fill_ns_offload(struct ath12k *ar, @@ -10717,6 +10764,7 @@ int ath12k_wmi_arp_ns_offload(struct ath12k *ar, void *buf_ptr; size_t len; u8 ns_cnt, ns_ext_tuples = 0; + int ret; ns_cnt = offload->ipv6_count; @@ -10752,7 +10800,13 @@ int ath12k_wmi_arp_ns_offload(struct ath12k *ar, if (ns_ext_tuples) ath12k_wmi_fill_ns_offload(ar, offload, &buf_ptr, enable, 1); - return ath12k_wmi_cmd_send(ar->wmi, skb, WMI_SET_ARP_NS_OFFLOAD_CMDID); + ret = ath12k_wmi_cmd_send(ar->wmi, skb, WMI_SET_ARP_NS_OFFLOAD_CMDID); + if (ret) { + ath12k_warn(ar->ab, "failed to send WMI_SET_ARP_NS_OFFLOAD_CMDID\n"); + dev_kfree_skb(skb); + } + + return ret; } int ath12k_wmi_gtk_rekey_offload(struct ath12k *ar, @@ -10762,7 +10816,7 @@ int ath12k_wmi_gtk_rekey_offload(struct ath12k *ar, struct wmi_gtk_rekey_offload_cmd *cmd; struct sk_buff *skb; __le64 replay_ctr; - int len; + int ret, len; len = sizeof(*cmd); skb = ath12k_wmi_alloc_skb(ar->wmi->wmi_ab, len); @@ -10789,7 +10843,13 @@ int ath12k_wmi_gtk_rekey_offload(struct ath12k *ar, ath12k_dbg(ar->ab, ATH12K_DBG_WMI, "offload gtk rekey vdev: %d %d\n", arvif->vdev_id, enable); - return ath12k_wmi_cmd_send(ar->wmi, skb, WMI_GTK_OFFLOAD_CMDID); + ret = ath12k_wmi_cmd_send(ar->wmi, skb, WMI_GTK_OFFLOAD_CMDID); + if (ret) { + ath12k_warn(ar->ab, "failed to send WMI_GTK_OFFLOAD_CMDID offload\n"); + dev_kfree_skb(skb); + } + + return ret; } int ath12k_wmi_gtk_rekey_getinfo(struct ath12k *ar, @@ -10797,7 +10857,7 @@ int ath12k_wmi_gtk_rekey_getinfo(struct ath12k *ar, { struct wmi_gtk_rekey_offload_cmd *cmd; struct sk_buff *skb; - int len; + int ret, len; len = sizeof(*cmd); skb = ath12k_wmi_alloc_skb(ar->wmi->wmi_ab, len); @@ -10811,7 +10871,13 @@ int ath12k_wmi_gtk_rekey_getinfo(struct ath12k *ar, ath12k_dbg(ar->ab, ATH12K_DBG_WMI, "get gtk rekey vdev_id: %d\n", arvif->vdev_id); - return ath12k_wmi_cmd_send(ar->wmi, skb, WMI_GTK_OFFLOAD_CMDID); + ret = ath12k_wmi_cmd_send(ar->wmi, skb, WMI_GTK_OFFLOAD_CMDID); + if (ret) { + ath12k_warn(ar->ab, "failed to send WMI_GTK_OFFLOAD_CMDID getinfo\n"); + dev_kfree_skb(skb); + } + + return ret; } int ath12k_wmi_sta_keepalive(struct ath12k *ar, @@ -10822,6 +10888,7 @@ int ath12k_wmi_sta_keepalive(struct ath12k *ar, struct wmi_sta_keepalive_cmd *cmd; struct sk_buff *skb; size_t len; + int ret; len = sizeof(*cmd) + sizeof(*arp); skb = ath12k_wmi_alloc_skb(wmi->wmi_ab, len); @@ -10849,7 +10916,13 @@ int ath12k_wmi_sta_keepalive(struct ath12k *ar, "wmi sta keepalive vdev %d enabled %d method %d interval %d\n", arg->vdev_id, arg->enabled, arg->method, arg->interval); - return ath12k_wmi_cmd_send(wmi, skb, WMI_STA_KEEPALIVE_CMDID); + ret = ath12k_wmi_cmd_send(wmi, skb, WMI_STA_KEEPALIVE_CMDID); + if (ret) { + ath12k_warn(ar->ab, "failed to send WMI_STA_KEEPALIVE_CMDID\n"); + dev_kfree_skb(skb); + } + + return ret; } int ath12k_wmi_mlo_setup(struct ath12k *ar, struct wmi_mlo_setup_arg *mlo_params) diff --git a/drivers/net/wireless/ath/ath5k/base.c b/drivers/net/wireless/ath/ath5k/base.c index 05c9c07591fc..6ca31d4ea437 100644 --- a/drivers/net/wireless/ath/ath5k/base.c +++ b/drivers/net/wireless/ath/ath5k/base.c @@ -1738,7 +1738,8 @@ ath5k_tx_frame_completed(struct ath5k_hw *ah, struct sk_buff *skb, } info->status.rates[ts->ts_final_idx].count = ts->ts_final_retry; - info->status.rates[ts->ts_final_idx + 1].idx = -1; + if (ts->ts_final_idx + 1 < IEEE80211_TX_MAX_RATES) + info->status.rates[ts->ts_final_idx + 1].idx = -1; if (unlikely(ts->ts_status)) { ah->stats.ack_fail++; diff --git a/drivers/net/wireless/broadcom/b43/xmit.c b/drivers/net/wireless/broadcom/b43/xmit.c index 7651b1bdb592..f0b082596637 100644 --- a/drivers/net/wireless/broadcom/b43/xmit.c +++ b/drivers/net/wireless/broadcom/b43/xmit.c @@ -702,7 +702,8 @@ void b43_rx(struct b43_wldev *dev, struct sk_buff *skb, const void *_rxhdr) * key index, but the ucode passed it slightly different. */ keyidx = b43_kidx_to_raw(dev, keyidx); - B43_WARN_ON(keyidx >= ARRAY_SIZE(dev->key)); + if (B43_WARN_ON(keyidx >= ARRAY_SIZE(dev->key))) + goto drop; if (dev->key[keyidx].algorithm != B43_SEC_ALGO_NONE) { wlhdr_len = ieee80211_hdrlen(fctl); diff --git a/drivers/net/wireless/broadcom/b43legacy/xmit.c b/drivers/net/wireless/broadcom/b43legacy/xmit.c index efd63f4ce74f..ee199d4eaf03 100644 --- a/drivers/net/wireless/broadcom/b43legacy/xmit.c +++ b/drivers/net/wireless/broadcom/b43legacy/xmit.c @@ -476,7 +476,8 @@ void b43legacy_rx(struct b43legacy_wldev *dev, * key index, but the ucode passed it slightly different. */ keyidx = b43legacy_kidx_to_raw(dev, keyidx); - B43legacy_WARN_ON(keyidx >= dev->max_nr_keys); + if (B43legacy_WARN_ON(keyidx >= dev->max_nr_keys)) + goto drop; if (dev->key[keyidx].algorithm != B43legacy_SEC_ALGO_NONE) { /* Remove PROTECTED flag to mark it as decrypted. */ diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c index 30f6fcb68632..8fb595733b9c 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c @@ -2476,8 +2476,9 @@ static void brcmf_sdio_bus_stop(struct device *dev) brcmf_dbg(TRACE, "Enter\n"); if (bus->watchdog_tsk) { + get_task_struct(bus->watchdog_tsk); send_sig(SIGTERM, bus->watchdog_tsk, 1); - kthread_stop(bus->watchdog_tsk); + kthread_stop_put(bus->watchdog_tsk); bus->watchdog_tsk = NULL; } @@ -4567,8 +4568,9 @@ void brcmf_sdio_remove(struct brcmf_sdio *bus) if (bus) { /* Stop watchdog task */ if (bus->watchdog_tsk) { + get_task_struct(bus->watchdog_tsk); send_sig(SIGTERM, bus->watchdog_tsk, 1); - kthread_stop(bus->watchdog_tsk); + kthread_stop_put(bus->watchdog_tsk); bus->watchdog_tsk = NULL; } diff --git a/drivers/net/wireless/marvell/libertas/if_usb.c b/drivers/net/wireless/marvell/libertas/if_usb.c index 4fae0e335136..5cc0c5cac257 100644 --- a/drivers/net/wireless/marvell/libertas/if_usb.c +++ b/drivers/net/wireless/marvell/libertas/if_usb.c @@ -310,6 +310,7 @@ static void if_usb_disconnect(struct usb_interface *intf) struct lbs_private *priv = cardp->priv; cardp->surprise_removed = 1; + wake_up(&cardp->fw_wq); if (priv) { lbs_stop_card(priv); @@ -633,9 +634,10 @@ static inline void process_cmdrequest(int recvlength, uint8_t *recvbuff, unsigned long flags; u8 i; - if (recvlength > LBS_CMD_BUFFER_SIZE) { + if (recvlength < MESSAGE_HEADER_LEN || + recvlength > LBS_CMD_BUFFER_SIZE) { lbs_deb_usbd(&cardp->udev->dev, - "The receive buffer is too large\n"); + "The receive buffer is invalid: %d\n", recvlength); kfree_skb(skb); return; } diff --git a/drivers/net/wireless/rsi/rsi_common.h b/drivers/net/wireless/rsi/rsi_common.h index 591602beeec6..3cdf9ded876d 100644 --- a/drivers/net/wireless/rsi/rsi_common.h +++ b/drivers/net/wireless/rsi/rsi_common.h @@ -70,12 +70,11 @@ static inline int rsi_create_kthread(struct rsi_common *common, return 0; } -static inline int rsi_kill_thread(struct rsi_thread *handle) +static inline void rsi_kill_thread(struct rsi_thread *handle) { atomic_inc(&handle->thread_done); rsi_set_event(&handle->event); - - return kthread_stop(handle->task); + wait_for_completion(&handle->completion); } void rsi_mac80211_detach(struct rsi_hw *hw); diff --git a/drivers/net/wireless/st/cw1200/pm.c b/drivers/net/wireless/st/cw1200/pm.c index 84eb15d729c7..120f0379f81d 100644 --- a/drivers/net/wireless/st/cw1200/pm.c +++ b/drivers/net/wireless/st/cw1200/pm.c @@ -264,14 +264,12 @@ int cw1200_wow_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) wiphy_err(priv->hw->wiphy, "PM request failed: %d. WoW is disabled.\n", ret); cw1200_wow_resume(hw); - mutex_unlock(&priv->conf_mutex); return -EBUSY; } /* Force resume if event is coming from the device. */ if (atomic_read(&priv->bh_rx)) { cw1200_wow_resume(hw); - mutex_unlock(&priv->conf_mutex); return -EAGAIN; } diff --git a/drivers/net/wwan/t7xx/t7xx_modem_ops.c b/drivers/net/wwan/t7xx/t7xx_modem_ops.c index 7968e208dd37..adb29d30c63f 100644 --- a/drivers/net/wwan/t7xx/t7xx_modem_ops.c +++ b/drivers/net/wwan/t7xx/t7xx_modem_ops.c @@ -457,8 +457,20 @@ static int t7xx_parse_host_rt_data(struct t7xx_fsm_ctl *ctl, struct t7xx_sys_inf offset = sizeof(struct feature_query); for (i = 0; i < FEATURE_COUNT && offset < data_length; i++) { + size_t remaining = data_length - offset; + size_t feat_data_len, feat_total; + + if (remaining < sizeof(*rt_feature)) + break; + rt_feature = data + offset; - offset += sizeof(*rt_feature) + le32_to_cpu(rt_feature->data_len); + feat_data_len = le32_to_cpu(rt_feature->data_len); + + if (feat_data_len > remaining - sizeof(*rt_feature)) + break; + + feat_total = sizeof(*rt_feature) + feat_data_len; + offset += feat_total; ft_spt_cfg = FIELD_GET(FEATURE_MSK, core->feature_set[i]); if (ft_spt_cfg != MTK_FEATURE_MUST_BE_SUPPORTED) @@ -468,8 +480,10 @@ static int t7xx_parse_host_rt_data(struct t7xx_fsm_ctl *ctl, struct t7xx_sys_inf if (ft_spt_st != MTK_FEATURE_MUST_BE_SUPPORTED) return -EINVAL; - if (i == RT_ID_MD_PORT_ENUM || i == RT_ID_AP_PORT_ENUM) - t7xx_port_enum_msg_handler(ctl->md, rt_feature->data); + if (i == RT_ID_MD_PORT_ENUM || i == RT_ID_AP_PORT_ENUM) { + t7xx_port_enum_msg_handler(ctl->md, rt_feature->data, + feat_data_len); + } } return 0; diff --git a/drivers/net/wwan/t7xx/t7xx_port_ctrl_msg.c b/drivers/net/wwan/t7xx/t7xx_port_ctrl_msg.c index ae632ef96698..f869e4ed9ee9 100644 --- a/drivers/net/wwan/t7xx/t7xx_port_ctrl_msg.c +++ b/drivers/net/wwan/t7xx/t7xx_port_ctrl_msg.c @@ -117,6 +117,7 @@ static int fsm_ee_message_handler(struct t7xx_port *port, struct t7xx_fsm_ctl *c * t7xx_port_enum_msg_handler() - Parse the port enumeration message to create/remove nodes. * @md: Modem context. * @msg: Message. + * @msg_len: Length of @msg in bytes. * * Used to control create/remove device node. * @@ -124,12 +125,18 @@ static int fsm_ee_message_handler(struct t7xx_port *port, struct t7xx_fsm_ctl *c * * 0 - Success. * * -EFAULT - Message check failure. */ -int t7xx_port_enum_msg_handler(struct t7xx_modem *md, void *msg) +int t7xx_port_enum_msg_handler(struct t7xx_modem *md, void *msg, size_t msg_len) { struct device *dev = &md->t7xx_dev->pdev->dev; unsigned int version, port_count, i; struct port_msg *port_msg = msg; + if (msg_len < sizeof(*port_msg)) { + dev_err(dev, "Port enum msg too short for header: need %zu, have %zu\n", + sizeof(*port_msg), msg_len); + return -EINVAL; + } + version = FIELD_GET(PORT_MSG_VERSION, le32_to_cpu(port_msg->info)); if (version != PORT_ENUM_VER || le32_to_cpu(port_msg->head_pattern) != PORT_ENUM_HEAD_PATTERN || @@ -141,6 +148,13 @@ int t7xx_port_enum_msg_handler(struct t7xx_modem *md, void *msg) } port_count = FIELD_GET(PORT_MSG_PRT_CNT, le32_to_cpu(port_msg->info)); + + if (msg_len < struct_size(port_msg, data, port_count)) { + dev_err(dev, "Port enum msg too short: need %zu, have %zu\n", + struct_size(port_msg, data, port_count), msg_len); + return -EINVAL; + } + for (i = 0; i < port_count; i++) { u32 port_info = le32_to_cpu(port_msg->data[i]); unsigned int ch_id; @@ -191,7 +205,7 @@ static int control_msg_handler(struct t7xx_port *port, struct sk_buff *skb) case CTL_ID_PORT_ENUM: skb_pull(skb, sizeof(*ctrl_msg_h)); - ret = t7xx_port_enum_msg_handler(ctl->md, (struct port_msg *)skb->data); + ret = t7xx_port_enum_msg_handler(ctl->md, (struct port_msg *)skb->data, skb->len); if (!ret) ret = port_ctl_send_msg_to_md(port, CTL_ID_PORT_ENUM, 0); else diff --git a/drivers/net/wwan/t7xx/t7xx_port_proxy.h b/drivers/net/wwan/t7xx/t7xx_port_proxy.h index f0918b36e899..7c3190bf0fcf 100644 --- a/drivers/net/wwan/t7xx/t7xx_port_proxy.h +++ b/drivers/net/wwan/t7xx/t7xx_port_proxy.h @@ -103,7 +103,7 @@ void t7xx_port_proxy_reset(struct port_proxy *port_prox); void t7xx_port_proxy_uninit(struct port_proxy *port_prox); int t7xx_port_proxy_init(struct t7xx_modem *md); void t7xx_port_proxy_md_status_notify(struct port_proxy *port_prox, unsigned int state); -int t7xx_port_enum_msg_handler(struct t7xx_modem *md, void *msg); +int t7xx_port_enum_msg_handler(struct t7xx_modem *md, void *msg, size_t msg_len); int t7xx_port_proxy_chl_enable_disable(struct port_proxy *port_prox, unsigned int ch_id, bool en_flag); void t7xx_port_proxy_set_cfg(struct t7xx_modem *md, enum port_cfg_id cfg_id); diff --git a/drivers/nfc/trf7970a.c b/drivers/nfc/trf7970a.c index d17c701c7888..08c27bb438b5 100644 --- a/drivers/nfc/trf7970a.c +++ b/drivers/nfc/trf7970a.c @@ -317,6 +317,7 @@ #define TRF7970A_RSSI_OSC_STATUS_RSSI_MASK (BIT(2) | BIT(1) | BIT(0)) #define TRF7970A_RSSI_OSC_STATUS_RSSI_X_MASK (BIT(5) | BIT(4) | BIT(3)) #define TRF7970A_RSSI_OSC_STATUS_RSSI_OSC_OK BIT(6) +#define TRF7970A_RSSI_OSC_STATUS_RSSI_NOISE_LEVEL 1 #define TRF7970A_SPECIAL_FCN_REG1_COL_7_6 BIT(0) #define TRF7970A_SPECIAL_FCN_REG1_14_ANTICOLL BIT(1) @@ -1300,7 +1301,7 @@ static int trf7970a_is_rf_field(struct trf7970a *trf, bool *is_rf_field) if (ret) return ret; - if (rssi & TRF7970A_RSSI_OSC_STATUS_RSSI_MASK) + if ((rssi & TRF7970A_RSSI_OSC_STATUS_RSSI_MASK) > TRF7970A_RSSI_OSC_STATUS_RSSI_NOISE_LEVEL) *is_rf_field = true; else *is_rf_field = false; diff --git a/drivers/parisc/lasi.c b/drivers/parisc/lasi.c index ef6125d83878..a5b80cd5cc37 100644 --- a/drivers/parisc/lasi.c +++ b/drivers/parisc/lasi.c @@ -193,8 +193,7 @@ static int __init lasi_init_chip(struct parisc_device *dev) ret = request_irq(lasi->gsc_irq.irq, gsc_asic_intr, 0, "lasi", lasi); if (ret < 0) { - kfree(lasi); - return ret; + goto err_free; } /* enable IRQ's for devices below LASI */ @@ -203,8 +202,7 @@ static int __init lasi_init_chip(struct parisc_device *dev) /* Done init'ing, register this driver */ ret = gsc_common_setup(dev, lasi); if (ret) { - kfree(lasi); - return ret; + goto err_irq; } gsc_fixup_irqs(dev, lasi, lasi_choose_irq); @@ -214,6 +212,12 @@ static int __init lasi_init_chip(struct parisc_device *dev) SYS_OFF_PRIO_DEFAULT, lasi_power_off, lasi); return ret; + +err_irq: + free_irq(lasi->gsc_irq.irq, lasi); +err_free: + kfree(lasi); + return ret; } static struct parisc_device_id lasi_tbl[] __initdata = { diff --git a/drivers/parisc/led.c b/drivers/parisc/led.c index b299fcc48b08..016c9d5a60a8 100644 --- a/drivers/parisc/led.c +++ b/drivers/parisc/led.c @@ -543,10 +543,8 @@ static void __init register_led_regions(void) static int __init startup_leds(void) { - if (platform_device_register(&platform_leds)) { - pr_info("LED: failed to register LEDs\n"); - platform_device_put(&platform_leds); - } + if (platform_device_register(&platform_leds)) + printk(KERN_INFO "LED: failed to register LEDs\n"); register_led_regions(); return 0; } diff --git a/drivers/platform/chrome/cros_typec_altmode.c b/drivers/platform/chrome/cros_typec_altmode.c index 557340b53af0..66c546bf89b5 100644 --- a/drivers/platform/chrome/cros_typec_altmode.c +++ b/drivers/platform/chrome/cros_typec_altmode.c @@ -359,6 +359,7 @@ cros_typec_register_thunderbolt(struct cros_typec_port *port, } INIT_WORK(&adata->work, cros_typec_altmode_work); + mutex_init(&adata->lock); adata->alt = alt; adata->port = port; adata->ap_mode_entry = true; diff --git a/drivers/platform/wmi/core.c b/drivers/platform/wmi/core.c index 7aa40dab6145..5a2ffcbab6af 100644 --- a/drivers/platform/wmi/core.c +++ b/drivers/platform/wmi/core.c @@ -411,6 +411,9 @@ int wmidev_invoke_method(struct wmi_device *wdev, u8 instance, u32 method_id, obj = aout.pointer; if (!obj) { + if (min_size != 0) + return -ENOMSG; + out->length = 0; out->data = ZERO_SIZE_PTR; diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c index d1cc6e7d176c..24c151289dd3 100644 --- a/drivers/platform/x86/hp/hp-wmi.c +++ b/drivers/platform/x86/hp/hp-wmi.c @@ -243,7 +243,7 @@ static const struct dmi_system_id victus_s_thermal_profile_boards[] __initconst }, { .matches = { DMI_MATCH(DMI_BOARD_NAME, "8D41") }, - .driver_data = (void *)&victus_s_thermal_params, + .driver_data = (void *)&omen_v1_no_ec_thermal_params, }, { .matches = { DMI_MATCH(DMI_BOARD_NAME, "8D87") }, diff --git a/drivers/platform/x86/lenovo/wmi-other.c b/drivers/platform/x86/lenovo/wmi-other.c index 6040f45aa2b0..6c2febe1a595 100644 --- a/drivers/platform/x86/lenovo/wmi-other.c +++ b/drivers/platform/x86/lenovo/wmi-other.c @@ -349,6 +349,8 @@ static int lwmi_om_hwmon_write(struct device *dev, enum hwmon_sensor_types type, */ if (!relax_fan_constraint) raw = val / LWMI_FAN_DIV * LWMI_FAN_DIV; + else + raw = val; err = lwmi_om_fan_get_set(priv, channel, &raw, true); if (err) diff --git a/drivers/pmdomain/core.c b/drivers/pmdomain/core.c index 4d32fc676aaf..71e930e80178 100644 --- a/drivers/pmdomain/core.c +++ b/drivers/pmdomain/core.c @@ -3089,6 +3089,7 @@ static const struct bus_type genpd_bus_type = { static void genpd_dev_pm_detach(struct device *dev, bool power_off) { struct generic_pm_domain *pd; + bool is_virt_dev; unsigned int i; int ret = 0; @@ -3098,6 +3099,13 @@ static void genpd_dev_pm_detach(struct device *dev, bool power_off) dev_dbg(dev, "removing from PM domain %s\n", pd->name); + /* Check if the device was created by genpd at attach. */ + is_virt_dev = dev->bus == &genpd_bus_type; + + /* Disable runtime PM if we enabled it at attach. */ + if (is_virt_dev) + pm_runtime_disable(dev); + /* Drop the default performance state */ if (dev_gpd_data(dev)->default_pstate) { dev_pm_genpd_set_performance_state(dev, 0); @@ -3123,7 +3131,7 @@ static void genpd_dev_pm_detach(struct device *dev, bool power_off) genpd_queue_power_off_work(pd); /* Unregister the device if it was created by genpd. */ - if (dev->bus == &genpd_bus_type) + if (is_virt_dev) device_unregister(dev); } diff --git a/drivers/pmdomain/mediatek/mtk-pm-domains.c b/drivers/pmdomain/mediatek/mtk-pm-domains.c index d2b8d0332951..e1cfd4223473 100644 --- a/drivers/pmdomain/mediatek/mtk-pm-domains.c +++ b/drivers/pmdomain/mediatek/mtk-pm-domains.c @@ -1015,6 +1015,7 @@ static int scpsys_get_bus_protection_legacy(struct device *dev, struct scpsys *s struct device_node *node, *smi_np; int num_regmaps = 0, i, j; struct regmap *regmap[3]; + int ret = 0; /* * Legacy code retrieves a maximum of three bus protection handles: @@ -1065,11 +1066,14 @@ static int scpsys_get_bus_protection_legacy(struct device *dev, struct scpsys *s if (node) { regmap[2] = syscon_regmap_lookup_by_phandle(node, "mediatek,infracfg-nao"); num_regmaps++; - of_node_put(node); - if (IS_ERR(regmap[2])) - return dev_err_probe(dev, PTR_ERR(regmap[2]), + if (IS_ERR(regmap[2])) { + ret = dev_err_probe(dev, PTR_ERR(regmap[2]), "%pOF: failed to get infracfg regmap\n", node); + of_node_put(node); + return ret; + } + of_node_put(node); } else { regmap[2] = NULL; } diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig index e8002526cfb0..d71dac9436e3 100644 --- a/drivers/regulator/Kconfig +++ b/drivers/regulator/Kconfig @@ -1231,6 +1231,7 @@ config REGULATOR_RASPBERRYPI_TOUCHSCREEN_ATTINY tristate "Raspberry Pi 7-inch touchscreen panel ATTINY regulator" depends on ARM || ARM64 || COMPILE_TEST depends on BACKLIGHT_CLASS_DEVICE + depends on GPIOLIB depends on I2C select REGMAP_I2C help diff --git a/drivers/regulator/qcom-rpmh-regulator.c b/drivers/regulator/qcom-rpmh-regulator.c index 6e4cb2871fca..0dcb50bf5c35 100644 --- a/drivers/regulator/qcom-rpmh-regulator.c +++ b/drivers/regulator/qcom-rpmh-regulator.c @@ -1512,7 +1512,7 @@ static const struct rpmh_vreg_init_data pmh0101_vreg_data[] = { RPMH_VREG("ldo13", LDO, 13, &pmic5_pldo530_mvp150, "vdd-l2-l13-l14"), RPMH_VREG("ldo14", LDO, 14, &pmic5_pldo530_mvp150, "vdd-l2-l13-l14"), RPMH_VREG("ldo15", LDO, 15, &pmic5_nldo530, "vdd-l15"), - RPMH_VREG("ldo16", LDO, 15, &pmic5_pldo530_mvp600, "vdd-l5-l16"), + RPMH_VREG("ldo16", LDO, 16, &pmic5_pldo530_mvp600, "vdd-l5-l16"), RPMH_VREG("ldo17", LDO, 17, &pmic5_pldo515_mv, "vdd-l17"), RPMH_VREG("ldo18", LDO, 18, &pmic5_nldo530, "vdd-l18"), RPMH_VREG("bob1", BOB, 1, &pmic5_bob, "vdd-bob1"), diff --git a/drivers/s390/char/Kconfig b/drivers/s390/char/Kconfig index 4d8f09910a46..7416f941e5b6 100644 --- a/drivers/s390/char/Kconfig +++ b/drivers/s390/char/Kconfig @@ -85,14 +85,6 @@ config HMC_DRV transfer cache size from its default value 0.5MB to N bytes. If N is zero, then no caching is performed. -config SCLP_OFB - def_bool n - prompt "Support for Open-for-Business SCLP Event" - depends on S390 - help - This option enables the Open-for-Business interface to the s390 - Service Element. - config S390_UV_UAPI def_tristate m prompt "Ultravisor userspace API" diff --git a/drivers/s390/char/sclp_config.c b/drivers/s390/char/sclp_config.c index 9cfbe3fc3dca..8c77e8c44fc2 100644 --- a/drivers/s390/char/sclp_config.c +++ b/drivers/s390/char/sclp_config.c @@ -80,14 +80,11 @@ static void sclp_conf_receiver_fn(struct evbuf_header *evbuf) static struct sclp_register sclp_conf_register = { -#ifdef CONFIG_SCLP_OFB .send_mask = EVTYP_CONFMGMDATA_MASK, -#endif .receive_mask = EVTYP_CONFMGMDATA_MASK, .receiver_fn = sclp_conf_receiver_fn, }; -#ifdef CONFIG_SCLP_OFB static int sclp_ofb_send_req(char *ev_data, size_t len) { static DEFINE_MUTEX(send_mutex); @@ -143,11 +140,9 @@ static const struct bin_attribute ofb_bin_attr = { }, .write = sysfs_ofb_data_write, }; -#endif static int __init sclp_ofb_setup(void) { -#ifdef CONFIG_SCLP_OFB struct kset *ofb_kset; int rc; @@ -159,7 +154,6 @@ static int __init sclp_ofb_setup(void) kset_unregister(ofb_kset); return rc; } -#endif return 0; } diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c index efb08b9b145a..80ab0ff921d4 100644 --- a/drivers/scsi/device_handler/scsi_dh_alua.c +++ b/drivers/scsi/device_handler/scsi_dh_alua.c @@ -37,7 +37,7 @@ #define TPGS_MODE_EXPLICIT 0x2 #define ALUA_RTPG_SIZE 128 -#define ALUA_FAILOVER_TIMEOUT 60 +#define ALUA_FAILOVER_TIMEOUT 255 /* max 255 (8-bit value) */ #define ALUA_FAILOVER_RETRIES 5 #define ALUA_RTPG_DELAY_MSECS 5 #define ALUA_RTPG_RETRY_DELAY 2 diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index fda07b193137..14d563e82d20 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -1491,7 +1491,7 @@ static void prep_ata_v3_hw(struct hisi_hba *hisi_hba, phy_id = device->phy->identify.phy_identifier; hdr->dw0 |= cpu_to_le32((1U << phy_id) << CMD_HDR_PHY_ID_OFF); - hdr->dw0 |= CMD_HDR_FORCE_PHY_MSK; + hdr->dw0 |= cpu_to_le32(CMD_HDR_FORCE_PHY_MSK); hdr->dw0 |= cpu_to_le32(4U << CMD_HDR_CMD_OFF); } diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index 6ff788557294..12caffeed3a0 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -2738,8 +2738,20 @@ scsih_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim) pcie_device->enclosure_level, pcie_device->connector_name); + /* + * The HBA firmware passes the NVMe drive's MDTS + * (Maximum Data Transfer Size) up to the driver. However, + * the driver hardcodes a 4K buffer size for the PRP list, + * accommodating at most 512 entries. This strictly limits + * the maximum supported NVMe I/O transfer to 2 MiB. + * + * Cap max_hw_sectors to the smaller of the drive's reported + * MDTS or the 2 MiB driver limit to prevent kernel oopses. + */ + lim->max_hw_sectors = SZ_2M >> SECTOR_SHIFT; if (pcie_device->nvme_mdts) - lim->max_hw_sectors = pcie_device->nvme_mdts / 512; + lim->max_hw_sectors = min(lim->max_hw_sectors, + pcie_device->nvme_mdts >> SECTOR_SHIFT); pcie_device_put(pcie_device); spin_unlock_irqrestore(&ioc->pcie_device_lock, flags); diff --git a/drivers/scsi/pmcraid.h b/drivers/scsi/pmcraid.h index 9f59930e8b4f..cd059b7599b4 100644 --- a/drivers/scsi/pmcraid.h +++ b/drivers/scsi/pmcraid.h @@ -657,7 +657,7 @@ struct pmcraid_hostrcb { */ struct pmcraid_instance { /* Array of allowed-to-be-exposed resources, initialized from - * Configutation Table, later updated with CCNs + * Configuration Table, later updated with CCNs */ struct pmcraid_resource_entry *res_entries; diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 2b4b2a1a8e44..74cd4e8a61c2 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1801,7 +1801,7 @@ sg_start_req(Sg_request *srp, unsigned char *cmd) } res = blk_rq_map_user_io(rq, md, hp->dxferp, hp->dxfer_len, - GFP_ATOMIC, iov_count, iov_count, 1, rw); + GFP_KERNEL, iov_count, iov_count, 1, rw); if (!res) { srp->bio = rq->bio; diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c index b4ed991976d0..2026ac645d6a 100644 --- a/drivers/scsi/smartpqi/smartpqi_init.c +++ b/drivers/scsi/smartpqi/smartpqi_init.c @@ -9427,6 +9427,7 @@ static void pqi_shutdown(struct pci_dev *pci_dev) pqi_crash_if_pending_command(ctrl_info); pqi_reset(ctrl_info); + pqi_ctrl_unblock_device_reset(ctrl_info); } static void pqi_process_lockup_action_param(void) diff --git a/drivers/spi/spi-amlogic-spisg.c b/drivers/spi/spi-amlogic-spisg.c index 19c5eba412ef..f9de2d2c9213 100644 --- a/drivers/spi/spi-amlogic-spisg.c +++ b/drivers/spi/spi-amlogic-spisg.c @@ -794,6 +794,7 @@ static int aml_spisg_probe(struct platform_device *pdev) dma_set_max_seg_size(&pdev->dev, SPISG_BLOCK_MAX); + init_completion(&spisg->completion); ret = devm_request_irq(&pdev->dev, irq, aml_spisg_irq, 0, NULL, spisg); if (ret) { dev_err(&pdev->dev, "irq request failed\n"); @@ -806,8 +807,6 @@ static int aml_spisg_probe(struct platform_device *pdev) goto out_clk; } - init_completion(&spisg->completion); - pm_runtime_put(&spisg->pdev->dev); return 0; diff --git a/drivers/spi/spi-axiado.c b/drivers/spi/spi-axiado.c index 9057a0a8df4a..649f149617ce 100644 --- a/drivers/spi/spi-axiado.c +++ b/drivers/spi/spi-axiado.c @@ -201,7 +201,7 @@ static void ax_spi_fill_tx_fifo(struct ax_spi *xspi) * then spi control did't work thoroughly, add one byte delay */ if (ax_spi_read(xspi, AX_SPI_IVR) & AX_SPI_IVR_TFOV) - usleep_range(10, 10); + udelay(10); if (xspi->tx_buf) ax_spi_write_b(xspi, AX_SPI_TXFIFO, *xspi->tx_buf++); else diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index 65aff2e70265..057381e56a7f 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -1860,14 +1860,10 @@ static int cqspi_probe(struct platform_device *pdev) if (irq < 0) return -ENXIO; - ret = pm_runtime_set_active(dev); - if (ret) - return ret; - ret = clk_bulk_prepare_enable(CLK_QSPI_NUM, cqspi->clks); if (ret) { dev_err(dev, "Cannot enable QSPI clocks.\n"); - goto disable_rpm; + return ret; } /* Obtain QSPI reset control */ @@ -1962,10 +1958,11 @@ static int cqspi_probe(struct platform_device *pdev) cqspi->sclk = 0; if (!(ddata && (ddata->quirks & CQSPI_DISABLE_RUNTIME_PM))) { - pm_runtime_enable(dev); pm_runtime_set_autosuspend_delay(dev, CQSPI_AUTOSUSPEND_TIMEOUT); pm_runtime_use_autosuspend(dev); pm_runtime_get_noresume(dev); + pm_runtime_set_active(dev); + pm_runtime_enable(dev); } host->num_chipselect = cqspi->num_chipselect; @@ -1977,7 +1974,7 @@ static int cqspi_probe(struct platform_device *pdev) ret = cqspi_request_mmap_dma(cqspi); if (ret == -EPROBE_DEFER) { dev_err_probe(&pdev->dev, ret, "Failed to request mmap DMA\n"); - goto disable_controller; + goto disable_rpm; } } @@ -1995,14 +1992,16 @@ static int cqspi_probe(struct platform_device *pdev) release_dma_chan: if (cqspi->rx_chan) dma_release_channel(cqspi->rx_chan); -disable_controller: - cqspi_controller_enable(cqspi, 0); -disable_clks: - if (pm_runtime_get_sync(&pdev->dev) >= 0) - clk_bulk_disable_unprepare(CLK_QSPI_NUM, cqspi->clks); disable_rpm: - if (!(ddata && (ddata->quirks & CQSPI_DISABLE_RUNTIME_PM))) + if (!(ddata && (ddata->quirks & CQSPI_DISABLE_RUNTIME_PM))) { pm_runtime_disable(dev); + pm_runtime_set_suspended(dev); + pm_runtime_put_noidle(dev); + pm_runtime_dont_use_autosuspend(dev); + } + cqspi_controller_enable(cqspi, 0); +disable_clks: + clk_bulk_disable_unprepare(CLK_QSPI_NUM, cqspi->clks); return ret; } @@ -2026,18 +2025,19 @@ static void cqspi_remove(struct platform_device *pdev) if (cqspi->rx_chan) dma_release_channel(cqspi->rx_chan); - cqspi_controller_enable(cqspi, 0); - - if (!(ddata && (ddata->quirks & CQSPI_DISABLE_RUNTIME_PM))) ret = pm_runtime_get_sync(&pdev->dev); - if (ret >= 0) + if (ret >= 0) { + cqspi_controller_enable(cqspi, 0); clk_bulk_disable_unprepare(CLK_QSPI_NUM, cqspi->clks); + } if (!(ddata && (ddata->quirks & CQSPI_DISABLE_RUNTIME_PM))) { - pm_runtime_put_sync(&pdev->dev); pm_runtime_disable(&pdev->dev); + pm_runtime_set_suspended(&pdev->dev); + pm_runtime_put_noidle(&pdev->dev); + pm_runtime_dont_use_autosuspend(&pdev->dev); } } diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c index 08d7dabe818d..891e2ba36958 100644 --- a/drivers/spi/spi-cadence.c +++ b/drivers/spi/spi-cadence.c @@ -741,7 +741,6 @@ static int cdns_spi_probe(struct platform_device *pdev) /* Set to default valid value */ ctlr->max_speed_hz = xspi->clk_rate / 4; xspi->speed_hz = ctlr->max_speed_hz; - pm_runtime_put_autosuspend(&pdev->dev); } else { ctlr->mode_bits |= SPI_NO_CS; ctlr->target_abort = cdns_target_abort; @@ -752,12 +751,17 @@ static int cdns_spi_probe(struct platform_device *pdev) goto clk_dis_all; } + if (!spi_controller_is_target(ctlr)) + pm_runtime_put_autosuspend(&pdev->dev); + return ret; clk_dis_all: if (!spi_controller_is_target(ctlr)) { pm_runtime_disable(&pdev->dev); pm_runtime_set_suspended(&pdev->dev); + pm_runtime_put_noidle(&pdev->dev); + pm_runtime_dont_use_autosuspend(&pdev->dev); } remove_ctlr: spi_controller_put(ctlr); @@ -776,16 +780,23 @@ static void cdns_spi_remove(struct platform_device *pdev) { struct spi_controller *ctlr = platform_get_drvdata(pdev); struct cdns_spi *xspi = spi_controller_get_devdata(ctlr); + int ret = 0; + + if (!spi_controller_is_target(ctlr)) + ret = pm_runtime_get_sync(&pdev->dev); spi_controller_get(ctlr); spi_unregister_controller(ctlr); - cdns_spi_write(xspi, CDNS_SPI_ER, CDNS_SPI_ER_DISABLE); + if (ret >= 0) + cdns_spi_write(xspi, CDNS_SPI_ER, CDNS_SPI_ER_DISABLE); if (!spi_controller_is_target(ctlr)) { pm_runtime_disable(&pdev->dev); pm_runtime_set_suspended(&pdev->dev); + pm_runtime_put_noidle(&pdev->dev); + pm_runtime_dont_use_autosuspend(&pdev->dev); } spi_controller_put(ctlr); diff --git a/drivers/spi/spi-ch341.c b/drivers/spi/spi-ch341.c index 3eaa8f176f63..6448a44a8b67 100644 --- a/drivers/spi/spi-ch341.c +++ b/drivers/spi/spi-ch341.c @@ -250,5 +250,5 @@ static struct usb_driver ch341a_usb_driver = { module_usb_driver(ch341a_usb_driver); MODULE_AUTHOR("Johannes Thumshirn <jth@kernel.org>"); -MODULE_DESCRIPTION("QiHeng Electronics ch341 USB2SPI"); +MODULE_DESCRIPTION("Nanjing Qinheng Microelectronics CH341 USB2SPI driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index e5c907c45b87..480d1e8b281f 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -1382,9 +1382,7 @@ static int spi_imx_setupxfer(struct spi_device *spi, spi_imx->target_burst = t->len; } - spi_imx->devtype_data->prepare_transfer(spi_imx, spi, t); - - return 0; + return spi_imx->devtype_data->prepare_transfer(spi_imx, spi, t); } static void spi_imx_sdma_exit(struct spi_imx_data *spi_imx) @@ -1709,6 +1707,7 @@ static int spi_imx_dma_data_prepare(struct spi_imx_data *spi_imx, kfree(spi_imx->dma_data[0].dma_tx_buf); kfree(spi_imx->dma_data[0].dma_rx_buf); kfree(spi_imx->dma_data); + return ret; } } @@ -1836,7 +1835,7 @@ static void spi_imx_dma_max_wml_find(struct spi_imx_data *spi_imx, unsigned int i; for (i = spi_imx->devtype_data->fifo_size / 2; i > 0; i--) { - if (!dma_data->dma_len % (i * bytes_per_word)) + if (!(dma_data->dma_len % (i * bytes_per_word))) break; } /* Use 1 as wml in case no available burst length got */ diff --git a/drivers/spi/spi-microchip-core-qspi.c b/drivers/spi/spi-microchip-core-qspi.c index eab059fb0bc2..4dee0fea1df8 100644 --- a/drivers/spi/spi-microchip-core-qspi.c +++ b/drivers/spi/spi-microchip-core-qspi.c @@ -74,6 +74,13 @@ #define STATUS_FLAGSX4 BIT(8) #define STATUS_MASK GENMASK(8, 0) +/* + * QSPI Direct Access register defines + */ +#define DIRECT_ACCESS_EN_SSEL BIT(0) +#define DIRECT_ACCESS_OP_SSEL BIT(1) +#define DIRECT_ACCESS_OP_SSEL_SHIFT 1 + #define BYTESUPPER_MASK GENMASK(31, 16) #define BYTESLOWER_MASK GENMASK(15, 0) @@ -158,7 +165,39 @@ static int mchp_coreqspi_set_mode(struct mchp_coreqspi *qspi, const struct spi_m return 0; } -static inline void mchp_coreqspi_read_op(struct mchp_coreqspi *qspi) +static void mchp_coreqspi_set_cs(struct spi_device *spi, bool enable) +{ + struct mchp_coreqspi *qspi = spi_controller_get_devdata(spi->controller); + u32 val; + + val = readl(qspi->regs + REG_DIRECT_ACCESS); + + val &= ~DIRECT_ACCESS_OP_SSEL; + val |= !enable << DIRECT_ACCESS_OP_SSEL_SHIFT; + + writel(val, qspi->regs + REG_DIRECT_ACCESS); +} + +static int mchp_coreqspi_setup(struct spi_device *spi) +{ + struct mchp_coreqspi *qspi = spi_controller_get_devdata(spi->controller); + u32 val; + + /* + * Active low devices need to be specifically set to their inactive + * states during probe. + */ + if (spi->mode & SPI_CS_HIGH) + return 0; + + val = readl(qspi->regs + REG_DIRECT_ACCESS); + val |= DIRECT_ACCESS_OP_SSEL; + writel(val, qspi->regs + REG_DIRECT_ACCESS); + + return 0; +} + +static void mchp_coreqspi_read_op(struct mchp_coreqspi *qspi) { u32 control, data; @@ -194,7 +233,7 @@ static inline void mchp_coreqspi_read_op(struct mchp_coreqspi *qspi) } } -static inline void mchp_coreqspi_write_op(struct mchp_coreqspi *qspi) +static void mchp_coreqspi_write_op(struct mchp_coreqspi *qspi) { u32 control, data; @@ -222,7 +261,7 @@ static inline void mchp_coreqspi_write_op(struct mchp_coreqspi *qspi) } } -static inline void mchp_coreqspi_write_read_op(struct mchp_coreqspi *qspi) +static void mchp_coreqspi_write_read_op(struct mchp_coreqspi *qspi) { u32 control, data; @@ -380,20 +419,7 @@ static int mchp_coreqspi_setup_clock(struct mchp_coreqspi *qspi, struct spi_devi return 0; } -static int mchp_coreqspi_setup_op(struct spi_device *spi_dev) -{ - struct spi_controller *ctlr = spi_dev->controller; - struct mchp_coreqspi *qspi = spi_controller_get_devdata(ctlr); - u32 control = readl_relaxed(qspi->regs + REG_CONTROL); - - control |= (CONTROL_MASTER | CONTROL_ENABLE); - control &= ~CONTROL_CLKIDLE; - writel_relaxed(control, qspi->regs + REG_CONTROL); - - return 0; -} - -static inline void mchp_coreqspi_config_op(struct mchp_coreqspi *qspi, const struct spi_mem_op *op) +static void mchp_coreqspi_config_op(struct mchp_coreqspi *qspi, const struct spi_mem_op *op) { u32 idle_cycles = 0; int total_bytes, cmd_bytes, frames, ctrl; @@ -483,6 +509,7 @@ static int mchp_coreqspi_exec_op(struct spi_mem *mem, const struct spi_mem_op *o reinit_completion(&qspi->data_completion); mchp_coreqspi_config_op(qspi, op); + mchp_coreqspi_set_cs(mem->spi, true); if (op->cmd.opcode) { qspi->txbuf = &opcode; qspi->rxbuf = NULL; @@ -523,6 +550,7 @@ static int mchp_coreqspi_exec_op(struct spi_mem *mem, const struct spi_mem_op *o err = -ETIMEDOUT; error: + mchp_coreqspi_set_cs(mem->spi, false); mutex_unlock(&qspi->op_lock); mchp_coreqspi_disable_ints(qspi); @@ -662,18 +690,28 @@ static int mchp_coreqspi_transfer_one(struct spi_controller *ctlr, struct spi_de struct spi_transfer *t) { struct mchp_coreqspi *qspi = spi_controller_get_devdata(ctlr); + bool dual_quad = false; qspi->tx_len = t->len; + if (t->tx_nbits == SPI_NBITS_QUAD || t->rx_nbits == SPI_NBITS_QUAD || + t->tx_nbits == SPI_NBITS_DUAL || + t->rx_nbits == SPI_NBITS_DUAL) + dual_quad = true; + if (t->tx_buf) qspi->txbuf = (u8 *)t->tx_buf; if (!t->rx_buf) { mchp_coreqspi_write_op(qspi); - } else { + } else if (!dual_quad) { qspi->rxbuf = (u8 *)t->rx_buf; qspi->rx_len = t->len; mchp_coreqspi_write_read_op(qspi); + } else { + qspi->rxbuf = (u8 *)t->rx_buf; + qspi->rx_len = t->len; + mchp_coreqspi_read_op(qspi); } return 0; @@ -686,6 +724,7 @@ static int mchp_coreqspi_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct device_node *np = dev->of_node; int ret; + u32 num_cs, val; ctlr = devm_spi_alloc_host(&pdev->dev, sizeof(*qspi)); if (!ctlr) @@ -718,10 +757,18 @@ static int mchp_coreqspi_probe(struct platform_device *pdev) return ret; } + /* + * The IP core only has a single CS, any more have to be provided via + * gpios + */ + if (of_property_read_u32(pdev->dev.of_node, "num-cs", &num_cs)) + num_cs = 1; + + ctlr->num_chipselect = num_cs; + ctlr->bits_per_word_mask = SPI_BPW_MASK(8); ctlr->mem_ops = &mchp_coreqspi_mem_ops; ctlr->mem_caps = &mchp_coreqspi_mem_caps; - ctlr->setup = mchp_coreqspi_setup_op; ctlr->mode_bits = SPI_CPOL | SPI_CPHA | SPI_RX_DUAL | SPI_RX_QUAD | SPI_TX_DUAL | SPI_TX_QUAD; ctlr->dev.of_node = np; @@ -729,9 +776,21 @@ static int mchp_coreqspi_probe(struct platform_device *pdev) ctlr->prepare_message = mchp_coreqspi_prepare_message; ctlr->unprepare_message = mchp_coreqspi_unprepare_message; ctlr->transfer_one = mchp_coreqspi_transfer_one; - ctlr->num_chipselect = 2; + ctlr->setup = mchp_coreqspi_setup; + ctlr->set_cs = mchp_coreqspi_set_cs; ctlr->use_gpio_descriptors = true; + val = readl_relaxed(qspi->regs + REG_CONTROL); + val |= (CONTROL_MASTER | CONTROL_ENABLE); + writel_relaxed(val, qspi->regs + REG_CONTROL); + + /* + * Put cs into software controlled mode + */ + val = readl_relaxed(qspi->regs + REG_DIRECT_ACCESS); + val |= DIRECT_ACCESS_EN_SSEL; + writel(val, qspi->regs + REG_DIRECT_ACCESS); + ret = spi_register_controller(ctlr); if (ret) return dev_err_probe(&pdev->dev, ret, diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c index 14cd1b9d9793..231fbcf0e7aa 100644 --- a/drivers/spi/spi-rockchip.c +++ b/drivers/spi/spi-rockchip.c @@ -98,7 +98,6 @@ #define CR0_FRF_MICROWIRE 0x2 #define CR0_XFM_OFFSET 18 -#define CR0_XFM_MASK (0x03 << SPI_XFM_OFFSET) #define CR0_XFM_TR 0x0 #define CR0_XFM_TO 0x1 #define CR0_XFM_RO 0x2 @@ -109,8 +108,6 @@ #define CR0_SOI_OFFSET 23 -#define CR0_MTM_OFFSET 0x21 - /* Bit fields in SER, 2bit */ #define SER_MASK 0x3 @@ -357,7 +354,8 @@ static irqreturn_t rockchip_spi_isr(int irq, void *dev_id) struct rockchip_spi *rs = spi_controller_get_devdata(ctlr); /* When int_cs_inactive comes, spi target abort */ - if (rs->cs_inactive && readl_relaxed(rs->regs + ROCKCHIP_SPI_IMR) & INT_CS_INACTIVE) { + if (rs->cs_inactive && + (readl_relaxed(rs->regs + ROCKCHIP_SPI_ISR) & INT_CS_INACTIVE)) { ctlr->target_abort(ctlr); writel_relaxed(0, rs->regs + ROCKCHIP_SPI_IMR); writel_relaxed(0xffffffff, rs->regs + ROCKCHIP_SPI_ICR); diff --git a/drivers/spi/spi-rzv2h-rspi.c b/drivers/spi/spi-rzv2h-rspi.c index f45af5884638..1655efda7d20 100644 --- a/drivers/spi/spi-rzv2h-rspi.c +++ b/drivers/spi/spi-rzv2h-rspi.c @@ -579,7 +579,7 @@ static u32 rzv2h_rspi_setup_clock(struct rzv2h_rspi_priv *rspi, u32 hz) rspi->info->find_pclk_rate(rspi->pclk, hz, &best_clock); if (!best_clock.clk_rate) - return -EINVAL; + return 0; ret = clk_set_rate(best_clock.clk, best_clock.clk_rate); if (ret) diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index e80449f6ce15..cb832fd523af 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -995,6 +995,7 @@ int iscsit_setup_scsi_cmd(struct iscsit_conn *conn, struct iscsit_cmd *cmd, int data_direction, payload_length; struct iscsi_ecdb_ahdr *ecdb_ahdr; struct iscsi_scsi_req *hdr; + u16 ahslength, cdb_length; int iscsi_task_attr; unsigned char *cdb; int sam_task_attr; @@ -1108,14 +1109,27 @@ int iscsit_setup_scsi_cmd(struct iscsit_conn *conn, struct iscsit_cmd *cmd, ISCSI_REASON_CMD_NOT_SUPPORTED, buf); } - cdb = kmalloc(be16_to_cpu(ecdb_ahdr->ahslength) + 15, - GFP_KERNEL); + ahslength = be16_to_cpu(ecdb_ahdr->ahslength); + if (!ahslength) { + pr_err("Extended CDB AHS with zero length, protocol error.\n"); + return iscsit_add_reject_cmd(cmd, + ISCSI_REASON_PROTOCOL_ERROR, buf); + } + if (ahslength > (hdr->hlength * 4) - 3) { + pr_err("Extended CDB AHS length %u exceeds available PDU buffer.\n", + ahslength); + return iscsit_add_reject_cmd(cmd, + ISCSI_REASON_PROTOCOL_ERROR, buf); + } + + cdb_length = ahslength - 1 + ISCSI_CDB_SIZE; + + cdb = kmalloc(cdb_length, GFP_KERNEL); if (cdb == NULL) return iscsit_add_reject_cmd(cmd, ISCSI_REASON_BOOKMARK_NO_RESOURCES, buf); memcpy(cdb, hdr->cdb, ISCSI_CDB_SIZE); - memcpy(cdb + ISCSI_CDB_SIZE, ecdb_ahdr->ecdb, - be16_to_cpu(ecdb_ahdr->ahslength) - 1); + memcpy(cdb + ISCSI_CDB_SIZE, ecdb_ahdr->ecdb, cdb_length - ISCSI_CDB_SIZE); } data_direction = (hdr->flags & ISCSI_FLAG_CMD_WRITE) ? DMA_TO_DEVICE : diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c index d93773b3227c..2b19a956007b 100644 --- a/drivers/target/target_core_configfs.c +++ b/drivers/target/target_core_configfs.c @@ -3249,7 +3249,7 @@ static ssize_t target_tg_pt_gp_members_show(struct config_item *item, config_item_name(&lun->lun_group.cg_item)); cur_len++; /* Extra byte for NULL terminator */ - if ((cur_len + len) > PAGE_SIZE) { + if (cur_len > TG_PT_GROUP_NAME_BUF || (cur_len + len) > PAGE_SIZE) { pr_warn("Ran out of lu_gp_show_attr" "_members buffer\n"); break; diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 4805e40ed4d7..c3f08957d179 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -9259,6 +9259,30 @@ static void ufshcd_config_mcq(struct ufs_hba *hba) hba->nutrs); } +/** + * ufshcd_get_op_mode - get UFS operating mode. + * @hba: per-adapter instance + * + * Use the PA_PWRMODE value to represent the operating mode of UFS. + * + */ +static enum ufs_op_mode ufshcd_get_op_mode(struct ufs_hba *hba) +{ + u32 mode; + u8 rx_mode; + u8 tx_mode; + + ufshcd_dme_get(hba, UIC_ARG_MIB(PA_PWRMODE), &mode); + rx_mode = (mode >> PWRMODE_RX_OFFSET) & PWRMODE_MASK; + tx_mode = mode & PWRMODE_MASK; + + if ((rx_mode == SLOW_MODE || rx_mode == SLOWAUTO_MODE) && + (tx_mode == SLOW_MODE || tx_mode == SLOWAUTO_MODE)) + return LS_MODE; + + return HS_MODE; +} + static int ufshcd_post_device_init(struct ufs_hba *hba) { int ret; @@ -9281,11 +9305,13 @@ static int ufshcd_post_device_init(struct ufs_hba *hba) return 0; /* - * Set the right value to bRefClkFreq before attempting to + * Set the right value to bRefClkFreq in LS_MODE before attempting to * switch to HS gears. */ - if (hba->dev_ref_clk_freq != REF_CLK_FREQ_INVAL) + if (ufshcd_get_op_mode(hba) == LS_MODE && + hba->dev_ref_clk_freq != REF_CLK_FREQ_INVAL) ufshcd_set_dev_ref_clk(hba); + /* Gear up to HS gear. */ ret = ufshcd_config_pwr_mode(hba, &hba->max_pwr_info.info, UFSHCD_PMC_POLICY_DONT_FORCE); diff --git a/drivers/video/fbdev/core/fb_defio.c b/drivers/video/fbdev/core/fb_defio.c index a12dd25ab697..fd00b86e1ae6 100644 --- a/drivers/video/fbdev/core/fb_defio.c +++ b/drivers/video/fbdev/core/fb_defio.c @@ -14,7 +14,6 @@ #include <linux/export.h> #include <linux/string.h> #include <linux/mm.h> -#include <linux/module.h> #include <linux/vmalloc.h> #include <linux/delay.h> #include <linux/interrupt.h> diff --git a/drivers/video/fbdev/udlfb.c b/drivers/video/fbdev/udlfb.c index c341d76bc564..fdbb8671a810 100644 --- a/drivers/video/fbdev/udlfb.c +++ b/drivers/video/fbdev/udlfb.c @@ -321,12 +321,32 @@ static int dlfb_set_video_mode(struct dlfb_data *dlfb, return retval; } +static void dlfb_vm_open(struct vm_area_struct *vma) +{ + struct dlfb_data *dlfb = vma->vm_private_data; + + atomic_inc(&dlfb->mmap_count); +} + +static void dlfb_vm_close(struct vm_area_struct *vma) +{ + struct dlfb_data *dlfb = vma->vm_private_data; + + atomic_dec(&dlfb->mmap_count); +} + +static const struct vm_operations_struct dlfb_vm_ops = { + .open = dlfb_vm_open, + .close = dlfb_vm_close, +}; + static int dlfb_ops_mmap(struct fb_info *info, struct vm_area_struct *vma) { unsigned long start = vma->vm_start; unsigned long size = vma->vm_end - vma->vm_start; unsigned long offset = vma->vm_pgoff << PAGE_SHIFT; unsigned long page, pos; + struct dlfb_data *dlfb = info->par; if (info->fbdefio) return fb_deferred_io_mmap(info, vma); @@ -358,6 +378,9 @@ static int dlfb_ops_mmap(struct fb_info *info, struct vm_area_struct *vma) size = 0; } + vma->vm_ops = &dlfb_vm_ops; + vma->vm_private_data = dlfb; + atomic_inc(&dlfb->mmap_count); return 0; } @@ -1176,7 +1199,6 @@ static void dlfb_deferred_vfree(struct dlfb_data *dlfb, void *mem) /* * Assumes &info->lock held by caller - * Assumes no active clients have framebuffer open */ static int dlfb_realloc_framebuffer(struct dlfb_data *dlfb, struct fb_info *info, u32 new_len) { @@ -1188,6 +1210,13 @@ static int dlfb_realloc_framebuffer(struct dlfb_data *dlfb, struct fb_info *info new_len = PAGE_ALIGN(new_len); if (new_len > old_len) { + if (atomic_read(&dlfb->mmap_count) > 0) { + dev_warn(info->dev, + "refusing realloc: %d active mmaps\n", + atomic_read(&dlfb->mmap_count)); + return -EBUSY; + } + /* * Alloc system memory for virtual framebuffer */ diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c index 15ba592236e8..725a49a0eee7 100644 --- a/drivers/xen/privcmd.c +++ b/drivers/xen/privcmd.c @@ -1620,6 +1620,12 @@ static void privcmd_close(struct vm_area_struct *vma) kvfree(pages); } +static int privcmd_may_split(struct vm_area_struct *area, unsigned long addr) +{ + /* Forbid splitting, avoids double free via privcmd_close(). */ + return -EINVAL; +} + static vm_fault_t privcmd_fault(struct vm_fault *vmf) { printk(KERN_DEBUG "privcmd_fault: vma=%p %lx-%lx, pgoff=%lx, uv=%p\n", @@ -1631,6 +1637,7 @@ static vm_fault_t privcmd_fault(struct vm_fault *vmf) static const struct vm_operations_struct privcmd_vm_ops = { .close = privcmd_close, + .may_split = privcmd_may_split, .fault = privcmd_fault }; diff --git a/drivers/xen/sys-hypervisor.c b/drivers/xen/sys-hypervisor.c index b1bb01ba82f8..91923242a5ae 100644 --- a/drivers/xen/sys-hypervisor.c +++ b/drivers/xen/sys-hypervisor.c @@ -366,6 +366,8 @@ static ssize_t buildid_show(struct hyp_sysfs_attr *attr, char *buffer) ret = sprintf(buffer, "<denied>"); return ret; } + if (ret > PAGE_SIZE) + return -ENOSPC; buildid = kmalloc(sizeof(*buildid) + ret, GFP_KERNEL); if (!buildid) @@ -373,8 +375,10 @@ static ssize_t buildid_show(struct hyp_sysfs_attr *attr, char *buffer) buildid->len = ret; ret = HYPERVISOR_xen_version(XENVER_build_id, buildid); - if (ret > 0) - ret = sprintf(buffer, "%s", buildid->buf); + if (ret > 0) { + /* Build id is binary, not a string. */ + memcpy(buffer, buildid->buf, ret); + } kfree(buildid); return ret; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index ca3e4b99aec2..2275189b7860 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4641,7 +4641,8 @@ int try_release_extent_buffer(struct folio *folio) * to read the block we will not block on anything. */ void btrfs_readahead_tree_block(struct btrfs_fs_info *fs_info, - u64 bytenr, u64 owner_root, u64 gen, int level) + u64 bytenr, u64 owner_root, u64 gen, int level, + const struct btrfs_key *first_key) { struct btrfs_tree_parent_check check = { .level = level, @@ -4650,6 +4651,11 @@ void btrfs_readahead_tree_block(struct btrfs_fs_info *fs_info, struct extent_buffer *eb; int ret; + if (first_key) { + memcpy(&check.first_key, first_key, sizeof(struct btrfs_key)); + check.has_first_key = true; + } + eb = btrfs_find_create_tree_block(fs_info, bytenr, owner_root, level); if (IS_ERR(eb)) return; @@ -4677,9 +4683,13 @@ void btrfs_readahead_tree_block(struct btrfs_fs_info *fs_info, */ void btrfs_readahead_node_child(struct extent_buffer *node, int slot) { + struct btrfs_key node_key; + + btrfs_node_key_to_cpu(node, &node_key, slot); btrfs_readahead_tree_block(node->fs_info, btrfs_node_blockptr(node, slot), btrfs_header_owner(node), btrfs_node_ptr_generation(node, slot), - btrfs_header_level(node) - 1); + btrfs_header_level(node) - 1, + &node_key); } diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index fd209233317f..b310a5145cf6 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -287,7 +287,8 @@ static inline void wait_on_extent_buffer_writeback(struct extent_buffer *eb) } void btrfs_readahead_tree_block(struct btrfs_fs_info *fs_info, - u64 bytenr, u64 owner_root, u64 gen, int level); + u64 bytenr, u64 owner_root, u64 gen, int level, + const struct btrfs_key *first_key); void btrfs_readahead_node_child(struct extent_buffer *node, int slot); /* Note: this can be used in for loops without caching the value in a variable. */ diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index 9efd1ec90f03..472b3060e5ac 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -259,7 +259,11 @@ int btrfs_convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans, nr++; path->slots[0]--; } else { - ASSERT(0); + btrfs_err(fs_info, "unexpected free space tree key type %u", + found_key.type); + ret = -EUCLEAN; + btrfs_abort_transaction(trans, ret); + goto out; } } @@ -405,7 +409,11 @@ int btrfs_convert_free_space_to_extents(struct btrfs_trans_handle *trans, nr++; } else { - ASSERT(0); + btrfs_err(fs_info, "unexpected free space tree key type %u", + found_key.type); + ret = -EUCLEAN; + btrfs_abort_transaction(trans, ret); + goto out; } } @@ -1518,7 +1526,11 @@ int btrfs_remove_block_group_free_space(struct btrfs_trans_handle *trans, nr++; path->slots[0]--; } else { - ASSERT(0); + btrfs_err(trans->fs_info, "unexpected free space tree key type %u", + found_key.type); + ret = -EUCLEAN; + btrfs_abort_transaction(trans, ret); + return ret; } } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 40474014c03f..906d5c21ebc4 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1153,7 +1153,7 @@ out_free_reserve: NULL, &cached, EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | - EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING, + EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV, PAGE_UNLOCK | PAGE_START_WRITEBACK | PAGE_END_WRITEBACK); if (async_extent->cb) @@ -4959,6 +4959,8 @@ static int btrfs_rmdir(struct inode *vfs_dir, struct dentry *dentry) if (ret) goto out; + btrfs_record_unlink_dir(trans, dir, inode, false); + /* now the directory is empty */ ret = btrfs_unlink_inode(trans, dir, inode, &fname.disk_name); if (!ret) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index b2e447f5005c..a39460bf68a7 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -5102,7 +5102,6 @@ static int btrfs_ioctl_subvol_sync(struct btrfs_fs_info *fs_info, void __user *a return 0; } -#ifdef CONFIG_BTRFS_EXPERIMENTAL static int btrfs_ioctl_shutdown(struct btrfs_fs_info *fs_info, unsigned long arg) { int ret = 0; @@ -5134,10 +5133,12 @@ static int btrfs_ioctl_shutdown(struct btrfs_fs_info *fs_info, unsigned long arg case BTRFS_SHUTDOWN_FLAGS_NOLOGFLUSH: btrfs_force_shutdown(fs_info); break; + default: + ret = -EINVAL; + break; } return ret; } -#endif long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg) @@ -5294,10 +5295,8 @@ long btrfs_ioctl(struct file *file, unsigned int #endif case BTRFS_IOC_SUBVOL_SYNC_WAIT: return btrfs_ioctl_subvol_sync(fs_info, argp); -#ifdef CONFIG_BTRFS_EXPERIMENTAL case BTRFS_IOC_SHUTDOWN: return btrfs_ioctl_shutdown(fs_info, arg); -#endif } return -ENOTTY; diff --git a/fs/btrfs/raid-stripe-tree.c b/fs/btrfs/raid-stripe-tree.c index 638c4ad572c9..4b0186c83ad1 100644 --- a/fs/btrfs/raid-stripe-tree.c +++ b/fs/btrfs/raid-stripe-tree.c @@ -45,8 +45,11 @@ static int btrfs_partially_delete_raid_extent(struct btrfs_trans_handle *trans, for (int i = 0; i < btrfs_num_raid_stripes(item_size); i++) { struct btrfs_raid_stride *stride = &extent->strides[i]; + u64 devid; u64 phys; + devid = btrfs_raid_stride_devid(leaf, stride); + btrfs_set_stack_raid_stride_devid(&newitem->strides[i], devid); phys = btrfs_raid_stride_physical(leaf, stride) + frontpad; btrfs_set_stack_raid_stride_physical(&newitem->strides[i], phys); } @@ -95,14 +98,26 @@ int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 le while (1) { key.objectid = start; key.type = BTRFS_RAID_STRIPE_KEY; - key.offset = 0; + key.offset = (u64)-1; ret = btrfs_search_slot(trans, stripe_root, &key, path, -1, 1); if (ret < 0) break; - if (path->slots[0] == btrfs_header_nritems(path->nodes[0])) - path->slots[0]--; + /* + * Search with offset=(u64)-1 ensures we land on the correct + * leaf even when the target entry is the first item on a leaf. + * Since no real entry has offset=(u64)-1, ret is always 1 and + * slot points past the last entry with objectid==start (or + * past the end of the leaf if that entry is the last item). + * Back up one slot to find the actual entry. + */ + if (path->slots[0] == 0) { + /* No entry with objectid <= start exists. */ + ret = 0; + break; + } + path->slots[0]--; leaf = path->nodes[0]; slot = path->slots[0]; @@ -123,7 +138,7 @@ int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 le */ if (found_start > start) { if (slot == 0) { - ret = btrfs_previous_item(stripe_root, path, start, + ret = btrfs_previous_item(stripe_root, path, 0, BTRFS_RAID_STRIPE_KEY); if (ret) { if (ret > 0) @@ -139,7 +154,10 @@ int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 le btrfs_item_key_to_cpu(leaf, &key, slot); found_start = key.objectid; found_end = found_start + key.offset; - ASSERT(found_start <= start); + if (found_start > start || found_end <= start) { + ret = -ENOENT; + break; + } } if (key.type != BTRFS_RAID_STRIPE_KEY) @@ -176,9 +194,19 @@ int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 le /* The "right" item. */ ret = btrfs_duplicate_item(trans, stripe_root, path, &newkey); + if (ret == -EAGAIN) { + btrfs_release_path(path); + continue; + } if (ret) break; + /* + * btrfs_duplicate_item() may have triggered a leaf + * split via setup_leaf_for_split(), so we must refresh + * our leaf pointer from the path. + */ + leaf = path->nodes[0]; item_size = btrfs_item_size(leaf, path->slots[0]); extent = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_stripe_extent); @@ -195,8 +223,9 @@ int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 le /* The "left" item. */ path->slots[0]--; btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); - btrfs_partially_delete_raid_extent(trans, path, &key, - diff_start, 0); + ret = btrfs_partially_delete_raid_extent(trans, path, + &key, + diff_start, 0); break; } @@ -212,8 +241,11 @@ int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 le if (found_start < start) { u64 diff_start = start - found_start; - btrfs_partially_delete_raid_extent(trans, path, &key, - diff_start, 0); + ret = btrfs_partially_delete_raid_extent(trans, path, + &key, + diff_start, 0); + if (ret) + break; start += (key.offset - diff_start); length -= (key.offset - diff_start); @@ -236,9 +268,10 @@ int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 le if (found_end > end) { u64 diff_end = found_end - end; - btrfs_partially_delete_raid_extent(trans, path, &key, - key.offset - length, - length); + ret = btrfs_partially_delete_raid_extent(trans, path, + &key, + key.offset - length, + length); ASSERT(key.offset - diff_end == length); break; } diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 1c42c5180bdd..3ebaf5880125 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -2607,7 +2607,7 @@ int relocate_tree_blocks(struct btrfs_trans_handle *trans, if (!block->key_ready) btrfs_readahead_tree_block(fs_info, block->bytenr, block->owner, 0, - block->level); + block->level, NULL); } /* Get first keys */ @@ -3876,7 +3876,7 @@ static int add_remap_tree_entries(struct btrfs_trans_handle *trans, struct btrfs ret = btrfs_insert_empty_items(trans, fs_info->remap_root, path, &batch); btrfs_release_path(path); - if (num_entries <= max_items) + if (ret || num_entries <= max_items) break; num_entries -= max_items; @@ -4174,6 +4174,12 @@ static int move_existing_remap(struct btrfs_fs_info *fs_info, return ret; } + if (ins.offset < length) { + spin_lock(&sinfo->lock); + btrfs_space_info_update_bytes_may_use(sinfo, ins.offset - length); + spin_unlock(&sinfo->lock); + } + dest_addr = ins.objectid; dest_length = ins.offset; @@ -5000,6 +5006,12 @@ static int do_remap_reloc_trans(struct btrfs_fs_info *fs_info, return ret; } + if (ins.offset < remap_length) { + spin_lock(&sinfo->lock); + btrfs_space_info_update_bytes_may_use(sinfo, ins.offset - remap_length); + spin_unlock(&sinfo->lock); + } + made_reservation = true; new_addr = ins.objectid; @@ -5023,21 +5035,27 @@ static int do_remap_reloc_trans(struct btrfs_fs_info *fs_info, if (bg_needs_free_space) { ret = btrfs_add_block_group_free_space(trans, dest_bg); - if (ret) + if (ret) { + btrfs_abort_transaction(trans, ret); goto fail; + } } ret = copy_remapped_data(fs_info, start, new_addr, length); - if (ret) + if (ret) { + btrfs_abort_transaction(trans, ret); goto fail; + } ret = btrfs_remove_from_free_space_tree(trans, new_addr, length); - if (ret) + if (ret) { + btrfs_abort_transaction(trans, ret); goto fail; + } ret = add_remap_entry(trans, path, src_bg, start, new_addr, length); if (ret) { - btrfs_add_to_free_space_tree(trans, new_addr, length); + btrfs_abort_transaction(trans, ret); goto fail; } diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index 1c5224cf183e..733c19571f1c 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -191,13 +191,10 @@ static const struct dentry_operations efivarfs_d_ops = { static struct dentry *efivarfs_alloc_dentry(struct dentry *parent, char *name) { + struct qstr q = QSTR(name); struct dentry *d; - struct qstr q; int err; - q.name = name; - q.len = strlen(name); - err = efivarfs_d_hash(parent, &q); if (err) return ERR_PTR(err); diff --git a/fs/isofs/export.c b/fs/isofs/export.c index 421d247fae52..78f80c1a5c54 100644 --- a/fs/isofs/export.c +++ b/fs/isofs/export.c @@ -24,7 +24,7 @@ isofs_export_iget(struct super_block *sb, { struct inode *inode; - if (block == 0) + if (block == 0 || block >= ISOFS_SB(sb)->s_nzones) return ERR_PTR(-ESTALE); inode = isofs_iget(sb, block, offset); if (IS_ERR(inode)) diff --git a/fs/isofs/namei.c b/fs/isofs/namei.c index 8dd3911717e0..3ace3d6a55e7 100644 --- a/fs/isofs/namei.c +++ b/fs/isofs/namei.c @@ -10,20 +10,13 @@ #include <linux/gfp.h> #include "isofs.h" -/* - * ok, we cannot use strncmp, as the name is not in our data space. - * Thus we'll have to use isofs_match. No big problem. Match also makes - * some sanity tests. - */ static int isofs_cmp(struct dentry *dentry, const char *compare, int dlen) { - struct qstr qstr; - qstr.name = compare; - qstr.len = dlen; if (likely(!dentry->d_op)) return dentry->d_name.len != dlen || memcmp(dentry->d_name.name, compare, dlen); - return dentry->d_op->d_compare(NULL, dentry->d_name.len, dentry->d_name.name, &qstr); + return dentry->d_op->d_compare(NULL, dentry->d_name.len, dentry->d_name.name, + &QSTR_LEN(compare, dlen)); } /* diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c index 6fe6dbd0c740..1232fab59a4e 100644 --- a/fs/isofs/rock.c +++ b/fs/isofs/rock.c @@ -101,6 +101,15 @@ static int rock_continue(struct rock_state *rs) goto out; } + if ((unsigned)rs->cont_extent >= ISOFS_SB(rs->inode->i_sb)->s_nzones) { + printk(KERN_NOTICE "rock: corrupted directory entry. " + "extent=%u out of volume (nzones=%lu)\n", + (unsigned)rs->cont_extent, + ISOFS_SB(rs->inode->i_sb)->s_nzones); + ret = -EIO; + goto out; + } + if (rs->cont_extent) { struct buffer_head *bh; diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index bfe884d624e7..38290b9c07f7 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -457,7 +457,7 @@ static int fanotify_encode_fh(struct fanotify_fh *fh, struct inode *inode, /* * Unlike file_handle, type and len of struct fanotify_fh are u8. * Traditionally, filesystem return handle_type < 0xff, but there - * is no enforecement for that in vfs. + * is no enforcement for that in vfs. */ BUILD_BUG_ON(MAX_HANDLE_SZ > 0xff || FILEID_INVALID > 0xff); if (type <= 0 || type >= FILEID_INVALID || fh_len != dwords << 2) diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index b7198c4744e3..2dac70b99b0d 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -388,7 +388,7 @@ static struct fsnotify_mark *fsnotify_first_mark(struct fsnotify_mark_connector return hlist_entry_safe(node, struct fsnotify_mark, obj_list); } -static struct fsnotify_mark *fsnotify_next_mark(struct fsnotify_mark *mark) +struct fsnotify_mark *fsnotify_next_mark(struct fsnotify_mark *mark) { struct hlist_node *node = NULL; diff --git a/fs/notify/mark.c b/fs/notify/mark.c index c2ed5b11b0fe..e256b420100d 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -238,7 +238,12 @@ static struct inode *fsnotify_update_iref(struct fsnotify_mark_connector *conn, return inode; } -static void *__fsnotify_recalc_mask(struct fsnotify_mark_connector *conn) +/* + * Calculate mask of events for a list of marks. + * + * Return true if any of the attached marks want to hold an inode reference. + */ +static bool __fsnotify_recalc_mask(struct fsnotify_mark_connector *conn) { u32 new_mask = 0; bool want_iref = false; @@ -262,6 +267,34 @@ static void *__fsnotify_recalc_mask(struct fsnotify_mark_connector *conn) */ WRITE_ONCE(*fsnotify_conn_mask_p(conn), new_mask); + return want_iref; +} + +/* + * Calculate mask of events for a list of marks after attach/modify mark + * and get an inode reference for the connector if needed. + * + * A concurrent add of evictable mark and detach of non-evictable mark can + * lead to __fsnotify_recalc_mask() returning false want_iref, but in this + * case we defer clearing iref to fsnotify_recalc_mask_clear_iref() called + * from fsnotify_put_mark(). + */ +static void fsnotify_recalc_mask_set_iref(struct fsnotify_mark_connector *conn) +{ + bool has_iref = conn->flags & FSNOTIFY_CONN_FLAG_HAS_IREF; + bool want_iref = __fsnotify_recalc_mask(conn) || has_iref; + + (void) fsnotify_update_iref(conn, want_iref); +} + +/* + * Calculate mask of events for a list of marks after detach mark + * and return the inode object if its reference is no longer needed. + */ +static void *fsnotify_recalc_mask_clear_iref(struct fsnotify_mark_connector *conn) +{ + bool want_iref = __fsnotify_recalc_mask(conn); + return fsnotify_update_iref(conn, want_iref); } @@ -298,7 +331,7 @@ void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn) spin_lock(&conn->lock); update_children = !fsnotify_conn_watches_children(conn); - __fsnotify_recalc_mask(conn); + fsnotify_recalc_mask_set_iref(conn); update_children &= fsnotify_conn_watches_children(conn); spin_unlock(&conn->lock); /* @@ -419,7 +452,7 @@ void fsnotify_put_mark(struct fsnotify_mark *mark) /* Update watched objects after detaching mark */ if (sb) fsnotify_update_sb_watchers(sb, conn); - objp = __fsnotify_recalc_mask(conn); + objp = fsnotify_recalc_mask_clear_iref(conn); type = conn->type; } WRITE_ONCE(mark->connector, NULL); @@ -457,9 +490,6 @@ EXPORT_SYMBOL_GPL(fsnotify_put_mark); */ static bool fsnotify_get_mark_safe(struct fsnotify_mark *mark) { - if (!mark) - return true; - if (refcount_inc_not_zero(&mark->refcnt)) { spin_lock(&mark->lock); if (mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED) { @@ -500,15 +530,22 @@ bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info) int type; fsnotify_foreach_iter_type(type) { + struct fsnotify_mark *mark = iter_info->marks[type]; + /* This can fail if mark is being removed */ - if (!fsnotify_get_mark_safe(iter_info->marks[type])) { - __release(&fsnotify_mark_srcu); - goto fail; + while (mark && !fsnotify_get_mark_safe(mark)) { + if (mark->group == iter_info->current_group) { + __release(&fsnotify_mark_srcu); + goto fail; + } + /* This is a mark in an unrelated group, skip */ + mark = fsnotify_next_mark(mark); + iter_info->marks[type] = mark; } } /* - * Now that both marks are pinned by refcount in the inode / vfsmount + * Now that all marks are pinned by refcount in the inode / vfsmount / etc * lists, we can drop SRCU lock, and safely resume the list iteration * once userspace returns. */ diff --git a/fs/ntfs/bitmap.c b/fs/ntfs/bitmap.c index 656d802333e3..b1436b3151b9 100644 --- a/fs/ntfs/bitmap.c +++ b/fs/ntfs/bitmap.c @@ -125,7 +125,7 @@ int __ntfs_bitmap_set_bits_in_run(struct inode *vi, const s64 start_bit, struct address_space *mapping; struct folio *folio; u8 *kaddr; - int pos, len; + int pos, len, err; u8 bit; struct ntfs_inode *ni = NTFS_I(vi); struct ntfs_volume *vol = ni->vol; @@ -201,8 +201,10 @@ int __ntfs_bitmap_set_bits_in_run(struct inode *vi, const s64 start_bit, /* If we are not in the last page, deal with all subsequent pages. */ while (index < end_index) { - if (cnt <= 0) + if (cnt <= 0) { + err = -EIO; goto rollback; + } /* Update @index and get the next folio. */ folio_mark_dirty(folio); @@ -214,6 +216,7 @@ int __ntfs_bitmap_set_bits_in_run(struct inode *vi, const s64 start_bit, ntfs_error(vi->i_sb, "Failed to map subsequent page (error %li), aborting.", PTR_ERR(folio)); + err = PTR_ERR(folio); goto rollback; } @@ -265,7 +268,7 @@ rollback: * - @count - @cnt is the number of bits that have been modified */ if (is_rollback) - return PTR_ERR(folio); + return err; if (count != cnt) pos = __ntfs_bitmap_set_bits_in_run(vi, start_bit, count - cnt, value ? 0 : 1, true); @@ -274,14 +277,14 @@ rollback: if (!pos) { /* Rollback was successful. */ ntfs_error(vi->i_sb, - "Failed to map subsequent page (error %li), aborting.", - PTR_ERR(folio)); + "Failed to map subsequent page (error %i), aborting.", + err); } else { /* Rollback failed. */ ntfs_error(vi->i_sb, - "Failed to map subsequent page (error %li) and rollback failed (error %i). Aborting and leaving inconsistent metadata. Unmount and run chkdsk.", - PTR_ERR(folio), pos); + "Failed to map subsequent page (error %i) and rollback failed (error %i). Aborting and leaving inconsistent metadata. Unmount and run chkdsk.", + err, pos); NVolSetErrors(NTFS_SB(vi->i_sb)); } - return PTR_ERR(folio); + return err; } diff --git a/fs/ntfs/dir.c b/fs/ntfs/dir.c index bfa904d2ce66..20f5c7074bdd 100644 --- a/fs/ntfs/dir.c +++ b/fs/ntfs/dir.c @@ -911,8 +911,8 @@ static int ntfs_readdir(struct file *file, struct dir_context *actor) if (next->flags & INDEX_ENTRY_NODE) { next = ntfs_index_walk_down(next, ictx); - if (!next) { - err = -EIO; + if (IS_ERR(next)) { + err = PTR_ERR(next); goto out; } } @@ -920,7 +920,14 @@ static int ntfs_readdir(struct file *file, struct dir_context *actor) if (next && !(next->flags & INDEX_ENTRY_END)) goto nextdir; - while ((next = ntfs_index_next(next, ictx)) != NULL) { + while (1) { + next = ntfs_index_next(next, ictx); + if (IS_ERR(next)) { + err = PTR_ERR(next); + goto out; + } + if (!next) + break; nextdir: /* Check the consistency of an index entry */ if (ntfs_index_entry_inconsistent(ictx, vol, next, COLLATION_FILE_NAME, diff --git a/fs/ntfs/index.c b/fs/ntfs/index.c index 2080f3969137..a547bdcfa456 100644 --- a/fs/ntfs/index.c +++ b/fs/ntfs/index.c @@ -1969,15 +1969,19 @@ err_out: struct index_entry *ntfs_index_walk_down(struct index_entry *ie, struct ntfs_index_context *ictx) { struct index_entry *entry; + struct index_block *ib; s64 vcn; entry = ie; do { vcn = ntfs_ie_get_vcn(entry); if (ictx->is_in_root) { + ib = kvzalloc(ictx->block_size, GFP_NOFS); + if (!ib) + return ERR_PTR(-ENOMEM); /* down from level zero */ ictx->ir = NULL; - ictx->ib = kvzalloc(ictx->block_size, GFP_NOFS); + ictx->ib = ib; ictx->pindex = 1; ictx->is_in_root = false; } else { @@ -1991,8 +1995,8 @@ struct index_entry *ntfs_index_walk_down(struct index_entry *ie, struct ntfs_ind ictx->entry = ntfs_ie_get_first(&ictx->ib->index); entry = ictx->entry; } else - entry = NULL; - } while (entry && (entry->flags & INDEX_ENTRY_NODE)); + entry = ERR_PTR(-EIO); + } while (!IS_ERR(entry) && (entry->flags & INDEX_ENTRY_NODE)); return entry; } @@ -2097,10 +2101,15 @@ struct index_entry *ntfs_index_next(struct index_entry *ie, struct ntfs_index_co /* walk down if it has a subnode */ if (flags & INDEX_ENTRY_NODE) { - if (!ictx->ia_ni) + if (!ictx->ia_ni) { ictx->ia_ni = ntfs_ia_open(ictx, ictx->idx_ni); + if (!ictx->ia_ni) + return ERR_PTR(-EIO); + } next = ntfs_index_walk_down(next, ictx); + if (IS_ERR(next)) + return next; } else { /* walk up it has no subnode, nor data */ diff --git a/fs/ntfs/iomap.c b/fs/ntfs/iomap.c index 74a4d3e971f4..dc7d8c893a69 100644 --- a/fs/ntfs/iomap.c +++ b/fs/ntfs/iomap.c @@ -788,8 +788,7 @@ static int ntfs_write_iomap_end_resident(struct inode *inode, loff_t pos, ctx = ntfs_attr_get_search_ctx(ni, NULL); if (!ctx) { written = -ENOMEM; - mutex_unlock(&ni->mrec_lock); - return written; + goto err_out; } err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len, @@ -810,7 +809,8 @@ static int ntfs_write_iomap_end_resident(struct inode *inode, loff_t pos, memcpy(kattr + pos, iomap_inline_data(iomap, pos), written); mark_mft_record_dirty(ctx->ntfs_ino); err_out: - ntfs_attr_put_search_ctx(ctx); + if (ctx) + ntfs_attr_put_search_ctx(ctx); put_page(ipage); mutex_unlock(&ni->mrec_lock); return written; diff --git a/fs/ntfs/namei.c b/fs/ntfs/namei.c index 10894de519c3..96c450e62efc 100644 --- a/fs/ntfs/namei.c +++ b/fs/ntfs/namei.c @@ -945,7 +945,8 @@ search: ni_mrec = actx->base_mrec ? actx->base_mrec : actx->mrec; ni_mrec->link_count = cpu_to_le16(le16_to_cpu(ni_mrec->link_count) - 1); - drop_nlink(VFS_I(ni)); + if (!S_ISDIR(VFS_I(ni)->i_mode)) + drop_nlink(VFS_I(ni)); mark_mft_record_dirty(ni); if (looking_for_dos_name) { @@ -956,6 +957,13 @@ search: } /* + * For directories, Drop VFS nlink only when mft record link count + * becomes zero. Because we fixes VFS nlink to 1 for directories. + */ + if (S_ISDIR(VFS_I(ni)->i_mode) && !le16_to_cpu(ni_mrec->link_count)) + drop_nlink(VFS_I(ni)); + + /* * If hard link count is not equal to zero then we are done. In other * case there are no reference to this inode left, so we should free all * non-resident attributes and mark all MFT record as not in use. @@ -1221,7 +1229,8 @@ static int __ntfs_link(struct ntfs_inode *ni, struct ntfs_inode *dir_ni, } /* Increment hard links count. */ ni_mrec->link_count = cpu_to_le16(le16_to_cpu(ni_mrec->link_count) + 1); - inc_nlink(VFS_I(ni)); + if (!S_ISDIR(vi->i_mode)) + inc_nlink(VFS_I(ni)); /* Done! */ mark_mft_record_dirty(ni); diff --git a/fs/ntfs/reparse.c b/fs/ntfs/reparse.c index 8f60ec6f66c1..74713716813f 100644 --- a/fs/ntfs/reparse.c +++ b/fs/ntfs/reparse.c @@ -505,7 +505,6 @@ int ntfs_reparse_set_wsl_symlink(struct ntfs_inode *ni, struct reparse_point *reparse; struct wsl_link_reparse_data *data; - utarget = (char *)NULL; len = ntfs_ucstonls(ni->vol, target, target_len, &utarget, 0); if (len <= 0) return -EINVAL; @@ -514,7 +513,7 @@ int ntfs_reparse_set_wsl_symlink(struct ntfs_inode *ni, reparse = kvzalloc(reparse_len, GFP_NOFS); if (!reparse) { err = -ENOMEM; - kvfree(utarget); + kfree(utarget); } else { data = (struct wsl_link_reparse_data *)reparse->reparse_data; reparse->reparse_tag = IO_REPARSE_TAG_LX_SYMLINK; @@ -528,6 +527,8 @@ int ntfs_reparse_set_wsl_symlink(struct ntfs_inode *ni, kvfree(reparse); if (!err) ni->target = utarget; + else + kfree(utarget); } return err; } diff --git a/fs/ntfs/runlist.c b/fs/ntfs/runlist.c index b213b4976d2b..da21dbeaaf66 100644 --- a/fs/ntfs/runlist.c +++ b/fs/ntfs/runlist.c @@ -15,6 +15,8 @@ * Copyright (c) 2007-2022 Jean-Pierre Andre */ +#include <linux/overflow.h> + #include "ntfs.h" #include "attrib.h" @@ -739,6 +741,7 @@ struct runlist_element *ntfs_mapping_pairs_decompress(const struct ntfs_volume * int rlsize; /* Size of runlist buffer. */ u16 rlpos; /* Current runlist position in units of struct runlist_elements. */ u8 b; /* Current byte offset in buf. */ + u64 lowest_vcn; /* Raw on-disk lowest_vcn. */ #ifdef DEBUG /* Make sure attr exists and is non-resident. */ @@ -747,8 +750,14 @@ struct runlist_element *ntfs_mapping_pairs_decompress(const struct ntfs_volume * return ERR_PTR(-EINVAL); } #endif + lowest_vcn = le64_to_cpu(attr->data.non_resident.lowest_vcn); + /* Validate lowest_vcn from on-disk metadata to ensure it is sane. */ + if (overflows_type(lowest_vcn, vcn)) { + ntfs_error(vol->sb, "Invalid lowest_vcn in mapping pairs."); + return ERR_PTR(-EIO); + } /* Start at vcn = lowest_vcn and lcn 0. */ - vcn = le64_to_cpu(attr->data.non_resident.lowest_vcn); + vcn = lowest_vcn; lcn = 0; /* Get start of the mapping pairs array. */ buf = (u8 *)attr + @@ -823,8 +832,17 @@ struct runlist_element *ntfs_mapping_pairs_decompress(const struct ntfs_volume * * element. */ rl[rlpos].length = deltaxcn; - /* Increment the current vcn by the current run length. */ - vcn += deltaxcn; + /* + * Increment the current vcn by the current run length. + * Guard against s64 overflow from a crafted mapping + * pairs array to preserve the monotonically-increasing + * vcn invariant. + */ + if (unlikely(check_add_overflow(vcn, deltaxcn, &vcn))) { + ntfs_error(vol->sb, "VCN overflow in mapping pairs array."); + goto err_out; + } + /* * There might be no lcn change at all, as is the case for * sparse clusters on NTFS 3.0+, in which case we set the lcn diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c index 02791ec3c5a1..88d5e9a32f28 100644 --- a/fs/smb/client/cached_dir.c +++ b/fs/smb/client/cached_dir.c @@ -286,6 +286,14 @@ replay_again: &rqst[0], &oplock, &oparms, utf16_path); if (rc) goto oshr_free; + + if (oplock != SMB2_OPLOCK_LEVEL_II) { + rc = -EINVAL; + cifs_dbg(FYI, "%s: Oplock level %d not suitable for cached directory\n", + __func__, oplock); + goto oshr_free; + } + smb2_set_next_command(tcon, &rqst[0]); memset(&qi_iov, 0, sizeof(qi_iov)); diff --git a/fs/smb/client/cifsacl.c b/fs/smb/client/cifsacl.c index ec5d47779304..786dbbc43c5b 100644 --- a/fs/smb/client/cifsacl.c +++ b/fs/smb/client/cifsacl.c @@ -1264,6 +1264,17 @@ static int parse_sid(struct smb_sid *psid, char *end_of_acl) return 0; } +static bool dacl_offset_valid(unsigned int acl_len, __u32 dacloffset) +{ + if (acl_len < sizeof(struct smb_acl)) + return false; + + if (dacloffset < sizeof(struct smb_ntsd)) + return false; + + return dacloffset <= acl_len - sizeof(struct smb_acl); +} + /* Convert CIFS ACL to POSIX form */ static int parse_sec_desc(struct cifs_sb_info *cifs_sb, @@ -1284,7 +1295,6 @@ static int parse_sec_desc(struct cifs_sb_info *cifs_sb, group_sid_ptr = (struct smb_sid *)((char *)pntsd + le32_to_cpu(pntsd->gsidoffset)); dacloffset = le32_to_cpu(pntsd->dacloffset); - dacl_ptr = (struct smb_acl *)((char *)pntsd + dacloffset); cifs_dbg(NOISY, "revision %d type 0x%x ooffset 0x%x goffset 0x%x sacloffset 0x%x dacloffset 0x%x\n", pntsd->revision, pntsd->type, le32_to_cpu(pntsd->osidoffset), le32_to_cpu(pntsd->gsidoffset), @@ -1315,11 +1325,18 @@ static int parse_sec_desc(struct cifs_sb_info *cifs_sb, return rc; } - if (dacloffset) + if (dacloffset) { + if (!dacl_offset_valid(acl_len, dacloffset)) { + cifs_dbg(VFS, "Server returned illegal DACL offset\n"); + return -EINVAL; + } + + dacl_ptr = (struct smb_acl *)((char *)pntsd + dacloffset); parse_dacl(dacl_ptr, end_of_acl, owner_sid_ptr, group_sid_ptr, fattr, get_mode_from_special_sid); - else + } else { cifs_dbg(FYI, "no ACL\n"); /* BB grant all or default perms? */ + } return rc; } @@ -1342,6 +1359,11 @@ static int build_sec_desc(struct smb_ntsd *pntsd, struct smb_ntsd *pnntsd, dacloffset = le32_to_cpu(pntsd->dacloffset); if (dacloffset) { + if (!dacl_offset_valid(secdesclen, dacloffset)) { + cifs_dbg(VFS, "Server returned illegal DACL offset\n"); + return -EINVAL; + } + dacl_ptr = (struct smb_acl *)((char *)pntsd + dacloffset); rc = validate_dacl(dacl_ptr, end_of_acl); if (rc) @@ -1710,6 +1732,12 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 *pnmode, nsecdesclen = sizeof(struct smb_ntsd) + (sizeof(struct smb_sid) * 2); dacloffset = le32_to_cpu(pntsd->dacloffset); if (dacloffset) { + if (!dacl_offset_valid(secdesclen, dacloffset)) { + cifs_dbg(VFS, "Server returned illegal DACL offset\n"); + rc = -EINVAL; + goto id_mode_to_cifs_acl_exit; + } + dacl_ptr = (struct smb_acl *)((char *)pntsd + dacloffset); rc = validate_dacl(dacl_ptr, (char *)pntsd + secdesclen); if (rc) { @@ -1732,7 +1760,7 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 *pnmode, * descriptor parameters, and security descriptor itself */ nsecdesclen = max_t(u32, nsecdesclen, DEFAULT_SEC_DESC_LEN); - pnntsd = kmalloc(nsecdesclen, GFP_KERNEL); + pnntsd = kzalloc(nsecdesclen, GFP_KERNEL); if (!pnntsd) { kfree(pntsd); cifs_put_tlink(tlink); @@ -1752,6 +1780,7 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 *pnmode, rc = ops->set_acl(pnntsd, nsecdesclen, inode, path, aclflag); cifs_dbg(NOISY, "set_cifs_acl rc: %d\n", rc); } +id_mode_to_cifs_acl_exit: cifs_put_tlink(tlink); kfree(pnntsd); diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h index 4a25afda9448..79d891f7df1a 100644 --- a/fs/smb/client/cifsproto.h +++ b/fs/smb/client/cifsproto.h @@ -89,7 +89,6 @@ int cifs_handle_standard(struct TCP_Server_Info *server, struct mid_q_entry *mid); char *smb3_fs_context_fullpath(const struct smb3_fs_context *ctx, char dirsep); int smb3_parse_devname(const char *devname, struct smb3_fs_context *ctx); -int smb3_parse_opt(const char *options, const char *key, char **val); int cifs_ipaddr_cmp(struct sockaddr *srcaddr, struct sockaddr *rhs); bool cifs_match_ipaddr(struct sockaddr *srcaddr, struct sockaddr *rhs); int cifs_discard_remaining_data(struct TCP_Server_Info *server); diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c index b9544eb0381b..b63ec7ab6e51 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -536,37 +536,6 @@ cifs_parse_smb_version(struct fs_context *fc, char *value, struct smb3_fs_contex return 0; } -int smb3_parse_opt(const char *options, const char *key, char **val) -{ - int rc = -ENOENT; - char *opts, *orig, *p; - - orig = opts = kstrdup(options, GFP_KERNEL); - if (!opts) - return -ENOMEM; - - while ((p = strsep(&opts, ","))) { - char *nval; - - if (!*p) - continue; - if (strncasecmp(p, key, strlen(key))) - continue; - nval = strchr(p, '='); - if (nval) { - if (nval == p) - continue; - *nval++ = 0; - *val = kstrdup(nval, GFP_KERNEL); - rc = !*val ? -ENOMEM : 0; - goto out; - } - } -out: - kfree(orig); - return rc; -} - /* * Remove duplicate path delimiters. Windows is supposed to do that * but there are some bugs that prevent rename from working if there are diff --git a/fs/smb/client/ioctl.c b/fs/smb/client/ioctl.c index 9afab3237e54..17408bb8ab65 100644 --- a/fs/smb/client/ioctl.c +++ b/fs/smb/client/ioctl.c @@ -296,7 +296,7 @@ search_end: break; case SMB2_ENCRYPTION_AES256_CCM: case SMB2_ENCRYPTION_AES256_GCM: - out.session_key_length = CIFS_SESS_KEY_SIZE; + out.session_key_length = ses->auth_key.len; out.server_in_key_length = out.server_out_key_length = SMB3_GCM256_CRYPTKEY_SIZE; break; default: diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c index c6dd282fc3a9..6c9c229b91f6 100644 --- a/fs/smb/client/smb2inode.c +++ b/fs/smb/client/smb2inode.c @@ -111,7 +111,7 @@ static int check_wsl_eas(struct kvec *rsp_iov) u32 outlen, next; u16 vlen; u8 nlen; - u8 *end; + u8 *ea_end, *iov_end; outlen = le32_to_cpu(rsp->OutputBufferLength); if (outlen < SMB2_WSL_MIN_QUERY_EA_RESP_SIZE || @@ -120,15 +120,19 @@ static int check_wsl_eas(struct kvec *rsp_iov) ea = (void *)((u8 *)rsp_iov->iov_base + le16_to_cpu(rsp->OutputBufferOffset)); - end = (u8 *)rsp_iov->iov_base + rsp_iov->iov_len; + ea_end = (u8 *)ea + outlen; + iov_end = (u8 *)rsp_iov->iov_base + rsp_iov->iov_len; + if (ea_end > iov_end) + return -EINVAL; + for (;;) { - if ((u8 *)ea > end - sizeof(*ea)) + if ((u8 *)ea > ea_end - sizeof(*ea)) return -EINVAL; nlen = ea->ea_name_length; vlen = le16_to_cpu(ea->ea_value_length); if (nlen != SMB2_WSL_XATTR_NAME_LEN || - (u8 *)ea->ea_data + nlen + 1 + vlen > end) + (u8 *)ea->ea_data + nlen + 1 + vlen > ea_end) return -EINVAL; switch (vlen) { @@ -230,7 +234,7 @@ replay_again: num_rqst = 0; server = cifs_pick_channel(ses); - vars = kzalloc_obj(*vars, GFP_ATOMIC); + vars = kzalloc_obj(*vars, GFP_KERNEL); if (vars == NULL) { rc = -ENOMEM; goto out; diff --git a/fs/smb/client/smb2misc.c b/fs/smb/client/smb2misc.c index 973fce3c959c..2a7355ce1a07 100644 --- a/fs/smb/client/smb2misc.c +++ b/fs/smb/client/smb2misc.c @@ -241,7 +241,8 @@ smb2_check_message(char *buf, unsigned int pdu_len, unsigned int len, if (len != calc_len) { /* create failed on symlink */ if (command == SMB2_CREATE_HE && - shdr->Status == STATUS_STOPPED_ON_SYMLINK) + shdr->Status == STATUS_STOPPED_ON_SYMLINK && + len > calc_len) return 0; /* Windows 7 server returns 24 bytes more */ if (calc_len + 24 == len && command == SMB2_OPLOCK_BREAK_HE) diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 7f346ee50289..e6cb9b144530 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -111,10 +111,21 @@ smb2_add_credits(struct TCP_Server_Info *server, cifs_trace_rw_credits_zero_in_flight); } server->in_flight--; + + /* + * Rebalance credits when an op drains in_flight. For session setup, + * do this only when the total accumulated credits are high enough (>2) + * so that a newly established secondary channel can reserve credits for + * echoes and oplocks. We expect this to happen at the end of the final + * session setup response. + */ if (server->in_flight == 0 && ((optype & CIFS_OP_MASK) != CIFS_NEG_OP) && ((optype & CIFS_OP_MASK) != CIFS_SESS_OP)) rc = change_conf(server); + else if (server->in_flight == 0 && + ((optype & CIFS_OP_MASK) == CIFS_SESS_OP) && *val > 2) + rc = change_conf(server); /* * Sometimes server returns 0 credits on oplock break ack - we need to * rebalance credits in this case. diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index cb61051f9af3..995fcdd30681 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -1713,17 +1713,30 @@ SMB2_auth_kerberos(struct SMB2_sess_data *sess_data) is_binding = (ses->ses_status == SES_GOOD); spin_unlock(&ses->ses_lock); + /* + * Per MS-SMB2 3.2.5.3, Session.SessionKey is the first 16 bytes of the + * GSS cryptographic key, right-padded with zero bytes if shorter. + * Allocate at least SMB2_NTLMV2_SESSKEY_SIZE bytes (zeroed) so the KDF + * input buffer is always valid for HMAC-SHA256 even with deprecated + * Kerberos enctypes that return a short session key. + */ + if (unlikely(msg->sesskey_len < SMB2_NTLMV2_SESSKEY_SIZE)) + cifs_dbg(VFS, + "short GSS session key (%u bytes); zero-padding per MS-SMB2 3.2.5.3\n", + msg->sesskey_len); + kfree_sensitive(ses->auth_key.response); - ses->auth_key.response = kmemdup(msg->data, - msg->sesskey_len, - GFP_KERNEL); + ses->auth_key.len = max_t(unsigned int, msg->sesskey_len, + SMB2_NTLMV2_SESSKEY_SIZE); + ses->auth_key.response = kzalloc(ses->auth_key.len, GFP_KERNEL); if (!ses->auth_key.response) { cifs_dbg(VFS, "%s: can't allocate (%u bytes) memory\n", - __func__, msg->sesskey_len); + __func__, ses->auth_key.len); + ses->auth_key.len = 0; rc = -ENOMEM; goto out_put_spnego_key; } - ses->auth_key.len = msg->sesskey_len; + memcpy(ses->auth_key.response, msg->data, msg->sesskey_len); sess_data->iov[1].iov_base = msg->data + msg->sesskey_len; sess_data->iov[1].iov_len = msg->secblob_len; diff --git a/fs/smb/client/smb2transport.c b/fs/smb/client/smb2transport.c index 41009039b4cb..e8eeff9e50d6 100644 --- a/fs/smb/client/smb2transport.c +++ b/fs/smb/client/smb2transport.c @@ -251,7 +251,8 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) } static void generate_key(struct cifs_ses *ses, struct kvec label, - struct kvec context, __u8 *key, unsigned int key_size) + struct kvec context, __u8 *key, unsigned int key_size, + unsigned int full_key_size) { unsigned char zero = 0x0; __u8 i[4] = {0, 0, 0, 1}; @@ -265,7 +266,7 @@ static void generate_key(struct cifs_ses *ses, struct kvec label, memset(key, 0x0, key_size); hmac_sha256_init_usingrawkey(&hmac_ctx, ses->auth_key.response, - SMB2_NTLMV2_SESSKEY_SIZE); + full_key_size); hmac_sha256_update(&hmac_ctx, i, 4); hmac_sha256_update(&hmac_ctx, label.iov_base, label.iov_len); hmac_sha256_update(&hmac_ctx, &zero, 1); @@ -298,6 +299,7 @@ generate_smb3signingkey(struct cifs_ses *ses, struct TCP_Server_Info *server, const struct derivation_triplet *ptriplet) { + unsigned int full_key_size = SMB2_NTLMV2_SESSKEY_SIZE; bool is_binding = false; int chan_index = 0; @@ -330,12 +332,24 @@ generate_smb3signingkey(struct cifs_ses *ses, if (is_binding) { generate_key(ses, ptriplet->signing.label, ptriplet->signing.context, - ses->chans[chan_index].signkey, - SMB3_SIGN_KEY_SIZE); + ses->chans[chan_index].signkey, SMB3_SIGN_KEY_SIZE, + SMB2_NTLMV2_SESSKEY_SIZE); } else { generate_key(ses, ptriplet->signing.label, - ptriplet->signing.context, - ses->smb3signingkey, SMB3_SIGN_KEY_SIZE); + ptriplet->signing.context, ses->smb3signingkey, + SMB3_SIGN_KEY_SIZE, SMB2_NTLMV2_SESSKEY_SIZE); + + /* + * Per MS-SMB2 3.2.5.3.1, signing key always uses Session.SessionKey + * (first 16 bytes). Encryption/decryption keys use + * Session.FullSessionKey when dialect is 3.1.1 and cipher is + * AES-256-CCM or AES-256-GCM, otherwise Session.SessionKey. + */ + + if (server->dialect == SMB311_PROT_ID && + (server->cipher_type == SMB2_ENCRYPTION_AES256_CCM || + server->cipher_type == SMB2_ENCRYPTION_AES256_GCM)) + full_key_size = ses->auth_key.len; /* safe to access primary channel, since it will never go away */ spin_lock(&ses->chan_lock); @@ -345,10 +359,13 @@ generate_smb3signingkey(struct cifs_ses *ses, generate_key(ses, ptriplet->encryption.label, ptriplet->encryption.context, - ses->smb3encryptionkey, SMB3_ENC_DEC_KEY_SIZE); + ses->smb3encryptionkey, SMB3_ENC_DEC_KEY_SIZE, + full_key_size); + generate_key(ses, ptriplet->decryption.label, ptriplet->decryption.context, - ses->smb3decryptionkey, SMB3_ENC_DEC_KEY_SIZE); + ses->smb3decryptionkey, SMB3_ENC_DEC_KEY_SIZE, + full_key_size); } #ifdef CONFIG_CIFS_DEBUG_DUMP_KEYS @@ -361,7 +378,7 @@ generate_smb3signingkey(struct cifs_ses *ses, &ses->Suid); cifs_dbg(VFS, "Cipher type %d\n", server->cipher_type); cifs_dbg(VFS, "Session Key %*ph\n", - SMB2_NTLMV2_SESSKEY_SIZE, ses->auth_key.response); + (int)ses->auth_key.len, ses->auth_key.response); cifs_dbg(VFS, "Signing Key %*ph\n", SMB3_SIGN_KEY_SIZE, ses->smb3signingkey); if ((server->cipher_type == SMB2_ENCRYPTION_AES256_CCM) || diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c index 75f9f91a7ec9..563ef488a225 100644 --- a/fs/smb/client/smbdirect.c +++ b/fs/smb/client/smbdirect.c @@ -9,7 +9,6 @@ #include "cifs_debug.h" #include "cifsproto.h" #include "smb2proto.h" -#include "../smbdirect/public.h" /* Port numbers for SMBD transport */ #define SMB_PORT 445 @@ -558,3 +557,5 @@ void smbd_debug_proc_show(struct TCP_Server_Info *server, struct seq_file *m) server->rdma_readwrite_threshold, m); } + +MODULE_IMPORT_NS("SMBDIRECT"); diff --git a/fs/smb/client/smbdirect.h b/fs/smb/client/smbdirect.h index 287ac849213d..be205ec02077 100644 --- a/fs/smb/client/smbdirect.h +++ b/fs/smb/client/smbdirect.h @@ -12,7 +12,7 @@ #include "cifsglob.h" -#include "../smbdirect/smbdirect.h" +#include <linux/smbdirect.h> extern int rdma_readwrite_threshold; extern int smbd_max_frmr_depth; diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c index fbbc0529743f..8347495dbc62 100644 --- a/fs/smb/server/connection.c +++ b/fs/smb/server/connection.c @@ -79,6 +79,85 @@ static int create_proc_clients(void) { return 0; } static void delete_proc_clients(void) {} #endif +static struct workqueue_struct *ksmbd_conn_wq; + +int ksmbd_conn_wq_init(void) +{ + ksmbd_conn_wq = alloc_workqueue("ksmbd-conn-release", + WQ_UNBOUND | WQ_MEM_RECLAIM, 0); + if (!ksmbd_conn_wq) + return -ENOMEM; + return 0; +} + +void ksmbd_conn_wq_destroy(void) +{ + if (ksmbd_conn_wq) { + destroy_workqueue(ksmbd_conn_wq); + ksmbd_conn_wq = NULL; + } +} + +/* + * __ksmbd_conn_release_work() - perform the final, once-per-struct cleanup + * of a ksmbd_conn whose refcount has just dropped to zero. + * + * This is the common release path used by ksmbd_conn_put() for the embedded + * state that outlives the connection thread: async_ida and the attached + * transport (which owns the socket and iov for TCP). Called from a workqueue + * so that sleep-allowed teardown (sock_release -> tcp_close -> + * lock_sock_nested) never runs from an RCU softirq callback (free_opinfo_rcu) + * or any other non-sleeping putter context. + */ +static void __ksmbd_conn_release_work(struct work_struct *work) +{ + struct ksmbd_conn *conn = + container_of(work, struct ksmbd_conn, release_work); + + ida_destroy(&conn->async_ida); + conn->transport->ops->free_transport(conn->transport); + kfree(conn); +} + +/** + * ksmbd_conn_get() - take a reference on @conn and return it. + * + * @conn: connection instance to get a reference to + * + * Returns @conn unchanged so callers can write + * "fp->conn = ksmbd_conn_get(work->conn);" in one expression. Returns NULL + * if @conn is NULL. + */ +struct ksmbd_conn *ksmbd_conn_get(struct ksmbd_conn *conn) +{ + if (!conn) + return NULL; + + atomic_inc(&conn->refcnt); + return conn; +} + +/** + * ksmbd_conn_put() - drop a reference and, if it was the last, queue the + * release onto ksmbd_conn_wq so it runs from process context. + * + * @conn: connection instance to put a reference to + * + * Callable from any context including RCU softirq callbacks and non-sleeping + * locks; the actual release is deferred to the workqueue. ksmbd_conn_wq is + * created in ksmbd_server_init() before any conn can be allocated and is + * destroyed in ksmbd_server_exit() after rcu_barrier(), so it is always + * non-NULL while a conn reference is held. + */ +void ksmbd_conn_put(struct ksmbd_conn *conn) +{ + if (!conn) + return; + + if (atomic_dec_and_test(&conn->refcnt)) + queue_work(ksmbd_conn_wq, &conn->release_work); +} + /** * ksmbd_conn_free() - free resources of the connection instance * @@ -93,23 +172,19 @@ void ksmbd_conn_free(struct ksmbd_conn *conn) hash_del(&conn->hlist); up_write(&conn_list_lock); + /* + * request_buf / preauth_info / mechToken are only ever accessed by the + * connection handler thread that owns @conn. ksmbd_conn_free() is + * called from the transport free_transport() path when that thread is + * exiting, so it is safe to release them unconditionally even when + * ksmbd_conn_put() below is not the final putter (oplock / ksmbd_file + * holders only retain the conn pointer, not these per-thread buffers). + */ xa_destroy(&conn->sessions); kvfree(conn->request_buf); kfree(conn->preauth_info); kfree(conn->mechToken); - if (atomic_dec_and_test(&conn->refcnt)) { - /* - * async_ida is embedded in struct ksmbd_conn, so pair - * ida_destroy() with the final kfree() rather than with - * the unconditional field teardown above. This keeps - * the IDA valid for the entire lifetime of the struct, - * even while other refcount holders (oplock / vfs - * durable handles) still reference the connection. - */ - ida_destroy(&conn->async_ida); - conn->transport->ops->free_transport(conn->transport); - kfree(conn); - } + ksmbd_conn_put(conn); } /** @@ -136,6 +211,7 @@ struct ksmbd_conn *ksmbd_conn_alloc(void) conn->um = ERR_PTR(-EOPNOTSUPP); if (IS_ERR(conn->um)) conn->um = NULL; + INIT_WORK(&conn->release_work, __ksmbd_conn_release_work); atomic_set(&conn->req_running, 0); atomic_set(&conn->r_count, 0); atomic_set(&conn->refcnt, 1); @@ -512,8 +588,7 @@ void ksmbd_conn_r_count_dec(struct ksmbd_conn *conn) if (!atomic_dec_return(&conn->r_count) && waitqueue_active(&conn->r_count_q)) wake_up(&conn->r_count_q); - if (atomic_dec_and_test(&conn->refcnt)) - kfree(conn); + ksmbd_conn_put(conn); } int ksmbd_conn_transport_init(void) @@ -540,24 +615,54 @@ out: static void stop_sessions(void) { - struct ksmbd_conn *conn; + struct ksmbd_conn *conn, *target; struct ksmbd_transport *t; + bool any; int bkt; + /* + * Serialised via init_lock; no concurrent stop_sessions() can + * touch conn->stop_called, so writing it under the read lock is + * safe. + */ again: + target = NULL; + any = false; down_read(&conn_list_lock); hash_for_each(conn_list, bkt, conn, hlist) { - t = conn->transport; - ksmbd_conn_set_exiting(conn); - if (t->ops->shutdown) { - up_read(&conn_list_lock); + any = true; + if (conn->stop_called) + continue; + atomic_inc(&conn->refcnt); + conn->stop_called = true; + /* + * Mark the connection EXITING while still holding the + * read lock so the selection and the status transition + * happen together. Do not regress a connection that has + * already advanced to RELEASING on its own (e.g. the + * handler exited its receive loop for an unrelated + * reason). + */ + if (READ_ONCE(conn->status) != KSMBD_SESS_RELEASING) + ksmbd_conn_set_exiting(conn); + target = conn; + break; + } + up_read(&conn_list_lock); + + if (target) { + t = target->transport; + if (t->ops->shutdown) t->ops->shutdown(t); - down_read(&conn_list_lock); + if (atomic_dec_and_test(&target->refcnt)) { + ida_destroy(&target->async_ida); + t->ops->free_transport(t); + kfree(target); } + goto again; } - up_read(&conn_list_lock); - if (!hash_empty(conn_list)) { + if (any) { msleep(100); goto again; } diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h index ae21a1bd4c70..e074be942582 100644 --- a/fs/smb/server/connection.h +++ b/fs/smb/server/connection.h @@ -16,6 +16,7 @@ #include <linux/kthread.h> #include <linux/nls.h> #include <linux/unicode.h> +#include <linux/workqueue.h> #include "smb_common.h" #include "ksmbd_work.h" @@ -49,6 +50,7 @@ struct ksmbd_conn { struct mutex srv_mutex; int status; unsigned int cli_cap; + bool stop_called; union { __be32 inet_addr; #if IS_ENABLED(CONFIG_IPV6) @@ -119,6 +121,7 @@ struct ksmbd_conn { bool binding; atomic_t refcnt; bool is_aapl; + struct work_struct release_work; }; struct ksmbd_conn_ops { @@ -163,6 +166,10 @@ void ksmbd_conn_wait_idle(struct ksmbd_conn *conn); int ksmbd_conn_wait_idle_sess_id(struct ksmbd_conn *curr_conn, u64 sess_id); struct ksmbd_conn *ksmbd_conn_alloc(void); void ksmbd_conn_free(struct ksmbd_conn *conn); +struct ksmbd_conn *ksmbd_conn_get(struct ksmbd_conn *conn); +void ksmbd_conn_put(struct ksmbd_conn *conn); +int ksmbd_conn_wq_init(void); +void ksmbd_conn_wq_destroy(void); bool ksmbd_conn_lookup_dialect(struct ksmbd_conn *c); int ksmbd_conn_write(struct ksmbd_work *work); int ksmbd_conn_rdma_read(struct ksmbd_conn *conn, diff --git a/fs/smb/server/mgmt/share_config.c b/fs/smb/server/mgmt/share_config.c index 53f44ff4d376..6f97f8d39657 100644 --- a/fs/smb/server/mgmt/share_config.c +++ b/fs/smb/server/mgmt/share_config.c @@ -167,7 +167,10 @@ static struct ksmbd_share_config *share_config_request(struct ksmbd_work *work, share->path = kstrndup(ksmbd_share_config_path(resp), path_len, KSMBD_DEFAULT_GFP); - if (share->path) { + if (!share->path) { + ret = -ENOMEM; + } else { + ret = 0; share->path_sz = strlen(share->path); while (share->path_sz > 1 && share->path[share->path_sz - 1] == '/') @@ -179,9 +182,10 @@ static struct ksmbd_share_config *share_config_request(struct ksmbd_work *work, share->force_directory_mode = resp->force_directory_mode; share->force_uid = resp->force_uid; share->force_gid = resp->force_gid; - ret = parse_veto_list(share, - KSMBD_SHARE_CONFIG_VETO_LIST(resp), - resp->veto_list_sz); + if (!ret) + ret = parse_veto_list(share, + KSMBD_SHARE_CONFIG_VETO_LIST(resp), + resp->veto_list_sz); if (!ret && share->path) { if (__ksmbd_override_fsids(work, share)) { kill_share(share); diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index cd3f28b0e7cb..8feca02ddbf2 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -30,7 +30,6 @@ static DEFINE_RWLOCK(lease_list_lock); static struct oplock_info *alloc_opinfo(struct ksmbd_work *work, u64 id, __u16 Tid) { - struct ksmbd_conn *conn = work->conn; struct ksmbd_session *sess = work->sess; struct oplock_info *opinfo; @@ -39,7 +38,7 @@ static struct oplock_info *alloc_opinfo(struct ksmbd_work *work, return NULL; opinfo->sess = sess; - opinfo->conn = conn; + opinfo->conn = ksmbd_conn_get(work->conn); opinfo->level = SMB2_OPLOCK_LEVEL_NONE; opinfo->op_state = OPLOCK_STATE_NONE; opinfo->pending_break = 0; @@ -50,7 +49,6 @@ static struct oplock_info *alloc_opinfo(struct ksmbd_work *work, init_waitqueue_head(&opinfo->oplock_brk); atomic_set(&opinfo->refcount, 1); atomic_set(&opinfo->breaking_cnt, 0); - atomic_inc(&opinfo->conn->refcnt); return opinfo; } @@ -132,8 +130,7 @@ static void __free_opinfo(struct oplock_info *opinfo) { if (opinfo->is_lease) free_lease(opinfo); - if (opinfo->conn && atomic_dec_and_test(&opinfo->conn->refcnt)) - kfree(opinfo->conn); + ksmbd_conn_put(opinfo->conn); kfree(opinfo); } diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c index 58ef02c423fc..5d799b2d4c62 100644 --- a/fs/smb/server/server.c +++ b/fs/smb/server/server.c @@ -596,8 +596,14 @@ static int __init ksmbd_server_init(void) if (ret) goto err_crypto_destroy; + ret = ksmbd_conn_wq_init(); + if (ret) + goto err_workqueue_destroy; + return 0; +err_workqueue_destroy: + ksmbd_workqueue_destroy(); err_crypto_destroy: ksmbd_crypto_destroy(); err_release_inode_hash: @@ -623,6 +629,12 @@ static void __exit ksmbd_server_exit(void) { ksmbd_server_shutdown(); rcu_barrier(); + /* + * ksmbd_conn_put() defers the final release onto ksmbd_conn_wq, + * so drain it after rcu_barrier() has fired any pending RCU + * callbacks that may have queued a release. + */ + ksmbd_conn_wq_destroy(); ksmbd_release_inode_hash(); } diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 21825a69c29a..62d4399a993d 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -3767,8 +3767,10 @@ err_out1: err_out2: if (!rc) { - ksmbd_update_fstate(&work->sess->file_table, fp, FP_INITED); - rc = ksmbd_iov_pin_rsp(work, (void *)rsp, iov_len); + rc = ksmbd_update_fstate(&work->sess->file_table, fp, + FP_INITED); + if (!rc) + rc = ksmbd_iov_pin_rsp(work, (void *)rsp, iov_len); } if (rc) { if (rc == -EINVAL) @@ -3946,7 +3948,13 @@ static int smb2_populate_readdir_entry(struct ksmbd_conn *conn, int info_level, goto free_conv_name; } - struct_sz = readdir_info_level_struct_sz(info_level) + conv_len; + struct_sz = readdir_info_level_struct_sz(info_level); + if (struct_sz == -EOPNOTSUPP) { + rc = -EINVAL; + goto free_conv_name; + } + + struct_sz += conv_len; next_entry_offset = ALIGN(struct_sz, KSMBD_DIR_INFO_ALIGNMENT); d_info->last_entry_off_align = next_entry_offset - struct_sz; diff --git a/fs/smb/server/smbacl.c b/fs/smb/server/smbacl.c index 4bbc2c27e680..c1d1f34581d6 100644 --- a/fs/smb/server/smbacl.c +++ b/fs/smb/server/smbacl.c @@ -1068,7 +1068,26 @@ static void smb_set_ace(struct smb_ace *ace, const struct smb_sid *sid, u8 type, ace->flags = flags; ace->access_req = access_req; smb_copy_sid(&ace->sid, sid); - ace->size = cpu_to_le16(1 + 1 + 2 + 4 + 1 + 1 + 6 + (sid->num_subauth * 4)); + ace->size = cpu_to_le16(1 + 1 + 2 + 4 + 1 + 1 + 6 + + (ace->sid.num_subauth * 4)); +} + +static int smb_append_inherited_ace(struct smb_ace **ace, int *nt_size, + u16 *ace_cnt, const struct smb_sid *sid, + u8 type, u8 flags, __le32 access_req) +{ + int ace_size; + + smb_set_ace(*ace, sid, type, flags, access_req); + ace_size = le16_to_cpu((*ace)->size); + /* pdacl->size is __le16 and includes struct smb_acl. */ + if (check_add_overflow(*nt_size, ace_size, nt_size) || + *nt_size > U16_MAX - (int)sizeof(struct smb_acl)) + return -EINVAL; + + (*ace_cnt)++; + *ace = (struct smb_ace *)((char *)*ace + ace_size); + return 0; } int smb_inherit_dacl(struct ksmbd_conn *conn, @@ -1157,6 +1176,12 @@ int smb_inherit_dacl(struct ksmbd_conn *conn, CIFS_SID_BASE_SIZE) break; + if (parent_aces->sid.num_subauth > SID_MAX_SUB_AUTHORITIES || + pace_size < offsetof(struct smb_ace, sid) + + CIFS_SID_BASE_SIZE + + sizeof(__le32) * parent_aces->sid.num_subauth) + break; + aces_size -= pace_size; flags = parent_aces->flags; @@ -1186,22 +1211,24 @@ int smb_inherit_dacl(struct ksmbd_conn *conn, } if (is_dir && creator && flags & CONTAINER_INHERIT_ACE) { - smb_set_ace(aces, psid, parent_aces->type, inherited_flags, - parent_aces->access_req); - nt_size += le16_to_cpu(aces->size); - ace_cnt++; - aces = (struct smb_ace *)((char *)aces + le16_to_cpu(aces->size)); + rc = smb_append_inherited_ace(&aces, &nt_size, &ace_cnt, + psid, parent_aces->type, + inherited_flags, + parent_aces->access_req); + if (rc) + goto free_aces_base; flags |= INHERIT_ONLY_ACE; psid = creator; } else if (is_dir && !(parent_aces->flags & NO_PROPAGATE_INHERIT_ACE)) { psid = &parent_aces->sid; } - smb_set_ace(aces, psid, parent_aces->type, flags | inherited_flags, - parent_aces->access_req); - nt_size += le16_to_cpu(aces->size); - aces = (struct smb_ace *)((char *)aces + le16_to_cpu(aces->size)); - ace_cnt++; + rc = smb_append_inherited_ace(&aces, &nt_size, &ace_cnt, psid, + parent_aces->type, + flags | inherited_flags, + parent_aces->access_req); + if (rc) + goto free_aces_base; pass: parent_aces = (struct smb_ace *)((char *)parent_aces + pace_size); } @@ -1211,7 +1238,7 @@ pass: struct smb_acl *pdacl; struct smb_sid *powner_sid = NULL, *pgroup_sid = NULL; int powner_sid_size = 0, pgroup_sid_size = 0, pntsd_size; - int pntsd_alloc_size; + size_t pntsd_alloc_size; if (parent_pntsd->osidoffset) { powner_sid = (struct smb_sid *)((char *)parent_pntsd + @@ -1224,8 +1251,19 @@ pass: pgroup_sid_size = 1 + 1 + 6 + (pgroup_sid->num_subauth * 4); } - pntsd_alloc_size = sizeof(struct smb_ntsd) + powner_sid_size + - pgroup_sid_size + sizeof(struct smb_acl) + nt_size; + if (check_add_overflow(sizeof(struct smb_ntsd), + (size_t)powner_sid_size, + &pntsd_alloc_size) || + check_add_overflow(pntsd_alloc_size, + (size_t)pgroup_sid_size, + &pntsd_alloc_size) || + check_add_overflow(pntsd_alloc_size, sizeof(struct smb_acl), + &pntsd_alloc_size) || + check_add_overflow(pntsd_alloc_size, (size_t)nt_size, + &pntsd_alloc_size)) { + rc = -EINVAL; + goto free_aces_base; + } pntsd = kzalloc(pntsd_alloc_size, KSMBD_DEFAULT_GFP); if (!pntsd) { diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c index a8242c00096f..b6d63ff8a8a3 100644 --- a/fs/smb/server/transport_rdma.c +++ b/fs/smb/server/transport_rdma.c @@ -18,7 +18,6 @@ #include "smb_common.h" #include "../common/smb2status.h" #include "transport_rdma.h" -#include "../smbdirect/public.h" #define SMB_DIRECT_PORT_IWARP 5445 @@ -540,3 +539,5 @@ static const struct ksmbd_transport_ops ksmbd_smb_direct_transport_ops = { .rdma_write = smb_direct_rdma_write, .free_transport = smb_direct_free_transport, }; + +MODULE_IMPORT_NS("SMBDIRECT"); diff --git a/fs/smb/server/transport_rdma.h b/fs/smb/server/transport_rdma.h index bde3d88aecc7..8b78917a1795 100644 --- a/fs/smb/server/transport_rdma.h +++ b/fs/smb/server/transport_rdma.h @@ -25,6 +25,6 @@ static inline void init_smbd_max_io_size(unsigned int sz) { } static inline unsigned int get_smbd_max_read_write_size(struct ksmbd_transport *kt) { return 0; } #endif -#include "../smbdirect/smbdirect.h" +#include <linux/smbdirect.h> #endif /* __KSMBD_TRANSPORT_RDMA_H__ */ diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index 3551f01a3fa0..354c4d8a1cfb 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -418,6 +418,14 @@ static void __ksmbd_remove_durable_fd(struct ksmbd_file *fp) return; idr_remove(global_ft.idr, fp->persistent_id); + /* + * Clear persistent_id so a later __ksmbd_close_fd() that runs from a + * delayed putter (e.g. when a concurrent ksmbd_lookup_fd_inode() + * walker held the final reference) does not re-issue idr_remove() on + * an id that idr_alloc_cyclic() may have already handed out to a new + * durable handle. + */ + fp->persistent_id = KSMBD_NO_FID; } static void ksmbd_remove_durable_fd(struct ksmbd_file *fp) @@ -431,13 +439,13 @@ static void ksmbd_remove_durable_fd(struct ksmbd_file *fp) static void __ksmbd_remove_fd(struct ksmbd_file_table *ft, struct ksmbd_file *fp) { - if (!has_file_id(fp->volatile_id)) - return; - down_write(&fp->f_ci->m_lock); list_del_init(&fp->node); up_write(&fp->f_ci->m_lock); + if (!has_file_id(fp->volatile_id)) + return; + write_lock(&ft->lock); idr_remove(ft->idr, fp->volatile_id); write_unlock(&ft->lock); @@ -475,6 +483,17 @@ static void __ksmbd_close_fd(struct ksmbd_file_table *ft, struct ksmbd_file *fp) kfree(smb_lock); } + /* + * Drop fp's strong reference on conn (taken in ksmbd_open_fd() / + * ksmbd_reopen_durable_fd()). Durable fps that reached the + * scavenger have already had fp->conn cleared by session_fd_check(), + * in which case there is nothing to drop here. + */ + if (fp->conn) { + ksmbd_conn_put(fp->conn); + fp->conn = NULL; + } + if (ksmbd_stream_fd(fp)) kfree(fp->stream.name); kfree(fp->owner.name); @@ -510,6 +529,20 @@ static struct ksmbd_file *__ksmbd_lookup_fd(struct ksmbd_file_table *ft, static void __put_fd_final(struct ksmbd_work *work, struct ksmbd_file *fp) { + /* + * Detached durable fp -- session_fd_check() cleared fp->conn at + * preserve, so this fp is no longer tracked by any conn's + * stats.open_files_count. This happens when + * ksmbd_scavenger_dispose_dh() hands the final close off to an + * m_fp_list walker (e.g. ksmbd_lookup_fd_inode()) whose work->conn + * is unrelated to the conn that originally opened the handle; close + * via the NULL-ft path so we do not underflow that unrelated + * counter. + */ + if (!fp->conn) { + __ksmbd_close_fd(NULL, fp); + return; + } __ksmbd_close_fd(&work->sess->file_table, fp); atomic_dec(&work->conn->stats.open_files_count); } @@ -752,7 +785,14 @@ struct ksmbd_file *ksmbd_open_fd(struct ksmbd_work *work, struct file *filp) atomic_set(&fp->refcount, 1); fp->filp = filp; - fp->conn = work->conn; + /* + * fp owns a strong reference on fp->conn for as long as fp->conn is + * non-NULL, so session_fd_check() and __ksmbd_close_fd() never + * dereference a dangling pointer. Paired with ksmbd_conn_put() in + * session_fd_check() (durable preserve), in __ksmbd_close_fd() + * (final close), and on the error paths below. + */ + fp->conn = ksmbd_conn_get(work->conn); fp->tcon = work->tcon; fp->volatile_id = KSMBD_NO_FID; fp->persistent_id = KSMBD_NO_FID; @@ -774,19 +814,64 @@ struct ksmbd_file *ksmbd_open_fd(struct ksmbd_work *work, struct file *filp) return fp; err_out: + /* fp->conn was set and refcounted before every branch here. */ + ksmbd_conn_put(fp->conn); kmem_cache_free(filp_cache, fp); return ERR_PTR(ret); } -void ksmbd_update_fstate(struct ksmbd_file_table *ft, struct ksmbd_file *fp, - unsigned int state) +/** + * ksmbd_update_fstate() - update an fp state under the file-table lock + * @ft: file table that publishes @fp's volatile id + * @fp: file pointer to update + * @state: new state + * + * Return: 0 on success. The FP_NEW -> FP_INITED transition is special: + * -ENOENT if teardown already unpublished @fp by advancing the state or + * clearing the volatile id. Other state updates preserve the historical + * fire-and-forget behavior. + */ +int ksmbd_update_fstate(struct ksmbd_file_table *ft, struct ksmbd_file *fp, + unsigned int state) { + int ret; + if (!fp) - return; + return -ENOENT; write_lock(&ft->lock); - fp->f_state = state; + if (state == FP_INITED && + (fp->f_state != FP_NEW || !has_file_id(fp->volatile_id))) { + ret = -ENOENT; + } else { + fp->f_state = state; + ret = 0; + } write_unlock(&ft->lock); + + return ret; +} + +/* + * ksmbd_mark_fp_closed() - mark fp closed under ft->lock and return how many + * refs the teardown path owns. + * + * FP_INITED has a normal idr-owned reference, so teardown owns both that + * reference and the transient lookup reference. FP_NEW is still owned by the + * in-flight opener/reopener, which will drop the original reference after + * ksmbd_update_fstate(..., FP_INITED) observes the cleared volatile id. + * FP_CLOSED on entry means an earlier ksmbd_close_fd() already consumed the + * idr-owned ref. + */ +static int ksmbd_mark_fp_closed(struct ksmbd_file *fp) +{ + if (fp->f_state == FP_INITED) { + set_close_state_blocked_works(fp); + fp->f_state = FP_CLOSED; + return 2; + } + + return 1; } static int @@ -794,7 +879,8 @@ __close_file_table_ids(struct ksmbd_session *sess, struct ksmbd_tree_connect *tcon, bool (*skip)(struct ksmbd_tree_connect *tcon, struct ksmbd_file *fp, - struct ksmbd_user *user)) + struct ksmbd_user *user), + bool skip_preserves_fp) { struct ksmbd_file_table *ft = &sess->file_table; struct ksmbd_file *fp; @@ -802,32 +888,120 @@ __close_file_table_ids(struct ksmbd_session *sess, int num = 0; while (1) { + int n_to_drop; + write_lock(&ft->lock); fp = idr_get_next(ft->idr, &id); if (!fp) { write_unlock(&ft->lock); break; } - - if (skip(tcon, fp, sess->user) || - !atomic_dec_and_test(&fp->refcount)) { + if (!atomic_inc_not_zero(&fp->refcount)) { id++; write_unlock(&ft->lock); continue; } - set_close_state_blocked_works(fp); - idr_remove(ft->idr, fp->volatile_id); - fp->volatile_id = KSMBD_NO_FID; - write_unlock(&ft->lock); + if (skip_preserves_fp) { + /* + * Session teardown: skip() is session_fd_check(), + * which may sleep and mutates fp->conn / fp->tcon / + * fp->volatile_id when it chooses to preserve fp + * for durable reconnect. Unpublish fp from the + * session idr here, under ft->lock, so that + * __ksmbd_lookup_fd() through this session cannot + * grant a new ksmbd_fp_get() reference to an fp + * whose fields are about to be rewritten outside + * the lock. Durable reconnect still reaches fp via + * global_ft. + */ + idr_remove(ft->idr, id); + fp->volatile_id = KSMBD_NO_FID; + write_unlock(&ft->lock); + if (skip(tcon, fp, sess->user)) { + /* + * session_fd_check() has converted fp to + * durable-preserve state and cleared its + * per-conn fields. fp is already unpublished + * above; the original idr-owned ref keeps it + * alive for the durable scavenger. Drop only + * the transient ref. atomic_dec() is safe -- + * atomic_inc_not_zero() succeeded on a + * positive value and we added one more, so + * refcount cannot be zero here. + */ + atomic_dec(&fp->refcount); + id++; + continue; + } + + /* + * Keep the close-state decision under the same lock + * observed by ksmbd_update_fstate(), which is how an + * in-flight FP_NEW opener learns that teardown has + * cleared its volatile id. + */ + write_lock(&ft->lock); + n_to_drop = ksmbd_mark_fp_closed(fp); + write_unlock(&ft->lock); + } else { + /* + * Tree teardown: skip() is tree_conn_fd_check(), a + * cheap pointer compare that doesn't sleep and has + * no side effects, so keep the skip decision plus + * the unpublish-and-mark-closed sequence atomic + * under ft->lock. fps belonging to other tree + * connects (skip() == true) stay fully published in + * the session idr with no lock window. + */ + if (skip(tcon, fp, sess->user)) { + atomic_dec(&fp->refcount); + write_unlock(&ft->lock); + id++; + continue; + } + idr_remove(ft->idr, id); + fp->volatile_id = KSMBD_NO_FID; + n_to_drop = ksmbd_mark_fp_closed(fp); + write_unlock(&ft->lock); + } + + /* + * fp->volatile_id is already cleared to prevent stale idr + * removal from a deferred final close. Remove fp from + * m_fp_list here because __ksmbd_remove_fd() will skip the + * list unlink when volatile_id is KSMBD_NO_FID. + */ down_write(&fp->f_ci->m_lock); list_del_init(&fp->node); up_write(&fp->f_ci->m_lock); - __ksmbd_close_fd(ft, fp); - - num++; + /* + * Drop the references this iteration owns: + * + * n_to_drop == 2: we observed FP_INITED and committed + * the FP_CLOSED transition ourselves, so we own the + * transient (+1) and the still-intact idr-owned ref. + * + * n_to_drop == 1: either a prior ksmbd_close_fd() + * already consumed the idr-owned ref, or fp was still + * FP_NEW and the in-flight opener/reopener must keep + * the original reference until ksmbd_update_fstate() + * observes the cleared volatile id. + * + * If we end up as the final putter, finalize fp and + * account the open_files_count decrement via the caller's + * atomic_sub(num, ...). Otherwise the remaining user's + * ksmbd_fd_put() reaches __put_fd_final(), which does its + * own atomic_dec(&open_files_count), so we must not count + * this fp here -- doing so would double-decrement the + * connection-wide counter. + */ + if (atomic_sub_and_test(n_to_drop, &fp->refcount)) { + __ksmbd_close_fd(NULL, fp); + num++; + } id++; } @@ -881,24 +1055,37 @@ static bool ksmbd_durable_scavenger_alive(void) return true; } -static void ksmbd_scavenger_dispose_dh(struct list_head *head) +static void ksmbd_scavenger_dispose_dh(struct ksmbd_file *fp) { - while (!list_empty(head)) { - struct ksmbd_file *fp; + /* + * Durable-preserved fp can remain linked on f_ci->m_fp_list for + * share-mode checks. Unlink it before final close; fp->node is not + * available as a scavenger-private list node because re-adding it to + * another list corrupts m_fp_list. + */ + down_write(&fp->f_ci->m_lock); + list_del_init(&fp->node); + up_write(&fp->f_ci->m_lock); - fp = list_first_entry(head, struct ksmbd_file, node); - list_del_init(&fp->node); + /* + * Drop both the durable lifetime reference and the transient reference + * taken by the scavenger under global_ft.lock. If a concurrent + * ksmbd_lookup_fd_inode() (or any other m_fp_list walker) snatched fp + * before the unlink above, that holder owns the final close via + * ksmbd_fd_put() -> __ksmbd_close_fd(). Otherwise the scavenger is + * the last putter and finalises fp here. + */ + if (atomic_sub_and_test(2, &fp->refcount)) __ksmbd_close_fd(NULL, fp); - } } static int ksmbd_durable_scavenger(void *dummy) { struct ksmbd_file *fp = NULL; + struct ksmbd_file *expired_fp; unsigned int id; unsigned int min_timeout = 1; bool found_fp_timeout; - LIST_HEAD(scavenger_list); unsigned long remaining_jiffies; __module_get(THIS_MODULE); @@ -908,8 +1095,6 @@ static int ksmbd_durable_scavenger(void *dummy) if (try_to_freeze()) continue; - found_fp_timeout = false; - remaining_jiffies = wait_event_timeout(dh_wq, ksmbd_durable_scavenger_alive() == false, __msecs_to_jiffies(min_timeout)); @@ -918,23 +1103,39 @@ static int ksmbd_durable_scavenger(void *dummy) else min_timeout = DURABLE_HANDLE_MAX_TIMEOUT; - write_lock(&global_ft.lock); - idr_for_each_entry(global_ft.idr, fp, id) { - if (!fp->durable_timeout) - continue; + do { + expired_fp = NULL; + found_fp_timeout = false; - if (atomic_read(&fp->refcount) > 1 || - fp->conn) - continue; - - found_fp_timeout = true; - if (fp->durable_scavenger_timeout <= - jiffies_to_msecs(jiffies)) { - __ksmbd_remove_durable_fd(fp); - list_add(&fp->node, &scavenger_list); - } else { + write_lock(&global_ft.lock); + idr_for_each_entry(global_ft.idr, fp, id) { unsigned long durable_timeout; + if (!fp->durable_timeout) + continue; + + if (atomic_read(&fp->refcount) > 1 || + fp->conn) + continue; + + found_fp_timeout = true; + if (fp->durable_scavenger_timeout <= + jiffies_to_msecs(jiffies)) { + __ksmbd_remove_durable_fd(fp); + /* + * Take a transient reference so fp + * cannot be freed by an in-flight + * ksmbd_lookup_fd_inode() that found + * it through f_ci->m_fp_list while we + * drop global_ft.lock and reach the + * m_fp_list unlink in + * ksmbd_scavenger_dispose_dh(). + */ + atomic_inc(&fp->refcount); + expired_fp = fp; + break; + } + durable_timeout = fp->durable_scavenger_timeout - jiffies_to_msecs(jiffies); @@ -942,10 +1143,11 @@ static int ksmbd_durable_scavenger(void *dummy) if (min_timeout > durable_timeout) min_timeout = durable_timeout; } - } - write_unlock(&global_ft.lock); + write_unlock(&global_ft.lock); - ksmbd_scavenger_dispose_dh(&scavenger_list); + if (expired_fp) + ksmbd_scavenger_dispose_dh(expired_fp); + } while (expired_fp); if (found_fp_timeout == false) break; @@ -1062,25 +1264,35 @@ static bool session_fd_check(struct ksmbd_tree_connect *tcon, if (!is_reconnectable(fp)) return false; + if (fp->f_state != FP_INITED) + return false; + + if (WARN_ON_ONCE(!fp->conn)) + return false; + if (ksmbd_vfs_copy_durable_owner(fp, user)) return false; + /* + * fp owns a strong reference on fp->conn (taken in ksmbd_open_fd() + * / ksmbd_reopen_durable_fd()), so conn stays valid for the whole + * body of this function regardless of any op->conn puts below. + */ conn = fp->conn; ci = fp->f_ci; down_write(&ci->m_lock); list_for_each_entry_rcu(op, &ci->m_op_list, op_entry) { if (op->conn != conn) continue; - if (op->conn && atomic_dec_and_test(&op->conn->refcnt)) - kfree(op->conn); + ksmbd_conn_put(op->conn); op->conn = NULL; } up_write(&ci->m_lock); list_for_each_entry_safe(smb_lock, tmp_lock, &fp->lock_list, flist) { - spin_lock(&fp->conn->llist_lock); + spin_lock(&conn->llist_lock); list_del_init(&smb_lock->clist); - spin_unlock(&fp->conn->llist_lock); + spin_unlock(&conn->llist_lock); } fp->conn = NULL; @@ -1091,6 +1303,8 @@ static bool session_fd_check(struct ksmbd_tree_connect *tcon, fp->durable_scavenger_timeout = jiffies_to_msecs(jiffies) + fp->durable_timeout; + /* Drop fp's own reference on conn. */ + ksmbd_conn_put(conn); return true; } @@ -1098,7 +1312,8 @@ void ksmbd_close_tree_conn_fds(struct ksmbd_work *work) { int num = __close_file_table_ids(work->sess, work->tcon, - tree_conn_fd_check); + tree_conn_fd_check, + false); atomic_sub(num, &work->conn->stats.open_files_count); } @@ -1107,7 +1322,8 @@ void ksmbd_close_session_fds(struct ksmbd_work *work) { int num = __close_file_table_ids(work->sess, work->tcon, - session_fd_check); + session_fd_check, + true); atomic_sub(num, &work->conn->stats.open_files_count); } @@ -1178,15 +1394,27 @@ int ksmbd_reopen_durable_fd(struct ksmbd_work *work, struct ksmbd_file *fp) old_f_state = fp->f_state; fp->f_state = FP_NEW; + + /* + * Initialize fp's connection binding before publishing fp into the + * session's file table. If __open_id() is ordered first, a + * concurrent teardown that iterates the table can observe a valid + * volatile_id with fp->conn == NULL and preserve a + * partially-initialized fp. fp owns a strong reference on the new + * conn (see ksmbd_open_fd()); undo it on __open_id() failure. + */ + fp->conn = ksmbd_conn_get(conn); + fp->tcon = work->tcon; + __open_id(&work->sess->file_table, fp, OPEN_ID_TYPE_VOLATILE_ID); if (!has_file_id(fp->volatile_id)) { + fp->conn = NULL; + fp->tcon = NULL; + ksmbd_conn_put(conn); fp->f_state = old_f_state; return -EBADF; } - fp->conn = conn; - fp->tcon = work->tcon; - list_for_each_entry(smb_lock, &fp->lock_list, flist) { spin_lock(&conn->llist_lock); list_add_tail(&smb_lock->clist, &conn->lock_list); @@ -1198,8 +1426,7 @@ int ksmbd_reopen_durable_fd(struct ksmbd_work *work, struct ksmbd_file *fp) list_for_each_entry_rcu(op, &ci->m_op_list, op_entry) { if (op->conn) continue; - op->conn = fp->conn; - atomic_inc(&op->conn->refcnt); + op->conn = ksmbd_conn_get(fp->conn); } up_write(&ci->m_lock); @@ -1228,7 +1455,7 @@ void ksmbd_destroy_file_table(struct ksmbd_session *sess) if (!ft->idr) return; - __close_file_table_ids(sess, NULL, session_fd_check); + __close_file_table_ids(sess, NULL, session_fd_check, true); idr_destroy(ft->idr); kfree(ft->idr); ft->idr = NULL; diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h index 866f32c10d4d..e6871266a94b 100644 --- a/fs/smb/server/vfs_cache.h +++ b/fs/smb/server/vfs_cache.h @@ -172,8 +172,8 @@ int ksmbd_close_inode_fds(struct ksmbd_work *work, struct inode *inode); int ksmbd_init_global_file_table(void); void ksmbd_free_global_file_table(void); void ksmbd_set_fd_limit(unsigned long limit); -void ksmbd_update_fstate(struct ksmbd_file_table *ft, struct ksmbd_file *fp, - unsigned int state); +int ksmbd_update_fstate(struct ksmbd_file_table *ft, struct ksmbd_file *fp, + unsigned int state); bool ksmbd_vfs_compare_durable_owner(struct ksmbd_file *fp, struct ksmbd_user *user); diff --git a/fs/smb/smbdirect/accept.c b/fs/smb/smbdirect/accept.c index 704b271af3a8..529740005838 100644 --- a/fs/smb/smbdirect/accept.c +++ b/fs/smb/smbdirect/accept.c @@ -854,4 +854,4 @@ struct smbdirect_socket *smbdirect_socket_accept(struct smbdirect_socket *lsc, return nsc; } -__SMBDIRECT_EXPORT_SYMBOL__(smbdirect_socket_accept); +EXPORT_SYMBOL_GPL(smbdirect_socket_accept); diff --git a/fs/smb/smbdirect/connect.c b/fs/smb/smbdirect/connect.c index 8addee43a381..cd726b399afe 100644 --- a/fs/smb/smbdirect/connect.c +++ b/fs/smb/smbdirect/connect.c @@ -60,7 +60,7 @@ int smbdirect_connect(struct smbdirect_socket *sc, const struct sockaddr *dst) */ return 0; } -__SMBDIRECT_EXPORT_SYMBOL__(smbdirect_connect); +EXPORT_SYMBOL_GPL(smbdirect_connect); static int smbdirect_connect_setup_connection(struct smbdirect_socket *sc) { @@ -922,4 +922,4 @@ int smbdirect_connect_sync(struct smbdirect_socket *sc, return 0; } -__SMBDIRECT_EXPORT_SYMBOL__(smbdirect_connect_sync); +EXPORT_SYMBOL_GPL(smbdirect_connect_sync); diff --git a/fs/smb/smbdirect/connection.c b/fs/smb/smbdirect/connection.c index 822366718d45..fe9912e53da6 100644 --- a/fs/smb/smbdirect/connection.c +++ b/fs/smb/smbdirect/connection.c @@ -706,7 +706,7 @@ bool smbdirect_connection_is_connected(struct smbdirect_socket *sc) return false; return true; } -__SMBDIRECT_EXPORT_SYMBOL__(smbdirect_connection_is_connected); +EXPORT_SYMBOL_GPL(smbdirect_connection_is_connected); int smbdirect_connection_wait_for_connected(struct smbdirect_socket *sc) { @@ -779,7 +779,7 @@ int smbdirect_connection_wait_for_connected(struct smbdirect_socket *sc) return 0; } -__SMBDIRECT_EXPORT_SYMBOL__(smbdirect_connection_wait_for_connected); +EXPORT_SYMBOL_GPL(smbdirect_connection_wait_for_connected); void smbdirect_connection_idle_timer_work(struct work_struct *work) { @@ -958,7 +958,7 @@ release_credit: return ret; } -__SMBDIRECT_EXPORT_SYMBOL__(smbdirect_connection_send_batch_flush); +EXPORT_SYMBOL_GPL(smbdirect_connection_send_batch_flush); struct smbdirect_send_batch * smbdirect_init_send_batch_storage(struct smbdirect_send_batch_storage *storage, @@ -976,7 +976,7 @@ smbdirect_init_send_batch_storage(struct smbdirect_send_batch_storage *storage, return batch; } -__SMBDIRECT_EXPORT_SYMBOL__(smbdirect_init_send_batch_storage); +EXPORT_SYMBOL_GPL(smbdirect_init_send_batch_storage); static int smbdirect_connection_wait_for_send_bcredit(struct smbdirect_socket *sc, struct smbdirect_send_batch *batch) @@ -1263,7 +1263,7 @@ lcredit_failed: bcredit_failed: return ret; } -__SMBDIRECT_EXPORT_SYMBOL__(smbdirect_connection_send_single_iter); +EXPORT_SYMBOL_GPL(smbdirect_connection_send_single_iter); int smbdirect_connection_send_wait_zero_pending(struct smbdirect_socket *sc) { @@ -1288,7 +1288,7 @@ int smbdirect_connection_send_wait_zero_pending(struct smbdirect_socket *sc) return 0; } -__SMBDIRECT_EXPORT_SYMBOL__(smbdirect_connection_send_wait_zero_pending); +EXPORT_SYMBOL_GPL(smbdirect_connection_send_wait_zero_pending); int smbdirect_connection_send_iter(struct smbdirect_socket *sc, struct iov_iter *iter, @@ -1373,7 +1373,7 @@ int smbdirect_connection_send_iter(struct smbdirect_socket *sc, return total_count; } -__SMBDIRECT_EXPORT_SYMBOL__(smbdirect_connection_send_iter); +EXPORT_SYMBOL_GPL(smbdirect_connection_send_iter); static void smbdirect_connection_send_io_done(struct ib_cq *cq, struct ib_wc *wc) { @@ -1937,7 +1937,7 @@ read_rfc1002_done: goto again; } -__SMBDIRECT_EXPORT_SYMBOL__(smbdirect_connection_recvmsg); +EXPORT_SYMBOL_GPL(smbdirect_connection_recvmsg); static bool smbdirect_map_sges_single_page(struct smbdirect_map_sges *state, struct page *page, size_t off, size_t len) diff --git a/fs/smb/smbdirect/debug.c b/fs/smb/smbdirect/debug.c index a66a19d4a463..05ba7c8d165e 100644 --- a/fs/smb/smbdirect/debug.c +++ b/fs/smb/smbdirect/debug.c @@ -85,4 +85,4 @@ void smbdirect_connection_legacy_debug_proc_show(struct smbdirect_socket *sc, atomic_read(&sc->mr_io.ready.count), atomic_read(&sc->mr_io.used.count)); } -__SMBDIRECT_EXPORT_SYMBOL__(smbdirect_connection_legacy_debug_proc_show); +EXPORT_SYMBOL_GPL(smbdirect_connection_legacy_debug_proc_show); diff --git a/fs/smb/smbdirect/devices.c b/fs/smb/smbdirect/devices.c index 44962f221c35..7adacbdfe12e 100644 --- a/fs/smb/smbdirect/devices.c +++ b/fs/smb/smbdirect/devices.c @@ -238,7 +238,7 @@ u8 smbdirect_netdev_rdma_capable_node_type(struct net_device *netdev) return RDMA_NODE_UNSPECIFIED; } -__SMBDIRECT_EXPORT_SYMBOL__(smbdirect_netdev_rdma_capable_node_type); +EXPORT_SYMBOL_GPL(smbdirect_netdev_rdma_capable_node_type); __init int smbdirect_devices_init(void) { diff --git a/fs/smb/smbdirect/internal.h b/fs/smb/smbdirect/internal.h index 2d5acf2c21bc..e9959e6dc13a 100644 --- a/fs/smb/smbdirect/internal.h +++ b/fs/smb/smbdirect/internal.h @@ -6,11 +6,11 @@ #ifndef __FS_SMB_COMMON_SMBDIRECT_INTERNAL_H__ #define __FS_SMB_COMMON_SMBDIRECT_INTERNAL_H__ +#define DEFAULT_SYMBOL_NAMESPACE "SMBDIRECT" #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include "smbdirect.h" +#include <linux/smbdirect.h> #include "pdu.h" -#include "public.h" #include <linux/mutex.h> diff --git a/fs/smb/smbdirect/listen.c b/fs/smb/smbdirect/listen.c index 143a7618d95f..2f78bcaedbf8 100644 --- a/fs/smb/smbdirect/listen.c +++ b/fs/smb/smbdirect/listen.c @@ -90,7 +90,7 @@ int smbdirect_socket_listen(struct smbdirect_socket *sc, int backlog) */ return 0; } -__SMBDIRECT_EXPORT_SYMBOL__(smbdirect_socket_listen); +EXPORT_SYMBOL_GPL(smbdirect_socket_listen); static int smbdirect_new_rdma_event_handler(struct rdma_cm_id *new_id, struct rdma_cm_event *event) diff --git a/fs/smb/smbdirect/mr.c b/fs/smb/smbdirect/mr.c index 5228e699cd5d..15c6363a2f97 100644 --- a/fs/smb/smbdirect/mr.c +++ b/fs/smb/smbdirect/mr.c @@ -269,7 +269,7 @@ smbdirect_connection_register_mr_io(struct smbdirect_socket *sc, { const struct smbdirect_socket_parameters *sp = &sc->parameters; struct smbdirect_mr_io *mr; - int ret, num_pages; + int ret, num_pages, num_mapped; struct ib_reg_wr *reg_wr; num_pages = iov_iter_npages(iter, sp->max_frmr_depth + 1); @@ -300,19 +300,22 @@ smbdirect_connection_register_mr_io(struct smbdirect_socket *sc, num_pages, iov_iter_count(iter), sp->max_frmr_depth); smbdirect_iter_to_sgt(iter, &mr->sgt, sp->max_frmr_depth); - ret = ib_dma_map_sg(sc->ib.dev, mr->sgt.sgl, mr->sgt.nents, mr->dir); - if (!ret) { + num_mapped = ib_dma_map_sg(sc->ib.dev, mr->sgt.sgl, mr->sgt.nents, mr->dir); + if (!num_mapped) { smbdirect_log_rdma_mr(sc, SMBDIRECT_LOG_ERR, - "ib_dma_map_sg num_pages=%u dir=%x ret=%d (%1pe)\n", - num_pages, mr->dir, ret, SMBDIRECT_DEBUG_ERR_PTR(ret)); + "ib_dma_map_sg num_pages=%u dir=%x num_mapped=%d\n", + num_pages, mr->dir, num_mapped); + ret = -EIO; goto dma_map_error; } - ret = ib_map_mr_sg(mr->mr, mr->sgt.sgl, mr->sgt.nents, NULL, PAGE_SIZE); - if (ret != mr->sgt.nents) { + ret = ib_map_mr_sg(mr->mr, mr->sgt.sgl, num_mapped, NULL, PAGE_SIZE); + if (ret != num_mapped) { smbdirect_log_rdma_mr(sc, SMBDIRECT_LOG_ERR, - "ib_map_mr_sg failed ret = %d nents = %u\n", - ret, mr->sgt.nents); + "ib_map_mr_sg failed ret = %d num_mapped = %u\n", + ret, num_mapped); + if (ret >= 0) + ret = -EIO; goto map_mr_error; } @@ -380,7 +383,7 @@ dma_map_error: mutex_unlock(&mr->mutex); return NULL; } -__SMBDIRECT_EXPORT_SYMBOL__(smbdirect_connection_register_mr_io); +EXPORT_SYMBOL_GPL(smbdirect_connection_register_mr_io); void smbdirect_mr_io_fill_buffer_descriptor(struct smbdirect_mr_io *mr, struct smbdirect_buffer_descriptor_v1 *v1) @@ -397,7 +400,7 @@ void smbdirect_mr_io_fill_buffer_descriptor(struct smbdirect_mr_io *mr, } mutex_unlock(&mr->mutex); } -__SMBDIRECT_EXPORT_SYMBOL__(smbdirect_mr_io_fill_buffer_descriptor); +EXPORT_SYMBOL_GPL(smbdirect_mr_io_fill_buffer_descriptor); /* * Deregister a MR after I/O is done @@ -490,4 +493,4 @@ put_kref: if (!kref_put(&mr->kref, smbdirect_mr_io_free_locked)) mutex_unlock(&mr->mutex); } -__SMBDIRECT_EXPORT_SYMBOL__(smbdirect_connection_deregister_mr_io); +EXPORT_SYMBOL_GPL(smbdirect_connection_deregister_mr_io); diff --git a/fs/smb/smbdirect/rw.c b/fs/smb/smbdirect/rw.c index c2f46b17731e..6fe38042cfb9 100644 --- a/fs/smb/smbdirect/rw.c +++ b/fs/smb/smbdirect/rw.c @@ -252,4 +252,4 @@ free_msg: kfree(msg); goto out; } -__SMBDIRECT_EXPORT_SYMBOL__(smbdirect_connection_rdma_xmit); +EXPORT_SYMBOL_GPL(smbdirect_connection_rdma_xmit); diff --git a/fs/smb/smbdirect/smbdirect.h b/fs/smb/smbdirect/smbdirect.h deleted file mode 100644 index bbab5f7f7cc9..000000000000 --- a/fs/smb/smbdirect/smbdirect.h +++ /dev/null @@ -1,52 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Copyright (C) 2025 Stefan Metzmacher - */ - -#ifndef __FS_SMB_COMMON_SMBDIRECT_SMBDIRECT_H__ -#define __FS_SMB_COMMON_SMBDIRECT_SMBDIRECT_H__ - -#include <linux/types.h> - -/* SMB-DIRECT buffer descriptor V1 structure [MS-SMBD] 2.2.3.1 */ -struct smbdirect_buffer_descriptor_v1 { - __le64 offset; - __le32 token; - __le32 length; -} __packed; - -/* - * Connection parameters mostly from [MS-SMBD] 3.1.1.1 - * - * These are setup and negotiated at the beginning of a - * connection and remain constant unless explicitly changed. - * - * Some values are important for the upper layer. - */ -struct smbdirect_socket_parameters { - __u64 flags; -#define SMBDIRECT_FLAG_PORT_RANGE_ONLY_IB ((__u64)0x1) -#define SMBDIRECT_FLAG_PORT_RANGE_ONLY_IW ((__u64)0x2) - __u32 resolve_addr_timeout_msec; - __u32 resolve_route_timeout_msec; - __u32 rdma_connect_timeout_msec; - __u32 negotiate_timeout_msec; - __u16 initiator_depth; /* limited to U8_MAX */ - __u16 responder_resources; /* limited to U8_MAX */ - __u16 recv_credit_max; - __u16 send_credit_target; - __u32 max_send_size; - __u32 max_fragmented_send_size; - __u32 max_recv_size; - __u32 max_fragmented_recv_size; - __u32 max_read_write_size; - __u32 max_frmr_depth; - __u32 keepalive_interval_msec; - __u32 keepalive_timeout_msec; -} __packed; - -#define SMBDIRECT_FLAG_PORT_RANGE_MASK ( \ - SMBDIRECT_FLAG_PORT_RANGE_ONLY_IB | \ - SMBDIRECT_FLAG_PORT_RANGE_ONLY_IW) - -#endif /* __FS_SMB_COMMON_SMBDIRECT_SMBDIRECT_H__ */ diff --git a/fs/smb/smbdirect/socket.c b/fs/smb/smbdirect/socket.c index 1b4ab01b745e..39cca7219c4d 100644 --- a/fs/smb/smbdirect/socket.c +++ b/fs/smb/smbdirect/socket.c @@ -20,7 +20,7 @@ bool smbdirect_frwr_is_supported(const struct ib_device_attr *attrs) return false; return true; } -__SMBDIRECT_EXPORT_SYMBOL__(smbdirect_frwr_is_supported); +EXPORT_SYMBOL_GPL(smbdirect_frwr_is_supported); static void smbdirect_socket_cleanup_work(struct work_struct *work); @@ -107,7 +107,7 @@ init_failed: alloc_failed: return ret; } -__SMBDIRECT_EXPORT_SYMBOL__(smbdirect_socket_create_kern); +EXPORT_SYMBOL_GPL(smbdirect_socket_create_kern); int smbdirect_socket_init_accepting(struct rdma_cm_id *id, struct smbdirect_socket *sc) { @@ -148,7 +148,7 @@ init_failed: alloc_failed: return ret; } -__SMBDIRECT_EXPORT_SYMBOL__(smbdirect_socket_create_accepting); +EXPORT_SYMBOL_GPL(smbdirect_socket_create_accepting); int smbdirect_socket_set_initial_parameters(struct smbdirect_socket *sc, const struct smbdirect_socket_parameters *sp) @@ -189,14 +189,14 @@ int smbdirect_socket_set_initial_parameters(struct smbdirect_socket *sc, return 0; } -__SMBDIRECT_EXPORT_SYMBOL__(smbdirect_socket_set_initial_parameters); +EXPORT_SYMBOL_GPL(smbdirect_socket_set_initial_parameters); const struct smbdirect_socket_parameters * smbdirect_socket_get_current_parameters(struct smbdirect_socket *sc) { return &sc->parameters; } -__SMBDIRECT_EXPORT_SYMBOL__(smbdirect_socket_get_current_parameters); +EXPORT_SYMBOL_GPL(smbdirect_socket_get_current_parameters); int smbdirect_socket_set_kernel_settings(struct smbdirect_socket *sc, enum ib_poll_context poll_ctx, @@ -220,7 +220,7 @@ int smbdirect_socket_set_kernel_settings(struct smbdirect_socket *sc, return 0; } -__SMBDIRECT_EXPORT_SYMBOL__(smbdirect_socket_set_kernel_settings); +EXPORT_SYMBOL_GPL(smbdirect_socket_set_kernel_settings); void smbdirect_socket_set_logging(struct smbdirect_socket *sc, void *private_ptr, @@ -240,7 +240,7 @@ void smbdirect_socket_set_logging(struct smbdirect_socket *sc, sc->logging.needed = needed; sc->logging.vaprintf = vaprintf; } -__SMBDIRECT_EXPORT_SYMBOL__(smbdirect_socket_set_logging); +EXPORT_SYMBOL_GPL(smbdirect_socket_set_logging); static void smbdirect_socket_wake_up_all(struct smbdirect_socket *sc) { @@ -663,13 +663,13 @@ int smbdirect_socket_bind(struct smbdirect_socket *sc, struct sockaddr *addr) return 0; } -__SMBDIRECT_EXPORT_SYMBOL__(smbdirect_socket_bind); +EXPORT_SYMBOL_GPL(smbdirect_socket_bind); void smbdirect_socket_shutdown(struct smbdirect_socket *sc) { smbdirect_socket_schedule_cleanup_lvl(sc, SMBDIRECT_LOG_INFO, -ESHUTDOWN); } -__SMBDIRECT_EXPORT_SYMBOL__(smbdirect_socket_shutdown); +EXPORT_SYMBOL_GPL(smbdirect_socket_shutdown); static void smbdirect_socket_release_disconnect(struct kref *kref) { @@ -712,7 +712,7 @@ void smbdirect_socket_release(struct smbdirect_socket *sc) */ kref_put(&sc->refs.destroy, smbdirect_socket_release_destroy); } -__SMBDIRECT_EXPORT_SYMBOL__(smbdirect_socket_release); +EXPORT_SYMBOL_GPL(smbdirect_socket_release); int smbdirect_socket_wait_for_credits(struct smbdirect_socket *sc, enum smbdirect_socket_status expected_status, diff --git a/fs/udf/misc.c b/fs/udf/misc.c index 0788593b6a1d..6928e378fbbd 100644 --- a/fs/udf/misc.c +++ b/fs/udf/misc.c @@ -230,8 +230,12 @@ struct buffer_head *udf_read_tagged(struct super_block *sb, uint32_t block, } /* Verify the descriptor CRC */ - if (le16_to_cpu(tag_p->descCRCLength) + sizeof(struct tag) > sb->s_blocksize || - le16_to_cpu(tag_p->descCRC) == crc_itu_t(0, + if (le16_to_cpu(tag_p->descCRCLength) + sizeof(struct tag) > sb->s_blocksize) { + udf_err(sb, "block %u: CRC length %u exceeds block size\n", + block, le16_to_cpu(tag_p->descCRCLength)); + goto error_out; + } + if (le16_to_cpu(tag_p->descCRC) == crc_itu_t(0, bh->b_data + sizeof(struct tag), le16_to_cpu(tag_p->descCRCLength))) return bh; diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index b701b5f972cb..c41d9a7565cf 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -17,6 +17,8 @@ #include <linux/property.h> #include <linux/types.h> +struct notifier_block; + struct acpi_handle_list { u32 count; acpi_handle *handles; diff --git a/include/acpi/actbl1.h b/include/acpi/actbl1.h index 4e15583e0d25..f72e00517eb3 100644 --- a/include/acpi/actbl1.h +++ b/include/acpi/actbl1.h @@ -1386,6 +1386,12 @@ enum acpi_einj_command_status { #define ACPI_EINJ_CXL_MEM_FATAL (1<<17) #define ACPI_EINJ_VENDOR_DEFINED (1<<31) +/* EINJV2 error types from EINJV2_GET_ERROR_TYPE (ACPI 6.6) */ + +#define ACPI_EINJV2_PROCESSOR (1) +#define ACPI_EINJV2_MEMORY (1<<1) +#define ACPI_EINJV2_PCIE (1<<2) + /******************************************************************************* * * ERST - Error Record Serialization Table (ACPI 4.0) diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h index bf391903443d..0c5e5ed7b5e7 100644 --- a/include/drm/drm_fb_helper.h +++ b/include/drm/drm_fb_helper.h @@ -273,6 +273,12 @@ int drm_fb_helper_hotplug_event(struct drm_fb_helper *fb_helper); int drm_fb_helper_initial_config(struct drm_fb_helper *fb_helper); bool drm_fb_helper_gem_is_fb(const struct drm_fb_helper *fb_helper, const struct drm_gem_object *obj); +#else +static inline bool drm_fb_helper_gem_is_fb(const struct drm_fb_helper *fb_helper, + const struct drm_gem_object *obj) +{ + return false; +} #endif #endif diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index f42563739d2e..50a784da7a81 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -611,8 +611,8 @@ struct cgroup { /* used to wait for offlining of csses */ wait_queue_head_t offline_waitq; - /* used by cgroup_rmdir() to wait for dying tasks to leave */ - wait_queue_head_t dying_populated_waitq; + /* defers killing csses after removal until cgroup is depopulated */ + struct work_struct finish_destroy_work; /* used to schedule release agent */ struct work_struct release_agent_work; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index e52160e85af4..f6d037a30fd8 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -53,6 +53,7 @@ struct kernel_clone_args; enum css_task_iter_flags { CSS_TASK_ITER_PROCS = (1U << 0), /* walk only threadgroup leaders */ CSS_TASK_ITER_THREADED = (1U << 1), /* walk all threaded css_sets in the domain */ + CSS_TASK_ITER_WITH_DEAD = (1U << 2), /* include exiting tasks */ CSS_TASK_ITER_SKIPPED = (1U << 16), /* internal flags */ }; diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 166933b82e27..d1203da56fc5 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -322,13 +322,13 @@ struct dma_buf { * @vmapping_counter: * * Used internally to refcnt the vmaps returned by dma_buf_vmap(). - * Protected by @lock. + * Protected by @resv. */ unsigned vmapping_counter; /** * @vmap_ptr: - * The current vmap ptr if @vmapping_counter > 0. Protected by @lock. + * The current vmap ptr if @vmapping_counter > 0. Protected by @resv. */ struct iosys_map vmap_ptr; diff --git a/include/linux/dpll.h b/include/linux/dpll.h index b7277a8b484d..f8037f1ab20b 100644 --- a/include/linux/dpll.h +++ b/include/linux/dpll.h @@ -286,6 +286,7 @@ int dpll_pin_ref_sync_pair_add(struct dpll_pin *pin, int dpll_device_change_ntf(struct dpll_device *dpll); +int __dpll_pin_change_ntf(struct dpll_pin *pin); int dpll_pin_change_ntf(struct dpll_pin *pin); int register_dpll_notifier(struct notifier_block *nb); diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 95985400d3d8..e5cde39d6e85 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -915,6 +915,7 @@ extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group, unsigned int obj_type); extern void fsnotify_get_mark(struct fsnotify_mark *mark); extern void fsnotify_put_mark(struct fsnotify_mark *mark); +struct fsnotify_mark *fsnotify_next_mark(struct fsnotify_mark *mark); extern void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info); extern bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info); diff --git a/include/linux/mailbox_client.h b/include/linux/mailbox_client.h index c6eea9afb943..e5997120f45c 100644 --- a/include/linux/mailbox_client.h +++ b/include/linux/mailbox_client.h @@ -45,6 +45,7 @@ int mbox_send_message(struct mbox_chan *chan, void *mssg); int mbox_flush(struct mbox_chan *chan, unsigned long timeout); void mbox_client_txdone(struct mbox_chan *chan, int r); /* atomic */ bool mbox_client_peek_data(struct mbox_chan *chan); /* atomic */ +unsigned int mbox_chan_tx_slots_available(struct mbox_chan *chan); /* atomic */ void mbox_free_channel(struct mbox_chan *chan); /* may sleep */ #endif /* __MAILBOX_CLIENT_H */ diff --git a/include/linux/mailbox_controller.h b/include/linux/mailbox_controller.h index 80a427c7ca29..dc93287a2a01 100644 --- a/include/linux/mailbox_controller.h +++ b/include/linux/mailbox_controller.h @@ -3,6 +3,7 @@ #ifndef __MAILBOX_CONTROLLER_H #define __MAILBOX_CONTROLLER_H +#include <linux/bits.h> #include <linux/completion.h> #include <linux/device.h> #include <linux/hrtimer.h> @@ -11,6 +12,13 @@ struct mbox_chan; +/* Sentinel value distinguishing "no active request" from "NULL message data" */ +#define MBOX_NO_MSG ((void *)-1) + +#define MBOX_TXDONE_BY_IRQ BIT(0) /* controller has remote RTR irq */ +#define MBOX_TXDONE_BY_POLL BIT(1) /* controller can read status of last TX */ +#define MBOX_TXDONE_BY_ACK BIT(2) /* S/W ACK received by Client ticks the TX */ + /** * struct mbox_chan_ops - methods to control mailbox channels * @send_data: The API asks the MBOX controller driver, in atomic @@ -54,10 +62,10 @@ struct mbox_chan_ops { /** * struct mbox_controller - Controller of a class of communication channels - * @dev: Device backing this controller - * @ops: Operators that work on each communication chan - * @chans: Array of channels - * @num_chans: Number of channels in the 'chans' array. + * @dev: Device backing this controller. Required. + * @ops: Operators that work on each communication chan. Required. + * @chans: Array of channels. Required. + * @num_chans: Number of channels in the 'chans' array. Required. * @txdone_irq: Indicates if the controller can report to API when * the last transmitted data was read by the remote. * Eg, if it has some TX ACK irq. @@ -70,6 +78,7 @@ struct mbox_chan_ops { * @of_xlate: Controller driver specific mapping of channel via DT * @poll_hrt: API private. hrtimer used to poll for TXDONE on all * channels. + * @poll_hrt_lock: API private. Lock protecting access to poll_hrt. * @node: API private. To hook into list of controllers. */ struct mbox_controller { diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h index 0c464eade1d6..4a5631906aff 100644 --- a/include/linux/maple_tree.h +++ b/include/linux/maple_tree.h @@ -4,7 +4,7 @@ /* * Maple Tree - An RCU-safe adaptive tree for storing ranges * Copyright (c) 2018-2022 Oracle - * Authors: Liam R. Howlett <Liam.Howlett@Oracle.com> + * Authors: Liam R. Howlett <liam@infradead.org> * Matthew Wilcox <willy@infradead.org> */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 0b776907152e..af23453e9dbd 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -4391,7 +4391,7 @@ static inline void mmap_action_map_kernel_pages_full(struct vm_area_desc *desc, int mmap_action_prepare(struct vm_area_desc *desc); int mmap_action_complete(struct vm_area_struct *vma, - struct mmap_action *action); + struct mmap_action *action, bool is_compat); /* Look up the first VMA which exactly match the interval vm_start ... vm_end */ static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm, diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h index cf3374580f74..5d75cc5b057e 100644 --- a/include/linux/mroute_base.h +++ b/include/linux/mroute_base.h @@ -226,6 +226,7 @@ struct mr_table_ops { /** * struct mr_table - a multicast routing table + * @work: used for table destruction * @list: entry within a list of multicast routing tables * @net: net where this table belongs * @ops: protocol specific operations @@ -243,6 +244,7 @@ struct mr_table_ops { * @mroute_reg_vif_num: PIM-device vif index */ struct mr_table { + struct rcu_work work; struct list_head list; possible_net_t net; struct mr_table_ops ops; @@ -274,6 +276,7 @@ void vif_device_init(struct vif_device *v, unsigned short flags, unsigned short get_iflink_mask); +void mr_table_free(struct mr_table *mrt); struct mr_table * mr_table_alloc(struct net *net, u32 id, struct mr_table_ops *ops, diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index 58abd306ebe3..782984ba3a20 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -290,6 +290,12 @@ SPI_MEM_OP_NO_DUMMY, \ SPI_MEM_OP_NO_DATA) +#define SPINAND_PAGE_READ_PACKED_8D_8D_0_OP(addr) \ + SPI_MEM_OP(SPI_MEM_DTR_OP_PACKED_CMD(0x13, addr >> 16, 8), \ + SPI_MEM_DTR_OP_ADDR(2, addr & 0xffff, 8), \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_NO_DATA) + #define SPINAND_PAGE_READ_FROM_CACHE_8D_8D_8D_OP(addr, ndummy, buf, len, freq) \ SPI_MEM_OP(SPI_MEM_DTR_OP_RPT_CMD(0x9d, 8), \ SPI_MEM_DTR_OP_ADDR(2, addr, 8), \ @@ -483,6 +489,7 @@ struct spinand_ecc_info { #define SPINAND_HAS_PROG_PLANE_SELECT_BIT BIT(2) #define SPINAND_HAS_READ_PLANE_SELECT_BIT BIT(3) #define SPINAND_NO_RAW_ACCESS BIT(4) +#define SPINAND_ODTR_PACKED_PAGE_READ BIT(5) /** * struct spinand_ondie_ecc_conf - private SPI-NAND on-die ECC engine structure diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 77c778d84d4c..a81b46af5118 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -146,6 +146,9 @@ struct xt_match { /* Called when user tries to insert an entry of this type. */ int (*checkentry)(const struct xt_mtchk_param *); + /* Called to validate hooks based on the match configuration. */ + int (*check_hooks)(const struct xt_mtchk_param *); + /* Called when entry of this type deleted. */ void (*destroy)(const struct xt_mtdtor_param *); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT @@ -187,6 +190,9 @@ struct xt_target { /* Should return 0 on success or an error code otherwise (-Exxxx). */ int (*checkentry)(const struct xt_tgchk_param *); + /* Called to validate hooks based on the target configuration. */ + int (*check_hooks)(const struct xt_tgchk_param *); + /* Called when entry of this type deleted. */ void (*destroy)(const struct xt_tgdtor_param *); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT @@ -279,8 +285,10 @@ bool xt_find_jump_offset(const unsigned int *offsets, int xt_check_proc_name(const char *name, unsigned int size); +int xt_check_hooks_match(struct xt_mtchk_param *par); int xt_check_match(struct xt_mtchk_param *, unsigned int size, u16 proto, bool inv_proto); +int xt_check_hooks_target(struct xt_tgchk_param *par); int xt_check_target(struct xt_tgchk_param *, unsigned int size, u16 proto, bool inv_proto); diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 2abba7552605..e3bc44225692 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -261,6 +261,35 @@ static inline void list_replace_rcu(struct list_head *old, old->prev = LIST_POISON2; } +static inline void __list_splice_rcu(struct list_head *list, + struct list_head *prev, + struct list_head *next) +{ + struct list_head *first = list->next; + struct list_head *last = list->prev; + + last->next = next; + first->prev = prev; + next->prev = last; + rcu_assign_pointer(list_next_rcu(prev), first); +} + +/** + * list_splice_rcu - splice a non-RCU list into an RCU-protected list, + * designed for stacks. + * @list: the non RCU-protected list to splice + * @head: the place in the existing RCU-protected list to splice + * + * The list pointed to by @head can be RCU-read traversed concurrently with + * this function. + */ +static inline void list_splice_rcu(struct list_head *list, + struct list_head *head) +{ + if (!list_empty(list)) + __list_splice_rcu(list, head, head->next); +} + /** * __list_splice_init_rcu - join an RCU-protected list into an existing list. * @list: the RCU-protected list to splice diff --git a/include/linux/rhashtable-types.h b/include/linux/rhashtable-types.h index 015c8298bebc..fc2f596a6df1 100644 --- a/include/linux/rhashtable-types.h +++ b/include/linux/rhashtable-types.h @@ -12,6 +12,7 @@ #include <linux/alloc_tag.h> #include <linux/atomic.h> #include <linux/compiler.h> +#include <linux/irq_work_types.h> #include <linux/mutex.h> #include <linux/workqueue_types.h> @@ -49,6 +50,7 @@ typedef int (*rht_obj_cmpfn_t)(struct rhashtable_compare_arg *arg, * @head_offset: Offset of rhash_head in struct to be hashed * @max_size: Maximum size while expanding * @min_size: Minimum size while shrinking + * @insecure_elasticity: Set to true to disable chain length checks * @automatic_shrinking: Enable automatic shrinking of tables * @hashfn: Hash function (default: jhash2 if !(key_len % 4), or jhash) * @obj_hashfn: Function to hash object @@ -61,6 +63,7 @@ struct rhashtable_params { u16 head_offset; unsigned int max_size; u16 min_size; + bool insecure_elasticity; bool automatic_shrinking; rht_hashfn_t hashfn; rht_obj_hashfn_t obj_hashfn; @@ -75,6 +78,7 @@ struct rhashtable_params { * @p: Configuration parameters * @rhlist: True if this is an rhltable * @run_work: Deferred worker to expand/shrink asynchronously + * @run_irq_work: Bounces the @run_work kick through hard IRQ context. * @mutex: Mutex to protect current/future table swapping * @lock: Spin lock to protect walker list * @nelems: Number of elements in table @@ -86,6 +90,7 @@ struct rhashtable { struct rhashtable_params p; bool rhlist; struct work_struct run_work; + struct irq_work run_irq_work; struct mutex mutex; spinlock_t lock; atomic_t nelems; diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 0480509a6339..ef5230cece36 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -20,6 +20,7 @@ #include <linux/err.h> #include <linux/errno.h> +#include <linux/irq_work.h> #include <linux/jhash.h> #include <linux/list_nulls.h> #include <linux/workqueue.h> @@ -821,14 +822,15 @@ slow_path: goto out; } - if (elasticity <= 0) + if (elasticity <= 0 && !params.insecure_elasticity) goto slow_path; data = ERR_PTR(-E2BIG); if (unlikely(rht_grow_above_max(ht, tbl))) goto out_unlock; - if (unlikely(rht_grow_above_100(ht, tbl))) + if (unlikely(rht_grow_above_100(ht, tbl)) && + !params.insecure_elasticity) goto slow_path; /* Inserting at head of list makes unlocking free. */ @@ -846,7 +848,7 @@ slow_path: rht_assign_unlock(tbl, bkt, obj, flags); if (rht_grow_above_75(ht, tbl)) - schedule_work(&ht->run_work); + irq_work_queue(&ht->run_irq_work); data = NULL; out: diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index 1a3af2ea2a79..adb9a4de068a 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -101,6 +101,7 @@ enum scx_ent_flags { SCX_TASK_DEQD_FOR_SLEEP = 1 << 3, /* last dequeue was for SLEEP */ SCX_TASK_SUB_INIT = 1 << 4, /* task being initialized for a sub sched */ SCX_TASK_IMMED = 1 << 5, /* task is on local DSQ with %SCX_ENQ_IMMED */ + SCX_TASK_OFF_TASKS = 1 << 6, /* removed from scx_tasks by sched_ext_dead() */ /* * Bits 8 and 9 are used to carry task state: diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index dc3975ff1b2e..cf0fd03dd7a2 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -21,6 +21,11 @@ enum hk_type { HK_TYPE_MAX, /* + * HK_TYPE_KTHREAD is now an alias of HK_TYPE_DOMAIN + */ + HK_TYPE_KTHREAD = HK_TYPE_DOMAIN, + + /* * The following housekeeping types are only set by the nohz_full * boot commandline option. So they can share the same value. */ @@ -29,7 +34,6 @@ enum hk_type { HK_TYPE_RCU = HK_TYPE_KERNEL_NOISE, HK_TYPE_MISC = HK_TYPE_KERNEL_NOISE, HK_TYPE_WQ = HK_TYPE_KERNEL_NOISE, - HK_TYPE_KTHREAD = HK_TYPE_KERNEL_NOISE }; #ifdef CONFIG_CPU_ISOLATION diff --git a/fs/smb/smbdirect/public.h b/include/linux/smbdirect.h index 50088155e7c3..97f5ba730fa7 100644 --- a/fs/smb/smbdirect/public.h +++ b/include/linux/smbdirect.h @@ -3,18 +3,56 @@ * Copyright (C) 2025, Stefan Metzmacher */ -#ifndef __FS_SMB_COMMON_SMBDIRECT_SMBDIRECT_PUBLIC_H__ -#define __FS_SMB_COMMON_SMBDIRECT_SMBDIRECT_PUBLIC_H__ +#ifndef __LINUX_SMBDIRECT_H__ +#define __LINUX_SMBDIRECT_H__ -struct smbdirect_buffer_descriptor_v1; -struct smbdirect_socket_parameters; +#include <linux/types.h> + +/* SMB-DIRECT buffer descriptor V1 structure [MS-SMBD] 2.2.3.1 */ +struct smbdirect_buffer_descriptor_v1 { + __le64 offset; + __le32 token; + __le32 length; +} __packed; + +/* + * Connection parameters mostly from [MS-SMBD] 3.1.1.1 + * + * These are setup and negotiated at the beginning of a + * connection and remain constant unless explicitly changed. + * + * Some values are important for the upper layer. + */ +struct smbdirect_socket_parameters { + __u64 flags; +#define SMBDIRECT_FLAG_PORT_RANGE_ONLY_IB ((__u64)0x1) +#define SMBDIRECT_FLAG_PORT_RANGE_ONLY_IW ((__u64)0x2) + __u32 resolve_addr_timeout_msec; + __u32 resolve_route_timeout_msec; + __u32 rdma_connect_timeout_msec; + __u32 negotiate_timeout_msec; + __u16 initiator_depth; /* limited to U8_MAX */ + __u16 responder_resources; /* limited to U8_MAX */ + __u16 recv_credit_max; + __u16 send_credit_target; + __u32 max_send_size; + __u32 max_fragmented_send_size; + __u32 max_recv_size; + __u32 max_fragmented_recv_size; + __u32 max_read_write_size; + __u32 max_frmr_depth; + __u32 keepalive_interval_msec; + __u32 keepalive_timeout_msec; +} __packed; + +#define SMBDIRECT_FLAG_PORT_RANGE_MASK ( \ + SMBDIRECT_FLAG_PORT_RANGE_ONLY_IB | \ + SMBDIRECT_FLAG_PORT_RANGE_ONLY_IW) struct smbdirect_socket; struct smbdirect_send_batch; struct smbdirect_mr_io; -#define __SMBDIRECT_EXPORT_SYMBOL__(__sym) EXPORT_SYMBOL_FOR_MODULES(__sym, "cifs,ksmbd") - #include <rdma/rw.h> u8 smbdirect_netdev_rdma_capable_node_type(struct net_device *netdev); @@ -145,4 +183,4 @@ void smbdirect_connection_legacy_debug_proc_show(struct smbdirect_socket *sc, unsigned int rdma_readwrite_threshold, struct seq_file *m); -#endif /* __FS_SMB_COMMON_SMBDIRECT_SMBDIRECT_PUBLIC_H__ */ +#endif /* __LINUX_SMBDIRECT_H__ */ diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 578e520b6ee6..763eea4d80d8 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -202,7 +202,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) #define TP_CONDITION(args...) args /* - * Individual subsystem my have a separate configuration to + * Individual subsystem may have a separate configuration to * enable their tracepoints. By default, this file will create * the tracepoints if CONFIG_TRACEPOINTS is defined. If a subsystem * wants to be able to disable its tracepoints from being created diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index ab6cb70ca1a5..6177624539b3 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -534,8 +534,10 @@ alloc_workqueue_noprof(const char *fmt, unsigned int flags, int max_active, ...) * Pointer to the allocated workqueue on success, %NULL on failure. */ __printf(2, 5) struct workqueue_struct * -devm_alloc_workqueue(struct device *dev, const char *fmt, unsigned int flags, - int max_active, ...); +devm_alloc_workqueue_noprof(struct device *dev, const char *fmt, + unsigned int flags, int max_active, ...); +#define devm_alloc_workqueue(...) \ + alloc_hooks(devm_alloc_workqueue_noprof(__VA_ARGS__)) #ifdef CONFIG_LOCKDEP /** diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index a7bffb908c1e..aa600fbf9a53 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -2495,7 +2495,7 @@ void mgmt_adv_monitor_device_lost(struct hci_dev *hdev, u16 handle, bdaddr_t *bdaddr, u8 addr_type); int hci_abort_conn(struct hci_conn *conn, u8 reason); -u8 hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, u16 latency, +void hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, u16 latency, u16 to_multiplier); void hci_le_start_enc(struct hci_conn *conn, __le16 ediv, __le64 rand, __u8 ltk[16], __u8 key_size); diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h index c92d4a976246..05572c19e14b 100644 --- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -243,7 +243,7 @@ typedef struct port { churn_state_t sm_churn_actor_state; churn_state_t sm_churn_partner_state; struct slave *slave; /* pointer to the bond slave that this port belongs to */ - struct aggregator *aggregator; /* pointer to an aggregator that this port related to */ + struct aggregator __rcu *aggregator; /* pointer to an aggregator that this port related to */ struct port *next_port_in_aggregator; /* Next port on the linked list of the parent aggregator */ u32 transaction_id; /* continuous number for identification of Marker PDU's; */ struct lacpdu lacpdu; /* the lacpdu that will be sent for this port */ diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h index e0ca3904ff8e..2f312d1f67d6 100644 --- a/include/net/dropreason-core.h +++ b/include/net/dropreason-core.h @@ -99,6 +99,7 @@ FN(FRAG_TOO_FAR) \ FN(TCP_MINTTL) \ FN(IPV6_BAD_EXTHDR) \ + FN(IPV6_TOO_MANY_EXTHDRS) \ FN(IPV6_NDISC_FRAG) \ FN(IPV6_NDISC_HOP_LIMIT) \ FN(IPV6_NDISC_BAD_CODE) \ @@ -494,6 +495,11 @@ enum skb_drop_reason { SKB_DROP_REASON_TCP_MINTTL, /** @SKB_DROP_REASON_IPV6_BAD_EXTHDR: Bad IPv6 extension header. */ SKB_DROP_REASON_IPV6_BAD_EXTHDR, + /** + * @SKB_DROP_REASON_IPV6_TOO_MANY_EXTHDRS: Number of IPv6 extension + * headers in the packet exceeds IP6_MAX_EXT_HDRS_CNT. + */ + SKB_DROP_REASON_IPV6_TOO_MANY_EXTHDRS, /** @SKB_DROP_REASON_IPV6_NDISC_FRAG: invalid frag (suppress_frag_ndisc). */ SKB_DROP_REASON_IPV6_NDISC_FRAG, /** @SKB_DROP_REASON_IPV6_NDISC_HOP_LIMIT: invalid hop limit. */ diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 72d325c81313..02762ce73a0c 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -491,6 +491,7 @@ struct ip_vs_est_kt_data { DECLARE_BITMAP(avail, IPVS_EST_NTICKS); /* tick has space for ests */ unsigned long est_timer; /* estimation timer (jiffies) */ struct ip_vs_stats *calc_stats; /* Used for calculation */ + int needed; /* task is needed */ int tick_len[IPVS_EST_NTICKS]; /* est count */ int id; /* ktid per netns */ int chain_max; /* max ests per tick chain */ @@ -1411,7 +1412,7 @@ static inline int sysctl_run_estimation(struct netns_ipvs *ipvs) return ipvs->sysctl_run_estimation; } -static inline const struct cpumask *sysctl_est_cpulist(struct netns_ipvs *ipvs) +static inline const struct cpumask *__sysctl_est_cpulist(struct netns_ipvs *ipvs) { if (ipvs->est_cpulist_valid) return ipvs->sysctl_est_cpulist; @@ -1529,7 +1530,7 @@ static inline int sysctl_run_estimation(struct netns_ipvs *ipvs) return 1; } -static inline const struct cpumask *sysctl_est_cpulist(struct netns_ipvs *ipvs) +static inline const struct cpumask *__sysctl_est_cpulist(struct netns_ipvs *ipvs) { return housekeeping_cpumask(HK_TYPE_KTHREAD); } @@ -1564,6 +1565,18 @@ static inline int sysctl_svc_lfactor(struct netns_ipvs *ipvs) return READ_ONCE(ipvs->sysctl_svc_lfactor); } +static inline bool sysctl_est_cpulist_empty(struct netns_ipvs *ipvs) +{ + guard(rcu)(); + return cpumask_empty(__sysctl_est_cpulist(ipvs)); +} + +static inline unsigned int sysctl_est_cpulist_weight(struct netns_ipvs *ipvs) +{ + guard(rcu)(); + return cpumask_weight(__sysctl_est_cpulist(ipvs)); +} + /* IPVS core functions * (from ip_vs_core.c) */ @@ -1884,18 +1897,26 @@ int ip_vs_start_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats); void ip_vs_stop_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats); void ip_vs_zero_estimator(struct ip_vs_stats *stats); void ip_vs_read_estimator(struct ip_vs_kstats *dst, struct ip_vs_stats *stats); -void ip_vs_est_reload_start(struct netns_ipvs *ipvs); +void ip_vs_est_reload_start(struct netns_ipvs *ipvs, bool restart); int ip_vs_est_kthread_start(struct netns_ipvs *ipvs, struct ip_vs_est_kt_data *kd); void ip_vs_est_kthread_stop(struct ip_vs_est_kt_data *kd); +static inline void ip_vs_stop_estimator_tot_stats(struct netns_ipvs *ipvs) +{ +#ifdef CONFIG_SYSCTL + ip_vs_stop_estimator(ipvs, &ipvs->tot_stats->s); + ipvs->tot_stats->s.est.ktid = -2; +#endif +} + static inline void ip_vs_est_stopped_recalc(struct netns_ipvs *ipvs) { #ifdef CONFIG_SYSCTL /* Stop tasks while cpulist is empty or if disabled with flag */ ipvs->est_stopped = !sysctl_run_estimation(ipvs) || (ipvs->est_cpulist_valid && - cpumask_empty(sysctl_est_cpulist(ipvs))); + sysctl_est_cpulist_empty(ipvs)); #endif } @@ -1911,7 +1932,7 @@ static inline bool ip_vs_est_stopped(struct netns_ipvs *ipvs) static inline int ip_vs_est_max_threads(struct netns_ipvs *ipvs) { unsigned int limit = IPVS_EST_CPU_KTHREADS * - cpumask_weight(sysctl_est_cpulist(ipvs)); + sysctl_est_cpulist_weight(ipvs); return max(1U, limit); } diff --git a/include/net/ipv6.h b/include/net/ipv6.h index d042afe7a245..1dec81faff28 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -90,6 +90,9 @@ struct ip_tunnel_info; #define IP6_DEFAULT_MAX_DST_OPTS_LEN INT_MAX /* No limit */ #define IP6_DEFAULT_MAX_HBH_OPTS_LEN INT_MAX /* No limit */ +/* Hard limit on traversed IPv6 extension headers */ +#define IP6_MAX_EXT_HDRS_CNT 12 + /* * Addr type * diff --git a/include/net/mana/shm_channel.h b/include/net/mana/shm_channel.h index 5199b41497ff..dbabcfb95daf 100644 --- a/include/net/mana/shm_channel.h +++ b/include/net/mana/shm_channel.h @@ -4,6 +4,12 @@ #ifndef _SHM_CHANNEL_H #define _SHM_CHANNEL_H +#define SMC_APERTURE_BITS 256 +#define SMC_BASIC_UNIT (sizeof(u32)) +#define SMC_APERTURE_DWORDS (SMC_APERTURE_BITS / (SMC_BASIC_UNIT * 8)) +#define SMC_LAST_DWORD (SMC_APERTURE_DWORDS - 1) +#define SMC_APERTURE_SIZE (SMC_APERTURE_BITS / 8) + struct shm_channel { struct device *dev; void __iomem *base; diff --git a/include/net/netfilter/nf_dup_netdev.h b/include/net/netfilter/nf_dup_netdev.h index b175d271aec9..609bcf422a9b 100644 --- a/include/net/netfilter/nf_dup_netdev.h +++ b/include/net/netfilter/nf_dup_netdev.h @@ -3,10 +3,23 @@ #define _NF_DUP_NETDEV_H_ #include <net/netfilter/nf_tables.h> +#include <linux/netdevice.h> +#include <linux/sched.h> void nf_dup_netdev_egress(const struct nft_pktinfo *pkt, int oif); void nf_fwd_netdev_egress(const struct nft_pktinfo *pkt, int oif); +#define NF_RECURSION_LIMIT 2 + +static inline u8 *nf_get_nf_dup_skb_recursion(void) +{ +#ifndef CONFIG_PREEMPT_RT + return this_cpu_ptr(&softnet_data.xmit.nf_dup_skb_recursion); +#else + return ¤t->net_xmit.nf_dup_skb_recursion; +#endif +} + struct nft_offload_ctx; struct nft_flow_rule; diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index b09c11c048d5..7b23b245a5a8 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -148,9 +148,10 @@ struct flow_offload_tuple { /* All members above are keys for lookups, see flow_offload_hash(). */ struct { } __hash; - u8 dir:2, + u16 dir:2, xmit_type:3, encap_num:2, + needs_gso_segment:1, tun_num:2, in_vlan_ingress:2; u16 mtu; @@ -232,6 +233,7 @@ struct nf_flow_route { u32 hw_ifindex; u8 h_source[ETH_ALEN]; u8 h_dest[ETH_ALEN]; + u8 needs_gso_segment:1; } out; enum flow_offload_xmit_type xmit_type; } tuple[FLOW_OFFLOAD_DIR_MAX]; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 2c0173d9309c..cff7b773e972 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1204,12 +1204,15 @@ struct nft_stats { struct u64_stats_sync syncp; }; +#define NFT_HOOK_REMOVE (1 << 0) + struct nft_hook { struct list_head list; struct list_head ops_list; struct rcu_head rcu; char ifname[IFNAMSIZ]; u8 ifnamelen; + u8 flags; }; struct nf_hook_ops *nft_hook_find_ops(const struct nft_hook *hook, @@ -1665,6 +1668,16 @@ struct nft_trans { }; /** + * struct nft_trans_hook - nf_tables hook update in transaction + * @list: used internally + * @hook: struct nft_hook with the device hook + */ +struct nft_trans_hook { + struct list_head list; + struct nft_hook *hook; +}; + +/** * struct nft_trans_binding - nf_tables object with binding support in transaction * @nft_trans: base structure, MUST be first member * @binding_list: list of objects with possible bindings diff --git a/include/net/netmem.h b/include/net/netmem.h index 507b74c9f52d..78fe51e5756b 100644 --- a/include/net/netmem.h +++ b/include/net/netmem.h @@ -127,6 +127,21 @@ static inline unsigned int net_iov_idx(const struct net_iov *niov) return niov - net_iov_owner(niov)->niovs; } +/* Initialize a niov: stamp the owning area, the memory provider type, + * and the page_type "no type" sentinel expected by the page-type API + * (see PAGE_TYPE_OPS in <linux/page-flags.h>) so that + * page_pool_set_pp_info() can later call __SetPageNetpp() on a niov + * cast to struct page. + */ +static inline void net_iov_init(struct net_iov *niov, + struct net_iov_area *owner, + enum net_iov_type type) +{ + niov->owner = owner; + niov->type = type; + niov->page_type = UINT_MAX; +} + /* netmem */ /** diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 80ccd4dda8e0..6e27c56514df 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -275,7 +275,7 @@ struct netns_ipv4 { #ifdef CONFIG_IP_MROUTE #ifndef CONFIG_IP_MROUTE_MULTIPLE_TABLES - struct mr_table *mrt; + struct mr_table __rcu *mrt; #else struct list_head mr_tables; struct fib_rules_ops *mr_rules_ops; diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 17ac1b785440..909fb7aea638 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -905,7 +905,8 @@ struct io_uring_buf_reg { __u32 ring_entries; __u16 bgid; __u16 flags; - __u64 resv[3]; + __u32 min_left; + __u32 resv[5]; }; /* argument for IORING_REGISTER_PBUF_STATUS */ diff --git a/include/ufs/unipro.h b/include/ufs/unipro.h index f849a2a101ae..9c168703b104 100644 --- a/include/ufs/unipro.h +++ b/include/ufs/unipro.h @@ -333,6 +333,11 @@ enum ufs_eom_eye_mask { #define DME_LocalTC0ReplayTimeOutVal 0xD042 #define DME_LocalAFC0ReqTimeOutVal 0xD043 +enum ufs_op_mode { + LS_MODE = 1, + HS_MODE = 2, +}; + /* PA power modes */ enum ufs_pa_pwr_mode { FAST_MODE = 1, diff --git a/include/video/imx-ipu-image-convert.h b/include/video/imx-ipu-image-convert.h index 003b3927ede5..6b77968a6a15 100644 --- a/include/video/imx-ipu-image-convert.h +++ b/include/video/imx-ipu-image-convert.h @@ -27,12 +27,13 @@ struct ipu_image_convert_run { int status; + /* private: */ /* internal to image converter, callers don't touch */ struct list_head list; }; /** - * ipu_image_convert_cb_t - conversion callback function prototype + * typedef ipu_image_convert_cb_t - conversion callback function prototype * * @run: the completed conversion run pointer * @ctx: a private context pointer for the callback @@ -60,7 +61,7 @@ void ipu_image_convert_adjust(struct ipu_image *in, struct ipu_image *out, * @out: output image format * @rot_mode: rotation mode * - * Returns 0 if the formats and rotation mode meet IPU restrictions, + * Returns: 0 if the formats and rotation mode meet IPU restrictions, * -EINVAL otherwise. */ int ipu_image_convert_verify(struct ipu_image *in, struct ipu_image *out, @@ -77,11 +78,11 @@ int ipu_image_convert_verify(struct ipu_image *in, struct ipu_image *out, * @complete: run completion callback * @complete_context: a context pointer for the completion callback * - * Returns an opaque conversion context pointer on success, error pointer + * In V4L2, drivers should call ipu_image_convert_prepare() at streamon. + * + * Returns: an opaque conversion context pointer on success, error pointer * on failure. The input/output formats and rotation mode must already meet * IPU retrictions. - * - * In V4L2, drivers should call ipu_image_convert_prepare() at streamon. */ struct ipu_image_convert_ctx * ipu_image_convert_prepare(struct ipu_soc *ipu, enum ipu_ic_task ic_task, @@ -122,6 +123,8 @@ void ipu_image_convert_unprepare(struct ipu_image_convert_ctx *ctx); * In V4L2, drivers should call ipu_image_convert_queue() while * streaming to queue the conversion of a received input buffer. * For example mem2mem devices this would be called in .device_run. + * + * Returns: 0 on success or -errno on error. */ int ipu_image_convert_queue(struct ipu_image_convert_run *run); @@ -155,6 +158,9 @@ void ipu_image_convert_abort(struct ipu_image_convert_ctx *ctx); * On successful return the caller can queue more run requests if needed, using * the prepared context in run->ctx. The caller is responsible for unpreparing * the context when no more conversion requests are needed. + * + * Returns: pointer to the created &struct ipu_image_convert_run that has + * been queued on success; an ERR_PTR(errno) on error. */ struct ipu_image_convert_run * ipu_image_convert(struct ipu_soc *ipu, enum ipu_ic_task ic_task, diff --git a/include/video/udlfb.h b/include/video/udlfb.h index 58fb5732831a..ab34790d57ec 100644 --- a/include/video/udlfb.h +++ b/include/video/udlfb.h @@ -56,6 +56,7 @@ struct dlfb_data { spinlock_t damage_lock; struct work_struct damage_work; struct fb_ops ops; + atomic_t mmap_count; /* blit-only rendering path metrics, exposed through sysfs */ atomic_t bytes_rendered; /* raw pixel-bytes driver asked to render */ atomic_t bytes_identical; /* saved effort with backbuffer comparison */ diff --git a/io_uring/eventfd.c b/io_uring/eventfd.c index 3da028500f76..d656cc2a0b9b 100644 --- a/io_uring/eventfd.c +++ b/io_uring/eventfd.c @@ -43,6 +43,7 @@ static void io_eventfd_do_signal(struct rcu_head *rcu) { struct io_ev_fd *ev_fd = container_of(rcu, struct io_ev_fd, rcu); + atomic_andnot(BIT(IO_EVENTFD_OP_SIGNAL_BIT), &ev_fd->ops); eventfd_signal_mask(ev_fd->cq_ev_fd, EPOLL_URING_WAKE); io_eventfd_put(ev_fd); } diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c index 8da2ff798170..63061aa1cab9 100644 --- a/io_uring/kbuf.c +++ b/io_uring/kbuf.c @@ -47,7 +47,7 @@ static bool io_kbuf_inc_commit(struct io_buffer_list *bl, int len) this_len = min_t(u32, len, buf_len); buf_len -= this_len; /* Stop looping for invalid buffer length of 0 */ - if (buf_len || !this_len) { + if (buf_len > bl->min_left_sub_one || !this_len) { WRITE_ONCE(buf->addr, READ_ONCE(buf->addr) + this_len); WRITE_ONCE(buf->len, buf_len); return false; @@ -637,6 +637,10 @@ int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg) if (reg.ring_entries >= 65536) return -EINVAL; + /* minimum left byte count is a property of incremental buffers */ + if (!(reg.flags & IOU_PBUF_RING_INC) && reg.min_left) + return -EINVAL; + bl = io_buffer_get_list(ctx, reg.bgid); if (bl) { /* if mapped buffer ring OR classic exists, don't allow */ @@ -680,10 +684,11 @@ int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg) } #endif - bl->nr_entries = reg.ring_entries; bl->mask = reg.ring_entries - 1; bl->flags |= IOBL_BUF_RING; bl->buf_ring = br; + if (reg.min_left) + bl->min_left_sub_one = reg.min_left - 1; if (reg.flags & IOU_PBUF_RING_INC) bl->flags |= IOBL_INC; ret = io_buffer_add_list(ctx, bl, reg.bgid); diff --git a/io_uring/kbuf.h b/io_uring/kbuf.h index bf15e26520d3..401773e1ef80 100644 --- a/io_uring/kbuf.h +++ b/io_uring/kbuf.h @@ -27,12 +27,18 @@ struct io_buffer_list { __u16 bgid; /* below is for ring provided buffers */ - __u16 nr_entries; __u16 head; __u16 mask; __u16 flags; + /* + * minimum required amount to be left to reuse an incrementally + * consumed buffer. If less than this is left at consumption time, + * buffer is done and head is incremented to the next buffer. + */ + __u32 min_left_sub_one; + struct io_mapped_region region; }; diff --git a/io_uring/napi.c b/io_uring/napi.c index 4a10de03e426..bfc771445912 100644 --- a/io_uring/napi.c +++ b/io_uring/napi.c @@ -38,7 +38,8 @@ static inline ktime_t net_to_ktime(unsigned long t) return ns_to_ktime(t << 10); } -int __io_napi_add_id(struct io_ring_ctx *ctx, unsigned int napi_id) +int __io_napi_add_id(struct io_ring_ctx *ctx, unsigned int napi_id, + unsigned int mode) { struct hlist_head *hash_list; struct io_napi_entry *e; @@ -69,6 +70,11 @@ int __io_napi_add_id(struct io_ring_ctx *ctx, unsigned int napi_id) * kfree() */ spin_lock(&ctx->napi_lock); + if (unlikely(READ_ONCE(ctx->napi_track_mode) != mode)) { + spin_unlock(&ctx->napi_lock); + kfree(e); + return -EINVAL; + } if (unlikely(io_napi_hash_find(hash_list, napi_id))) { spin_unlock(&ctx->napi_lock); kfree(e); @@ -196,9 +202,14 @@ __io_napi_do_busy_loop(struct io_ring_ctx *ctx, bool (*loop_end)(void *, unsigned long), void *loop_end_arg) { - if (READ_ONCE(ctx->napi_track_mode) == IO_URING_NAPI_TRACKING_STATIC) + switch (READ_ONCE(ctx->napi_track_mode)) { + case IO_URING_NAPI_TRACKING_STATIC: return static_tracking_do_busy_loop(ctx, loop_end, loop_end_arg); - return dynamic_tracking_do_busy_loop(ctx, loop_end, loop_end_arg); + case IO_URING_NAPI_TRACKING_DYNAMIC: + return dynamic_tracking_do_busy_loop(ctx, loop_end, loop_end_arg); + default: + return false; + } } static void io_napi_blocking_busy_loop(struct io_ring_ctx *ctx, @@ -273,11 +284,13 @@ static int io_napi_register_napi(struct io_ring_ctx *ctx, default: return -EINVAL; } - /* clean the napi list for new settings */ + WRITE_ONCE(ctx->napi_track_mode, IO_URING_NAPI_TRACKING_INACTIVE); io_napi_free(ctx); - WRITE_ONCE(ctx->napi_track_mode, napi->op_param); + /* cap NAPI at 10 msec of spin time */ + napi->busy_poll_to = min(10000, napi->busy_poll_to); WRITE_ONCE(ctx->napi_busy_poll_dt, napi->busy_poll_to * NSEC_PER_USEC); WRITE_ONCE(ctx->napi_prefer_busy_poll, !!napi->prefer_busy_poll); + WRITE_ONCE(ctx->napi_track_mode, napi->op_param); return 0; } @@ -313,7 +326,8 @@ int io_register_napi(struct io_ring_ctx *ctx, void __user *arg) case IO_URING_NAPI_STATIC_ADD_ID: if (curr.op_param != IO_URING_NAPI_TRACKING_STATIC) return -EINVAL; - return __io_napi_add_id(ctx, napi.op_param); + return __io_napi_add_id(ctx, napi.op_param, + IO_URING_NAPI_TRACKING_STATIC); case IO_URING_NAPI_STATIC_DEL_ID: if (curr.op_param != IO_URING_NAPI_TRACKING_STATIC) return -EINVAL; @@ -341,9 +355,10 @@ int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg) if (arg && copy_to_user(arg, &curr, sizeof(curr))) return -EFAULT; + WRITE_ONCE(ctx->napi_track_mode, IO_URING_NAPI_TRACKING_INACTIVE); WRITE_ONCE(ctx->napi_busy_poll_dt, 0); WRITE_ONCE(ctx->napi_prefer_busy_poll, false); - WRITE_ONCE(ctx->napi_track_mode, IO_URING_NAPI_TRACKING_INACTIVE); + io_napi_free(ctx); return 0; } diff --git a/io_uring/napi.h b/io_uring/napi.h index fa742f42e09b..e0aecccc5065 100644 --- a/io_uring/napi.h +++ b/io_uring/napi.h @@ -15,7 +15,8 @@ void io_napi_free(struct io_ring_ctx *ctx); int io_register_napi(struct io_ring_ctx *ctx, void __user *arg); int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg); -int __io_napi_add_id(struct io_ring_ctx *ctx, unsigned int napi_id); +int __io_napi_add_id(struct io_ring_ctx *ctx, unsigned int napi_id, + unsigned int mode); void __io_napi_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq); int io_napi_sqpoll_busy_poll(struct io_ring_ctx *ctx); @@ -43,13 +44,14 @@ static inline void io_napi_add(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; struct socket *sock; + unsigned int mode = IO_URING_NAPI_TRACKING_DYNAMIC; - if (READ_ONCE(ctx->napi_track_mode) != IO_URING_NAPI_TRACKING_DYNAMIC) + if (READ_ONCE(ctx->napi_track_mode) != mode) return; sock = sock_from_file(req->file); if (sock && sock->sk) - __io_napi_add_id(ctx, READ_ONCE(sock->sk->sk_napi_id)); + __io_napi_add_id(ctx, READ_ONCE(sock->sk->sk_napi_id), mode); } #else diff --git a/io_uring/timeout.c b/io_uring/timeout.c index 4cfdfc519770..e2595cae2b07 100644 --- a/io_uring/timeout.c +++ b/io_uring/timeout.c @@ -3,6 +3,7 @@ #include <linux/errno.h> #include <linux/file.h> #include <linux/io_uring.h> +#include <linux/time_namespace.h> #include <trace/events/io_uring.h> @@ -35,6 +36,22 @@ struct io_timeout_rem { bool ltimeout; }; +static clockid_t io_flags_to_clock(unsigned flags) +{ + switch (flags & IORING_TIMEOUT_CLOCK_MASK) { + case IORING_TIMEOUT_BOOTTIME: + return CLOCK_BOOTTIME; + case IORING_TIMEOUT_REALTIME: + return CLOCK_REALTIME; + default: + /* can't happen, vetted at prep time */ + WARN_ON_ONCE(1); + fallthrough; + case 0: + return CLOCK_MONOTONIC; + } +} + static int io_parse_user_time(ktime_t *time, u64 arg, unsigned flags) { struct timespec64 ts; @@ -43,7 +60,7 @@ static int io_parse_user_time(ktime_t *time, u64 arg, unsigned flags) *time = ns_to_ktime(arg); if (*time < 0) return -EINVAL; - return 0; + goto out; } if (get_timespec64(&ts, u64_to_user_ptr(arg))) @@ -51,6 +68,9 @@ static int io_parse_user_time(ktime_t *time, u64 arg, unsigned flags) if (ts.tv_sec < 0 || ts.tv_nsec < 0) return -EINVAL; *time = timespec64_to_ktime(ts); +out: + if (flags & IORING_TIMEOUT_ABS) + *time = timens_ktime_to_host(io_flags_to_clock(flags), *time); return 0; } @@ -399,18 +419,7 @@ static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer) static clockid_t io_timeout_get_clock(struct io_timeout_data *data) { - switch (data->flags & IORING_TIMEOUT_CLOCK_MASK) { - case IORING_TIMEOUT_BOOTTIME: - return CLOCK_BOOTTIME; - case IORING_TIMEOUT_REALTIME: - return CLOCK_REALTIME; - default: - /* can't happen, vetted at prep time */ - WARN_ON_ONCE(1); - fallthrough; - case 0: - return CLOCK_MONOTONIC; - } + return io_flags_to_clock(data->flags); } static int io_linked_timeout_update(struct io_ring_ctx *ctx, __u64 user_data, diff --git a/io_uring/tw.c b/io_uring/tw.c index fdff81eebc95..023d5e6bc491 100644 --- a/io_uring/tw.c +++ b/io_uring/tw.c @@ -273,8 +273,18 @@ void io_req_task_work_add_remote(struct io_kiocb *req, unsigned flags) void __cold io_move_task_work_from_local(struct io_ring_ctx *ctx) { - struct llist_node *node = llist_del_all(&ctx->work_llist); + struct llist_node *node; + /* + * Running the work items may utilize ->retry_llist as a means + * for capping the number of task_work entries run at the same + * time. But that list can potentially race with moving the work + * from here, if the task is exiting. As any normal task_work + * running holds ->uring_lock already, just guard this slow path + * with ->uring_lock to avoid racing on ->retry_llist. + */ + guard(mutex)(&ctx->uring_lock); + node = llist_del_all(&ctx->work_llist); __io_fallback_tw(node, false); node = llist_del_all(&ctx->retry_llist); __io_fallback_tw(node, false); diff --git a/io_uring/wait.c b/io_uring/wait.c index 91df86ce0d18..ec01e78a216d 100644 --- a/io_uring/wait.c +++ b/io_uring/wait.c @@ -5,6 +5,7 @@ #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/io_uring.h> +#include <linux/time_namespace.h> #include <trace/events/io_uring.h> @@ -229,7 +230,10 @@ int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, u32 flags, if (ext_arg->ts_set) { iowq.timeout = timespec64_to_ktime(ext_arg->ts); - if (!(flags & IORING_ENTER_ABS_TIMER)) + if (flags & IORING_ENTER_ABS_TIMER) + iowq.timeout = timens_ktime_to_host(ctx->clockid, + iowq.timeout); + else iowq.timeout = ktime_add(iowq.timeout, start_time); } diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c index 7b93c87b8371..19837e0b5e91 100644 --- a/io_uring/zcrx.c +++ b/io_uring/zcrx.c @@ -495,10 +495,9 @@ static int io_zcrx_create_area(struct io_zcrx_ifq *ifq, for (i = 0; i < nr_iovs; i++) { struct net_iov *niov = &area->nia.niovs[i]; - niov->owner = &area->nia; + net_iov_init(niov, &area->nia, NET_IOV_IOURING); area->freelist[i] = i; atomic_set(&area->user_refs[i], 0); - niov->type = NET_IOV_IOURING; } if (ifq->dev) { diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 43adc96c7f1a..6152add0c5eb 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -264,10 +264,12 @@ static void cgroup_finalize_control(struct cgroup *cgrp, int ret); static void css_task_iter_skip(struct css_task_iter *it, struct task_struct *task); static int cgroup_destroy_locked(struct cgroup *cgrp); +static void cgroup_finish_destroy(struct cgroup *cgrp); +static void kill_css_sync(struct cgroup_subsys_state *css); +static void kill_css_finish(struct cgroup_subsys_state *css); static struct cgroup_subsys_state *css_create(struct cgroup *cgrp, struct cgroup_subsys *ss); static void css_release(struct percpu_ref *ref); -static void kill_css(struct cgroup_subsys_state *css); static int cgroup_addrm_files(struct cgroup_subsys_state *css, struct cgroup *cgrp, struct cftype cfts[], bool is_add); @@ -797,6 +799,16 @@ static void cgroup_update_populated(struct cgroup *cgrp, bool populated) if (was_populated == cgroup_is_populated(cgrp)) break; + /* + * Subtree just emptied below an offlined cgrp. Fire deferred + * destroy. The transition is one-shot. + */ + if (was_populated && !css_is_online(&cgrp->self)) { + cgroup_get(cgrp); + WARN_ON_ONCE(!queue_work(cgroup_offline_wq, + &cgrp->finish_destroy_work)); + } + cgroup1_check_for_release(cgrp); TRACE_CGROUP_PATH(notify_populated, cgrp, cgroup_is_populated(cgrp)); @@ -2039,6 +2051,16 @@ static int cgroup_reconfigure(struct fs_context *fc) return 0; } +static void cgroup_finish_destroy_work_fn(struct work_struct *work) +{ + struct cgroup *cgrp = container_of(work, struct cgroup, finish_destroy_work); + + cgroup_lock(); + cgroup_finish_destroy(cgrp); + cgroup_unlock(); + cgroup_put(cgrp); +} + static void init_cgroup_housekeeping(struct cgroup *cgrp) { struct cgroup_subsys *ss; @@ -2065,7 +2087,7 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp) #endif init_waitqueue_head(&cgrp->offline_waitq); - init_waitqueue_head(&cgrp->dying_populated_waitq); + INIT_WORK(&cgrp->finish_destroy_work, cgroup_finish_destroy_work_fn); INIT_WORK(&cgrp->release_agent_work, cgroup1_release_agent); } @@ -3375,7 +3397,8 @@ static void cgroup_apply_control_disable(struct cgroup *cgrp) if (css->parent && !(cgroup_ss_mask(dsct) & (1 << ss->id))) { - kill_css(css); + kill_css_sync(css); + kill_css_finish(css); } else if (!css_visible(css)) { css_clear_dir(css); if (ss->css_reset) @@ -3934,33 +3957,41 @@ static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v) static ssize_t pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, enum psi_res res) { - struct cgroup_file_ctx *ctx = of->priv; + struct cgroup_file_ctx *ctx; struct psi_trigger *new; struct cgroup *cgrp; struct psi_group *psi; + ssize_t ret = 0; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENODEV; - cgroup_get(cgrp); - cgroup_kn_unlock(of->kn); + ctx = of->priv; + if (!ctx) { + ret = -ENODEV; + goto out_unlock; + } /* Allow only one trigger per file descriptor */ if (ctx->psi.trigger) { - cgroup_put(cgrp); - return -EBUSY; + ret = -EBUSY; + goto out_unlock; } psi = cgroup_psi(cgrp); new = psi_trigger_create(psi, buf, res, of->file, of); if (IS_ERR(new)) { - cgroup_put(cgrp); - return PTR_ERR(new); + ret = PTR_ERR(new); + goto out_unlock; } smp_store_release(&ctx->psi.trigger, new); - cgroup_put(cgrp); + +out_unlock: + cgroup_kn_unlock(of->kn); + if (ret) + return ret; return nbytes; } @@ -5059,10 +5090,12 @@ repeat: task = list_entry(it->task_pos, struct task_struct, cg_list); /* - * Hide tasks that are exiting but not yet removed. Keep zombie - * leaders with live threads visible. + * Hide tasks that are exiting but not yet removed by default. Keep + * zombie leaders with live threads visible. Usages that need to walk + * every existing task can opt out via CSS_TASK_ITER_WITH_DEAD. */ - if ((task->flags & PF_EXITING) && !atomic_read(&task->signal->live)) + if (!(it->flags & CSS_TASK_ITER_WITH_DEAD) && + (task->flags & PF_EXITING) && !atomic_read(&task->signal->live)) goto repeat; if (it->flags & CSS_TASK_ITER_PROCS) { @@ -5506,7 +5539,7 @@ static struct cftype cgroup_psi_files[] = { * css destruction is four-stage process. * * 1. Destruction starts. Killing of the percpu_ref is initiated. - * Implemented in kill_css(). + * Implemented in kill_css_finish(). * * 2. When the percpu_ref is confirmed to be visible as killed on all CPUs * and thus css_tryget_online() is guaranteed to fail, the css can be @@ -5716,16 +5749,6 @@ static void offline_css(struct cgroup_subsys_state *css) RCU_INIT_POINTER(css->cgroup->subsys[ss->id], NULL); wake_up_all(&css->cgroup->offline_waitq); - - css->cgroup->nr_dying_subsys[ss->id]++; - /* - * Parent css and cgroup cannot be freed until after the freeing - * of child css, see css_free_rwork_fn(). - */ - while ((css = css->parent)) { - css->nr_descendants--; - css->cgroup->nr_dying_subsys[ss->id]++; - } } /** @@ -5995,7 +6018,7 @@ out_unlock: /* * This is called when the refcnt of a css is confirmed to be killed. * css_tryget_online() is now guaranteed to fail. Tell the subsystem to - * initiate destruction and put the css ref from kill_css(). + * initiate destruction and put the css ref from kill_css_finish(). */ static void css_killed_work_fn(struct work_struct *work) { @@ -6028,16 +6051,15 @@ static void css_killed_ref_fn(struct percpu_ref *ref) } /** - * kill_css - destroy a css - * @css: css to destroy + * kill_css_sync - synchronous half of css teardown + * @css: css being killed * - * This function initiates destruction of @css by removing cgroup interface - * files and putting its base reference. ->css_offline() will be invoked - * asynchronously once css_tryget_online() is guaranteed to fail and when - * the reference count reaches zero, @css will be released. + * See cgroup_destroy_locked(). */ -static void kill_css(struct cgroup_subsys_state *css) +static void kill_css_sync(struct cgroup_subsys_state *css) { + struct cgroup_subsys *ss = css->ss; + lockdep_assert_held(&cgroup_mutex); if (css->flags & CSS_DYING) @@ -6057,64 +6079,100 @@ static void kill_css(struct cgroup_subsys_state *css) */ css_clear_dir(css); + css->cgroup->nr_dying_subsys[ss->id]++; + /* + * Parent css and cgroup cannot be freed until after the freeing + * of child css, see css_free_rwork_fn(). + */ + while ((css = css->parent)) { + css->nr_descendants--; + css->cgroup->nr_dying_subsys[ss->id]++; + } +} + +/** + * kill_css_finish - deferred half of css teardown + * @css: css being killed + * + * See cgroup_destroy_locked(). + */ +static void kill_css_finish(struct cgroup_subsys_state *css) +{ + lockdep_assert_held(&cgroup_mutex); + + /* + * Skip on re-entry: cgroup_apply_control_disable() may have killed @css + * earlier. cgroup_destroy_locked() can still walk it because + * offline_css() (which NULLs cgrp->subsys[ssid]) runs async. + */ + if (percpu_ref_is_dying(&css->refcnt)) + return; + /* - * Killing would put the base ref, but we need to keep it alive - * until after ->css_offline(). + * Killing would put the base ref, but we need to keep it alive until + * after ->css_offline(). */ css_get(css); /* - * cgroup core guarantees that, by the time ->css_offline() is - * invoked, no new css reference will be given out via - * css_tryget_online(). We can't simply call percpu_ref_kill() and - * proceed to offlining css's because percpu_ref_kill() doesn't - * guarantee that the ref is seen as killed on all CPUs on return. + * cgroup core guarantees that, by the time ->css_offline() is invoked, + * no new css reference will be given out via css_tryget_online(). We + * can't simply call percpu_ref_kill() and proceed to offlining css's + * because percpu_ref_kill() doesn't guarantee that the ref is seen as + * killed on all CPUs on return. * - * Use percpu_ref_kill_and_confirm() to get notifications as each - * css is confirmed to be seen as killed on all CPUs. + * Use percpu_ref_kill_and_confirm() to get notifications as each css is + * confirmed to be seen as killed on all CPUs. */ percpu_ref_kill_and_confirm(&css->refcnt, css_killed_ref_fn); } /** - * cgroup_destroy_locked - the first stage of cgroup destruction + * cgroup_destroy_locked - destroy @cgrp (called on rmdir) * @cgrp: cgroup to be destroyed * - * css's make use of percpu refcnts whose killing latency shouldn't be - * exposed to userland and are RCU protected. Also, cgroup core needs to - * guarantee that css_tryget_online() won't succeed by the time - * ->css_offline() is invoked. To satisfy all the requirements, - * destruction is implemented in the following two steps. - * - * s1. Verify @cgrp can be destroyed and mark it dying. Remove all - * userland visible parts and start killing the percpu refcnts of - * css's. Set up so that the next stage will be kicked off once all - * the percpu refcnts are confirmed to be killed. - * - * s2. Invoke ->css_offline(), mark the cgroup dead and proceed with the - * rest of destruction. Once all cgroup references are gone, the - * cgroup is RCU-freed. - * - * This function implements s1. After this step, @cgrp is gone as far as - * the userland is concerned and a new cgroup with the same name may be - * created. As cgroup doesn't care about the names internally, this - * doesn't cause any problem. + * Tear down @cgrp on behalf of rmdir. Constraints: + * + * - Userspace: rmdir must succeed when cgroup.procs and friends are empty. + * + * - Kernel: subsystem ->css_offline() must not run while any task in @cgrp's + * subtree is still doing kernel work. A task hidden from cgroup.procs (past + * exit_signals() with signal->live cleared) can still schedule, allocate, and + * consume resources until its final context switch. Dying descendants in the + * subtree can host such tasks too. + * + * - Kernel: css_tryget_online() must fail by the time ->css_offline() runs. + * + * The destruction runs in three parts: + * + * - This function: synchronous user-visible state teardown plus kill_css_sync() + * on each subsystem css. + * + * - cgroup_finish_destroy(): kicks the percpu_ref kill via kill_css_finish() on + * each subsystem css. Fires once @cgrp's subtree is fully drained, either + * inline here or from cgroup_update_populated(). + * + * - The percpu_ref kill chain: css_killed_ref_fn -> css_killed_work_fn -> + * ->css_offline() -> release/free. + * + * Return 0 on success, -EBUSY if a userspace-visible task or an online child + * remains. */ static int cgroup_destroy_locked(struct cgroup *cgrp) - __releases(&cgroup_mutex) __acquires(&cgroup_mutex) { struct cgroup *tcgrp, *parent = cgroup_parent(cgrp); struct cgroup_subsys_state *css; struct cgrp_cset_link *link; + struct css_task_iter it; + struct task_struct *task; int ssid, ret; lockdep_assert_held(&cgroup_mutex); - /* - * Only migration can raise populated from zero and we're already - * holding cgroup_mutex. - */ - if (cgroup_is_populated(cgrp)) + css_task_iter_start(&cgrp->self, 0, &it); + task = css_task_iter_next(&it); + css_task_iter_end(&it); + if (task) return -EBUSY; /* @@ -6138,9 +6196,8 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) link->cset->dead = true; spin_unlock_irq(&css_set_lock); - /* initiate massacre of all css's */ for_each_css(css, ssid, cgrp) - kill_css(css); + kill_css_sync(css); /* clear and remove @cgrp dir, @cgrp has an extra ref on its kn */ css_clear_dir(&cgrp->self); @@ -6171,79 +6228,27 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) /* put the base reference */ percpu_ref_kill(&cgrp->self.refcnt); + if (!cgroup_is_populated(cgrp)) + cgroup_finish_destroy(cgrp); + return 0; }; /** - * cgroup_drain_dying - wait for dying tasks to leave before rmdir - * @cgrp: the cgroup being removed - * - * cgroup.procs and cgroup.threads use css_task_iter which filters out - * PF_EXITING tasks so that userspace doesn't see tasks that have already been - * reaped via waitpid(). However, cgroup_has_tasks() - which tests whether the - * cgroup has non-empty css_sets - is only updated when dying tasks pass through - * cgroup_task_dead() in finish_task_switch(). This creates a window where - * cgroup.procs reads empty but cgroup_has_tasks() is still true, making rmdir - * fail with -EBUSY from cgroup_destroy_locked() even though userspace sees no - * tasks. - * - * This function aligns cgroup_has_tasks() with what userspace can observe. If - * cgroup_has_tasks() but the task iterator sees nothing (all remaining tasks are - * PF_EXITING), we wait for cgroup_task_dead() to finish processing them. As the - * window between PF_EXITING and cgroup_task_dead() is short, the wait is brief. - * - * This function only concerns itself with this cgroup's own dying tasks. - * Whether the cgroup has children is cgroup_destroy_locked()'s problem. - * - * Each cgroup_task_dead() kicks the waitqueue via cset->cgrp_links, and we - * retry the full check from scratch. + * cgroup_finish_destroy - deferred half of @cgrp destruction + * @cgrp: cgroup whose subtree just became empty * - * Must be called with cgroup_mutex held. + * See cgroup_destroy_locked() for the rationale. */ -static int cgroup_drain_dying(struct cgroup *cgrp) - __releases(&cgroup_mutex) __acquires(&cgroup_mutex) +static void cgroup_finish_destroy(struct cgroup *cgrp) { - struct css_task_iter it; - struct task_struct *task; - DEFINE_WAIT(wait); + struct cgroup_subsys_state *css; + int ssid; lockdep_assert_held(&cgroup_mutex); -retry: - if (!cgroup_has_tasks(cgrp)) - return 0; - - /* Same iterator as cgroup.threads - if any task is visible, it's busy */ - css_task_iter_start(&cgrp->self, 0, &it); - task = css_task_iter_next(&it); - css_task_iter_end(&it); - if (task) - return -EBUSY; - - /* - * All remaining tasks are PF_EXITING and will pass through - * cgroup_task_dead() shortly. Wait for a kick and retry. - * - * cgroup_has_tasks() can't transition from false to true while we're - * holding cgroup_mutex, but the true to false transition happens - * under css_set_lock (via cgroup_task_dead()). We must retest and - * prepare_to_wait() under css_set_lock. Otherwise, the transition - * can happen between our first test and prepare_to_wait(), and we - * sleep with no one to wake us. - */ - spin_lock_irq(&css_set_lock); - if (!cgroup_has_tasks(cgrp)) { - spin_unlock_irq(&css_set_lock); - return 0; - } - prepare_to_wait(&cgrp->dying_populated_waitq, &wait, - TASK_UNINTERRUPTIBLE); - spin_unlock_irq(&css_set_lock); - mutex_unlock(&cgroup_mutex); - schedule(); - finish_wait(&cgrp->dying_populated_waitq, &wait); - mutex_lock(&cgroup_mutex); - goto retry; + for_each_css(css, ssid, cgrp) + kill_css_finish(css); } int cgroup_rmdir(struct kernfs_node *kn) @@ -6255,12 +6260,9 @@ int cgroup_rmdir(struct kernfs_node *kn) if (!cgrp) return 0; - ret = cgroup_drain_dying(cgrp); - if (!ret) { - ret = cgroup_destroy_locked(cgrp); - if (!ret) - TRACE_CGROUP_PATH(rmdir, cgrp); - } + ret = cgroup_destroy_locked(cgrp); + if (!ret) + TRACE_CGROUP_PATH(rmdir, cgrp); cgroup_kn_unlock(kn); return ret; @@ -7020,7 +7022,6 @@ void cgroup_task_exit(struct task_struct *tsk) static void do_cgroup_task_dead(struct task_struct *tsk) { - struct cgrp_cset_link *link; struct css_set *cset; unsigned long flags; @@ -7034,11 +7035,6 @@ static void do_cgroup_task_dead(struct task_struct *tsk) if (thread_group_leader(tsk) && atomic_read(&tsk->signal->live)) list_add_tail(&tsk->cg_list, &cset->dying_tasks); - /* kick cgroup_drain_dying() waiters, see cgroup_rmdir() */ - list_for_each_entry(link, &cset->cgrp_links, cgrp_link) - if (waitqueue_active(&link->cgrp->dying_populated_waitq)) - wake_up(&link->cgrp->dying_populated_waitq); - if (dl_task(tsk)) dec_dl_tasks_cs(tsk); diff --git a/kernel/cgroup/cpuset-internal.h b/kernel/cgroup/cpuset-internal.h index fd7d19842ded..bb4e692bea30 100644 --- a/kernel/cgroup/cpuset-internal.h +++ b/kernel/cgroup/cpuset-internal.h @@ -168,6 +168,11 @@ struct cpuset { int nr_deadline_tasks; int nr_migrate_dl_tasks; u64 sum_migrate_dl_bw; + /* + * CPU used for temporary DL bandwidth allocation during attach; + * -1 if no DL bandwidth was allocated in the current attach. + */ + int dl_bw_cpu; /* Invalid partition error code, not lock protected */ enum prs_errcode prs_err; diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 1335e437098e..e3a081a07c6d 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -288,6 +288,7 @@ struct cpuset top_cpuset = { .flags = BIT(CS_CPU_EXCLUSIVE) | BIT(CS_MEM_EXCLUSIVE) | BIT(CS_SCHED_LOAD_BALANCE), .partition_root_state = PRS_ROOT, + .dl_bw_cpu = -1, }; /** @@ -579,6 +580,8 @@ static struct cpuset *dup_or_alloc_cpuset(struct cpuset *cs) if (!trial) return NULL; + trial->dl_bw_cpu = -1; + /* Setup cpumask pointer array */ cpumask_var_t *pmask[4] = { &trial->cpus_allowed, @@ -2980,6 +2983,7 @@ static void reset_migrate_dl_data(struct cpuset *cs) { cs->nr_migrate_dl_tasks = 0; cs->sum_migrate_dl_bw = 0; + cs->dl_bw_cpu = -1; } /* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */ @@ -3056,6 +3060,8 @@ static int cpuset_can_attach(struct cgroup_taskset *tset) reset_migrate_dl_data(cs); goto out_unlock; } + + cs->dl_bw_cpu = cpu; } out_success: @@ -3080,12 +3086,11 @@ static void cpuset_cancel_attach(struct cgroup_taskset *tset) mutex_lock(&cpuset_mutex); dec_attach_in_progress_locked(cs); - if (cs->nr_migrate_dl_tasks) { - int cpu = cpumask_any(cs->effective_cpus); + if (cs->dl_bw_cpu >= 0) + dl_bw_free(cs->dl_bw_cpu, cs->sum_migrate_dl_bw); - dl_bw_free(cpu, cs->sum_migrate_dl_bw); + if (cs->nr_migrate_dl_tasks) reset_migrate_dl_data(cs); - } mutex_unlock(&cpuset_mutex); } diff --git a/kernel/cgroup/rdma.c b/kernel/cgroup/rdma.c index 9967fb25c563..4fdab4cf49e0 100644 --- a/kernel/cgroup/rdma.c +++ b/kernel/cgroup/rdma.c @@ -283,7 +283,7 @@ int rdmacg_try_charge(struct rdma_cgroup **rdmacg, ret = PTR_ERR(rpool); goto err; } else { - new = rpool->resources[index].usage + 1; + new = (s64)rpool->resources[index].usage + 1; if (new > rpool->resources[index].max) { ret = -EAGAIN; goto err; diff --git a/kernel/fork.c b/kernel/fork.c index f1ad69c6dc2d..5f3fdfdb14c7 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1951,9 +1951,11 @@ static void rv_task_fork(struct task_struct *p) static bool need_futex_hash_allocate_default(u64 clone_flags) { - if ((clone_flags & (CLONE_THREAD | CLONE_VM)) != (CLONE_THREAD | CLONE_VM)) - return false; - return true; + /* + * Allocate a default futex hash for any sibling that will + * share the parent's mm, except vfork. + */ + return (clone_flags & (CLONE_VM | CLONE_VFORK)) == CLONE_VM; } /* @@ -2380,10 +2382,6 @@ __latent_entropy struct task_struct *copy_process( if (retval) goto bad_fork_cancel_cgroup; - /* - * Allocate a default futex hash for the user process once the first - * thread spawns. - */ if (need_futex_hash_allocate_default(clone_flags)) { retval = futex_hash_allocate_default(); if (retval) diff --git a/kernel/futex/requeue.c b/kernel/futex/requeue.c index d818b4d47f1b..b597cb3d17fc 100644 --- a/kernel/futex/requeue.c +++ b/kernel/futex/requeue.c @@ -319,8 +319,11 @@ futex_proxy_trylock_atomic(u32 __user *pifutex, struct futex_hash_bucket *hb1, return -EINVAL; /* Ensure that this does not race against an early wakeup */ - if (!futex_requeue_pi_prepare(top_waiter, NULL)) + if (!futex_requeue_pi_prepare(top_waiter, NULL)) { + plist_del(&top_waiter->list, &hb1->chain); + futex_hb_waiters_dec(hb1); return -EAGAIN; + } /* * Try to take the lock for top_waiter and set the FUTEX_WAITERS bit @@ -722,10 +725,12 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb, /* * We were woken prior to requeue by a timeout or a signal. - * Unqueue the futex_q and determine which it was. + * Conditionally unqueue the futex_q and determine which it was. */ - plist_del(&q->list, &hb->chain); - futex_hb_waiters_dec(hb); + if (!plist_node_empty(&q->list)) { + plist_del(&q->list, &hb->chain); + futex_hb_waiters_dec(hb); + } /* Handle spurious wakeups gracefully */ ret = -EWOULDBLOCK; diff --git a/kernel/liveupdate/kexec_handover.c b/kernel/liveupdate/kexec_handover.c index 94762de1fe5f..18509d8082ea 100644 --- a/kernel/liveupdate/kexec_handover.c +++ b/kernel/liveupdate/kexec_handover.c @@ -762,19 +762,24 @@ int kho_add_subtree(const char *name, void *blob, size_t size) goto out_pack; } - err = fdt_setprop(root_fdt, off, KHO_SUB_TREE_PROP_NAME, - &phys, sizeof(phys)); - if (err < 0) - goto out_pack; + fdt_err = fdt_setprop(root_fdt, off, KHO_SUB_TREE_PROP_NAME, + &phys, sizeof(phys)); + if (fdt_err < 0) + goto out_del_node; - err = fdt_setprop(root_fdt, off, KHO_SUB_TREE_SIZE_PROP_NAME, - &size_u64, sizeof(size_u64)); - if (err < 0) - goto out_pack; + fdt_err = fdt_setprop(root_fdt, off, KHO_SUB_TREE_SIZE_PROP_NAME, + &size_u64, sizeof(size_u64)); + if (fdt_err < 0) + goto out_del_node; WARN_ON_ONCE(kho_debugfs_blob_add(&kho_out.dbg, name, blob, size, false)); + err = 0; + goto out_pack; + +out_del_node: + fdt_del_node(root_fdt, off); out_pack: fdt_pack(root_fdt); diff --git a/kernel/liveupdate/luo_session.c b/kernel/liveupdate/luo_session.c index a3327a28fc1f..7a42385dabe2 100644 --- a/kernel/liveupdate/luo_session.c +++ b/kernel/liveupdate/luo_session.c @@ -514,11 +514,12 @@ int luo_session_deserialize(void) { struct luo_session_header *sh = &luo_session_global.incoming; static bool is_deserialized; - static int err; + static int saved_err; + int err; /* If has been deserialized, always return the same error code */ if (is_deserialized) - return err; + return saved_err; is_deserialized = true; if (!sh->active) @@ -547,7 +548,8 @@ int luo_session_deserialize(void) pr_warn("Failed to allocate session [%.*s] during deserialization %pe\n", (int)sizeof(sh->ser[i].name), sh->ser[i].name, session); - return PTR_ERR(session); + err = PTR_ERR(session); + goto save_err; } err = luo_session_insert(sh, session); @@ -555,7 +557,7 @@ int luo_session_deserialize(void) pr_warn("Failed to insert session [%s] %pe\n", session->name, ERR_PTR(err)); luo_session_free(session); - return err; + goto save_err; } scoped_guard(mutex, &session->mutex) { @@ -565,7 +567,7 @@ int luo_session_deserialize(void) if (err) { pr_warn("Failed to deserialize files for session [%s] %pe\n", session->name, ERR_PTR(err)); - return err; + goto save_err; } } @@ -574,6 +576,9 @@ int luo_session_deserialize(void) sh->ser = NULL; return 0; +save_err: + saved_err = err; + return err; } int luo_session_serialize(void) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index da20fb6ea25a..b8871449d3c6 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4458,6 +4458,7 @@ static void __sched_fork(u64 clone_flags, struct task_struct *p) p->se.nr_migrations = 0; p->se.vruntime = 0; p->se.vlag = 0; + p->se.rel_deadline = 0; INIT_LIST_HEAD(&p->se.group_node); /* A delayed task cannot be in clone(). */ diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index e426e27b6794..38d90baf78cf 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -32,6 +32,7 @@ static const struct rhashtable_params scx_sched_hash_params = { .key_len = sizeof_field(struct scx_sched, ops.sub_cgroup_id), .key_offset = offsetof(struct scx_sched, ops.sub_cgroup_id), .head_offset = offsetof(struct scx_sched, hash_node), + .insecure_elasticity = true, /* inserted under scx_sched_lock */ }; static struct rhashtable scx_sched_hash; @@ -52,8 +53,6 @@ DEFINE_STATIC_KEY_FALSE(__scx_enabled); DEFINE_STATIC_PERCPU_RWSEM(scx_fork_rwsem); static atomic_t scx_enable_state_var = ATOMIC_INIT(SCX_DISABLED); static DEFINE_RAW_SPINLOCK(scx_bypass_lock); -static cpumask_var_t scx_bypass_lb_donee_cpumask; -static cpumask_var_t scx_bypass_lb_resched_cpumask; static bool scx_init_task_enabled; static bool scx_switching_all; DEFINE_STATIC_KEY_FALSE(__scx_switched_all); @@ -469,24 +468,35 @@ static inline void update_locked_rq(struct rq *rq) __this_cpu_write(scx_locked_rq_state, rq); } -#define SCX_CALL_OP(sch, op, rq, args...) \ +/* + * SCX ops can recurse via scx_bpf_sub_dispatch() - the inner call must not + * clobber the outer's scx_locked_rq_state. Save it on entry, restore on exit. + */ +#define SCX_CALL_OP(sch, op, locked_rq, args...) \ do { \ - if (rq) \ - update_locked_rq(rq); \ + struct rq *__prev_locked_rq; \ + \ + if (locked_rq) { \ + __prev_locked_rq = scx_locked_rq(); \ + update_locked_rq(locked_rq); \ + } \ (sch)->ops.op(args); \ - if (rq) \ - update_locked_rq(NULL); \ + if (locked_rq) \ + update_locked_rq(__prev_locked_rq); \ } while (0) -#define SCX_CALL_OP_RET(sch, op, rq, args...) \ +#define SCX_CALL_OP_RET(sch, op, locked_rq, args...) \ ({ \ + struct rq *__prev_locked_rq; \ __typeof__((sch)->ops.op(args)) __ret; \ \ - if (rq) \ - update_locked_rq(rq); \ + if (locked_rq) { \ + __prev_locked_rq = scx_locked_rq(); \ + update_locked_rq(locked_rq); \ + } \ __ret = (sch)->ops.op(args); \ - if (rq) \ - update_locked_rq(NULL); \ + if (locked_rq) \ + update_locked_rq(__prev_locked_rq); \ __ret; \ }) @@ -498,39 +508,39 @@ do { \ * those subject tasks. * * Every SCX_CALL_OP_TASK*() call site invokes its op with @p's rq lock held - - * either via the @rq argument here, or (for ops.select_cpu()) via @p's pi_lock - * held by try_to_wake_up() with rq tracking via scx_rq.in_select_cpu. So if - * kf_tasks[] is set, @p's scheduler-protected fields are stable. + * either via the @locked_rq argument here, or (for ops.select_cpu()) via @p's + * pi_lock held by try_to_wake_up() with rq tracking via scx_rq.in_select_cpu. + * So if kf_tasks[] is set, @p's scheduler-protected fields are stable. * * kf_tasks[] can not stack, so task-based SCX ops must not nest. The * WARN_ON_ONCE() in each macro catches a re-entry of any of the three variants * while a previous one is still in progress. */ -#define SCX_CALL_OP_TASK(sch, op, rq, task, args...) \ +#define SCX_CALL_OP_TASK(sch, op, locked_rq, task, args...) \ do { \ WARN_ON_ONCE(current->scx.kf_tasks[0]); \ current->scx.kf_tasks[0] = task; \ - SCX_CALL_OP((sch), op, rq, task, ##args); \ + SCX_CALL_OP((sch), op, locked_rq, task, ##args); \ current->scx.kf_tasks[0] = NULL; \ } while (0) -#define SCX_CALL_OP_TASK_RET(sch, op, rq, task, args...) \ +#define SCX_CALL_OP_TASK_RET(sch, op, locked_rq, task, args...) \ ({ \ __typeof__((sch)->ops.op(task, ##args)) __ret; \ WARN_ON_ONCE(current->scx.kf_tasks[0]); \ current->scx.kf_tasks[0] = task; \ - __ret = SCX_CALL_OP_RET((sch), op, rq, task, ##args); \ + __ret = SCX_CALL_OP_RET((sch), op, locked_rq, task, ##args); \ current->scx.kf_tasks[0] = NULL; \ __ret; \ }) -#define SCX_CALL_OP_2TASKS_RET(sch, op, rq, task0, task1, args...) \ +#define SCX_CALL_OP_2TASKS_RET(sch, op, locked_rq, task0, task1, args...) \ ({ \ __typeof__((sch)->ops.op(task0, task1, ##args)) __ret; \ WARN_ON_ONCE(current->scx.kf_tasks[0]); \ current->scx.kf_tasks[0] = task0; \ current->scx.kf_tasks[1] = task1; \ - __ret = SCX_CALL_OP_RET((sch), op, rq, task0, task1, ##args); \ + __ret = SCX_CALL_OP_RET((sch), op, locked_rq, task0, task1, ##args); \ current->scx.kf_tasks[0] = NULL; \ current->scx.kf_tasks[1] = NULL; \ __ret; \ @@ -756,7 +766,8 @@ static void scx_task_iter_start(struct scx_task_iter *iter, struct cgroup *cgrp) lockdep_assert_held(&cgroup_mutex); iter->cgrp = cgrp; iter->css_pos = css_next_descendant_pre(NULL, &iter->cgrp->self); - css_task_iter_start(iter->css_pos, 0, &iter->css_iter); + css_task_iter_start(iter->css_pos, CSS_TASK_ITER_WITH_DEAD, + &iter->css_iter); return; } #endif @@ -856,7 +867,8 @@ static struct task_struct *scx_task_iter_next(struct scx_task_iter *iter) iter->css_pos = css_next_descendant_pre(iter->css_pos, &iter->cgrp->self); if (iter->css_pos) - css_task_iter_start(iter->css_pos, 0, &iter->css_iter); + css_task_iter_start(iter->css_pos, CSS_TASK_ITER_WITH_DEAD, + &iter->css_iter); } return NULL; } @@ -916,16 +928,27 @@ static struct task_struct *scx_task_iter_next_locked(struct scx_task_iter *iter) * * Test for idle_sched_class as only init_tasks are on it. */ - if (p->sched_class != &idle_sched_class) - break; - } - if (!p) - return NULL; + if (p->sched_class == &idle_sched_class) + continue; - iter->rq = task_rq_lock(p, &iter->rf); - iter->locked_task = p; + iter->rq = task_rq_lock(p, &iter->rf); + iter->locked_task = p; - return p; + /* + * cgroup_task_dead() removes the dead tasks from cset->tasks + * after sched_ext_dead() and cgroup iteration may see tasks + * which already finished sched_ext_dead(). %SCX_TASK_OFF_TASKS + * is set by sched_ext_dead() under @p's rq lock. Test it to + * avoid visiting tasks which are already dead from SCX POV. + */ + if (p->scx.flags & SCX_TASK_OFF_TASKS) { + __scx_task_iter_rq_unlock(iter); + continue; + } + + return p; + } + return NULL; } /** @@ -1388,18 +1411,55 @@ static void call_task_dequeue(struct scx_sched *sch, struct rq *rq, p->scx.flags &= ~SCX_TASK_IN_CUSTODY; } -static void local_dsq_post_enq(struct scx_dispatch_q *dsq, struct task_struct *p, - u64 enq_flags) +static void local_dsq_post_enq(struct scx_sched *sch, struct scx_dispatch_q *dsq, + struct task_struct *p, u64 enq_flags) { struct rq *rq = container_of(dsq, struct rq, scx.local_dsq); - bool preempt = false; - call_task_dequeue(scx_root, rq, p, 0); + call_task_dequeue(sch, rq, p, 0); + + /* + * Note that @rq's lock may be dropped between this enqueue and @p + * actually getting on CPU. This gives higher-class tasks (e.g. RT) + * an opportunity to wake up on @rq and prevent @p from running. + * Here are some concrete examples: + * + * Example 1: + * + * We dispatch two tasks from a single ops.dispatch(): + * - First, a local task to this CPU's local DSQ; + * - Second, a local/remote task to a remote CPU's local DSQ. + * We must drop the local rq lock in order to finish the second + * dispatch. In that time, an RT task can wake up on the local rq. + * + * Example 2: + * + * We dispatch a local/remote task to a remote CPU's local DSQ. + * We must drop the remote rq lock before the dispatched task can run, + * which gives an RT task an opportunity to wake up on the remote rq. + * + * Both examples work the same if we replace dispatching with moving + * the tasks from a user-created DSQ. + * + * We must detect these wakeups so that we can re-enqueue IMMED tasks + * from @rq's local DSQ. scx_wakeup_preempt() serves exactly this + * purpose, but for it to be invoked, we must ensure that we bump + * @rq->next_class to &ext_sched_class if it's currently idle. + * + * wakeup_preempt() does the bumping, and since we only invoke it if + * @rq->next_class is below &ext_sched_class, it will also + * resched_curr(rq). + */ + if (sched_class_above(p->sched_class, rq->next_class)) + wakeup_preempt(rq, p, 0); /* * If @rq is in balance, the CPU is already vacant and looking for the * next task to run. No need to preempt or trigger resched after moving * @p into its local DSQ. + * Note that the wakeup_preempt() above may have already triggered + * a resched if @rq->next_class was idle. It's harmless, since + * need_resched is cleared immediately after task pick. */ if (rq->scx.flags & SCX_RQ_IN_BALANCE) return; @@ -1407,11 +1467,8 @@ static void local_dsq_post_enq(struct scx_dispatch_q *dsq, struct task_struct *p if ((enq_flags & SCX_ENQ_PREEMPT) && p != rq->curr && rq->curr->sched_class == &ext_sched_class) { rq->curr->scx.slice = 0; - preempt = true; - } - - if (preempt || sched_class_above(&ext_sched_class, rq->curr->sched_class)) resched_curr(rq); + } } static void dispatch_enqueue(struct scx_sched *sch, struct rq *rq, @@ -1494,11 +1551,13 @@ static void dispatch_enqueue(struct scx_sched *sch, struct rq *rq, if (!(dsq->id & SCX_DSQ_FLAG_BUILTIN)) rcu_assign_pointer(dsq->first_task, p); } else { - bool was_empty; - - was_empty = list_empty(&dsq->list); + /* + * dsq->list can contain parked BPF iterator cursors, so + * list_empty() here isn't a reliable proxy for "no real + * task in the DSQ". Test dsq->first_task directly. + */ list_add_tail(&p->scx.dsq_list.node, &dsq->list); - if (was_empty && !(dsq->id & SCX_DSQ_FLAG_BUILTIN)) + if (!dsq->first_task && !(dsq->id & SCX_DSQ_FLAG_BUILTIN)) rcu_assign_pointer(dsq->first_task, p); } } @@ -1518,7 +1577,7 @@ static void dispatch_enqueue(struct scx_sched *sch, struct rq *rq, * concurrently in a non-atomic way. */ if (is_local) { - local_dsq_post_enq(dsq, p, enq_flags); + local_dsq_post_enq(sch, dsq, p, enq_flags); } else { /* * Task on global/bypass DSQ: leave custody, task on @@ -2129,7 +2188,8 @@ static void wakeup_preempt_scx(struct rq *rq, struct task_struct *p, int wake_fl schedule_reenq_local(rq, 0); } -static void move_local_task_to_local_dsq(struct task_struct *p, u64 enq_flags, +static void move_local_task_to_local_dsq(struct scx_sched *sch, + struct task_struct *p, u64 enq_flags, struct scx_dispatch_q *src_dsq, struct rq *dst_rq) { @@ -2149,7 +2209,7 @@ static void move_local_task_to_local_dsq(struct task_struct *p, u64 enq_flags, dsq_inc_nr(dst_dsq, p, enq_flags); p->scx.dsq = dst_dsq; - local_dsq_post_enq(dst_dsq, p, enq_flags); + local_dsq_post_enq(sch, dst_dsq, p, enq_flags); } /** @@ -2370,7 +2430,7 @@ static struct rq *move_task_between_dsqs(struct scx_sched *sch, /* @p is going from a non-local DSQ to a local DSQ */ if (src_rq == dst_rq) { task_unlink_from_dsq(p, src_dsq); - move_local_task_to_local_dsq(p, enq_flags, + move_local_task_to_local_dsq(sch, p, enq_flags, src_dsq, dst_rq); raw_spin_unlock(&src_dsq->lock); } else { @@ -2423,7 +2483,7 @@ retry: if (rq == task_rq) { task_unlink_from_dsq(p, dsq); - move_local_task_to_local_dsq(p, enq_flags, dsq, rq); + move_local_task_to_local_dsq(sch, p, enq_flags, dsq, rq); raw_spin_unlock(&dsq->lock); return true; } @@ -3183,7 +3243,7 @@ bool scx_prio_less(const struct task_struct *a, const struct task_struct *b, if (sch_a == sch_b && SCX_HAS_OP(sch_a, core_sched_before) && !scx_bypassing(sch_a, task_cpu(a))) return SCX_CALL_OP_2TASKS_RET(sch_a, core_sched_before, - NULL, + task_rq(a), (struct task_struct *)a, (struct task_struct *)b); else @@ -3631,6 +3691,22 @@ static void __scx_disable_and_exit_task(struct scx_sched *sch, SCX_CALL_OP_TASK(sch, exit_task, task_rq(p), p, &args); } +/* + * Undo a completed __scx_init_task(sch, p, false) when scx_enable_task() never + * ran. The task state has not been transitioned, so this mirrors the + * SCX_TASK_INIT branch in __scx_disable_and_exit_task(). + */ +static void scx_sub_init_cancel_task(struct scx_sched *sch, struct task_struct *p) +{ + struct scx_exit_task_args args = { .cancelled = true }; + + lockdep_assert_held(&p->pi_lock); + lockdep_assert_rq_held(task_rq(p)); + + if (SCX_HAS_OP(sch, exit_task)) + SCX_CALL_OP_TASK(sch, exit_task, task_rq(p), p, &args); +} + static void scx_disable_and_exit_task(struct scx_sched *sch, struct task_struct *p) { @@ -3639,11 +3715,12 @@ static void scx_disable_and_exit_task(struct scx_sched *sch, /* * If set, @p exited between __scx_init_task() and scx_enable_task() in * scx_sub_enable() and is initialized for both the associated sched and - * its parent. Disable and exit for the child too. + * its parent. Exit for the child too - scx_enable_task() never ran for + * it, so undo only init_task. */ - if ((p->scx.flags & SCX_TASK_SUB_INIT) && - !WARN_ON_ONCE(!scx_enabling_sub_sched)) { - __scx_disable_and_exit_task(scx_enabling_sub_sched, p); + if (p->scx.flags & SCX_TASK_SUB_INIT) { + if (!WARN_ON_ONCE(!scx_enabling_sub_sched)) + scx_sub_init_cancel_task(scx_enabling_sub_sched, p); p->scx.flags &= ~SCX_TASK_SUB_INIT; } @@ -3784,6 +3861,11 @@ void sched_ext_dead(struct task_struct *p) /* * @p is off scx_tasks and wholly ours. scx_root_enable()'s READY -> * ENABLED transitions can't race us. Disable ops for @p. + * + * %SCX_TASK_OFF_TASKS synchronizes against cgroup task iteration - see + * scx_task_iter_next_locked(). NONE tasks need no marking: cgroup + * iteration is only used from sub-sched paths, which require root + * enabled. Root enable transitions every live task to at least READY. */ if (scx_get_task_state(p) != SCX_TASK_NONE) { struct rq_flags rf; @@ -3791,6 +3873,7 @@ void sched_ext_dead(struct task_struct *p) rq = task_rq_lock(p, &rf); scx_disable_and_exit_task(scx_task_sched(p), p); + p->scx.flags |= SCX_TASK_OFF_TASKS; task_rq_unlock(rq, p, &rf); } } @@ -4324,9 +4407,10 @@ void scx_cgroup_cancel_attach(struct cgroup_taskset *tset) void scx_group_set_weight(struct task_group *tg, unsigned long weight) { - struct scx_sched *sch = scx_root; + struct scx_sched *sch; percpu_down_read(&scx_cgroup_ops_rwsem); + sch = scx_root; if (scx_cgroup_enabled && SCX_HAS_OP(sch, cgroup_set_weight) && tg->scx.weight != weight) @@ -4339,9 +4423,10 @@ void scx_group_set_weight(struct task_group *tg, unsigned long weight) void scx_group_set_idle(struct task_group *tg, bool idle) { - struct scx_sched *sch = scx_root; + struct scx_sched *sch; percpu_down_read(&scx_cgroup_ops_rwsem); + sch = scx_root; if (scx_cgroup_enabled && SCX_HAS_OP(sch, cgroup_set_idle)) SCX_CALL_OP(sch, cgroup_set_idle, NULL, tg_cgrp(tg), idle); @@ -4355,9 +4440,10 @@ void scx_group_set_idle(struct task_group *tg, bool idle) void scx_group_set_bandwidth(struct task_group *tg, u64 period_us, u64 quota_us, u64 burst_us) { - struct scx_sched *sch = scx_root; + struct scx_sched *sch; percpu_down_read(&scx_cgroup_ops_rwsem); + sch = scx_root; if (scx_cgroup_enabled && SCX_HAS_OP(sch, cgroup_set_bandwidth) && (tg->scx.bw_period_us != period_us || @@ -4380,21 +4466,6 @@ static struct cgroup *root_cgroup(void) return &cgrp_dfl_root.cgrp; } -static struct cgroup *sch_cgroup(struct scx_sched *sch) -{ - return sch->cgrp; -} - -/* for each descendant of @cgrp including self, set ->scx_sched to @sch */ -static void set_cgroup_sched(struct cgroup *cgrp, struct scx_sched *sch) -{ - struct cgroup *pos; - struct cgroup_subsys_state *css; - - cgroup_for_each_live_descendant_pre(pos, css, cgrp) - rcu_assign_pointer(pos->scx_sched, sch); -} - static void scx_cgroup_lock(void) { #ifdef CONFIG_EXT_GROUP_SCHED @@ -4412,12 +4483,30 @@ static void scx_cgroup_unlock(void) } #else /* CONFIG_EXT_GROUP_SCHED || CONFIG_EXT_SUB_SCHED */ static struct cgroup *root_cgroup(void) { return NULL; } -static struct cgroup *sch_cgroup(struct scx_sched *sch) { return NULL; } -static void set_cgroup_sched(struct cgroup *cgrp, struct scx_sched *sch) {} static void scx_cgroup_lock(void) {} static void scx_cgroup_unlock(void) {} #endif /* CONFIG_EXT_GROUP_SCHED || CONFIG_EXT_SUB_SCHED */ +#ifdef CONFIG_EXT_SUB_SCHED +static struct cgroup *sch_cgroup(struct scx_sched *sch) +{ + return sch->cgrp; +} + +/* for each descendant of @cgrp including self, set ->scx_sched to @sch */ +static void set_cgroup_sched(struct cgroup *cgrp, struct scx_sched *sch) +{ + struct cgroup *pos; + struct cgroup_subsys_state *css; + + cgroup_for_each_live_descendant_pre(pos, css, cgrp) + rcu_assign_pointer(pos->scx_sched, sch); +} +#else /* CONFIG_EXT_SUB_SCHED */ +static struct cgroup *sch_cgroup(struct scx_sched *sch) { return NULL; } +static void set_cgroup_sched(struct cgroup *cgrp, struct scx_sched *sch) {} +#endif /* CONFIG_EXT_SUB_SCHED */ + /* * Omitted operations: * @@ -4712,6 +4801,8 @@ static void scx_sched_free_rcu_work(struct work_struct *work) irq_work_sync(&sch->disable_irq_work); kthread_destroy_worker(sch->helper); timer_shutdown_sync(&sch->bypass_lb_timer); + free_cpumask_var(sch->bypass_lb_donee_cpumask); + free_cpumask_var(sch->bypass_lb_resched_cpumask); #ifdef CONFIG_EXT_SUB_SCHED kfree(sch->cgrp_path); @@ -4938,6 +5029,25 @@ void scx_softlockup(u32 dur_s) smp_processor_id(), dur_s); } +/* + * scx_hardlockup() runs from NMI and eventually calls scx_claim_exit(), + * which takes scx_sched_lock. scx_sched_lock isn't NMI-safe and grabbing + * it from NMI context can lead to deadlocks. Defer via irq_work; the + * disable path runs off irq_work anyway. + */ +static atomic_t scx_hardlockup_cpu = ATOMIC_INIT(-1); + +static void scx_hardlockup_irq_workfn(struct irq_work *work) +{ + int cpu = atomic_xchg(&scx_hardlockup_cpu, -1); + + if (cpu >= 0 && handle_lockup("hard lockup - CPU %d", cpu)) + printk_deferred(KERN_ERR "sched_ext: Hard lockup - CPU %d, disabling BPF scheduler\n", + cpu); +} + +static DEFINE_IRQ_WORK(scx_hardlockup_irq_work, scx_hardlockup_irq_workfn); + /** * scx_hardlockup - sched_ext hardlockup handler * @@ -4946,17 +5056,19 @@ void scx_softlockup(u32 dur_s) * Try kicking out the current scheduler in an attempt to recover the system to * a good state before taking more drastic actions. * - * Returns %true if sched_ext is enabled and abort was initiated, which may - * resolve the reported hardlockup. %false if sched_ext is not enabled or - * someone else already initiated abort. + * Queues an irq_work; the handle_lockup() call happens in IRQ context (see + * scx_hardlockup_irq_workfn). + * + * Returns %true if sched_ext is enabled and the work was queued, %false + * otherwise. */ bool scx_hardlockup(int cpu) { - if (!handle_lockup("hard lockup - CPU %d", cpu)) + if (!rcu_access_pointer(scx_root)) return false; - printk_deferred(KERN_ERR "sched_ext: Hard lockup - CPU %d, disabling BPF scheduler\n", - cpu); + atomic_cmpxchg(&scx_hardlockup_cpu, -1, cpu); + irq_work_queue(&scx_hardlockup_irq_work); return true; } @@ -5000,6 +5112,15 @@ resume: if (cpumask_empty(donee_mask)) break; + /* + * If an earlier pass placed @p on @donor_dsq from a different + * CPU and the donee hasn't consumed it yet, @p is still on the + * previous CPU and task_rq(@p) != @donor_rq. @p can't be moved + * without its rq locked. Skip. + */ + if (task_rq(p) != donor_rq) + continue; + donee = cpumask_any_and_distribute(donee_mask, p->cpus_ptr); if (donee >= nr_cpu_ids) continue; @@ -5058,8 +5179,8 @@ resume: static void bypass_lb_node(struct scx_sched *sch, int node) { const struct cpumask *node_mask = cpumask_of_node(node); - struct cpumask *donee_mask = scx_bypass_lb_donee_cpumask; - struct cpumask *resched_mask = scx_bypass_lb_resched_cpumask; + struct cpumask *donee_mask = sch->bypass_lb_donee_cpumask; + struct cpumask *resched_mask = sch->bypass_lb_resched_cpumask; u32 nr_tasks = 0, nr_cpus = 0, nr_balanced = 0; u32 nr_target, nr_donor_target; u32 before_min = U32_MAX, before_max = 0; @@ -5698,6 +5819,8 @@ static void scx_sub_disable(struct scx_sched *sch) if (sch->ops.exit) SCX_CALL_OP(sch, exit, NULL, sch->exit_info); + if (sch->sub_kset) + kset_unregister(sch->sub_kset); kobject_del(&sch->kobj); } #else /* CONFIG_EXT_SUB_SCHED */ @@ -5829,6 +5952,10 @@ static void scx_root_disable(struct scx_sched *sch) * could observe an object of the same name still in the hierarchy when * the next scheduler is loaded. */ +#ifdef CONFIG_EXT_SUB_SCHED + if (sch->sub_kset) + kset_unregister(sch->sub_kset); +#endif kobject_del(&sch->kobj); free_kick_syncs(); @@ -5921,6 +6048,25 @@ static void scx_disable(struct scx_sched *sch, enum scx_exit_kind kind) irq_work_queue(&sch->disable_irq_work); } +/** + * scx_flush_disable_work - flush the disable work and wait for it to finish + * @sch: the scheduler + * + * sch->disable_work might still not queued, causing kthread_flush_work() + * as a noop. Syncing the irq_work first is required to guarantee the + * kthread work has been queued before waiting for it. + */ +static void scx_flush_disable_work(struct scx_sched *sch) +{ + int kind; + + do { + irq_work_sync(&sch->disable_irq_work); + kthread_flush_work(&sch->disable_work); + kind = atomic_read(&sch->exit_kind); + } while (kind != SCX_EXIT_NONE && kind != SCX_EXIT_DONE); +} + static void dump_newline(struct seq_buf *s) { trace_sched_ext_dump(""); @@ -6032,9 +6178,8 @@ static void ops_dump_exit(void) scx_dump_data.cpu = -1; } -static void scx_dump_task(struct scx_sched *sch, - struct seq_buf *s, struct scx_dump_ctx *dctx, - struct task_struct *p, char marker) +static void scx_dump_task(struct scx_sched *sch, struct seq_buf *s, struct scx_dump_ctx *dctx, + struct rq *rq, struct task_struct *p, char marker) { static unsigned long bt[SCX_EXIT_BT_LEN]; struct scx_sched *task_sch = scx_task_sched(p); @@ -6075,7 +6220,7 @@ static void scx_dump_task(struct scx_sched *sch, if (SCX_HAS_OP(sch, dump_task)) { ops_dump_init(s, " "); - SCX_CALL_OP(sch, dump_task, NULL, dctx, p); + SCX_CALL_OP(sch, dump_task, rq, dctx, p); ops_dump_exit(); } @@ -6199,8 +6344,7 @@ static void scx_dump_state(struct scx_sched *sch, struct scx_exit_info *ei, used = seq_buf_used(&ns); if (SCX_HAS_OP(sch, dump_cpu)) { ops_dump_init(&ns, " "); - SCX_CALL_OP(sch, dump_cpu, NULL, - &dctx, cpu, idle); + SCX_CALL_OP(sch, dump_cpu, rq, &dctx, cpu, idle); ops_dump_exit(); } @@ -6223,11 +6367,11 @@ static void scx_dump_state(struct scx_sched *sch, struct scx_exit_info *ei, if (rq->curr->sched_class == &ext_sched_class && (dump_all_tasks || scx_task_on_sched(sch, rq->curr))) - scx_dump_task(sch, &s, &dctx, rq->curr, '*'); + scx_dump_task(sch, &s, &dctx, rq, rq->curr, '*'); list_for_each_entry(p, &rq->scx.runnable_list, scx.runnable_node) if (dump_all_tasks || scx_task_on_sched(sch, p)) - scx_dump_task(sch, &s, &dctx, p, ' '); + scx_dump_task(sch, &s, &dctx, rq, p, ' '); next: rq_unlock_irqrestore(rq, &rf); } @@ -6437,6 +6581,15 @@ static struct scx_sched *scx_alloc_and_add_sched(struct sched_ext_ops *ops, init_irq_work(&sch->disable_irq_work, scx_disable_irq_workfn); kthread_init_work(&sch->disable_work, scx_disable_workfn); timer_setup(&sch->bypass_lb_timer, scx_bypass_lb_timerfn, 0); + + if (!alloc_cpumask_var(&sch->bypass_lb_donee_cpumask, GFP_KERNEL)) { + ret = -ENOMEM; + goto err_stop_helper; + } + if (!alloc_cpumask_var(&sch->bypass_lb_resched_cpumask, GFP_KERNEL)) { + ret = -ENOMEM; + goto err_free_lb_cpumask; + } sch->ops = *ops; rcu_assign_pointer(ops->priv, sch); @@ -6446,14 +6599,14 @@ static struct scx_sched *scx_alloc_and_add_sched(struct sched_ext_ops *ops, char *buf = kzalloc(PATH_MAX, GFP_KERNEL); if (!buf) { ret = -ENOMEM; - goto err_stop_helper; + goto err_free_lb_resched; } cgroup_path(cgrp, buf, PATH_MAX); sch->cgrp_path = kstrdup(buf, GFP_KERNEL); kfree(buf); if (!sch->cgrp_path) { ret = -ENOMEM; - goto err_stop_helper; + goto err_free_lb_resched; } sch->cgrp = cgrp; @@ -6488,10 +6641,12 @@ static struct scx_sched *scx_alloc_and_add_sched(struct sched_ext_ops *ops, #endif /* CONFIG_EXT_SUB_SCHED */ return sch; -#ifdef CONFIG_EXT_SUB_SCHED +err_free_lb_resched: + free_cpumask_var(sch->bypass_lb_resched_cpumask); +err_free_lb_cpumask: + free_cpumask_var(sch->bypass_lb_donee_cpumask); err_stop_helper: kthread_destroy_worker(sch->helper); -#endif err_free_pcpu: for_each_possible_cpu(cpu) { if (cpu == bypass_fail_cpu) @@ -6510,7 +6665,7 @@ err_free_ei: err_free_sch: kfree(sch); err_put_cgrp: -#if defined(CONFIG_EXT_GROUP_SCHED) || defined(CONFIG_EXT_SUB_SCHED) +#ifdef CONFIG_EXT_SUB_SCHED cgroup_put(cgrp); #endif return ERR_PTR(ret); @@ -6601,7 +6756,7 @@ static void scx_root_enable_workfn(struct kthread_work *work) if (ret) goto err_unlock; -#if defined(CONFIG_EXT_GROUP_SCHED) || defined(CONFIG_EXT_SUB_SCHED) +#ifdef CONFIG_EXT_SUB_SCHED cgroup_get(cgrp); #endif sch = scx_alloc_and_add_sched(ops, cgrp, NULL); @@ -6639,8 +6794,10 @@ static void scx_root_enable_workfn(struct kthread_work *work) rcu_assign_pointer(scx_root, sch); ret = scx_link_sched(sch); - if (ret) + if (ret) { + cpus_read_unlock(); goto err_disable; + } scx_idle_enable(ops); @@ -6821,7 +6978,7 @@ err_disable: * completion. sch's base reference will be put by bpf_scx_unreg(). */ scx_error(sch, "scx_root_enable() failed (%d)", ret); - kthread_flush_work(&sch->disable_work); + scx_flush_disable_work(sch); cmd->ret = 0; } @@ -7072,23 +7229,30 @@ out_unlock: abort: put_task_struct(p); scx_task_iter_stop(&sti); - scx_enabling_sub_sched = NULL; + /* + * Undo __scx_init_task() for tasks we marked. scx_enable_task() never + * ran for @sch on them, so calling scx_disable_task() here would invoke + * ops.disable() without a matching ops.enable(). scx_enabling_sub_sched + * must stay set until SUB_INIT is cleared from every marked task - + * scx_disable_and_exit_task() reads it when a task exits concurrently. + */ scx_task_iter_start(&sti, sch->cgrp); while ((p = scx_task_iter_next_locked(&sti))) { if (p->scx.flags & SCX_TASK_SUB_INIT) { - __scx_disable_and_exit_task(sch, p); + scx_sub_init_cancel_task(sch, p); p->scx.flags &= ~SCX_TASK_SUB_INIT; } } scx_task_iter_stop(&sti); + scx_enabling_sub_sched = NULL; err_unlock_and_disable: /* we'll soon enter disable path, keep bypass on */ scx_cgroup_unlock(); percpu_up_write(&scx_fork_rwsem); err_disable: mutex_unlock(&scx_enable_mutex); - kthread_flush_work(&sch->disable_work); + scx_flush_disable_work(sch); cmd->ret = 0; } @@ -7349,7 +7513,7 @@ static void bpf_scx_unreg(void *kdata, struct bpf_link *link) struct scx_sched *sch = rcu_dereference_protected(ops->priv, true); scx_disable(sch, SCX_EXIT_UNREG); - kthread_flush_work(&sch->disable_work); + scx_flush_disable_work(sch); RCU_INIT_POINTER(ops->priv, NULL); kobject_put(&sch->kobj); } @@ -8033,12 +8197,22 @@ static bool scx_dsq_move(struct bpf_iter_scx_dsq_kern *kit, struct task_struct *p, u64 dsq_id, u64 enq_flags) { struct scx_dispatch_q *src_dsq = kit->dsq, *dst_dsq; - struct scx_sched *sch = src_dsq->sched; + struct scx_sched *sch; struct rq *this_rq, *src_rq, *locked_rq; bool dispatched = false; bool in_balance; unsigned long flags; + /* + * The verifier considers an iterator slot initialized on any + * KF_ITER_NEW return, so a BPF program may legally reach here after + * bpf_iter_scx_dsq_new() failed and left @kit->dsq NULL. + */ + if (unlikely(!src_dsq)) + return false; + + sch = src_dsq->sched; + if (!scx_vet_enq_flags(sch, dsq_id, &enq_flags)) return false; @@ -8526,7 +8700,7 @@ __bpf_kfunc bool scx_bpf_task_set_slice(struct task_struct *p, u64 slice, guard(rcu)(); sch = scx_prog_sched(aux); - if (unlikely(!scx_task_on_sched(sch, p))) + if (unlikely(!sch || !scx_task_on_sched(sch, p))) return false; p->scx.slice = slice; @@ -8549,7 +8723,7 @@ __bpf_kfunc bool scx_bpf_task_set_dsq_vtime(struct task_struct *p, u64 vtime, guard(rcu)(); sch = scx_prog_sched(aux); - if (unlikely(!scx_task_on_sched(sch, p))) + if (unlikely(!sch || !scx_task_on_sched(sch, p))) return false; p->scx.dsq_vtime = vtime; @@ -8633,11 +8807,12 @@ __bpf_kfunc void scx_bpf_kick_cpu(s32 cpu, u64 flags, const struct bpf_prog_aux /** * scx_bpf_dsq_nr_queued - Return the number of queued tasks * @dsq_id: id of the DSQ + * @aux: implicit BPF argument to access bpf_prog_aux hidden from BPF progs * * Return the number of tasks in the DSQ matching @dsq_id. If not found, * -%ENOENT is returned. */ -__bpf_kfunc s32 scx_bpf_dsq_nr_queued(u64 dsq_id) +__bpf_kfunc s32 scx_bpf_dsq_nr_queued(u64 dsq_id, const struct bpf_prog_aux *aux) { struct scx_sched *sch; struct scx_dispatch_q *dsq; @@ -8645,7 +8820,7 @@ __bpf_kfunc s32 scx_bpf_dsq_nr_queued(u64 dsq_id) preempt_disable(); - sch = rcu_dereference_sched(scx_root); + sch = scx_prog_sched(aux); if (unlikely(!sch)) { ret = -ENODEV; goto out; @@ -8677,21 +8852,21 @@ out: /** * scx_bpf_destroy_dsq - Destroy a custom DSQ * @dsq_id: DSQ to destroy + * @aux: implicit BPF argument to access bpf_prog_aux hidden from BPF progs * * Destroy the custom DSQ identified by @dsq_id. Only DSQs created with * scx_bpf_create_dsq() can be destroyed. The caller must ensure that the DSQ is * empty and no further tasks are dispatched to it. Ignored if called on a DSQ * which doesn't exist. Can be called from any online scx_ops operations. */ -__bpf_kfunc void scx_bpf_destroy_dsq(u64 dsq_id) +__bpf_kfunc void scx_bpf_destroy_dsq(u64 dsq_id, const struct bpf_prog_aux *aux) { struct scx_sched *sch; - rcu_read_lock(); - sch = rcu_dereference(scx_root); + guard(rcu)(); + sch = scx_prog_sched(aux); if (sch) destroy_dsq(sch, dsq_id); - rcu_read_unlock(); } /** @@ -9445,8 +9620,8 @@ BTF_KFUNCS_START(scx_kfunc_ids_any) BTF_ID_FLAGS(func, scx_bpf_task_set_slice, KF_IMPLICIT_ARGS | KF_RCU); BTF_ID_FLAGS(func, scx_bpf_task_set_dsq_vtime, KF_IMPLICIT_ARGS | KF_RCU); BTF_ID_FLAGS(func, scx_bpf_kick_cpu, KF_IMPLICIT_ARGS) -BTF_ID_FLAGS(func, scx_bpf_dsq_nr_queued) -BTF_ID_FLAGS(func, scx_bpf_destroy_dsq) +BTF_ID_FLAGS(func, scx_bpf_dsq_nr_queued, KF_IMPLICIT_ARGS) +BTF_ID_FLAGS(func, scx_bpf_destroy_dsq, KF_IMPLICIT_ARGS) BTF_ID_FLAGS(func, scx_bpf_dsq_peek, KF_IMPLICIT_ARGS | KF_RCU_PROTECTED | KF_RET_NULL) BTF_ID_FLAGS(func, scx_bpf_dsq_reenq, KF_IMPLICIT_ARGS) BTF_ID_FLAGS(func, scx_bpf_reenqueue_local___v2, KF_IMPLICIT_ARGS) @@ -9479,6 +9654,7 @@ BTF_KFUNCS_END(scx_kfunc_ids_any) static const struct btf_kfunc_id_set scx_kfunc_set_any = { .owner = THIS_MODULE, .set = &scx_kfunc_ids_any, + .filter = scx_kfunc_context_filter, }; /* @@ -9526,13 +9702,12 @@ static const u32 scx_kf_allow_flags[] = { }; /* - * Verifier-time filter for context-sensitive SCX kfuncs. Registered via the - * .filter field on each per-group btf_kfunc_id_set. The BPF core invokes this - * for every kfunc call in the registered hook (BPF_PROG_TYPE_STRUCT_OPS or + * Verifier-time filter for SCX kfuncs. Registered via the .filter field on + * each per-group btf_kfunc_id_set. The BPF core invokes this for every kfunc + * call in the registered hook (BPF_PROG_TYPE_STRUCT_OPS or * BPF_PROG_TYPE_SYSCALL), regardless of which set originally introduced the - * kfunc - so the filter must short-circuit on kfuncs it doesn't govern (e.g. - * scx_kfunc_ids_any) by falling through to "allow" when none of the - * context-sensitive sets contain the kfunc. + * kfunc - so the filter must short-circuit on kfuncs it doesn't govern by + * falling through to "allow" when none of the SCX sets contain the kfunc. */ int scx_kfunc_context_filter(const struct bpf_prog *prog, u32 kfunc_id) { @@ -9541,18 +9716,21 @@ int scx_kfunc_context_filter(const struct bpf_prog *prog, u32 kfunc_id) bool in_enqueue = btf_id_set8_contains(&scx_kfunc_ids_enqueue_dispatch, kfunc_id); bool in_dispatch = btf_id_set8_contains(&scx_kfunc_ids_dispatch, kfunc_id); bool in_cpu_release = btf_id_set8_contains(&scx_kfunc_ids_cpu_release, kfunc_id); + bool in_idle = btf_id_set8_contains(&scx_kfunc_ids_idle, kfunc_id); + bool in_any = btf_id_set8_contains(&scx_kfunc_ids_any, kfunc_id); u32 moff, flags; - /* Not a context-sensitive kfunc (e.g. from scx_kfunc_ids_any) - allow. */ - if (!(in_unlocked || in_select_cpu || in_enqueue || in_dispatch || in_cpu_release)) + /* Not an SCX kfunc - allow. */ + if (!(in_unlocked || in_select_cpu || in_enqueue || in_dispatch || + in_cpu_release || in_idle || in_any)) return 0; /* SYSCALL progs (e.g. BPF test_run()) may call unlocked and select_cpu kfuncs. */ if (prog->type == BPF_PROG_TYPE_SYSCALL) - return (in_unlocked || in_select_cpu) ? 0 : -EACCES; + return (in_unlocked || in_select_cpu || in_idle || in_any) ? 0 : -EACCES; if (prog->type != BPF_PROG_TYPE_STRUCT_OPS) - return -EACCES; + return (in_any || in_idle) ? 0 : -EACCES; /* * add_subprog_and_kfunc() collects all kfunc calls, including dead code @@ -9565,14 +9743,15 @@ int scx_kfunc_context_filter(const struct bpf_prog *prog, u32 kfunc_id) return 0; /* - * Non-SCX struct_ops: only unlocked kfuncs are safe. The other - * context-sensitive kfuncs assume the rq lock is held by the SCX - * dispatch path, which doesn't apply to other struct_ops users. + * Non-SCX struct_ops: SCX kfuncs are not permitted. */ if (prog->aux->st_ops != &bpf_sched_ext_ops) - return in_unlocked ? 0 : -EACCES; + return -EACCES; /* SCX struct_ops: check the per-op allow list. */ + if (in_any || in_idle) + return 0; + moff = prog->aux->attach_st_ops_member_off; flags = scx_kf_allow_flags[SCX_MOFF_IDX(moff)]; @@ -9656,12 +9835,6 @@ static int __init scx_init(void) return ret; } - if (!alloc_cpumask_var(&scx_bypass_lb_donee_cpumask, GFP_KERNEL) || - !alloc_cpumask_var(&scx_bypass_lb_resched_cpumask, GFP_KERNEL)) { - pr_err("sched_ext: Failed to allocate cpumasks\n"); - return -ENOMEM; - } - return 0; } __initcall(scx_init); diff --git a/kernel/sched/ext_idle.c b/kernel/sched/ext_idle.c index 443d12a3df67..6e1980763270 100644 --- a/kernel/sched/ext_idle.c +++ b/kernel/sched/ext_idle.c @@ -466,12 +466,6 @@ s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, preempt_disable(); /* - * Check whether @prev_cpu is still within the allowed set. If not, - * we can still try selecting a nearby CPU. - */ - is_prev_allowed = cpumask_test_cpu(prev_cpu, allowed); - - /* * Determine the subset of CPUs usable by @p within @cpus_allowed. */ if (allowed != p->cpus_ptr) { @@ -488,6 +482,12 @@ s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, } /* + * Check whether @prev_cpu is still within the allowed set. If not, + * we can still try selecting a nearby CPU. + */ + is_prev_allowed = cpumask_test_cpu(prev_cpu, allowed); + + /* * This is necessary to protect llc_cpus. */ rcu_read_lock(); @@ -927,14 +927,24 @@ static s32 select_cpu_from_kfunc(struct scx_sched *sch, struct task_struct *p, * Accessing p->cpus_ptr / p->nr_cpus_allowed needs either @p's rq * lock or @p's pi_lock. Three cases: * - * - inside ops.select_cpu(): try_to_wake_up() holds @p's pi_lock. + * - inside ops.select_cpu(): try_to_wake_up() holds the wake-up + * task's pi_lock; the wake-up task is recorded in kf_tasks[0] + * by SCX_CALL_OP_TASK_RET(). * - other rq-locked SCX op: scx_locked_rq() points at the held rq. * - truly unlocked (UNLOCKED ops, SYSCALL, non-SCX struct_ops): * nothing held, take pi_lock ourselves. + * + * In the first two cases, BPF schedulers may pass an arbitrary task + * that the held lock doesn't cover. Refuse those. */ if (this_rq()->scx.in_select_cpu) { + if (!scx_kf_arg_task_ok(sch, p)) + return -EINVAL; lockdep_assert_held(&p->pi_lock); - } else if (!scx_locked_rq()) { + } else if (scx_locked_rq()) { + if (task_rq(p) != scx_locked_rq()) + goto cross_task; + } else { raw_spin_lock_irqsave(&p->pi_lock, irq_flags); we_locked = true; } @@ -960,6 +970,11 @@ static s32 select_cpu_from_kfunc(struct scx_sched *sch, struct task_struct *p, raw_spin_unlock_irqrestore(&p->pi_lock, irq_flags); return cpu; + +cross_task: + scx_error(sch, "select_cpu kfunc called cross-task on %s[%d]", + p->comm, p->pid); + return -EINVAL; } /** @@ -1467,6 +1482,7 @@ BTF_KFUNCS_END(scx_kfunc_ids_idle) static const struct btf_kfunc_id_set scx_kfunc_set_idle = { .owner = THIS_MODULE, .set = &scx_kfunc_ids_idle, + .filter = scx_kfunc_context_filter, }; /* diff --git a/kernel/sched/ext_idle.h b/kernel/sched/ext_idle.h index dc35f850481e..8d169d3bbdf9 100644 --- a/kernel/sched/ext_idle.h +++ b/kernel/sched/ext_idle.h @@ -12,6 +12,7 @@ struct sched_ext_ops; +extern struct btf_id_set8 scx_kfunc_ids_idle; extern struct btf_id_set8 scx_kfunc_ids_select_cpu; void scx_idle_update_selcpu_topology(struct sched_ext_ops *ops); diff --git a/kernel/sched/ext_internal.h b/kernel/sched/ext_internal.h index 62ce4eaf6a3f..a075732d4430 100644 --- a/kernel/sched/ext_internal.h +++ b/kernel/sched/ext_internal.h @@ -1075,6 +1075,8 @@ struct scx_sched { struct irq_work disable_irq_work; struct kthread_work disable_work; struct timer_list bypass_lb_timer; + cpumask_var_t bypass_lb_donee_cpumask; + cpumask_var_t bypass_lb_resched_cpumask; struct rcu_work rcu_work; /* all ancestors including self */ diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 69361c63353a..728965851842 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -847,13 +847,19 @@ static s64 entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se, u64 avrunt * Similarly, check that the entity didn't gain positive lag when DELAY_ZERO * is set. * - * Return true if the lag has been adjusted. + * Return true if the vlag has been modified. Specifically: + * + * se->vlag != avg_vruntime() - se->vruntime + * + * This can be due to clamping in entity_lag() or clamping due to + * sched_delayed. Either way, when vlag is modified and the entity is + * retained, the tree needs to be adjusted. */ static __always_inline bool update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se) { - s64 vlag = entity_lag(cfs_rq, se, avg_vruntime(cfs_rq)); - bool ret; + u64 avruntime = avg_vruntime(cfs_rq); + s64 vlag = entity_lag(cfs_rq, se, avruntime); WARN_ON_ONCE(!se->on_rq); @@ -863,10 +869,9 @@ bool update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se) if (sched_feat(DELAY_ZERO)) vlag = min(vlag, 0); } - ret = (vlag == se->vlag); se->vlag = vlag; - return ret; + return avruntime - vlag != se->vruntime; } /* @@ -1099,7 +1104,7 @@ static inline void cancel_protect_slice(struct sched_entity *se) * * Which allows tree pruning through eligibility. */ -static struct sched_entity *__pick_eevdf(struct cfs_rq *cfs_rq, bool protect) +static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq, bool protect) { struct rb_node *node = cfs_rq->tasks_timeline.rb_root.rb_node; struct sched_entity *se = __pick_first_entity(cfs_rq); @@ -1170,11 +1175,6 @@ found: return best; } -static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq) -{ - return __pick_eevdf(cfs_rq, true); -} - struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq) { struct rb_node *last = rb_last(&cfs_rq->tasks_timeline.rb_root); @@ -5749,11 +5749,11 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags); * 4) do not run the "skip" process, if something else is available */ static struct sched_entity * -pick_next_entity(struct rq *rq, struct cfs_rq *cfs_rq) +pick_next_entity(struct rq *rq, struct cfs_rq *cfs_rq, bool protect) { struct sched_entity *se; - se = pick_eevdf(cfs_rq); + se = pick_eevdf(cfs_rq, protect); if (se->sched_delayed) { dequeue_entities(rq, se, DEQUEUE_SLEEP | DEQUEUE_DELAYED); /* @@ -9027,7 +9027,7 @@ static void wakeup_preempt_fair(struct rq *rq, struct task_struct *p, int wake_f { enum preempt_wakeup_action preempt_action = PREEMPT_WAKEUP_PICK; struct task_struct *donor = rq->donor; - struct sched_entity *se = &donor->se, *pse = &p->se; + struct sched_entity *nse, *se = &donor->se, *pse = &p->se; struct cfs_rq *cfs_rq = task_cfs_rq(donor); int cse_is_idle, pse_is_idle; @@ -9138,11 +9138,17 @@ static void wakeup_preempt_fair(struct rq *rq, struct task_struct *p, int wake_f } pick: + nse = pick_next_entity(rq, cfs_rq, preempt_action != PREEMPT_WAKEUP_SHORT); + /* If @p has become the most eligible task, force preemption */ + if (nse == pse) + goto preempt; + /* - * If @p has become the most eligible task, force preemption. + * Because p is enqueued, nse being null can only mean that we + * dequeued a delayed task. */ - if (__pick_eevdf(cfs_rq, preempt_action != PREEMPT_WAKEUP_SHORT) == pse) - goto preempt; + if (!nse) + goto pick; if (sched_feat(RUN_TO_PARITY)) update_protect_slice(cfs_rq, se); @@ -9179,7 +9185,7 @@ again: throttled |= check_cfs_rq_runtime(cfs_rq); - se = pick_next_entity(rq, cfs_rq); + se = pick_next_entity(rq, cfs_rq, true); if (!se) goto again; cfs_rq = group_cfs_rq(se); diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c index 6809b370e991..d1564db95a8f 100644 --- a/kernel/trace/trace_branch.c +++ b/kernel/trace/trace_branch.c @@ -373,10 +373,10 @@ __init static int init_annotated_branch_stats(void) int ret; ret = register_stat_tracer(&annotated_branch_stats); - if (!ret) { + if (ret) { printk(KERN_WARNING "Warning: could not register " "annotated branches stats\n"); - return 1; + return ret; } return 0; } @@ -438,10 +438,10 @@ __init static int all_annotated_branch_stats(void) int ret; ret = register_stat_tracer(&all_branch_stats); - if (!ret) { + if (ret) { printk(KERN_WARNING "Warning: could not register " "all branches stats\n"); - return 1; + return ret; } return 0; } diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index e1c73065dae5..e0d3a0da26af 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -1523,6 +1523,12 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size, parg->offset = *size; *size += parg->type->size * (parg->count ?: 1); + if (*size > MAX_PROBE_EVENT_SIZE) { + ret = -E2BIG; + trace_probe_log_err(ctx->offset, EVENT_TOO_BIG); + goto fail; + } + if (parg->count) { len = strlen(parg->type->fmttype) + 6; parg->fmt = kmalloc(len, GFP_KERNEL); diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index 9fc56c937130..262d8707a3df 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -38,6 +38,7 @@ #define MAX_BTF_ARGS_LEN 128 #define MAX_DENTRY_ARGS_LEN 256 #define MAX_STRING_SIZE PATH_MAX +#define MAX_PROBE_EVENT_SIZE 3072 /* Reserved field names */ #define FIELD_STRING_IP "__probe_ip" @@ -561,7 +562,8 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call, C(BAD_TYPE4STR, "This type does not fit for string."),\ C(NEED_STRING_TYPE, "$comm and immediate-string only accepts string type"),\ C(TOO_MANY_ARGS, "Too many arguments are specified"), \ - C(TOO_MANY_EARGS, "Too many entry arguments specified"), + C(TOO_MANY_EARGS, "Too many entry arguments specified"), \ + C(EVENT_TOO_BIG, "Event too big (too many fields?)"), #undef C #define C(a, b) TP_ERR_##a diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 5f747f241a5f..3d2e3b2ec528 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -5906,6 +5906,21 @@ err_destroy: return NULL; } +__printf(1, 0) +static struct workqueue_struct *alloc_workqueue_va(const char *fmt, + unsigned int flags, + int max_active, + va_list args) +{ + struct workqueue_struct *wq; + + wq = __alloc_workqueue(fmt, flags, max_active, args); + if (wq) + wq_init_lockdep(wq); + + return wq; +} + __printf(1, 4) struct workqueue_struct *alloc_workqueue_noprof(const char *fmt, unsigned int flags, @@ -5915,12 +5930,8 @@ struct workqueue_struct *alloc_workqueue_noprof(const char *fmt, va_list args; va_start(args, max_active); - wq = __alloc_workqueue(fmt, flags, max_active, args); + wq = alloc_workqueue_va(fmt, flags, max_active, args); va_end(args); - if (!wq) - return NULL; - - wq_init_lockdep(wq); return wq; } @@ -5932,15 +5943,15 @@ static void devm_workqueue_release(void *res) } __printf(2, 5) struct workqueue_struct * -devm_alloc_workqueue(struct device *dev, const char *fmt, unsigned int flags, - int max_active, ...) +devm_alloc_workqueue_noprof(struct device *dev, const char *fmt, + unsigned int flags, int max_active, ...) { struct workqueue_struct *wq; va_list args; int ret; va_start(args, max_active); - wq = alloc_workqueue(fmt, flags, max_active, args); + wq = alloc_workqueue_va(fmt, flags, max_active, args); va_end(args); if (!wq) return NULL; @@ -5951,7 +5962,7 @@ devm_alloc_workqueue(struct device *dev, const char *fmt, unsigned int flags, return wq; } -EXPORT_SYMBOL_GPL(devm_alloc_workqueue); +EXPORT_SYMBOL_GPL(devm_alloc_workqueue_noprof); #ifdef CONFIG_LOCKDEP __printf(1, 5) diff --git a/lib/fonts/font_rotate.c b/lib/fonts/font_rotate.c index 065e0fc0667b..275406008823 100644 --- a/lib/fonts/font_rotate.c +++ b/lib/fonts/font_rotate.c @@ -106,7 +106,7 @@ static void __font_glyph_rotate_180(const unsigned char *glyph, for (y = 0; y < height; y++) { for (x = 0; x < width; x++) { if (font_glyph_test_bit(glyph, x, y, bit_pitch)) { - font_glyph_set_bit(out, width - (1 + x + shift), height - (1 + y), + font_glyph_set_bit(out, bit_pitch - 1 - x - shift, height - 1 - y, bit_pitch); } } diff --git a/lib/maple_tree.c b/lib/maple_tree.c index d18d7ed9ab67..60ae5e6fc1ee 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -2,7 +2,7 @@ /* * Maple Tree implementation * Copyright (c) 2018-2022 Oracle Corporation - * Authors: Liam R. Howlett <Liam.Howlett@oracle.com> + * Authors: Liam R. Howlett <liam@infradead.org> * Matthew Wilcox <willy@infradead.org> * Copyright (c) 2023 ByteDance * Author: Peng Zhang <zhangpeng.00@bytedance.com> diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 6074ed5f66f3..7a67ef5b67b6 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -441,10 +441,33 @@ static void rht_deferred_worker(struct work_struct *work) mutex_unlock(&ht->mutex); + /* + * Re-arm via @run_work, not @run_irq_work. + * rhashtable_free_and_destroy() drains async work as irq_work_sync() + * followed by cancel_work_sync(). If this site queued irq_work while + * cancel_work_sync() was waiting for us, irq_work_sync() would already + * have returned and the stale irq_work could fire post-teardown. + * cancel_work_sync() natively handles self-requeue on @run_work. + */ if (err) schedule_work(&ht->run_work); } +/* + * Insert-path callers can run under a raw spinlock (e.g. an insecure_elasticity + * user). Calling schedule_work() under that lock records caller_lock -> + * pool->lock -> pi_lock -> rq->__lock, closing a locking cycle if any of + * these is acquired in the reverse direction elsewhere. Bounce through + * irq_work so the schedule_work() runs with the caller's lock no longer held. + */ +static void rht_deferred_irq_work(struct irq_work *irq_work) +{ + struct rhashtable *ht = container_of(irq_work, struct rhashtable, + run_irq_work); + + schedule_work(&ht->run_work); +} + static int rhashtable_insert_rehash(struct rhashtable *ht, struct bucket_table *tbl) { @@ -477,7 +500,7 @@ static int rhashtable_insert_rehash(struct rhashtable *ht, if (err == -EEXIST) err = 0; } else - schedule_work(&ht->run_work); + irq_work_queue(&ht->run_irq_work); return err; @@ -488,7 +511,7 @@ fail: /* Schedule async rehash to retry allocation in process context. */ if (err == -ENOMEM) - schedule_work(&ht->run_work); + irq_work_queue(&ht->run_irq_work); return err; } @@ -538,7 +561,7 @@ static void *rhashtable_lookup_one(struct rhashtable *ht, return NULL; } - if (elasticity <= 0) + if (elasticity <= 0 && !ht->p.insecure_elasticity) return ERR_PTR(-EAGAIN); return ERR_PTR(-ENOENT); @@ -568,7 +591,8 @@ static struct bucket_table *rhashtable_insert_one( if (unlikely(rht_grow_above_max(ht, tbl))) return ERR_PTR(-E2BIG); - if (unlikely(rht_grow_above_100(ht, tbl))) + if (unlikely(rht_grow_above_100(ht, tbl)) && + !ht->p.insecure_elasticity) return ERR_PTR(-EAGAIN); head = rht_ptr(bkt, tbl, hash); @@ -629,7 +653,7 @@ static void *rhashtable_try_insert(struct rhashtable *ht, const void *key, rht_unlock(tbl, bkt, flags); if (inserted && rht_grow_above_75(ht, tbl)) - schedule_work(&ht->run_work); + irq_work_queue(&ht->run_irq_work); } } while (!IS_ERR_OR_NULL(new_tbl)); @@ -1084,6 +1108,7 @@ int rhashtable_init_noprof(struct rhashtable *ht, RCU_INIT_POINTER(ht->tbl, tbl); INIT_WORK(&ht->run_work, rht_deferred_worker); + init_irq_work(&ht->run_irq_work, rht_deferred_irq_work); return 0; } @@ -1149,6 +1174,7 @@ void rhashtable_free_and_destroy(struct rhashtable *ht, struct bucket_table *tbl, *next_tbl; unsigned int i; + irq_work_sync(&ht->run_irq_work); cancel_work_sync(&ht->run_work); mutex_lock(&ht->mutex); diff --git a/lib/test_maple_tree.c b/lib/test_maple_tree.c index 434d8a2fdd99..b9367c61e8b5 100644 --- a/lib/test_maple_tree.c +++ b/lib/test_maple_tree.c @@ -2,7 +2,7 @@ /* * test_maple_tree.c: Test the maple tree API * Copyright (c) 2018-2022 Oracle Corporation - * Author: Liam R. Howlett <Liam.Howlett@Oracle.com> + * Author: Liam R. Howlett <liam@infradead.org> * * Any tests that only require the interface of the tree. */ @@ -4021,6 +4021,6 @@ static void __exit maple_tree_harvest(void) module_init(maple_tree_seed); module_exit(maple_tree_harvest); -MODULE_AUTHOR("Liam R. Howlett <Liam.Howlett@Oracle.com>"); +MODULE_AUTHOR("Liam R. Howlett <liam@infradead.org>"); MODULE_DESCRIPTION("maple tree API test module"); MODULE_LICENSE("GPL"); diff --git a/mm/damon/lru_sort.c b/mm/damon/lru_sort.c index 554559d72976..8494040b1ee4 100644 --- a/mm/damon/lru_sort.c +++ b/mm/damon/lru_sort.c @@ -161,15 +161,6 @@ module_param(monitor_region_end, ulong, 0600); */ static unsigned long addr_unit __read_mostly = 1; -/* - * PID of the DAMON thread - * - * If DAMON_LRU_SORT is enabled, this becomes the PID of the worker thread. - * Else, -1. - */ -static int kdamond_pid __read_mostly = -1; -module_param(kdamond_pid, int, 0400); - static struct damos_stat damon_lru_sort_hot_stat; DEFINE_DAMON_MODULES_DAMOS_STATS_PARAMS(damon_lru_sort_hot_stat, lru_sort_tried_hot_regions, lru_sorted_hot_regions, @@ -386,12 +377,8 @@ static int damon_lru_sort_turn(bool on) { int err; - if (!on) { - err = damon_stop(&ctx, 1); - if (!err) - kdamond_pid = -1; - return err; - } + if (!on) + return damon_stop(&ctx, 1); err = damon_lru_sort_apply_parameters(); if (err) @@ -400,9 +387,6 @@ static int damon_lru_sort_turn(bool on) err = damon_start(&ctx, 1, true); if (err) return err; - kdamond_pid = damon_kdamond_pid(ctx); - if (kdamond_pid < 0) - return kdamond_pid; return damon_call(ctx, &call_control); } @@ -430,42 +414,83 @@ module_param_cb(addr_unit, &addr_unit_param_ops, &addr_unit, 0600); MODULE_PARM_DESC(addr_unit, "Scale factor for DAMON_LRU_SORT to ops address conversion (default: 1)"); +static bool damon_lru_sort_enabled(void) +{ + if (!ctx) + return false; + return damon_is_running(ctx); +} + static int damon_lru_sort_enabled_store(const char *val, const struct kernel_param *kp) { - bool is_enabled = enabled; - bool enable; int err; - err = kstrtobool(val, &enable); + err = kstrtobool(val, &enabled); if (err) return err; - if (is_enabled == enable) + if (damon_lru_sort_enabled() == enabled) return 0; /* Called before init function. The function will handle this. */ if (!damon_initialized()) - goto set_param_out; + return 0; - err = damon_lru_sort_turn(enable); - if (err) - return err; + return damon_lru_sort_turn(enabled); +} -set_param_out: - enabled = enable; - return err; +static int damon_lru_sort_enabled_load(char *buffer, + const struct kernel_param *kp) +{ + return sprintf(buffer, "%c\n", damon_lru_sort_enabled() ? 'Y' : 'N'); } static const struct kernel_param_ops enabled_param_ops = { .set = damon_lru_sort_enabled_store, - .get = param_get_bool, + .get = damon_lru_sort_enabled_load, }; module_param_cb(enabled, &enabled_param_ops, &enabled, 0600); MODULE_PARM_DESC(enabled, "Enable or disable DAMON_LRU_SORT (default: disabled)"); +static int damon_lru_sort_kdamond_pid_store(const char *val, + const struct kernel_param *kp) +{ + /* + * kdamond_pid is read-only, but kernel command line could write it. + * Do nothing here. + */ + return 0; +} + +static int damon_lru_sort_kdamond_pid_load(char *buffer, + const struct kernel_param *kp) +{ + int kdamond_pid = -1; + + if (ctx) { + kdamond_pid = damon_kdamond_pid(ctx); + if (kdamond_pid < 0) + kdamond_pid = -1; + } + return sprintf(buffer, "%d\n", kdamond_pid); +} + +static const struct kernel_param_ops kdamond_pid_param_ops = { + .set = damon_lru_sort_kdamond_pid_store, + .get = damon_lru_sort_kdamond_pid_load, +}; + +/* + * PID of the DAMON thread + * + * If DAMON_LRU_SORT is enabled, this becomes the PID of the worker thread. + * Else, -1. + */ +module_param_cb(kdamond_pid, &kdamond_pid_param_ops, NULL, 0400); + static int __init damon_lru_sort_init(void) { int err; diff --git a/mm/damon/reclaim.c b/mm/damon/reclaim.c index 86da14778658..fe7fce26cf6c 100644 --- a/mm/damon/reclaim.c +++ b/mm/damon/reclaim.c @@ -144,15 +144,6 @@ static unsigned long addr_unit __read_mostly = 1; static bool skip_anon __read_mostly; module_param(skip_anon, bool, 0600); -/* - * PID of the DAMON thread - * - * If DAMON_RECLAIM is enabled, this becomes the PID of the worker thread. - * Else, -1. - */ -static int kdamond_pid __read_mostly = -1; -module_param(kdamond_pid, int, 0400); - static struct damos_stat damon_reclaim_stat; DEFINE_DAMON_MODULES_DAMOS_STATS_PARAMS(damon_reclaim_stat, reclaim_tried_regions, reclaimed_regions, quota_exceeds); @@ -288,12 +279,8 @@ static int damon_reclaim_turn(bool on) { int err; - if (!on) { - err = damon_stop(&ctx, 1); - if (!err) - kdamond_pid = -1; - return err; - } + if (!on) + return damon_stop(&ctx, 1); err = damon_reclaim_apply_parameters(); if (err) @@ -302,9 +289,6 @@ static int damon_reclaim_turn(bool on) err = damon_start(&ctx, 1, true); if (err) return err; - kdamond_pid = damon_kdamond_pid(ctx); - if (kdamond_pid < 0) - return kdamond_pid; return damon_call(ctx, &call_control); } @@ -332,42 +316,83 @@ module_param_cb(addr_unit, &addr_unit_param_ops, &addr_unit, 0600); MODULE_PARM_DESC(addr_unit, "Scale factor for DAMON_RECLAIM to ops address conversion (default: 1)"); +static bool damon_reclaim_enabled(void) +{ + if (!ctx) + return false; + return damon_is_running(ctx); +} + static int damon_reclaim_enabled_store(const char *val, const struct kernel_param *kp) { - bool is_enabled = enabled; - bool enable; int err; - err = kstrtobool(val, &enable); + err = kstrtobool(val, &enabled); if (err) return err; - if (is_enabled == enable) + if (damon_reclaim_enabled() == enabled) return 0; /* Called before init function. The function will handle this. */ if (!damon_initialized()) - goto set_param_out; + return 0; - err = damon_reclaim_turn(enable); - if (err) - return err; + return damon_reclaim_turn(enabled); +} -set_param_out: - enabled = enable; - return err; +static int damon_reclaim_enabled_load(char *buffer, + const struct kernel_param *kp) +{ + return sprintf(buffer, "%c\n", damon_reclaim_enabled() ? 'Y' : 'N'); } static const struct kernel_param_ops enabled_param_ops = { .set = damon_reclaim_enabled_store, - .get = param_get_bool, + .get = damon_reclaim_enabled_load, }; module_param_cb(enabled, &enabled_param_ops, &enabled, 0600); MODULE_PARM_DESC(enabled, "Enable or disable DAMON_RECLAIM (default: disabled)"); +static int damon_reclaim_kdamond_pid_store(const char *val, + const struct kernel_param *kp) +{ + /* + * kdamond_pid is read-only, but kernel command line could write it. + * Do nothing here. + */ + return 0; +} + +static int damon_reclaim_kdamond_pid_load(char *buffer, + const struct kernel_param *kp) +{ + int kdamond_pid = -1; + + if (ctx) { + kdamond_pid = damon_kdamond_pid(ctx); + if (kdamond_pid < 0) + kdamond_pid = -1; + } + return sprintf(buffer, "%d\n", kdamond_pid); +} + +static const struct kernel_param_ops kdamond_pid_param_ops = { + .set = damon_reclaim_kdamond_pid_store, + .get = damon_reclaim_kdamond_pid_load, +}; + +/* + * PID of the DAMON thread + * + * If DAMON_RECLAIM is enabled, this becomes the PID of the worker thread. + * Else, -1. + */ +module_param_cb(kdamond_pid, &kdamond_pid_param_ops, NULL, 0400); + static int __init damon_reclaim_init(void) { int err; diff --git a/mm/damon/stat.c b/mm/damon/stat.c index 99ba346f9e32..3951b762cbdd 100644 --- a/mm/damon/stat.c +++ b/mm/damon/stat.c @@ -19,14 +19,17 @@ static int damon_stat_enabled_store( const char *val, const struct kernel_param *kp); +static int damon_stat_enabled_load(char *buffer, + const struct kernel_param *kp); + static const struct kernel_param_ops enabled_param_ops = { .set = damon_stat_enabled_store, - .get = param_get_bool, + .get = damon_stat_enabled_load, }; static bool enabled __read_mostly = IS_ENABLED( CONFIG_DAMON_STAT_ENABLED_DEFAULT); -module_param_cb(enabled, &enabled_param_ops, &enabled, 0600); +module_param_cb(enabled, &enabled_param_ops, NULL, 0600); MODULE_PARM_DESC(enabled, "Enable of disable DAMON_STAT"); static unsigned long estimated_memory_bandwidth __read_mostly; @@ -273,17 +276,23 @@ static void damon_stat_stop(void) damon_stat_context = NULL; } +static bool damon_stat_enabled(void) +{ + if (!damon_stat_context) + return false; + return damon_is_running(damon_stat_context); +} + static int damon_stat_enabled_store( const char *val, const struct kernel_param *kp) { - bool is_enabled = enabled; int err; err = kstrtobool(val, &enabled); if (err) return err; - if (is_enabled == enabled) + if (damon_stat_enabled() == enabled) return 0; if (!damon_initialized()) @@ -293,16 +302,17 @@ static int damon_stat_enabled_store( */ return 0; - if (enabled) { - err = damon_stat_start(); - if (err) - enabled = false; - return err; - } + if (enabled) + return damon_stat_start(); damon_stat_stop(); return 0; } +static int damon_stat_enabled_load(char *buffer, const struct kernel_param *kp) +{ + return sprintf(buffer, "%c\n", damon_stat_enabled() ? 'Y' : 'N'); +} + static int __init damon_stat_init(void) { int err = 0; diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c index 5186966dafb3..245d63808411 100644 --- a/mm/damon/sysfs-schemes.c +++ b/mm/damon/sysfs-schemes.c @@ -533,9 +533,14 @@ static ssize_t memcg_path_show(struct kobject *kobj, { struct damon_sysfs_scheme_filter *filter = container_of(kobj, struct damon_sysfs_scheme_filter, kobj); + int len; - return sysfs_emit(buf, "%s\n", + if (!mutex_trylock(&damon_sysfs_lock)) + return -EBUSY; + len = sysfs_emit(buf, "%s\n", filter->memcg_path ? filter->memcg_path : ""); + mutex_unlock(&damon_sysfs_lock); + return len; } static ssize_t memcg_path_store(struct kobject *kobj, @@ -550,8 +555,13 @@ static ssize_t memcg_path_store(struct kobject *kobj, return -ENOMEM; strscpy(path, buf, count + 1); + if (!mutex_trylock(&damon_sysfs_lock)) { + kfree(path); + return -EBUSY; + } kfree(filter->memcg_path); filter->memcg_path = path; + mutex_unlock(&damon_sysfs_lock); return count; } @@ -1187,8 +1197,13 @@ static ssize_t path_show(struct kobject *kobj, { struct damos_sysfs_quota_goal *goal = container_of(kobj, struct damos_sysfs_quota_goal, kobj); + int len; - return sysfs_emit(buf, "%s\n", goal->path ? goal->path : ""); + if (!mutex_trylock(&damon_sysfs_lock)) + return -EBUSY; + len = sysfs_emit(buf, "%s\n", goal->path ? goal->path : ""); + mutex_unlock(&damon_sysfs_lock); + return len; } static ssize_t path_store(struct kobject *kobj, @@ -1203,8 +1218,13 @@ static ssize_t path_store(struct kobject *kobj, return -ENOMEM; strscpy(path, buf, count + 1); + if (!mutex_trylock(&damon_sysfs_lock)) { + kfree(path); + return -EBUSY; + } kfree(goal->path); goal->path = path; + mutex_unlock(&damon_sysfs_lock); return count; } diff --git a/mm/hugetlb_cma.c b/mm/hugetlb_cma.c index f83ae4998990..7693ccefd0c6 100644 --- a/mm/hugetlb_cma.c +++ b/mm/hugetlb_cma.c @@ -204,6 +204,7 @@ void __init hugetlb_cma_reserve(void) */ per_node = DIV_ROUND_UP(hugetlb_cma_size, nodes_weight(hugetlb_bootmem_nodes)); + per_node = round_up(per_node, PAGE_SIZE << order); pr_info("hugetlb_cma: reserve %lu MiB, up to %lu MiB per node\n", hugetlb_cma_size / SZ_1M, per_node / SZ_1M); } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index c3d98ab41f1f..c03d4787d466 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -805,12 +805,17 @@ static long memcg_state_val_in_pages(int idx, long val) * Used in mod_memcg_state() and mod_memcg_lruvec_state() to avoid race with * reparenting of non-hierarchical state_locals. */ -static inline struct mem_cgroup *get_non_dying_memcg_start(struct mem_cgroup *memcg) +static inline struct mem_cgroup *get_non_dying_memcg_start(struct mem_cgroup *memcg, + bool *rcu_locked) { - if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) + /* Rebinding can cause this value to be changed at runtime */ + if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) { + *rcu_locked = false; return memcg; + } rcu_read_lock(); + *rcu_locked = true; while (memcg_is_dying(memcg)) memcg = parent_mem_cgroup(memcg); @@ -818,20 +823,21 @@ static inline struct mem_cgroup *get_non_dying_memcg_start(struct mem_cgroup *me return memcg; } -static inline void get_non_dying_memcg_end(void) +static inline void get_non_dying_memcg_end(bool rcu_locked) { - if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) + if (!rcu_locked) return; rcu_read_unlock(); } #else -static inline struct mem_cgroup *get_non_dying_memcg_start(struct mem_cgroup *memcg) +static inline struct mem_cgroup *get_non_dying_memcg_start(struct mem_cgroup *memcg, + bool *rcu_locked) { return memcg; } -static inline void get_non_dying_memcg_end(void) +static inline void get_non_dying_memcg_end(bool rcu_locked) { } #endif @@ -865,12 +871,14 @@ static void __mod_memcg_state(struct mem_cgroup *memcg, void mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item idx, int val) { + bool rcu_locked = false; + if (mem_cgroup_disabled()) return; - memcg = get_non_dying_memcg_start(memcg); + memcg = get_non_dying_memcg_start(memcg, &rcu_locked); __mod_memcg_state(memcg, idx, val); - get_non_dying_memcg_end(); + get_non_dying_memcg_end(rcu_locked); } #ifdef CONFIG_MEMCG_V1 @@ -933,14 +941,15 @@ static void mod_memcg_lruvec_state(struct lruvec *lruvec, struct pglist_data *pgdat = lruvec_pgdat(lruvec); struct mem_cgroup_per_node *pn; struct mem_cgroup *memcg; + bool rcu_locked = false; pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); - memcg = get_non_dying_memcg_start(pn->memcg); + memcg = get_non_dying_memcg_start(pn->memcg, &rcu_locked); pn = memcg->nodeinfo[pgdat->node_id]; __mod_memcg_lruvec_state(pn, idx, val); - get_non_dying_memcg_end(); + get_non_dying_memcg_end(rcu_locked); } /** diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 88cd53d4ba09..833f743f309f 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1835,7 +1835,9 @@ static int balance_dirty_pages(struct bdi_writeback *wb, balance_domain_limits(mdtc, strictlimit); } - if (nr_dirty > gdtc->bg_thresh && !writeback_in_progress(wb)) + if (!writeback_in_progress(wb) && + (nr_dirty > gdtc->bg_thresh || + (strictlimit && gdtc->wb_dirty > gdtc->wb_bg_thresh))) wb_start_background_writeback(wb); /* @@ -1862,15 +1864,9 @@ free_running: * Unconditionally start background writeback if it's not * already in progress. We need to do this because the global * dirty threshold check above (nr_dirty > gdtc->bg_thresh) - * doesn't account for these cases: - * - * a) strictlimit BDIs: throttling is calculated using per-wb - * thresholds. The per-wb threshold can be exceeded even when - * nr_dirty < gdtc->bg_thresh - * - * b) memcg-based throttling: memcg uses its own dirty count and - * thresholds and can trigger throttling even when global - * nr_dirty < gdtc->bg_thresh + * doesn't account for the memcg-based throttling case. memcg + * uses its own dirty count and thresholds and can trigger + * throttling even when global nr_dirty < gdtc->bg_thresh * * Writeback needs to be started else the writer stalls in the * throttle loop waiting for dirty pages to be written back diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 65e205111553..227d58dc3de6 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -7737,6 +7737,11 @@ struct page *alloc_frozen_pages_nolock_noprof(gfp_t gfp_flags, int nid, unsigned */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && (in_nmi() || in_hardirq())) return NULL; + + /* On UP, spin_trylock() always succeeds even when it is locked */ + if (!IS_ENABLED(CONFIG_SMP) && in_nmi()) + return NULL; + if (!pcp_allowed_order(order)) return NULL; diff --git a/mm/slub.c b/mm/slub.c index 161079ac5ba1..0baa906f39ab 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -5339,6 +5339,10 @@ void *kmalloc_nolock_noprof(size_t size, gfp_t gfp_flags, int node) if (IS_ENABLED(CONFIG_PREEMPT_RT) && (in_nmi() || in_hardirq())) return NULL; + /* On UP, spin_trylock() always succeeds even when it is locked */ + if (!IS_ENABLED(CONFIG_SMP) && in_nmi()) + return NULL; + retry: if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) return NULL; diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 885da1e56466..180bad42fc79 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -443,8 +443,10 @@ static int mfill_copy_folio_locked(struct folio *folio, unsigned long src_addr) return ret; } -static int mfill_copy_folio_retry(struct mfill_state *state, struct folio *folio) +static int mfill_copy_folio_retry(struct mfill_state *state, + struct folio *folio) { + const struct vm_uffd_ops *orig_ops = vma_uffd_ops(state->vma); unsigned long src_addr = state->src_addr; void *kaddr; int err; @@ -465,6 +467,14 @@ static int mfill_copy_folio_retry(struct mfill_state *state, struct folio *folio if (err) return err; + /* + * The VMA type may have changed while the lock was dropped + * (e.g. replaced with a hugetlb mapping), making the caller's + * ops pointer stale. + */ + if (vma_uffd_ops(state->vma) != orig_ops) + return -EAGAIN; + err = mfill_establish_pmd(state); if (err) return err; diff --git a/mm/util.c b/mm/util.c index 232c3930a662..3cc949a0b7ed 100644 --- a/mm/util.c +++ b/mm/util.c @@ -1232,7 +1232,7 @@ int __compat_vma_mmap(struct vm_area_desc *desc, /* Update the VMA from the descriptor. */ compat_set_vma_from_desc(vma, desc); /* Complete any specified mmap actions. */ - return mmap_action_complete(vma, &desc->action); + return mmap_action_complete(vma, &desc->action, /*is_compat=*/true); } EXPORT_SYMBOL(__compat_vma_mmap); @@ -1389,7 +1389,8 @@ static int call_vma_mapped(struct vm_area_struct *vma) } static int mmap_action_finish(struct vm_area_struct *vma, - struct mmap_action *action, int err) + struct mmap_action *action, int err, + bool is_compat) { size_t len; @@ -1400,8 +1401,12 @@ static int mmap_action_finish(struct vm_area_struct *vma, /* do_munmap() might take rmap lock, so release if held. */ maybe_rmap_unlock_action(vma, action); - if (!err) - return 0; + /* + * If this is invoked from the compatibility layer, post-mmap() hook + * logic will handle cleanup for us. + */ + if (!err || is_compat) + return err; /* * If an error occurs, unmap the VMA altogether and return an error. We @@ -1451,13 +1456,15 @@ EXPORT_SYMBOL(mmap_action_prepare); * mmap_action_complete - Execute VMA descriptor action. * @vma: The VMA to perform the action upon. * @action: The action to perform. + * @is_compat: Is this being invoked from the compatibility layer? * * Similar to mmap_action_prepare(). * - * Return: 0 on success, or error, at which point the VMA will be unmapped. + * Return: 0 on success, or error, at which point the VMA will be unmapped if + * !@is_compat. */ int mmap_action_complete(struct vm_area_struct *vma, - struct mmap_action *action) + struct mmap_action *action, bool is_compat) { int err = 0; @@ -1478,7 +1485,7 @@ int mmap_action_complete(struct vm_area_struct *vma, break; } - return mmap_action_finish(vma, action, err); + return mmap_action_finish(vma, action, err, is_compat); } EXPORT_SYMBOL(mmap_action_complete); #else @@ -1500,7 +1507,8 @@ int mmap_action_prepare(struct vm_area_desc *desc) EXPORT_SYMBOL(mmap_action_prepare); int mmap_action_complete(struct vm_area_struct *vma, - struct mmap_action *action) + struct mmap_action *action, + bool is_compat) { int err = 0; @@ -1517,7 +1525,7 @@ int mmap_action_complete(struct vm_area_struct *vma, break; } - return mmap_action_finish(vma, action, err); + return mmap_action_finish(vma, action, err, is_compat); } EXPORT_SYMBOL(mmap_action_complete); #endif @@ -2780,7 +2780,8 @@ static unsigned long __mmap_region(struct file *file, unsigned long addr, __mmap_complete(&map, vma); if (have_mmap_prepare && allocated_new) { - error = mmap_action_complete(vma, &desc.action); + error = mmap_action_complete(vma, &desc.action, + /*is_compat=*/false); if (error) return error; } diff --git a/mm/vmalloc.c b/mm/vmalloc.c index aa08651ec0df..c31a8615a832 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -4361,7 +4361,7 @@ need_realloc: return NULL; if (p) { - memcpy(n, p, old_size); + memcpy(n, p, min(size, old_size)); vfree(p); } diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index d44987d4515c..853c8d7644b5 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -330,11 +330,18 @@ static int bnep_rx_frame(struct bnep_session *s, struct sk_buff *skb) goto badframe; break; case BNEP_FILTER_MULTI_ADDR_SET: - case BNEP_FILTER_NET_TYPE_SET: - /* Pull: ctrl type (1 b), len (2 b), data (len bytes) */ - if (!skb_pull(skb, 3 + *(u16 *)(skb->data + 1) * 2)) + case BNEP_FILTER_NET_TYPE_SET: { + u8 *hdr; + + /* Pull ctrl type (1 b) + len (2 b) */ + hdr = skb_pull_data(skb, 3); + if (!hdr) + goto badframe; + /* Pull data (len bytes); length is big-endian */ + if (!skb_pull(skb, get_unaligned_be16(&hdr[1]))) goto badframe; break; + } default: kfree_skb(skb); return 0; diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 3a0592599086..17b46ad6a349 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -480,40 +480,107 @@ bool hci_setup_sync(struct hci_conn *conn, __u16 handle) return hci_setup_sync_conn(conn, handle); } -u8 hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, u16 latency, - u16 to_multiplier) +struct le_conn_update_data { + struct hci_conn *conn; + u16 min; + u16 max; + u16 latency; + u16 to_multiplier; +}; + +static int le_conn_update_sync(struct hci_dev *hdev, void *data) { - struct hci_dev *hdev = conn->hdev; + struct le_conn_update_data *d = data; + struct hci_conn *conn = d->conn; struct hci_conn_params *params; struct hci_cp_le_conn_update cp; + u16 timeout; + u8 store_hint; + int err; + /* Verify connection is still alive and read conn fields under + * the same lock to prevent a concurrent disconnect from freeing + * or reusing the connection while we build the HCI command. + */ hci_dev_lock(hdev); - params = hci_conn_params_lookup(hdev, &conn->dst, conn->dst_type); - if (params) { - params->conn_min_interval = min; - params->conn_max_interval = max; - params->conn_latency = latency; - params->supervision_timeout = to_multiplier; + if (!hci_conn_valid(hdev, conn)) { + hci_dev_unlock(hdev); + return -ECANCELED; } - hci_dev_unlock(hdev); - memset(&cp, 0, sizeof(cp)); cp.handle = cpu_to_le16(conn->handle); - cp.conn_interval_min = cpu_to_le16(min); - cp.conn_interval_max = cpu_to_le16(max); - cp.conn_latency = cpu_to_le16(latency); - cp.supervision_timeout = cpu_to_le16(to_multiplier); + cp.conn_interval_min = cpu_to_le16(d->min); + cp.conn_interval_max = cpu_to_le16(d->max); + cp.conn_latency = cpu_to_le16(d->latency); + cp.supervision_timeout = cpu_to_le16(d->to_multiplier); cp.min_ce_len = cpu_to_le16(0x0000); cp.max_ce_len = cpu_to_le16(0x0000); + timeout = conn->conn_timeout; + + hci_dev_unlock(hdev); - hci_send_cmd(hdev, HCI_OP_LE_CONN_UPDATE, sizeof(cp), &cp); + err = __hci_cmd_sync_status_sk(hdev, HCI_OP_LE_CONN_UPDATE, + sizeof(cp), &cp, + HCI_EV_LE_CONN_UPDATE_COMPLETE, + timeout, NULL); + if (err) + return err; + + /* Update stored connection parameters after the controller has + * confirmed the update via the LE Connection Update Complete event. + */ + hci_dev_lock(hdev); + + params = hci_conn_params_lookup(hdev, &conn->dst, conn->dst_type); + if (params) { + params->conn_min_interval = d->min; + params->conn_max_interval = d->max; + params->conn_latency = d->latency; + params->supervision_timeout = d->to_multiplier; + store_hint = 0x01; + } else { + store_hint = 0x00; + } - if (params) - return 0x01; + hci_dev_unlock(hdev); - return 0x00; + mgmt_new_conn_param(hdev, &conn->dst, conn->dst_type, store_hint, + d->min, d->max, d->latency, d->to_multiplier); + + return 0; +} + +static void le_conn_update_complete(struct hci_dev *hdev, void *data, int err) +{ + struct le_conn_update_data *d = data; + + hci_conn_put(d->conn); + kfree(d); +} + +void hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, u16 latency, + u16 to_multiplier) +{ + struct le_conn_update_data *d; + + d = kzalloc_obj(*d); + if (!d) + return; + + hci_conn_get(conn); + d->conn = conn; + d->min = min; + d->max = max; + d->latency = latency; + d->to_multiplier = to_multiplier; + + if (hci_cmd_sync_queue(conn->hdev, le_conn_update_sync, d, + le_conn_update_complete) < 0) { + hci_conn_put(conn); + kfree(d); + } } void hci_le_start_enc(struct hci_conn *conn, __le16 ediv, __le64 rand, @@ -2130,6 +2197,9 @@ static int create_big_sync(struct hci_dev *hdev, void *data) u32 flags = 0; int err; + if (!hci_conn_valid(hdev, conn)) + return -ECANCELED; + if (qos->bcast.out.phys == BIT(1)) flags |= MGMT_ADV_FLAG_SEC_2M; @@ -2204,11 +2274,24 @@ static void create_big_complete(struct hci_dev *hdev, void *data, int err) bt_dev_dbg(hdev, "conn %p", conn); + if (err == -ECANCELED) + goto done; + + hci_dev_lock(hdev); + + if (!hci_conn_valid(hdev, conn)) + goto unlock; + if (err) { bt_dev_err(hdev, "Unable to create BIG: %d", err); hci_connect_cfm(conn, err); hci_conn_del(conn); } + +unlock: + hci_dev_unlock(hdev); +done: + hci_conn_put(conn); } struct hci_conn *hci_bind_bis(struct hci_dev *hdev, bdaddr_t *dst, __u8 sid, @@ -2336,10 +2419,11 @@ struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst, BT_BOUND, &data); /* Queue start periodic advertising and create BIG */ - err = hci_cmd_sync_queue(hdev, create_big_sync, conn, + err = hci_cmd_sync_queue(hdev, create_big_sync, hci_conn_get(conn), create_big_complete); if (err < 0) { hci_conn_drop(conn); + hci_conn_put(conn); return ERR_PTR(err); } diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index b2ee6b6a0f56..eea2f810aafa 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -7118,9 +7118,29 @@ static void hci_le_create_big_complete_evt(struct hci_dev *hdev, void *data, continue; } + if (ev->num_bis <= i) { + bt_dev_err(hdev, + "Not enough BIS handles for BIG 0x%2.2x", + ev->handle); + ev->status = HCI_ERROR_UNSPECIFIED; + hci_connect_cfm(conn, ev->status); + hci_conn_del(conn); + continue; + } + if (hci_conn_set_handle(conn, - __le16_to_cpu(ev->bis_handle[i++]))) + __le16_to_cpu(ev->bis_handle[i++]))) { + bt_dev_err(hdev, + "Failed to set BIS handle for BIG 0x%2.2x", + ev->handle); + /* Force error so BIG gets terminated as not all BIS + * could be connected. + */ + ev->status = HCI_ERROR_UNSPECIFIED; + hci_connect_cfm(conn, ev->status); + hci_conn_del(conn); continue; + } conn->state = BT_CONNECTED; set_bit(HCI_CONN_BIG_CREATED, &conn->flags); @@ -7129,7 +7149,10 @@ static void hci_le_create_big_complete_evt(struct hci_dev *hdev, void *data, hci_iso_setup_path(conn); } - if (!ev->status && !i) + /* If there is an unexpected error or if no BISes have been connected + * for the BIG, terminate it. + */ + if (ev->status == HCI_ERROR_UNSPECIFIED || (!ev->status && !i)) /* If no BISes have been connected for the BIG, * terminate. This is in case all bound connections * have been closed before the BIG creation @@ -7168,7 +7191,7 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data, clear_bit(HCI_CONN_CREATE_BIG_SYNC, &conn->flags); conn->num_bis = 0; - memset(conn->bis, 0, sizeof(conn->num_bis)); + memset(conn->bis, 0, sizeof(conn->bis)); for (i = 0; i < ev->num_bis; i++) { u16 handle = le16_to_cpu(ev->bis[i]); diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index 7bcf8c5ceaee..976f91eeb745 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -1036,6 +1036,28 @@ static struct hidp_session *hidp_session_find(const bdaddr_t *bdaddr) } /* + * Consume session->conn: clear the member under hidp_session_sem, then + * l2cap_unregister_user() and l2cap_conn_put() the snapshot outside the + * sem. At most one caller wins; later callers see NULL and skip. The + * reference is the one hidp_session_new() took via l2cap_conn_get(). + */ +static void hidp_session_unregister_conn(struct hidp_session *session) +{ + struct l2cap_conn *conn; + + down_write(&hidp_session_sem); + conn = session->conn; + if (conn) + session->conn = NULL; + up_write(&hidp_session_sem); + + if (conn) { + l2cap_unregister_user(conn, &session->user); + l2cap_conn_put(conn); + } +} + +/* * Start session synchronously * This starts a session thread and waits until initialization * is done or returns an error if it couldn't be started. @@ -1311,8 +1333,7 @@ static int hidp_session_thread(void *arg) * Instead, this call has the same semantics as if user-space tried to * delete the session. */ - if (session->conn) - l2cap_unregister_user(session->conn, &session->user); + hidp_session_unregister_conn(session); hidp_session_put(session); @@ -1418,7 +1439,7 @@ int hidp_connection_del(struct hidp_conndel_req *req) HIDP_CTRL_VIRTUAL_CABLE_UNPLUG, NULL, 0); else - l2cap_unregister_user(session->conn, &session->user); + hidp_session_unregister_conn(session); hidp_session_put(session); diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index be145e2736b7..7cb2864fe872 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -347,6 +347,7 @@ static int iso_connect_bis(struct sock *sk) return -EHOSTUNREACH; hci_dev_lock(hdev); + lock_sock(sk); if (!bis_capable(hdev)) { err = -EOPNOTSUPP; @@ -399,13 +400,9 @@ static int iso_connect_bis(struct sock *sk) goto unlock; } - lock_sock(sk); - err = iso_chan_add(conn, sk, NULL); - if (err) { - release_sock(sk); + if (err) goto unlock; - } /* Update source addr of the socket */ bacpy(&iso_pi(sk)->src, &hcon->src); @@ -421,9 +418,8 @@ static int iso_connect_bis(struct sock *sk) iso_sock_set_timer(sk, READ_ONCE(sk->sk_sndtimeo)); } - release_sock(sk); - unlock: + release_sock(sk); hci_dev_unlock(hdev); hci_dev_put(hdev); return err; @@ -444,6 +440,7 @@ static int iso_connect_cis(struct sock *sk) return -EHOSTUNREACH; hci_dev_lock(hdev); + lock_sock(sk); if (!cis_central_capable(hdev)) { err = -EOPNOTSUPP; @@ -498,13 +495,9 @@ static int iso_connect_cis(struct sock *sk) goto unlock; } - lock_sock(sk); - err = iso_chan_add(conn, sk, NULL); - if (err) { - release_sock(sk); + if (err) goto unlock; - } /* Update source addr of the socket */ bacpy(&iso_pi(sk)->src, &hcon->src); @@ -520,9 +513,8 @@ static int iso_connect_cis(struct sock *sk) iso_sock_set_timer(sk, READ_ONCE(sk->sk_sndtimeo)); } - release_sock(sk); - unlock: + release_sock(sk); hci_dev_unlock(hdev); hci_dev_put(hdev); return err; @@ -1193,7 +1185,7 @@ static int iso_sock_connect(struct socket *sock, struct sockaddr_unsized *addr, release_sock(sk); - if (bacmp(&iso_pi(sk)->dst, BDADDR_ANY)) + if (bacmp(&sa->iso_bdaddr, BDADDR_ANY)) err = iso_connect_cis(sk); else err = iso_connect_bis(sk); @@ -2256,8 +2248,10 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) sk = iso_get_sock(hdev, &hdev->bdaddr, bdaddr, BT_LISTEN, iso_match_sid, ev1); if (sk && !ev1->status) { + lock_sock(sk); iso_pi(sk)->sync_handle = le16_to_cpu(ev1->handle); iso_pi(sk)->bc_sid = ev1->sid; + release_sock(sk); } goto done; @@ -2268,8 +2262,10 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) sk = iso_get_sock(hdev, &hdev->bdaddr, bdaddr, BT_LISTEN, iso_match_sid_past, ev1a); if (sk && !ev1a->status) { + lock_sock(sk); iso_pi(sk)->sync_handle = le16_to_cpu(ev1a->sync_handle); iso_pi(sk)->bc_sid = ev1a->sid; + release_sock(sk); } goto done; @@ -2296,27 +2292,35 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) ev2); if (sk) { - int err; - struct hci_conn *hcon = iso_pi(sk)->conn->hcon; + int err = 0; + bool big_sync; + struct hci_conn *hcon; + lock_sock(sk); + + hcon = iso_pi(sk)->conn->hcon; iso_pi(sk)->qos.bcast.encryption = ev2->encryption; if (ev2->num_bis < iso_pi(sk)->bc_num_bis) iso_pi(sk)->bc_num_bis = ev2->num_bis; - if (!test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags) && - !test_and_set_bit(BT_SK_BIG_SYNC, &iso_pi(sk)->flags)) { + big_sync = !test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags) && + !test_and_set_bit(BT_SK_BIG_SYNC, &iso_pi(sk)->flags); + + if (big_sync) err = hci_conn_big_create_sync(hdev, hcon, &iso_pi(sk)->qos, iso_pi(sk)->sync_handle, iso_pi(sk)->bc_num_bis, iso_pi(sk)->bc_bis); - if (err) { - bt_dev_err(hdev, "hci_le_big_create_sync: %d", - err); - sock_put(sk); - sk = NULL; - } + + release_sock(sk); + + if (big_sync && err) { + bt_dev_err(hdev, "hci_le_big_create_sync: %d", + err); + sock_put(sk); + sk = NULL; } } @@ -2370,8 +2374,10 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) if (!base || base_len > BASE_MAX_LENGTH) goto done; + lock_sock(sk); memcpy(iso_pi(sk)->base, base, base_len); iso_pi(sk)->base_len = base_len; + release_sock(sk); } else { /* This is a PA data fragment. Keep pa_data_len set to 0 * until all data has been reassembled. diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 77dec104a9c3..7701528f1167 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -4706,16 +4706,8 @@ static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn, l2cap_send_cmd(conn, cmd->ident, L2CAP_CONN_PARAM_UPDATE_RSP, sizeof(rsp), &rsp); - if (!err) { - u8 store_hint; - - store_hint = hci_le_conn_update(hcon, min, max, latency, - to_multiplier); - mgmt_new_conn_param(hcon->hdev, &hcon->dst, hcon->dst_type, - store_hint, min, max, latency, - to_multiplier); - - } + if (!err) + hci_le_conn_update(hcon, min, max, latency, to_multiplier); return 0; } @@ -5428,7 +5420,7 @@ static inline int l2cap_ecred_reconf_req(struct l2cap_conn *conn, * configured, the MPS field may be less than the current MPS * of that channel. */ - if (chan[i]->remote_mps >= mps && i) { + if (chan[i]->remote_mps > mps && num_scid > 1) { BT_ERR("chan %p decreased MPS %u -> %u", chan[i], chan[i]->remote_mps, mps); result = L2CAP_RECONF_INVALID_MPS; diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 71e8c1b45bce..cf590a67d364 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1498,6 +1498,9 @@ static struct l2cap_chan *l2cap_sock_new_connection_cb(struct l2cap_chan *chan) { struct sock *sk, *parent = chan->data; + if (!parent) + return NULL; + lock_sock(parent); /* Check for backlog size */ @@ -1657,6 +1660,9 @@ static void l2cap_sock_state_change_cb(struct l2cap_chan *chan, int state, { struct sock *sk = chan->data; + if (!sk) + return; + sk->sk_state = state; if (err) @@ -1758,6 +1764,9 @@ static long l2cap_sock_get_sndtimeo_cb(struct l2cap_chan *chan) { struct sock *sk = chan->data; + if (!sk) + return 0; + return READ_ONCE(sk->sk_sndtimeo); } diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 611a9a94151e..d11bd5337d57 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -1715,9 +1715,12 @@ static int rfcomm_recv_data(struct rfcomm_session *s, u8 dlci, int pf, struct sk } if (pf && d->cfc) { - u8 credits = *(u8 *) skb->data; skb_pull(skb, 1); + u8 *credits = skb_pull_data(skb, 1); - d->tx_credits += credits; + if (!credits) + goto drop; + + d->tx_credits += *credits; if (d->tx_credits) clear_bit(RFCOMM_TX_THROTTLED, &d->flags); } diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 18826d4b9c0b..eba44525d41d 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -472,9 +472,13 @@ static struct sock *sco_get_sock_listen(bdaddr_t *src) sk1 = sk; } + sk = sk ? sk : sk1; + if (sk) + sock_hold(sk); + read_unlock(&sco_sk_list.lock); - return sk ? sk : sk1; + return sk; } static void sco_sock_destruct(struct sock *sk) @@ -515,11 +519,13 @@ static void sco_sock_kill(struct sock *sk) BT_DBG("sk %p state %d", sk, sk->sk_state); /* Sock is dead, so set conn->sk to NULL to avoid possible UAF */ + lock_sock(sk); if (sco_pi(sk)->conn) { sco_conn_lock(sco_pi(sk)->conn); sco_pi(sk)->conn->sk = NULL; sco_conn_unlock(sco_pi(sk)->conn); } + release_sock(sk); /* Kill poor orphan */ bt_sock_unlink(&sco_sk_list, sk); @@ -1365,40 +1371,51 @@ static int sco_sock_release(struct socket *sock) static void sco_conn_ready(struct sco_conn *conn) { - struct sock *parent; - struct sock *sk = conn->sk; + struct sock *parent, *sk; + + sco_conn_lock(conn); + sk = sco_sock_hold(conn); + sco_conn_unlock(conn); BT_DBG("conn %p", conn); if (sk) { lock_sock(sk); - sco_sock_clear_timer(sk); - sk->sk_state = BT_CONNECTED; - sk->sk_state_change(sk); + + /* conn->sk may have become NULL if racing with sk close, but + * due to held hdev->lock, it can't become different sk. + */ + if (conn->sk) { + sco_sock_clear_timer(sk); + sk->sk_state = BT_CONNECTED; + sk->sk_state_change(sk); + } + release_sock(sk); + sock_put(sk); } else { - sco_conn_lock(conn); - - if (!conn->hcon) { - sco_conn_unlock(conn); + if (!conn->hcon) return; - } + + lockdep_assert_held(&conn->hcon->hdev->lock); parent = sco_get_sock_listen(&conn->hcon->src); - if (!parent) { - sco_conn_unlock(conn); + if (!parent) return; - } lock_sock(parent); + sco_conn_lock(conn); + + /* hdev->lock guarantees conn->sk == NULL still here */ + + if (parent->sk_state != BT_LISTEN) + goto release; + sk = sco_sock_alloc(sock_net(parent), NULL, BTPROTO_SCO, GFP_ATOMIC, 0); - if (!sk) { - release_sock(parent); - sco_conn_unlock(conn); - return; - } + if (!sk) + goto release; sco_sock_init(sk, parent); @@ -1417,9 +1434,10 @@ static void sco_conn_ready(struct sco_conn *conn) /* Wake up parent */ parent->sk_data_ready(parent); - release_sock(parent); - +release: sco_conn_unlock(conn); + release_sock(parent); + sock_put(parent); } } diff --git a/net/core/dev.c b/net/core/dev.c index 06c195906231..8bfa8313ef62 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -371,7 +371,7 @@ static void netdev_name_node_alt_free(struct rcu_head *head) static void __netdev_name_node_alt_destroy(struct netdev_name_node *name_node) { netdev_name_node_del(name_node); - list_del(&name_node->list); + list_del_rcu(&name_node->list); call_rcu(&name_node->rcu, netdev_name_node_alt_free); } diff --git a/net/core/devmem.c b/net/core/devmem.c index cde4c89bc146..468344739db2 100644 --- a/net/core/devmem.c +++ b/net/core/devmem.c @@ -297,8 +297,7 @@ net_devmem_bind_dmabuf(struct net_device *dev, for (i = 0; i < owner->area.num_niovs; i++) { niov = &owner->area.niovs[i]; - niov->type = NET_IOV_DMABUF; - niov->owner = &owner->area; + net_iov_init(niov, &owner->area, NET_IOV_DMABUF); page_pool_set_dma_addr_netmem(net_iov_to_netmem(niov), net_devmem_get_dma_addr(niov)); if (direction == DMA_TO_DEVICE) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 9e12524b67fa..5d9216016507 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -3210,8 +3210,10 @@ int neigh_xmit(int index, struct net_device *dev, rcu_read_lock(); tbl = rcu_dereference(neigh_tables[index]); - if (!tbl) - goto out_unlock; + if (!tbl) { + rcu_read_unlock(); + goto out_kfree_skb; + } if (index == NEIGH_ARP_TABLE) { u32 key = *((u32 *)addr); @@ -3227,7 +3229,6 @@ int neigh_xmit(int index, struct net_device *dev, goto out_kfree_skb; } err = READ_ONCE(neigh->output)(neigh, skb); -out_unlock: rcu_read_unlock(); } else if (index == NEIGH_LINK_TABLE) { @@ -3237,11 +3238,10 @@ out_unlock: goto out_kfree_skb; err = dev_queue_xmit(skb); } -out: return err; out_kfree_skb: kfree_skb(skb); - goto out; + return err; } EXPORT_SYMBOL(neigh_xmit); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index cd74beffd209..84faace50ac2 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -608,14 +608,16 @@ EXPORT_SYMBOL_GPL(__netpoll_setup); /* * Returns a pointer to a string representation of the identifier used * to select the egress interface for the given netpoll instance. buf - * must be a buffer of length at least MAC_ADDR_STR_LEN + 1. + * is used to format np->dev_mac when np->dev_name is empty; bufsz must + * be at least MAC_ADDR_STR_LEN + 1 to fit the formatted MAC address + * and its NUL terminator. */ -static char *egress_dev(struct netpoll *np, char *buf) +static char *egress_dev(struct netpoll *np, char *buf, size_t bufsz) { if (np->dev_name[0]) return np->dev_name; - snprintf(buf, MAC_ADDR_STR_LEN, "%pM", np->dev_mac); + snprintf(buf, bufsz, "%pM", np->dev_mac); return buf; } @@ -645,7 +647,7 @@ static int netpoll_take_ipv6(struct netpoll *np, struct net_device *ndev) if (!IS_ENABLED(CONFIG_IPV6)) { np_err(np, "IPv6 is not supported %s, aborting\n", - egress_dev(np, buf)); + egress_dev(np, buf, sizeof(buf))); return -EINVAL; } @@ -667,7 +669,7 @@ static int netpoll_take_ipv6(struct netpoll *np, struct net_device *ndev) } if (err) { np_err(np, "no IPv6 address for %s, aborting\n", - egress_dev(np, buf)); + egress_dev(np, buf, sizeof(buf))); return err; } @@ -687,14 +689,14 @@ static int netpoll_take_ipv4(struct netpoll *np, struct net_device *ndev) in_dev = __in_dev_get_rtnl(ndev); if (!in_dev) { np_err(np, "no IP address for %s, aborting\n", - egress_dev(np, buf)); + egress_dev(np, buf, sizeof(buf))); return -EDESTADDRREQ; } ifa = rtnl_dereference(in_dev->ifa_list); if (!ifa) { np_err(np, "no IP address for %s, aborting\n", - egress_dev(np, buf)); + egress_dev(np, buf, sizeof(buf))); return -EDESTADDRREQ; } @@ -704,6 +706,23 @@ static int netpoll_take_ipv4(struct netpoll *np, struct net_device *ndev) return 0; } +/* + * Test whether the caller left np->local_ip unset, so that + * netpoll_setup() should auto-populate it from the egress device. + * + * np->local_ip is a union of __be32 (IPv4) and struct in6_addr (IPv6), + * so an IPv6 address whose first 4 bytes are zero (e.g. ::1, ::2, + * IPv4-mapped ::ffff:a.b.c.d) must not be tested via the IPv4 arm — + * doing so would misclassify a caller-supplied address as unset and + * silently overwrite it with whatever address the device exposes. + */ +static bool netpoll_local_ip_unset(const struct netpoll *np) +{ + if (np->ipv6) + return ipv6_addr_any(&np->local_ip.in6); + return !np->local_ip.ip; +} + int netpoll_setup(struct netpoll *np) { struct net *net = current->nsproxy->net_ns; @@ -719,7 +738,8 @@ int netpoll_setup(struct netpoll *np) ndev = dev_getbyhwaddr(net, ARPHRD_ETHER, np->dev_mac); if (!ndev) { - np_err(np, "%s doesn't exist, aborting\n", egress_dev(np, buf)); + np_err(np, "%s doesn't exist, aborting\n", + egress_dev(np, buf, sizeof(buf))); err = -ENODEV; goto unlock; } @@ -727,14 +747,14 @@ int netpoll_setup(struct netpoll *np) if (netdev_master_upper_dev_get(ndev)) { np_err(np, "%s is a slave device, aborting\n", - egress_dev(np, buf)); + egress_dev(np, buf, sizeof(buf))); err = -EBUSY; goto put; } if (!netif_running(ndev)) { np_info(np, "device %s not up yet, forcing it\n", - egress_dev(np, buf)); + egress_dev(np, buf, sizeof(buf))); err = dev_open(ndev, NULL); if (err) { @@ -747,7 +767,7 @@ int netpoll_setup(struct netpoll *np) rtnl_lock(); } - if (!np->local_ip.ip) { + if (netpoll_local_ip_unset(np)) { if (!np->ipv6) { err = netpoll_take_ipv4(np, ndev); if (err) diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 877bbf7a1938..6e576dec80db 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -327,6 +327,11 @@ static void page_pool_uninit(struct page_pool *pool) if (!pool->system) free_percpu(pool->recycle_stats); #endif + + if (pool->mp_ops) { + pool->mp_ops->destroy(pool); + static_branch_dec(&page_pool_mem_providers); + } } /** @@ -1146,11 +1151,6 @@ static void __page_pool_destroy(struct page_pool *pool) page_pool_unlist(pool); page_pool_uninit(pool); - if (pool->mp_ops) { - pool->mp_ops->destroy(pool); - static_branch_dec(&page_pool_mem_providers); - } - kfree(pool); } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index b613bb6e07df..df042da422ef 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1572,6 +1572,7 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, port_guid.vf = ivi.vf; memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac)); + memset(&vf_broadcast, 0, sizeof(vf_broadcast)); memcpy(vf_broadcast.broadcast, dev->broadcast, dev->addr_len); vf_vlan.vlan = ivi.vlan; vf_vlan.qos = ivi.qos; diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index 5fb812443a08..4366cbac3f06 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -124,9 +124,14 @@ static void ah_output_done(void *data, int err) struct iphdr *top_iph = ip_hdr(skb); struct ip_auth_hdr *ah = ip_auth_hdr(skb); int ihl = ip_hdrlen(skb); + int seqhi_len = 0; + __be32 *seqhi; + if (x->props.flags & XFRM_STATE_ESN) + seqhi_len = sizeof(*seqhi); iph = AH_SKB_CB(skb)->tmp; - icv = ah_tmp_icv(iph, ihl); + seqhi = (__be32 *)((char *)iph + ihl); + icv = ah_tmp_icv(seqhi, seqhi_len); memcpy(ah->auth_data, icv, ahp->icv_trunc_len); top_iph->tos = iph->tos; @@ -270,12 +275,17 @@ static void ah_input_done(void *data, int err) struct ip_auth_hdr *ah = ip_auth_hdr(skb); int ihl = ip_hdrlen(skb); int ah_hlen = (ah->hdrlen + 2) << 2; + int seqhi_len = 0; + __be32 *seqhi; if (err) goto out; + if (x->props.flags & XFRM_STATE_ESN) + seqhi_len = sizeof(*seqhi); work_iph = AH_SKB_CB(skb)->tmp; - auth_data = ah_tmp_auth(work_iph, ihl); + seqhi = (__be32 *)((char *)work_iph + ihl); + auth_data = ah_tmp_auth(seqhi, seqhi_len); icv = ah_tmp_icv(auth_data, ahp->icv_trunc_len); err = crypto_memneq(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG : 0; diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 6dfc0bcdef65..6a5febbdbee4 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -873,7 +873,8 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb) nfrags = 1; goto skip_cow; - } else if (!skb_has_frag_list(skb)) { + } else if (!skb_has_frag_list(skb) && + !skb_has_shared_frag(skb)) { nfrags = skb_shinfo(skb)->nr_frags; nfrags++; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index a674fb44ec25..a9ad39064f3b 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -122,16 +122,29 @@ * contradict to specs provided this delay is small enough. */ -#define IGMP_V1_SEEN(in_dev) \ - (IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), FORCE_IGMP_VERSION) == 1 || \ - IN_DEV_CONF_GET((in_dev), FORCE_IGMP_VERSION) == 1 || \ - ((in_dev)->mr_v1_seen && \ - time_before(jiffies, (in_dev)->mr_v1_seen))) -#define IGMP_V2_SEEN(in_dev) \ - (IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), FORCE_IGMP_VERSION) == 2 || \ - IN_DEV_CONF_GET((in_dev), FORCE_IGMP_VERSION) == 2 || \ - ((in_dev)->mr_v2_seen && \ - time_before(jiffies, (in_dev)->mr_v2_seen))) +static bool IGMP_V1_SEEN(const struct in_device *in_dev) +{ + unsigned long seen; + + if (IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), FORCE_IGMP_VERSION) == 1) + return true; + if (IN_DEV_CONF_GET((in_dev), FORCE_IGMP_VERSION) == 1) + return true; + seen = READ_ONCE(in_dev->mr_v1_seen); + return seen && time_before(jiffies, seen); +} + +static bool IGMP_V2_SEEN(const struct in_device *in_dev) +{ + unsigned long seen; + + if (IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), FORCE_IGMP_VERSION) == 2) + return true; + if (IN_DEV_CONF_GET((in_dev), FORCE_IGMP_VERSION) == 2) + return true; + seen = READ_ONCE(in_dev->mr_v2_seen); + return seen && time_before(jiffies, seen); +} static int unsolicited_report_interval(struct in_device *in_dev) { @@ -954,23 +967,21 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, int max_delay; int mark = 0; struct net *net = dev_net(in_dev->dev); - + unsigned long seen; if (len == 8) { + seen = jiffies + READ_ONCE(in_dev->mr_qrv) * READ_ONCE(in_dev->mr_qi) + + READ_ONCE(in_dev->mr_qri); if (ih->code == 0) { /* Alas, old v1 router presents here. */ max_delay = IGMP_QUERY_RESPONSE_INTERVAL; - in_dev->mr_v1_seen = jiffies + - (in_dev->mr_qrv * in_dev->mr_qi) + - in_dev->mr_qri; + WRITE_ONCE(in_dev->mr_v1_seen, seen); group = 0; } else { /* v2 router present */ max_delay = ih->code*(HZ/IGMP_TIMER_SCALE); - in_dev->mr_v2_seen = jiffies + - (in_dev->mr_qrv * in_dev->mr_qi) + - in_dev->mr_qri; + WRITE_ONCE(in_dev->mr_v2_seen, seen); } /* cancel the interface change timer */ WRITE_ONCE(in_dev->mr_ifc_count, 0); @@ -995,6 +1006,8 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, if (!max_delay) max_delay = 1; /* can't mod w/ 0 */ } else { /* v3 */ + unsigned long mr_qi; + if (!pskb_may_pull(skb, sizeof(struct igmpv3_query))) return true; @@ -1015,15 +1028,16 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, * received value was zero, use the default or statically * configured value. */ - in_dev->mr_qrv = ih3->qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); - in_dev->mr_qi = IGMPV3_QQIC(ih3->qqic)*HZ ?: IGMP_QUERY_INTERVAL; - + WRITE_ONCE(in_dev->mr_qrv, + ih3->qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv)); + mr_qi = IGMPV3_QQIC(ih3->qqic)*HZ ?: IGMP_QUERY_INTERVAL; + WRITE_ONCE(in_dev->mr_qi, mr_qi); /* RFC3376, 8.3. Query Response Interval: * The number of seconds represented by the [Query Response * Interval] must be less than the [Query Interval]. */ - if (in_dev->mr_qri >= in_dev->mr_qi) - in_dev->mr_qri = (in_dev->mr_qi/HZ - 1)*HZ; + if (READ_ONCE(in_dev->mr_qri) >= mr_qi) + WRITE_ONCE(in_dev->mr_qri, (mr_qi/HZ - 1) * HZ); if (!group) { /* general query */ if (ih3->nsrcs) diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index d8083b9033c2..5b957a831e7c 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -179,7 +179,8 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base, seq = read_seqbegin(&base->lock); p = lookup(daddr, base, seq, NULL, &gc_cnt, &parent, &pp); - if (p) + /* Make sure tree was not modified during our lookup. */ + if (p && !read_seqretry(&base->lock, seq)) return p; /* retry an exact lookup, taking the lock before. diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index e4790cc7b5c2..5bcd73cbdb41 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1233,6 +1233,8 @@ alloc_new_skb: if (err < 0) goto error; copy = err; + if (!(flags & MSG_NO_SHARED_FRAGS)) + skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG; wmem_alloc_delta += copy; } else if (!zc) { int i = skb_shinfo(skb)->nr_frags; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 8a08d09b4c30..2628cd3a93a6 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -151,16 +151,6 @@ static struct mr_table *__ipmr_get_table(struct net *net, u32 id) return NULL; } -static struct mr_table *ipmr_get_table(struct net *net, u32 id) -{ - struct mr_table *mrt; - - rcu_read_lock(); - mrt = __ipmr_get_table(net, id); - rcu_read_unlock(); - return mrt; -} - static int ipmr_fib_lookup(struct net *net, struct flowi4 *flp4, struct mr_table **mrt) { @@ -293,7 +283,7 @@ static void __net_exit ipmr_rules_exit_rtnl(struct net *net, struct mr_table *mrt, *next; list_for_each_entry_safe(mrt, next, &net->ipv4.mr_tables, list) { - list_del(&mrt->list); + list_del_rcu(&mrt->list); ipmr_free_table(mrt, dev_kill_list); } } @@ -315,28 +305,30 @@ bool ipmr_rule_default(const struct fib_rule *rule) } EXPORT_SYMBOL(ipmr_rule_default); #else -#define ipmr_for_each_table(mrt, net) \ - for (mrt = net->ipv4.mrt; mrt; mrt = NULL) - static struct mr_table *ipmr_mr_table_iter(struct net *net, struct mr_table *mrt) { if (!mrt) - return net->ipv4.mrt; + return rcu_dereference(net->ipv4.mrt); return NULL; } -static struct mr_table *ipmr_get_table(struct net *net, u32 id) +static struct mr_table *__ipmr_get_table(struct net *net, u32 id) { - return net->ipv4.mrt; + return rcu_dereference_check(net->ipv4.mrt, + lockdep_rtnl_is_held() || + !rcu_access_pointer(net->ipv4.mrt)); } -#define __ipmr_get_table ipmr_get_table +#define ipmr_for_each_table(mrt, net) \ + for (mrt = __ipmr_get_table(net, 0); mrt; mrt = NULL) static int ipmr_fib_lookup(struct net *net, struct flowi4 *flp4, struct mr_table **mrt) { - *mrt = net->ipv4.mrt; + *mrt = rcu_dereference(net->ipv4.mrt); + if (!*mrt) + return -EAGAIN; return 0; } @@ -347,7 +339,8 @@ static int __net_init ipmr_rules_init(struct net *net) mrt = ipmr_new_table(net, RT_TABLE_DEFAULT); if (IS_ERR(mrt)) return PTR_ERR(mrt); - net->ipv4.mrt = mrt; + + rcu_assign_pointer(net->ipv4.mrt, mrt); return 0; } @@ -358,9 +351,10 @@ static void __net_exit ipmr_rules_exit(struct net *net) static void __net_exit ipmr_rules_exit_rtnl(struct net *net, struct list_head *dev_kill_list) { - ipmr_free_table(net->ipv4.mrt, dev_kill_list); + struct mr_table *mrt = rcu_dereference_protected(net->ipv4.mrt, 1); - net->ipv4.mrt = NULL; + RCU_INIT_POINTER(net->ipv4.mrt, NULL); + ipmr_free_table(mrt, dev_kill_list); } static int ipmr_rules_dump(struct net *net, struct notifier_block *nb, @@ -381,6 +375,17 @@ bool ipmr_rule_default(const struct fib_rule *rule) EXPORT_SYMBOL(ipmr_rule_default); #endif +static struct mr_table *ipmr_get_table(struct net *net, u32 id) +{ + struct mr_table *mrt; + + rcu_read_lock(); + mrt = __ipmr_get_table(net, id); + rcu_read_unlock(); + + return mrt; +} + static inline int ipmr_hash_cmp(struct rhashtable_compare_arg *arg, const void *ptr) { @@ -441,12 +446,11 @@ static void ipmr_free_table(struct mr_table *mrt, struct list_head *dev_kill_lis WARN_ON_ONCE(!mr_can_free_table(net)); - timer_shutdown_sync(&mrt->ipmr_expire_timer); mroute_clean_tables(mrt, MRT_FLUSH_VIFS | MRT_FLUSH_VIFS_STATIC | MRT_FLUSH_MFC | MRT_FLUSH_MFC_STATIC, &ipmr_dev_kill_list); - rhltable_destroy(&mrt->mfc_hash); - kfree(mrt); + timer_shutdown_sync(&mrt->ipmr_expire_timer); + mr_table_free(mrt); WARN_ON_ONCE(!net_initialized(net) && !list_empty(&ipmr_dev_kill_list)); list_splice(&ipmr_dev_kill_list, dev_kill_list); @@ -533,15 +537,16 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) }; int err; + rcu_read_lock(); err = ipmr_fib_lookup(net, &fl4, &mrt); if (err < 0) { + rcu_read_unlock(); kfree_skb(skb); return err; } DEV_STATS_ADD(dev, tx_bytes, skb->len); DEV_STATS_INC(dev, tx_packets); - rcu_read_lock(); /* Pairs with WRITE_ONCE() in vif_add() and vif_delete() */ ipmr_cache_report(mrt, skb, READ_ONCE(mrt->mroute_reg_vif_num), @@ -1108,11 +1113,12 @@ static int ipmr_cache_report(const struct mr_table *mrt, msg->im_vif_hi = vifi >> 8; ipv4_pktinfo_prepare(mroute_sk, pkt, false); memcpy(skb->cb, pkt->cb, sizeof(skb->cb)); - /* Add our header */ - igmp = skb_put(skb, sizeof(struct igmphdr)); + /* Add our header. + * Note that code, csum and group fields are cleared. + */ + igmp = skb_put_zero(skb, sizeof(struct igmphdr)); igmp->type = assert; msg->im_msgtype = assert; - igmp->code = 0; ip_hdr(skb)->tot_len = htons(skb->len); /* Fix the length */ skb->transport_header = skb->network_header; } @@ -1135,12 +1141,19 @@ static int ipmr_cache_report(const struct mr_table *mrt, static int ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, struct sk_buff *skb, struct net_device *dev) { + struct net *net = read_pnet(&mrt->net); const struct iphdr *iph = ip_hdr(skb); - struct mfc_cache *c; + struct mfc_cache *c = NULL; bool found = false; int err; spin_lock_bh(&mfc_unres_lock); + + if (!check_net(net)) { + err = -EINVAL; + goto err; + } + list_for_each_entry(c, &mrt->mfc_unres_queue, _c.list) { if (c->mfc_mcastgrp == iph->daddr && c->mfc_origin == iph->saddr) { @@ -1153,10 +1166,8 @@ static int ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, /* Create a new entry if allowable */ c = ipmr_cache_alloc_unres(); if (!c) { - spin_unlock_bh(&mfc_unres_lock); - - kfree_skb(skb); - return -ENOBUFS; + err = -ENOBUFS; + goto err; } /* Fill in the new cache entry */ @@ -1166,17 +1177,8 @@ static int ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, /* Reflect first query at mrouted. */ err = ipmr_cache_report(mrt, skb, vifi, IGMPMSG_NOCACHE); - - if (err < 0) { - /* If the report failed throw the cache entry - out - Brad Parker - */ - spin_unlock_bh(&mfc_unres_lock); - - ipmr_cache_free(c); - kfree_skb(skb); - return err; - } + if (err < 0) + goto err; atomic_inc(&mrt->cache_resolve_queue_len); list_add(&c->_c.list, &mrt->mfc_unres_queue); @@ -1189,18 +1191,26 @@ static int ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, /* See if we can append the packet */ if (c->_c.mfc_un.unres.unresolved.qlen > 3) { - kfree_skb(skb); + c = NULL; err = -ENOBUFS; - } else { - if (dev) { - skb->dev = dev; - skb->skb_iif = dev->ifindex; - } - skb_queue_tail(&c->_c.mfc_un.unres.unresolved, skb); - err = 0; + goto err; } + if (dev) { + skb->dev = dev; + skb->skb_iif = dev->ifindex; + } + + skb_queue_tail(&c->_c.mfc_un.unres.unresolved, skb); + spin_unlock_bh(&mfc_unres_lock); + return 0; + +err: + spin_unlock_bh(&mfc_unres_lock); + if (c) + ipmr_cache_free(c); + kfree_skb(skb); return err; } @@ -1346,7 +1356,7 @@ static void mroute_clean_tables(struct mr_table *mrt, int flags, } if (flags & MRT_FLUSH_MFC) { - if (atomic_read(&mrt->cache_resolve_queue_len) != 0) { + if (atomic_read(&mrt->cache_resolve_queue_len) != 0 || !check_net(net)) { spin_lock_bh(&mfc_unres_lock); list_for_each_entry_safe(c, tmp, &mrt->mfc_unres_queue, list) { list_del(&c->list); diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c index 37a3c144276c..3930d612c3de 100644 --- a/net/ipv4/ipmr_base.c +++ b/net/ipv4/ipmr_base.c @@ -28,6 +28,20 @@ void vif_device_init(struct vif_device *v, v->link = dev->ifindex; } +static void __mr_free_table(struct work_struct *work) +{ + struct mr_table *mrt = container_of(to_rcu_work(work), + struct mr_table, work); + + rhltable_destroy(&mrt->mfc_hash); + kfree(mrt); +} + +void mr_table_free(struct mr_table *mrt) +{ + queue_rcu_work(system_unbound_wq, &mrt->work); +} + struct mr_table * mr_table_alloc(struct net *net, u32 id, struct mr_table_ops *ops, @@ -50,6 +64,8 @@ mr_table_alloc(struct net *net, u32 id, kfree(mrt); return ERR_PTR(err); } + + INIT_RCU_WORK(&mrt->work, __mr_free_table); INIT_LIST_HEAD(&mrt->mfc_cache_list); INIT_LIST_HEAD(&mrt->mfc_unres_queue); diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 1cdd9c28ab2d..97ead883e4a1 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -110,13 +110,25 @@ static inline int arp_packet_match(const struct arphdr *arphdr, arpptr += dev->addr_len; memcpy(&src_ipaddr, arpptr, sizeof(u32)); arpptr += sizeof(u32); - tgt_devaddr = arpptr; - arpptr += dev->addr_len; + + if (IS_ENABLED(CONFIG_FIREWIRE_NET) && dev->type == ARPHRD_IEEE1394) { + if (unlikely(memchr_inv(arpinfo->tgt_devaddr.mask, 0, + sizeof(arpinfo->tgt_devaddr.mask)))) + return 0; + + tgt_devaddr = NULL; + } else { + tgt_devaddr = arpptr; + arpptr += dev->addr_len; + } memcpy(&tgt_ipaddr, arpptr, sizeof(u32)); if (NF_INVF(arpinfo, ARPT_INV_SRCDEVADDR, arp_devaddr_compare(&arpinfo->src_devaddr, src_devaddr, - dev->addr_len)) || + dev->addr_len))) + return 0; + + if (tgt_devaddr && NF_INVF(arpinfo, ARPT_INV_TGTDEVADDR, arp_devaddr_compare(&arpinfo->tgt_devaddr, tgt_devaddr, dev->addr_len))) diff --git a/net/ipv4/netfilter/arpt_mangle.c b/net/ipv4/netfilter/arpt_mangle.c index a4e07e5e9c11..f65dd339208e 100644 --- a/net/ipv4/netfilter/arpt_mangle.c +++ b/net/ipv4/netfilter/arpt_mangle.c @@ -40,6 +40,10 @@ target(struct sk_buff *skb, const struct xt_action_param *par) } arpptr += pln; if (mangle->flags & ARPT_MANGLE_TDEV) { + if (unlikely(IS_ENABLED(CONFIG_FIREWIRE_NET) && + skb->dev->type == ARPHRD_IEEE1394)) + return NF_DROP; + if (ARPT_DEV_ADDR_LEN_MAX < hln || (arpptr + hln > skb_tail_pointer(skb))) return NF_DROP; @@ -47,6 +51,10 @@ target(struct sk_buff *skb, const struct xt_action_param *par) } arpptr += hln; if (mangle->flags & ARPT_MANGLE_TIP) { + if (unlikely(IS_ENABLED(CONFIG_FIREWIRE_NET) && + skb->dev->type == ARPHRD_IEEE1394)) + return NF_DROP; + if (ARPT_MANGLE_ADDR_LEN_MAX < pln || (arpptr + pln > skb_tail_pointer(skb))) return NF_DROP; diff --git a/net/ipv4/netfilter/nf_socket_ipv4.c b/net/ipv4/netfilter/nf_socket_ipv4.c index 5080fa5fbf6a..f9c6755f5ec5 100644 --- a/net/ipv4/netfilter/nf_socket_ipv4.c +++ b/net/ipv4/netfilter/nf_socket_ipv4.c @@ -94,6 +94,9 @@ struct sock *nf_sk_lookup_slow_v4(struct net *net, const struct sk_buff *skb, #endif int doff = 0; + if (ntohs(iph->frag_off) & IP_OFFSET) + return NULL; + if (iph->protocol == IPPROTO_UDP || iph->protocol == IPPROTO_TCP) { struct tcphdr _hdr; struct udphdr *hp; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 8fc24c3743c5..c0526cc03980 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1827,7 +1827,6 @@ INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *, int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) { enum skb_drop_reason reason; - struct sock *rsk; reason = psp_sk_rx_policy_check(sk, skb); if (reason) @@ -1863,24 +1862,21 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) return 0; if (nsk != sk) { reason = tcp_child_process(sk, nsk, skb); - if (reason) { - rsk = nsk; + sock_put(nsk); + if (reason) goto reset; - } return 0; } } else sock_rps_save_rxhash(sk, skb); reason = tcp_rcv_state_process(sk, skb); - if (reason) { - rsk = sk; + if (reason) goto reset; - } return 0; reset: - tcp_v4_send_reset(rsk, skb, sk_rst_convert_drop_reason(reason)); + tcp_v4_send_reset(sk, skb, sk_rst_convert_drop_reason(reason)); discard: sk_skb_reason_drop(sk, skb, reason); /* Be careful here. If this function gets more complicated and @@ -2193,8 +2189,10 @@ lookup: rst_reason = sk_rst_convert_drop_reason(drop_reason); tcp_v4_send_reset(nsk, skb, rst_reason); + sock_put(nsk); goto discard_and_relse; } + sock_put(nsk); sock_put(sk); return 0; } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 199f0b579e89..e6092c3ac840 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -1012,6 +1012,6 @@ enum skb_drop_reason tcp_child_process(struct sock *parent, struct sock *child, } bh_unlock_sock(child); - sock_put(child); + return reason; } diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 8d791a954cd6..322db13333c7 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -50,7 +50,8 @@ static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk) u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when) { const struct inet_connection_sock *icsk = inet_csk(sk); - u32 remaining, user_timeout; + u32 user_timeout; + s32 remaining; s32 elapsed; user_timeout = READ_ONCE(icsk->icsk_user_timeout); @@ -61,7 +62,7 @@ u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when) if (unlikely(elapsed < 0)) elapsed = 0; remaining = msecs_to_jiffies(user_timeout) - elapsed; - remaining = max_t(u32, remaining, TCP_TIMEOUT_MIN); + remaining = max_t(int, remaining, TCP_TIMEOUT_MIN); return min_t(u32, remaining, when); } diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index c024aa77f25b..c3806c6ac96f 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -164,7 +164,7 @@ config IPV6_SIT select INET_TUNNEL select NET_IP_TUNNEL select IPV6_NDISC_NODETYPE - default y + default m help Tunneling means encapsulating data of one protocol type within another protocol and sending it over a channel that understands the @@ -172,7 +172,7 @@ config IPV6_SIT into IPv4 packets. This is useful if you want to connect two IPv6 networks over an IPv4-only path. - Saying M here will produce a module called sit. If unsure, say Y. + Saying M here will produce a module called sit. If unsure, say M. config IPV6_SIT_6RD bool "IPv6: IPv6 Rapid Deployment (6RD)" diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index cb26beea4398..de1e68199a01 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -317,14 +317,19 @@ static void ah6_output_done(void *data, int err) struct ipv6hdr *top_iph = ipv6_hdr(skb); struct ip_auth_hdr *ah = ip_auth_hdr(skb); struct tmp_ext *iph_ext; + int seqhi_len = 0; + __be32 *seqhi; extlen = skb_network_header_len(skb) - sizeof(struct ipv6hdr); if (extlen) extlen += sizeof(*iph_ext); + if (x->props.flags & XFRM_STATE_ESN) + seqhi_len = sizeof(*seqhi); iph_base = AH_SKB_CB(skb)->tmp; iph_ext = ah_tmp_ext(iph_base); - icv = ah_tmp_icv(iph_ext, extlen); + seqhi = (__be32 *)((char *)iph_ext + extlen); + icv = ah_tmp_icv(seqhi, seqhi_len); memcpy(ah->auth_data, icv, ahp->icv_trunc_len); memcpy(top_iph, iph_base, IPV6HDR_BASELEN); @@ -471,13 +476,18 @@ static void ah6_input_done(void *data, int err) struct ip_auth_hdr *ah = ip_auth_hdr(skb); int hdr_len = skb_network_header_len(skb); int ah_hlen = ipv6_authlen(ah); + int seqhi_len = 0; + __be32 *seqhi; if (err) goto out; + if (x->props.flags & XFRM_STATE_ESN) + seqhi_len = sizeof(*seqhi); work_iph = AH_SKB_CB(skb)->tmp; auth_data = ah_tmp_auth(work_iph, hdr_len); - icv = ah_tmp_icv(auth_data, ahp->icv_trunc_len); + seqhi = (__be32 *)(auth_data + ahp->icv_trunc_len); + icv = ah_tmp_icv(seqhi, seqhi_len); err = crypto_memneq(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG : 0; if (err) diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 9f75313734f8..9c06c5a1419d 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -915,7 +915,8 @@ static int esp6_input(struct xfrm_state *x, struct sk_buff *skb) nfrags = 1; goto skip_cow; - } else if (!skb_has_frag_list(skb)) { + } else if (!skb_has_frag_list(skb) && + !skb_has_shared_frag(skb)) { nfrags = skb_shinfo(skb)->nr_frags; nfrags++; diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 95558fd6f447..03cbce842c1a 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -491,6 +491,7 @@ static int ipv6_rpl_srh_rcv(struct sk_buff *skb) struct net *net = dev_net(skb->dev); struct inet6_dev *idev; struct ipv6hdr *oldhdr; + unsigned int chdr_len; unsigned char *buf; int accept_rpl_seg; int i, err; @@ -592,8 +593,10 @@ looped_back: skb_pull(skb, ((hdr->hdrlen + 1) << 3)); skb_postpull_rcsum(skb, oldhdr, sizeof(struct ipv6hdr) + ((hdr->hdrlen + 1) << 3)); - if (unlikely(!hdr->segments_left)) { - if (pskb_expand_head(skb, sizeof(struct ipv6hdr) + ((chdr->hdrlen + 1) << 3), 0, + chdr_len = sizeof(struct ipv6hdr) + ((chdr->hdrlen + 1) << 3); + if (unlikely(!hdr->segments_left || + skb_headroom(skb) < chdr_len + skb->mac_len)) { + if (pskb_expand_head(skb, chdr_len + skb->mac_len, 0, GFP_ATOMIC)) { __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); @@ -603,7 +606,7 @@ looped_back: oldhdr = ipv6_hdr(skb); } - skb_push(skb, ((chdr->hdrlen + 1) << 3) + sizeof(struct ipv6hdr)); + skb_push(skb, chdr_len); skb_reset_network_header(skb); skb_mac_header_rebuild(skb); skb_set_transport_header(skb, sizeof(struct ipv6hdr)); diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index 49e31e4ae7b7..9d06d487e8b1 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -73,6 +73,7 @@ int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp, __be16 *frag_offp) { u8 nexthdr = *nexthdrp; + int exthdr_cnt = 0; *frag_offp = 0; @@ -82,6 +83,8 @@ int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp, if (nexthdr == NEXTHDR_NONE) return -1; + if (unlikely(exthdr_cnt++ >= IP6_MAX_EXT_HDRS_CNT)) + return -1; hp = skb_header_pointer(skb, start, sizeof(_hdr), &_hdr); if (!hp) return -1; @@ -190,6 +193,7 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, { unsigned int start = skb_network_offset(skb) + sizeof(struct ipv6hdr); u8 nexthdr = ipv6_hdr(skb)->nexthdr; + int exthdr_cnt = 0; bool found; if (fragoff) @@ -216,6 +220,9 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, return -ENOENT; } + if (unlikely(exthdr_cnt++ >= IP6_MAX_EXT_HDRS_CNT)) + return -EBADMSG; + hp = skb_header_pointer(skb, start, sizeof(_hdr), &_hdr); if (!hp) return -EBADMSG; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 63fc8556b475..365b4059eb20 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -2262,10 +2262,11 @@ static int ip6erspan_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { - struct ip6gre_net *ign = net_generic(dev_net(dev), ip6gre_net_id); + struct ip6_tnl *t = netdev_priv(dev); struct __ip6_tnl_parm p; - struct ip6_tnl *t; + struct ip6gre_net *ign; + ign = net_generic(t->net, ip6gre_net_id); t = ip6gre_changelink_common(dev, tb, data, &p, extack); if (IS_ERR(t)) return PTR_ERR(t); diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 967b07aeb683..8972863c93ee 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -403,6 +403,7 @@ INDIRECT_CALLABLE_DECLARE(int tcp_v6_rcv(struct sk_buff *)); void ip6_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int nexthdr, bool have_final) { + int exthdr_cnt = IP6CB(skb)->flags & IP6SKB_HOPBYHOP ? 1 : 0; const struct inet6_protocol *ipprot; struct inet6_dev *idev; unsigned int nhoff; @@ -487,6 +488,10 @@ resubmit_final: nexthdr = ret; goto resubmit_final; } else { + if (unlikely(exthdr_cnt++ >= IP6_MAX_EXT_HDRS_CNT)) { + SKB_DR_SET(reason, IPV6_TOO_MANY_EXTHDRS); + goto discard; + } goto resubmit; } } else if (ret == 0) { diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 7e92909ab5be..c14adcdd4396 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -468,6 +468,7 @@ static int ip6_forward_proxy_check(struct sk_buff *skb) default: break; } + hdr = ipv6_hdr(skb); } /* @@ -582,6 +583,8 @@ int ip6_forward(struct sk_buff *skb) if (READ_ONCE(net->ipv6.devconf_all->proxy_ndp) && pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev)) { int proxied = ip6_forward_proxy_check(skb); + + hdr = ipv6_hdr(skb); if (proxied > 0) { /* It's tempting to decrease the hop limit * here by 1, as we do at the end of the @@ -1794,6 +1797,8 @@ alloc_new_skb: if (err < 0) goto error; copy = err; + if (!(flags & MSG_NO_SHARED_FRAGS)) + skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG; wmem_alloc_delta += copy; } else if (!zc) { int i = skb_shinfo(skb)->nr_frags; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index c468c83af0f2..9d1037ac082f 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -399,11 +399,15 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw) unsigned int nhoff = raw - skb->data; unsigned int off = nhoff + sizeof(*ipv6h); u8 nexthdr = ipv6h->nexthdr; + int exthdr_cnt = 0; while (ipv6_ext_hdr(nexthdr) && nexthdr != NEXTHDR_NONE) { struct ipv6_opt_hdr *hdr; u16 optlen; + if (unlikely(exthdr_cnt++ >= IP6_MAX_EXT_HDRS_CNT)) + break; + if (!pskb_may_pull(skb, off + sizeof(*hdr))) break; diff --git a/net/ipv6/netfilter/nf_socket_ipv6.c b/net/ipv6/netfilter/nf_socket_ipv6.c index ced8bd44828e..893f2aeb4711 100644 --- a/net/ipv6/netfilter/nf_socket_ipv6.c +++ b/net/ipv6/netfilter/nf_socket_ipv6.c @@ -100,6 +100,7 @@ struct sock *nf_sk_lookup_slow_v6(struct net *net, const struct sk_buff *skb, const struct in6_addr *daddr = NULL, *saddr = NULL; struct ipv6hdr *iph = ipv6_hdr(skb), ipv6_var; struct sk_buff *data_skb = NULL; + unsigned short fragoff = 0; int doff = 0; int thoff = 0, tproto; #if IS_ENABLED(CONFIG_NF_CONNTRACK) @@ -107,8 +108,8 @@ struct sock *nf_sk_lookup_slow_v6(struct net *net, const struct sk_buff *skb, struct nf_conn const *ct; #endif - tproto = ipv6_find_hdr(skb, &thoff, -1, NULL, NULL); - if (tproto < 0) { + tproto = ipv6_find_hdr(skb, &thoff, -1, &fragoff, NULL); + if (tproto < 0 || fragoff) { pr_debug("unable to find transport header in IPv6 packet, dropping\n"); return NULL; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 19eb6b702227..e3d355d1fbd6 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1645,6 +1645,10 @@ static unsigned int fib6_mtu(const struct fib6_result *res) rcu_read_lock(); idev = __in6_dev_get(dev); + if (!idev) { + rcu_read_unlock(); + return 0; + } mtu = READ_ONCE(idev->cnf.mtu6); rcu_read_unlock(); } @@ -4995,6 +4999,7 @@ static int fib6_ifdown(struct fib6_info *rt, void *p_arg) rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) break; rt->fib6_nh->fib_nh_flags |= RTNH_F_LINKDOWN; + fib6_update_sernum(net, rt); rt6_multipath_rebalance(rt); break; } diff --git a/net/ipv6/rpl_iptunnel.c b/net/ipv6/rpl_iptunnel.c index c7942cf65567..4e10adcd70e8 100644 --- a/net/ipv6/rpl_iptunnel.c +++ b/net/ipv6/rpl_iptunnel.c @@ -287,7 +287,16 @@ static int rpl_input(struct sk_buff *skb) if (!dst) { ip6_route_input(skb); + + /* ip6_route_input() sets a NOREF dst; force a refcount on it + * before caching or further use. + */ + skb_dst_force(skb); dst = skb_dst(skb); + if (unlikely(!dst)) { + err = -ENETUNREACH; + goto drop; + } /* cache only if we don't create a dst reference loop */ if (!dst->error && lwtst != dst->lwtstate) { diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 9b64343ebad6..4c45c0a77d75 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -515,7 +515,16 @@ static int seg6_input_core(struct net *net, struct sock *sk, if (!dst) { ip6_route_input(skb); + + /* ip6_route_input() sets a NOREF dst; force a refcount on it + * before caching or further use. + */ + skb_dst_force(skb); dst = skb_dst(skb); + if (unlikely(!dst)) { + err = -ENETUNREACH; + goto drop; + } /* cache only if we don't create a dst reference loop */ if (!dst->error && lwtst != dst->lwtstate) { diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 2c3f7a739709..d13d49bfef19 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -288,8 +288,10 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr_unsized *uaddr, saddr = &fl6->saddr; err = inet_bhash2_update_saddr(sk, saddr, AF_INET6); - if (err) + if (err) { + dst_release(dst); goto failure; + } } /* set the source address */ @@ -1617,12 +1619,13 @@ int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) if (sk->sk_state == TCP_LISTEN) { struct sock *nsk = tcp_v6_cookie_check(sk, skb); + if (!nsk) + return 0; if (nsk != sk) { - if (nsk) { - reason = tcp_child_process(sk, nsk, skb); - if (reason) - goto reset; - } + reason = tcp_child_process(sk, nsk, skb); + sock_put(nsk); + if (reason) + goto reset; return 0; } } else @@ -1827,8 +1830,10 @@ lookup: rst_reason = sk_rst_convert_drop_reason(drop_reason); tcp_v6_send_reset(nsk, skb, rst_reason); + sock_put(nsk); goto discard_and_relse; } + sock_put(nsk); sock_put(sk); return 0; } diff --git a/net/ipv6/xfrm6_protocol.c b/net/ipv6/xfrm6_protocol.c index ea2f805d3b01..9b586fcec485 100644 --- a/net/ipv6/xfrm6_protocol.c +++ b/net/ipv6/xfrm6_protocol.c @@ -88,8 +88,10 @@ int xfrm6_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi, dst = ip6_route_input_lookup(dev_net(skb->dev), skb->dev, &fl6, skb, flags); - if (dst->error) + if (dst->error) { + dst_release(dst); goto drop; + } skb_dst_set(skb, dst); } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 160ae65a5c64..0a0f27836d57 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -438,6 +438,15 @@ ieee80211_verify_sta_ht_mcs_support(struct ieee80211_sub_if_data *sdata, ieee80211_apply_htcap_overrides(sdata, &sta_ht_cap); /* + * Some Xfinity XB8 firmware advertises >1 spatial stream MCS indexes in + * their basic HT-MCS set. On cards with lower spatial streams, the check + * would fail, and we'd be stuck with no HT when it in fact work fine with + * its own supported rate. So check it only in strict mode. + */ + if (!ieee80211_hw_check(&sdata->local->hw, STRICT)) + return true; + + /* * P802.11REVme/D7.0 - 6.5.4.2.4 * ... * If the MLME of an HT STA receives an MLME-JOIN.request primitive @@ -9140,7 +9149,7 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, struct ieee80211_bss *bss = (void *)cbss->priv; struct sta_info *new_sta = NULL; struct ieee80211_link_data *link; - bool have_sta = false; + struct sta_info *have_sta = NULL; bool mlo; int err; u16 new_links; @@ -9159,11 +9168,8 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, mlo = false; } - if (assoc) { - rcu_read_lock(); + if (assoc) have_sta = sta_info_get(sdata, ap_mld_addr); - rcu_read_unlock(); - } if (mlo && !have_sta && WARN_ON(sdata->vif.valid_links || sdata->vif.active_links)) @@ -9327,6 +9333,8 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, out_release_chan: ieee80211_link_release_channel(link); out_err: + if (mlo && have_sta) + WARN_ON(__sta_info_destroy(have_sta)); ieee80211_vif_set_links(sdata, 0, 0); return err; } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 3e5d1c47a5b0..d18e962126ce 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -4971,7 +4971,7 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx, struct sk_buff *skb = rx->skb; struct ieee80211_hdr *hdr = (void *)skb->data; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); - static ieee80211_rx_result res; + ieee80211_rx_result res; int orig_len = skb->len; int hdrlen = ieee80211_hdrlen(hdr->frame_control); int snap_offs = hdrlen; @@ -5380,7 +5380,9 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, if (!link_sta) goto out; - ieee80211_rx_data_set_link(&rx, link_sta->link_id); + if (!ieee80211_rx_data_set_link(&rx, + link_sta->link_id)) + goto out; } if (ieee80211_prepare_and_rx_handle(&rx, skb, true)) diff --git a/net/mac80211/tests/chan-mode.c b/net/mac80211/tests/chan-mode.c index adc069065e73..fa370831d617 100644 --- a/net/mac80211/tests/chan-mode.c +++ b/net/mac80211/tests/chan-mode.c @@ -65,6 +65,7 @@ static const struct determine_chan_mode_case { .ht_capa_mask = { .mcs.rx_mask[0] = 0xf7, }, + .strict = true, }, { .desc = "Masking out a RX rate in VHT capabilities", .conn_mode = IEEE80211_CONN_MODE_EHT, diff --git a/net/mac80211/util.c b/net/mac80211/util.c index b093bc203c81..2529b01e2cd5 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -3700,11 +3700,11 @@ void ieee80211_dfs_radar_detected_work(struct wiphy *wiphy, struct ieee80211_local *local = container_of(work, struct ieee80211_local, radar_detected_work); struct cfg80211_chan_def chandef; - struct ieee80211_chanctx *ctx; + struct ieee80211_chanctx *ctx, *tmp; lockdep_assert_wiphy(local->hw.wiphy); - list_for_each_entry(ctx, &local->chanctx_list, list) { + list_for_each_entry_safe(ctx, tmp, &local->chanctx_list, list) { if (ctx->replace_state == IEEE80211_CHANCTX_REPLACES_OTHER) continue; diff --git a/net/mctp/test/route-test.c b/net/mctp/test/route-test.c index e1033643fab0..e4b230ef6099 100644 --- a/net/mctp/test/route-test.c +++ b/net/mctp/test/route-test.c @@ -920,9 +920,9 @@ static void mctp_test_route_input_cloned_frag(struct kunit *test) static void mctp_test_route_input_null_eid(struct kunit *test) { struct mctp_hdr hdr = RX_HDR(1, 10, 0, FL_S | FL_E | FL_TO); + struct sockaddr_mctp addr = { 0 }; struct sk_buff *skb_pkt, *skb_sk; struct mctp_test_dev *dev; - struct sockaddr_mctp addr; struct socket *sock; u8 type = 0; int rc; diff --git a/net/mctp/test/utils.c b/net/mctp/test/utils.c index c3987d5ade7a..6eef8d485c25 100644 --- a/net/mctp/test/utils.c +++ b/net/mctp/test/utils.c @@ -116,7 +116,7 @@ void mctp_test_destroy_dev(struct mctp_test_dev *dev) static int mctp_test_dst_output(struct mctp_dst *dst, struct sk_buff *skb) { skb->dev = dst->dev->dev; - dev_queue_xmit(skb); + dev_direct_xmit(skb, 0); return 0; } diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c index 82ec15bcfd7f..082c46c0f50e 100644 --- a/net/mptcp/fastopen.c +++ b/net/mptcp/fastopen.c @@ -12,6 +12,7 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf struct sock *sk, *ssk; struct sk_buff *skb; struct tcp_sock *tp; + bool has_rxtstamp; /* on early fallback the subflow context is deleted by * subflow_syn_recv_sock() @@ -40,12 +41,13 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf */ tp->copied_seq += skb->len; subflow->ssn_offset += skb->len; + has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp; /* Only the sequence delta is relevant */ MPTCP_SKB_CB(skb)->map_seq = -skb->len; MPTCP_SKB_CB(skb)->end_seq = 0; MPTCP_SKB_CB(skb)->offset = 0; - MPTCP_SKB_CB(skb)->has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp; + MPTCP_SKB_CB(skb)->has_rxtstamp = has_rxtstamp; MPTCP_SKB_CB(skb)->cant_coalesce = 1; mptcp_data_lock(sk); diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 57a456690406..3c152bf66cd5 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -16,6 +16,7 @@ struct mptcp_pm_add_entry { struct list_head list; struct mptcp_addr_info addr; u8 retrans_times; + bool timer_done; struct timer_list add_timer; struct mptcp_sock *sock; struct rcu_head rcu; @@ -283,6 +284,9 @@ int mptcp_pm_mp_prio_send_ack(struct mptcp_sock *msk, struct sock *ssk = mptcp_subflow_tcp_sock(subflow); struct mptcp_addr_info local, remote; + if (!__mptcp_subflow_active(subflow)) + continue; + mptcp_local_address((struct sock_common *)ssk, &local); if (!mptcp_addresses_equal(&local, addr, addr->port)) continue; @@ -305,18 +309,31 @@ static unsigned int mptcp_adjust_add_addr_timeout(struct mptcp_sock *msk) const struct net *net = sock_net((struct sock *)msk); unsigned int rto = mptcp_get_add_addr_timeout(net); struct mptcp_subflow_context *subflow; - unsigned int max = 0; + unsigned int max = 0, max_stale = 0; + + if (!rto) + return 0; mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); struct inet_connection_sock *icsk = inet_csk(ssk); - if (icsk->icsk_rto > max) + if (!__mptcp_subflow_active(subflow)) + continue; + + if (unlikely(subflow->stale)) { + if (icsk->icsk_rto > max_stale) + max_stale = icsk->icsk_rto; + } else if (icsk->icsk_rto > max) { max = icsk->icsk_rto; + } } - if (max && max < rto) - rto = max; + if (max) + return min(max, rto); + + if (max_stale) + return min(max_stale, rto); return rto; } @@ -327,26 +344,22 @@ static void mptcp_pm_add_timer(struct timer_list *timer) add_timer); struct mptcp_sock *msk = entry->sock; struct sock *sk = (struct sock *)msk; - unsigned int timeout; + unsigned int timeout = 0; pr_debug("msk=%p\n", msk); - if (!msk) - return; - - if (inet_sk_state_load(sk) == TCP_CLOSE) - return; - - if (!entry->addr.id) - return; + bh_lock_sock(sk); + if (unlikely(inet_sk_state_load(sk) == TCP_CLOSE)) + goto out; - if (mptcp_pm_should_add_signal_addr(msk)) { - sk_reset_timer(sk, timer, jiffies + TCP_RTO_MAX / 8); + if (sock_owned_by_user(sk)) { + /* Try again later. */ + timeout = HZ / 20; goto out; } timeout = mptcp_adjust_add_addr_timeout(msk); - if (!timeout) + if (!timeout || mptcp_pm_should_add_signal_addr(msk)) goto out; spin_lock_bh(&msk->pm.lock); @@ -359,8 +372,9 @@ static void mptcp_pm_add_timer(struct timer_list *timer) } if (entry->retrans_times < ADD_ADDR_RETRANS_MAX) - sk_reset_timer(sk, timer, - jiffies + (timeout << entry->retrans_times)); + timeout <<= entry->retrans_times; + else + timeout = 0; spin_unlock_bh(&msk->pm.lock); @@ -368,7 +382,13 @@ static void mptcp_pm_add_timer(struct timer_list *timer) mptcp_pm_subflow_established(msk); out: - __sock_put(sk); + if (timeout) + sk_reset_timer(sk, timer, jiffies + timeout); + else + /* if sock_put calls sk_free: avoid waiting for this timer */ + entry->timer_done = true; + bh_unlock_sock(sk); + sock_put(sk); } struct mptcp_pm_add_entry * @@ -431,6 +451,7 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk, timer_setup(&add_entry->add_timer, mptcp_pm_add_timer, 0); reset_timer: + add_entry->timer_done = false; timeout = mptcp_adjust_add_addr_timeout(msk); if (timeout) sk_reset_timer(sk, &add_entry->add_timer, jiffies + timeout); @@ -451,7 +472,8 @@ static void mptcp_pm_free_anno_list(struct mptcp_sock *msk) spin_unlock_bh(&msk->pm.lock); list_for_each_entry_safe(entry, tmp, &free_list, list) { - sk_stop_timer_sync(sk, &entry->add_timer); + if (!entry->timer_done) + sk_stop_timer_sync(sk, &entry->add_timer); kfree_rcu(entry, rcu); } } diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c index 0ebf43be9939..fc818b63752e 100644 --- a/net/mptcp/pm_kernel.c +++ b/net/mptcp/pm_kernel.c @@ -347,6 +347,8 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) /* check first for announce */ if (msk->pm.add_addr_signaled < endp_signal_max) { + u8 endp_id; + /* due to racing events on both ends we can reach here while * previous add address is still running: if we invoke now * mptcp_pm_announce_addr(), that will fail and the @@ -360,19 +362,20 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) if (!select_signal_address(pernet, msk, &local)) goto subflow; + /* Special case for ID0: set the correct ID */ + endp_id = local.addr.id; + if (endp_id == msk->mpc_endpoint_id) + local.addr.id = 0; + /* If the alloc fails, we are on memory pressure, not worth * continuing, and trying to create subflows. */ if (!mptcp_pm_alloc_anno_list(msk, &local.addr)) return; - __clear_bit(local.addr.id, msk->pm.id_avail_bitmap); + __clear_bit(endp_id, msk->pm.id_avail_bitmap); msk->pm.add_addr_signaled++; - /* Special case for ID0: set the correct ID */ - if (local.addr.id == msk->mpc_endpoint_id) - local.addr.id = 0; - mptcp_pm_announce_addr(msk, &local.addr, false); mptcp_pm_addr_send_ack(msk); @@ -1278,6 +1281,7 @@ static void __reset_counters(struct pm_nl_pernet *pernet) WRITE_ONCE(pernet->endp_signal_max, 0); WRITE_ONCE(pernet->endp_subflow_max, 0); WRITE_ONCE(pernet->endp_laminar_max, 0); + WRITE_ONCE(pernet->endp_fullmesh_max, 0); pernet->endpoints = 0; } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 718e910ff23f..4546a8b09884 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3302,7 +3302,8 @@ bool __mptcp_close(struct sock *sk, long timeout) goto cleanup; } - if (mptcp_data_avail(msk) || timeout < 0) { + if (mptcp_data_avail(msk) || timeout < 0 || + (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime)) { /* If the msk has read data, or the caller explicitly ask it, * do the MPTCP equivalent of TCP reset, aka MPTCP fastclose */ diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index de90a2897d2d..1cf608e7357b 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -159,10 +159,10 @@ static int mptcp_setsockopt_sol_socket_tstamp(struct mptcp_sock *msk, int optnam lock_sock(sk); mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - bool slow = lock_sock_fast(ssk); - sock_set_timestamp(sk, optname, !!val); - unlock_sock_fast(ssk, slow); + lock_sock(ssk); + sock_set_timestamp(ssk, optname, !!val); + release_sock(ssk); } release_sock(sk); @@ -235,10 +235,10 @@ static int mptcp_setsockopt_sol_socket_timestamping(struct mptcp_sock *msk, mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - bool slow = lock_sock_fast(ssk); - sock_set_timestamping(sk, optname, timestamping); - unlock_sock_fast(ssk, slow); + lock_sock(ssk); + sock_set_timestamping(ssk, optname, timestamping); + release_sock(ssk); } release_sock(sk); @@ -812,6 +812,10 @@ static int mptcp_setsockopt_all_sf(struct mptcp_sock *msk, int level, if (ret) break; } + + if (!ret) + sockopt_seq_inc(msk); + return ret; } diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index e2cb9d23e4a0..d562e149606f 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -581,7 +581,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->backup); if (!subflow_thmac_valid(subflow)) { - MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINACKMAC); + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKMAC); subflow->reset_reason = MPTCP_RST_EMPTCP; goto do_reset; } @@ -908,7 +908,7 @@ create_child: if (!subflow_hmac_valid(subflow_req, &mp_opt)) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC); - subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT); + subflow_add_reset_reason(skb, MPTCP_RST_EMPTCP); goto dispose_child; } diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 2082bfb2d93c..9ea6b4fa78bf 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -267,27 +267,20 @@ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp) hash_key2 = hash_key; use2 = false; } + conn_tab_lock(t, cp, hash_key, hash_key2, use2, true /* new_hash */, &head, &head2); - spin_lock(&cp->lock); - - if (!(cp->flags & IP_VS_CONN_F_HASHED)) { - cp->flags |= IP_VS_CONN_F_HASHED; - WRITE_ONCE(cp->hn0.hash_key, hash_key); - WRITE_ONCE(cp->hn1.hash_key, hash_key2); - refcount_inc(&cp->refcnt); - hlist_bl_add_head_rcu(&cp->hn0.node, head); - if (use2) - hlist_bl_add_head_rcu(&cp->hn1.node, head2); - ret = 1; - } else { - pr_err("%s(): request for already hashed, called from %pS\n", - __func__, __builtin_return_address(0)); - ret = 0; - } - spin_unlock(&cp->lock); + cp->flags |= IP_VS_CONN_F_HASHED; + WRITE_ONCE(cp->hn0.hash_key, hash_key); + WRITE_ONCE(cp->hn1.hash_key, hash_key2); + refcount_inc(&cp->refcnt); + hlist_bl_add_head_rcu(&cp->hn0.node, head); + if (use2) + hlist_bl_add_head_rcu(&cp->hn1.node, head2); + conn_tab_unlock(head, head2); + ret = 1; /* Schedule resizing if load increases */ if (atomic_read(&ipvs->conn_count) > t->u_thresh && @@ -321,7 +314,6 @@ static inline bool ip_vs_conn_unlink(struct ip_vs_conn *cp) conn_tab_lock(t, cp, hash_key, hash_key2, use2, false /* new_hash */, &head, &head2); - spin_lock(&cp->lock); if (cp->flags & IP_VS_CONN_F_HASHED) { /* Decrease refcnt and unlink conn only if we are last user */ @@ -334,7 +326,6 @@ static inline bool ip_vs_conn_unlink(struct ip_vs_conn *cp) } } - spin_unlock(&cp->lock); conn_tab_unlock(head, head2); rcu_read_unlock(); @@ -637,6 +628,7 @@ void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport) struct ip_vs_conn_hnode *hn; u32 hash_key, hash_key_new; struct ip_vs_conn_param p; + bool by_me = false; int ntbl; int dir; @@ -664,8 +656,16 @@ retry: t = rcu_dereference(t->new_tbl); ntbl++; /* We are lost? */ - if (ntbl >= 2) + if (ntbl >= 2) { + spin_lock_bh(&cp->lock); + if (cp->flags & IP_VS_CONN_F_NO_CPORT && by_me) + cp->cport = 0; + /* hn1 will be rehashed on next packet */ + spin_unlock_bh(&cp->lock); + IP_VS_ERR_RL("%s(): Too many ht changes for dir %d\n", + __func__, dir); return; + } } /* Rehashing during resize? Use the recent table for adds */ @@ -683,10 +683,13 @@ retry: if (head > head2 && t == t2) swap(head, head2); + /* Protect the cp->flags modification */ + spin_lock_bh(&cp->lock); + /* Lock seqcount only for the old bucket, even if we are on new table * because it affects the del operation, not the adding. */ - spin_lock_bh(&t->lock[hash_key & t->lock_mask].l); + spin_lock(&t->lock[hash_key & t->lock_mask].l); preempt_disable_nested(); write_seqcount_begin(&t->seqc[hash_key & t->seqc_mask]); @@ -704,14 +707,23 @@ retry: hlist_bl_unlock(head); write_seqcount_end(&t->seqc[hash_key & t->seqc_mask]); preempt_enable_nested(); - spin_unlock_bh(&t->lock[hash_key & t->lock_mask].l); + spin_unlock(&t->lock[hash_key & t->lock_mask].l); + spin_unlock_bh(&cp->lock); hash_key = hash_key_new; goto retry; } - spin_lock(&cp->lock); - if ((cp->flags & IP_VS_CONN_F_NO_CPORT) && - (cp->flags & IP_VS_CONN_F_HASHED)) { + /* Fill cport once, even if multiple packets try to do it */ + if (cp->flags & IP_VS_CONN_F_NO_CPORT && (!cp->cport || by_me)) { + /* If we race with resizing make sure cport is set for dir 1 */ + if (!cp->cport) { + cp->cport = cport; + by_me = true; + } + if (!dir) { + atomic_dec(&ipvs->no_cport_conns[af_id]); + cp->flags &= ~IP_VS_CONN_F_NO_CPORT; + } /* We do not recalc hash_key_r under lock, we assume the * parameters in cp do not change, i.e. cport is * the only possible change. @@ -726,21 +738,17 @@ retry: hlist_bl_del_rcu(&hn->node); hlist_bl_add_head_rcu(&hn->node, head_new); } - if (!dir) { - atomic_dec(&ipvs->no_cport_conns[af_id]); - cp->flags &= ~IP_VS_CONN_F_NO_CPORT; - cp->cport = cport; - } } - spin_unlock(&cp->lock); if (head != head2) hlist_bl_unlock(head2); hlist_bl_unlock(head); write_seqcount_end(&t->seqc[hash_key & t->seqc_mask]); preempt_enable_nested(); - spin_unlock_bh(&t->lock[hash_key & t->lock_mask].l); - if (dir--) + spin_unlock(&t->lock[hash_key & t->lock_mask].l); + + spin_unlock_bh(&cp->lock); + if (dir-- && by_me) goto next_dir; } @@ -1835,7 +1843,7 @@ static void ip_vs_conn_flush(struct netns_ipvs *ipvs) if (!rcu_dereference_protected(ipvs->conn_tab, 1)) return; - cancel_delayed_work_sync(&ipvs->conn_resize_work); + disable_delayed_work_sync(&ipvs->conn_resize_work); if (!atomic_read(&ipvs->conn_count)) goto unreg; diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index f5b7a2047291..d40b404c1bf6 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -237,7 +237,7 @@ int ip_vs_rht_desired_size(struct netns_ipvs *ipvs, struct ip_vs_rht *t, int n, { if (!t) return 1 << min_bits; - n = roundup_pow_of_two(n); + n = n > 0 ? roundup_pow_of_two(n) : 1; if (lfactor < 0) { int factor = min(-lfactor, max_bits); diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 6632daa87ded..c7c7f6a7a9f6 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -261,12 +261,28 @@ static void est_reload_work_handler(struct work_struct *work) if (!kd) continue; /* New config ? Stop kthread tasks */ - if (genid != genid_done) - ip_vs_est_kthread_stop(kd); + if (genid != genid_done) { + if (!id) { + /* Only we can stop kt 0 but not under mutex */ + mutex_unlock(&ipvs->est_mutex); + ip_vs_est_kthread_stop(kd); + mutex_lock(&ipvs->est_mutex); + if (!READ_ONCE(ipvs->enable)) + goto unlock; + /* kd for kt 0 is never destroyed */ + } else { + ip_vs_est_kthread_stop(kd); + } + } if (!kd->task && !ip_vs_est_stopped(ipvs)) { + bool start; + /* Do not start kthreads above 0 in calc phase */ - if ((!id || !ipvs->est_calc_phase) && - ip_vs_est_kthread_start(ipvs, kd) < 0) + if (id) + start = !ipvs->est_calc_phase; + else + start = kd->needed; + if (start && ip_vs_est_kthread_start(ipvs, kd) < 0) repeat = true; } } @@ -1102,6 +1118,24 @@ out: return dest; } +/* Put destination in trash */ +static void ip_vs_trash_put_dest(struct netns_ipvs *ipvs, + struct ip_vs_dest *dest, unsigned long istart, + bool cleanup) +{ + spin_lock_bh(&ipvs->dest_trash_lock); + IP_VS_DBG_BUF(3, "Moving dest %s:%u into trash, dest->refcnt=%d\n", + IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port), + refcount_read(&dest->refcnt)); + if (list_empty(&ipvs->dest_trash) && !cleanup) + mod_timer(&ipvs->dest_trash_timer, + jiffies + (IP_VS_DEST_TRASH_PERIOD >> 1)); + /* dest lives in trash with reference */ + list_add(&dest->t_list, &ipvs->dest_trash); + dest->idle_start = istart; + spin_unlock_bh(&ipvs->dest_trash_lock); +} + static void ip_vs_dest_rcu_free(struct rcu_head *head) { struct ip_vs_dest *dest; @@ -1461,9 +1495,12 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) ntohs(dest->vport)); ret = ip_vs_start_estimator(svc->ipvs, &dest->stats); + /* On error put back dest into the trash */ if (ret < 0) - return ret; - __ip_vs_update_dest(svc, dest, udest, 1); + ip_vs_trash_put_dest(svc->ipvs, dest, dest->idle_start, + false); + else + __ip_vs_update_dest(svc, dest, udest, 1); } else { /* * Allocate and initialize the dest structure @@ -1533,17 +1570,7 @@ static void __ip_vs_del_dest(struct netns_ipvs *ipvs, struct ip_vs_dest *dest, */ ip_vs_rs_unhash(dest); - spin_lock_bh(&ipvs->dest_trash_lock); - IP_VS_DBG_BUF(3, "Moving dest %s:%u into trash, dest->refcnt=%d\n", - IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port), - refcount_read(&dest->refcnt)); - if (list_empty(&ipvs->dest_trash) && !cleanup) - mod_timer(&ipvs->dest_trash_timer, - jiffies + (IP_VS_DEST_TRASH_PERIOD >> 1)); - /* dest lives in trash with reference */ - list_add(&dest->t_list, &ipvs->dest_trash); - dest->idle_start = 0; - spin_unlock_bh(&ipvs->dest_trash_lock); + ip_vs_trash_put_dest(ipvs, dest, 0, cleanup); /* Queue up delayed work to expire all no destination connections. * No-op when CONFIG_SYSCTL is disabled. @@ -1812,11 +1839,16 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u, *svc_p = svc; if (!READ_ONCE(ipvs->enable)) { + mutex_lock(&ipvs->est_mutex); + /* Now there is a service - full throttle */ WRITE_ONCE(ipvs->enable, 1); + ipvs->est_max_threads = ip_vs_est_max_threads(ipvs); + /* Start estimation for first time */ - ip_vs_est_reload_start(ipvs); + ip_vs_est_reload_start(ipvs, true); + mutex_unlock(&ipvs->est_mutex); } return 0; @@ -2032,6 +2064,9 @@ static int ip_vs_del_service(struct ip_vs_service *svc) cancel_delayed_work_sync(&ipvs->svc_resize_work); if (t) { rcu_assign_pointer(ipvs->svc_table, NULL); + /* Inform readers that table is removed */ + smp_mb__before_atomic(); + atomic_inc(&ipvs->svc_table_changes); while (1) { p = rcu_dereference_protected(t->new_tbl, 1); call_rcu(&t->rcu_head, ip_vs_rht_rcu_free); @@ -2078,6 +2113,9 @@ static int ip_vs_flush(struct netns_ipvs *ipvs, bool cleanup) t = rcu_dereference_protected(ipvs->svc_table, 1); if (t) { rcu_assign_pointer(ipvs->svc_table, NULL); + /* Inform readers that table is removed */ + smp_mb__before_atomic(); + atomic_inc(&ipvs->svc_table_changes); while (1) { p = rcu_dereference_protected(t->new_tbl, 1); call_rcu(&t->rcu_head, ip_vs_rht_rcu_free); @@ -2086,6 +2124,11 @@ static int ip_vs_flush(struct netns_ipvs *ipvs, bool cleanup) t = p; } } + /* Stop the tot_stats estimator early under service_mutex + * to avoid locking it again later. + */ + if (cleanup) + ip_vs_stop_estimator_tot_stats(ipvs); return 0; } @@ -2331,7 +2374,7 @@ static int ipvs_proc_est_cpumask_set(const struct ctl_table *table, /* est_max_threads may depend on cpulist size */ ipvs->est_max_threads = ip_vs_est_max_threads(ipvs); ipvs->est_calc_phase = 1; - ip_vs_est_reload_start(ipvs); + ip_vs_est_reload_start(ipvs, true); unlock: mutex_unlock(&ipvs->est_mutex); @@ -2351,11 +2394,14 @@ static int ipvs_proc_est_cpumask_get(const struct ctl_table *table, mutex_lock(&ipvs->est_mutex); - if (ipvs->est_cpulist_valid) - mask = *valp; - else - mask = (struct cpumask *)housekeeping_cpumask(HK_TYPE_KTHREAD); - ret = scnprintf(buffer, size, "%*pbl\n", cpumask_pr_args(mask)); + /* HK_TYPE_KTHREAD cpumask needs RCU protection */ + scoped_guard(rcu) { + if (ipvs->est_cpulist_valid) + mask = *valp; + else + mask = (struct cpumask *)housekeeping_cpumask(HK_TYPE_KTHREAD); + ret = scnprintf(buffer, size, "%*pbl\n", cpumask_pr_args(mask)); + } mutex_unlock(&ipvs->est_mutex); @@ -2411,7 +2457,7 @@ static int ipvs_proc_est_nice(const struct ctl_table *table, int write, mutex_lock(&ipvs->est_mutex); if (*valp != val) { *valp = val; - ip_vs_est_reload_start(ipvs); + ip_vs_est_reload_start(ipvs, true); } mutex_unlock(&ipvs->est_mutex); } @@ -2438,7 +2484,7 @@ static int ipvs_proc_run_estimation(const struct ctl_table *table, int write, mutex_lock(&ipvs->est_mutex); if (*valp != val) { *valp = val; - ip_vs_est_reload_start(ipvs); + ip_vs_est_reload_start(ipvs, true); } mutex_unlock(&ipvs->est_mutex); } @@ -2463,7 +2509,7 @@ static int ipvs_proc_conn_lfactor(const struct ctl_table *table, int write, if (val < -8 || val > 8) { ret = -EINVAL; } else { - *valp = val; + WRITE_ONCE(*valp, val); if (rcu_access_pointer(ipvs->conn_tab)) mod_delayed_work(system_unbound_wq, &ipvs->conn_resize_work, 0); @@ -2490,10 +2536,16 @@ static int ipvs_proc_svc_lfactor(const struct ctl_table *table, int write, if (val < -8 || val > 8) { ret = -EINVAL; } else { - *valp = val; - if (rcu_access_pointer(ipvs->svc_table)) + mutex_lock(&ipvs->service_mutex); + WRITE_ONCE(*valp, val); + /* Make sure the services are present */ + if (rcu_access_pointer(ipvs->svc_table) && + READ_ONCE(ipvs->enable) && + !test_bit(IP_VS_WORK_SVC_NORESIZE, + &ipvs->work_flags)) mod_delayed_work(system_unbound_wq, &ipvs->svc_resize_work, 0); + mutex_unlock(&ipvs->service_mutex); } } return ret; @@ -3004,7 +3056,8 @@ static int ip_vs_status_show(struct seq_file *seq, void *v) int old_gen, new_gen; u32 counts[8]; u32 bucket; - int count; + u32 count; + int loops; u32 sum1; u32 sum; int i; @@ -3020,6 +3073,7 @@ static int ip_vs_status_show(struct seq_file *seq, void *v) if (!atomic_read(&ipvs->conn_count)) goto after_conns; old_gen = atomic_read(&ipvs->conn_tab_changes); + loops = 0; repeat_conn: smp_rmb(); /* ipvs->conn_tab and conn_tab_changes */ @@ -3032,8 +3086,11 @@ repeat_conn: resched_score++; ip_vs_rht_walk_bucket_rcu(t, bucket, head) { count = 0; - hlist_bl_for_each_entry_rcu(hn, e, head, node) + hlist_bl_for_each_entry_rcu(hn, e, head, node) { count++; + if (count >= ARRAY_SIZE(counts) - 1) + break; + } } resched_score += count; if (resched_score >= 100) { @@ -3042,37 +3099,41 @@ repeat_conn: new_gen = atomic_read(&ipvs->conn_tab_changes); /* New table installed ? */ if (old_gen != new_gen) { + /* Too many changes? */ + if (++loops >= 5) + goto after_conns; old_gen = new_gen; goto repeat_conn; } } - counts[min(count, (int)ARRAY_SIZE(counts) - 1)]++; + counts[count]++; } } for (sum = 0, i = 0; i < ARRAY_SIZE(counts); i++) sum += counts[i]; sum1 = sum - counts[0]; - seq_printf(seq, "Conn buckets empty:\t%u (%lu%%)\n", - counts[0], (unsigned long)counts[0] * 100 / max(sum, 1U)); + seq_printf(seq, "Conn buckets empty:\t%u (%llu%%)\n", + counts[0], div_u64((u64)counts[0] * 100U, max(sum, 1U))); for (i = 1; i < ARRAY_SIZE(counts); i++) { if (!counts[i]) continue; - seq_printf(seq, "Conn buckets len-%d:\t%u (%lu%%)\n", + seq_printf(seq, "Conn buckets len-%d:\t%u (%llu%%)\n", i, counts[i], - (unsigned long)counts[i] * 100 / max(sum1, 1U)); + div_u64((u64)counts[i] * 100U, max(sum1, 1U))); } after_conns: t = rcu_dereference(ipvs->svc_table); count = ip_vs_get_num_services(ipvs); - seq_printf(seq, "Services:\t%d\n", count); + seq_printf(seq, "Services:\t%u\n", count); seq_printf(seq, "Service buckets:\t%d (%d bits, lfactor %d)\n", t ? t->size : 0, t ? t->bits : 0, t ? t->lfactor : 0); if (!count) goto after_svc; old_gen = atomic_read(&ipvs->svc_table_changes); + loops = 0; repeat_svc: smp_rmb(); /* ipvs->svc_table and svc_table_changes */ @@ -3086,8 +3147,11 @@ repeat_svc: ip_vs_rht_walk_bucket_rcu(t, bucket, head) { count = 0; hlist_bl_for_each_entry_rcu(svc, e, head, - s_list) + s_list) { count++; + if (count >= ARRAY_SIZE(counts) - 1) + break; + } } resched_score += count; if (resched_score >= 100) { @@ -3096,24 +3160,27 @@ repeat_svc: new_gen = atomic_read(&ipvs->svc_table_changes); /* New table installed ? */ if (old_gen != new_gen) { + /* Too many changes? */ + if (++loops >= 5) + goto after_svc; old_gen = new_gen; goto repeat_svc; } } - counts[min(count, (int)ARRAY_SIZE(counts) - 1)]++; + counts[count]++; } } for (sum = 0, i = 0; i < ARRAY_SIZE(counts); i++) sum += counts[i]; sum1 = sum - counts[0]; - seq_printf(seq, "Service buckets empty:\t%u (%lu%%)\n", - counts[0], (unsigned long)counts[0] * 100 / max(sum, 1U)); + seq_printf(seq, "Service buckets empty:\t%u (%llu%%)\n", + counts[0], div_u64((u64)counts[0] * 100U, max(sum, 1U))); for (i = 1; i < ARRAY_SIZE(counts); i++) { if (!counts[i]) continue; - seq_printf(seq, "Service buckets len-%d:\t%u (%lu%%)\n", + seq_printf(seq, "Service buckets len-%d:\t%u (%llu%%)\n", i, counts[i], - (unsigned long)counts[i] * 100 / max(sum1, 1U)); + div_u64((u64)counts[i] * 100U, max(sum1, 1U))); } after_svc: @@ -4967,7 +5034,14 @@ static void __net_exit ip_vs_control_net_cleanup_sysctl(struct netns_ipvs *ipvs) cancel_delayed_work_sync(&ipvs->defense_work); cancel_work_sync(&ipvs->defense_work.work); unregister_net_sysctl_table(ipvs->sysctl_hdr); - ip_vs_stop_estimator(ipvs, &ipvs->tot_stats->s); + if (ipvs->tot_stats->s.est.ktid != -2) { + /* Not stopped yet? This happens only on netns init error and + * we even do not need to lock the service_mutex for this case. + */ + mutex_lock(&ipvs->service_mutex); + ip_vs_stop_estimator(ipvs, &ipvs->tot_stats->s); + mutex_unlock(&ipvs->service_mutex); + } if (ipvs->est_cpulist_valid) free_cpumask_var(ipvs->sysctl_est_cpulist); @@ -5039,7 +5113,7 @@ int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs) ipvs->net->proc_net, ip_vs_stats_percpu_show, NULL)) goto err_percpu; - if (!proc_create_net_single("ip_vs_status", 0, ipvs->net->proc_net, + if (!proc_create_net_single("ip_vs_status", 0440, ipvs->net->proc_net, ip_vs_status_show, NULL)) goto err_status; #endif diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index 433ba3cab58c..ab09f5182951 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -68,6 +68,11 @@ and the limit of estimators per kthread - est_add_ktid: ktid where to add new ests, can point to empty slot where we should add kt data + - data protected by service_mutex: est_temp_list, est_add_ktid, + est_kt_count(R/W), est_kt_arr(R/W), est_genid_done, kd->needed(R/W) + - data protected by est_mutex: est_genid, est_max_threads, sysctl_est_cpulist, + est_cpulist_valid, sysctl_est_nice, est_stopped, sysctl_run_estimation, + est_kt_count(R), est_kt_arr(R), kd->needed(R), kd->task (id > 0) */ static struct lock_class_key __ipvs_est_key; @@ -227,14 +232,17 @@ static int ip_vs_estimation_kthread(void *data) } /* Schedule stop/start for kthread tasks */ -void ip_vs_est_reload_start(struct netns_ipvs *ipvs) +void ip_vs_est_reload_start(struct netns_ipvs *ipvs, bool restart) { + lockdep_assert_held(&ipvs->est_mutex); + /* Ignore reloads before first service is added */ if (!READ_ONCE(ipvs->enable)) return; ip_vs_est_stopped_recalc(ipvs); - /* Bump the kthread configuration genid */ - atomic_inc(&ipvs->est_genid); + /* Bump the kthread configuration genid if stopping is requested */ + if (restart) + atomic_inc(&ipvs->est_genid); queue_delayed_work(system_long_wq, &ipvs->est_reload_work, 0); } @@ -304,12 +312,17 @@ static int ip_vs_est_add_kthread(struct netns_ipvs *ipvs) void *arr = NULL; int i; - if ((unsigned long)ipvs->est_kt_count >= ipvs->est_max_threads && - READ_ONCE(ipvs->enable) && ipvs->est_max_threads) - return -EINVAL; - mutex_lock(&ipvs->est_mutex); + /* Allow kt 0 data to be created before the services are added + * and limit the kthreads when services are present. + */ + if ((unsigned long)ipvs->est_kt_count >= ipvs->est_max_threads && + READ_ONCE(ipvs->enable) && ipvs->est_max_threads) { + ret = -EINVAL; + goto out; + } + for (i = 0; i < id; i++) { if (!ipvs->est_kt_arr[i]) break; @@ -333,6 +346,7 @@ static int ip_vs_est_add_kthread(struct netns_ipvs *ipvs) kd->est_timer = jiffies; kd->id = id; ip_vs_est_set_params(ipvs, kd); + kd->needed = 1; /* Pre-allocate stats used in calc phase */ if (!id && !kd->calc_stats) { @@ -341,12 +355,8 @@ static int ip_vs_est_add_kthread(struct netns_ipvs *ipvs) goto out; } - /* Start kthread tasks only when services are present */ - if (READ_ONCE(ipvs->enable) && !ip_vs_est_stopped(ipvs)) { - ret = ip_vs_est_kthread_start(ipvs, kd); - if (ret < 0) - goto out; - } + /* Request kthread to be started */ + ip_vs_est_reload_start(ipvs, false); if (arr) ipvs->est_kt_count++; @@ -482,12 +492,11 @@ out: /* Start estimation for stats */ int ip_vs_start_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats) { + struct ip_vs_est_kt_data *kd = ipvs->est_kt_count > 0 ? + ipvs->est_kt_arr[0] : NULL; struct ip_vs_estimator *est = &stats->est; int ret; - if (!ipvs->est_max_threads && READ_ONCE(ipvs->enable)) - ipvs->est_max_threads = ip_vs_est_max_threads(ipvs); - est->ktid = -1; est->ktrow = IPVS_EST_NTICKS - 1; /* Initial delay */ @@ -496,8 +505,15 @@ int ip_vs_start_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats) * will not allocate much memory, just for kt 0. */ ret = 0; - if (!ipvs->est_kt_count || !ipvs->est_kt_arr[0]) + if (!kd) { ret = ip_vs_est_add_kthread(ipvs); + } else if (!kd->needed) { + mutex_lock(&ipvs->est_mutex); + /* We have job for the kt 0 task */ + kd->needed = 1; + ip_vs_est_reload_start(ipvs, true); + mutex_unlock(&ipvs->est_mutex); + } if (ret >= 0) hlist_add_head(&est->list, &ipvs->est_temp_list); else @@ -578,16 +594,14 @@ void ip_vs_stop_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats) } end_kt0: - /* kt 0 is freed after all other kthreads and chains are empty */ + /* kt 0 task is stopped after all other kt slots and chains are empty */ if (ipvs->est_kt_count == 1 && hlist_empty(&ipvs->est_temp_list)) { kd = ipvs->est_kt_arr[0]; - if (!kd || !kd->est_count) { + if (kd && !kd->est_count) { mutex_lock(&ipvs->est_mutex); - if (kd) { - ip_vs_est_kthread_destroy(kd); - ipvs->est_kt_arr[0] = NULL; - } - ipvs->est_kt_count--; + /* Keep the kt0 data but request kthread_stop */ + kd->needed = 0; + ip_vs_est_reload_start(ipvs, true); mutex_unlock(&ipvs->est_mutex); ipvs->est_add_ktid = 0; } @@ -647,9 +661,9 @@ static int ip_vs_est_calc_limits(struct netns_ipvs *ipvs, int *chain_max) u64 val; INIT_HLIST_HEAD(&chain); - mutex_lock(&ipvs->service_mutex); + mutex_lock(&ipvs->est_mutex); kd = ipvs->est_kt_arr[0]; - mutex_unlock(&ipvs->service_mutex); + mutex_unlock(&ipvs->est_mutex); s = kd ? kd->calc_stats : NULL; if (!s) goto out; @@ -748,16 +762,16 @@ static void ip_vs_est_calc_phase(struct netns_ipvs *ipvs) if (!ip_vs_est_calc_limits(ipvs, &chain_max)) return; - mutex_lock(&ipvs->service_mutex); - /* Stop all other tasks, so that we can immediately move the * estimators to est_temp_list without RCU grace period */ mutex_lock(&ipvs->est_mutex); for (id = 1; id < ipvs->est_kt_count; id++) { /* netns clean up started, abort */ - if (!READ_ONCE(ipvs->enable)) - goto unlock2; + if (kthread_should_stop() || !READ_ONCE(ipvs->enable)) { + mutex_unlock(&ipvs->est_mutex); + return; + } kd = ipvs->est_kt_arr[id]; if (!kd) continue; @@ -765,9 +779,11 @@ static void ip_vs_est_calc_phase(struct netns_ipvs *ipvs) } mutex_unlock(&ipvs->est_mutex); + mutex_lock(&ipvs->service_mutex); + /* Move all estimators to est_temp_list but carefully, * all estimators and kthread data can be released while - * we reschedule. Even for kthread 0. + * we reschedule. */ step = 0; @@ -849,9 +865,7 @@ walk_chain: ip_vs_stop_estimator(ipvs, stats); /* Tasks are stopped, move without RCU grace period */ est->ktid = -1; - est->ktrow = row - kd->est_row; - if (est->ktrow < 0) - est->ktrow += IPVS_EST_NTICKS; + est->ktrow = delay; hlist_add_head(&est->list, &ipvs->est_temp_list); /* kd freed ? */ if (last) @@ -889,7 +903,6 @@ end_dequeue: if (genid == atomic_read(&ipvs->est_genid)) ipvs->est_calc_phase = 0; -unlock2: mutex_unlock(&ipvs->est_mutex); unlock: diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 645d2c43ebf7..7e10fa65cbdd 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -466,9 +466,13 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, if (!ih) goto out_unlock; - if (ct->proto.sctp.init[dir] && ct->proto.sctp.init[!dir]) - ct->proto.sctp.init[!dir] = 0; - ct->proto.sctp.init[dir] = 1; + /* Do not record INIT matching peer vtag (stale or retransmitted INIT). */ + if (old_state == SCTP_CONNTRACK_NONE || + ct->proto.sctp.vtag[!dir] != ih->init_tag) { + if (ct->proto.sctp.init[dir] && ct->proto.sctp.init[!dir]) + ct->proto.sctp.init[!dir] = 0; + ct->proto.sctp.init[dir] = 1; + } pr_debug("Setting vtag %x for dir %d\n", ih->init_tag, !dir); ct->proto.sctp.vtag[!dir] = ih->init_tag; diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 182cfb119448..1eb55907d470 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -181,6 +181,57 @@ static int sip_parse_addr(const struct nf_conn *ct, const char *cp, return 1; } +/* Parse optional port number after IP address. + * Returns false on malformed input, true otherwise. + * If port is non-NULL, stores parsed port in network byte order. + * If no port is present, sets *port to default SIP port. + */ +static bool sip_parse_port(const char *dptr, const char **endp, + const char *limit, __be16 *port) +{ + unsigned int p = 0; + int len = 0; + + if (dptr >= limit) + return false; + + if (*dptr != ':') { + if (port) + *port = htons(SIP_PORT); + if (endp) + *endp = dptr; + return true; + } + + dptr++; /* skip ':' */ + + while (dptr < limit && isdigit(*dptr)) { + p = p * 10 + (*dptr - '0'); + dptr++; + len++; + if (len > 5) /* max "65535" */ + return false; + } + + if (len == 0) + return false; + + /* reached limit while parsing port */ + if (dptr >= limit) + return false; + + if (p < 1024 || p > 65535) + return false; + + if (port) + *port = htons(p); + + if (endp) + *endp = dptr; + + return true; +} + /* skip ip address. returns its length. */ static int epaddr_len(const struct nf_conn *ct, const char *dptr, const char *limit, int *shift) @@ -193,11 +244,8 @@ static int epaddr_len(const struct nf_conn *ct, const char *dptr, return 0; } - /* Port number */ - if (*dptr == ':') { - dptr++; - dptr += digits_len(ct, dptr, limit, shift); - } + if (!sip_parse_port(dptr, &dptr, limit, NULL)) + return 0; return dptr - aux; } @@ -228,6 +276,51 @@ static int skp_epaddr_len(const struct nf_conn *ct, const char *dptr, return epaddr_len(ct, dptr, limit, shift); } +/* simple_strtoul stops after first non-number character. + * But as we're not dealing with c-strings, we can't rely on + * hitting \r,\n,\0 etc. before moving past end of buffer. + * + * This is a variant of simple_strtoul, but doesn't require + * a c-string. + * + * If value exceeds UINT_MAX, 0 is returned. + */ +static unsigned int sip_strtouint(const char *cp, unsigned int len, char **endp) +{ + const unsigned int max = sizeof("4294967295"); + unsigned int olen = len; + const char *s = cp; + u64 result = 0; + + if (len > max) + len = max; + + while (olen > 0 && isdigit(*s)) { + unsigned int value; + + if (len == 0) + goto err; + + value = *s - '0'; + result = result * 10 + value; + + if (result > UINT_MAX) + goto err; + s++; + len--; + olen--; + } + + if (endp) + *endp = (char *)s; + + return result; +err: + if (endp) + *endp = (char *)cp; + return 0; +} + /* Parse a SIP request line of the form: * * Request-Line = Method SP Request-URI SP SIP-Version CRLF @@ -241,7 +334,6 @@ int ct_sip_parse_request(const struct nf_conn *ct, { const char *start = dptr, *limit = dptr + datalen, *end; unsigned int mlen; - unsigned int p; int shift = 0; /* Skip method and following whitespace */ @@ -267,14 +359,8 @@ int ct_sip_parse_request(const struct nf_conn *ct, if (!sip_parse_addr(ct, dptr, &end, addr, limit, true)) return -1; - if (end < limit && *end == ':') { - end++; - p = simple_strtoul(end, (char **)&end, 10); - if (p < 1024 || p > 65535) - return -1; - *port = htons(p); - } else - *port = htons(SIP_PORT); + if (!sip_parse_port(end, &end, limit, port)) + return -1; if (end == dptr) return 0; @@ -509,7 +595,6 @@ int ct_sip_parse_header_uri(const struct nf_conn *ct, const char *dptr, union nf_inet_addr *addr, __be16 *port) { const char *c, *limit = dptr + datalen; - unsigned int p; int ret; ret = ct_sip_walk_headers(ct, dptr, dataoff ? *dataoff : 0, datalen, @@ -520,14 +605,8 @@ int ct_sip_parse_header_uri(const struct nf_conn *ct, const char *dptr, if (!sip_parse_addr(ct, dptr + *matchoff, &c, addr, limit, true)) return -1; - if (*c == ':') { - c++; - p = simple_strtoul(c, (char **)&c, 10); - if (p < 1024 || p > 65535) - return -1; - *port = htons(p); - } else - *port = htons(SIP_PORT); + if (!sip_parse_port(c, &c, limit, port)) + return -1; if (dataoff) *dataoff = c - dptr; @@ -609,7 +688,7 @@ int ct_sip_parse_numerical_param(const struct nf_conn *ct, const char *dptr, return 0; start += strlen(name); - *val = simple_strtoul(start, &end, 0); + *val = sip_strtouint(start, limit - start, (char **)&end); if (start == end) return -1; if (matchoff && matchlen) { @@ -1064,6 +1143,8 @@ static int process_sdp(struct sk_buff *skb, unsigned int protoff, mediaoff = sdpoff; for (i = 0; i < ARRAY_SIZE(sdp_media_types); ) { + char *end; + if (ct_sip_get_sdp_header(ct, *dptr, mediaoff, *datalen, SDP_HDR_MEDIA, SDP_HDR_UNSPEC, &mediaoff, &medialen) <= 0) @@ -1079,8 +1160,8 @@ static int process_sdp(struct sk_buff *skb, unsigned int protoff, mediaoff += t->len; medialen -= t->len; - port = simple_strtoul(*dptr + mediaoff, NULL, 10); - if (port == 0) + port = sip_strtouint(*dptr + mediaoff, *datalen - mediaoff, (char **)&end); + if (port == 0 || *dptr + mediaoff == end) continue; if (port < 1024 || port > 65535) { nf_ct_helper_log(skb, ct, "wrong port %u", port); @@ -1254,7 +1335,7 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff, */ if (ct_sip_get_header(ct, *dptr, 0, *datalen, SIP_HDR_EXPIRES, &matchoff, &matchlen) > 0) - expires = simple_strtoul(*dptr + matchoff, NULL, 10); + expires = sip_strtouint(*dptr + matchoff, *datalen - matchoff, NULL); ret = ct_sip_parse_header_uri(ct, *dptr, NULL, *datalen, SIP_HDR_CONTACT, NULL, @@ -1358,7 +1439,7 @@ static int process_register_response(struct sk_buff *skb, unsigned int protoff, if (ct_sip_get_header(ct, *dptr, 0, *datalen, SIP_HDR_EXPIRES, &matchoff, &matchlen) > 0) - expires = simple_strtoul(*dptr + matchoff, NULL, 10); + expires = sip_strtouint(*dptr + matchoff, *datalen - matchoff, NULL); while (1) { unsigned int c_expires = expires; @@ -1418,10 +1499,12 @@ static int process_sip_response(struct sk_buff *skb, unsigned int protoff, struct nf_conn *ct = nf_ct_get(skb, &ctinfo); unsigned int matchoff, matchlen, matchend; unsigned int code, cseq, i; + char *end; if (*datalen < strlen("SIP/2.0 200")) return NF_ACCEPT; - code = simple_strtoul(*dptr + strlen("SIP/2.0 "), NULL, 10); + code = sip_strtouint(*dptr + strlen("SIP/2.0 "), + *datalen - strlen("SIP/2.0 "), NULL); if (!code) { nf_ct_helper_log(skb, ct, "cannot get code"); return NF_DROP; @@ -1432,8 +1515,8 @@ static int process_sip_response(struct sk_buff *skb, unsigned int protoff, nf_ct_helper_log(skb, ct, "cannot parse cseq"); return NF_DROP; } - cseq = simple_strtoul(*dptr + matchoff, NULL, 10); - if (!cseq && *(*dptr + matchoff) != '0') { + cseq = sip_strtouint(*dptr + matchoff, *datalen - matchoff, (char **)&end); + if (*dptr + matchoff == end) { nf_ct_helper_log(skb, ct, "cannot get cseq"); return NF_DROP; } @@ -1482,6 +1565,7 @@ static int process_sip_request(struct sk_buff *skb, unsigned int protoff, for (i = 0; i < ARRAY_SIZE(sip_handlers); i++) { const struct sip_handler *handler; + char *end; handler = &sip_handlers[i]; if (handler->request == NULL) @@ -1498,8 +1582,8 @@ static int process_sip_request(struct sk_buff *skb, unsigned int protoff, nf_ct_helper_log(skb, ct, "cannot parse cseq"); return NF_DROP; } - cseq = simple_strtoul(*dptr + matchoff, NULL, 10); - if (!cseq && *(*dptr + matchoff) != '0') { + cseq = sip_strtouint(*dptr + matchoff, *datalen - matchoff, (char **)&end); + if (*dptr + matchoff == end) { nf_ct_helper_log(skb, ct, "cannot get cseq"); return NF_DROP; } @@ -1575,7 +1659,7 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff, &matchoff, &matchlen) <= 0) break; - clen = simple_strtoul(dptr + matchoff, (char **)&end, 10); + clen = sip_strtouint(dptr + matchoff, datalen - matchoff, (char **)&end); if (dptr + matchoff == end) break; diff --git a/net/netfilter/nf_dup_netdev.c b/net/netfilter/nf_dup_netdev.c index e348fb90b8dc..3b0a70e154cd 100644 --- a/net/netfilter/nf_dup_netdev.c +++ b/net/netfilter/nf_dup_netdev.c @@ -13,22 +13,6 @@ #include <net/netfilter/nf_tables_offload.h> #include <net/netfilter/nf_dup_netdev.h> -#define NF_RECURSION_LIMIT 2 - -#ifndef CONFIG_PREEMPT_RT -static u8 *nf_get_nf_dup_skb_recursion(void) -{ - return this_cpu_ptr(&softnet_data.xmit.nf_dup_skb_recursion); -} -#else - -static u8 *nf_get_nf_dup_skb_recursion(void) -{ - return ¤t->net_xmit.nf_dup_skb_recursion; -} - -#endif - static void nf_do_netdev_egress(struct sk_buff *skb, struct net_device *dev, enum nf_dev_hooks hook) { diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 2c4140e6f53c..785d8c244a77 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -122,6 +122,7 @@ static int flow_offload_fill_route(struct flow_offload *flow, flow_tuple->tun = route->tuple[dir].in.tun; flow_tuple->encap_num = route->tuple[dir].in.num_encaps; + flow_tuple->needs_gso_segment = route->tuple[dir].out.needs_gso_segment; flow_tuple->tun_num = route->tuple[dir].in.num_tuns; switch (route->tuple[dir].xmit_type) { diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index fd56d663cb5b..9c05a50d6013 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -445,13 +445,13 @@ static void nf_flow_encap_pop(struct nf_flowtable_ctx *ctx, switch (skb->protocol) { case htons(ETH_P_8021Q): vlan_hdr = (struct vlan_hdr *)skb->data; - __skb_pull(skb, VLAN_HLEN); + skb_pull_rcsum(skb, VLAN_HLEN); vlan_set_encap_proto(skb, vlan_hdr); skb_reset_network_header(skb); break; case htons(ETH_P_PPP_SES): skb->protocol = __nf_flow_pppoe_proto(skb); - skb_pull(skb, PPPOE_SES_HLEN); + skb_pull_rcsum(skb, PPPOE_SES_HLEN); skb_reset_network_header(skb); break; } @@ -462,23 +462,6 @@ static void nf_flow_encap_pop(struct nf_flowtable_ctx *ctx, nf_flow_ip_tunnel_pop(ctx, skb); } -struct nf_flow_xmit { - const void *dest; - const void *source; - struct net_device *outdev; -}; - -static unsigned int nf_flow_queue_xmit(struct net *net, struct sk_buff *skb, - struct nf_flow_xmit *xmit) -{ - skb->dev = xmit->outdev; - dev_hard_header(skb, skb->dev, ntohs(skb->protocol), - xmit->dest, xmit->source, skb->len); - dev_queue_xmit(skb); - - return NF_STOLEN; -} - static struct flow_offload_tuple_rhash * nf_flow_offload_lookup(struct nf_flowtable_ctx *ctx, struct nf_flowtable *flow_table, struct sk_buff *skb) @@ -524,7 +507,7 @@ static int nf_flow_offload_forward(struct nf_flowtable_ctx *ctx, return 0; } - if (skb_try_make_writable(skb, thoff + ctx->hdrsize)) + if (skb_ensure_writable(skb, thoff + ctx->hdrsize)) return -1; flow_offload_refresh(flow_table, flow, false); @@ -544,7 +527,34 @@ static int nf_flow_offload_forward(struct nf_flowtable_ctx *ctx, return 1; } -static int nf_flow_pppoe_push(struct sk_buff *skb, u16 id) +/* Similar to skb_vlan_push. */ +static int nf_flow_vlan_push(struct sk_buff *skb, __be16 proto, u16 id, + u32 needed_headroom) +{ + if (skb_vlan_tag_present(skb)) { + struct vlan_hdr *vhdr; + + if (skb_cow_head(skb, needed_headroom + VLAN_HLEN)) + return -1; + + __skb_push(skb, VLAN_HLEN); + if (skb_mac_header_was_set(skb)) + skb->mac_header -= VLAN_HLEN; + + vhdr = (struct vlan_hdr *)skb->data; + skb->network_header -= VLAN_HLEN; + vhdr->h_vlan_TCI = htons(skb_vlan_tag_get(skb)); + vhdr->h_vlan_encapsulated_proto = skb->protocol; + skb->protocol = skb->vlan_proto; + skb_postpush_rcsum(skb, skb->data, VLAN_HLEN); + } + __vlan_hwaccel_put_tag(skb, proto, id); + + return 0; +} + +static int nf_flow_pppoe_push(struct sk_buff *skb, u16 id, + u32 needed_headroom) { int data_len = skb->len + sizeof(__be16); struct ppp_hdr { @@ -553,7 +563,7 @@ static int nf_flow_pppoe_push(struct sk_buff *skb, u16 id) } *ph; __be16 proto; - if (skb_cow_head(skb, PPPOE_SES_HLEN)) + if (skb_cow_head(skb, needed_headroom + PPPOE_SES_HLEN)) return -1; switch (skb->protocol) { @@ -730,21 +740,24 @@ static int nf_flow_tunnel_v6_push(struct net *net, struct sk_buff *skb, } static int nf_flow_encap_push(struct sk_buff *skb, - struct flow_offload_tuple *tuple) + struct flow_offload_tuple *tuple, + struct net_device *outdev) { + u32 needed_headroom = LL_RESERVED_SPACE(outdev); int i; - for (i = 0; i < tuple->encap_num; i++) { + for (i = tuple->encap_num - 1; i >= 0; i--) { switch (tuple->encap[i].proto) { case htons(ETH_P_8021Q): case htons(ETH_P_8021AD): - skb_reset_mac_header(skb); - if (skb_vlan_push(skb, tuple->encap[i].proto, - tuple->encap[i].id) < 0) + if (nf_flow_vlan_push(skb, tuple->encap[i].proto, + tuple->encap[i].id, + needed_headroom) < 0) return -1; break; case htons(ETH_P_PPP_SES): - if (nf_flow_pppoe_push(skb, tuple->encap[i].id) < 0) + if (nf_flow_pppoe_push(skb, tuple->encap[i].id, + needed_headroom) < 0) return -1; break; } @@ -753,6 +766,76 @@ static int nf_flow_encap_push(struct sk_buff *skb, return 0; } +struct nf_flow_xmit { + const void *dest; + const void *source; + struct net_device *outdev; + struct flow_offload_tuple *tuple; + bool needs_gso_segment; +}; + +static void __nf_flow_queue_xmit(struct net *net, struct sk_buff *skb, + struct nf_flow_xmit *xmit) +{ + struct net_device *dev = xmit->outdev; + unsigned int hh_len = LL_RESERVED_SPACE(dev); + + if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { + skb = skb_expand_head(skb, hh_len); + if (!skb) + return; + } + + skb->dev = dev; + dev_hard_header(skb, dev, ntohs(skb->protocol), + xmit->dest, xmit->source, skb->len); + dev_queue_xmit(skb); +} + +static unsigned int nf_flow_encap_gso_xmit(struct net *net, struct sk_buff *skb, + struct nf_flow_xmit *xmit) +{ + struct sk_buff *segs, *nskb; + + segs = skb_gso_segment(skb, 0); + if (IS_ERR(segs)) + return NF_DROP; + + if (segs) + consume_skb(skb); + else + segs = skb; + + skb_list_walk_safe(segs, segs, nskb) { + skb_mark_not_on_list(segs); + + if (nf_flow_encap_push(segs, xmit->tuple, xmit->outdev) < 0) { + kfree_skb(segs); + kfree_skb_list(nskb); + return NF_STOLEN; + } + __nf_flow_queue_xmit(net, segs, xmit); + } + + return NF_STOLEN; +} + +static unsigned int nf_flow_queue_xmit(struct net *net, struct sk_buff *skb, + struct nf_flow_xmit *xmit) +{ + if (xmit->tuple->encap_num) { + if (skb_is_gso(skb) && xmit->needs_gso_segment) + return nf_flow_encap_gso_xmit(net, skb, xmit); + + if (nf_flow_encap_push(skb, xmit->tuple, xmit->outdev) < 0) + return NF_DROP; + } + + __nf_flow_queue_xmit(net, skb, xmit); + + return NF_STOLEN; +} + unsigned int nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) @@ -797,9 +880,6 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, if (nf_flow_tunnel_v4_push(state->net, skb, other_tuple, &ip_daddr) < 0) return NF_DROP; - if (nf_flow_encap_push(skb, other_tuple) < 0) - return NF_DROP; - switch (tuplehash->tuple.xmit_type) { case FLOW_OFFLOAD_XMIT_NEIGH: rt = dst_rtable(tuplehash->tuple.dst_cache); @@ -829,6 +909,8 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, WARN_ON_ONCE(1); return NF_DROP; } + xmit.tuple = other_tuple; + xmit.needs_gso_segment = tuplehash->tuple.needs_gso_segment; return nf_flow_queue_xmit(state->net, skb, &xmit); } @@ -1037,7 +1119,7 @@ static int nf_flow_offload_ipv6_forward(struct nf_flowtable_ctx *ctx, return 0; } - if (skb_try_make_writable(skb, thoff + ctx->hdrsize)) + if (skb_ensure_writable(skb, thoff + ctx->hdrsize)) return -1; flow_offload_refresh(flow_table, flow, false); @@ -1119,9 +1201,6 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, &ip6_daddr, encap_limit) < 0) return NF_DROP; - if (nf_flow_encap_push(skb, other_tuple) < 0) - return NF_DROP; - switch (tuplehash->tuple.xmit_type) { case FLOW_OFFLOAD_XMIT_NEIGH: rt = dst_rt6_info(tuplehash->tuple.dst_cache); @@ -1151,6 +1230,8 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, WARN_ON_ONCE(1); return NF_DROP; } + xmit.tuple = other_tuple; + xmit.needs_gso_segment = tuplehash->tuple.needs_gso_segment; return nf_flow_queue_xmit(state->net, skb, &xmit); } diff --git a/net/netfilter/nf_flow_table_path.c b/net/netfilter/nf_flow_table_path.c index 6bb9579dcc2a..9e88ea6a2eef 100644 --- a/net/netfilter/nf_flow_table_path.c +++ b/net/netfilter/nf_flow_table_path.c @@ -86,6 +86,7 @@ struct nft_forward_info { u8 ingress_vlans; u8 h_source[ETH_ALEN]; u8 h_dest[ETH_ALEN]; + bool needs_gso_segment; enum flow_offload_xmit_type xmit_type; }; @@ -138,8 +139,11 @@ static void nft_dev_path_info(const struct net_device_path_stack *stack, path->encap.proto; info->num_encaps++; } - if (path->type == DEV_PATH_PPPOE) + if (path->type == DEV_PATH_PPPOE) { memcpy(info->h_dest, path->encap.h_dest, ETH_ALEN); + info->xmit_type = FLOW_OFFLOAD_XMIT_DIRECT; + info->needs_gso_segment = 1; + } break; case DEV_PATH_BRIDGE: if (is_zero_ether_addr(info->h_source)) @@ -279,6 +283,7 @@ static void nft_dev_forward_path(const struct nft_pktinfo *pkt, memcpy(route->tuple[dir].out.h_dest, info.h_dest, ETH_ALEN); route->tuple[dir].xmit_type = info.xmit_type; } + route->tuple[dir].out.needs_gso_segment = info.needs_gso_segment; } int nft_flow_route(const struct nft_pktinfo *pkt, const struct nf_conn *ct, diff --git a/net/netfilter/nf_nat_sip.c b/net/netfilter/nf_nat_sip.c index c845b6d1a2bd..9fbfc6bff0c2 100644 --- a/net/netfilter/nf_nat_sip.c +++ b/net/netfilter/nf_nat_sip.c @@ -246,6 +246,7 @@ static unsigned int nf_nat_sip(struct sk_buff *skb, unsigned int protoff, if (ct_sip_parse_numerical_param(ct, *dptr, matchend, *datalen, "rport=", &poff, &plen, &n) > 0 && + n >= 1024 && n <= 65535 && htons(n) == ct->tuplehash[dir].tuple.dst.u.udp.port && htons(n) != ct->tuplehash[!dir].tuple.src.u.udp.port) { __be16 p = ct->tuplehash[!dir].tuple.src.u.udp.port; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 8537b94653d3..87387adbca65 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -374,7 +374,40 @@ static void nft_netdev_hook_free_rcu(struct nft_hook *hook) call_rcu(&hook->rcu, __nft_netdev_hook_free_rcu); } +static void nft_netdev_hook_unlink_free_rcu(struct nft_hook *hook) +{ + list_del_rcu(&hook->list); + nft_netdev_hook_free_rcu(hook); +} + +static void nft_trans_hook_destroy(struct nft_trans_hook *trans_hook) +{ + list_del(&trans_hook->list); + kfree(trans_hook); +} + +static void nft_netdev_unregister_trans_hook(struct net *net, + const struct nft_table *table, + struct list_head *hook_list) +{ + struct nft_trans_hook *trans_hook, *next; + struct nf_hook_ops *ops; + struct nft_hook *hook; + + list_for_each_entry_safe(trans_hook, next, hook_list, list) { + hook = trans_hook->hook; + + if (!(table->flags & NFT_TABLE_F_DORMANT)) { + list_for_each_entry(ops, &hook->ops_list, list) + nf_unregister_net_hook(net, ops); + } + nft_netdev_hook_unlink_free_rcu(hook); + nft_trans_hook_destroy(trans_hook); + } +} + static void nft_netdev_unregister_hooks(struct net *net, + const struct nft_table *table, struct list_head *hook_list, bool release_netdev) { @@ -382,12 +415,12 @@ static void nft_netdev_unregister_hooks(struct net *net, struct nf_hook_ops *ops; list_for_each_entry_safe(hook, next, hook_list, list) { - list_for_each_entry(ops, &hook->ops_list, list) - nf_unregister_net_hook(net, ops); - if (release_netdev) { - list_del(&hook->list); - nft_netdev_hook_free_rcu(hook); + if (!(table->flags & NFT_TABLE_F_DORMANT)) { + list_for_each_entry(ops, &hook->ops_list, list) + nf_unregister_net_hook(net, ops); } + if (release_netdev) + nft_netdev_hook_unlink_free_rcu(hook); } } @@ -422,20 +455,25 @@ static void __nf_tables_unregister_hook(struct net *net, struct nft_base_chain *basechain; const struct nf_hook_ops *ops; - if (table->flags & NFT_TABLE_F_DORMANT || - !nft_is_base_chain(chain)) + if (!nft_is_base_chain(chain)) return; basechain = nft_base_chain(chain); ops = &basechain->ops; + /* must also be called for dormant tables */ + if (nft_base_chain_netdev(table->family, basechain->ops.hooknum)) { + nft_netdev_unregister_hooks(net, table, &basechain->hook_list, + release_netdev); + return; + } + + if (table->flags & NFT_TABLE_F_DORMANT) + return; + if (basechain->type->ops_unregister) return basechain->type->ops_unregister(net, ops); - if (nft_base_chain_netdev(table->family, basechain->ops.hooknum)) - nft_netdev_unregister_hooks(net, &basechain->hook_list, - release_netdev); - else - nf_unregister_net_hook(net, &basechain->ops); + nf_unregister_net_hook(net, &basechain->ops); } static void nf_tables_unregister_hook(struct net *net, @@ -1942,15 +1980,69 @@ static int nft_nla_put_hook_dev(struct sk_buff *skb, struct nft_hook *hook) return nla_put_string(skb, attr, hook->ifname); } +struct nft_hook_dump_ctx { + struct nft_hook *first; + int n; +}; + +static int nft_dump_basechain_hook_one(struct sk_buff *skb, + struct nft_hook *hook, + struct nft_hook_dump_ctx *dump_ctx) +{ + if (!dump_ctx->first) + dump_ctx->first = hook; + + if (nft_nla_put_hook_dev(skb, hook)) + return -1; + + dump_ctx->n++; + + return 0; +} + +static int nft_dump_basechain_hook_list(struct sk_buff *skb, + const struct net *net, + const struct list_head *hook_list, + struct nft_hook_dump_ctx *dump_ctx) +{ + struct nft_hook *hook; + int err; + + list_for_each_entry_rcu(hook, hook_list, list, + lockdep_commit_lock_is_held(net)) { + err = nft_dump_basechain_hook_one(skb, hook, dump_ctx); + if (err < 0) + return err; + } + + return 0; +} + +static int nft_dump_basechain_trans_hook_list(struct sk_buff *skb, + const struct list_head *trans_hook_list, + struct nft_hook_dump_ctx *dump_ctx) +{ + struct nft_trans_hook *trans_hook; + int err; + + list_for_each_entry(trans_hook, trans_hook_list, list) { + err = nft_dump_basechain_hook_one(skb, trans_hook->hook, dump_ctx); + if (err < 0) + return err; + } + + return 0; +} + static int nft_dump_basechain_hook(struct sk_buff *skb, const struct net *net, int family, const struct nft_base_chain *basechain, - const struct list_head *hook_list) + const struct list_head *hook_list, + const struct list_head *trans_hook_list) { const struct nf_hook_ops *ops = &basechain->ops; - struct nft_hook *hook, *first = NULL; + struct nft_hook_dump_ctx dump_hook_ctx = {}; struct nlattr *nest, *nest_devs; - int n = 0; nest = nla_nest_start_noflag(skb, NFTA_CHAIN_HOOK); if (nest == NULL) @@ -1965,23 +2057,23 @@ static int nft_dump_basechain_hook(struct sk_buff *skb, if (!nest_devs) goto nla_put_failure; - if (!hook_list) + if (!hook_list && !trans_hook_list) hook_list = &basechain->hook_list; - list_for_each_entry_rcu(hook, hook_list, list, - lockdep_commit_lock_is_held(net)) { - if (!first) - first = hook; - - if (nft_nla_put_hook_dev(skb, hook)) - goto nla_put_failure; - n++; + if (hook_list && + nft_dump_basechain_hook_list(skb, net, hook_list, &dump_hook_ctx)) { + goto nla_put_failure; + } else if (trans_hook_list && + nft_dump_basechain_trans_hook_list(skb, trans_hook_list, + &dump_hook_ctx)) { + goto nla_put_failure; } + nla_nest_end(skb, nest_devs); - if (n == 1 && - !hook_is_prefix(first) && - nla_put_string(skb, NFTA_HOOK_DEV, first->ifname)) + if (dump_hook_ctx.n == 1 && + !hook_is_prefix(dump_hook_ctx.first) && + nla_put_string(skb, NFTA_HOOK_DEV, dump_hook_ctx.first->ifname)) goto nla_put_failure; } nla_nest_end(skb, nest); @@ -1995,7 +2087,8 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, u32 portid, u32 seq, int event, u32 flags, int family, const struct nft_table *table, const struct nft_chain *chain, - const struct list_head *hook_list) + const struct list_head *hook_list, + const struct list_head *trans_hook_list) { struct nlmsghdr *nlh; @@ -2011,7 +2104,7 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, NFTA_CHAIN_PAD)) goto nla_put_failure; - if (!hook_list && + if (!hook_list && !trans_hook_list && (event == NFT_MSG_DELCHAIN || event == NFT_MSG_DESTROYCHAIN)) { nlmsg_end(skb, nlh); @@ -2022,7 +2115,8 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, const struct nft_base_chain *basechain = nft_base_chain(chain); struct nft_stats __percpu *stats; - if (nft_dump_basechain_hook(skb, net, family, basechain, hook_list)) + if (nft_dump_basechain_hook(skb, net, family, basechain, + hook_list, trans_hook_list)) goto nla_put_failure; if (nla_put_be32(skb, NFTA_CHAIN_POLICY, @@ -2058,7 +2152,8 @@ nla_put_failure: } static void nf_tables_chain_notify(const struct nft_ctx *ctx, int event, - const struct list_head *hook_list) + const struct list_head *hook_list, + const struct list_head *trans_hook_list) { struct nftables_pernet *nft_net; struct sk_buff *skb; @@ -2078,7 +2173,7 @@ static void nf_tables_chain_notify(const struct nft_ctx *ctx, int event, err = nf_tables_fill_chain_info(skb, ctx->net, ctx->portid, ctx->seq, event, flags, ctx->family, ctx->table, - ctx->chain, hook_list); + ctx->chain, hook_list, trans_hook_list); if (err < 0) { kfree_skb(skb); goto err; @@ -2124,7 +2219,7 @@ static int nf_tables_dump_chains(struct sk_buff *skb, NFT_MSG_NEWCHAIN, NLM_F_MULTI, table->family, table, - chain, NULL) < 0) + chain, NULL, NULL) < 0) goto done; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); @@ -2178,7 +2273,7 @@ static int nf_tables_getchain(struct sk_buff *skb, const struct nfnl_info *info, err = nf_tables_fill_chain_info(skb2, net, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, NFT_MSG_NEWCHAIN, - 0, family, table, chain, NULL); + 0, family, table, chain, NULL, NULL); if (err < 0) goto err_fill_chain_info; @@ -2271,10 +2366,8 @@ void nf_tables_chain_destroy(struct nft_chain *chain) if (nft_base_chain_netdev(table->family, basechain->ops.hooknum)) { list_for_each_entry_safe(hook, next, - &basechain->hook_list, list) { - list_del_rcu(&hook->list); - nft_netdev_hook_free_rcu(hook); - } + &basechain->hook_list, list) + nft_netdev_hook_unlink_free_rcu(hook); } module_put(basechain->type->owner); if (rcu_access_pointer(basechain->stats)) { @@ -2343,8 +2436,12 @@ static struct nft_hook *nft_hook_list_find(struct list_head *hook_list, list_for_each_entry(hook, hook_list, list) { if (!strncmp(hook->ifname, this->ifname, - min(hook->ifnamelen, this->ifnamelen))) + min(hook->ifnamelen, this->ifnamelen))) { + if (hook->flags & NFT_HOOK_REMOVE) + continue; + return hook; + } } return NULL; @@ -2974,6 +3071,7 @@ err_hooks: list_for_each_entry(ops, &h->ops_list, list) nf_unregister_net_hook(ctx->net, ops); } + /* hook.list is on stack, no need for list_del_rcu() */ list_del(&h->list); nft_netdev_hook_free_rcu(h); } @@ -3102,6 +3200,32 @@ static int nf_tables_newchain(struct sk_buff *skb, const struct nfnl_info *info, return nf_tables_addchain(&ctx, family, policy, flags, extack); } +static int nft_trans_delhook(struct nft_hook *hook, + struct list_head *del_list) +{ + struct nft_trans_hook *trans_hook; + + trans_hook = kmalloc_obj(*trans_hook, GFP_KERNEL); + if (!trans_hook) + return -ENOMEM; + + trans_hook->hook = hook; + list_add_tail(&trans_hook->list, del_list); + hook->flags |= NFT_HOOK_REMOVE; + + return 0; +} + +static void nft_trans_delhook_abort(struct list_head *del_list) +{ + struct nft_trans_hook *trans_hook, *next; + + list_for_each_entry_safe(trans_hook, next, del_list, list) { + trans_hook->hook->flags &= ~NFT_HOOK_REMOVE; + nft_trans_hook_destroy(trans_hook); + } +} + static int nft_delchain_hook(struct nft_ctx *ctx, struct nft_base_chain *basechain, struct netlink_ext_ack *extack) @@ -3128,7 +3252,10 @@ static int nft_delchain_hook(struct nft_ctx *ctx, err = -ENOENT; goto err_chain_del_hook; } - list_move(&hook->list, &chain_del_list); + if (nft_trans_delhook(hook, &chain_del_list) < 0) { + err = -ENOMEM; + goto err_chain_del_hook; + } } trans = nft_trans_alloc_chain(ctx, NFT_MSG_DELCHAIN); @@ -3148,7 +3275,7 @@ static int nft_delchain_hook(struct nft_ctx *ctx, return 0; err_chain_del_hook: - list_splice(&chain_del_list, &basechain->hook_list); + nft_trans_delhook_abort(&chain_del_list); nft_chain_release_hook(&chain_hook); return err; @@ -4086,6 +4213,7 @@ static int nft_table_validate(struct net *net, const struct nft_table *table) struct nft_chain *chain; struct nft_ctx ctx = { .net = net, + .table = (struct nft_table *)table, .family = table->family, }; int err = 0; @@ -8852,10 +8980,8 @@ static void __nft_unregister_flowtable_net_hooks(struct net *net, list_for_each_entry_safe(hook, next, hook_list, list) { list_for_each_entry(ops, &hook->ops_list, list) nft_unregister_flowtable_ops(net, flowtable, ops); - if (release_netdev) { - list_del(&hook->list); - nft_netdev_hook_free_rcu(hook); - } + if (release_netdev) + nft_netdev_hook_unlink_free_rcu(hook); } } @@ -8926,8 +9052,7 @@ err_unregister_net_hooks: nft_unregister_flowtable_ops(net, flowtable, ops); } - list_del_rcu(&hook->list); - nft_netdev_hook_free_rcu(hook); + nft_netdev_hook_unlink_free_rcu(hook); } return err; @@ -8937,9 +9062,25 @@ static void nft_hooks_destroy(struct list_head *hook_list) { struct nft_hook *hook, *next; - list_for_each_entry_safe(hook, next, hook_list, list) { - list_del_rcu(&hook->list); - nft_netdev_hook_free_rcu(hook); + list_for_each_entry_safe(hook, next, hook_list, list) + nft_netdev_hook_unlink_free_rcu(hook); +} + +static void nft_flowtable_unregister_trans_hook(struct net *net, + struct nft_flowtable *flowtable, + struct list_head *hook_list) +{ + struct nft_trans_hook *trans_hook, *next; + struct nf_hook_ops *ops; + struct nft_hook *hook; + + list_for_each_entry_safe(trans_hook, next, hook_list, list) { + hook = trans_hook->hook; + list_for_each_entry(ops, &hook->ops_list, list) + nft_unregister_flowtable_ops(net, flowtable, ops); + + nft_netdev_hook_unlink_free_rcu(hook); + nft_trans_hook_destroy(trans_hook); } } @@ -9028,8 +9169,7 @@ err_flowtable_update_hook: nft_unregister_flowtable_ops(ctx->net, flowtable, ops); } - list_del_rcu(&hook->list); - nft_netdev_hook_free_rcu(hook); + nft_netdev_hook_unlink_free_rcu(hook); } return err; @@ -9202,7 +9342,10 @@ static int nft_delflowtable_hook(struct nft_ctx *ctx, err = -ENOENT; goto err_flowtable_del_hook; } - list_move(&hook->list, &flowtable_del_list); + if (nft_trans_delhook(hook, &flowtable_del_list) < 0) { + err = -ENOMEM; + goto err_flowtable_del_hook; + } } trans = nft_trans_alloc(ctx, NFT_MSG_DELFLOWTABLE, @@ -9223,7 +9366,7 @@ static int nft_delflowtable_hook(struct nft_ctx *ctx, return 0; err_flowtable_del_hook: - list_splice(&flowtable_del_list, &flowtable->hook_list); + nft_trans_delhook_abort(&flowtable_del_list); nft_flowtable_hook_release(&flowtable_hook); return err; @@ -9288,8 +9431,10 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net, u32 portid, u32 seq, int event, u32 flags, int family, struct nft_flowtable *flowtable, - struct list_head *hook_list) + struct list_head *hook_list, + struct list_head *trans_hook_list) { + struct nft_trans_hook *trans_hook; struct nlattr *nest, *nest_devs; struct nft_hook *hook; struct nlmsghdr *nlh; @@ -9306,7 +9451,7 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net, NFTA_FLOWTABLE_PAD)) goto nla_put_failure; - if (!hook_list && + if (!hook_list && !trans_hook_list && (event == NFT_MSG_DELFLOWTABLE || event == NFT_MSG_DESTROYFLOWTABLE)) { nlmsg_end(skb, nlh); @@ -9328,13 +9473,20 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net, if (!nest_devs) goto nla_put_failure; - if (!hook_list) + if (!hook_list && !trans_hook_list) hook_list = &flowtable->hook_list; - list_for_each_entry_rcu(hook, hook_list, list, - lockdep_commit_lock_is_held(net)) { - if (nft_nla_put_hook_dev(skb, hook)) - goto nla_put_failure; + if (hook_list) { + list_for_each_entry_rcu(hook, hook_list, list, + lockdep_commit_lock_is_held(net)) { + if (nft_nla_put_hook_dev(skb, hook)) + goto nla_put_failure; + } + } else if (trans_hook_list) { + list_for_each_entry(trans_hook, trans_hook_list, list) { + if (nft_nla_put_hook_dev(skb, trans_hook->hook)) + goto nla_put_failure; + } } nla_nest_end(skb, nest_devs); nla_nest_end(skb, nest); @@ -9388,7 +9540,7 @@ static int nf_tables_dump_flowtable(struct sk_buff *skb, NFT_MSG_NEWFLOWTABLE, NLM_F_MULTI | NLM_F_APPEND, table->family, - flowtable, NULL) < 0) + flowtable, NULL, NULL) < 0) goto done; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); @@ -9488,7 +9640,7 @@ static int nf_tables_getflowtable(struct sk_buff *skb, err = nf_tables_fill_flowtable_info(skb2, net, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, NFT_MSG_NEWFLOWTABLE, 0, family, - flowtable, NULL); + flowtable, NULL, NULL); if (err < 0) goto err_fill_flowtable_info; @@ -9501,7 +9653,9 @@ err_fill_flowtable_info: static void nf_tables_flowtable_notify(struct nft_ctx *ctx, struct nft_flowtable *flowtable, - struct list_head *hook_list, int event) + struct list_head *hook_list, + struct list_head *trans_hook_list, + int event) { struct nftables_pernet *nft_net = nft_pernet(ctx->net); struct sk_buff *skb; @@ -9521,7 +9675,8 @@ static void nf_tables_flowtable_notify(struct nft_ctx *ctx, err = nf_tables_fill_flowtable_info(skb, ctx->net, ctx->portid, ctx->seq, event, flags, - ctx->family, flowtable, hook_list); + ctx->family, flowtable, + hook_list, trans_hook_list); if (err < 0) { kfree_skb(skb); goto err; @@ -9535,13 +9690,8 @@ err: static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable) { - struct nft_hook *hook, *next; - flowtable->data.type->free(&flowtable->data); - list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) { - list_del_rcu(&hook->list); - nft_netdev_hook_free_rcu(hook); - } + nft_hooks_destroy(&flowtable->hook_list); kfree(flowtable->name); module_put(flowtable->data.type->owner); kfree(flowtable); @@ -10060,9 +10210,7 @@ static void nft_commit_release(struct nft_trans *trans) break; case NFT_MSG_DELCHAIN: case NFT_MSG_DESTROYCHAIN: - if (nft_trans_chain_update(trans)) - nft_hooks_destroy(&nft_trans_chain_hooks(trans)); - else + if (!nft_trans_chain_update(trans)) nf_tables_chain_destroy(nft_trans_chain(trans)); break; case NFT_MSG_DELRULE: @@ -10083,9 +10231,7 @@ static void nft_commit_release(struct nft_trans *trans) break; case NFT_MSG_DELFLOWTABLE: case NFT_MSG_DESTROYFLOWTABLE: - if (nft_trans_flowtable_update(trans)) - nft_hooks_destroy(&nft_trans_flowtable_hooks(trans)); - else + if (!nft_trans_flowtable_update(trans)) nf_tables_flowtable_destroy(nft_trans_flowtable(trans)); break; } @@ -10845,31 +10991,28 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) if (nft_trans_chain_update(trans)) { nft_chain_commit_update(nft_trans_container_chain(trans)); nf_tables_chain_notify(&ctx, NFT_MSG_NEWCHAIN, - &nft_trans_chain_hooks(trans)); - list_splice(&nft_trans_chain_hooks(trans), - &nft_trans_basechain(trans)->hook_list); + &nft_trans_chain_hooks(trans), NULL); + list_splice_rcu(&nft_trans_chain_hooks(trans), + &nft_trans_basechain(trans)->hook_list); /* trans destroyed after rcu grace period */ } else { nft_chain_commit_drop_policy(nft_trans_container_chain(trans)); nft_clear(net, nft_trans_chain(trans)); - nf_tables_chain_notify(&ctx, NFT_MSG_NEWCHAIN, NULL); + nf_tables_chain_notify(&ctx, NFT_MSG_NEWCHAIN, NULL, NULL); nft_trans_destroy(trans); } break; case NFT_MSG_DELCHAIN: case NFT_MSG_DESTROYCHAIN: if (nft_trans_chain_update(trans)) { - nf_tables_chain_notify(&ctx, NFT_MSG_DELCHAIN, + nf_tables_chain_notify(&ctx, NFT_MSG_DELCHAIN, NULL, &nft_trans_chain_hooks(trans)); - if (!(table->flags & NFT_TABLE_F_DORMANT)) { - nft_netdev_unregister_hooks(net, - &nft_trans_chain_hooks(trans), - true); - } + nft_netdev_unregister_trans_hook(net, table, + &nft_trans_chain_hooks(trans)); } else { nft_chain_del(nft_trans_chain(trans)); nf_tables_chain_notify(&ctx, NFT_MSG_DELCHAIN, - NULL); + NULL, NULL); nf_tables_unregister_hook(ctx.net, ctx.table, nft_trans_chain(trans)); } @@ -10975,14 +11118,16 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nf_tables_flowtable_notify(&ctx, nft_trans_flowtable(trans), &nft_trans_flowtable_hooks(trans), + NULL, NFT_MSG_NEWFLOWTABLE); - list_splice(&nft_trans_flowtable_hooks(trans), - &nft_trans_flowtable(trans)->hook_list); + list_splice_rcu(&nft_trans_flowtable_hooks(trans), + &nft_trans_flowtable(trans)->hook_list); } else { nft_clear(net, nft_trans_flowtable(trans)); nf_tables_flowtable_notify(&ctx, nft_trans_flowtable(trans), NULL, + NULL, NFT_MSG_NEWFLOWTABLE); } nft_trans_destroy(trans); @@ -10992,16 +11137,18 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) if (nft_trans_flowtable_update(trans)) { nf_tables_flowtable_notify(&ctx, nft_trans_flowtable(trans), + NULL, &nft_trans_flowtable_hooks(trans), trans->msg_type); - nft_unregister_flowtable_net_hooks(net, - nft_trans_flowtable(trans), - &nft_trans_flowtable_hooks(trans)); + nft_flowtable_unregister_trans_hook(net, + nft_trans_flowtable(trans), + &nft_trans_flowtable_hooks(trans)); } else { list_del_rcu(&nft_trans_flowtable(trans)->list); nf_tables_flowtable_notify(&ctx, nft_trans_flowtable(trans), NULL, + NULL, trans->msg_type); nft_unregister_flowtable_net_hooks(net, nft_trans_flowtable(trans), @@ -11143,11 +11290,9 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) break; case NFT_MSG_NEWCHAIN: if (nft_trans_chain_update(trans)) { - if (!(table->flags & NFT_TABLE_F_DORMANT)) { - nft_netdev_unregister_hooks(net, - &nft_trans_chain_hooks(trans), - true); - } + nft_netdev_unregister_hooks(net, table, + &nft_trans_chain_hooks(trans), + true); free_percpu(nft_trans_chain_stats(trans)); kfree(nft_trans_chain_name(trans)); nft_trans_destroy(trans); @@ -11165,8 +11310,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) case NFT_MSG_DELCHAIN: case NFT_MSG_DESTROYCHAIN: if (nft_trans_chain_update(trans)) { - list_splice(&nft_trans_chain_hooks(trans), - &nft_trans_basechain(trans)->hook_list); + nft_trans_delhook_abort(&nft_trans_chain_hooks(trans)); } else { nft_use_inc_restore(&table->use); nft_clear(trans->net, nft_trans_chain(trans)); @@ -11280,8 +11424,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) case NFT_MSG_DELFLOWTABLE: case NFT_MSG_DESTROYFLOWTABLE: if (nft_trans_flowtable_update(trans)) { - list_splice(&nft_trans_flowtable_hooks(trans), - &nft_trans_flowtable(trans)->hook_list); + nft_trans_delhook_abort(&nft_trans_flowtable_hooks(trans)); } else { nft_use_inc_restore(&table->use); nft_clear(trans->net, nft_trans_flowtable(trans)); diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 5ddd5b6e135f..8ab186f86dd4 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -153,7 +153,7 @@ static bool nft_payload_fast_eval(const struct nft_expr *expr, if (priv->base == NFT_PAYLOAD_NETWORK_HEADER) ptr = skb_network_header(skb) + pkt->nhoff; else { - if (!(pkt->flags & NFT_PKTINFO_L4PROTO)) + if (!(pkt->flags & NFT_PKTINFO_L4PROTO) || pkt->fragoff) return false; ptr = skb->data + nft_thoff(pkt); } diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c index 13808e9cd999..94dccdcfa06b 100644 --- a/net/netfilter/nft_bitwise.c +++ b/net/netfilter/nft_bitwise.c @@ -196,7 +196,8 @@ static int nft_bitwise_init_shift(struct nft_bitwise *priv, if (err < 0) return err; - if (priv->data.data[0] >= BITS_PER_TYPE(u32)) { + if (!priv->data.data[0] || + priv->data.data[0] >= BITS_PER_TYPE(u32)) { nft_data_release(&priv->data, desc.type); return -EINVAL; } diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index decc725a33c2..0caa9304d2d0 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -261,10 +261,10 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, return ret; } - nft_target_set_tgchk_param(&par, ctx, target, info, &e, proto, inv); - nft_compat_wait_for_destructors(ctx->net); + nft_target_set_tgchk_param(&par, ctx, target, info, &e, proto, inv); + ret = xt_check_target(&par, size, proto, inv); if (ret < 0) { if (ret == -ENOENT) { @@ -353,8 +353,6 @@ nla_put_failure: static int nft_target_validate(const struct nft_ctx *ctx, const struct nft_expr *expr) { - struct xt_target *target = expr->ops->data; - unsigned int hook_mask = 0; int ret; if (ctx->family != NFPROTO_IPV4 && @@ -377,11 +375,21 @@ static int nft_target_validate(const struct nft_ctx *ctx, const struct nft_base_chain *basechain = nft_base_chain(ctx->chain); const struct nf_hook_ops *ops = &basechain->ops; + unsigned int hook_mask = 1 << ops->hooknum; + struct xt_target *target = expr->ops->data; + void *info = nft_expr_priv(expr); + struct xt_tgchk_param par; + union nft_entry e = {}; - hook_mask = 1 << ops->hooknum; if (target->hooks && !(hook_mask & target->hooks)) return -EINVAL; + nft_target_set_tgchk_param(&par, ctx, target, info, &e, 0, false); + + ret = xt_check_hooks_target(&par); + if (ret < 0) + return ret; + ret = nft_compat_chain_validate_dependency(ctx, target->table); if (ret < 0) return ret; @@ -515,10 +523,10 @@ __nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr, return ret; } - nft_match_set_mtchk_param(&par, ctx, match, info, &e, proto, inv); - nft_compat_wait_for_destructors(ctx->net); + nft_match_set_mtchk_param(&par, ctx, match, info, &e, proto, inv); + return xt_check_match(&par, size, proto, inv); } @@ -614,8 +622,6 @@ static int nft_match_large_dump(struct sk_buff *skb, static int nft_match_validate(const struct nft_ctx *ctx, const struct nft_expr *expr) { - struct xt_match *match = expr->ops->data; - unsigned int hook_mask = 0; int ret; if (ctx->family != NFPROTO_IPV4 && @@ -638,11 +644,30 @@ static int nft_match_validate(const struct nft_ctx *ctx, const struct nft_base_chain *basechain = nft_base_chain(ctx->chain); const struct nf_hook_ops *ops = &basechain->ops; + unsigned int hook_mask = 1 << ops->hooknum; + struct xt_match *match = expr->ops->data; + size_t size = XT_ALIGN(match->matchsize); + struct xt_mtchk_param par; + union nft_entry e = {}; + void *info; - hook_mask = 1 << ops->hooknum; if (match->hooks && !(hook_mask & match->hooks)) return -EINVAL; + if (NFT_EXPR_SIZE(size) > NFT_MATCH_LARGE_THRESH) { + struct nft_xt_match_priv *priv = nft_expr_priv(expr); + + info = priv->info; + } else { + info = nft_expr_priv(expr); + } + + nft_match_set_mtchk_param(&par, ctx, match, info, &e, 0, false); + + ret = xt_check_hooks_match(&par); + if (ret < 0) + return ret; + ret = nft_compat_chain_validate_dependency(ctx, match->table); if (ret < 0) return ret; diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index 0407d6f708ae..e6a07c0df207 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -376,7 +376,7 @@ static void nft_exthdr_sctp_eval(const struct nft_expr *expr, const struct sctp_chunkhdr *sch; struct sctp_chunkhdr _sch; - if (pkt->tprot != IPPROTO_SCTP) + if (pkt->tprot != IPPROTO_SCTP || pkt->fragoff) goto err; do { diff --git a/net/netfilter/nft_fwd_netdev.c b/net/netfilter/nft_fwd_netdev.c index 4bce36c3a6a0..b9e88d7cf308 100644 --- a/net/netfilter/nft_fwd_netdev.c +++ b/net/netfilter/nft_fwd_netdev.c @@ -95,12 +95,15 @@ static void nft_fwd_neigh_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { + u8 *nf_dup_skb_recursion = nf_get_nf_dup_skb_recursion(); struct nft_fwd_neigh *priv = nft_expr_priv(expr); void *addr = ®s->data[priv->sreg_addr]; int oif = regs->data[priv->sreg_dev]; unsigned int verdict = NF_STOLEN; struct sk_buff *skb = pkt->skb; + int nhoff = skb_network_offset(skb); struct net_device *dev; + unsigned int hh_len; int neigh_table; switch (priv->nfproto) { @@ -111,7 +114,7 @@ static void nft_fwd_neigh_eval(const struct nft_expr *expr, verdict = NFT_BREAK; goto out; } - if (skb_try_make_writable(skb, sizeof(*iph))) { + if (skb_ensure_writable(skb, nhoff + sizeof(*iph))) { verdict = NF_DROP; goto out; } @@ -132,7 +135,7 @@ static void nft_fwd_neigh_eval(const struct nft_expr *expr, verdict = NFT_BREAK; goto out; } - if (skb_try_make_writable(skb, sizeof(*ip6h))) { + if (skb_ensure_writable(skb, nhoff + sizeof(*ip6h))) { verdict = NF_DROP; goto out; } @@ -151,13 +154,31 @@ static void nft_fwd_neigh_eval(const struct nft_expr *expr, goto out; } + if (*nf_dup_skb_recursion > NF_RECURSION_LIMIT) { + verdict = NF_DROP; + goto out; + } + dev = dev_get_by_index_rcu(nft_net(pkt), oif); - if (dev == NULL) - return; + if (dev == NULL) { + verdict = NF_DROP; + goto out; + } + + hh_len = LL_RESERVED_SPACE(dev); + if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { + skb = skb_expand_head(skb, hh_len); + if (!skb) { + verdict = NF_STOLEN; + goto out; + } + } skb->dev = dev; skb_clear_tstamp(skb); + (*nf_dup_skb_recursion)++; neigh_xmit(neigh_table, dev, addr, skb); + (*nf_dup_skb_recursion)--; out: regs->verdict.code = verdict; } diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c index c02d5cb52143..45fe56da5044 100644 --- a/net/netfilter/nft_osf.c +++ b/net/netfilter/nft_osf.c @@ -33,7 +33,7 @@ static void nft_osf_eval(const struct nft_expr *expr, struct nft_regs *regs, return; } - if (pkt->tprot != IPPROTO_TCP) { + if (pkt->tprot != IPPROTO_TCP || pkt->fragoff) { regs->verdict.code = NFT_BREAK; return; } diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c index f2101af8c867..89be443734f6 100644 --- a/net/netfilter/nft_tproxy.c +++ b/net/netfilter/nft_tproxy.c @@ -30,8 +30,8 @@ static void nft_tproxy_eval_v4(const struct nft_expr *expr, __be16 tport = 0; struct sock *sk; - if (pkt->tprot != IPPROTO_TCP && - pkt->tprot != IPPROTO_UDP) { + if ((pkt->tprot != IPPROTO_TCP && + pkt->tprot != IPPROTO_UDP) || pkt->fragoff) { regs->verdict.code = NFT_BREAK; return; } @@ -97,8 +97,8 @@ static void nft_tproxy_eval_v6(const struct nft_expr *expr, memset(&taddr, 0, sizeof(taddr)); - if (pkt->tprot != IPPROTO_TCP && - pkt->tprot != IPPROTO_UDP) { + if ((pkt->tprot != IPPROTO_TCP && + pkt->tprot != IPPROTO_UDP) || pkt->fragoff) { regs->verdict.code = NFT_BREAK; return; } diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 9f837fb5ceb4..2c67c2e6b132 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -477,11 +477,9 @@ int xt_check_proc_name(const char *name, unsigned int size) } EXPORT_SYMBOL(xt_check_proc_name); -int xt_check_match(struct xt_mtchk_param *par, - unsigned int size, u16 proto, bool inv_proto) +static int xt_check_match_common(struct xt_mtchk_param *par, + unsigned int size, u16 proto, bool inv_proto) { - int ret; - if (XT_ALIGN(par->match->matchsize) != size && par->match->matchsize != -1) { /* @@ -530,6 +528,14 @@ int xt_check_match(struct xt_mtchk_param *par, par->match->proto); return -EINVAL; } + + return 0; +} + +static int xt_checkentry_match(struct xt_mtchk_param *par) +{ + int ret; + if (par->match->checkentry != NULL) { ret = par->match->checkentry(par); if (ret < 0) @@ -538,8 +544,34 @@ int xt_check_match(struct xt_mtchk_param *par, /* Flag up potential errors. */ return -EIO; } + + return 0; +} + +int xt_check_hooks_match(struct xt_mtchk_param *par) +{ + if (par->match->check_hooks != NULL) + return par->match->check_hooks(par); + return 0; } +EXPORT_SYMBOL_GPL(xt_check_hooks_match); + +int xt_check_match(struct xt_mtchk_param *par, + unsigned int size, u16 proto, bool inv_proto) +{ + int ret; + + ret = xt_check_match_common(par, size, proto, inv_proto); + if (ret < 0) + return ret; + + ret = xt_check_hooks_match(par); + if (ret < 0) + return ret; + + return xt_checkentry_match(par); +} EXPORT_SYMBOL_GPL(xt_check_match); /** xt_check_entry_match - check that matches end before start of target @@ -1012,11 +1044,9 @@ bool xt_find_jump_offset(const unsigned int *offsets, } EXPORT_SYMBOL(xt_find_jump_offset); -int xt_check_target(struct xt_tgchk_param *par, - unsigned int size, u16 proto, bool inv_proto) +static int xt_check_target_common(struct xt_tgchk_param *par, + unsigned int size, u16 proto, bool inv_proto) { - int ret; - if (XT_ALIGN(par->target->targetsize) != size) { pr_err_ratelimited("%s_tables: %s.%u target: invalid size %u (kernel) != (user) %u\n", xt_prefix[par->family], par->target->name, @@ -1061,6 +1091,23 @@ int xt_check_target(struct xt_tgchk_param *par, par->target->proto); return -EINVAL; } + + return 0; +} + +int xt_check_hooks_target(struct xt_tgchk_param *par) +{ + if (par->target->check_hooks != NULL) + return par->target->check_hooks(par); + + return 0; +} +EXPORT_SYMBOL_GPL(xt_check_hooks_target); + +static int xt_checkentry_target(struct xt_tgchk_param *par) +{ + int ret; + if (par->target->checkentry != NULL) { ret = par->target->checkentry(par); if (ret < 0) @@ -1071,6 +1118,22 @@ int xt_check_target(struct xt_tgchk_param *par, } return 0; } + +int xt_check_target(struct xt_tgchk_param *par, + unsigned int size, u16 proto, bool inv_proto) +{ + int ret; + + ret = xt_check_target_common(par, size, proto, inv_proto); + if (ret < 0) + return ret; + + ret = xt_check_hooks_target(par); + if (ret < 0) + return ret; + + return xt_checkentry_target(par); +} EXPORT_SYMBOL_GPL(xt_check_target); /** diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index 498f5871c84a..d2aeacf94230 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -354,7 +354,7 @@ static struct xt_target xt_ct_tg_reg[] __read_mostly = { .family = NFPROTO_IPV4, .revision = 1, .targetsize = sizeof(struct xt_ct_target_info_v1), - .usersize = offsetof(struct xt_ct_target_info, ct), + .usersize = offsetof(struct xt_ct_target_info_v1, ct), .checkentry = xt_ct_tg_check_v1, .destroy = xt_ct_tg_destroy_v1, .target = xt_ct_target_v1, @@ -366,7 +366,7 @@ static struct xt_target xt_ct_tg_reg[] __read_mostly = { .family = NFPROTO_IPV4, .revision = 2, .targetsize = sizeof(struct xt_ct_target_info_v1), - .usersize = offsetof(struct xt_ct_target_info, ct), + .usersize = offsetof(struct xt_ct_target_info_v1, ct), .checkentry = xt_ct_tg_check_v2, .destroy = xt_ct_tg_destroy_v1, .target = xt_ct_target_v1, @@ -398,7 +398,7 @@ static struct xt_target xt_ct_tg_reg[] __read_mostly = { .family = NFPROTO_IPV6, .revision = 1, .targetsize = sizeof(struct xt_ct_target_info_v1), - .usersize = offsetof(struct xt_ct_target_info, ct), + .usersize = offsetof(struct xt_ct_target_info_v1, ct), .checkentry = xt_ct_tg_check_v1, .destroy = xt_ct_tg_destroy_v1, .target = xt_ct_target_v1, @@ -410,7 +410,7 @@ static struct xt_target xt_ct_tg_reg[] __read_mostly = { .family = NFPROTO_IPV6, .revision = 2, .targetsize = sizeof(struct xt_ct_target_info_v1), - .usersize = offsetof(struct xt_ct_target_info, ct), + .usersize = offsetof(struct xt_ct_target_info_v1, ct), .checkentry = xt_ct_tg_check_v2, .destroy = xt_ct_tg_destroy_v1, .target = xt_ct_target_v1, diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index 116a885adb3c..80e1634bc51f 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -247,6 +247,21 @@ tcpmss_tg6(struct sk_buff *skb, const struct xt_action_param *par) } #endif +static int tcpmss_tg4_check_hooks(const struct xt_tgchk_param *par) +{ + const struct xt_tcpmss_info *info = par->targinfo; + + if (info->mss == XT_TCPMSS_CLAMP_PMTU && + (par->hook_mask & ~((1 << NF_INET_FORWARD) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_POST_ROUTING))) != 0) { + pr_info_ratelimited("path-MTU clamping only supported in FORWARD, OUTPUT and POSTROUTING hooks\n"); + return -EINVAL; + } + + return 0; +} + /* Must specify -p tcp --syn */ static inline bool find_syn_match(const struct xt_entry_match *m) { @@ -262,17 +277,9 @@ static inline bool find_syn_match(const struct xt_entry_match *m) static int tcpmss_tg4_check(const struct xt_tgchk_param *par) { - const struct xt_tcpmss_info *info = par->targinfo; const struct ipt_entry *e = par->entryinfo; const struct xt_entry_match *ematch; - if (info->mss == XT_TCPMSS_CLAMP_PMTU && - (par->hook_mask & ~((1 << NF_INET_FORWARD) | - (1 << NF_INET_LOCAL_OUT) | - (1 << NF_INET_POST_ROUTING))) != 0) { - pr_info_ratelimited("path-MTU clamping only supported in FORWARD, OUTPUT and POSTROUTING hooks\n"); - return -EINVAL; - } if (par->nft_compat) return 0; @@ -286,17 +293,9 @@ static int tcpmss_tg4_check(const struct xt_tgchk_param *par) #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) static int tcpmss_tg6_check(const struct xt_tgchk_param *par) { - const struct xt_tcpmss_info *info = par->targinfo; const struct ip6t_entry *e = par->entryinfo; const struct xt_entry_match *ematch; - if (info->mss == XT_TCPMSS_CLAMP_PMTU && - (par->hook_mask & ~((1 << NF_INET_FORWARD) | - (1 << NF_INET_LOCAL_OUT) | - (1 << NF_INET_POST_ROUTING))) != 0) { - pr_info_ratelimited("path-MTU clamping only supported in FORWARD, OUTPUT and POSTROUTING hooks\n"); - return -EINVAL; - } if (par->nft_compat) return 0; @@ -312,6 +311,7 @@ static struct xt_target tcpmss_tg_reg[] __read_mostly = { { .family = NFPROTO_IPV4, .name = "TCPMSS", + .check_hooks = tcpmss_tg4_check_hooks, .checkentry = tcpmss_tg4_check, .target = tcpmss_tg4, .targetsize = sizeof(struct xt_tcpmss_info), @@ -322,6 +322,7 @@ static struct xt_target tcpmss_tg_reg[] __read_mostly = { { .family = NFPROTO_IPV6, .name = "TCPMSS", + .check_hooks = tcpmss_tg4_check_hooks, .checkentry = tcpmss_tg6_check, .target = tcpmss_tg6, .targetsize = sizeof(struct xt_tcpmss_info), diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index e4bea1d346cf..5f60e7298a1e 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -86,6 +86,9 @@ tproxy_tg4_v0(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_tproxy_target_info *tgi = par->targinfo; + if (par->fragoff) + return NF_DROP; + return tproxy_tg4(xt_net(par), skb, tgi->laddr, tgi->lport, tgi->mark_mask, tgi->mark_value); } @@ -95,6 +98,9 @@ tproxy_tg4_v1(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_tproxy_target_info_v1 *tgi = par->targinfo; + if (par->fragoff) + return NF_DROP; + return tproxy_tg4(xt_net(par), skb, tgi->laddr.ip, tgi->lport, tgi->mark_mask, tgi->mark_value); } @@ -106,6 +112,7 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par) { const struct ipv6hdr *iph = ipv6_hdr(skb); const struct xt_tproxy_target_info_v1 *tgi = par->targinfo; + unsigned short fragoff = 0; struct udphdr _hdr, *hp; struct sock *sk; const struct in6_addr *laddr; @@ -113,8 +120,8 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par) int thoff = 0; int tproto; - tproto = ipv6_find_hdr(skb, &thoff, -1, NULL, NULL); - if (tproto < 0) + tproto = ipv6_find_hdr(skb, &thoff, -1, &fragoff, NULL); + if (tproto < 0 || fragoff) return NF_DROP; hp = skb_header_pointer(skb, thoff, sizeof(_hdr), &_hdr); diff --git a/net/netfilter/xt_addrtype.c b/net/netfilter/xt_addrtype.c index a77088943107..913dbe3aa5e2 100644 --- a/net/netfilter/xt_addrtype.c +++ b/net/netfilter/xt_addrtype.c @@ -153,14 +153,10 @@ addrtype_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) return ret; } -static int addrtype_mt_checkentry_v1(const struct xt_mtchk_param *par) +static int addrtype_mt_check_hooks(const struct xt_mtchk_param *par) { - const char *errmsg = "both incoming and outgoing interface limitation cannot be selected"; struct xt_addrtype_info_v1 *info = par->matchinfo; - - if (info->flags & XT_ADDRTYPE_LIMIT_IFACE_IN && - info->flags & XT_ADDRTYPE_LIMIT_IFACE_OUT) - goto err; + const char *errmsg; if (par->hook_mask & ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN)) && @@ -176,6 +172,21 @@ static int addrtype_mt_checkentry_v1(const struct xt_mtchk_param *par) goto err; } + return 0; +err: + pr_info_ratelimited("%s\n", errmsg); + return -EINVAL; +} + +static int addrtype_mt_checkentry_v1(const struct xt_mtchk_param *par) +{ + const char *errmsg = "both incoming and outgoing interface limitation cannot be selected"; + struct xt_addrtype_info_v1 *info = par->matchinfo; + + if (info->flags & XT_ADDRTYPE_LIMIT_IFACE_IN && + info->flags & XT_ADDRTYPE_LIMIT_IFACE_OUT) + goto err; + #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) if (par->family == NFPROTO_IPV6) { if ((info->source | info->dest) & XT_ADDRTYPE_BLACKHOLE) { @@ -211,6 +222,7 @@ static struct xt_match addrtype_mt_reg[] __read_mostly = { .family = NFPROTO_IPV4, .revision = 1, .match = addrtype_mt_v1, + .check_hooks = addrtype_mt_check_hooks, .checkentry = addrtype_mt_checkentry_v1, .matchsize = sizeof(struct xt_addrtype_info_v1), .me = THIS_MODULE @@ -221,6 +233,7 @@ static struct xt_match addrtype_mt_reg[] __read_mostly = { .family = NFPROTO_IPV6, .revision = 1, .match = addrtype_mt_v1, + .check_hooks = addrtype_mt_check_hooks, .checkentry = addrtype_mt_checkentry_v1, .matchsize = sizeof(struct xt_addrtype_info_v1), .me = THIS_MODULE diff --git a/net/netfilter/xt_devgroup.c b/net/netfilter/xt_devgroup.c index 9520dd00070b..6d1a44ab5eee 100644 --- a/net/netfilter/xt_devgroup.c +++ b/net/netfilter/xt_devgroup.c @@ -33,14 +33,10 @@ static bool devgroup_mt(const struct sk_buff *skb, struct xt_action_param *par) return true; } -static int devgroup_mt_checkentry(const struct xt_mtchk_param *par) +static int devgroup_mt_check_hooks(const struct xt_mtchk_param *par) { const struct xt_devgroup_info *info = par->matchinfo; - if (info->flags & ~(XT_DEVGROUP_MATCH_SRC | XT_DEVGROUP_INVERT_SRC | - XT_DEVGROUP_MATCH_DST | XT_DEVGROUP_INVERT_DST)) - return -EINVAL; - if (info->flags & XT_DEVGROUP_MATCH_SRC && par->hook_mask & ~((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN) | @@ -56,9 +52,21 @@ static int devgroup_mt_checkentry(const struct xt_mtchk_param *par) return 0; } +static int devgroup_mt_checkentry(const struct xt_mtchk_param *par) +{ + const struct xt_devgroup_info *info = par->matchinfo; + + if (info->flags & ~(XT_DEVGROUP_MATCH_SRC | XT_DEVGROUP_INVERT_SRC | + XT_DEVGROUP_MATCH_DST | XT_DEVGROUP_INVERT_DST)) + return -EINVAL; + + return 0; +} + static struct xt_match devgroup_mt_reg __read_mostly = { .name = "devgroup", .match = devgroup_mt, + .check_hooks = devgroup_mt_check_hooks, .checkentry = devgroup_mt_checkentry, .matchsize = sizeof(struct xt_devgroup_info), .family = NFPROTO_UNSPEC, diff --git a/net/netfilter/xt_ecn.c b/net/netfilter/xt_ecn.c index b96e8203ac54..a8503f5d26bf 100644 --- a/net/netfilter/xt_ecn.c +++ b/net/netfilter/xt_ecn.c @@ -30,6 +30,10 @@ static bool match_tcp(const struct sk_buff *skb, struct xt_action_param *par) struct tcphdr _tcph; const struct tcphdr *th; + /* this is fine for IPv6 as ecn_mt_check6() enforces -p tcp */ + if (par->fragoff) + return false; + /* In practice, TCP match does this, so can't fail. But let's * be good citizens. */ diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 3bd127bfc114..2704b4b60d1e 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -658,6 +658,8 @@ hashlimit_init_dst(const struct xt_hashlimit_htable *hinfo, if (!(hinfo->cfg.mode & (XT_HASHLIMIT_HASH_DPT | XT_HASHLIMIT_HASH_SPT))) return 0; + if (ntohs(ip_hdr(skb)->frag_off) & IP_OFFSET) + return -1; nexthdr = ip_hdr(skb)->protocol; break; #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) @@ -681,7 +683,7 @@ hashlimit_init_dst(const struct xt_hashlimit_htable *hinfo, return 0; nexthdr = ipv6_hdr(skb)->nexthdr; protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, &frag_off); - if ((int)protoff < 0) + if ((int)protoff < 0 || ntohs(frag_off) & IP6_OFFSET) return -1; break; } diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c index dc9485854002..e8807caede68 100644 --- a/net/netfilter/xt_osf.c +++ b/net/netfilter/xt_osf.c @@ -27,6 +27,9 @@ static bool xt_osf_match_packet(const struct sk_buff *skb, struct xt_action_param *p) { + if (p->fragoff) + return false; + return nf_osf_match(skb, xt_family(p), xt_hooknum(p), xt_in(p), xt_out(p), p->matchinfo, xt_net(p), nf_osf_fingers); } diff --git a/net/netfilter/xt_physdev.c b/net/netfilter/xt_physdev.c index d2b0b52434fa..dd98f758176c 100644 --- a/net/netfilter/xt_physdev.c +++ b/net/netfilter/xt_physdev.c @@ -91,14 +91,10 @@ match_outdev: return (!!ret ^ !(info->invert & XT_PHYSDEV_OP_OUT)); } -static int physdev_mt_check(const struct xt_mtchk_param *par) +static int physdev_mt_check_hooks(const struct xt_mtchk_param *par) { const struct xt_physdev_info *info = par->matchinfo; - static bool brnf_probed __read_mostly; - if (!(info->bitmask & XT_PHYSDEV_OP_MASK) || - info->bitmask & ~XT_PHYSDEV_OP_MASK) - return -EINVAL; if (info->bitmask & (XT_PHYSDEV_OP_OUT | XT_PHYSDEV_OP_ISOUT) && (!(info->bitmask & XT_PHYSDEV_OP_BRIDGED) || info->invert & XT_PHYSDEV_OP_BRIDGED) && @@ -107,6 +103,18 @@ static int physdev_mt_check(const struct xt_mtchk_param *par) return -EINVAL; } + return 0; +} + +static int physdev_mt_check(const struct xt_mtchk_param *par) +{ + const struct xt_physdev_info *info = par->matchinfo; + static bool brnf_probed __read_mostly; + + if (!(info->bitmask & XT_PHYSDEV_OP_MASK) || + info->bitmask & ~XT_PHYSDEV_OP_MASK) + return -EINVAL; + #define X(memb) strnlen(info->memb, sizeof(info->memb)) >= sizeof(info->memb) if (info->bitmask & XT_PHYSDEV_OP_IN) { if (info->physindev[0] == '\0') @@ -141,6 +149,7 @@ static struct xt_match physdev_mt_reg[] __read_mostly = { { .name = "physdev", .family = NFPROTO_IPV4, + .check_hooks = physdev_mt_check_hooks, .checkentry = physdev_mt_check, .match = physdev_mt, .matchsize = sizeof(struct xt_physdev_info), @@ -149,6 +158,7 @@ static struct xt_match physdev_mt_reg[] __read_mostly = { { .name = "physdev", .family = NFPROTO_IPV6, + .check_hooks = physdev_mt_check_hooks, .checkentry = physdev_mt_check, .match = physdev_mt, .matchsize = sizeof(struct xt_physdev_info), diff --git a/net/netfilter/xt_policy.c b/net/netfilter/xt_policy.c index cb6e8279010a..ff54e3a8581e 100644 --- a/net/netfilter/xt_policy.c +++ b/net/netfilter/xt_policy.c @@ -63,7 +63,7 @@ match_policy_in(const struct sk_buff *skb, const struct xt_policy_info *info, return 0; for (i = sp->len - 1; i >= 0; i--) { - pos = strict ? i - sp->len + 1 : 0; + pos = strict ? sp->len - i - 1 : 0; if (pos >= info->len) return 0; e = &info->pol[pos]; @@ -126,13 +126,10 @@ policy_mt(const struct sk_buff *skb, struct xt_action_param *par) return ret; } -static int policy_mt_check(const struct xt_mtchk_param *par) +static int policy_mt_check_hooks(const struct xt_mtchk_param *par) { const struct xt_policy_info *info = par->matchinfo; - const char *errmsg = "neither incoming nor outgoing policy selected"; - - if (!(info->flags & (XT_POLICY_MATCH_IN|XT_POLICY_MATCH_OUT))) - goto err; + const char *errmsg; if (par->hook_mask & ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN)) && info->flags & XT_POLICY_MATCH_OUT) { @@ -144,6 +141,21 @@ static int policy_mt_check(const struct xt_mtchk_param *par) errmsg = "input policy not valid in POSTROUTING and OUTPUT"; goto err; } + + return 0; +err: + pr_info_ratelimited("%s\n", errmsg); + return -EINVAL; +} + +static int policy_mt_check(const struct xt_mtchk_param *par) +{ + const struct xt_policy_info *info = par->matchinfo; + const char *errmsg = "neither incoming nor outgoing policy selected"; + + if (!(info->flags & (XT_POLICY_MATCH_IN|XT_POLICY_MATCH_OUT))) + goto err; + if (info->len > XT_POLICY_MAX_ELEM) { errmsg = "too many policy elements"; goto err; @@ -158,6 +170,7 @@ static struct xt_match policy_mt_reg[] __read_mostly = { { .name = "policy", .family = NFPROTO_IPV4, + .check_hooks = policy_mt_check_hooks, .checkentry = policy_mt_check, .match = policy_mt, .matchsize = sizeof(struct xt_policy_info), @@ -166,6 +179,7 @@ static struct xt_match policy_mt_reg[] __read_mostly = { { .name = "policy", .family = NFPROTO_IPV6, + .check_hooks = policy_mt_check_hooks, .checkentry = policy_mt_check, .match = policy_mt, .matchsize = sizeof(struct xt_policy_info), diff --git a/net/netfilter/xt_set.c b/net/netfilter/xt_set.c index 731bc2cafae4..4ae04bba9358 100644 --- a/net/netfilter/xt_set.c +++ b/net/netfilter/xt_set.c @@ -431,6 +431,29 @@ set_target_v3(struct sk_buff *skb, const struct xt_action_param *par) } static int +set_target_v3_check_hooks(const struct xt_tgchk_param *par) +{ + const struct xt_set_info_target_v3 *info = par->targinfo; + + if (info->map_set.index != IPSET_INVALID_ID) { + if (strncmp(par->table, "mangle", 7)) { + pr_info_ratelimited("--map-set only usable from mangle table\n"); + return -EINVAL; + } + if (((info->flags & IPSET_FLAG_MAP_SKBPRIO) | + (info->flags & IPSET_FLAG_MAP_SKBQUEUE)) && + (par->hook_mask & ~(1 << NF_INET_FORWARD | + 1 << NF_INET_LOCAL_OUT | + 1 << NF_INET_POST_ROUTING))) { + pr_info_ratelimited("mapping of prio or/and queue is allowed only from OUTPUT/FORWARD/POSTROUTING chains\n"); + return -EINVAL; + } + } + + return 0; +} + +static int set_target_v3_checkentry(const struct xt_tgchk_param *par) { const struct xt_set_info_target_v3 *info = par->targinfo; @@ -459,20 +482,6 @@ set_target_v3_checkentry(const struct xt_tgchk_param *par) } if (info->map_set.index != IPSET_INVALID_ID) { - if (strncmp(par->table, "mangle", 7)) { - pr_info_ratelimited("--map-set only usable from mangle table\n"); - ret = -EINVAL; - goto cleanup_del; - } - if (((info->flags & IPSET_FLAG_MAP_SKBPRIO) | - (info->flags & IPSET_FLAG_MAP_SKBQUEUE)) && - (par->hook_mask & ~(1 << NF_INET_FORWARD | - 1 << NF_INET_LOCAL_OUT | - 1 << NF_INET_POST_ROUTING))) { - pr_info_ratelimited("mapping of prio or/and queue is allowed only from OUTPUT/FORWARD/POSTROUTING chains\n"); - ret = -EINVAL; - goto cleanup_del; - } index = ip_set_nfnl_get_byindex(par->net, info->map_set.index); if (index == IPSET_INVALID_ID) { @@ -672,6 +681,7 @@ static struct xt_target set_targets[] __read_mostly = { .family = NFPROTO_IPV4, .target = set_target_v3, .targetsize = sizeof(struct xt_set_info_target_v3), + .check_hooks = set_target_v3_check_hooks, .checkentry = set_target_v3_checkentry, .destroy = set_target_v3_destroy, .me = THIS_MODULE @@ -682,6 +692,7 @@ static struct xt_target set_targets[] __read_mostly = { .family = NFPROTO_IPV6, .target = set_target_v3, .targetsize = sizeof(struct xt_set_info_target_v3), + .check_hooks = set_target_v3_check_hooks, .checkentry = set_target_v3_checkentry, .destroy = set_target_v3_destroy, .me = THIS_MODULE diff --git a/net/netfilter/xt_tcpmss.c b/net/netfilter/xt_tcpmss.c index 0d32d4841cb3..b9da8269161d 100644 --- a/net/netfilter/xt_tcpmss.c +++ b/net/netfilter/xt_tcpmss.c @@ -32,6 +32,10 @@ tcpmss_mt(const struct sk_buff *skb, struct xt_action_param *par) u8 _opt[15 * 4 - sizeof(_tcph)]; unsigned int i, optlen; + /* this is fine for IPv6 as xt_tcpmss enforces -p tcp */ + if (par->fragoff) + return false; + /* If we don't have the whole header, drop packet. */ th = skb_header_pointer(skb, par->thoff, sizeof(_tcph), &_tcph); if (th == NULL) diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c index b10e1602c6b1..cb5ea4424ffc 100644 --- a/net/openvswitch/vport-geneve.c +++ b/net/openvswitch/vport-geneve.c @@ -97,6 +97,9 @@ static struct vport *geneve_tnl_create(const struct vport_parms *parms) goto error; } + vport->dev = dev; + netdev_hold(vport->dev, &vport->dev_tracker, GFP_KERNEL); + rtnl_unlock(); return vport; error: @@ -111,7 +114,7 @@ static struct vport *geneve_create(const struct vport_parms *parms) if (IS_ERR(vport)) return vport; - return ovs_netdev_link(vport, parms->name); + return ovs_netdev_link(vport, true); } static struct vport_ops ovs_geneve_vport_ops = { diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c index 4014c9b5eb79..6cb5a697b396 100644 --- a/net/openvswitch/vport-gre.c +++ b/net/openvswitch/vport-gre.c @@ -63,6 +63,9 @@ static struct vport *gre_tnl_create(const struct vport_parms *parms) return ERR_PTR(err); } + vport->dev = dev; + netdev_hold(vport->dev, &vport->dev_tracker, GFP_KERNEL); + rtnl_unlock(); return vport; } @@ -75,7 +78,7 @@ static struct vport *gre_create(const struct vport_parms *parms) if (IS_ERR(vport)) return vport; - return ovs_netdev_link(vport, parms->name); + return ovs_netdev_link(vport, true); } static struct vport_ops ovs_gre_vport_ops = { diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c index 12055af832dc..c42642075685 100644 --- a/net/openvswitch/vport-netdev.c +++ b/net/openvswitch/vport-netdev.c @@ -73,37 +73,21 @@ static struct net_device *get_dpdev(const struct datapath *dp) return local->dev; } -struct vport *ovs_netdev_link(struct vport *vport, const char *name) +struct vport *ovs_netdev_link(struct vport *vport, bool tunnel) { int err; - vport->dev = dev_get_by_name(ovs_dp_get_net(vport->dp), name); - if (!vport->dev) { + if (WARN_ON_ONCE(!vport->dev)) { err = -ENODEV; goto error_free_vport; } - /* Ensure that the device exists and that the provided - * name is not one of its aliases. - */ - if (strcmp(name, ovs_vport_name(vport))) { - err = -ENODEV; - goto error_put; - } - netdev_tracker_alloc(vport->dev, &vport->dev_tracker, GFP_KERNEL); - if (vport->dev->flags & IFF_LOOPBACK || - (vport->dev->type != ARPHRD_ETHER && - vport->dev->type != ARPHRD_NONE) || - ovs_is_internal_dev(vport->dev)) { - err = -EINVAL; - goto error_put; - } rtnl_lock(); err = netdev_master_upper_dev_link(vport->dev, get_dpdev(vport->dp), NULL, NULL, NULL); if (err) - goto error_unlock; + goto error_put_unlock; err = netdev_rx_handler_register(vport->dev, netdev_frame_hook, vport); @@ -119,10 +103,11 @@ struct vport *ovs_netdev_link(struct vport *vport, const char *name) error_master_upper_dev_unlink: netdev_upper_dev_unlink(vport->dev, get_dpdev(vport->dp)); -error_unlock: - rtnl_unlock(); -error_put: +error_put_unlock: + if (tunnel && vport->dev->reg_state == NETREG_REGISTERED) + rtnl_delete_link(vport->dev, 0, NULL); netdev_put(vport->dev, &vport->dev_tracker); + rtnl_unlock(); error_free_vport: ovs_vport_free(vport); return ERR_PTR(err); @@ -132,12 +117,39 @@ EXPORT_SYMBOL_GPL(ovs_netdev_link); static struct vport *netdev_create(const struct vport_parms *parms) { struct vport *vport; + int err; vport = ovs_vport_alloc(0, &ovs_netdev_vport_ops, parms); if (IS_ERR(vport)) return vport; - return ovs_netdev_link(vport, parms->name); + vport->dev = dev_get_by_name(ovs_dp_get_net(vport->dp), parms->name); + if (!vport->dev) { + err = -ENODEV; + goto error_free_vport; + } + netdev_tracker_alloc(vport->dev, &vport->dev_tracker, GFP_KERNEL); + + /* Ensure that the provided name is not an alias. */ + if (strcmp(parms->name, ovs_vport_name(vport))) { + err = -ENODEV; + goto error_put; + } + + if (vport->dev->flags & IFF_LOOPBACK || + (vport->dev->type != ARPHRD_ETHER && + vport->dev->type != ARPHRD_NONE) || + ovs_is_internal_dev(vport->dev)) { + err = -EINVAL; + goto error_put; + } + + return ovs_netdev_link(vport, false); +error_put: + netdev_put(vport->dev, &vport->dev_tracker); +error_free_vport: + ovs_vport_free(vport); + return ERR_PTR(err); } static void vport_netdev_free(struct rcu_head *rcu) @@ -196,9 +208,13 @@ void ovs_netdev_tunnel_destroy(struct vport *vport) */ if (vport->dev->reg_state == NETREG_REGISTERED) rtnl_delete_link(vport->dev, 0, NULL); - rtnl_unlock(); + /* We can't put the device reference yet, since it can still be in + * use, but rtnl_unlock()->netdev_run_todo() will block until all + * the references are released, so the RCU call must be before it. + */ call_rcu(&vport->rcu, vport_netdev_free); + rtnl_unlock(); } EXPORT_SYMBOL_GPL(ovs_netdev_tunnel_destroy); diff --git a/net/openvswitch/vport-netdev.h b/net/openvswitch/vport-netdev.h index c5d83a43bfc4..6c0d7366f986 100644 --- a/net/openvswitch/vport-netdev.h +++ b/net/openvswitch/vport-netdev.h @@ -13,7 +13,7 @@ struct vport *ovs_netdev_get_vport(struct net_device *dev); -struct vport *ovs_netdev_link(struct vport *vport, const char *name); +struct vport *ovs_netdev_link(struct vport *vport, bool tunnel); void ovs_netdev_detach_dev(struct vport *); int __init ovs_netdev_init(void); diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c index 0b881b043bcf..c1b37b50d29e 100644 --- a/net/openvswitch/vport-vxlan.c +++ b/net/openvswitch/vport-vxlan.c @@ -126,6 +126,9 @@ static struct vport *vxlan_tnl_create(const struct vport_parms *parms) goto error; } + vport->dev = dev; + netdev_hold(vport->dev, &vport->dev_tracker, GFP_KERNEL); + rtnl_unlock(); return vport; error: @@ -140,7 +143,7 @@ static struct vport *vxlan_create(const struct vport_parms *parms) if (IS_ERR(vport)) return vport; - return ovs_netdev_link(vport, parms->name); + return ovs_netdev_link(vport, true); } static struct vport_ops ovs_vxlan_netdev_vport_ops = { diff --git a/net/phonet/socket.c b/net/phonet/socket.c index c4af26357144..631a99cdbd00 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -208,9 +208,15 @@ static int pn_socket_autobind(struct socket *sock) sa.spn_family = AF_PHONET; err = pn_socket_bind(sock, (struct sockaddr_unsized *)&sa, sizeof(struct sockaddr_pn)); - if (err != -EINVAL) + /* + * pn_socket_bind() also returns -EINVAL when sk_state != TCP_CLOSE + * without a prior bind, so -EINVAL alone is not sufficient to infer + * that the socket was already bound. Only treat it as "already + * bound" when the port is non-zero; otherwise propagate the error + * instead of crashing the kernel. + */ + if (err != -EINVAL || unlikely(!pn_port(pn_sk(sock->sk)->sobject))) return err; - BUG_ON(!pn_port(pn_sk(sock->sk)->sobject)); return 0; /* socket was already bound */ } diff --git a/net/psp/psp-nl-gen.c b/net/psp/psp-nl-gen.c index 22a48d0fa378..953309952cef 100644 --- a/net/psp/psp-nl-gen.c +++ b/net/psp/psp-nl-gen.c @@ -76,7 +76,7 @@ static const struct genl_split_ops psp_nl_ops[] = { .post_doit = psp_device_unlock, .policy = psp_dev_set_nl_policy, .maxattr = PSP_A_DEV_PSP_VERSIONS_ENA, - .flags = GENL_CMD_CAP_DO, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, { .cmd = PSP_CMD_KEY_ROTATE, @@ -85,7 +85,7 @@ static const struct genl_split_ops psp_nl_ops[] = { .post_doit = psp_device_unlock, .policy = psp_key_rotate_nl_policy, .maxattr = PSP_A_DEV_ID, - .flags = GENL_CMD_CAP_DO, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, { .cmd = PSP_CMD_RX_ASSOC, diff --git a/net/psp/psp_main.c b/net/psp/psp_main.c index 9508b6c38003..e45549f08eef 100644 --- a/net/psp/psp_main.c +++ b/net/psp/psp_main.c @@ -263,15 +263,16 @@ EXPORT_SYMBOL(psp_dev_encapsulate); /* Receive handler for PSP packets. * - * Presently it accepts only already-authenticated packets and does not - * support optional fields, such as virtualization cookies. The caller should - * ensure that skb->data is pointing to the mac header, and that skb->mac_len - * is set. This function does not currently adjust skb->csum (CHECKSUM_COMPLETE - * is not supported). + * Accepts only already-authenticated packets. The full PSP header is + * stripped according to psph->hdrlen; any optional fields it advertises + * (virtualization cookies, etc.) are ignored and discarded along with the + * rest of the header. The caller should ensure that skb->data is pointing + * to the mac header, and that skb->mac_len is set. This function does not + * currently adjust skb->csum (CHECKSUM_COMPLETE is not supported). */ int psp_dev_rcv(struct sk_buff *skb, u16 dev_id, u8 generation, bool strip_icv) { - int l2_hlen = 0, l3_hlen, encap; + int l2_hlen = 0, l3_hlen, encap, psp_hlen; struct psp_skb_ext *pse; struct psphdr *psph; struct ethhdr *eth; @@ -312,18 +313,36 @@ int psp_dev_rcv(struct sk_buff *skb, u16 dev_id, u8 generation, bool strip_icv) if (unlikely(uh->dest != htons(PSP_DEFAULT_UDP_PORT))) return -EINVAL; - pse = skb_ext_add(skb, SKB_EXT_PSP); - if (!pse) + psph = (struct psphdr *)(skb->data + l2_hlen + l3_hlen + + sizeof(struct udphdr)); + + /* Strip the full PSP header per psph->hdrlen; VC/options are pulled + * into the linear region only so they can be discarded with the + * rest of the header. + */ + psp_hlen = (psph->hdrlen + 1) * 8; + + if (unlikely(psp_hlen < sizeof(struct psphdr))) + return -EINVAL; + + if (psp_hlen > sizeof(struct psphdr) && + !pskb_may_pull(skb, l2_hlen + l3_hlen + + sizeof(struct udphdr) + psp_hlen)) return -EINVAL; psph = (struct psphdr *)(skb->data + l2_hlen + l3_hlen + sizeof(struct udphdr)); + + pse = skb_ext_add(skb, SKB_EXT_PSP); + if (!pse) + return -EINVAL; + pse->spi = psph->spi; pse->dev_id = dev_id; pse->generation = generation; pse->version = FIELD_GET(PSPHDR_VERFL_VERSION, psph->verfl); - encap = PSP_ENCAP_HLEN; + encap = sizeof(struct udphdr) + psp_hlen; encap += strip_icv ? PSP_TRL_SIZE : 0; if (proto == htons(ETH_P_IP)) { @@ -340,8 +359,9 @@ int psp_dev_rcv(struct sk_buff *skb, u16 dev_id, u8 generation, bool strip_icv) ipv6h->payload_len = htons(ntohs(ipv6h->payload_len) - encap); } - memmove(skb->data + PSP_ENCAP_HLEN, skb->data, l2_hlen + l3_hlen); - skb_pull(skb, PSP_ENCAP_HLEN); + memmove(skb->data + sizeof(struct udphdr) + psp_hlen, + skb->data, l2_hlen + l3_hlen); + skb_pull(skb, sizeof(struct udphdr) + psp_hlen); if (strip_icv) pskb_trim(skb, skb->len - PSP_TRL_SIZE); diff --git a/net/psp/psp_nl.c b/net/psp/psp_nl.c index 6afd7707ec12..0cc744a6e1c9 100644 --- a/net/psp/psp_nl.c +++ b/net/psp/psp_nl.c @@ -305,8 +305,13 @@ int psp_assoc_device_get_locked(const struct genl_split_ops *ops, psd = psp_dev_get_for_sock(socket->sk); if (psd) { - err = psp_dev_check_access(psd, genl_info_net(info)); - if (err) { + /* Extra care needed here, psp_dev_get_for_sock() only gives + * us access to struct psp_dev's memory, which is quite weak. + */ + mutex_lock(&psd->lock); + if (!psp_dev_is_registered(psd) || + psp_dev_check_access(psd, genl_info_net(info))) { + mutex_unlock(&psd->lock); psp_dev_put(psd); psd = NULL; } @@ -319,7 +324,6 @@ int psp_assoc_device_get_locked(const struct genl_split_ops *ops, id = info->attrs[PSP_A_ASSOC_DEV_ID]; if (psd) { - mutex_lock(&psd->lock); if (id && psd->id != nla_get_u32(id)) { mutex_unlock(&psd->lock); NL_SET_ERR_MSG_ATTR(info->extack, id, diff --git a/net/rds/message.c b/net/rds/message.c index eaa6f22601a4..25fedcb3cd00 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -131,24 +131,34 @@ static void rds_rm_zerocopy_callback(struct rds_sock *rs, */ static void rds_message_purge(struct rds_message *rm) { + struct rds_znotifier *znotifier; unsigned long i, flags; - bool zcopy = false; + bool zcopy; if (unlikely(test_bit(RDS_MSG_PAGEVEC, &rm->m_flags))) return; spin_lock_irqsave(&rm->m_rs_lock, flags); + znotifier = rm->data.op_mmp_znotifier; + rm->data.op_mmp_znotifier = NULL; + zcopy = !!znotifier; + if (rm->m_rs) { struct rds_sock *rs = rm->m_rs; - if (rm->data.op_mmp_znotifier) { - zcopy = true; - rds_rm_zerocopy_callback(rs, rm->data.op_mmp_znotifier); + if (znotifier) { + rds_rm_zerocopy_callback(rs, znotifier); rds_wake_sk_sleep(rs); - rm->data.op_mmp_znotifier = NULL; } sock_put(rds_rs_to_sk(rs)); rm->m_rs = NULL; + } else if (znotifier) { + /* + * Zerocopy can fail before the message is queued on the + * socket, so there is no rs to carry the notification. + */ + mm_unaccount_pinned_pages(&znotifier->z_mmp); + kfree(rds_info_from_znotifier(znotifier)); } spin_unlock_irqrestore(&rm->m_rs_lock, flags); diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 02e1fa4577ae..5862933be8d7 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -399,14 +399,14 @@ static void cake_configure_rates(struct Qdisc *sch, u64 rate, bool rate_adjust); * Here, invsqrt is a fixed point number (< 1.0), 32bit mantissa, aka Q0.32 */ -static void cobalt_newton_step(struct cobalt_vars *vars) +static void cobalt_newton_step(struct cobalt_vars *vars, u32 count) { u32 invsqrt, invsqrt2; u64 val; invsqrt = vars->rec_inv_sqrt; invsqrt2 = ((u64)invsqrt * invsqrt) >> 32; - val = (3LL << 32) - ((u64)vars->count * invsqrt2); + val = (3LL << 32) - ((u64)count * invsqrt2); val >>= 2; /* avoid overflow in following multiply */ val = (val * invsqrt) >> (32 - 2 + 1); @@ -414,12 +414,12 @@ static void cobalt_newton_step(struct cobalt_vars *vars) vars->rec_inv_sqrt = val; } -static void cobalt_invsqrt(struct cobalt_vars *vars) +static void cobalt_invsqrt(struct cobalt_vars *vars, u32 count) { - if (vars->count < REC_INV_SQRT_CACHE) - vars->rec_inv_sqrt = inv_sqrt_cache[vars->count]; + if (count < REC_INV_SQRT_CACHE) + vars->rec_inv_sqrt = inv_sqrt_cache[count]; else - cobalt_newton_step(vars); + cobalt_newton_step(vars, count); } static void cobalt_vars_init(struct cobalt_vars *vars) @@ -449,16 +449,19 @@ static bool cobalt_queue_full(struct cobalt_vars *vars, bool up = false; if (ktime_to_ns(ktime_sub(now, vars->blue_timer)) > p->target) { - up = !vars->p_drop; - vars->p_drop += p->p_inc; - if (vars->p_drop < p->p_inc) - vars->p_drop = ~0; - vars->blue_timer = now; - } - vars->dropping = true; - vars->drop_next = now; + u32 p_drop = vars->p_drop; + + up = !p_drop; + p_drop += p->p_inc; + if (p_drop < p->p_inc) + p_drop = ~0; + WRITE_ONCE(vars->p_drop, p_drop); + WRITE_ONCE(vars->blue_timer, now); + } + WRITE_ONCE(vars->dropping, true); + WRITE_ONCE(vars->drop_next, now); if (!vars->count) - vars->count = 1; + WRITE_ONCE(vars->count, 1); return up; } @@ -475,20 +478,20 @@ static bool cobalt_queue_empty(struct cobalt_vars *vars, if (vars->p_drop && ktime_to_ns(ktime_sub(now, vars->blue_timer)) > p->target) { if (vars->p_drop < p->p_dec) - vars->p_drop = 0; + WRITE_ONCE(vars->p_drop, 0); else - vars->p_drop -= p->p_dec; - vars->blue_timer = now; + WRITE_ONCE(vars->p_drop, vars->p_drop - p->p_dec); + WRITE_ONCE(vars->blue_timer, now); down = !vars->p_drop; } - vars->dropping = false; + WRITE_ONCE(vars->dropping, false); if (vars->count && ktime_to_ns(ktime_sub(now, vars->drop_next)) >= 0) { - vars->count--; - cobalt_invsqrt(vars); - vars->drop_next = cobalt_control(vars->drop_next, - p->interval, - vars->rec_inv_sqrt); + WRITE_ONCE(vars->count, vars->count - 1); + cobalt_invsqrt(vars, vars->count); + WRITE_ONCE(vars->drop_next, + cobalt_control(vars->drop_next, p->interval, + vars->rec_inv_sqrt)); } return down; @@ -507,6 +510,7 @@ static enum qdisc_drop_reason cobalt_should_drop(struct cobalt_vars *vars, bool next_due, over_target; ktime_t schedule; u64 sojourn; + u32 count; /* The 'schedule' variable records, in its sign, whether 'now' is before or * after 'drop_next'. This allows 'drop_next' to be updated before the next @@ -528,21 +532,22 @@ static enum qdisc_drop_reason cobalt_should_drop(struct cobalt_vars *vars, over_target = sojourn > p->target && sojourn > p->mtu_time * bulk_flows * 2 && sojourn > p->mtu_time * 4; - next_due = vars->count && ktime_to_ns(schedule) >= 0; + count = vars->count; + next_due = count && ktime_to_ns(schedule) >= 0; vars->ecn_marked = false; if (over_target) { if (!vars->dropping) { - vars->dropping = true; - vars->drop_next = cobalt_control(now, - p->interval, - vars->rec_inv_sqrt); + WRITE_ONCE(vars->dropping, true); + WRITE_ONCE(vars->drop_next, + cobalt_control(now, p->interval, + vars->rec_inv_sqrt)); } - if (!vars->count) - vars->count = 1; + if (!count) + count = 1; } else if (vars->dropping) { - vars->dropping = false; + WRITE_ONCE(vars->dropping, false); } if (next_due && vars->dropping) { @@ -550,23 +555,23 @@ static enum qdisc_drop_reason cobalt_should_drop(struct cobalt_vars *vars, if (!(vars->ecn_marked = INET_ECN_set_ce(skb))) reason = QDISC_DROP_CONGESTED; - vars->count++; - if (!vars->count) - vars->count--; - cobalt_invsqrt(vars); - vars->drop_next = cobalt_control(vars->drop_next, - p->interval, - vars->rec_inv_sqrt); + count++; + if (!count) + count--; + cobalt_invsqrt(vars, count); + WRITE_ONCE(vars->drop_next, + cobalt_control(vars->drop_next, p->interval, + vars->rec_inv_sqrt)); schedule = ktime_sub(now, vars->drop_next); } else { while (next_due) { - vars->count--; - cobalt_invsqrt(vars); - vars->drop_next = cobalt_control(vars->drop_next, - p->interval, - vars->rec_inv_sqrt); + count--; + cobalt_invsqrt(vars, count); + WRITE_ONCE(vars->drop_next, + cobalt_control(vars->drop_next, p->interval, + vars->rec_inv_sqrt)); schedule = ktime_sub(now, vars->drop_next); - next_due = vars->count && ktime_to_ns(schedule) >= 0; + next_due = count && ktime_to_ns(schedule) >= 0; } } @@ -575,11 +580,12 @@ static enum qdisc_drop_reason cobalt_should_drop(struct cobalt_vars *vars, get_random_u32() < vars->p_drop) reason = QDISC_DROP_FLOOD_PROTECTION; + WRITE_ONCE(vars->count, count); /* Overload the drop_next field as an activity timeout */ - if (!vars->count) - vars->drop_next = ktime_add_ns(now, p->interval); + if (!count) + WRITE_ONCE(vars->drop_next, ktime_add_ns(now, p->interval)); else if (ktime_to_ns(schedule) > 0 && reason == QDISC_DROP_UNSPEC) - vars->drop_next = now; + WRITE_ONCE(vars->drop_next, now); return reason; } @@ -813,7 +819,7 @@ skip_hash: i++, k = (k + 1) % CAKE_SET_WAYS) { if (q->tags[outer_hash + k] == flow_hash) { if (i) - q->way_hits++; + WRITE_ONCE(q->way_hits, q->way_hits + 1); if (!q->flows[outer_hash + k].set) { /* need to increment host refcnts */ @@ -831,7 +837,7 @@ skip_hash: for (i = 0; i < CAKE_SET_WAYS; i++, k = (k + 1) % CAKE_SET_WAYS) { if (!q->flows[outer_hash + k].set) { - q->way_misses++; + WRITE_ONCE(q->way_misses, q->way_misses + 1); allocate_src = cake_dsrc(flow_mode); allocate_dst = cake_ddst(flow_mode); goto found; @@ -841,7 +847,7 @@ skip_hash: /* With no empty queues, default to the original * queue, accept the collision, update the host tags. */ - q->way_collisions++; + WRITE_ONCE(q->way_collisions, q->way_collisions + 1); allocate_src = cake_dsrc(flow_mode); allocate_dst = cake_ddst(flow_mode); @@ -914,7 +920,7 @@ static struct sk_buff *dequeue_head(struct cake_flow *flow) struct sk_buff *skb = flow->head; if (skb) { - flow->head = skb->next; + WRITE_ONCE(flow->head, skb->next); skb_mark_not_on_list(skb); } @@ -926,7 +932,7 @@ static struct sk_buff *dequeue_head(struct cake_flow *flow) static void flow_queue_add(struct cake_flow *flow, struct sk_buff *skb) { if (!flow->head) - flow->head = skb; + WRITE_ONCE(flow->head, skb); else flow->tail->next = skb; flow->tail = skb; @@ -1357,7 +1363,7 @@ found: if (elig_ack_prev) elig_ack_prev->next = elig_ack->next; else - flow->head = elig_ack->next; + WRITE_ONCE(flow->head, elig_ack->next); skb_mark_not_on_list(elig_ack); @@ -1379,9 +1385,9 @@ static u32 cake_calc_overhead(struct cake_sched_data *qd, u32 len, u32 off) len -= off; if (qd->max_netlen < len) - qd->max_netlen = len; + WRITE_ONCE(qd->max_netlen, len); if (qd->min_netlen > len) - qd->min_netlen = len; + WRITE_ONCE(qd->min_netlen, len); len += q->rate_overhead; @@ -1401,9 +1407,9 @@ static u32 cake_calc_overhead(struct cake_sched_data *qd, u32 len, u32 off) } if (qd->max_adjlen < len) - qd->max_adjlen = len; + WRITE_ONCE(qd->max_adjlen, len); if (qd->min_adjlen > len) - qd->min_adjlen = len; + WRITE_ONCE(qd->min_adjlen, len); return len; } @@ -1416,7 +1422,7 @@ static u32 cake_overhead(struct cake_sched_data *q, const struct sk_buff *skb) u16 segs = qdisc_pkt_segs(skb); u32 len = qdisc_pkt_len(skb); - q->avg_netoff = cake_ewma(q->avg_netoff, off << 16, 8); + WRITE_ONCE(q->avg_netoff, cake_ewma(q->avg_netoff, off << 16, 8)); if (segs == 1) return cake_calc_overhead(q, len, off); @@ -1590,16 +1596,17 @@ static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free) } if (cobalt_queue_full(&flow->cvars, &b->cparams, now)) - b->unresponsive_flow_count++; + WRITE_ONCE(b->unresponsive_flow_count, + b->unresponsive_flow_count + 1); len = qdisc_pkt_len(skb); q->buffer_used -= skb->truesize; - b->backlogs[idx] -= len; - b->tin_backlog -= len; + WRITE_ONCE(b->tin_backlog, b->tin_backlog - len); + WRITE_ONCE(b->backlogs[idx], b->backlogs[idx] - len); sch->qstats.backlog -= len; - flow->dropped++; - b->tin_dropped++; + WRITE_ONCE(flow->dropped, flow->dropped + 1); + WRITE_ONCE(b->tin_dropped, b->tin_dropped + 1); if (q->config->rate_flags & CAKE_FLAG_INGRESS) cake_advance_shaper(q, b, skb, now, true); @@ -1795,7 +1802,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, } if (unlikely(len > b->max_skblen)) - b->max_skblen = len; + WRITE_ONCE(b->max_skblen, len); if (qdisc_pkt_segs(skb) > 1 && q->config->rate_flags & CAKE_FLAG_SPLIT_GSO) { struct sk_buff *segs, *nskb; @@ -1819,15 +1826,15 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, numsegs++; slen += segs->len; q->buffer_used += segs->truesize; - b->packets++; + WRITE_ONCE(b->packets, b->packets + 1); } /* stats */ - b->bytes += slen; - b->backlogs[idx] += slen; - b->tin_backlog += slen; sch->qstats.backlog += slen; q->avg_window_bytes += slen; + WRITE_ONCE(b->bytes, b->bytes + slen); + WRITE_ONCE(b->tin_backlog, b->tin_backlog + slen); + WRITE_ONCE(b->backlogs[idx], b->backlogs[idx] + slen); qdisc_tree_reduce_backlog(sch, 1-numsegs, len-slen); consume_skb(skb); @@ -1843,10 +1850,10 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, ack = cake_ack_filter(q, flow); if (ack) { - b->ack_drops++; + WRITE_ONCE(b->ack_drops, b->ack_drops + 1); sch->qstats.drops++; ack_pkt_len = qdisc_pkt_len(ack); - b->bytes += ack_pkt_len; + WRITE_ONCE(b->bytes, b->bytes + ack_pkt_len); q->buffer_used += skb->truesize - ack->truesize; if (q->config->rate_flags & CAKE_FLAG_INGRESS) cake_advance_shaper(q, b, ack, now, true); @@ -1859,12 +1866,12 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, } /* stats */ - b->packets++; - b->bytes += len - ack_pkt_len; - b->backlogs[idx] += len - ack_pkt_len; - b->tin_backlog += len - ack_pkt_len; + WRITE_ONCE(b->packets, b->packets + 1); sch->qstats.backlog += len - ack_pkt_len; q->avg_window_bytes += len - ack_pkt_len; + WRITE_ONCE(b->bytes, b->bytes + len - ack_pkt_len); + WRITE_ONCE(b->tin_backlog, b->tin_backlog + len - ack_pkt_len); + WRITE_ONCE(b->backlogs[idx], b->backlogs[idx] + len - ack_pkt_len); } if (q->overflow_timeout) @@ -1894,9 +1901,9 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, u64 b = q->avg_window_bytes * (u64)NSEC_PER_SEC; b = div64_u64(b, window_interval); - q->avg_peak_bandwidth = - cake_ewma(q->avg_peak_bandwidth, b, - b > q->avg_peak_bandwidth ? 2 : 8); + WRITE_ONCE(q->avg_peak_bandwidth, + cake_ewma(q->avg_peak_bandwidth, b, + b > q->avg_peak_bandwidth ? 2 : 8)); q->avg_window_bytes = 0; q->avg_window_begin = now; @@ -1917,27 +1924,27 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (!flow->set) { list_add_tail(&flow->flowchain, &b->new_flows); } else { - b->decaying_flow_count--; + WRITE_ONCE(b->decaying_flow_count, b->decaying_flow_count - 1); list_move_tail(&flow->flowchain, &b->new_flows); } flow->set = CAKE_SET_SPARSE; - b->sparse_flow_count++; + WRITE_ONCE(b->sparse_flow_count, b->sparse_flow_count + 1); - flow->deficit = cake_get_flow_quantum(b, flow, q->config->flow_mode); + WRITE_ONCE(flow->deficit, cake_get_flow_quantum(b, flow, q->config->flow_mode)); } else if (flow->set == CAKE_SET_SPARSE_WAIT) { /* this flow was empty, accounted as a sparse flow, but actually * in the bulk rotation. */ flow->set = CAKE_SET_BULK; - b->sparse_flow_count--; - b->bulk_flow_count++; + WRITE_ONCE(b->sparse_flow_count, b->sparse_flow_count - 1); + WRITE_ONCE(b->bulk_flow_count, b->bulk_flow_count + 1); cake_inc_srchost_bulk_flow_count(b, flow, q->config->flow_mode); cake_inc_dsthost_bulk_flow_count(b, flow, q->config->flow_mode); } if (q->buffer_used > q->buffer_max_used) - q->buffer_max_used = q->buffer_used; + WRITE_ONCE(q->buffer_max_used, q->buffer_used); if (q->buffer_used <= q->buffer_limit) return NET_XMIT_SUCCESS; @@ -1976,8 +1983,8 @@ static struct sk_buff *cake_dequeue_one(struct Qdisc *sch) if (flow->head) { skb = dequeue_head(flow); len = qdisc_pkt_len(skb); - b->backlogs[q->cur_flow] -= len; - b->tin_backlog -= len; + WRITE_ONCE(b->backlogs[q->cur_flow], b->backlogs[q->cur_flow] - len); + WRITE_ONCE(b->tin_backlog, b->tin_backlog - len); sch->qstats.backlog -= len; q->buffer_used -= skb->truesize; sch->q.qlen--; @@ -2042,7 +2049,7 @@ static struct sk_buff *cake_dequeue(struct Qdisc *sch) cake_configure_rates(sch, new_rate, true); q->last_checked_active = now; - q->active_queues = num_active_qs; + WRITE_ONCE(q->active_queues, num_active_qs); } begin: @@ -2149,8 +2156,8 @@ retry: */ if (flow->set == CAKE_SET_SPARSE) { if (flow->head) { - b->sparse_flow_count--; - b->bulk_flow_count++; + WRITE_ONCE(b->sparse_flow_count, b->sparse_flow_count - 1); + WRITE_ONCE(b->bulk_flow_count, b->bulk_flow_count + 1); cake_inc_srchost_bulk_flow_count(b, flow, q->config->flow_mode); cake_inc_dsthost_bulk_flow_count(b, flow, q->config->flow_mode); @@ -2165,7 +2172,8 @@ retry: } } - flow->deficit += cake_get_flow_quantum(b, flow, q->config->flow_mode); + WRITE_ONCE(flow->deficit, + flow->deficit + cake_get_flow_quantum(b, flow, q->config->flow_mode)); list_move_tail(&flow->flowchain, &b->old_flows); goto retry; @@ -2177,7 +2185,8 @@ retry: if (!skb) { /* this queue was actually empty */ if (cobalt_queue_empty(&flow->cvars, &b->cparams, now)) - b->unresponsive_flow_count--; + WRITE_ONCE(b->unresponsive_flow_count, + b->unresponsive_flow_count - 1); if (flow->cvars.p_drop || flow->cvars.count || ktime_before(now, flow->cvars.drop_next)) { @@ -2187,32 +2196,32 @@ retry: list_move_tail(&flow->flowchain, &b->decaying_flows); if (flow->set == CAKE_SET_BULK) { - b->bulk_flow_count--; + WRITE_ONCE(b->bulk_flow_count, b->bulk_flow_count - 1); cake_dec_srchost_bulk_flow_count(b, flow, q->config->flow_mode); cake_dec_dsthost_bulk_flow_count(b, flow, q->config->flow_mode); - b->decaying_flow_count++; + WRITE_ONCE(b->decaying_flow_count, b->decaying_flow_count + 1); } else if (flow->set == CAKE_SET_SPARSE || flow->set == CAKE_SET_SPARSE_WAIT) { - b->sparse_flow_count--; - b->decaying_flow_count++; + WRITE_ONCE(b->sparse_flow_count, b->sparse_flow_count - 1); + WRITE_ONCE(b->decaying_flow_count, b->decaying_flow_count + 1); } flow->set = CAKE_SET_DECAYING; } else { /* remove empty queue from the flowchain */ list_del_init(&flow->flowchain); if (flow->set == CAKE_SET_SPARSE || - flow->set == CAKE_SET_SPARSE_WAIT) - b->sparse_flow_count--; - else if (flow->set == CAKE_SET_BULK) { - b->bulk_flow_count--; + flow->set == CAKE_SET_SPARSE_WAIT) { + WRITE_ONCE(b->sparse_flow_count, b->sparse_flow_count - 1); + } else if (flow->set == CAKE_SET_BULK) { + WRITE_ONCE(b->bulk_flow_count, b->bulk_flow_count - 1); cake_dec_srchost_bulk_flow_count(b, flow, q->config->flow_mode); cake_dec_dsthost_bulk_flow_count(b, flow, q->config->flow_mode); - } else - b->decaying_flow_count--; - + } else { + WRITE_ONCE(b->decaying_flow_count, b->decaying_flow_count - 1); + } flow->set = CAKE_SET_NONE; } goto begin; @@ -2230,11 +2239,11 @@ retry: if (q->config->rate_flags & CAKE_FLAG_INGRESS) { len = cake_advance_shaper(q, b, skb, now, true); - flow->deficit -= len; + WRITE_ONCE(flow->deficit, flow->deficit - len); b->tin_deficit -= len; } - flow->dropped++; - b->tin_dropped++; + WRITE_ONCE(flow->dropped, flow->dropped + 1); + WRITE_ONCE(b->tin_dropped, b->tin_dropped + 1); qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(skb)); qdisc_qstats_drop(sch); qdisc_dequeue_drop(sch, skb, reason); @@ -2242,20 +2251,22 @@ retry: goto retry; } - b->tin_ecn_mark += !!flow->cvars.ecn_marked; + WRITE_ONCE(b->tin_ecn_mark, b->tin_ecn_mark + !!flow->cvars.ecn_marked); qdisc_bstats_update(sch, skb); WRITE_ONCE(q->last_active, now); /* collect delay stats */ delay = ktime_to_ns(ktime_sub(now, cobalt_get_enqueue_time(skb))); - b->avge_delay = cake_ewma(b->avge_delay, delay, 8); - b->peak_delay = cake_ewma(b->peak_delay, delay, - delay > b->peak_delay ? 2 : 8); - b->base_delay = cake_ewma(b->base_delay, delay, - delay < b->base_delay ? 2 : 8); + WRITE_ONCE(b->avge_delay, cake_ewma(b->avge_delay, delay, 8)); + WRITE_ONCE(b->peak_delay, + cake_ewma(b->peak_delay, delay, + delay > b->peak_delay ? 2 : 8)); + WRITE_ONCE(b->base_delay, + cake_ewma(b->base_delay, delay, + delay < b->base_delay ? 2 : 8)); len = cake_advance_shaper(q, b, skb, now, false); - flow->deficit -= len; + WRITE_ONCE(flow->deficit, flow->deficit - len); b->tin_deficit -= len; if (ktime_after(q->time_next_packet, now) && sch->q.qlen) { @@ -2329,9 +2340,9 @@ static void cake_set_rate(struct cake_tin_data *b, u64 rate, u32 mtu, u8 rate_shft = 0; u64 rate_ns = 0; - b->flow_quantum = 1514; if (rate) { - b->flow_quantum = max(min(rate >> 12, 1514ULL), 300ULL); + WRITE_ONCE(b->flow_quantum, + max(min(rate >> 12, 1514ULL), 300ULL)); rate_shft = 34; rate_ns = ((u64)NSEC_PER_SEC) << rate_shft; rate_ns = div64_u64(rate_ns, max(MIN_RATE, rate)); @@ -2339,9 +2350,11 @@ static void cake_set_rate(struct cake_tin_data *b, u64 rate, u32 mtu, rate_ns >>= 1; rate_shft--; } - } /* else unlimited, ie. zero delay */ - - b->tin_rate_bps = rate; + } else { + /* else unlimited, ie. zero delay */ + WRITE_ONCE(b->flow_quantum, 1514); + } + WRITE_ONCE(b->tin_rate_bps, rate); b->tin_rate_ns = rate_ns; b->tin_rate_shft = rate_shft; @@ -2350,10 +2363,11 @@ static void cake_set_rate(struct cake_tin_data *b, u64 rate, u32 mtu, byte_target_ns = (byte_target * rate_ns) >> rate_shft; - b->cparams.target = max((byte_target_ns * 3) / 2, target_ns); - b->cparams.interval = max(rtt_est_ns + - b->cparams.target - target_ns, - b->cparams.target * 2); + WRITE_ONCE(b->cparams.target, + max((byte_target_ns * 3) / 2, target_ns)); + WRITE_ONCE(b->cparams.interval, + max(rtt_est_ns + b->cparams.target - target_ns, + b->cparams.target * 2)); b->cparams.mtu_time = byte_target_ns; b->cparams.p_inc = 1 << 24; /* 1/256 */ b->cparams.p_dec = 1 << 20; /* 1/4096 */ @@ -2611,25 +2625,27 @@ static void cake_reconfigure(struct Qdisc *sch) { struct cake_sched_data *qd = qdisc_priv(sch); struct cake_sched_config *q = qd->config; + u32 buffer_limit; cake_configure_rates(sch, qd->config->rate_bps, false); if (q->buffer_config_limit) { - qd->buffer_limit = q->buffer_config_limit; + buffer_limit = q->buffer_config_limit; } else if (q->rate_bps) { u64 t = q->rate_bps * q->interval; do_div(t, USEC_PER_SEC / 4); - qd->buffer_limit = max_t(u32, t, 4U << 20); + buffer_limit = max_t(u32, t, 4U << 20); } else { - qd->buffer_limit = ~0; + buffer_limit = ~0; } sch->flags &= ~TCQ_F_CAN_BYPASS; - qd->buffer_limit = min(qd->buffer_limit, - max(sch->limit * psched_mtu(qdisc_dev(sch)), - q->buffer_config_limit)); + WRITE_ONCE(qd->buffer_limit, + min(buffer_limit, + max(sch->limit * psched_mtu(qdisc_dev(sch)), + q->buffer_config_limit))); } static int cake_config_change(struct cake_sched_config *q, struct nlattr *opt, @@ -2774,10 +2790,10 @@ static int cake_change(struct Qdisc *sch, struct nlattr *opt, return ret; if (overhead_changed) { - qd->max_netlen = 0; - qd->max_adjlen = 0; - qd->min_netlen = ~0; - qd->min_adjlen = ~0; + WRITE_ONCE(qd->max_netlen, 0); + WRITE_ONCE(qd->max_adjlen, 0); + WRITE_ONCE(qd->min_netlen, ~0); + WRITE_ONCE(qd->min_adjlen, ~0); } if (qd->tins) { @@ -2995,15 +3011,15 @@ static int cake_dump_stats(struct Qdisc *sch, struct gnet_dump *d) goto nla_put_failure; \ } while (0) - PUT_STAT_U64(CAPACITY_ESTIMATE64, q->avg_peak_bandwidth); - PUT_STAT_U32(MEMORY_LIMIT, q->buffer_limit); - PUT_STAT_U32(MEMORY_USED, q->buffer_max_used); - PUT_STAT_U32(AVG_NETOFF, ((q->avg_netoff + 0x8000) >> 16)); - PUT_STAT_U32(MAX_NETLEN, q->max_netlen); - PUT_STAT_U32(MAX_ADJLEN, q->max_adjlen); - PUT_STAT_U32(MIN_NETLEN, q->min_netlen); - PUT_STAT_U32(MIN_ADJLEN, q->min_adjlen); - PUT_STAT_U32(ACTIVE_QUEUES, q->active_queues); + PUT_STAT_U64(CAPACITY_ESTIMATE64, READ_ONCE(q->avg_peak_bandwidth)); + PUT_STAT_U32(MEMORY_LIMIT, READ_ONCE(q->buffer_limit)); + PUT_STAT_U32(MEMORY_USED, READ_ONCE(q->buffer_max_used)); + PUT_STAT_U32(AVG_NETOFF, ((READ_ONCE(q->avg_netoff) + 0x8000) >> 16)); + PUT_STAT_U32(MAX_NETLEN, READ_ONCE(q->max_netlen)); + PUT_STAT_U32(MAX_ADJLEN, READ_ONCE(q->max_adjlen)); + PUT_STAT_U32(MIN_NETLEN, READ_ONCE(q->min_netlen)); + PUT_STAT_U32(MIN_ADJLEN, READ_ONCE(q->min_adjlen)); + PUT_STAT_U32(ACTIVE_QUEUES, READ_ONCE(q->active_queues)); #undef PUT_STAT_U32 #undef PUT_STAT_U64 @@ -3029,38 +3045,38 @@ static int cake_dump_stats(struct Qdisc *sch, struct gnet_dump *d) if (!ts) goto nla_put_failure; - PUT_TSTAT_U64(THRESHOLD_RATE64, b->tin_rate_bps); - PUT_TSTAT_U64(SENT_BYTES64, b->bytes); - PUT_TSTAT_U32(BACKLOG_BYTES, b->tin_backlog); + PUT_TSTAT_U64(THRESHOLD_RATE64, READ_ONCE(b->tin_rate_bps)); + PUT_TSTAT_U64(SENT_BYTES64, READ_ONCE(b->bytes)); + PUT_TSTAT_U32(BACKLOG_BYTES, READ_ONCE(b->tin_backlog)); PUT_TSTAT_U32(TARGET_US, - ktime_to_us(ns_to_ktime(b->cparams.target))); + ktime_to_us(ns_to_ktime(READ_ONCE(b->cparams.target)))); PUT_TSTAT_U32(INTERVAL_US, - ktime_to_us(ns_to_ktime(b->cparams.interval))); + ktime_to_us(ns_to_ktime(READ_ONCE(b->cparams.interval)))); - PUT_TSTAT_U32(SENT_PACKETS, b->packets); - PUT_TSTAT_U32(DROPPED_PACKETS, b->tin_dropped); - PUT_TSTAT_U32(ECN_MARKED_PACKETS, b->tin_ecn_mark); - PUT_TSTAT_U32(ACKS_DROPPED_PACKETS, b->ack_drops); + PUT_TSTAT_U32(SENT_PACKETS, READ_ONCE(b->packets)); + PUT_TSTAT_U32(DROPPED_PACKETS, READ_ONCE(b->tin_dropped)); + PUT_TSTAT_U32(ECN_MARKED_PACKETS, READ_ONCE(b->tin_ecn_mark)); + PUT_TSTAT_U32(ACKS_DROPPED_PACKETS, READ_ONCE(b->ack_drops)); PUT_TSTAT_U32(PEAK_DELAY_US, - ktime_to_us(ns_to_ktime(b->peak_delay))); + ktime_to_us(ns_to_ktime(READ_ONCE(b->peak_delay)))); PUT_TSTAT_U32(AVG_DELAY_US, - ktime_to_us(ns_to_ktime(b->avge_delay))); + ktime_to_us(ns_to_ktime(READ_ONCE(b->avge_delay)))); PUT_TSTAT_U32(BASE_DELAY_US, - ktime_to_us(ns_to_ktime(b->base_delay))); + ktime_to_us(ns_to_ktime(READ_ONCE(b->base_delay)))); - PUT_TSTAT_U32(WAY_INDIRECT_HITS, b->way_hits); - PUT_TSTAT_U32(WAY_MISSES, b->way_misses); - PUT_TSTAT_U32(WAY_COLLISIONS, b->way_collisions); + PUT_TSTAT_U32(WAY_INDIRECT_HITS, READ_ONCE(b->way_hits)); + PUT_TSTAT_U32(WAY_MISSES, READ_ONCE(b->way_misses)); + PUT_TSTAT_U32(WAY_COLLISIONS, READ_ONCE(b->way_collisions)); - PUT_TSTAT_U32(SPARSE_FLOWS, b->sparse_flow_count + - b->decaying_flow_count); - PUT_TSTAT_U32(BULK_FLOWS, b->bulk_flow_count); - PUT_TSTAT_U32(UNRESPONSIVE_FLOWS, b->unresponsive_flow_count); - PUT_TSTAT_U32(MAX_SKBLEN, b->max_skblen); + PUT_TSTAT_U32(SPARSE_FLOWS, READ_ONCE(b->sparse_flow_count) + + READ_ONCE(b->decaying_flow_count)); + PUT_TSTAT_U32(BULK_FLOWS, READ_ONCE(b->bulk_flow_count)); + PUT_TSTAT_U32(UNRESPONSIVE_FLOWS, READ_ONCE(b->unresponsive_flow_count)); + PUT_TSTAT_U32(MAX_SKBLEN, READ_ONCE(b->max_skblen)); - PUT_TSTAT_U32(FLOW_QUANTUM, b->flow_quantum); + PUT_TSTAT_U32(FLOW_QUANTUM, READ_ONCE(b->flow_quantum)); nla_nest_end(d->skb, ts); } @@ -3128,7 +3144,7 @@ static int cake_dump_class_stats(struct Qdisc *sch, unsigned long cl, flow = &b->flows[idx % CAKE_QUEUES]; - if (flow->head) { + if (READ_ONCE(flow->head)) { sch_tree_lock(sch); skb = flow->head; while (skb) { @@ -3137,13 +3153,15 @@ static int cake_dump_class_stats(struct Qdisc *sch, unsigned long cl, } sch_tree_unlock(sch); } - qs.backlog = b->backlogs[idx % CAKE_QUEUES]; - qs.drops = flow->dropped; + qs.backlog = READ_ONCE(b->backlogs[idx % CAKE_QUEUES]); + qs.drops = READ_ONCE(flow->dropped); } if (gnet_stats_copy_queue(d, NULL, &qs, qs.qlen) < 0) return -1; if (flow) { ktime_t now = ktime_get(); + bool dropping; + u32 p_drop; stats = nla_nest_start_noflag(d->skb, TCA_STATS_APP); if (!stats) @@ -3158,21 +3176,23 @@ static int cake_dump_class_stats(struct Qdisc *sch, unsigned long cl, goto nla_put_failure; \ } while (0) - PUT_STAT_S32(DEFICIT, flow->deficit); - PUT_STAT_U32(DROPPING, flow->cvars.dropping); - PUT_STAT_U32(COBALT_COUNT, flow->cvars.count); - PUT_STAT_U32(P_DROP, flow->cvars.p_drop); - if (flow->cvars.p_drop) { + PUT_STAT_S32(DEFICIT, READ_ONCE(flow->deficit)); + dropping = READ_ONCE(flow->cvars.dropping); + PUT_STAT_U32(DROPPING, dropping); + PUT_STAT_U32(COBALT_COUNT, READ_ONCE(flow->cvars.count)); + p_drop = READ_ONCE(flow->cvars.p_drop); + PUT_STAT_U32(P_DROP, p_drop); + if (p_drop) { PUT_STAT_S32(BLUE_TIMER_US, ktime_to_us( ktime_sub(now, - flow->cvars.blue_timer))); + READ_ONCE(flow->cvars.blue_timer)))); } - if (flow->cvars.dropping) { + if (dropping) { PUT_STAT_S32(DROP_NEXT_US, ktime_to_us( ktime_sub(now, - flow->cvars.drop_next))); + READ_ONCE(flow->cvars.drop_next)))); } if (nla_nest_end(d->skb, stats) < 0) @@ -3298,10 +3318,10 @@ static int cake_mq_change(struct Qdisc *sch, struct nlattr *opt, struct cake_sched_data *qd = qdisc_priv(chld); if (overhead_changed) { - qd->max_netlen = 0; - qd->max_adjlen = 0; - qd->min_netlen = ~0; - qd->min_adjlen = ~0; + WRITE_ONCE(qd->max_netlen, 0); + WRITE_ONCE(qd->max_adjlen, 0); + WRITE_ONCE(qd->min_netlen, ~0); + WRITE_ONCE(qd->min_adjlen, ~0); } if (qd->tins) { diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index 94df8e741a97..2875bcdb18a4 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -229,7 +229,7 @@ static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* Draw a packet at random from queue and compare flow */ if (choke_match_random(q, skb, &idx)) { - q->stats.matched++; + WRITE_ONCE(q->stats.matched, q->stats.matched + 1); choke_drop_by_idx(sch, idx, to_free); goto congestion_drop; } @@ -241,11 +241,13 @@ static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch, qdisc_qstats_overlimit(sch); if (use_harddrop(q) || !use_ecn(q) || !INET_ECN_set_ce(skb)) { - q->stats.forced_drop++; + WRITE_ONCE(q->stats.forced_drop, + q->stats.forced_drop + 1); goto congestion_drop; } - q->stats.forced_mark++; + WRITE_ONCE(q->stats.forced_mark, + q->stats.forced_mark + 1); } else if (++q->vars.qcount) { if (red_mark_probability(p, &q->vars, q->vars.qavg)) { q->vars.qcount = 0; @@ -253,11 +255,13 @@ static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch, qdisc_qstats_overlimit(sch); if (!use_ecn(q) || !INET_ECN_set_ce(skb)) { - q->stats.prob_drop++; + WRITE_ONCE(q->stats.prob_drop, + q->stats.prob_drop + 1); goto congestion_drop; } - q->stats.prob_mark++; + WRITE_ONCE(q->stats.prob_mark, + q->stats.prob_mark + 1); } } else q->vars.qR = red_random(p); @@ -272,7 +276,7 @@ static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch, return NET_XMIT_SUCCESS; } - q->stats.pdrop++; + WRITE_ONCE(q->stats.pdrop, q->stats.pdrop + 1); return qdisc_drop(skb, sch, to_free); congestion_drop: @@ -461,10 +465,12 @@ static int choke_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { struct choke_sched_data *q = qdisc_priv(sch); struct tc_choke_xstats st = { - .early = q->stats.prob_drop + q->stats.forced_drop, - .marked = q->stats.prob_mark + q->stats.forced_mark, - .pdrop = q->stats.pdrop, - .matched = q->stats.matched, + .early = READ_ONCE(q->stats.prob_drop) + + READ_ONCE(q->stats.forced_drop), + .marked = READ_ONCE(q->stats.prob_mark) + + READ_ONCE(q->stats.forced_mark), + .pdrop = READ_ONCE(q->stats.pdrop), + .matched = READ_ONCE(q->stats.matched), }; return gnet_stats_copy_app(d, &st, sizeof(st)); diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 0664b2f2d6f2..24db54684e8a 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -117,7 +117,7 @@ static inline struct sk_buff *dequeue_head(struct fq_codel_flow *flow) { struct sk_buff *skb = flow->head; - flow->head = skb->next; + WRITE_ONCE(flow->head, skb->next); skb_mark_not_on_list(skb); return skb; } @@ -127,7 +127,7 @@ static inline void flow_queue_add(struct fq_codel_flow *flow, struct sk_buff *skb) { if (flow->head == NULL) - flow->head = skb; + WRITE_ONCE(flow->head, skb); else flow->tail->next = skb; flow->tail = skb; @@ -173,8 +173,8 @@ static unsigned int fq_codel_drop(struct Qdisc *sch, unsigned int max_packets, } while (++i < max_packets && len < threshold); /* Tell codel to increase its signal strength also */ - flow->cvars.count += i; - q->backlogs[idx] -= len; + WRITE_ONCE(flow->cvars.count, flow->cvars.count + i); + WRITE_ONCE(q->backlogs[idx], q->backlogs[idx] - len); q->memory_usage -= mem; sch->qstats.drops += i; sch->qstats.backlog -= len; @@ -204,13 +204,13 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch, codel_set_enqueue_time(skb); flow = &q->flows[idx]; flow_queue_add(flow, skb); - q->backlogs[idx] += qdisc_pkt_len(skb); + WRITE_ONCE(q->backlogs[idx], q->backlogs[idx] + qdisc_pkt_len(skb)); qdisc_qstats_backlog_inc(sch, skb); if (list_empty(&flow->flowchain)) { list_add_tail(&flow->flowchain, &q->new_flows); q->new_flow_count++; - flow->deficit = q->quantum; + WRITE_ONCE(flow->deficit, q->quantum); } get_codel_cb(skb)->mem_usage = skb->truesize; q->memory_usage += get_codel_cb(skb)->mem_usage; @@ -263,7 +263,8 @@ static struct sk_buff *dequeue_func(struct codel_vars *vars, void *ctx) flow = container_of(vars, struct fq_codel_flow, cvars); if (flow->head) { skb = dequeue_head(flow); - q->backlogs[flow - q->flows] -= qdisc_pkt_len(skb); + WRITE_ONCE(q->backlogs[flow - q->flows], + q->backlogs[flow - q->flows] - qdisc_pkt_len(skb)); q->memory_usage -= get_codel_cb(skb)->mem_usage; sch->q.qlen--; sch->qstats.backlog -= qdisc_pkt_len(skb); @@ -296,7 +297,7 @@ begin: flow = list_first_entry(head, struct fq_codel_flow, flowchain); if (flow->deficit <= 0) { - flow->deficit += q->quantum; + WRITE_ONCE(flow->deficit, flow->deficit + q->quantum); list_move_tail(&flow->flowchain, &q->old_flows); goto begin; } @@ -314,7 +315,7 @@ begin: goto begin; } qdisc_bstats_update(sch, skb); - flow->deficit -= qdisc_pkt_len(skb); + WRITE_ONCE(flow->deficit, flow->deficit - qdisc_pkt_len(skb)); if (q->cstats.drop_count) { qdisc_tree_reduce_backlog(sch, q->cstats.drop_count, @@ -328,7 +329,7 @@ begin: static void fq_codel_flow_purge(struct fq_codel_flow *flow) { rtnl_kfree_skbs(flow->head, flow->tail); - flow->head = NULL; + WRITE_ONCE(flow->head, NULL); } static void fq_codel_reset(struct Qdisc *sch) @@ -656,21 +657,21 @@ static int fq_codel_dump_class_stats(struct Qdisc *sch, unsigned long cl, memset(&xstats, 0, sizeof(xstats)); xstats.type = TCA_FQ_CODEL_XSTATS_CLASS; - xstats.class_stats.deficit = flow->deficit; + xstats.class_stats.deficit = READ_ONCE(flow->deficit); xstats.class_stats.ldelay = - codel_time_to_us(flow->cvars.ldelay); - xstats.class_stats.count = flow->cvars.count; - xstats.class_stats.lastcount = flow->cvars.lastcount; - xstats.class_stats.dropping = flow->cvars.dropping; - if (flow->cvars.dropping) { - codel_tdiff_t delta = flow->cvars.drop_next - + codel_time_to_us(READ_ONCE(flow->cvars.ldelay)); + xstats.class_stats.count = READ_ONCE(flow->cvars.count); + xstats.class_stats.lastcount = READ_ONCE(flow->cvars.lastcount); + xstats.class_stats.dropping = READ_ONCE(flow->cvars.dropping); + if (xstats.class_stats.dropping) { + codel_tdiff_t delta = READ_ONCE(flow->cvars.drop_next) - codel_get_time(); xstats.class_stats.drop_next = (delta >= 0) ? codel_time_to_us(delta) : -codel_time_to_us(-delta); } - if (flow->head) { + if (READ_ONCE(flow->head)) { sch_tree_lock(sch); skb = flow->head; while (skb) { @@ -679,7 +680,7 @@ static int fq_codel_dump_class_stats(struct Qdisc *sch, unsigned long cl, } sch_tree_unlock(sch); } - qs.backlog = q->backlogs[idx]; + qs.backlog = READ_ONCE(q->backlogs[idx]); qs.drops = 0; } if (gnet_stats_copy_queue(d, NULL, &qs, qs.qlen) < 0) diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index 154c70f489f2..7becbf5362b3 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -509,18 +509,19 @@ nla_put_failure: static int fq_pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { struct fq_pie_sched_data *q = qdisc_priv(sch); - struct tc_fq_pie_xstats st = { - .packets_in = q->stats.packets_in, - .overlimit = q->stats.overlimit, - .overmemory = q->overmemory, - .dropped = q->stats.dropped, - .ecn_mark = q->stats.ecn_mark, - .new_flow_count = q->new_flow_count, - .memory_usage = q->memory_usage, - }; + struct tc_fq_pie_xstats st = { 0 }; struct list_head *pos; sch_tree_lock(sch); + + st.packets_in = q->stats.packets_in; + st.overlimit = q->stats.overlimit; + st.overmemory = q->overmemory; + st.dropped = q->stats.dropped; + st.ecn_mark = q->stats.ecn_mark; + st.new_flow_count = q->new_flow_count; + st.memory_usage = q->memory_usage; + list_for_each(pos, &q->new_flows) st.new_flows_len++; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 20df1c08b1e9..bc18e1976b6e 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -227,10 +227,10 @@ static bool loss_4state(struct netem_sched_data *q) if (rnd < clg->a4) { clg->state = LOST_IN_GAP_PERIOD; return true; - } else if (clg->a4 < rnd && rnd < clg->a1 + clg->a4) { + } else if (rnd < clg->a1 + clg->a4) { clg->state = LOST_IN_BURST_PERIOD; return true; - } else if (clg->a1 + clg->a4 < rnd) { + } else { clg->state = TX_IN_GAP_PERIOD; } @@ -247,9 +247,9 @@ static bool loss_4state(struct netem_sched_data *q) case LOST_IN_BURST_PERIOD: if (rnd < clg->a3) clg->state = TX_IN_BURST_PERIOD; - else if (clg->a3 < rnd && rnd < clg->a2 + clg->a3) { + else if (rnd < clg->a2 + clg->a3) { clg->state = TX_IN_GAP_PERIOD; - } else if (clg->a2 + clg->a3 < rnd) { + } else { clg->state = LOST_IN_BURST_PERIOD; return true; } @@ -524,7 +524,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, 1 << get_random_u32_below(8); } - if (unlikely(q->t_len >= sch->limit)) { + if (unlikely(sch->q.qlen >= sch->limit)) { /* re-link segs, so that qdisc_drop_all() frees them all */ skb->next = segs; qdisc_drop_all(skb, sch, to_free); @@ -659,9 +659,8 @@ static void get_slot_next(struct netem_sched_data *q, u64 now) if (!q->slot_dist) next_delay = q->slot_config.min_delay + - (get_random_u32() * - (q->slot_config.max_delay - - q->slot_config.min_delay) >> 32); + mul_u64_u32_shr(q->slot_config.max_delay - q->slot_config.min_delay, + get_random_u32(), 32); else next_delay = tabledist(q->slot_config.dist_delay, (s32)(q->slot_config.dist_jitter), @@ -827,6 +826,39 @@ static int get_dist_table(struct disttable **tbl, const struct nlattr *attr) return 0; } +static int validate_time(const struct nlattr *attr, const char *name, + struct netlink_ext_ack *extack) +{ + if (nla_get_s64(attr) < 0) { + NL_SET_ERR_MSG_ATTR_FMT(extack, attr, "negative %s", name); + return -EINVAL; + } + return 0; +} + +static int validate_slot(const struct nlattr *attr, struct netlink_ext_ack *extack) +{ + const struct tc_netem_slot *c = nla_data(attr); + + if (c->min_delay < 0 || c->max_delay < 0) { + NL_SET_ERR_MSG_ATTR(extack, attr, "negative slot delay"); + return -EINVAL; + } + if (c->min_delay > c->max_delay) { + NL_SET_ERR_MSG_ATTR(extack, attr, "slot min delay greater than max delay"); + return -EINVAL; + } + if (c->dist_delay < 0 || c->dist_jitter < 0) { + NL_SET_ERR_MSG_ATTR(extack, attr, "negative dist delay"); + return -EINVAL; + } + if (c->max_packets < 0 || c->max_bytes < 0) { + NL_SET_ERR_MSG_ATTR(extack, attr, "negative slot limit"); + return -EINVAL; + } + return 0; +} + static void get_slot(struct netem_sched_data *q, const struct nlattr *attr) { const struct tc_netem_slot *c = nla_data(attr); @@ -1040,6 +1072,24 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, goto table_free; } + if (tb[TCA_NETEM_SLOT]) { + ret = validate_slot(tb[TCA_NETEM_SLOT], extack); + if (ret) + goto table_free; + } + + if (tb[TCA_NETEM_LATENCY64]) { + ret = validate_time(tb[TCA_NETEM_LATENCY64], "latency", extack); + if (ret) + goto table_free; + } + + if (tb[TCA_NETEM_JITTER64]) { + ret = validate_time(tb[TCA_NETEM_JITTER64], "jitter", extack); + if (ret) + goto table_free; + } + sch_tree_lock(sch); /* backup q->clg and q->loss_model */ old_clg = q->clg; @@ -1112,11 +1162,10 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, /* capping jitter to the range acceptable by tabledist() */ q->jitter = min_t(s64, abs(q->jitter), INT_MAX); - if (tb[TCA_NETEM_PRNG_SEED]) + if (tb[TCA_NETEM_PRNG_SEED]) { q->prng.seed = nla_get_u64(tb[TCA_NETEM_PRNG_SEED]); - else - q->prng.seed = get_random_u64(); - prandom_seed_state(&q->prng.prng_state, q->prng.seed); + prandom_seed_state(&q->prng.prng_state, q->prng.seed); + } unlock: sch_tree_unlock(sch); @@ -1139,6 +1188,9 @@ static int netem_init(struct Qdisc *sch, struct nlattr *opt, return -EINVAL; q->loss_model = CLG_RANDOM; + q->prng.seed = get_random_u64(); + prandom_seed_state(&q->prng.prng_state, q->prng.seed); + ret = netem_change(sch, opt, extack); if (ret) pr_info("netem: change failed\n"); diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index fb53fbf0e328..b41f2def2e2c 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -219,16 +219,14 @@ void pie_process_dequeue(struct sk_buff *skb, struct pie_params *params, * packet timestamp. */ if (!params->dq_rate_estimator) { - vars->qdelay = now - pie_get_enqueue_time(skb); + WRITE_ONCE(vars->qdelay, + backlog ? now - pie_get_enqueue_time(skb) : 0); if (vars->dq_tstamp != DTIME_INVALID) dtime = now - vars->dq_tstamp; vars->dq_tstamp = now; - if (backlog == 0) - vars->qdelay = 0; - if (dtime == 0) return; @@ -376,7 +374,7 @@ void pie_calculate_probability(struct pie_params *params, struct pie_vars *vars, if (qdelay > (PSCHED_NS2TICKS(250 * NSEC_PER_MSEC))) delta += MAX_PROB / (100 / 2); - vars->prob += delta; + WRITE_ONCE(vars->prob, vars->prob + delta); if (delta > 0) { /* prevent overflow */ @@ -401,7 +399,7 @@ void pie_calculate_probability(struct pie_params *params, struct pie_vars *vars, if (qdelay == 0 && qdelay_old == 0 && update_prob) /* Reduce drop probability to 98.4% */ - vars->prob -= vars->prob / 64; + WRITE_ONCE(vars->prob, vars->prob - vars->prob / 64); WRITE_ONCE(vars->qdelay, qdelay); vars->backlog_old = backlog; @@ -501,7 +499,7 @@ static int pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { struct pie_sched_data *q = qdisc_priv(sch); struct tc_pie_xstats st = { - .prob = q->vars.prob << BITS_PER_BYTE, + .prob = READ_ONCE(q->vars.prob) << BITS_PER_BYTE, .delay = ((u32)PSCHED_TICKS2NS(READ_ONCE(q->vars.qdelay))) / NSEC_PER_USEC, .packets_in = READ_ONCE(q->stats.packets_in), @@ -512,7 +510,7 @@ static int pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d) }; /* avg_dq_rate is only valid if dq_rate_estimator is enabled */ - st.dq_rate_estimating = q->params.dq_rate_estimator; + st.dq_rate_estimating = READ_ONCE(q->params.dq_rate_estimator); /* unscale and return dq_rate in bytes per sec */ if (st.dq_rate_estimating) diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 432b8a3000a5..4d0e44a2e7c6 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -162,7 +162,7 @@ static struct sk_buff *red_dequeue(struct Qdisc *sch) struct red_sched_data *q = qdisc_priv(sch); struct Qdisc *child = q->qdisc; - skb = child->dequeue(child); + skb = qdisc_dequeue_peeked(child); if (skb) { qdisc_bstats_update(sch, skb); qdisc_qstats_backlog_dec(sch, skb); diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index bd5ef561030f..d3ee8e5479b3 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -441,7 +441,7 @@ static struct sk_buff *sfb_dequeue(struct Qdisc *sch) struct Qdisc *child = q->qdisc; struct sk_buff *skb; - skb = child->dequeue(q->qdisc); + skb = qdisc_dequeue_peeked(child); if (skb) { qdisc_bstats_update(sch, skb); diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index c3f3181dba54..f39822babf88 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -225,7 +225,8 @@ static inline void sfq_dec(struct sfq_sched_data *q, sfq_index x) sfq_unlink(q, x, n, p); - d = q->slots[x].qlen--; + d = q->slots[x].qlen; + WRITE_ONCE(q->slots[x].qlen, d - 1); if (n == p && q->cur_depth == d) q->cur_depth--; sfq_link(q, x); @@ -238,7 +239,8 @@ static inline void sfq_inc(struct sfq_sched_data *q, sfq_index x) sfq_unlink(q, x, n, p); - d = ++q->slots[x].qlen; + d = q->slots[x].qlen + 1; + WRITE_ONCE(q->slots[x].qlen, d); if (q->cur_depth < d) q->cur_depth = d; sfq_link(q, x); @@ -298,7 +300,7 @@ static unsigned int sfq_drop(struct Qdisc *sch, struct sk_buff **to_free) drop: skb = q->headdrop ? slot_dequeue_head(slot) : slot_dequeue_tail(slot); len = qdisc_pkt_len(skb); - slot->backlog -= len; + WRITE_ONCE(slot->backlog, slot->backlog - len); sfq_dec(q, x); sch->q.qlen--; qdisc_qstats_backlog_dec(sch, skb); @@ -314,7 +316,7 @@ drop: q->tail = NULL; /* no more active slots */ else q->tail->next = slot->next; - q->ht[slot->hash] = SFQ_EMPTY_SLOT; + WRITE_ONCE(q->ht[slot->hash], SFQ_EMPTY_SLOT); goto drop; } @@ -364,10 +366,10 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) x = q->dep[0].next; /* get a free slot */ if (x >= SFQ_MAX_FLOWS) return qdisc_drop_reason(skb, sch, to_free, QDISC_DROP_MAXFLOWS); - q->ht[hash] = x; + WRITE_ONCE(q->ht[hash], x); slot = &q->slots[x]; slot->hash = hash; - slot->backlog = 0; /* should already be 0 anyway... */ + WRITE_ONCE(slot->backlog, 0); /* should already be 0 anyway... */ red_set_vars(&slot->vars); goto enqueue; } @@ -426,7 +428,7 @@ congestion_drop: head = slot_dequeue_head(slot); delta = qdisc_pkt_len(head) - qdisc_pkt_len(skb); sch->qstats.backlog -= delta; - slot->backlog -= delta; + WRITE_ONCE(slot->backlog, slot->backlog - delta); qdisc_drop_reason(head, sch, to_free, QDISC_DROP_FLOW_LIMIT); slot_queue_add(slot, skb); @@ -436,7 +438,7 @@ congestion_drop: enqueue: qdisc_qstats_backlog_inc(sch, skb); - slot->backlog += qdisc_pkt_len(skb); + WRITE_ONCE(slot->backlog, slot->backlog + qdisc_pkt_len(skb)); slot_queue_add(slot, skb); sfq_inc(q, x); if (slot->qlen == 1) { /* The flow is new */ @@ -452,7 +454,7 @@ enqueue: */ q->tail = slot; /* We could use a bigger initial quantum for new flows */ - slot->allot = q->quantum; + WRITE_ONCE(slot->allot, q->quantum); } if (++sch->q.qlen <= q->limit) return NET_XMIT_SUCCESS; @@ -489,7 +491,7 @@ next_slot: slot = &q->slots[a]; if (slot->allot <= 0) { q->tail = slot; - slot->allot += q->quantum; + WRITE_ONCE(slot->allot, slot->allot + q->quantum); goto next_slot; } skb = slot_dequeue_head(slot); @@ -497,10 +499,10 @@ next_slot: qdisc_bstats_update(sch, skb); sch->q.qlen--; qdisc_qstats_backlog_dec(sch, skb); - slot->backlog -= qdisc_pkt_len(skb); + WRITE_ONCE(slot->backlog, slot->backlog - qdisc_pkt_len(skb)); /* Is the slot empty? */ if (slot->qlen == 0) { - q->ht[slot->hash] = SFQ_EMPTY_SLOT; + WRITE_ONCE(q->ht[slot->hash], SFQ_EMPTY_SLOT); next_a = slot->next; if (a == next_a) { q->tail = NULL; /* no more active slots */ @@ -508,7 +510,7 @@ next_slot: } q->tail->next = next_a; } else { - slot->allot -= qdisc_pkt_len(skb); + WRITE_ONCE(slot->allot, slot->allot - qdisc_pkt_len(skb)); } return skb; } @@ -549,9 +551,9 @@ static void sfq_rehash(struct Qdisc *sch) sfq_dec(q, i); __skb_queue_tail(&list, skb); } - slot->backlog = 0; + WRITE_ONCE(slot->backlog, 0); red_set_vars(&slot->vars); - q->ht[slot->hash] = SFQ_EMPTY_SLOT; + WRITE_ONCE(q->ht[slot->hash], SFQ_EMPTY_SLOT); } q->tail = NULL; @@ -570,7 +572,7 @@ drop: dropped++; continue; } - q->ht[hash] = x; + WRITE_ONCE(q->ht[hash], x); slot = &q->slots[x]; slot->hash = hash; } @@ -581,7 +583,7 @@ drop: slot->vars.qavg = red_calc_qavg(q->red_parms, &slot->vars, slot->backlog); - slot->backlog += qdisc_pkt_len(skb); + WRITE_ONCE(slot->backlog, slot->backlog + qdisc_pkt_len(skb)); sfq_inc(q, x); if (slot->qlen == 1) { /* The flow is new */ if (q->tail == NULL) { /* It is the first flow */ @@ -591,7 +593,7 @@ drop: q->tail->next = x; } q->tail = slot; - slot->allot = q->quantum; + WRITE_ONCE(slot->allot, q->quantum); } } sch->q.qlen -= dropped; @@ -905,16 +907,16 @@ static int sfq_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct gnet_dump *d) { struct sfq_sched_data *q = qdisc_priv(sch); - sfq_index idx = q->ht[cl - 1]; + sfq_index idx = READ_ONCE(q->ht[cl - 1]); struct gnet_stats_queue qs = { 0 }; struct tc_sfq_xstats xstats = { 0 }; if (idx != SFQ_EMPTY_SLOT) { const struct sfq_slot *slot = &q->slots[idx]; - xstats.allot = slot->allot; - qs.qlen = slot->qlen; - qs.backlog = slot->backlog; + xstats.allot = READ_ONCE(slot->allot); + qs.qlen = READ_ONCE(slot->qlen); + qs.backlog = READ_ONCE(slot->backlog); } if (gnet_stats_copy_queue(d, NULL, &qs, qs.qlen) < 0) return -1; @@ -930,7 +932,7 @@ static void sfq_walk(struct Qdisc *sch, struct qdisc_walker *arg) return; for (i = 0; i < q->divisor; i++) { - if (q->ht[i] == SFQ_EMPTY_SLOT) { + if (READ_ONCE(q->ht[i]) == SFQ_EMPTY_SLOT) { arg->count++; continue; } diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index a47a09d76400..45245157e00a 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -634,7 +634,7 @@ static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, queue = skb_get_queue_mapping(skb); child = q->qdiscs[queue]; - if (unlikely(!child)) + if (unlikely(child == &noop_qdisc)) return qdisc_drop(skb, sch, to_free); if (taprio_skb_exceeds_queue_max_sdu(sch, skb)) { @@ -717,7 +717,7 @@ static struct sk_buff *taprio_dequeue_from_txq(struct Qdisc *sch, int txq, int len; u8 tc; - if (unlikely(!child)) + if (unlikely(child == &noop_qdisc)) return NULL; if (TXTIME_ASSIST_IS_ENABLED(q->flags)) @@ -2184,6 +2184,9 @@ static int taprio_graft(struct Qdisc *sch, unsigned long cl, if (!dev_queue) return -EINVAL; + if (!new) + new = &noop_qdisc; + if (dev->flags & IFF_UP) dev_deactivate(dev, false); @@ -2197,14 +2200,14 @@ static int taprio_graft(struct Qdisc *sch, unsigned long cl, *old = q->qdiscs[cl - 1]; if (FULL_OFFLOAD_IS_ENABLED(q->flags)) { WARN_ON_ONCE(dev_graft_qdisc(dev_queue, new) != *old); - if (new) + if (new != &noop_qdisc) qdisc_refcount_inc(new); - if (*old) + if (*old && *old != &noop_qdisc) qdisc_put(*old); } q->qdiscs[cl - 1] = new; - if (new) + if (new != &noop_qdisc) new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; if (dev->flags & IFF_UP) diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 7b823d759141..8e89a870780c 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -1556,6 +1556,12 @@ static enum sctp_disposition sctp_sf_do_unexpected_init( /* Tag the variable length parameters. */ chunk->param_hdr.v = skb_pull(chunk->skb, sizeof(struct sctp_inithdr)); + if (asoc->state >= SCTP_STATE_ESTABLISHED) { + /* Discard INIT matching peer vtag after handshake completion (stale INIT). */ + if (ntohl(chunk->subh.init_hdr->init_tag) == asoc->peer.i.init_tag) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + } + /* Verify the INIT chunk before processing it. */ err_chunk = NULL; if (!sctp_verify_init(net, ep, asoc, chunk->chunk_hdr->type, diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 1a565095376a..185dbed7de5d 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1628,12 +1628,8 @@ static void smc_connect_work(struct work_struct *work) lock_sock(&smc->sk); if (rc != 0 || smc->sk.sk_err) { smc->sk.sk_state = SMC_CLOSED; - if (rc == -EPIPE || rc == -EAGAIN) - smc->sk.sk_err = EPIPE; - else if (rc == -ECONNREFUSED) - smc->sk.sk_err = ECONNREFUSED; - else if (signal_pending(current)) - smc->sk.sk_err = -sock_intr_errno(timeo); + if (!smc->sk.sk_err) + smc->sk.sk_err = (rc == -EAGAIN) ? EPIPE : -rc; sock_put(&smc->sk); /* passive closing */ goto out; } diff --git a/net/tls/tls.h b/net/tls/tls.h index e8f81a006520..12f44cb649c9 100644 --- a/net/tls/tls.h +++ b/net/tls/tls.h @@ -188,6 +188,7 @@ int tls_strp_dev_init(void); void tls_strp_dev_exit(void); void tls_strp_done(struct tls_strparser *strp); +void __tls_strp_done(struct tls_strparser *strp); void tls_strp_stop(struct tls_strparser *strp); int tls_strp_init(struct tls_strparser *strp, struct sock *sk); void tls_strp_data_ready(struct tls_strparser *strp); diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index 98e12f0ff57e..c72e88317627 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -624,6 +624,12 @@ void tls_strp_done(struct tls_strparser *strp) WARN_ON(!strp->stopped); cancel_work_sync(&strp->work); + __tls_strp_done(strp); +} + +/* For setup error paths where the strparser was initialized but never armed. */ +void __tls_strp_done(struct tls_strparser *strp) +{ tls_strp_anchor_free(strp); } diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 94d2ae0daa8c..2590e855f6a5 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2317,9 +2317,9 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, if (copied < 0) goto splice_requeue; - if (chunk < rxm->full_len) { - rxm->offset += len; - rxm->full_len -= len; + if (copied < rxm->full_len) { + rxm->offset += copied; + rxm->full_len -= copied; goto splice_requeue; } @@ -2624,8 +2624,12 @@ void tls_sw_free_ctx_rx(struct tls_context *tls_ctx) void tls_sw_free_resources_rx(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context_rx *ctx; + + ctx = tls_sw_ctx_rx(tls_ctx); tls_sw_release_resources_rx(sk); + __tls_strp_done(&ctx->strp); tls_sw_free_ctx_rx(tls_ctx); } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index e2d787ca3e74..1cbf36ea043b 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -3323,6 +3323,9 @@ static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) struct sk_buff *skb; int answ = 0; + if (sk->sk_type != SOCK_STREAM) + return -EOPNOTSUPP; + mutex_lock(&u->iolock); skb = skb_peek(&sk->sk_receive_queue); diff --git a/net/unix/garbage.c b/net/unix/garbage.c index a7967a345827..0783555e2526 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -607,6 +607,8 @@ static void unix_gc(struct work_struct *work) struct sk_buff_head hitlist; struct sk_buff *skb; + WRITE_ONCE(gc_in_progress, true); + spin_lock(&unix_gc_lock); if (unix_graph_state == UNIX_GRAPH_NOT_CYCLIC) { @@ -649,10 +651,8 @@ void unix_schedule_gc(struct user_struct *user) READ_ONCE(user->unix_inflight) < UNIX_INFLIGHT_SANE_USER) return; - if (!READ_ONCE(gc_in_progress)) { - WRITE_ONCE(gc_in_progress, true); + if (!READ_ONCE(gc_in_progress)) queue_work(system_dfl_wq, &unix_gc_work); - } if (user && READ_ONCE(unix_graph_cyclic_sccs)) flush_work(&unix_gc_work); diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c index f862988c1e86..7a8963595bf9 100644 --- a/net/vmw_vsock/hyperv_transport.c +++ b/net/vmw_vsock/hyperv_transport.c @@ -375,10 +375,10 @@ static void hvs_open_connection(struct vmbus_channel *chan) } else { sndbuf = max_t(int, sk->sk_sndbuf, RINGBUFFER_HVS_SND_SIZE); sndbuf = min_t(int, sndbuf, RINGBUFFER_HVS_MAX_SIZE); - sndbuf = ALIGN(sndbuf, HV_HYP_PAGE_SIZE); + sndbuf = VMBUS_RING_SIZE(sndbuf); rcvbuf = max_t(int, sk->sk_rcvbuf, RINGBUFFER_HVS_RCV_SIZE); rcvbuf = min_t(int, rcvbuf, RINGBUFFER_HVS_MAX_SIZE); - rcvbuf = ALIGN(rcvbuf, HV_HYP_PAGE_SIZE); + rcvbuf = VMBUS_RING_SIZE(rcvbuf); } chan->max_pkt_size = HVS_MAX_PKT_SIZE; diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 416d533f493d..9b8014516f4f 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -447,7 +447,9 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, static bool virtio_transport_inc_rx_pkt(struct virtio_vsock_sock *vvs, u32 len) { - if (vvs->buf_used + len > vvs->buf_alloc) + u64 skb_overhead = (skb_queue_len(&vvs->rx_queue) + 1) * SKB_TRUESIZE(0); + + if (skb_overhead + vvs->buf_used + len > vvs->buf_alloc) return false; vvs->rx_bytes += len; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index f334cdef8958..7db9cd433801 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1276,6 +1276,18 @@ static int nl80211_prepare_wdev_dump(struct netlink_callback *cb, rtnl_unlock(); return -ENODEV; } + + /* + * The first invocation validated the wdev's netns against + * the caller via __cfg80211_wdev_from_attrs(). The wiphy + * may have moved netns between dumpit invocations (via + * NL80211_CMD_SET_WIPHY_NETNS), so re-check here. + */ + if (!net_eq(wiphy_net(wiphy), sock_net(cb->skb->sk))) { + rtnl_unlock(); + return -ENODEV; + } + *rdev = wiphy_to_rdev(wiphy); *wdev = NULL; @@ -13867,6 +13879,19 @@ static int nl80211_wiphy_netns(struct sk_buff *skb, struct genl_info *info) if (IS_ERR(net)) return PTR_ERR(net); + /* + * The caller already has CAP_NET_ADMIN over the source netns + * (enforced by GENL_UNS_ADMIN_PERM on the genl op). Mirror the + * convention used by net/core/rtnetlink.c::rtnl_get_net_ns_capable() + * and require CAP_NET_ADMIN over the target netns as well, so that + * a caller that is privileged in their own user namespace cannot + * push a wiphy into a netns where they have no privilege. + */ + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) { + put_net(net); + return -EPERM; + } + err = 0; /* check if anything to do */ @@ -19828,6 +19853,7 @@ static const struct genl_small_ops nl80211_small_ops[] = { .cmd = NL80211_CMD_SET_PMK, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_set_pmk, + .flags = GENL_UNS_ADMIN_PERM, .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_CLEAR_SKB), }, @@ -19835,6 +19861,7 @@ static const struct genl_small_ops nl80211_small_ops[] = { .cmd = NL80211_CMD_DEL_PMK, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_del_pmk, + .flags = GENL_UNS_ADMIN_PERM, .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP), }, { diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c index 4c8ea0583f94..d6cd0de64d1f 100644 --- a/net/wireless/pmsr.c +++ b/net/wireless/pmsr.c @@ -88,7 +88,7 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev, out->ftm.ftms_per_burst = 0; if (tb[NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST]) out->ftm.ftms_per_burst = - nla_get_u32(tb[NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST]); + nla_get_u8(tb[NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST]); if (capa->ftm.max_ftms_per_burst && (out->ftm.ftms_per_burst > capa->ftm.max_ftms_per_burst || diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 887abed25466..5e5786cd9af5 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -646,9 +646,42 @@ static u64 xsk_skb_destructor_get_addr(struct sk_buff *skb) return (u64)((uintptr_t)skb_shinfo(skb)->destructor_arg & ~0x1UL); } -static void xsk_skb_destructor_set_addr(struct sk_buff *skb, u64 addr) +static struct xsk_addrs *__xsk_addrs_alloc(struct sk_buff *skb, u64 addr) { - skb_shinfo(skb)->destructor_arg = (void *)((uintptr_t)addr | 0x1UL); + struct xsk_addrs *xsk_addr; + + xsk_addr = kmem_cache_zalloc(xsk_tx_generic_cache, GFP_KERNEL); + if (unlikely(!xsk_addr)) + return NULL; + + xsk_addr->addrs[0] = addr; + skb_shinfo(skb)->destructor_arg = (void *)xsk_addr; + return xsk_addr; +} + +static struct xsk_addrs *xsk_addrs_alloc(struct sk_buff *skb) +{ + struct xsk_addrs *xsk_addr; + + if (!xsk_skb_destructor_is_addr(skb)) + return (struct xsk_addrs *)skb_shinfo(skb)->destructor_arg; + + xsk_addr = __xsk_addrs_alloc(skb, xsk_skb_destructor_get_addr(skb)); + if (likely(xsk_addr)) + xsk_addr->num_descs = 1; + return xsk_addr; +} + +static int xsk_skb_destructor_set_addr(struct sk_buff *skb, u64 addr) +{ + if (IS_ENABLED(CONFIG_64BIT)) { + skb_shinfo(skb)->destructor_arg = (void *)((uintptr_t)addr | 0x1UL); + return 0; + } + + if (unlikely(!__xsk_addrs_alloc(skb, addr))) + return -ENOMEM; + return 0; } static void xsk_inc_num_desc(struct sk_buff *skb) @@ -685,7 +718,7 @@ static void xsk_cq_submit_addr_locked(struct xsk_buff_pool *pool, spin_lock_irqsave(&pool->cq_prod_lock, flags); idx = xskq_get_prod(pool->cq); - if (unlikely(num_descs > 1)) { + if (unlikely(!xsk_skb_destructor_is_addr(skb))) { xsk_addr = (struct xsk_addrs *)skb_shinfo(skb)->destructor_arg; for (i = 0; i < num_descs; i++) { @@ -724,14 +757,20 @@ void xsk_destruct_skb(struct sk_buff *skb) sock_wfree(skb); } -static void xsk_skb_init_misc(struct sk_buff *skb, struct xdp_sock *xs, - u64 addr) +static int xsk_skb_init_misc(struct sk_buff *skb, struct xdp_sock *xs, + u64 addr) { + int err; + + err = xsk_skb_destructor_set_addr(skb, addr); + if (unlikely(err)) + return err; + skb->dev = xs->dev; skb->priority = READ_ONCE(xs->sk.sk_priority); skb->mark = READ_ONCE(xs->sk.sk_mark); skb->destructor = xsk_destruct_skb; - xsk_skb_destructor_set_addr(skb, addr); + return 0; } static void xsk_consume_skb(struct sk_buff *skb) @@ -740,7 +779,7 @@ static void xsk_consume_skb(struct sk_buff *skb) u32 num_descs = xsk_get_num_desc(skb); struct xsk_addrs *xsk_addr; - if (unlikely(num_descs > 1)) { + if (unlikely(!xsk_skb_destructor_is_addr(skb))) { xsk_addr = (struct xsk_addrs *)skb_shinfo(skb)->destructor_arg; kmem_cache_free(xsk_tx_generic_cache, xsk_addr); } @@ -819,28 +858,19 @@ static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs, return ERR_PTR(err); skb_reserve(skb, hr); - - xsk_skb_init_misc(skb, xs, desc->addr); if (desc->options & XDP_TX_METADATA) { err = xsk_skb_metadata(skb, buffer, desc, pool, hr); - if (unlikely(err)) + if (unlikely(err)) { + kfree_skb(skb); return ERR_PTR(err); + } } } else { struct xsk_addrs *xsk_addr; - if (xsk_skb_destructor_is_addr(skb)) { - xsk_addr = kmem_cache_zalloc(xsk_tx_generic_cache, - GFP_KERNEL); - if (!xsk_addr) - return ERR_PTR(-ENOMEM); - - xsk_addr->num_descs = 1; - xsk_addr->addrs[0] = xsk_skb_destructor_get_addr(skb); - skb_shinfo(skb)->destructor_arg = (void *)xsk_addr; - } else { - xsk_addr = (struct xsk_addrs *)skb_shinfo(skb)->destructor_arg; - } + xsk_addr = xsk_addrs_alloc(skb); + if (!xsk_addr) + return ERR_PTR(-ENOMEM); /* in case of -EOVERFLOW that could happen below, * xsk_consume_skb() will release this node as whole skb @@ -856,8 +886,11 @@ static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs, addr = buffer - pool->addrs; for (copied = 0, i = skb_shinfo(skb)->nr_frags; copied < len; i++) { - if (unlikely(i >= MAX_SKB_FRAGS)) + if (unlikely(i >= MAX_SKB_FRAGS)) { + if (!xs->skb) + kfree_skb(skb); return ERR_PTR(-EOVERFLOW); + } page = pool->umem->pgs[addr >> PAGE_SHIFT]; get_page(page); @@ -914,7 +947,6 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, if (unlikely(err)) goto free_err; - xsk_skb_init_misc(skb, xs, desc->addr); if (desc->options & XDP_TX_METADATA) { err = xsk_skb_metadata(skb, buffer, desc, xs->pool, hr); @@ -927,19 +959,10 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, struct page *page; u8 *vaddr; - if (xsk_skb_destructor_is_addr(skb)) { - xsk_addr = kmem_cache_zalloc(xsk_tx_generic_cache, - GFP_KERNEL); - if (!xsk_addr) { - err = -ENOMEM; - goto free_err; - } - - xsk_addr->num_descs = 1; - xsk_addr->addrs[0] = xsk_skb_destructor_get_addr(skb); - skb_shinfo(skb)->destructor_arg = (void *)xsk_addr; - } else { - xsk_addr = (struct xsk_addrs *)skb_shinfo(skb)->destructor_arg; + xsk_addr = xsk_addrs_alloc(skb); + if (!xsk_addr) { + err = -ENOMEM; + goto free_err; } if (unlikely(nr_frags == (MAX_SKB_FRAGS - 1) && xp_mb_desc(desc))) { @@ -964,18 +987,28 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, } } + if (!xs->skb) { + err = xsk_skb_init_misc(skb, xs, desc->addr); + if (unlikely(err)) + goto free_err; + } xsk_inc_num_desc(skb); return skb; free_err: - if (skb && !skb_shinfo(skb)->nr_frags) + if (skb && !xs->skb) kfree_skb(skb); if (err == -EOVERFLOW) { - /* Drop the packet */ - xsk_inc_num_desc(xs->skb); - xsk_drop_skb(xs->skb); + if (xs->skb) { + /* Drop the packet */ + xsk_inc_num_desc(xs->skb); + xsk_drop_skb(xs->skb); + } else { + xsk_cq_cancel_locked(xs->pool, 1); + xs->tx->invalid_descs++; + } xskq_cons_release(xs->tx); } else { /* Let application retry */ diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index cd7bc50872f6..d981cfdd8535 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -175,6 +175,9 @@ int xp_assign_dev(struct xsk_buff_pool *pool, if (force_zc && force_copy) return -EINVAL; + if (pool->tx_sw_csum && (netdev->priv_flags & IFF_TX_SKB_NO_LINEAR)) + return -EOPNOTSUPP; + if (xsk_get_pool_from_qid(netdev, queue_id)) return -EBUSY; diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index a9652b422f51..cc35c2fcbbe0 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -66,7 +66,9 @@ static int xfrm4_transport_output(struct xfrm_state *x, struct sk_buff *skb) struct iphdr *iph = ip_hdr(skb); int ihl = iph->ihl * 4; - skb_set_inner_transport_header(skb, skb_transport_offset(skb)); + if (!skb->inner_protocol) + skb_set_inner_transport_header(skb, + skb_transport_offset(skb)); skb_set_network_header(skb, -x->props.header_len); skb->mac_header = skb->network_header + @@ -167,7 +169,9 @@ static int xfrm6_transport_output(struct xfrm_state *x, struct sk_buff *skb) int hdr_len; iph = ipv6_hdr(skb); - skb_set_inner_transport_header(skb, skb_transport_offset(skb)); + if (!skb->inner_protocol) + skb_set_inner_transport_header(skb, + skb_transport_offset(skb)); hdr_len = xfrm6_hdr_offset(x, skb, &prevhdr); if (hdr_len < 0) @@ -276,8 +280,10 @@ static int xfrm4_tunnel_encap_add(struct xfrm_state *x, struct sk_buff *skb) struct iphdr *top_iph; int flags; - skb_set_inner_network_header(skb, skb_network_offset(skb)); - skb_set_inner_transport_header(skb, skb_transport_offset(skb)); + if (!skb->inner_protocol) { + skb_set_inner_network_header(skb, skb_network_offset(skb)); + skb_set_inner_transport_header(skb, skb_transport_offset(skb)); + } skb_set_network_header(skb, -x->props.header_len); skb->mac_header = skb->network_header + @@ -321,8 +327,10 @@ static int xfrm6_tunnel_encap_add(struct xfrm_state *x, struct sk_buff *skb) struct ipv6hdr *top_iph; int dsfield; - skb_set_inner_network_header(skb, skb_network_offset(skb)); - skb_set_inner_transport_header(skb, skb_transport_offset(skb)); + if (!skb->inner_protocol) { + skb_set_inner_network_header(skb, skb_network_offset(skb)); + skb_set_inner_transport_header(skb, skb_transport_offset(skb)); + } skb_set_network_header(skb, -x->props.header_len); skb->mac_header = skb->network_header + diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 1748d374abca..686014d39429 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -818,17 +818,17 @@ int __xfrm_state_delete(struct xfrm_state *x) spin_lock(&net->xfrm.xfrm_state_lock); list_del(&x->km.all); - hlist_del_rcu(&x->bydst); - hlist_del_rcu(&x->bysrc); - if (x->km.seq) - hlist_del_rcu(&x->byseq); + hlist_del_init_rcu(&x->bydst); + hlist_del_init_rcu(&x->bysrc); + if (!hlist_unhashed(&x->byseq)) + hlist_del_init_rcu(&x->byseq); if (!hlist_unhashed(&x->state_cache)) hlist_del_rcu(&x->state_cache); if (!hlist_unhashed(&x->state_cache_input)) hlist_del_rcu(&x->state_cache_input); - if (x->id.spi) - hlist_del_rcu(&x->byspi); + if (!hlist_unhashed(&x->byspi)) + hlist_del_init_rcu(&x->byspi); net->xfrm.state_num--; xfrm_nat_keepalive_state_updated(x); spin_unlock(&net->xfrm.xfrm_state_lock); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index d56450f61669..38a90e5ee3d9 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -3323,6 +3323,7 @@ const int xfrm_msg_min[XFRM_NR_MSGTYPES] = { [XFRM_MSG_GETSADINFO - XFRM_MSG_BASE] = sizeof(u32), [XFRM_MSG_NEWSPDINFO - XFRM_MSG_BASE] = sizeof(u32), [XFRM_MSG_GETSPDINFO - XFRM_MSG_BASE] = sizeof(u32), + [XFRM_MSG_MAPPING - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_mapping), [XFRM_MSG_SETDEFAULT - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_default), [XFRM_MSG_GETDEFAULT - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_default), }; diff --git a/rust/kernel/drm/device.rs b/rust/kernel/drm/device.rs index adbafe8db54d..403fc35353c7 100644 --- a/rust/kernel/drm/device.rs +++ b/rust/kernel/drm/device.rs @@ -119,13 +119,20 @@ impl<T: drm::Driver> Device<T> { // compatible `Layout`. let layout = Kmalloc::aligned_layout(Layout::new::<Self>()); + // Use a temporary vtable without a `release` callback until `data` is initialized, so + // init failure can release the DRM device without dropping uninitialized fields. + let alloc_vtable = bindings::drm_driver { + release: None, + ..Self::VTABLE + }; + // SAFETY: - // - `VTABLE`, as a `const` is pinned to the read-only section of the compilation, + // - `alloc_vtable` reference remains valid until no longer used, // - `dev` is valid by its type invarants, let raw_drm: *mut Self = unsafe { bindings::__drm_dev_alloc( dev.as_raw(), - &Self::VTABLE, + &alloc_vtable, layout.size(), mem::offset_of!(Self, dev), ) @@ -133,6 +140,10 @@ impl<T: drm::Driver> Device<T> { .cast(); let raw_drm = NonNull::new(from_err_ptr(raw_drm)?).ok_or(ENOMEM)?; + // SAFETY: `raw_drm` is a valid pointer to `Self`, given that `__drm_dev_alloc` was + // successful. + let drm_dev = unsafe { Self::into_drm_device(raw_drm) }; + // SAFETY: `raw_drm` is a valid pointer to `Self`. let raw_data = unsafe { ptr::addr_of_mut!((*raw_drm.as_ptr()).data) }; @@ -140,15 +151,14 @@ impl<T: drm::Driver> Device<T> { // - `raw_data` is a valid pointer to uninitialized memory. // - `raw_data` will not move until it is dropped. unsafe { data.__pinned_init(raw_data) }.inspect_err(|_| { - // SAFETY: `raw_drm` is a valid pointer to `Self`, given that `__drm_dev_alloc` was - // successful. - let drm_dev = unsafe { Self::into_drm_device(raw_drm) }; - // SAFETY: `__drm_dev_alloc()` was successful, hence `drm_dev` must be valid and the // refcount must be non-zero. unsafe { bindings::drm_dev_put(drm_dev) }; })?; + // SAFETY: `drm_dev` is still private to this function. + unsafe { (*drm_dev).driver = const { &Self::VTABLE } }; + // SAFETY: The reference count is one, and now we take ownership of that reference as a // `drm::Device`. Ok(unsafe { ARef::from_raw(raw_drm) }) diff --git a/rust/kernel/drm/gem/mod.rs b/rust/kernel/drm/gem/mod.rs index 75acda7ba500..01b5bd47a333 100644 --- a/rust/kernel/drm/gem/mod.rs +++ b/rust/kernel/drm/gem/mod.rs @@ -277,8 +277,17 @@ impl<T: DriverObject> Object<T> { // SAFETY: `obj.as_raw()` is guaranteed to be valid by the initialization above. unsafe { (*obj.as_raw()).funcs = &Self::OBJECT_FUNCS }; - // SAFETY: The arguments are all valid per the type invariants. - to_result(unsafe { bindings::drm_gem_object_init(dev.as_raw(), obj.obj.get(), size) })?; + if let Err(err) = + // SAFETY: The arguments are all valid per the type invariants. + to_result(unsafe { + bindings::drm_gem_object_init(dev.as_raw(), obj.obj.get(), size) + }) + { + // SAFETY: `drm_gem_object_init()` initializes the private GEM object state before + // failing, so `drm_gem_private_object_fini()` is the matching cleanup. + unsafe { bindings::drm_gem_private_object_fini(obj.obj.get()) }; + return Err(err); + } // SAFETY: We will never move out of `Self` as `ARef<Self>` is always treated as pinned. let ptr = KBox::into_raw(unsafe { Pin::into_inner_unchecked(obj) }); diff --git a/rust/kernel/drm/gem/shmem.rs b/rust/kernel/drm/gem/shmem.rs index d025fb035195..e1b648920d2f 100644 --- a/rust/kernel/drm/gem/shmem.rs +++ b/rust/kernel/drm/gem/shmem.rs @@ -19,10 +19,8 @@ use crate::{ }, error::to_result, prelude::*, - types::{ - ARef, - Opaque, // - }, // + sync::aref::ARef, + types::Opaque, // }; use core::{ ops::{ diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 97801966bf32..0f704380a8c8 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -2966,7 +2966,7 @@ static int selinux_inode_init_security(struct inode *inode, struct inode *dir, { const struct cred_security_struct *crsec = selinux_cred(current_cred()); struct superblock_security_struct *sbsec; - struct xattr *xattr = lsm_get_xattr_slot(xattrs, xattr_count); + struct xattr *xattr; u32 newsid, clen; u16 newsclass; int rc; @@ -2992,6 +2992,7 @@ static int selinux_inode_init_security(struct inode *inode, struct inode *dir, !(sbsec->flags & SBLABEL_MNT)) return -EOPNOTSUPP; + xattr = lsm_get_xattr_slot(xattrs, xattr_count); if (xattr) { rc = security_sid_to_context_force(newsid, &context, &clen); @@ -3208,15 +3209,13 @@ static inline int task_avdcache_search(struct task_security_struct *tsec, * @tsec: the task's security state * @isec: the inode associated with the cache entry * @avd: the AVD to cache - * @audited: the permission audit bitmask to cache * - * Update the AVD cache in @tsec with the @avdc and @audited info associated + * Update the AVD cache in @tsec with the @avd info associated * with @isec. */ static inline void task_avdcache_update(struct task_security_struct *tsec, struct inode_security_struct *isec, - struct av_decision *avd, - u32 audited) + struct av_decision *avd) { int spot; @@ -3228,9 +3227,7 @@ static inline void task_avdcache_update(struct task_security_struct *tsec, spot = (tsec->avdcache.dir_spot + 1) & (TSEC_AVDC_DIR_SIZE - 1); tsec->avdcache.dir_spot = spot; tsec->avdcache.dir[spot].isid = isec->sid; - tsec->avdcache.dir[spot].audited = audited; - tsec->avdcache.dir[spot].allowed = avd->allowed; - tsec->avdcache.dir[spot].permissive = avd->flags & AVD_FLAGS_PERMISSIVE; + tsec->avdcache.dir[spot].avd = *avd; tsec->avdcache.permissive_neveraudit = (avd->flags == (AVD_FLAGS_PERMISSIVE|AVD_FLAGS_NEVERAUDIT)); } @@ -3251,6 +3248,7 @@ static int selinux_inode_permission(struct inode *inode, int requested) struct task_security_struct *tsec; struct inode_security_struct *isec; struct avdc_entry *avdc; + struct av_decision avd, *avdp = &avd; int rc, rc2; u32 audited, denied; @@ -3272,23 +3270,21 @@ static int selinux_inode_permission(struct inode *inode, int requested) rc = task_avdcache_search(tsec, isec, &avdc); if (likely(!rc)) { /* Cache hit. */ - audited = perms & avdc->audited; - denied = perms & ~avdc->allowed; - if (unlikely(denied && enforcing_enabled() && - !avdc->permissive)) + avdp = &avdc->avd; + denied = perms & ~avdp->allowed; + if (unlikely(denied) && enforcing_enabled() && + !(avdp->flags & AVD_FLAGS_PERMISSIVE)) rc = -EACCES; } else { - struct av_decision avd; - /* Cache miss. */ rc = avc_has_perm_noaudit(sid, isec->sid, isec->sclass, - perms, 0, &avd); - audited = avc_audit_required(perms, &avd, rc, - (requested & MAY_ACCESS) ? FILE__AUDIT_ACCESS : 0, - &denied); - task_avdcache_update(tsec, isec, &avd, audited); + perms, 0, avdp); + task_avdcache_update(tsec, isec, avdp); } + audited = avc_audit_required(perms, avdp, rc, + (requested & MAY_ACCESS) ? + FILE__AUDIT_ACCESS : 0, &denied); if (likely(!audited)) return rc; @@ -4920,7 +4916,7 @@ static bool sock_skip_has_perm(u32 sid) static int sock_has_perm(struct sock *sk, u32 perms) { - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); struct common_audit_data ad; struct lsm_network_audit net; @@ -6227,7 +6223,7 @@ static unsigned int selinux_ip_postroute(void *priv, static int nlmsg_sock_has_extended_perms(struct sock *sk, u32 perms, u16 nlmsg_type) { - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); struct common_audit_data ad; u8 driver; u8 xperm; diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h index b19e5d978e82..3c0a16ec978b 100644 --- a/security/selinux/include/objsec.h +++ b/security/selinux/include/objsec.h @@ -32,9 +32,7 @@ struct avdc_entry { u32 isid; /* inode SID */ - u32 allowed; /* allowed permission bitmask */ - u32 audited; /* audited permission bitmask */ - bool permissive; /* AVC permissive flag */ + struct av_decision avd; /* av decision */ }; struct cred_security_struct { diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h index d1f16d7f684d..0babb8992181 100644 --- a/security/selinux/include/security.h +++ b/security/selinux/include/security.h @@ -312,8 +312,6 @@ int security_context_to_sid_default(const char *scontext, u32 scontext_len, int security_context_to_sid_force(const char *scontext, u32 scontext_len, u32 *sid); -int security_get_user_sids(u32 fromsid, const char *username, u32 **sids, u32 *nel); - int security_port_sid(u8 protocol, u16 port, u32 *out_sid); int security_ib_pkey_sid(u64 subnet_prefix, u16 pkey_num, u32 *out_sid); diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index 83aa765a09f9..25ca7d714014 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -76,7 +76,6 @@ struct selinux_fs_info { int *bool_pending_values; struct dentry *class_dir; unsigned long last_class_ino; - bool policy_opened; unsigned long last_ino; struct super_block *sb; }; @@ -272,35 +271,13 @@ static ssize_t sel_write_disable(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - char *page; - ssize_t length; - int new_value; - - if (count >= PAGE_SIZE) - return -ENOMEM; - - /* No partial writes. */ - if (*ppos != 0) - return -EINVAL; - - page = memdup_user_nul(buf, count); - if (IS_ERR(page)) - return PTR_ERR(page); - - if (sscanf(page, "%d", &new_value) != 1) { - length = -EINVAL; - goto out; - } - length = count; - - if (new_value) { - pr_err("SELinux: https://github.com/SELinuxProject/selinux-kernel/wiki/DEPRECATE-runtime-disable\n"); - pr_err("SELinux: Runtime disable is not supported, use selinux=0 on the kernel cmdline.\n"); - } - -out: - kfree(page); - return length; + /* + * Setting disable is no longer supported, see + * https://github.com/SELinuxProject/selinux-kernel/wiki/DEPRECATE-runtime-disable + */ + pr_err_once("SELinux: %s (%d) wrote to disable. This is no longer supported.\n", + current->comm, current->pid); + return count; } static const struct file_operations sel_disable_ops = { @@ -362,44 +339,31 @@ struct policy_load_memory { static int sel_open_policy(struct inode *inode, struct file *filp) { - struct selinux_fs_info *fsi = inode->i_sb->s_fs_info; struct policy_load_memory *plm = NULL; int rc; - BUG_ON(filp->private_data); - - mutex_lock(&selinux_state.policy_mutex); - rc = avc_has_perm(current_sid(), SECINITSID_SECURITY, SECCLASS_SECURITY, SECURITY__READ_POLICY, NULL); if (rc) - goto err; - - rc = -EBUSY; - if (fsi->policy_opened) - goto err; + return rc; - rc = -ENOMEM; plm = kzalloc_obj(*plm); if (!plm) - goto err; + return -ENOMEM; + mutex_lock(&selinux_state.policy_mutex); rc = security_read_policy(&plm->data, &plm->len); if (rc) goto err; - if ((size_t)i_size_read(inode) != plm->len) { inode_lock(inode); i_size_write(inode, plm->len); inode_unlock(inode); } - - fsi->policy_opened = 1; + mutex_unlock(&selinux_state.policy_mutex); filp->private_data = plm; - mutex_unlock(&selinux_state.policy_mutex); - return 0; err: mutex_unlock(&selinux_state.policy_mutex); @@ -412,13 +376,8 @@ err: static int sel_release_policy(struct inode *inode, struct file *filp) { - struct selinux_fs_info *fsi = inode->i_sb->s_fs_info; struct policy_load_memory *plm = filp->private_data; - BUG_ON(!plm); - - fsi->policy_opened = 0; - vfree(plm->data); kfree(plm); @@ -594,34 +553,31 @@ static ssize_t sel_write_load(struct file *file, const char __user *buf, if (!count) return -EINVAL; - mutex_lock(&selinux_state.policy_mutex); - length = avc_has_perm(current_sid(), SECINITSID_SECURITY, SECCLASS_SECURITY, SECURITY__LOAD_POLICY, NULL); if (length) - goto out; + return length; data = vmalloc(count); - if (!data) { - length = -ENOMEM; - goto out; - } + if (!data) + return -ENOMEM; if (copy_from_user(data, buf, count) != 0) { length = -EFAULT; goto out; } + mutex_lock(&selinux_state.policy_mutex); length = security_load_policy(data, count, &load_state); if (length) { pr_warn_ratelimited("SELinux: failed to load policy\n"); - goto out; + goto out_unlock; } fsi = file_inode(file)->i_sb->s_fs_info; length = sel_make_policy_nodes(fsi, load_state.policy); if (length) { pr_warn_ratelimited("SELinux: failed to initialize selinuxfs\n"); selinux_policy_cancel(&load_state); - goto out; + goto out_unlock; } selinux_policy_commit(&load_state); @@ -631,8 +587,9 @@ static ssize_t sel_write_load(struct file *file, const char __user *buf, from_kuid(&init_user_ns, audit_get_loginuid(current)), audit_get_sessionid(current)); -out: +out_unlock: mutex_unlock(&selinux_state.policy_mutex); +out: vfree(data); return length; } @@ -689,46 +646,13 @@ static ssize_t sel_read_checkreqprot(struct file *filp, char __user *buf, static ssize_t sel_write_checkreqprot(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - char *page; - ssize_t length; - unsigned int new_value; - - length = avc_has_perm(current_sid(), SECINITSID_SECURITY, - SECCLASS_SECURITY, SECURITY__SETCHECKREQPROT, - NULL); - if (length) - return length; - - if (count >= PAGE_SIZE) - return -ENOMEM; - - /* No partial writes. */ - if (*ppos != 0) - return -EINVAL; - - page = memdup_user_nul(buf, count); - if (IS_ERR(page)) - return PTR_ERR(page); - - if (sscanf(page, "%u", &new_value) != 1) { - length = -EINVAL; - goto out; - } - length = count; - - if (new_value) { - char comm[sizeof(current->comm)]; - - strscpy(comm, current->comm); - pr_err("SELinux: %s (%d) set checkreqprot to 1. This is no longer supported.\n", - comm, current->pid); - } - - selinux_ima_measure_state(); - -out: - kfree(page); - return length; + /* + * Setting checkreqprot is no longer supported, see + * https://github.com/SELinuxProject/selinux-kernel/wiki/DEPRECATE-checkreqprot + */ + pr_err_once("SELinux: %s (%d) wrote to checkreqprot. This is no longer supported.\n", + current->comm, current->pid); + return count; } static const struct file_operations sel_checkreqprot_ops = { .read = sel_read_checkreqprot, @@ -1073,69 +997,11 @@ out: static ssize_t sel_write_user(struct file *file, char *buf, size_t size) { - char *con = NULL, *user = NULL, *ptr; - u32 sid, *sids = NULL; - ssize_t length; - char *newcon; - int rc; - u32 i, len, nsids; - - pr_warn_ratelimited("SELinux: %s (%d) wrote to /sys/fs/selinux/user!" - " This will not be supported in the future; please update your" - " userspace.\n", current->comm, current->pid); - ssleep(5); - - length = avc_has_perm(current_sid(), SECINITSID_SECURITY, - SECCLASS_SECURITY, SECURITY__COMPUTE_USER, - NULL); - if (length) - goto out; - - length = -ENOMEM; - con = kzalloc(size + 1, GFP_KERNEL); - if (!con) - goto out; - - length = -ENOMEM; - user = kzalloc(size + 1, GFP_KERNEL); - if (!user) - goto out; - - length = -EINVAL; - if (sscanf(buf, "%s %s", con, user) != 2) - goto out; - - length = security_context_str_to_sid(con, &sid, GFP_KERNEL); - if (length) - goto out; - - length = security_get_user_sids(sid, user, &sids, &nsids); - if (length) - goto out; - - length = sprintf(buf, "%u", nsids) + 1; - ptr = buf + length; - for (i = 0; i < nsids; i++) { - rc = security_sid_to_context(sids[i], &newcon, &len); - if (rc) { - length = rc; - goto out; - } - if ((length + len) >= SIMPLE_TRANSACTION_LIMIT) { - kfree(newcon); - length = -ERANGE; - goto out; - } - memcpy(ptr, newcon, len); - kfree(newcon); - ptr += len; - length += len; - } -out: - kfree(sids); - kfree(user); - kfree(con); - return length; + pr_err_once("SELinux: %s (%d) wrote to user. This is no longer supported.\n", + current->comm, current->pid); + buf[0] = '0'; + buf[1] = 0; + return 2; } static ssize_t sel_write_member(struct file *file, char *buf, size_t size) diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c index e8e7ccbd1e44..143021c5e326 100644 --- a/security/selinux/ss/services.c +++ b/security/selinux/ss/services.c @@ -2746,131 +2746,6 @@ out: return rc; } -#define SIDS_NEL 25 - -/** - * security_get_user_sids - Obtain reachable SIDs for a user. - * @fromsid: starting SID - * @username: username - * @sids: array of reachable SIDs for user - * @nel: number of elements in @sids - * - * Generate the set of SIDs for legal security contexts - * for a given user that can be reached by @fromsid. - * Set *@sids to point to a dynamically allocated - * array containing the set of SIDs. Set *@nel to the - * number of elements in the array. - */ - -int security_get_user_sids(u32 fromsid, - const char *username, - u32 **sids, - u32 *nel) -{ - struct selinux_policy *policy; - struct policydb *policydb; - struct sidtab *sidtab; - struct context *fromcon, usercon; - u32 *mysids = NULL, *mysids2, sid; - u32 i, j, mynel, maxnel = SIDS_NEL; - struct user_datum *user; - struct role_datum *role; - struct ebitmap_node *rnode, *tnode; - int rc; - - *sids = NULL; - *nel = 0; - - if (!selinux_initialized()) - return 0; - - mysids = kcalloc(maxnel, sizeof(*mysids), GFP_KERNEL); - if (!mysids) - return -ENOMEM; - -retry: - mynel = 0; - rcu_read_lock(); - policy = rcu_dereference(selinux_state.policy); - policydb = &policy->policydb; - sidtab = policy->sidtab; - - context_init(&usercon); - - rc = -EINVAL; - fromcon = sidtab_search(sidtab, fromsid); - if (!fromcon) - goto out_unlock; - - rc = -EINVAL; - user = symtab_search(&policydb->p_users, username); - if (!user) - goto out_unlock; - - usercon.user = user->value; - - ebitmap_for_each_positive_bit(&user->roles, rnode, i) { - role = policydb->role_val_to_struct[i]; - usercon.role = i + 1; - ebitmap_for_each_positive_bit(&role->types, tnode, j) { - usercon.type = j + 1; - - if (mls_setup_user_range(policydb, fromcon, user, - &usercon)) - continue; - - rc = sidtab_context_to_sid(sidtab, &usercon, &sid); - if (rc == -ESTALE) { - rcu_read_unlock(); - goto retry; - } - if (rc) - goto out_unlock; - if (mynel < maxnel) { - mysids[mynel++] = sid; - } else { - rc = -ENOMEM; - maxnel += SIDS_NEL; - mysids2 = kcalloc(maxnel, sizeof(*mysids2), GFP_ATOMIC); - if (!mysids2) - goto out_unlock; - memcpy(mysids2, mysids, mynel * sizeof(*mysids2)); - kfree(mysids); - mysids = mysids2; - mysids[mynel++] = sid; - } - } - } - rc = 0; -out_unlock: - rcu_read_unlock(); - if (rc || !mynel) { - kfree(mysids); - return rc; - } - - rc = -ENOMEM; - mysids2 = kcalloc(mynel, sizeof(*mysids2), GFP_KERNEL); - if (!mysids2) { - kfree(mysids); - return rc; - } - for (i = 0, j = 0; i < mynel; i++) { - struct av_decision dummy_avd; - rc = avc_has_perm_noaudit(fromsid, mysids[i], - SECCLASS_PROCESS, /* kernel value */ - PROCESS__TRANSITION, AVC_STRICT, - &dummy_avd); - if (!rc) - mysids2[j++] = mysids[i]; - cond_resched(); - } - kfree(mysids); - *sids = mysids2; - *nel = j; - return 0; -} - /** * __security_genfs_sid - Helper to obtain a SID for a file in a filesystem * @policy: policy diff --git a/sound/core/misc.c b/sound/core/misc.c index 5aca09edf971..833124c8e4fa 100644 --- a/sound/core/misc.c +++ b/sound/core/misc.c @@ -148,9 +148,11 @@ EXPORT_SYMBOL_GPL(snd_fasync_helper); void snd_kill_fasync(struct snd_fasync *fasync, int signal, int poll) { - if (!fasync || !fasync->on) + if (!fasync) return; guard(spinlock_irqsave)(&snd_fasync_lock); + if (!fasync->on) + return; fasync->signal = signal; fasync->poll = poll; list_move(&fasync->list, &snd_fasync_list); @@ -163,8 +165,10 @@ void snd_fasync_free(struct snd_fasync *fasync) if (!fasync) return; - scoped_guard(spinlock_irq, &snd_fasync_lock) + scoped_guard(spinlock_irq, &snd_fasync_lock) { + fasync->on = 0; list_del_init(&fasync->list); + } flush_work(&snd_fasync_work); kfree(fasync); diff --git a/sound/core/oss/pcm_oss.c b/sound/core/oss/pcm_oss.c index a140a0d9abb8..33fd34f0d615 100644 --- a/sound/core/oss/pcm_oss.c +++ b/sound/core/oss/pcm_oss.c @@ -2155,10 +2155,16 @@ static int snd_pcm_oss_get_trigger(struct snd_pcm_oss_file *pcm_oss_file) psubstream = pcm_oss_file->streams[SNDRV_PCM_STREAM_PLAYBACK]; csubstream = pcm_oss_file->streams[SNDRV_PCM_STREAM_CAPTURE]; - if (psubstream && psubstream->runtime && psubstream->runtime->oss.trigger) - result |= PCM_ENABLE_OUTPUT; - if (csubstream && csubstream->runtime && csubstream->runtime->oss.trigger) - result |= PCM_ENABLE_INPUT; + if (psubstream && psubstream->runtime) { + guard(mutex)(&psubstream->runtime->oss.params_lock); + if (psubstream->runtime->oss.trigger) + result |= PCM_ENABLE_OUTPUT; + } + if (csubstream && csubstream->runtime) { + guard(mutex)(&csubstream->runtime->oss.params_lock); + if (csubstream->runtime->oss.trigger) + result |= PCM_ENABLE_INPUT; + } return result; } @@ -2832,6 +2838,17 @@ static int snd_pcm_oss_capture_ready(struct snd_pcm_substream *substream) runtime->oss.period_frames; } +static bool need_input_retrigger(struct snd_pcm_runtime *runtime) +{ + bool ret; + + guard(mutex)(&runtime->oss.params_lock); + ret = runtime->oss.trigger; + if (ret) + runtime->oss.trigger = 0; + return ret; +} + static __poll_t snd_pcm_oss_poll(struct file *file, poll_table * wait) { struct snd_pcm_oss_file *pcm_oss_file; @@ -2864,11 +2881,11 @@ static __poll_t snd_pcm_oss_poll(struct file *file, poll_table * wait) snd_pcm_oss_capture_ready(csubstream)) mask |= EPOLLIN | EPOLLRDNORM; } - if (ostate != SNDRV_PCM_STATE_RUNNING && runtime->oss.trigger) { + if (ostate != SNDRV_PCM_STATE_RUNNING && + need_input_retrigger(runtime)) { struct snd_pcm_oss_file ofile; memset(&ofile, 0, sizeof(ofile)); ofile.streams[SNDRV_PCM_STREAM_CAPTURE] = pcm_oss_file->streams[SNDRV_PCM_STREAM_CAPTURE]; - runtime->oss.trigger = 0; snd_pcm_oss_set_trigger(&ofile, PCM_ENABLE_INPUT); } } diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 75a7a2af9d8c..5719637575a9 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -1253,7 +1253,7 @@ static int snd_seq_ioctl_set_client_info(struct snd_seq_client *client, if (client->user_pversion >= SNDRV_PROTOCOL_VERSION(1, 0, 3)) client->midi_version = client_info->midi_version; memcpy(client->event_filter, client_info->event_filter, 32); - client->group_filter = client_info->group_filter; + client->group_filter = client_info->group_filter & SND_SEQ_GROUP_FILTER_MASK; /* notify the change */ snd_seq_system_client_ev_client_change(client->number); diff --git a/sound/core/seq/seq_clientmgr.h b/sound/core/seq/seq_clientmgr.h index ece02c58db70..feea8bb7d987 100644 --- a/sound/core/seq/seq_clientmgr.h +++ b/sound/core/seq/seq_clientmgr.h @@ -14,6 +14,9 @@ /* client manager */ +#define SND_SEQ_GROUP_FILTER_MASK GENMASK(SNDRV_UMP_MAX_GROUPS, 0) +#define SND_SEQ_GROUP_FILTER_GROUPS GENMASK(SNDRV_UMP_MAX_GROUPS, 1) + struct snd_seq_user_client { struct file *file; /* file struct of client */ /* ... */ @@ -40,7 +43,7 @@ struct snd_seq_client { int number; /* client number */ unsigned int filter; /* filter flags */ DECLARE_BITMAP(event_filter, 256); - unsigned short group_filter; + unsigned int group_filter; snd_use_lock_t use_lock; int event_lost; /* ports */ diff --git a/sound/core/seq/seq_ump_client.c b/sound/core/seq/seq_ump_client.c index fdc76f23e03f..9079ccfdc866 100644 --- a/sound/core/seq/seq_ump_client.c +++ b/sound/core/seq/seq_ump_client.c @@ -369,7 +369,7 @@ static void setup_client_group_filter(struct seq_ump_client *client) cptr = snd_seq_kernel_client_get(client->seq_client); if (!cptr) return; - filter = ~(1U << 0); /* always allow groupless messages */ + filter = SND_SEQ_GROUP_FILTER_GROUPS; /* always allow groupless messages */ for (p = 0; p < SNDRV_UMP_MAX_GROUPS; p++) { if (client->ump->groups[p].active) filter &= ~(1U << (p + 1)); diff --git a/sound/drivers/aloop.c b/sound/drivers/aloop.c index aa0d2fcb1a18..a37a1695f51c 100644 --- a/sound/drivers/aloop.c +++ b/sound/drivers/aloop.c @@ -99,6 +99,9 @@ struct loopback_ops { struct loopback_cable { spinlock_t lock; struct loopback_pcm *streams[2]; + /* in-flight peer stops running outside cable->lock */ + atomic_t stop_count; + wait_queue_head_t stop_wait; struct snd_pcm_hardware hw; /* flags */ unsigned int valid; @@ -366,8 +369,11 @@ static int loopback_check_format(struct loopback_cable *cable, int stream) return 0; if (stream == SNDRV_PCM_STREAM_CAPTURE) return -EIO; - else if (cruntime->state == SNDRV_PCM_STATE_RUNNING) + else if (cruntime->state == SNDRV_PCM_STATE_RUNNING) { + /* close must not free the peer runtime below */ + atomic_inc(&cable->stop_count); stop_capture = true; + } } setup = get_setup(dpcm_play); @@ -396,8 +402,11 @@ static int loopback_check_format(struct loopback_cable *cable, int stream) } } - if (stop_capture) + if (stop_capture) { snd_pcm_stop(dpcm_capt->substream, SNDRV_PCM_STATE_DRAINING); + if (atomic_dec_and_test(&cable->stop_count)) + wake_up(&cable->stop_wait); + } return 0; } @@ -1049,23 +1058,29 @@ static void free_cable(struct snd_pcm_substream *substream) struct loopback *loopback = substream->private_data; int dev = get_cable_index(substream); struct loopback_cable *cable; + struct loopback_pcm *dpcm; + bool other_alive; cable = loopback->cables[substream->number][dev]; if (!cable) return; - if (cable->streams[!substream->stream]) { - /* other stream is still alive */ - guard(spinlock_irq)(&cable->lock); - cable->streams[substream->stream] = NULL; - } else { - struct loopback_pcm *dpcm = substream->runtime->private_data; - if (cable->ops && cable->ops->close_cable && dpcm) - cable->ops->close_cable(dpcm); - /* free the cable */ - loopback->cables[substream->number][dev] = NULL; - kfree(cable); + scoped_guard(spinlock_irq, &cable->lock) { + cable->streams[substream->stream] = NULL; + other_alive = cable->streams[!substream->stream]; } + + /* Pair with the stop_count increment in loopback_check_format(). */ + wait_event(cable->stop_wait, !atomic_read(&cable->stop_count)); + if (other_alive) + return; + + dpcm = substream->runtime->private_data; + if (cable->ops && cable->ops->close_cable && dpcm) + cable->ops->close_cable(dpcm); + /* free the cable */ + loopback->cables[substream->number][dev] = NULL; + kfree(cable); } static int loopback_jiffies_timer_open(struct loopback_pcm *dpcm) @@ -1260,6 +1275,8 @@ static int loopback_open(struct snd_pcm_substream *substream) goto unlock; } spin_lock_init(&cable->lock); + atomic_set(&cable->stop_count, 0); + init_waitqueue_head(&cable->stop_wait); cable->hw = loopback_pcm_hardware; if (loopback->timer_source) cable->ops = &loopback_snd_timer_ops; diff --git a/sound/drivers/pcmtest.c b/sound/drivers/pcmtest.c index 5bfec4c7bf71..7f93557b51ec 100644 --- a/sound/drivers/pcmtest.c +++ b/sound/drivers/pcmtest.c @@ -679,9 +679,9 @@ static ssize_t pattern_read(struct file *file, char __user *u_buff, size_t len, return 0; if (copy_to_user(u_buff, patt_buf->buf + *off, to_read)) - to_read = 0; - else - *off += to_read; + return -EFAULT; + + *off += to_read; return to_read; } diff --git a/sound/firewire/tascam/tascam-hwdep.c b/sound/firewire/tascam/tascam-hwdep.c index 867b4ea1096e..6270263e7bf4 100644 --- a/sound/firewire/tascam/tascam-hwdep.c +++ b/sound/firewire/tascam/tascam-hwdep.c @@ -73,6 +73,7 @@ static long tscm_hwdep_read_queue(struct snd_tscm *tscm, char __user *buf, length = rounddown(remained, sizeof(*entries)); if (length == 0) break; + tail_pos = head_pos + length / sizeof(*entries); spin_unlock_irq(&tscm->lock); if (copy_to_user(pos, &entries[head_pos], length)) diff --git a/sound/hda/codecs/Makefile b/sound/hda/codecs/Makefile index e7f03e281999..88d2f8a79467 100644 --- a/sound/hda/codecs/Makefile +++ b/sound/hda/codecs/Makefile @@ -7,7 +7,6 @@ snd-hda-codec-cm9825-y := cm9825.o snd-hda-codec-analog-y := analog.o snd-hda-codec-ca0110-y := ca0110.o snd-hda-codec-ca0132-y := ca0132.o -snd-hda-codec-cmedia-y := cmedia.o snd-hda-codec-conexant-y := conexant.o snd-hda-codec-idt-y := sigmatel.o snd-hda-codec-senarytech-y := senarytech.o @@ -26,7 +25,6 @@ obj-$(CONFIG_SND_HDA_CODEC_CM9825) += snd-hda-codec-cm9825.o obj-$(CONFIG_SND_HDA_CODEC_ANALOG) += snd-hda-codec-analog.o obj-$(CONFIG_SND_HDA_CODEC_CA0110) += snd-hda-codec-ca0110.o obj-$(CONFIG_SND_HDA_CODEC_CA0132) += snd-hda-codec-ca0132.o -obj-$(CONFIG_SND_HDA_CODEC_CMEDIA) += snd-hda-codec-cmedia.o obj-$(CONFIG_SND_HDA_CODEC_CONEXANT) += snd-hda-codec-conexant.o obj-$(CONFIG_SND_HDA_CODEC_SIGMATEL) += snd-hda-codec-idt.o obj-$(CONFIG_SND_HDA_CODEC_SENARYTECH) += snd-hda-codec-senarytech.o diff --git a/sound/hda/codecs/conexant.c b/sound/hda/codecs/conexant.c index 3a9717df39b4..e3b6aaabe3a9 100644 --- a/sound/hda/codecs/conexant.c +++ b/sound/hda/codecs/conexant.c @@ -1175,6 +1175,7 @@ static void add_cx5051_fake_mutes(struct hda_codec *codec) static int cx_probe(struct hda_codec *codec, const struct hda_device_id *id) { struct conexant_spec *spec; + struct hda_jack_callback *callback; int err; codec_info(codec, "%s: BIOS auto-probing.\n", codec->core.chip_name); @@ -1190,7 +1191,12 @@ static int cx_probe(struct hda_codec *codec, const struct hda_device_id *id) case 0x14f11f86: case 0x14f11f87: spec->is_cx11880_sn6140 = true; - snd_hda_jack_detect_enable_callback(codec, 0x19, cx_update_headset_mic_vref); + callback = snd_hda_jack_detect_enable_callback(codec, 0x19, + cx_update_headset_mic_vref); + if (IS_ERR(callback)) { + err = PTR_ERR(callback); + goto error; + } break; } diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index d720565db4aa..11d0ea8ed859 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -1669,6 +1669,21 @@ static void alc295_fixup_hp_mute_led_coefbit11(struct hda_codec *codec, } } +/* Override wrong pin to NID 0x1b (F.32 BIOS reports 0x18 via DMI OEM string) + * on HP pavilion 15-cs1xxx laptops + */ +static void alc295_fixup_hp_pavilion_mute_led_1b(struct hda_codec *codec, + const struct hda_fixup *fix, + int action) +{ + struct alc_spec *spec = codec->spec; + + alc269_fixup_hp_mute_led(codec, fix, action); + + if (action == HDA_FIXUP_ACT_PRE_PROBE) + spec->mute_led_nid = 0x1b; +} + static void alc233_fixup_lenovo_coef_micmute_led(struct hda_codec *codec, const struct hda_fixup *fix, int action) { @@ -3390,6 +3405,19 @@ static void alc256_fixup_mic_no_presence_and_resume(struct hda_codec *codec, } } +static void alc256_fixup_xiaomi_pro15_resume(struct hda_codec *codec, + const struct hda_fixup *fix, + int action) +{ + /* + * On the Xiaomi Mi Laptop Pro 15 (TM1905, SSID 1d72:1905) the ALC256 + * codec sets coefficient 0x10 bit 9 to 1 after S3 resume, silencing + * the internal speaker. Bluetooth and HDMI audio are unaffected. + * Clear the bit so the speaker keeps working across suspend cycles. + */ + alc_update_coef_idx(codec, 0x10, 1<<9, 0); +} + static void alc256_decrease_headphone_amp_val(struct hda_codec *codec, const struct hda_fixup *fix, int action) { @@ -3694,6 +3722,17 @@ static void alc287_fixup_lenovo_thinkpad_with_alc1318(struct hda_codec *codec, spec->power_hook = alc287_s4_power_gpio3_default; spec->gen.pcm_playback_hook = alc287_alc1318_playback_pcm_hook; } + +static void alc287_fixup_tb_vmaster_led(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + struct alc_spec *spec = codec->spec; + + if (action == HDA_FIXUP_ACT_PRE_PROBE) + spec->gen.vmaster_mute_led = 1; + + alc287_fixup_bind_dacs(codec, fix, action); +} /* GPIO2: mute led GPIO3: micmute led */ static void alc245_tas2781_spi_hp_fixup_muteled(struct hda_codec *codec, const struct hda_fixup *fix, int action) @@ -3846,6 +3885,7 @@ enum { ALC290_FIXUP_SUBWOOFER, ALC290_FIXUP_SUBWOOFER_HSJACK, ALC295_FIXUP_HP_MUTE_LED_COEFBIT11, + ALC295_FIXUP_HP_PAVILION_MUTE_LED_1B, ALC269_FIXUP_THINKPAD_ACPI, ALC269_FIXUP_LENOVO_XPAD_ACPI, ALC269_FIXUP_DMIC_THINKPAD_ACPI, @@ -4041,6 +4081,7 @@ enum { ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE, ALC233_FIXUP_NO_AUDIO_JACK, ALC256_FIXUP_MIC_NO_PRESENCE_AND_RESUME, + ALC256_FIXUP_XIAOMI_PRO15_RESUME, ALC285_FIXUP_LEGION_Y9000X_SPEAKERS, ALC285_FIXUP_LEGION_Y9000X_AUTOMUTE, ALC287_FIXUP_LEGION_16ACHG6, @@ -4112,6 +4153,7 @@ enum { ALC245_FIXUP_CS35L41_I2C_2_MUTE_LED, ALC236_FIXUP_HP_DMIC, ALC256_FIXUP_HONOR_MRB_XXX_M1020_AUDIO, + ALC245_FIXUP_HP_ENVY_X360_15_FH0XXX, }; /* A special fixup for Lenovo C940 and Yoga Duet 7; @@ -5689,6 +5731,10 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc295_fixup_hp_mute_led_coefbit11, }, + [ALC295_FIXUP_HP_PAVILION_MUTE_LED_1B] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc295_fixup_hp_pavilion_mute_led_1b, + }, [ALC298_FIXUP_SAMSUNG_AMP] = { .type = HDA_FIXUP_FUNC, .v.func = alc298_fixup_samsung_amp, @@ -6229,6 +6275,10 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC }, + [ALC256_FIXUP_XIAOMI_PRO15_RESUME] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc256_fixup_xiaomi_pro15_resume, + }, [ALC287_FIXUP_LEGION_16ACHG6] = { .type = HDA_FIXUP_FUNC, .v.func = alc287_fixup_legion_16achg6_speakers, @@ -6448,7 +6498,7 @@ static const struct hda_fixup alc269_fixups[] = { }, [ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD] = { .type = HDA_FIXUP_FUNC, - .v.func = alc287_fixup_bind_dacs, + .v.func = alc287_fixup_tb_vmaster_led, .chained = true, .chain_id = ALC287_FIXUP_CS35L41_I2C_2_THINKPAD_ACPI, }, @@ -6664,6 +6714,12 @@ static const struct hda_fixup alc269_fixups[] = { { 0x1b, 0x90170110 }, { } } + }, + [ALC245_FIXUP_HP_ENVY_X360_15_FH0XXX] = { + .type = HDA_FIXUP_FUNC, + .v.func = cs35l41_fixup_i2c_two, + .chained = true, + .chain_id = ALC245_FIXUP_HP_X360_MUTE_LEDS } }; @@ -6717,6 +6773,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x159c, "Acer Nitro 5 AN515-58", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x1597, "Acer Nitro 5 AN517-55", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x160e, "Acer PT316-51S", ALC2XX_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1025, 0x1640, "Acer Aspire A315-44P", ALC256_FIXUP_ACER_SFG16_MICMUTE_LED), SND_PCI_QUIRK(0x1025, 0x1679, "Acer Nitro 16 AN16-41", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x169a, "Acer Swift SFG16", ALC256_FIXUP_ACER_SFG16_MICMUTE_LED), SND_PCI_QUIRK(0x1025, 0x171e, "Acer Nitro ANV15-51", ALC245_FIXUP_ACER_MICMUTE_LED), @@ -6894,6 +6951,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8537, "HP ProBook 440 G6", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8548, "HP EliteBook x360 830 G6", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x854a, "HP EliteBook 830 G6", ALC285_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x856a, "HP Pavilion 15-cs1xxx", ALC295_FIXUP_HP_PAVILION_MUTE_LED_1B), SND_PCI_QUIRK(0x103c, 0x85c6, "HP Pavilion x360 Convertible 14-dy1xxx", ALC295_FIXUP_HP_MUTE_LED_COEFBIT11), SND_PCI_QUIRK(0x103c, 0x85de, "HP Envy x360 13-ar0xxx", ALC285_FIXUP_HP_ENVY_X360), SND_PCI_QUIRK(0x103c, 0x8603, "HP Omen 17-cb0xxx", ALC285_FIXUP_HP_MUTE_LED), @@ -7085,7 +7143,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8be6, "HP Envy 16", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8be7, "HP Envy 17", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8be8, "HP Envy 17", ALC287_FIXUP_CS35L41_I2C_2), - SND_PCI_QUIRK(0x103c, 0x8be9, "HP Envy 15", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8be9, "HP Envy x360 2-in-1 Laptop 15-fh0xxx", ALC245_FIXUP_HP_ENVY_X360_15_FH0XXX), SND_PCI_QUIRK(0x103c, 0x8bf0, "HP", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c15, "HP Spectre x360 2-in-1 Laptop 14-eu0xxx", ALC245_FIXUP_HP_SPECTRE_X360_EU0XXX), SND_PCI_QUIRK(0x103c, 0x8c16, "HP Spectre x360 2-in-1 Laptop 16-aa0xxx", ALC245_FIXUP_HP_SPECTRE_X360_16_AA0XXX), @@ -7617,6 +7675,10 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x3801, "Lenovo Yoga9 14IAP7", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), HDA_CODEC_QUIRK(0x17aa, 0x3802, "DuetITL 2021", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x3802, "Lenovo Yoga Pro 9 14IRP8", ALC287_FIXUP_TAS2781_I2C), + /* Yoga Pro 9 16IMH9 shares PCI SSID 17aa:3811 with Legion S7 15IMH05; + * use codec SSID to distinguish them + */ + HDA_CODEC_QUIRK(0x17aa, 0x38d6, "Lenovo Yoga Pro 9 16IMH9", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x3811, "Legion S7 15IMH05", ALC287_FIXUP_LEGION_15IMHG05_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x3813, "Legion 7i 15IMHG05", ALC287_FIXUP_LEGION_15IMHG05_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x3818, "Lenovo C940 / Yoga Duet 7", ALC298_FIXUP_LENOVO_C940_DUET7), @@ -7762,6 +7824,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1d72, 0x1602, "RedmiBook", ALC255_FIXUP_XIAOMI_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1701, "XiaomiNotebook Pro", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC), + SND_PCI_QUIRK(0x1d72, 0x1905, "Xiaomi Mi Laptop Pro 15", ALC256_FIXUP_XIAOMI_PRO15_RESUME), SND_PCI_QUIRK(0x1d72, 0x1945, "Redmi G", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1947, "RedmiBook Air", ALC255_FIXUP_XIAOMI_HEADSET_MIC), SND_PCI_QUIRK(0x1e39, 0xca14, "MEDION NM14LNL", ALC233_FIXUP_MEDION_MTL_SPK), diff --git a/sound/hda/codecs/side-codecs/cs35l56_hda.c b/sound/hda/codecs/side-codecs/cs35l56_hda.c index 1ace4beef508..4c8d01799931 100644 --- a/sound/hda/codecs/side-codecs/cs35l56_hda.c +++ b/sound/hda/codecs/side-codecs/cs35l56_hda.c @@ -180,11 +180,15 @@ static int cs35l56_hda_mixer_get(struct snd_kcontrol *kcontrol, { struct cs35l56_hda *cs35l56 = snd_kcontrol_chip(kcontrol); unsigned int reg_val; - int i; + int i, ret; cs35l56_hda_wait_dsp_ready(cs35l56); - regmap_read(cs35l56->base.regmap, kcontrol->private_value, ®_val); + ret = regmap_read(cs35l56->base.regmap, kcontrol->private_value, + ®_val); + if (ret) + return ret; + reg_val &= CS35L56_ASP_TXn_SRC_MASK; for (i = 0; i < CS35L56_NUM_INPUT_SRC; ++i) { @@ -203,15 +207,20 @@ static int cs35l56_hda_mixer_put(struct snd_kcontrol *kcontrol, struct cs35l56_hda *cs35l56 = snd_kcontrol_chip(kcontrol); unsigned int item = ucontrol->value.enumerated.item[0]; bool changed; + int ret; if (item >= CS35L56_NUM_INPUT_SRC) return -EINVAL; cs35l56_hda_wait_dsp_ready(cs35l56); - regmap_update_bits_check(cs35l56->base.regmap, kcontrol->private_value, - CS35L56_INPUT_MASK, cs35l56_tx_input_values[item], - &changed); + ret = regmap_update_bits_check(cs35l56->base.regmap, + kcontrol->private_value, + CS35L56_INPUT_MASK, + cs35l56_tx_input_values[item], + &changed); + if (ret) + return ret; return changed; } @@ -967,6 +976,7 @@ static int cs35l56_hda_system_resume(struct device *dev) static int cs35l56_hda_fixup_yoga9(struct cs35l56_hda *cs35l56, int *bus_addr) { /* The cirrus,dev-index property has the wrong values */ + cs35l56->num_amps = 2; switch (*bus_addr) { case 0x30: cs35l56->index = 1; @@ -1016,7 +1026,6 @@ static int cs35l56_hda_read_acpi(struct cs35l56_hda *cs35l56, int hid, int id) char hid_string[8]; struct acpi_device *adev; const char *property, *sub; - size_t nval; int i, ret; /* @@ -1052,13 +1061,14 @@ static int cs35l56_hda_read_acpi(struct cs35l56_hda *cs35l56, int hid, int id) ret = -EINVAL; goto err; } - nval = ret; + cs35l56->num_amps = ret; - ret = device_property_read_u32_array(cs35l56->base.dev, property, values, nval); + ret = device_property_read_u32_array(cs35l56->base.dev, property, values, + cs35l56->num_amps); if (ret) goto err; - for (i = 0; i < nval; i++) { + for (i = 0; i < cs35l56->num_amps; i++) { if (values[i] == id) { cs35l56->index = i; break; @@ -1081,7 +1091,8 @@ static int cs35l56_hda_read_acpi(struct cs35l56_hda *cs35l56, int hid, int id) "Read ACPI _SUB failed(%ld): fallback to generic firmware\n", PTR_ERR(sub)); } else { - ret = cirrus_scodec_get_speaker_id(cs35l56->base.dev, cs35l56->index, nval, -1); + ret = cirrus_scodec_get_speaker_id(cs35l56->base.dev, cs35l56->index, + cs35l56->num_amps, -1); if (ret == -ENOENT) { cs35l56->system_name = sub; } else if (ret >= 0) { diff --git a/sound/hda/codecs/side-codecs/cs35l56_hda.h b/sound/hda/codecs/side-codecs/cs35l56_hda.h index cb4b5e7356a3..3705af7c186b 100644 --- a/sound/hda/codecs/side-codecs/cs35l56_hda.h +++ b/sound/hda/codecs/side-codecs/cs35l56_hda.h @@ -26,6 +26,7 @@ struct cs35l56_hda { struct work_struct dsp_work; int index; + int num_amps; const char *system_name; const char *amp_name; diff --git a/sound/hda/codecs/side-codecs/tas2781_hda_spi.c b/sound/hda/codecs/side-codecs/tas2781_hda_spi.c index 560f2385212d..0e4f3553f273 100644 --- a/sound/hda/codecs/side-codecs/tas2781_hda_spi.c +++ b/sound/hda/codecs/side-codecs/tas2781_hda_spi.c @@ -132,10 +132,18 @@ static int tasdevice_spi_dev_update_bits(struct tasdevice_priv *tas_priv, int ret, val; /* - * In our TAS2781 SPI mode, read/write was masked in last bit of - * address, it cause regmap_update_bits() not work as expected. + * In TAS2781 SPI mode, when accessing non-book-zero or page numbers + * greater than 1 in book 0, an additional byte must be read. The + * first byte in such cases is a dummy byte and should be ignored. */ - ret = tasdevice_dev_read(tas_priv, chn, reg, &val); + if ((TASDEVICE_BOOK_ID(reg) > 0) || (TASDEVICE_PAGE_ID(reg) > 1)) { + unsigned char buf[2]; + + ret = tasdevice_dev_bulk_read(tas_priv, chn, reg, buf, 2); + val = buf[1]; + } else { + ret = tasdevice_dev_read(tas_priv, chn, reg, &val); + } if (ret < 0) { dev_err(tas_priv->dev, "%s, E=%d\n", __func__, ret); return ret; diff --git a/sound/hda/core/hdmi_chmap.c b/sound/hda/core/hdmi_chmap.c index 7b276047f85a..c897fc443467 100644 --- a/sound/hda/core/hdmi_chmap.c +++ b/sound/hda/core/hdmi_chmap.c @@ -353,13 +353,16 @@ static void hdmi_std_setup_channel_mapping(struct hdac_chmap *chmap, if (hdmi_channel_mapping[ca][1] == 0) { int hdmi_slot = 0; /* fill actual channel mappings in ALSA channel (i) order */ - for (i = 0; i < ch_alloc->channels; i++) { - while (!WARN_ON(hdmi_slot >= 8) && - !ch_alloc->speakers[7 - hdmi_slot]) - hdmi_slot++; /* skip zero slots */ + for (i = 0; i < ch_alloc->channels && hdmi_slot < 8; i++) { + while (!ch_alloc->speakers[7 - hdmi_slot]) { + /* skip zero slots */ + if (++hdmi_slot >= 8) + goto out; + } hdmi_channel_mapping[ca][i] = (i << 4) | hdmi_slot++; } + out: /* fill the rest of the slots with ALSA channel 0xf */ for (hdmi_slot = 0; hdmi_slot < 8; hdmi_slot++) if (!ch_alloc->speakers[7 - hdmi_slot]) diff --git a/sound/soc/amd/acp/acp-legacy-mach.c b/sound/soc/amd/acp/acp-legacy-mach.c index a7a551366a40..235d6cc83fa9 100644 --- a/sound/soc/amd/acp/acp-legacy-mach.c +++ b/sound/soc/amd/acp/acp-legacy-mach.c @@ -174,7 +174,7 @@ static int acp_asoc_probe(struct platform_device *pdev) acp_card_drvdata->acp_rev = mach->mach_params.subsystem_rev; dmi_id = dmi_first_match(acp_quirk_table); - if (dmi_id && dmi_id->driver_data) + if (dmi_id && dmi_id->driver_data == (void *)QUIRK_TDM_MODE_ENABLE) acp_card_drvdata->tdm_mode = dmi_id->driver_data; ret = acp_legacy_dai_links_create(card); diff --git a/sound/soc/amd/acp/acp-mach-common.c b/sound/soc/amd/acp/acp-mach-common.c index 09f6c9a2c041..ef784cca13f2 100644 --- a/sound/soc/amd/acp/acp-mach-common.c +++ b/sound/soc/amd/acp/acp-mach-common.c @@ -20,6 +20,7 @@ #include <sound/soc.h> #include <linux/input.h> #include <linux/module.h> +#include <linux/dmi.h> #include "../../codecs/rt5682.h" #include "../../codecs/rt1019.h" @@ -37,15 +38,21 @@ #define NAU8821_FREQ_OUT 12288000 #define MAX98388_CODEC_DAI "max98388-aif1" -#define TDM_MODE_ENABLE 1 - const struct dmi_system_id acp_quirk_table[] = { { /* Google skyrim proto-0 */ .matches = { DMI_EXACT_MATCH(DMI_PRODUCT_FAMILY, "Google_Skyrim"), }, - .driver_data = (void *)TDM_MODE_ENABLE, + .driver_data = (void *)QUIRK_TDM_MODE_ENABLE, + }, + { + /* Valve Steam Deck OLED */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Valve"), + DMI_MATCH(DMI_PRODUCT_NAME, "Galileo"), + }, + .driver_data = (void *)QUIRK_REMAP_DMIC_BT, }, {} }; @@ -1401,6 +1408,7 @@ int acp_sofdsp_dai_links_create(struct snd_soc_card *card) struct snd_soc_dai_link *links; struct device *dev = card->dev; struct acp_card_drvdata *drv_data = card->drvdata; + const struct dmi_system_id *dmi_id = dmi_first_match(acp_quirk_table); int i = 0, num_links = 0; if (drv_data->hs_cpu_id) @@ -1572,6 +1580,9 @@ int acp_sofdsp_dai_links_create(struct snd_soc_card *card) links[i].codecs = &snd_soc_dummy_dlc; links[i].num_codecs = 1; } + + if (dmi_id && dmi_id->driver_data == (void *)QUIRK_REMAP_DMIC_BT) + links[i].id = DMIC_BE_ID; i++; } @@ -1587,6 +1598,11 @@ int acp_sofdsp_dai_links_create(struct snd_soc_card *card) links[i].capture_only = 1; links[i].nonatomic = true; links[i].no_pcm = 1; + + if (dmi_id && dmi_id->driver_data == (void *)QUIRK_REMAP_DMIC_BT) { + links[i].id = BT_BE_ID; + dev_dbg(dev, "quirk REMAP_DMIC_BT enabled\n"); + } } card->dai_link = links; diff --git a/sound/soc/amd/acp/acp-mach.h b/sound/soc/amd/acp/acp-mach.h index f94c30c20f20..7177d3fd9619 100644 --- a/sound/soc/amd/acp/acp-mach.h +++ b/sound/soc/amd/acp/acp-mach.h @@ -26,6 +26,10 @@ #define acp_get_drvdata(card) ((struct acp_card_drvdata *)(card)->drvdata) +/* List of DMI quirks - check acp-mach-common.c for usage. */ +#define QUIRK_TDM_MODE_ENABLE 1 +#define QUIRK_REMAP_DMIC_BT 2 + enum be_id { HEADSET_BE_ID = 0, AMP_BE_ID, diff --git a/sound/soc/amd/acp/acp-sof-mach.c b/sound/soc/amd/acp/acp-sof-mach.c index 6215e31ecedd..36ecef7013b9 100644 --- a/sound/soc/amd/acp/acp-sof-mach.c +++ b/sound/soc/amd/acp/acp-sof-mach.c @@ -110,7 +110,7 @@ static int acp_sof_probe(struct platform_device *pdev) acp_card_drvdata = card->drvdata; dmi_id = dmi_first_match(acp_quirk_table); - if (dmi_id && dmi_id->driver_data) + if (dmi_id && dmi_id->driver_data == (void *)QUIRK_TDM_MODE_ENABLE) acp_card_drvdata->tdm_mode = dmi_id->driver_data; acp_card_drvdata->acp_rev = mach->mach_params.subsystem_rev; diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index c5cf45881416..7a637d6b5576 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -62,6 +62,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { { .driver_data = &acp6x_card, .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "HP"), + DMI_MATCH(DMI_PRODUCT_NAME, "OMEN Gaming Laptop 16-ap0xxx"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "Dell Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "Dell G15 5525"), } @@ -483,6 +490,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { .driver_data = &acp6x_card, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "Micro-Star International Co., Ltd."), + DMI_MATCH(DMI_PRODUCT_NAME, "Bravo 15 C7VE"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Micro-Star International Co., Ltd."), DMI_MATCH(DMI_PRODUCT_NAME, "Bravo 15 C7VF"), } }, @@ -671,6 +685,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { { .driver_data = &acp6x_card, .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "HP"), + DMI_MATCH(DMI_BOARD_NAME, "8E35"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "MECHREVO"), DMI_MATCH(DMI_BOARD_NAME, "MRID6"), } diff --git a/sound/soc/codecs/ab8500-codec.c b/sound/soc/codecs/ab8500-codec.c index fdda1b747bf7..6e8ef9cd1b31 100644 --- a/sound/soc/codecs/ab8500-codec.c +++ b/sound/soc/codecs/ab8500-codec.c @@ -60,19 +60,6 @@ low before proceeding with the configuration sequence */ #define AB8500_ANC_SM_DELAY 2000 -#define AB8500_FILTER_CONTROL(xname, xcount, xmin, xmax) \ -{ .iface = SNDRV_CTL_ELEM_IFACE_MIXER, .name = (xname), \ - .info = filter_control_info, \ - .get = filter_control_get, .put = filter_control_put, \ - .private_value = (unsigned long)&(struct filter_control) \ - {.count = xcount, .min = xmin, .max = xmax} } - -struct filter_control { - long min, max; - unsigned int count; - long value[128]; -}; - /* Sidetone states */ static const char * const enum_sid_state[] = { "Unconfigured", @@ -85,45 +72,13 @@ enum sid_state { SID_FIR_CONFIGURED = 2, }; -static const char * const enum_anc_state[] = { - "Unconfigured", - "Apply FIR and IIR", - "FIR and IIR are configured", - "Apply FIR", - "FIR is configured", - "Apply IIR", - "IIR is configured" -}; -enum anc_state { - ANC_UNCONFIGURED = 0, - ANC_APPLY_FIR_IIR = 1, - ANC_FIR_IIR_CONFIGURED = 2, - ANC_APPLY_FIR = 3, - ANC_FIR_CONFIGURED = 4, - ANC_APPLY_IIR = 5, - ANC_IIR_CONFIGURED = 6 -}; - -/* Analog microphones */ -enum amic_idx { - AMIC_IDX_1A, - AMIC_IDX_1B, - AMIC_IDX_2 -}; - /* Private data for AB8500 device-driver */ struct ab8500_codec_drvdata { struct regmap *regmap; struct mutex ctrl_lock; /* Sidetone */ - long *sid_fir_values; enum sid_state sid_status; - - /* ANC */ - long *anc_fir_values; - long *anc_iir_values; - enum anc_state anc_status; }; static inline const char *amic_micbias_str(enum amic_micbias micbias) @@ -1024,89 +979,6 @@ static const struct snd_soc_dapm_route ab8500_dapm_routes_mic2_vamicx[] = { {"MIC2 V-AMICx Enable", NULL, "V-AMIC2"}, }; -/* ANC FIR-coefficients configuration sequence */ -static void anc_fir(struct snd_soc_component *component, - unsigned int bnk, unsigned int par, unsigned int val) -{ - if (par == 0 && bnk == 0) - snd_soc_component_update_bits(component, AB8500_ANCCONF1, - BIT(AB8500_ANCCONF1_ANCFIRUPDATE), - BIT(AB8500_ANCCONF1_ANCFIRUPDATE)); - - snd_soc_component_write(component, AB8500_ANCCONF5, val >> 8 & 0xff); - snd_soc_component_write(component, AB8500_ANCCONF6, val & 0xff); - - if (par == AB8500_ANC_FIR_COEFFS - 1 && bnk == 1) - snd_soc_component_update_bits(component, AB8500_ANCCONF1, - BIT(AB8500_ANCCONF1_ANCFIRUPDATE), 0); -} - -/* ANC IIR-coefficients configuration sequence */ -static void anc_iir(struct snd_soc_component *component, unsigned int bnk, - unsigned int par, unsigned int val) -{ - if (par == 0) { - if (bnk == 0) { - snd_soc_component_update_bits(component, AB8500_ANCCONF1, - BIT(AB8500_ANCCONF1_ANCIIRINIT), - BIT(AB8500_ANCCONF1_ANCIIRINIT)); - usleep_range(AB8500_ANC_SM_DELAY, AB8500_ANC_SM_DELAY*2); - snd_soc_component_update_bits(component, AB8500_ANCCONF1, - BIT(AB8500_ANCCONF1_ANCIIRINIT), 0); - usleep_range(AB8500_ANC_SM_DELAY, AB8500_ANC_SM_DELAY*2); - } else { - snd_soc_component_update_bits(component, AB8500_ANCCONF1, - BIT(AB8500_ANCCONF1_ANCIIRUPDATE), - BIT(AB8500_ANCCONF1_ANCIIRUPDATE)); - } - } else if (par > 3) { - snd_soc_component_write(component, AB8500_ANCCONF7, 0); - snd_soc_component_write(component, AB8500_ANCCONF8, val >> 16 & 0xff); - } - - snd_soc_component_write(component, AB8500_ANCCONF7, val >> 8 & 0xff); - snd_soc_component_write(component, AB8500_ANCCONF8, val & 0xff); - - if (par == AB8500_ANC_IIR_COEFFS - 1 && bnk == 1) - snd_soc_component_update_bits(component, AB8500_ANCCONF1, - BIT(AB8500_ANCCONF1_ANCIIRUPDATE), 0); -} - -/* ANC IIR-/FIR-coefficients configuration sequence */ -static void anc_configure(struct snd_soc_component *component, - bool apply_fir, bool apply_iir) -{ - struct ab8500_codec_drvdata *drvdata = dev_get_drvdata(component->dev); - unsigned int bnk, par, val; - - dev_dbg(component->dev, "%s: Enter.\n", __func__); - - if (apply_fir) - snd_soc_component_update_bits(component, AB8500_ANCCONF1, - BIT(AB8500_ANCCONF1_ENANC), 0); - - snd_soc_component_update_bits(component, AB8500_ANCCONF1, - BIT(AB8500_ANCCONF1_ENANC), BIT(AB8500_ANCCONF1_ENANC)); - - if (apply_fir) - for (bnk = 0; bnk < AB8500_NR_OF_ANC_COEFF_BANKS; bnk++) - for (par = 0; par < AB8500_ANC_FIR_COEFFS; par++) { - val = snd_soc_component_read(component, - drvdata->anc_fir_values[par]); - anc_fir(component, bnk, par, val); - } - - if (apply_iir) - for (bnk = 0; bnk < AB8500_NR_OF_ANC_COEFF_BANKS; bnk++) - for (par = 0; par < AB8500_ANC_IIR_COEFFS; par++) { - val = snd_soc_component_read(component, - drvdata->anc_iir_values[par]); - anc_iir(component, bnk, par, val); - } - - dev_dbg(component->dev, "%s: Exit.\n", __func__); -} - /* * Control-events */ @@ -1130,7 +1002,7 @@ static int sid_status_control_put(struct snd_kcontrol *kcontrol, { struct snd_soc_component *component = snd_kcontrol_chip(kcontrol); struct ab8500_codec_drvdata *drvdata = dev_get_drvdata(component->dev); - unsigned int param, sidconf, val; + unsigned int param, sidconf; int status = 1; dev_dbg(component->dev, "%s: Enter\n", __func__); @@ -1159,9 +1031,8 @@ static int sid_status_control_put(struct snd_kcontrol *kcontrol, snd_soc_component_write(component, AB8500_SIDFIRADR, 0); for (param = 0; param < AB8500_SID_FIR_COEFFS; param++) { - val = snd_soc_component_read(component, drvdata->sid_fir_values[param]); - snd_soc_component_write(component, AB8500_SIDFIRCOEF1, val >> 8 & 0xff); - snd_soc_component_write(component, AB8500_SIDFIRCOEF2, val & 0xff); + snd_soc_component_write(component, AB8500_SIDFIRCOEF1, 0); + snd_soc_component_write(component, AB8500_SIDFIRCOEF2, 0); } snd_soc_component_update_bits(component, AB8500_SIDFIRADR, @@ -1180,136 +1051,6 @@ out: return status; } -static int anc_status_control_get(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol) -{ - struct snd_soc_component *component = snd_kcontrol_chip(kcontrol); - struct ab8500_codec_drvdata *drvdata = dev_get_drvdata(component->dev); - - mutex_lock(&drvdata->ctrl_lock); - ucontrol->value.enumerated.item[0] = drvdata->anc_status; - mutex_unlock(&drvdata->ctrl_lock); - - return 0; -} - -static int anc_status_control_put(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol) -{ - struct snd_soc_component *component = snd_kcontrol_chip(kcontrol); - struct snd_soc_dapm_context *dapm = snd_soc_component_to_dapm(component); - struct ab8500_codec_drvdata *drvdata = dev_get_drvdata(component->dev); - struct device *dev = component->dev; - bool apply_fir, apply_iir; - unsigned int req; - int status; - - dev_dbg(dev, "%s: Enter.\n", __func__); - - mutex_lock(&drvdata->ctrl_lock); - - req = ucontrol->value.enumerated.item[0]; - if (req >= ARRAY_SIZE(enum_anc_state)) { - status = -EINVAL; - goto cleanup; - } - if (req != ANC_APPLY_FIR_IIR && req != ANC_APPLY_FIR && - req != ANC_APPLY_IIR) { - dev_err(dev, "%s: ERROR: Unsupported status to set '%s'!\n", - __func__, enum_anc_state[req]); - status = -EINVAL; - goto cleanup; - } - apply_fir = req == ANC_APPLY_FIR || req == ANC_APPLY_FIR_IIR; - apply_iir = req == ANC_APPLY_IIR || req == ANC_APPLY_FIR_IIR; - - status = snd_soc_dapm_force_enable_pin(dapm, "ANC Configure Input"); - if (status < 0) { - dev_err(dev, - "%s: ERROR: Failed to enable power (status = %d)!\n", - __func__, status); - goto cleanup; - } - snd_soc_dapm_sync(dapm); - - anc_configure(component, apply_fir, apply_iir); - - if (apply_fir) { - if (drvdata->anc_status == ANC_IIR_CONFIGURED) - drvdata->anc_status = ANC_FIR_IIR_CONFIGURED; - else if (drvdata->anc_status != ANC_FIR_IIR_CONFIGURED) - drvdata->anc_status = ANC_FIR_CONFIGURED; - } - if (apply_iir) { - if (drvdata->anc_status == ANC_FIR_CONFIGURED) - drvdata->anc_status = ANC_FIR_IIR_CONFIGURED; - else if (drvdata->anc_status != ANC_FIR_IIR_CONFIGURED) - drvdata->anc_status = ANC_IIR_CONFIGURED; - } - - status = snd_soc_dapm_disable_pin(dapm, "ANC Configure Input"); - snd_soc_dapm_sync(dapm); - -cleanup: - mutex_unlock(&drvdata->ctrl_lock); - - if (status < 0) - dev_err(dev, "%s: Unable to configure ANC! (status = %d)\n", - __func__, status); - - dev_dbg(dev, "%s: Exit.\n", __func__); - - return (status < 0) ? status : 1; -} - -static int filter_control_info(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_info *uinfo) -{ - struct filter_control *fc = - (struct filter_control *)kcontrol->private_value; - - uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER; - uinfo->count = fc->count; - uinfo->value.integer.min = fc->min; - uinfo->value.integer.max = fc->max; - - return 0; -} - -static int filter_control_get(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol) -{ - struct snd_soc_component *component = snd_kcontrol_chip(kcontrol); - struct ab8500_codec_drvdata *drvdata = snd_soc_component_get_drvdata(component); - struct filter_control *fc = - (struct filter_control *)kcontrol->private_value; - unsigned int i; - - mutex_lock(&drvdata->ctrl_lock); - for (i = 0; i < fc->count; i++) - ucontrol->value.integer.value[i] = fc->value[i]; - mutex_unlock(&drvdata->ctrl_lock); - - return 0; -} - -static int filter_control_put(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol) -{ - struct snd_soc_component *component = snd_kcontrol_chip(kcontrol); - struct ab8500_codec_drvdata *drvdata = snd_soc_component_get_drvdata(component); - struct filter_control *fc = - (struct filter_control *)kcontrol->private_value; - unsigned int i; - - mutex_lock(&drvdata->ctrl_lock); - for (i = 0; i < fc->count; i++) - fc->value[i] = ucontrol->value.integer.value[i]; - mutex_unlock(&drvdata->ctrl_lock); - - return 0; -} - /* * Controls - Non-DAPM ASoC */ @@ -1597,7 +1338,6 @@ static SOC_ENUM_SINGLE_DECL(soc_enum_bfifomast, static SOC_ENUM_SINGLE_EXT_DECL(soc_enum_sidstate, enum_sid_state); /* ANC */ -static SOC_ENUM_SINGLE_EXT_DECL(soc_enum_ancstate, enum_anc_state); static struct snd_kcontrol_new ab8500_ctrls[] = { /* Charge pump */ @@ -1873,8 +1613,6 @@ static struct snd_kcontrol_new ab8500_ctrls[] = { AB8500_FIFOCONF6_BFIFOSAMPLE_MAX, 0), /* ANC */ - SOC_ENUM_EXT("ANC Status", soc_enum_ancstate, - anc_status_control_get, anc_status_control_put), SOC_SINGLE_XR_SX("ANC Warp Delay Shift", AB8500_ANCCONF2, 1, AB8500_ANCCONF2_SHIFT, AB8500_ANCCONF2_MIN, AB8500_ANCCONF2_MAX, 0), @@ -1895,21 +1633,6 @@ static struct snd_kcontrol_new ab8500_ctrls[] = { AB8500_SIDFIRADR, AB8500_SIDFIRADR_FIRSIDSET, 0), }; -static struct snd_kcontrol_new ab8500_filter_controls[] = { - AB8500_FILTER_CONTROL("ANC FIR Coefficients", AB8500_ANC_FIR_COEFFS, - AB8500_ANC_FIR_COEFF_MIN, AB8500_ANC_FIR_COEFF_MAX), - AB8500_FILTER_CONTROL("ANC IIR Coefficients", AB8500_ANC_IIR_COEFFS, - AB8500_ANC_IIR_COEFF_MIN, AB8500_ANC_IIR_COEFF_MAX), - AB8500_FILTER_CONTROL("Sidetone FIR Coefficients", - AB8500_SID_FIR_COEFFS, AB8500_SID_FIR_COEFF_MIN, - AB8500_SID_FIR_COEFF_MAX) -}; -enum ab8500_filter { - AB8500_FILTER_ANC_FIR = 0, - AB8500_FILTER_ANC_IIR = 1, - AB8500_FILTER_SID_FIR = 2, -}; - /* * Extended interface for codec-driver */ @@ -2454,7 +2177,6 @@ static int ab8500_codec_probe(struct snd_soc_component *component) struct device_node *np = dev->of_node; struct ab8500_codec_drvdata *drvdata = dev_get_drvdata(dev); struct ab8500_codec_platform_data codec_pdata; - struct filter_control *fc; int status; dev_dbg(dev, "%s: Enter.\n", __func__); @@ -2486,25 +2208,6 @@ static int ab8500_codec_probe(struct snd_soc_component *component) snd_soc_component_write(component, AB8500_SHORTCIRCONF, BIT(AB8500_SHORTCIRCONF_HSZCDDIS)); - /* Add filter controls */ - status = snd_soc_add_component_controls(component, ab8500_filter_controls, - ARRAY_SIZE(ab8500_filter_controls)); - if (status < 0) { - dev_err(dev, - "%s: failed to add ab8500 filter controls (%d).\n", - __func__, status); - return status; - } - fc = (struct filter_control *) - &ab8500_filter_controls[AB8500_FILTER_ANC_FIR].private_value; - drvdata->anc_fir_values = (long *)fc->value; - fc = (struct filter_control *) - &ab8500_filter_controls[AB8500_FILTER_ANC_IIR].private_value; - drvdata->anc_iir_values = (long *)fc->value; - fc = (struct filter_control *) - &ab8500_filter_controls[AB8500_FILTER_SID_FIR].private_value; - drvdata->sid_fir_values = (long *)fc->value; - snd_soc_dapm_disable_pin(dapm, "ANC Configure Input"); mutex_init(&drvdata->ctrl_lock); @@ -2538,7 +2241,6 @@ static int ab8500_codec_driver_probe(struct platform_device *pdev) if (!drvdata) return -ENOMEM; drvdata->sid_status = SID_UNCONFIGURED; - drvdata->anc_status = ANC_UNCONFIGURED; dev_set_drvdata(&pdev->dev, drvdata); drvdata->regmap = devm_regmap_init(&pdev->dev, NULL, &pdev->dev, diff --git a/sound/soc/codecs/aw88395/aw88395.c b/sound/soc/codecs/aw88395/aw88395.c index 3602b5b9f7d7..dd09bac652f7 100644 --- a/sound/soc/codecs/aw88395/aw88395.c +++ b/sound/soc/codecs/aw88395/aw88395.c @@ -456,8 +456,6 @@ static void aw88395_hw_reset(struct aw88395 *aw88395) usleep_range(AW88395_1000_US, AW88395_1000_US + 10); gpiod_set_value_cansleep(aw88395->reset_gpio, 1); usleep_range(AW88395_1000_US, AW88395_1000_US + 10); - } else { - dev_err(aw88395->aw_pa->dev, "%s failed", __func__); } } @@ -522,9 +520,10 @@ static int aw88395_i2c_probe(struct i2c_client *i2c) i2c_set_clientdata(i2c, aw88395); aw88395->reset_gpio = devm_gpiod_get_optional(&i2c->dev, "reset", GPIOD_OUT_LOW); - if (IS_ERR(aw88395->reset_gpio)) - dev_info(&i2c->dev, "reset gpio not defined\n"); - + if (IS_ERR(aw88395->reset_gpio)) { + return dev_err_probe(&i2c->dev, PTR_ERR(aw88395->reset_gpio), + "failed to get reset gpio\n"); + } /* hardware reset */ aw88395_hw_reset(aw88395); diff --git a/sound/soc/codecs/cs35l56-shared.c b/sound/soc/codecs/cs35l56-shared.c index e05d975ba794..795e2764d67e 100644 --- a/sound/soc/codecs/cs35l56-shared.c +++ b/sound/soc/codecs/cs35l56-shared.c @@ -108,8 +108,6 @@ int cs35l56_set_patch(struct cs35l56_base *cs35l56_base) EXPORT_SYMBOL_NS_GPL(cs35l56_set_patch, "SND_SOC_CS35L56_SHARED"); static const struct reg_default cs35l56_reg_defaults[] = { - /* no defaults for OTP_MEM - first read populates cache */ - { CS35L56_ASP1_ENABLES1, 0x00000000 }, { CS35L56_ASP1_CONTROL1, 0x00000028 }, { CS35L56_ASP1_CONTROL2, 0x18180200 }, @@ -138,8 +136,6 @@ static const struct reg_default cs35l56_reg_defaults[] = { }; static const struct reg_default cs35l63_reg_defaults[] = { - /* no defaults for OTP_MEM - first read populates cache */ - { CS35L56_ASP1_ENABLES1, 0x00000000 }, { CS35L56_ASP1_CONTROL1, 0x00000028 }, { CS35L56_ASP1_CONTROL2, 0x18180200 }, @@ -282,6 +278,9 @@ static bool cs35l56_common_volatile_reg(unsigned int reg) case CS35L56_GLOBAL_ENABLES: /* owned by firmware */ case CS35L56_BLOCK_ENABLES: /* owned by firmware */ case CS35L56_BLOCK_ENABLES2: /* owned by firmware */ + case CS35L56_OTP_MEM_53: + case CS35L56_OTP_MEM_54: + case CS35L56_OTP_MEM_55: case CS35L56_SYNC_GPIO1_CFG ... CS35L56_ASP2_DIO_GPIO13_CFG: case CS35L56_UPDATE_REGS: case CS35L56_REFCLK_INPUT: /* owned by firmware */ @@ -852,9 +851,11 @@ out_sync: err: regcache_cache_only(cs35l56_base->regmap, true); - regmap_multi_reg_write_bypassed(cs35l56_base->regmap, - cs35l56_hibernate_seq, - ARRAY_SIZE(cs35l56_hibernate_seq)); + if (cs35l56_base->can_hibernate) { + regmap_multi_reg_write_bypassed(cs35l56_base->regmap, + cs35l56_hibernate_seq, + ARRAY_SIZE(cs35l56_hibernate_seq)); + } return ret; } @@ -1729,8 +1730,7 @@ int cs35l56_read_onchip_spkid(struct cs35l56_base *cs35l56_base) ret = regmap_read(regmap, CS35L56_GPIO_STATUS1, &val); if (ret) { - dev_err(cs35l56_base->dev, "GPIO%d status read failed: %d\n", - cs35l56_base->onchip_spkid_gpios[i] + 1, ret); + dev_err(cs35l56_base->dev, "GPIO status read failed: %d\n", ret); return ret; } diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c index 378017fcea10..849d70ca23d6 100644 --- a/sound/soc/codecs/cs35l56.c +++ b/sound/soc/codecs/cs35l56.c @@ -1956,9 +1956,9 @@ int cs35l56_common_probe(struct cs35l56_private *cs35l56) goto err; } - ret = devm_snd_soc_register_component(cs35l56->base.dev, - &soc_component_dev_cs35l56, - cs35l56_dai, ARRAY_SIZE(cs35l56_dai)); + ret = snd_soc_register_component(cs35l56->base.dev, + &soc_component_dev_cs35l56, + cs35l56_dai, ARRAY_SIZE(cs35l56_dai)); if (ret < 0) { dev_err_probe(cs35l56->base.dev, ret, "Register codec failed\n"); goto err; @@ -1970,6 +1970,9 @@ err: gpiod_set_value_cansleep(cs35l56->base.reset_gpio, 0); regulator_bulk_disable(ARRAY_SIZE(cs35l56->supplies), cs35l56->supplies); + if (cs35l56->dsp_wq) + destroy_workqueue(cs35l56->dsp_wq); + return ret; } EXPORT_SYMBOL_NS_GPL(cs35l56_common_probe, "SND_SOC_CS35L56_CORE"); @@ -2057,6 +2060,8 @@ EXPORT_SYMBOL_NS_GPL(cs35l56_init, "SND_SOC_CS35L56_CORE"); void cs35l56_remove(struct cs35l56_private *cs35l56) { + snd_soc_unregister_component(cs35l56->base.dev); + cs35l56->base.init_done = false; /* diff --git a/sound/soc/codecs/es8389.c b/sound/soc/codecs/es8389.c index 8d418cae371a..449d9574b03a 100644 --- a/sound/soc/codecs/es8389.c +++ b/sound/soc/codecs/es8389.c @@ -892,7 +892,7 @@ static int es8389_probe(struct snd_soc_component *component) return ret; } - es8389->mclk = devm_clk_get(component->dev, "mclk"); + es8389->mclk = devm_clk_get_optional(component->dev, "mclk"); if (IS_ERR(es8389->mclk)) return dev_err_probe(component->dev, PTR_ERR(es8389->mclk), "ES8389 is unable to get mclk\n"); diff --git a/sound/soc/codecs/tas2764.c b/sound/soc/codecs/tas2764.c index 423b7073b302..55211266927d 100644 --- a/sound/soc/codecs/tas2764.c +++ b/sound/soc/codecs/tas2764.c @@ -684,18 +684,33 @@ static int tas2764_read_die_temp(struct tas2764_priv *tas2764, long *result) * As per datasheet, subtract 93 from raw value to get degrees * Celsius. hwmon wants millidegrees. * - * NOTE: The chip will initialise the TAS2764_TEMP register to - * 2.6 *C to avoid triggering temperature protection. Since the - * ADC is powered down during software shutdown, this value will - * persist until the chip is fully powered up (e.g. the PCM it's - * attached to is opened). The ADC will power down again when - * the chip is put back into software shutdown, with the last - * value sampled persisting in the ADC's register. + * NOTE: The TAS2764 datasheet mentions initialising TAS2764_TEMP + * such that the temperature is 2.6 *C, however the register + * is actually initialised to 0. The ADC is also powered down during + * software shutdown. The last sampled temperature will persist + * in the register while the amp is in this power state. */ + if (reg == 0) + return -ENODATA; + *result = (reg - 93) * 1000; return 0; } +static int tas2764_hwmon_is_fault(struct tas2764_priv *tas2764, long *result) +{ + int ret; + long temp; + + ret = tas2764_read_die_temp(tas2764, &temp); + if (ret == -ENODATA) { + *result = true; + return 0; + } + + return ret; +} + static umode_t tas2764_hwmon_is_visible(const void *data, enum hwmon_sensor_types type, u32 attr, int channel) @@ -705,6 +720,7 @@ static umode_t tas2764_hwmon_is_visible(const void *data, switch (attr) { case hwmon_temp_input: + case hwmon_temp_fault: return 0444; default: break; @@ -724,6 +740,9 @@ static int tas2764_hwmon_read(struct device *dev, case hwmon_temp_input: ret = tas2764_read_die_temp(tas2764, val); break; + case hwmon_temp_fault: + ret = tas2764_hwmon_is_fault(tas2764, val); + break; default: ret = -EOPNOTSUPP; break; @@ -733,7 +752,7 @@ static int tas2764_hwmon_read(struct device *dev, } static const struct hwmon_channel_info *const tas2764_hwmon_info[] = { - HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT), + HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT | HWMON_T_FAULT), NULL }; @@ -904,6 +923,7 @@ static bool tas2764_volatile_register(struct device *dev, unsigned int reg) { switch (reg) { case TAS2764_SW_RST: + case TAS2764_TEMP: case TAS2764_INT_LTCH0 ... TAS2764_INT_LTCH4: case TAS2764_INT_CLK_CFG: return true; diff --git a/sound/soc/codecs/tas2770.c b/sound/soc/codecs/tas2770.c index d4d7d056141b..dbda9f327535 100644 --- a/sound/soc/codecs/tas2770.c +++ b/sound/soc/codecs/tas2770.c @@ -624,7 +624,7 @@ static int tas2770_read_die_temp(struct tas2770_priv *tas2770, long *result) /* * As per datasheet: divide register by 16 and subtract 93 to get * degrees Celsius. hwmon requires millidegrees. Let's avoid rounding - * errors by subtracting 93 * 16 then multiplying by 1000 / 16. + * errors by subtracting 93 * 16 and scaling before dividing. * * NOTE: The ADC registers are initialised to 0 on reset. This means * that the temperature will read -93 *C until the chip is brought out @@ -633,10 +633,27 @@ static int tas2770_read_die_temp(struct tas2770_priv *tas2770, long *result) * value read back from its registers will be the last value sampled * before entering software shutdown. */ - *result = (reading - (93 * 16)) * (1000 / 16); + if (reading == 0) + return -ENODATA; + + *result = (reading - (93 * 16)) * 1000 / 16; return 0; } +static int tas2770_hwmon_is_fault(struct tas2770_priv *tas2770, long *result) +{ + int ret; + long temp; + + ret = tas2770_read_die_temp(tas2770, &temp); + if (ret == -ENODATA) { + *result = true; + return 0; + } + + return ret; +} + static umode_t tas2770_hwmon_is_visible(const void *data, enum hwmon_sensor_types type, u32 attr, int channel) @@ -646,6 +663,7 @@ static umode_t tas2770_hwmon_is_visible(const void *data, switch (attr) { case hwmon_temp_input: + case hwmon_temp_fault: return 0444; default: break; @@ -665,6 +683,9 @@ static int tas2770_hwmon_read(struct device *dev, case hwmon_temp_input: ret = tas2770_read_die_temp(tas2770, val); break; + case hwmon_temp_fault: + ret = tas2770_hwmon_is_fault(tas2770, val); + break; default: ret = -EOPNOTSUPP; break; @@ -674,7 +695,7 @@ static int tas2770_hwmon_read(struct device *dev, } static const struct hwmon_channel_info *const tas2770_hwmon_info[] = { - HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT), + HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT | HWMON_T_FAULT), NULL }; diff --git a/sound/soc/codecs/wcd937x.c b/sound/soc/codecs/wcd937x.c index 10a2d598caa7..72a53f95d688 100644 --- a/sound/soc/codecs/wcd937x.c +++ b/sound/soc/codecs/wcd937x.c @@ -547,6 +547,9 @@ static int wcd937x_codec_aux_dac_event(struct snd_soc_dapm_widget *w, WCD937X_DIGITAL_CDC_ANA_CLK_CTL, BIT(2), BIT(2)); snd_soc_component_update_bits(component, + WCD937X_AUX_AUXPA, + BIT(4), BIT(4)); + snd_soc_component_update_bits(component, WCD937X_DIGITAL_CDC_DIG_CLK_CTL, BIT(2), BIT(2)); snd_soc_component_update_bits(component, @@ -562,6 +565,9 @@ static int wcd937x_codec_aux_dac_event(struct snd_soc_dapm_widget *w, snd_soc_component_update_bits(component, WCD937X_DIGITAL_CDC_ANA_CLK_CTL, BIT(2), 0x00); + snd_soc_component_update_bits(component, + WCD937X_AUX_AUXPA, + BIT(4), 0x00); break; } @@ -730,10 +736,23 @@ static int wcd937x_codec_enable_aux_pa(struct snd_soc_dapm_widget *w, snd_soc_component_update_bits(component, WCD937X_ANA_RX_SUPPLIES, BIT(1), BIT(1)); + /* Enable AUX PA related RX supplies */ + snd_soc_component_update_bits(component, + WCD937X_ANA_RX_SUPPLIES, + BIT(6), BIT(6)); + snd_soc_component_update_bits(component, + WCD937X_ANA_RX_SUPPLIES, + BIT(7), BIT(7)); enable_irq(wcd937x->aux_pdm_wd_int); break; case SND_SOC_DAPM_PRE_PMD: disable_irq_nosync(wcd937x->aux_pdm_wd_int); + snd_soc_component_update_bits(component, + WCD937X_ANA_RX_SUPPLIES, + BIT(6), 0x00); + snd_soc_component_update_bits(component, + WCD937X_ANA_RX_SUPPLIES, + BIT(7), 0x00); break; case SND_SOC_DAPM_POST_PMD: usleep_range(2000, 2010); @@ -2051,7 +2070,12 @@ static const struct snd_kcontrol_new wcd937x_snd_controls[] = { wcd937x_get_swr_port, wcd937x_set_swr_port), SOC_SINGLE_EXT("LO Switch", WCD937X_LO, 0, 1, 0, wcd937x_get_swr_port, wcd937x_set_swr_port), - + SOC_SINGLE_EXT("CLSH PA Switch", WCD937X_CLSH, 0, 1, 0, + wcd937x_get_swr_port, wcd937x_set_swr_port), + SOC_SINGLE_EXT("DSD_L Switch", WCD937X_DSD_L, 0, 1, 0, + wcd937x_get_swr_port, wcd937x_set_swr_port), + SOC_SINGLE_EXT("DSD_R Switch", WCD937X_DSD_R, 0, 1, 0, + wcd937x_get_swr_port, wcd937x_set_swr_port), SOC_SINGLE_EXT("ADC1 Switch", WCD937X_ADC1, 1, 1, 0, wcd937x_get_swr_port, wcd937x_set_swr_port), SOC_SINGLE_EXT("ADC2 Switch", WCD937X_ADC2, 1, 1, 0, diff --git a/sound/soc/codecs/wm_adsp_fw_find_test.c b/sound/soc/codecs/wm_adsp_fw_find_test.c index d0c7fb30a95d..ae686dc4fa94 100644 --- a/sound/soc/codecs/wm_adsp_fw_find_test.c +++ b/sound/soc/codecs/wm_adsp_fw_find_test.c @@ -45,6 +45,34 @@ struct wm_adsp_fw_find_test_params { /* Dummy struct firmware to return from wm_adsp_request_firmware_files */ static const struct firmware wm_adsp_find_test_dummy_firmware; +static void wm_adsp_fw_find_test_release_firmware_files_stub(struct wm_adsp_fw_files *fw) +{ + /* + * fw->wmfw.firmware and fw->coeff.firmware allocated by this KUnit + * test are dummies not allocated by the real request_firmware() call + * so they must not be passed to release_firmware(). + * This function replaces wm_adsp_release_firmware_files(). + */ + + if (!fw) + return; + + kfree(fw->wmfw.filename); + kfree(fw->coeff.filename); + + fw->wmfw.firmware = NULL; + fw->coeff.firmware = NULL; + fw->wmfw.filename = NULL; + fw->coeff.filename = NULL; +} + +static void wm_adsp_free_found_fw(struct kunit *test) +{ + struct wm_adsp_fw_find_test *priv = test->priv; + + wm_adsp_fw_find_test_release_firmware_files_stub(&priv->found_fw); +} + /* Simple lookup of a filename in a list of names */ static int wm_adsp_fw_find_test_firmware_request_simple_stub(const struct firmware **firmware, const char *filename, @@ -97,9 +125,14 @@ static void wm_adsp_fw_find_test_pick_file(struct kunit *test) kunit_activate_static_stub(test, wm_adsp_firmware_request, wm_adsp_fw_find_test_firmware_request_simple_stub); + kunit_activate_static_stub(test, + wm_adsp_release_firmware_files, + wm_adsp_fw_find_test_release_firmware_files_stub); ret = wm_adsp_request_firmware_files(dsp, &priv->found_fw); kunit_deactivate_static_stub(test, wm_adsp_firmware_request); + kunit_deactivate_static_stub(test, wm_adsp_release_firmware_files); + KUNIT_EXPECT_EQ_MSG(test, ret, (params->expect_wmfw || params->expect_bin) ? 0 : -ENOENT, "%s\n", priv->searched_fw_files); @@ -173,10 +206,13 @@ static void wm_adsp_fw_find_test_search_order(struct kunit *test) kunit_activate_static_stub(test, wm_adsp_firmware_request, wm_adsp_fw_find_test_firmware_request_stub); + kunit_activate_static_stub(test, + wm_adsp_release_firmware_files, + wm_adsp_fw_find_test_release_firmware_files_stub); wm_adsp_request_firmware_files(dsp, &priv->found_fw); - kunit_deactivate_static_stub(test, wm_adsp_firmware_request); + kunit_deactivate_static_stub(test, wm_adsp_release_firmware_files); KUNIT_EXPECT_STREQ(test, priv->searched_fw_files, params->expected_searches); @@ -201,6 +237,7 @@ static void wm_adsp_fw_find_test_find_firmware_byindex(struct kunit *test) dsp->cs_dsp.name = "cs1234"; dsp->part = "dsp1"; + for (dsp->fw = 0;; dsp->fw++) { fw_name = wm_adsp_get_fwf_name_by_index(dsp->fw); if (!fw_name) @@ -209,14 +246,22 @@ static void wm_adsp_fw_find_test_find_firmware_byindex(struct kunit *test) kunit_activate_static_stub(test, wm_adsp_firmware_request, wm_adsp_fw_find_test_firmware_request_stub); + kunit_activate_static_stub(test, + wm_adsp_release_firmware_files, + wm_adsp_fw_find_test_release_firmware_files_stub); wm_adsp_request_firmware_files(dsp, &priv->found_fw); + kunit_deactivate_static_stub(test, wm_adsp_firmware_request); + kunit_deactivate_static_stub(test, wm_adsp_release_firmware_files); KUNIT_EXPECT_NOT_NULL_MSG(test, strstr(priv->searched_fw_files, fw_name), "fw#%d Did not find '%s' in '%s'\n", dsp->fw, fw_name, priv->searched_fw_files); + + wm_adsp_free_found_fw(test); + memset(priv->searched_fw_files, 0, sizeof(priv->searched_fw_files)); } } @@ -255,15 +300,7 @@ static int wm_adsp_fw_find_test_case_init(struct kunit *test) static void wm_adsp_fw_find_test_case_exit(struct kunit *test) { - struct wm_adsp_fw_find_test *priv = test->priv; - - /* - * priv->found_wmfw_firmware and priv->found_bin_firmware are - * dummies not allocated by the real request_firmware() call they - * must not be passed to release_firmware(). - */ - kfree(priv->found_fw.wmfw.filename); - kfree(priv->found_fw.coeff.filename); + wm_adsp_free_found_fw(test); } static void wm_adsp_fw_find_test_param_desc(const struct wm_adsp_fw_find_test_params *param, diff --git a/sound/soc/fsl/fsl_xcvr.c b/sound/soc/fsl/fsl_xcvr.c index ee16cf681488..6677d3bf36ec 100644 --- a/sound/soc/fsl/fsl_xcvr.c +++ b/sound/soc/fsl/fsl_xcvr.c @@ -228,10 +228,14 @@ static int fsl_xcvr_capds_put(struct snd_kcontrol *kcontrol, { struct snd_soc_dai *dai = snd_kcontrol_chip(kcontrol); struct fsl_xcvr *xcvr = snd_soc_dai_get_drvdata(dai); + int changed; - memcpy(xcvr->cap_ds, ucontrol->value.bytes.data, FSL_XCVR_CAPDS_SIZE); + changed = memcmp(xcvr->cap_ds, ucontrol->value.bytes.data, + sizeof(xcvr->cap_ds)) != 0; + memcpy(xcvr->cap_ds, ucontrol->value.bytes.data, + sizeof(xcvr->cap_ds)); - return 0; + return changed; } static struct snd_kcontrol_new fsl_xcvr_earc_capds_kctl = { @@ -1040,10 +1044,15 @@ static int fsl_xcvr_tx_cs_put(struct snd_kcontrol *kcontrol, { struct snd_soc_dai *dai = snd_kcontrol_chip(kcontrol); struct fsl_xcvr *xcvr = snd_soc_dai_get_drvdata(dai); + int changed; - memcpy(xcvr->tx_iec958.status, ucontrol->value.iec958.status, 24); + changed = memcmp(xcvr->tx_iec958.status, + ucontrol->value.iec958.status, + sizeof(xcvr->tx_iec958.status)) != 0; + memcpy(xcvr->tx_iec958.status, ucontrol->value.iec958.status, + sizeof(xcvr->tx_iec958.status)); - return 0; + return changed; } static struct snd_kcontrol_new fsl_xcvr_rx_ctls[] = { diff --git a/sound/soc/intel/boards/bytcr_wm5102.c b/sound/soc/intel/boards/bytcr_wm5102.c index 4879f79aef29..4aa0cf49b033 100644 --- a/sound/soc/intel/boards/bytcr_wm5102.c +++ b/sound/soc/intel/boards/bytcr_wm5102.c @@ -170,6 +170,7 @@ static int platform_clock_control(struct snd_soc_dapm_widget *w, ret = byt_wm5102_prepare_and_enable_pll1(codec_dai, 48000); if (ret) { dev_err(card->dev, "Error setting codec sysclk: %d\n", ret); + clk_disable_unprepare(priv->mclk); return ret; } } else { diff --git a/sound/soc/sdw_utils/soc_sdw_utils.c b/sound/soc/sdw_utils/soc_sdw_utils.c index 1637cc3f3d59..849ae876d7a4 100644 --- a/sound/soc/sdw_utils/soc_sdw_utils.c +++ b/sound/soc/sdw_utils/soc_sdw_utils.c @@ -1608,6 +1608,7 @@ int asoc_sdw_get_dai_type(u32 type) switch (type) { case SDCA_FUNCTION_TYPE_SMART_AMP: case SDCA_FUNCTION_TYPE_SIMPLE_AMP: + case SDCA_FUNCTION_TYPE_COMPANION_AMP: return SOC_SDW_DAI_TYPE_AMP; case SDCA_FUNCTION_TYPE_SMART_MIC: case SDCA_FUNCTION_TYPE_SIMPLE_MIC: diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c index b3d61d973ce4..8662b422eb80 100644 --- a/sound/soc/sof/intel/hda.c +++ b/sound/soc/sof/intel/hda.c @@ -1412,7 +1412,8 @@ static struct snd_soc_acpi_mach *hda_sdw_machine_select(struct snd_sof_dev *sdev link_mask |= BIT(peripherals->array[i]->bus->link_id); link_num = hweight32(link_mask); - links = devm_kcalloc(sdev->dev, link_num, sizeof(*links), GFP_KERNEL); + /* An empty adr_link is needed to terminate the adr_link loop */ + links = devm_kcalloc(sdev->dev, link_num + 1, sizeof(*links), GFP_KERNEL); if (!links) return NULL; diff --git a/sound/soc/spacemit/k1_i2s.c b/sound/soc/spacemit/k1_i2s.c index 1cb99f1abc7c..5420ca2aefbd 100644 --- a/sound/soc/spacemit/k1_i2s.c +++ b/sound/soc/spacemit/k1_i2s.c @@ -93,8 +93,8 @@ static void spacemit_i2s_init(struct spacemit_i2s_dev *i2s) u32 sscr_val, sspsp_val, ssfcr_val, ssrwt_val; sscr_val = SSCR_TRAIL | SSCR_FRF_PSP; - ssfcr_val = FIELD_PREP(SSFCR_FIELD_TFT, 5) | - FIELD_PREP(SSFCR_FIELD_RFT, 5) | + ssfcr_val = FIELD_PREP(SSFCR_FIELD_TFT, 0xF) | + FIELD_PREP(SSFCR_FIELD_RFT, 0xF) | SSFCR_RSRE | SSFCR_TSRE; ssrwt_val = SSRWT_RWOT; sspsp_val = SSPSP_SFRMP; @@ -106,6 +106,37 @@ static void spacemit_i2s_init(struct spacemit_i2s_dev *i2s) writel(0, i2s->base + SSINTEN); } +static int spacemit_i2s_startup(struct snd_pcm_substream *substream, + struct snd_soc_dai *dai) +{ + struct spacemit_i2s_dev *i2s = snd_soc_dai_get_drvdata(dai); + + switch (i2s->dai_fmt & SND_SOC_DAIFMT_FORMAT_MASK) { + case SND_SOC_DAIFMT_I2S: + snd_pcm_hw_constraint_minmax(substream->runtime, + SNDRV_PCM_HW_PARAM_CHANNELS, + 2, 2); + snd_pcm_hw_constraint_mask64(substream->runtime, + SNDRV_PCM_HW_PARAM_FORMAT, + SNDRV_PCM_FMTBIT_S16_LE); + break; + case SND_SOC_DAIFMT_DSP_A: + case SND_SOC_DAIFMT_DSP_B: + snd_pcm_hw_constraint_minmax(substream->runtime, + SNDRV_PCM_HW_PARAM_CHANNELS, + 1, 1); + snd_pcm_hw_constraint_mask64(substream->runtime, + SNDRV_PCM_HW_PARAM_FORMAT, + SNDRV_PCM_FMTBIT_S32_LE); + break; + default: + dev_dbg(i2s->dev, "unexpected format type"); + return -EINVAL; + } + + return 0; +} + static int spacemit_i2s_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params, struct snd_soc_dai *dai) @@ -117,10 +148,6 @@ static int spacemit_i2s_hw_params(struct snd_pcm_substream *substream, u32 val; int ret; - val = readl(i2s->base + SSCR); - if (val & SSCR_SSE) - return 0; - dma_data = &i2s->playback_dma_data; if (substream->stream == SNDRV_PCM_STREAM_CAPTURE) @@ -157,22 +184,9 @@ static int spacemit_i2s_hw_params(struct snd_pcm_substream *substream, dma_data->maxburst = 32; dma_data->addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES; } - - snd_pcm_hw_constraint_minmax(substream->runtime, - SNDRV_PCM_HW_PARAM_CHANNELS, - 1, 2); - snd_pcm_hw_constraint_mask64(substream->runtime, - SNDRV_PCM_HW_PARAM_FORMAT, - SNDRV_PCM_FMTBIT_S16_LE); break; case SND_SOC_DAIFMT_DSP_A: case SND_SOC_DAIFMT_DSP_B: - snd_pcm_hw_constraint_minmax(substream->runtime, - SNDRV_PCM_HW_PARAM_CHANNELS, - 1, 1); - snd_pcm_hw_constraint_mask64(substream->runtime, - SNDRV_PCM_HW_PARAM_FORMAT, - SNDRV_PCM_FMTBIT_S32_LE); break; default: dev_dbg(i2s->dev, "unexpected format type"); @@ -181,6 +195,9 @@ static int spacemit_i2s_hw_params(struct snd_pcm_substream *substream, } val = readl(i2s->base + SSCR); + if (val & SSCR_SSE) + return 0; + val &= ~SSCR_DW_32BYTE; val |= data_width; writel(val, i2s->base + SSCR); @@ -303,6 +320,7 @@ static int spacemit_i2s_dai_remove(struct snd_soc_dai *dai) static const struct snd_soc_dai_ops spacemit_i2s_dai_ops = { .probe = spacemit_i2s_dai_probe, .remove = spacemit_i2s_dai_remove, + .startup = spacemit_i2s_startup, .hw_params = spacemit_i2s_hw_params, .set_sysclk = spacemit_i2s_set_sysclk, .set_fmt = spacemit_i2s_set_fmt, diff --git a/sound/soc/tegra/Makefile b/sound/soc/tegra/Makefile index 3f396c87802e..1c18ef6971c0 100644 --- a/sound/soc/tegra/Makefile +++ b/sound/soc/tegra/Makefile @@ -1,7 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 # Tegra platform Support snd-soc-tegra-pcm-y := tegra_pcm.o -snd-soc-tegra-utils-y += tegra_asoc_utils.o snd-soc-tegra20-ac97-y := tegra20_ac97.o snd-soc-tegra20-das-y := tegra20_das.o snd-soc-tegra20-i2s-y := tegra20_i2s.o diff --git a/sound/sparc/dbri.c b/sound/sparc/dbri.c index 75f82a92ff44..2f5f62079fa4 100644 --- a/sound/sparc/dbri.c +++ b/sound/sparc/dbri.c @@ -592,6 +592,7 @@ static __u32 reverse_bytes(__u32 b, int len) fallthrough; case 2: b = ((b & 0xaaaaaaaa) >> 1) | ((b & 0x55555555) << 1); + fallthrough; case 1: case 0: break; diff --git a/sound/usb/caiaq/device.c b/sound/usb/caiaq/device.c index 8af0c04041ee..b20aae0caf60 100644 --- a/sound/usb/caiaq/device.c +++ b/sound/usb/caiaq/device.c @@ -366,7 +366,7 @@ static int setup_card(struct snd_usb_caiaqdev *cdev) #ifdef CONFIG_SND_USB_CAIAQ_INPUT ret = snd_usb_caiaq_input_init(cdev); - if (ret < 0) { + if (ret < 0 && ret != -ENODEV) { dev_err(dev, "Unable to set up input system (ret=%d)\n", ret); return ret; } @@ -423,6 +423,7 @@ static int create_card(struct usb_device *usb_dev, cdev = caiaqdev(card); cdev->chip.dev = usb_get_dev(usb_dev); + card->private_free = card_free; cdev->chip.card = card; cdev->chip.usb_id = USB_ID(le16_to_cpu(usb_dev->descriptor.idVendor), le16_to_cpu(usb_dev->descriptor.idProduct)); @@ -511,10 +512,9 @@ static int init_card(struct snd_usb_caiaqdev *cdev) scnprintf(card->longname, sizeof(card->longname), "%s %s (%s)", cdev->vendor_name, cdev->product_name, usbpath); - card->private_free = card_free; err = setup_card(cdev); if (err < 0) - return err; + goto err_kill_urb; return 0; diff --git a/sound/usb/caiaq/input.c b/sound/usb/caiaq/input.c index a9130891bb69..5c70fdf61cc1 100644 --- a/sound/usb/caiaq/input.c +++ b/sound/usb/caiaq/input.c @@ -804,7 +804,7 @@ int snd_usb_caiaq_input_init(struct snd_usb_caiaqdev *cdev) default: /* no input methods supported on this device */ - ret = -EINVAL; + ret = -ENODEV; goto exit_free_idev; } diff --git a/sound/usb/clock.c b/sound/usb/clock.c index 842ba5b801ea..2e0c18e35281 100644 --- a/sound/usb/clock.c +++ b/sound/usb/clock.c @@ -208,11 +208,18 @@ static bool uac_clock_source_is_valid_quirk(struct snd_usb_audio *chip, } /* - * MOTU MicroBook IIc - * Sample rate changes takes more than 2 seconds for this device. Clock - * validity request returns false during that period. + * Quirk for older MOTU AVB / hybrid interfaces + * + * These devices take more than 2 seconds to switch sample rate or + * clock source. During this period the clock validity request + * returns false, causing ALSA to fail prematurely. + * + * Affected models (all use vendor 0x07fd): + * - MicroBook IIc → 0x0004 + * - 1248, 624, 8A, UltraLite AVB, 8M, 16A, ... → 0x0005 */ - if (chip->usb_id == USB_ID(0x07fd, 0x0004)) { + if (chip->usb_id == USB_ID(0x07fd, 0x0004) || /* MicroBook IIc */ + chip->usb_id == USB_ID(0x07fd, 0x0005)) { /* 1248 / 624 / 8A / UltraLite AVB / ... */ count = 0; while ((!ret) && (count < 50)) { diff --git a/sound/usb/midi2.c b/sound/usb/midi2.c index 3546ba926cb3..2785600d2312 100644 --- a/sound/usb/midi2.c +++ b/sound/usb/midi2.c @@ -227,7 +227,7 @@ static void kill_midi_urbs(struct snd_usb_midi2_endpoint *ep, bool suspending) if (!ep) return; if (suspending) - ep->suspended = ep->running; + atomic_set(&ep->suspended, atomic_read(&ep->running)); atomic_set(&ep->running, 0); for (i = 0; i < ep->num_urbs; i++) { if (!ep->urbs[i].urb) @@ -1188,10 +1188,11 @@ void snd_usb_midi_v2_suspend_all(struct snd_usb_audio *chip) static void resume_midi2_endpoint(struct snd_usb_midi2_endpoint *ep) { - ep->running = ep->suspended; - if (ep->direction == STR_IN) + atomic_set(&ep->running, atomic_read(&ep->suspended)); + atomic_set(&ep->suspended, 0); + + if (ep->direction == STR_IN || atomic_read(&ep->running)) submit_io_urbs(ep); - /* FIXME: does it all? */ } void snd_usb_midi_v2_resume_all(struct snd_usb_audio *chip) diff --git a/sound/usb/misc/ua101.c b/sound/usb/misc/ua101.c index 49b3dd8d827d..d129b42eb979 100644 --- a/sound/usb/misc/ua101.c +++ b/sound/usb/misc/ua101.c @@ -974,6 +974,13 @@ static int detect_usb_format(struct ua101 *ua) ua->capture.channels = fmt_capture->bNrChannels; ua->playback.channels = fmt_playback->bNrChannels; + if (!ua->capture.channels || !ua->playback.channels) { + dev_err(&ua->dev->dev, + "invalid channel count: capture %u, playback %u\n", + ua->capture.channels, ua->playback.channels); + return -EINVAL; + } + ua->capture.frame_bytes = fmt_capture->bSubframeSize * ua->capture.channels; ua->playback.frame_bytes = diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 85653112e7f3..5fba456eb4a9 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -1190,6 +1190,16 @@ static void volume_control_quirks(struct usb_mixer_elem_info *cval, cval->res = 1; } break; + + case USB_ID(0x0e6f, 0x024a): /* PDP Riffmaster for PS4 */ + case USB_ID(0x0e6f, 0x0249): /* PDP Riffmaster for PS5 */ + if (!strcmp(kctl->id.name, "PCM Playback Volume")) { + usb_audio_info(chip, + "set volume quirk for PDP Riffmaster for PS4/PS5\n"); + cval->min = -2560; /* Mute under it */ + } + break; + case USB_ID(0x3302, 0x12db): /* MOONDROP Quark2 */ if (!strcmp(kctl->id.name, "PCM Playback Volume")) { usb_audio_info(chip, diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index 803e03d4d77b..4e9cfff4047f 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -2652,6 +2652,9 @@ YAMAHA_DEVICE(0x7010, "UB99"), } } }, + +#endif /* disabled */ + { /* * The AudioBox USB advertises S24_3LE as the only supported format @@ -2700,7 +2703,6 @@ YAMAHA_DEVICE(0x7010, "UB99"), } } }, -#endif /* disabled */ { /* diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 7b803ad58487..17983d9774f8 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -125,7 +125,7 @@ static int add_audio_stream_from_fixed_fmt(struct snd_usb_audio *chip, snd_usb_audioformat_set_sync_ep(chip, fp); - err = snd_usb_add_audio_stream(chip, stream, fp); + err = snd_usb_add_audio_stream(chip, stream, fp, NULL); if (err < 0) return err; @@ -2277,6 +2277,9 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_ALIGN_TRANSFER), DEVICE_FLG(0x05e1, 0x0480, /* Hauppauge Woodbury */ QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER), + DEVICE_FLG(0x05fc, 0x0231, /* JBL Pebbles */ + QUIRK_FLAG_MIXER_PLAYBACK_LINEAR_VOL | QUIRK_FLAG_MIXER_CAPTURE_LINEAR_VOL | + QUIRK_FLAG_GET_SAMPLE_RATE), DEVICE_FLG(0x0624, 0x3d3f, /* AB13X USB Audio */ QUIRK_FLAG_FORCE_IFACE_RESET | QUIRK_FLAG_IFACE_DELAY), DEVICE_FLG(0x0644, 0x8043, /* TEAC UD-501/UD-501V2/UD-503/NT-503 */ @@ -2366,6 +2369,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_IGNORE_CTL_ERROR), DEVICE_FLG(0x152a, 0x880a, /* NeuralDSP Quad Cortex */ 0), /* Doesn't have the vendor quirk which would otherwise apply */ + DEVICE_FLG(0x1532, 0x055e, /* Razer Nommo V2 X */ + QUIRK_FLAG_MIXER_PLAYBACK_MIN_MUTE), DEVICE_FLG(0x154e, 0x1002, /* Denon DCD-1500RE */ QUIRK_FLAG_ITF_USB_DSD_DAC | QUIRK_FLAG_CTL_MSG_DELAY), DEVICE_FLG(0x154e, 0x1003, /* Denon DA-300USB */ @@ -2458,6 +2463,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_GENERIC_IMPLICIT_FB), DEVICE_FLG(0x2b53, 0x0031, /* Fiero SC-01 (firmware v1.1.0) */ QUIRK_FLAG_GENERIC_IMPLICIT_FB), + DEVICE_FLG(0x2b73, 0x0047, /* AlphaTheta EUPHONIA */ + QUIRK_FLAG_PLAYBACK_FIRST | QUIRK_FLAG_GENERIC_IMPLICIT_FB), DEVICE_FLG(0x2d95, 0x8011, /* VIVO USB-C HEADSET */ QUIRK_FLAG_CTL_MSG_DELAY_1M), DEVICE_FLG(0x2d95, 0x8021, /* VIVO USB-C-XE710 HEADSET */ diff --git a/sound/usb/stream.c b/sound/usb/stream.c index 2532bf97e05e..b2c5c8198281 100644 --- a/sound/usb/stream.c +++ b/sound/usb/stream.c @@ -79,7 +79,7 @@ static void snd_usb_audio_pcm_free(struct snd_pcm *pcm) static void snd_usb_init_substream(struct snd_usb_stream *as, int stream, struct audioformat *fp, - struct snd_usb_power_domain *pd) + struct snd_usb_power_domain **pdptr) { struct snd_usb_substream *subs = &as->substream[stream]; @@ -105,10 +105,11 @@ static void snd_usb_init_substream(struct snd_usb_stream *as, if (fp->channels > subs->channels_max) subs->channels_max = fp->channels; - if (pd) { - subs->str_pd = pd; + if (pdptr && *pdptr) { + subs->str_pd = *pdptr; + *pdptr = NULL; /* assigned */ /* Initialize Power Domain to idle status D1 */ - snd_usb_power_domain_set(subs->stream->chip, pd, + snd_usb_power_domain_set(subs->stream->chip, subs->str_pd, UAC3_PD_STATE_D1); } @@ -352,6 +353,8 @@ snd_pcm_chmap_elem *convert_chmap_v3(struct uac3_cluster_header_descriptor if (len < sizeof(*cs_desc)) break; cs_len = le16_to_cpu(cs_desc->wLength); + if (cs_len < sizeof(*cs_desc)) + break; if (len < cs_len) break; cs_type = cs_desc->bSegmentType; @@ -492,11 +495,14 @@ snd_pcm_chmap_elem *convert_chmap_v3(struct uac3_cluster_header_descriptor * if not, create a new pcm stream. note, fp is added to the substream * fmt_list and will be freed on the chip instance release. do not free * fp or do remove it from the substream fmt_list to avoid double-free. + * + * pdptr is optional and can be NULL. When it's non-NULL and the PD gets + * assigned to the stream, *pdptr is cleared to NULL upon return. */ -static int __snd_usb_add_audio_stream(struct snd_usb_audio *chip, - int stream, - struct audioformat *fp, - struct snd_usb_power_domain *pd) +int snd_usb_add_audio_stream(struct snd_usb_audio *chip, + int stream, + struct audioformat *fp, + struct snd_usb_power_domain **pdptr) { struct snd_usb_stream *as; @@ -529,7 +535,7 @@ static int __snd_usb_add_audio_stream(struct snd_usb_audio *chip, err = snd_pcm_new_stream(as->pcm, stream, 1); if (err < 0) return err; - snd_usb_init_substream(as, stream, fp, pd); + snd_usb_init_substream(as, stream, fp, pdptr); return add_chmap(as->pcm, stream, subs); } @@ -558,7 +564,7 @@ static int __snd_usb_add_audio_stream(struct snd_usb_audio *chip, else strscpy(pcm->name, "USB Audio"); - snd_usb_init_substream(as, stream, fp, pd); + snd_usb_init_substream(as, stream, fp, pdptr); /* * Keep using head insertion for M-Audio Audiophile USB (tm) which has a @@ -576,21 +582,6 @@ static int __snd_usb_add_audio_stream(struct snd_usb_audio *chip, return add_chmap(pcm, stream, &as->substream[stream]); } -int snd_usb_add_audio_stream(struct snd_usb_audio *chip, - int stream, - struct audioformat *fp) -{ - return __snd_usb_add_audio_stream(chip, stream, fp, NULL); -} - -static int snd_usb_add_audio_stream_v3(struct snd_usb_audio *chip, - int stream, - struct audioformat *fp, - struct snd_usb_power_domain *pd) -{ - return __snd_usb_add_audio_stream(chip, stream, fp, pd); -} - static int parse_uac_endpoint_attributes(struct snd_usb_audio *chip, struct usb_host_interface *alts, int protocol, int iface_no) @@ -1003,7 +994,7 @@ snd_usb_get_audioformat_uac3(struct snd_usb_audio *chip, * and request Cluster Descriptor */ wLength = le16_to_cpu(hc_header.wLength); - if (wLength < sizeof(cluster)) + if (wLength < sizeof(*cluster)) return NULL; cluster = kzalloc(wLength, GFP_KERNEL); if (!cluster) @@ -1113,8 +1104,7 @@ found_clock: } } - if (pd) - *pd_out = pd; + *pd_out = pd; return fp; } @@ -1129,7 +1119,6 @@ static int __snd_usb_parse_audio_interface(struct snd_usb_audio *chip, struct usb_interface_descriptor *altsd; int i, altno, err, stream; struct audioformat *fp = NULL; - struct snd_usb_power_domain *pd = NULL; bool set_iface_first; int num, protocol; @@ -1171,6 +1160,12 @@ static int __snd_usb_parse_audio_interface(struct snd_usb_audio *chip, if (snd_usb_apply_interface_quirk(chip, iface_no, altno)) continue; + /* pd may be allocated at snd_usb_get_audioformat_uac3() and + * assigned at snd_usb_add_audio_stream(); otherwise it'll be + * freed automatically by cleanup at each loop. + */ + struct snd_usb_power_domain *pd __free(kfree) = NULL; + /* * Roland audio streaming interfaces are marked with protocols * 0/1/2, but are UAC 1 compatible. @@ -1226,23 +1221,16 @@ static int __snd_usb_parse_audio_interface(struct snd_usb_audio *chip, *has_non_pcm = true; if ((fp->fmt_type == UAC_FORMAT_TYPE_I) == non_pcm) { audioformat_free(fp); - kfree(pd); fp = NULL; - pd = NULL; continue; } snd_usb_audioformat_set_sync_ep(chip, fp); dev_dbg(&dev->dev, "%u:%d: add audio endpoint %#x\n", iface_no, altno, fp->endpoint); - if (protocol == UAC_VERSION_3) - err = snd_usb_add_audio_stream_v3(chip, stream, fp, pd); - else - err = snd_usb_add_audio_stream(chip, stream, fp); - + err = snd_usb_add_audio_stream(chip, stream, fp, &pd); if (err < 0) { audioformat_free(fp); - kfree(pd); return err; } diff --git a/sound/usb/stream.h b/sound/usb/stream.h index d92e18d5818f..61b9a133da01 100644 --- a/sound/usb/stream.h +++ b/sound/usb/stream.h @@ -7,7 +7,8 @@ int snd_usb_parse_audio_interface(struct snd_usb_audio *chip, int snd_usb_add_audio_stream(struct snd_usb_audio *chip, int stream, - struct audioformat *fp); + struct audioformat *fp, + struct snd_usb_power_domain **pdptr); #endif /* __USBAUDIO_STREAM_H */ diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c index b68abb9e760b..aad698fe294b 100644 --- a/tools/sched_ext/scx_qmap.bpf.c +++ b/tools/sched_ext/scx_qmap.bpf.c @@ -159,13 +159,7 @@ static s32 pick_direct_dispatch_cpu(struct task_struct *p, s32 prev_cpu) static struct task_ctx *lookup_task_ctx(struct task_struct *p) { - struct task_ctx *tctx; - - if (!(tctx = bpf_task_storage_get(&task_ctx_stor, p, 0, 0))) { - scx_bpf_error("task_ctx lookup failed"); - return NULL; - } - return tctx; + return bpf_task_storage_get(&task_ctx_stor, p, 0, 0); } s32 BPF_STRUCT_OPS(qmap_select_cpu, struct task_struct *p, @@ -175,7 +169,7 @@ s32 BPF_STRUCT_OPS(qmap_select_cpu, struct task_struct *p, s32 cpu; if (!(tctx = lookup_task_ctx(p))) - return -ESRCH; + return prev_cpu; if (p->scx.weight < 2 && !(p->flags & PF_KTHREAD)) return prev_cpu; @@ -540,13 +534,9 @@ void BPF_STRUCT_OPS(qmap_dispatch, s32 cpu, struct task_struct *prev) */ if (prev) { tctx = bpf_task_storage_get(&task_ctx_stor, prev, 0, 0); - if (!tctx) { - scx_bpf_error("task_ctx lookup failed"); - return; - } - - tctx->core_sched_seq = - core_sched_tail_seqs[weight_to_idx(prev->scx.weight)]++; + if (tctx) + tctx->core_sched_seq = + core_sched_tail_seqs[weight_to_idx(prev->scx.weight)]++; } } @@ -584,10 +574,8 @@ static s64 task_qdist(struct task_struct *p) s64 qdist; tctx = bpf_task_storage_get(&task_ctx_stor, p, 0, 0); - if (!tctx) { - scx_bpf_error("task_ctx lookup failed"); + if (!tctx) return 0; - } qdist = tctx->core_sched_seq - core_sched_head_seqs[idx]; diff --git a/tools/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c index feedd5ab7058..0607913a3022 100644 --- a/tools/testing/radix-tree/maple.c +++ b/tools/testing/radix-tree/maple.c @@ -2,7 +2,7 @@ /* * maple_tree.c: Userspace testing for maple tree test-suite * Copyright (c) 2018-2022 Oracle Corporation - * Author: Liam R. Howlett <Liam.Howlett@Oracle.com> + * Author: Liam R. Howlett <liam@infradead.org> * * Any tests that require internal knowledge of the tree or threads and other * difficult to handle in kernel tests. diff --git a/tools/testing/selftests/arm64/gcs/gcs-util.h b/tools/testing/selftests/arm64/gcs/gcs-util.h index c99a6b39ac14..7a81bb07ed4b 100644 --- a/tools/testing/selftests/arm64/gcs/gcs-util.h +++ b/tools/testing/selftests/arm64/gcs/gcs-util.h @@ -18,12 +18,6 @@ #ifndef NT_ARM_GCS #define NT_ARM_GCS 0x410 - -struct user_gcs { - __u64 features_enabled; - __u64 features_locked; - __u64 gcspr_el0; -}; #endif /* Shadow Stack/Guarded Control Stack interface */ diff --git a/tools/testing/selftests/arm64/gcs/libc-gcs.c b/tools/testing/selftests/arm64/gcs/libc-gcs.c index 17b2fabfec38..72e82bfbecc9 100644 --- a/tools/testing/selftests/arm64/gcs/libc-gcs.c +++ b/tools/testing/selftests/arm64/gcs/libc-gcs.c @@ -16,6 +16,7 @@ #include <asm/hwcap.h> #include <asm/mman.h> +#include <asm/ptrace.h> #include <linux/compiler.h> diff --git a/tools/testing/selftests/drivers/net/README.rst b/tools/testing/selftests/drivers/net/README.rst index c8588436c224..c6bed9a985bc 100644 --- a/tools/testing/selftests/drivers/net/README.rst +++ b/tools/testing/selftests/drivers/net/README.rst @@ -211,8 +211,8 @@ Avoid libraries and frameworks Test files should be relatively self contained. The libraries should only include very core or non-trivial code. -It may be tempting to "factor out" the common code, but fight that urge. -Library code increases the barrier of entry, and complexity in general. +It may be tempting to "factor out" the common code to lib/py/, but fight that +urge. Library code increases the barrier of entry, and complexity in general. Avoid mixing test code and boilerplate ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -290,6 +290,12 @@ or:: def test(cfg, mode, protocol): pass +Linters +~~~~~~~ + +We expect clean ``ruff check`` and ``pylint --disable=R``. +The code should be clean, avoid disabling pylint warnings explicitly! + Running tests CI-style ====================== diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile index 85ca4d1ecf9e..82809d5b2478 100644 --- a/tools/testing/selftests/drivers/net/hw/Makefile +++ b/tools/testing/selftests/drivers/net/hw/Makefile @@ -31,6 +31,7 @@ TEST_PROGS = \ hw_stats_l3.sh \ hw_stats_l3_gre.sh \ iou-zcrx.py \ + ipsec_vxlan.py \ irq.py \ loopback.sh \ nic_timestamp.py \ diff --git a/tools/testing/selftests/drivers/net/hw/config b/tools/testing/selftests/drivers/net/hw/config index dd50cb8a7911..8c132ace2b8d 100644 --- a/tools/testing/selftests/drivers/net/hw/config +++ b/tools/testing/selftests/drivers/net/hw/config @@ -3,6 +3,10 @@ CONFIG_FAIL_FUNCTION=y CONFIG_FAULT_INJECTION=y CONFIG_FAULT_INJECTION_DEBUG_FS=y CONFIG_FUNCTION_ERROR_INJECTION=y +CONFIG_INET6_ESP=y +CONFIG_INET6_ESP_OFFLOAD=y +CONFIG_INET_ESP=y +CONFIG_INET_ESP_OFFLOAD=y CONFIG_IO_URING=y CONFIG_IPV6=y CONFIG_IPV6_GRE=y @@ -14,3 +18,4 @@ CONFIG_NETKIT=y CONFIG_NET_SCH_INGRESS=y CONFIG_UDMABUF=y CONFIG_VXLAN=y +CONFIG_XFRM_USER=y diff --git a/tools/testing/selftests/drivers/net/hw/ipsec_vxlan.py b/tools/testing/selftests/drivers/net/hw/ipsec_vxlan.py new file mode 100755 index 000000000000..0740a4d85240 --- /dev/null +++ b/tools/testing/selftests/drivers/net/hw/ipsec_vxlan.py @@ -0,0 +1,204 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +"""Traffic test for VXLAN + IPsec crypto-offload.""" + +import os + +from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_ge +from lib.py import ksft_variants, KsftNamedVariant, KsftSkipEx +from lib.py import CmdExitFailure, NetDrvEpEnv, cmd, defer, ethtool, ip +from lib.py import Iperf3Runner + +# Inner tunnel addresses - TEST-NET-2 (RFC 5737) / doc prefix (RFC 3849) +INNER_V4_LOCAL = "198.51.100.1" +INNER_V4_REMOTE = "198.51.100.2" +INNER_V6_LOCAL = "2001:db8:100::1" +INNER_V6_REMOTE = "2001:db8:100::2" + +# ESP parameters +SPI_OUT = "0x1000" +SPI_IN = "0x1001" +# 128-bit key + 32-bit salt = 20 bytes hex, 128-bit ICV +ESP_AEAD = "aead 'rfc4106(gcm(aes))' 0x" + "01" * 20 + " 128" + + +def xfrm(args, host=None): + """Runs 'ip xfrm' via shell to preserve parentheses in algo names.""" + cmd(f"ip xfrm {args}", shell=True, host=host) + + +def check_xfrm_offload_support(): + """Skips if iproute2 lacks xfrm offload support.""" + out = cmd("ip xfrm state help", fail=False) + if "offload" not in out.stdout + out.stderr: + raise KsftSkipEx("iproute2 too old, missing xfrm offload") + + +def check_esp_hw_offload(cfg): + """Skips if device lacks esp-hw-offload support.""" + check_xfrm_offload_support() + try: + feat = ethtool(f"-k {cfg.ifname}", json=True)[0] + except (CmdExitFailure, IndexError) as e: + raise KsftSkipEx(f"can't query features: {e}") from e + if not feat.get("esp-hw-offload", {}).get("active"): + raise KsftSkipEx("Device does not support esp-hw-offload") + + +def get_tx_drops(cfg): + """Returns TX dropped counter from the physical device.""" + stats = ip("-s -s link show dev " + cfg.ifname, json=True)[0] + return stats["stats64"]["tx"]["dropped"] + + +def setup_vxlan_ipsec(cfg, outer_ipver, inner_ipver): + """Sets up VXLAN tunnel with IPsec transport-mode crypto-offload.""" + vxlan_name = f"vx{os.getpid()}" + local_addr = cfg.addr_v[outer_ipver] + remote_addr = cfg.remote_addr_v[outer_ipver] + + if inner_ipver == "4": + inner_local = f"{INNER_V4_LOCAL}/24" + inner_remote = f"{INNER_V4_REMOTE}/24" + addr_extra = "" + else: + inner_local = f"{INNER_V6_LOCAL}/64" + inner_remote = f"{INNER_V6_REMOTE}/64" + addr_extra = " nodad" + + if outer_ipver == "6": + vxlan_opts = "udp6zerocsumtx udp6zerocsumrx" + else: + vxlan_opts = "noudpcsum" + + # VXLAN tunnel - local side + ip(f"link add {vxlan_name} type vxlan id 100 dstport 4789 {vxlan_opts} " + f"local {local_addr} remote {remote_addr} dev {cfg.ifname}") + defer(ip, f"link del {vxlan_name}") + ip(f"addr add {inner_local} dev {vxlan_name}{addr_extra}") + ip(f"link set {vxlan_name} up") + + # VXLAN tunnel - remote side + ip(f"link add {vxlan_name} type vxlan id 100 dstport 4789 {vxlan_opts} " + f"local {remote_addr} remote {local_addr} dev {cfg.remote_ifname}", + host=cfg.remote) + defer(ip, f"link del {vxlan_name}", host=cfg.remote) + ip(f"addr add {inner_remote} dev {vxlan_name}{addr_extra}", + host=cfg.remote) + ip(f"link set {vxlan_name} up", host=cfg.remote) + + # xfrm state - local outbound SA + xfrm(f"state add src {local_addr} dst {remote_addr} " + f"proto esp spi {SPI_OUT} " + f"{ESP_AEAD} " + f"mode transport offload crypto dev {cfg.ifname} dir out") + defer(xfrm, f"state del src {local_addr} dst {remote_addr} " + f"proto esp spi {SPI_OUT}") + + # xfrm state - local inbound SA + xfrm(f"state add src {remote_addr} dst {local_addr} " + f"proto esp spi {SPI_IN} " + f"{ESP_AEAD} " + f"mode transport offload crypto dev {cfg.ifname} dir in") + defer(xfrm, f"state del src {remote_addr} dst {local_addr} " + f"proto esp spi {SPI_IN}") + + # xfrm state - remote outbound SA (mirror, software crypto) + xfrm(f"state add src {remote_addr} dst {local_addr} " + f"proto esp spi {SPI_IN} " + f"{ESP_AEAD} " + f"mode transport", + host=cfg.remote) + defer(xfrm, f"state del src {remote_addr} dst {local_addr} " + f"proto esp spi {SPI_IN}", host=cfg.remote) + + # xfrm state - remote inbound SA (mirror, software crypto) + xfrm(f"state add src {local_addr} dst {remote_addr} " + f"proto esp spi {SPI_OUT} " + f"{ESP_AEAD} " + f"mode transport", + host=cfg.remote) + defer(xfrm, f"state del src {local_addr} dst {remote_addr} " + f"proto esp spi {SPI_OUT}", host=cfg.remote) + + # xfrm policy - local out + xfrm(f"policy add src {local_addr} dst {remote_addr} " + f"proto udp dport 4789 dir out " + f"tmpl src {local_addr} dst {remote_addr} proto esp mode transport") + defer(xfrm, f"policy del src {local_addr} dst {remote_addr} " + f"proto udp dport 4789 dir out") + + # xfrm policy - local in + xfrm(f"policy add src {remote_addr} dst {local_addr} " + f"proto udp dport 4789 dir in " + f"tmpl src {remote_addr} dst {local_addr} proto esp mode transport") + defer(xfrm, f"policy del src {remote_addr} dst {local_addr} " + f"proto udp dport 4789 dir in") + + # xfrm policy - remote out + xfrm(f"policy add src {remote_addr} dst {local_addr} " + f"proto udp dport 4789 dir out " + f"tmpl src {remote_addr} dst {local_addr} proto esp mode transport", + host=cfg.remote) + defer(xfrm, f"policy del src {remote_addr} dst {local_addr} " + f"proto udp dport 4789 dir out", host=cfg.remote) + + # xfrm policy - remote in + xfrm(f"policy add src {local_addr} dst {remote_addr} " + f"proto udp dport 4789 dir in " + f"tmpl src {local_addr} dst {remote_addr} proto esp mode transport", + host=cfg.remote) + defer(xfrm, f"policy del src {local_addr} dst {remote_addr} " + f"proto udp dport 4789 dir in", host=cfg.remote) + + +def _vxlan_ipsec_variants(): + """Generates outer/inner IP version variants.""" + for outer in ["4", "6"]: + for inner in ["4", "6"]: + yield KsftNamedVariant(f"outer_v{outer}_inner_v{inner}", outer, inner) + + +@ksft_variants(_vxlan_ipsec_variants()) +def test_vxlan_ipsec_crypto_offload(cfg, outer_ipver, inner_ipver): + """Tests VXLAN+IPsec crypto-offload has no TX drops.""" + cfg.require_ipver(outer_ipver) + check_esp_hw_offload(cfg) + + setup_vxlan_ipsec(cfg, outer_ipver, inner_ipver) + + if inner_ipver == "4": + inner_local = INNER_V4_LOCAL + inner_remote = INNER_V4_REMOTE + ping = "ping" + else: + inner_local = INNER_V6_LOCAL + inner_remote = INNER_V6_REMOTE + ping = "ping -6" + + cmd(f"{ping} -c 1 -W 2 {inner_remote}") + + drops_before = get_tx_drops(cfg) + + runner = Iperf3Runner(cfg, server_ip=inner_local, + client_ip=inner_remote) + bw_gbps = runner.measure_bandwidth(reverse=True) + + cfg.wait_hw_stats_settle() + drops_after = get_tx_drops(cfg) + + ksft_eq(drops_after - drops_before, 0, + comment="TX drops during VXLAN+IPsec") + ksft_ge(bw_gbps, 0.1, + comment="Minimum 100Mbps over VXLAN+IPsec") + + +def main(): + """Runs VXLAN+IPsec crypto-offload GSO selftest.""" + with NetDrvEpEnv(__file__, nsim_test=False) as cfg: + ksft_run([test_vxlan_ipsec_crypto_offload], args=(cfg,)) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/drivers/net/lib/py/load.py b/tools/testing/selftests/drivers/net/lib/py/load.py index f181fa2d38fc..e24660e5c27f 100644 --- a/tools/testing/selftests/drivers/net/lib/py/load.py +++ b/tools/testing/selftests/drivers/net/lib/py/load.py @@ -48,7 +48,10 @@ class Iperf3Runner: Starts the iperf3 client with the configured options. """ cmdline = self._build_client(streams, duration, reverse) - return cmd(cmdline, background=background, host=self.env.remote) + kwargs = {"background": background, "host": self.env.remote} + if not background: + kwargs["timeout"] = duration + 5 + return cmd(cmdline, **kwargs) def measure_bandwidth(self, reverse=False): """ diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index 6d809f08ab7b..60838b61a2da 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -450,7 +450,7 @@ static inline __noreturn __printf(1, 2) void ksft_exit_skip(const char *msg, ... */ if (ksft_plan || ksft_test_num()) { ksft_cnt.ksft_xskip++; - printf("ok %u # SKIP ", 1 + ksft_test_num()); + printf("ok %u # SKIP ", ksft_test_num()); } else { printf("1..0 # SKIP "); } diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 75fb016cd190..cfdce9cd252e 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -76,7 +76,7 @@ static inline void __kselftest_memset_safe(void *s, int c, size_t n) memset(s, c, n); } -#define KSELFTEST_PRIO_TEST_F 20000 +#define KSELFTEST_PRIO_TEST 20000 #define KSELFTEST_PRIO_XFAIL 20001 #define TEST_TIMEOUT_DEFAULT 30 @@ -194,7 +194,7 @@ static inline void __kselftest_memset_safe(void *s, int c, size_t n) .fixture = &_fixture_global, \ .termsig = _signal, \ .timeout = TEST_TIMEOUT_DEFAULT, }; \ - static void __attribute__((constructor)) _register_##test_name(void) \ + static void __attribute__((constructor(KSELFTEST_PRIO_TEST))) _register_##test_name(void) \ { \ __register_test(&_##test_name##_object); \ } \ @@ -238,7 +238,7 @@ static inline void __kselftest_memset_safe(void *s, int c, size_t n) FIXTURE_VARIANT(fixture_name); \ static struct __fixture_metadata _##fixture_name##_fixture_object = \ { .name = #fixture_name, }; \ - static void __attribute__((constructor)) \ + static void __attribute__((constructor(KSELFTEST_PRIO_TEST))) \ _register_##fixture_name##_data(void) \ { \ __register_fixture(&_##fixture_name##_fixture_object); \ @@ -364,7 +364,7 @@ static inline void __kselftest_memset_safe(void *s, int c, size_t n) _##fixture_name##_##variant_name##_object = \ { .name = #variant_name, \ .data = &_##fixture_name##_##variant_name##_variant}; \ - static void __attribute__((constructor)) \ + static void __attribute__((constructor(KSELFTEST_PRIO_TEST))) \ _register_##fixture_name##_##variant_name(void) \ { \ __register_fixture_variant(&_##fixture_name##_fixture_object, \ @@ -468,7 +468,7 @@ static inline void __kselftest_memset_safe(void *s, int c, size_t n) fixture_name##_teardown(_metadata, self, variant); \ } \ static struct __test_metadata *_##fixture_name##_##test_name##_object; \ - static void __attribute__((constructor(KSELFTEST_PRIO_TEST_F))) \ + static void __attribute__((constructor(KSELFTEST_PRIO_TEST))) \ _register_##fixture_name##_##test_name(void) \ { \ struct __test_metadata *object = mmap(NULL, sizeof(*object), \ @@ -1323,7 +1323,7 @@ static int test_harness_run(int argc, char **argv) return KSFT_FAIL; } -static void __attribute__((constructor)) __constructor_order_first(void) +static void __attribute__((constructor(KSELFTEST_PRIO_TEST))) __constructor_order_first(void) { __constructor_order_forward = true; } diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c index b058f27b2141..e5bbdb5bbdc3 100644 --- a/tools/testing/selftests/kvm/access_tracking_perf_test.c +++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c @@ -101,15 +101,15 @@ struct test_params { enum vm_mem_backing_src_type backing_src; /* The amount of memory to allocate for each vCPU. */ - uint64_t vcpu_memory_bytes; + u64 vcpu_memory_bytes; /* The number of vCPUs to create in the VM. */ int nr_vcpus; }; -static uint64_t pread_uint64(int fd, const char *filename, uint64_t index) +static u64 pread_u64(int fd, const char *filename, u64 index) { - uint64_t value; + u64 value; off_t offset = index * sizeof(value); TEST_ASSERT(pread(fd, &value, sizeof(value), offset) == sizeof(value), @@ -123,13 +123,13 @@ static uint64_t pread_uint64(int fd, const char *filename, uint64_t index) #define PAGEMAP_PRESENT (1ULL << 63) #define PAGEMAP_PFN_MASK ((1ULL << 55) - 1) -static uint64_t lookup_pfn(int pagemap_fd, struct kvm_vm *vm, uint64_t gva) +static u64 lookup_pfn(int pagemap_fd, struct kvm_vm *vm, gva_t gva) { - uint64_t hva = (uint64_t) addr_gva2hva(vm, gva); - uint64_t entry; - uint64_t pfn; + u64 hva = (u64)addr_gva2hva(vm, gva); + u64 entry; + u64 pfn; - entry = pread_uint64(pagemap_fd, "pagemap", hva / getpagesize()); + entry = pread_u64(pagemap_fd, "pagemap", hva / getpagesize()); if (!(entry & PAGEMAP_PRESENT)) return 0; @@ -139,16 +139,16 @@ static uint64_t lookup_pfn(int pagemap_fd, struct kvm_vm *vm, uint64_t gva) return pfn; } -static bool is_page_idle(int page_idle_fd, uint64_t pfn) +static bool is_page_idle(int page_idle_fd, u64 pfn) { - uint64_t bits = pread_uint64(page_idle_fd, "page_idle", pfn / 64); + u64 bits = pread_u64(page_idle_fd, "page_idle", pfn / 64); return !!((bits >> (pfn % 64)) & 1); } -static void mark_page_idle(int page_idle_fd, uint64_t pfn) +static void mark_page_idle(int page_idle_fd, u64 pfn) { - uint64_t bits = 1ULL << (pfn % 64); + u64 bits = 1ULL << (pfn % 64); TEST_ASSERT(pwrite(page_idle_fd, &bits, 8, 8 * (pfn / 64)) == 8, "Set page_idle bits for PFN 0x%" PRIx64, pfn); @@ -174,11 +174,11 @@ static void pageidle_mark_vcpu_memory_idle(struct kvm_vm *vm, struct memstress_vcpu_args *vcpu_args) { int vcpu_idx = vcpu_args->vcpu_idx; - uint64_t base_gva = vcpu_args->gva; - uint64_t pages = vcpu_args->pages; - uint64_t page; - uint64_t still_idle = 0; - uint64_t no_pfn = 0; + gva_t base_gva = vcpu_args->gva; + u64 pages = vcpu_args->pages; + u64 page; + u64 still_idle = 0; + u64 no_pfn = 0; int page_idle_fd; int pagemap_fd; @@ -193,8 +193,8 @@ static void pageidle_mark_vcpu_memory_idle(struct kvm_vm *vm, TEST_ASSERT(pagemap_fd > 0, "Failed to open pagemap."); for (page = 0; page < pages; page++) { - uint64_t gva = base_gva + page * memstress_args.guest_page_size; - uint64_t pfn = lookup_pfn(pagemap_fd, vm, gva); + gva_t gva = base_gva + page * memstress_args.guest_page_size; + u64 pfn = lookup_pfn(pagemap_fd, vm, gva); if (!pfn) { no_pfn++; @@ -297,10 +297,10 @@ static void lru_gen_mark_memory_idle(struct kvm_vm *vm) lru_gen_last_gen = new_gen; } -static void assert_ucall(struct kvm_vcpu *vcpu, uint64_t expected_ucall) +static void assert_ucall(struct kvm_vcpu *vcpu, u64 expected_ucall) { struct ucall uc; - uint64_t actual_ucall = get_ucall(vcpu, &uc); + u64 actual_ucall = get_ucall(vcpu, &uc); TEST_ASSERT(expected_ucall == actual_ucall, "Guest exited unexpectedly (expected ucall %" PRIu64 @@ -417,7 +417,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) */ test_pages = params->nr_vcpus * params->vcpu_memory_bytes / max(memstress_args.guest_page_size, - (uint64_t)getpagesize()); + (u64)getpagesize()); memstress_start_vcpu_threads(nr_vcpus, vcpu_thread_main); diff --git a/tools/testing/selftests/kvm/arch_timer.c b/tools/testing/selftests/kvm/arch_timer.c index cf8fb67104f1..90c475a61b22 100644 --- a/tools/testing/selftests/kvm/arch_timer.c +++ b/tools/testing/selftests/kvm/arch_timer.c @@ -78,9 +78,9 @@ static void *test_vcpu_run(void *arg) return NULL; } -static uint32_t test_get_pcpu(void) +static u32 test_get_pcpu(void) { - uint32_t pcpu; + u32 pcpu; unsigned int nproc_conf; cpu_set_t online_cpuset; @@ -98,7 +98,7 @@ static uint32_t test_get_pcpu(void) static int test_migrate_vcpu(unsigned int vcpu_idx) { int ret; - uint32_t new_pcpu = test_get_pcpu(); + u32 new_pcpu = test_get_pcpu(); pr_debug("Migrating vCPU: %u to pCPU: %u\n", vcpu_idx, new_pcpu); diff --git a/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c b/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c index 713005b6f508..8a019cbaf4c4 100644 --- a/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c +++ b/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c @@ -66,7 +66,7 @@ static void test_guest_raz(struct kvm_vcpu *vcpu) } } -static uint64_t raz_wi_reg_ids[] = { +static u64 raz_wi_reg_ids[] = { KVM_ARM64_SYS_REG(SYS_ID_PFR0_EL1), KVM_ARM64_SYS_REG(SYS_ID_PFR1_EL1), KVM_ARM64_SYS_REG(SYS_ID_DFR0_EL1), @@ -94,8 +94,8 @@ static void test_user_raz_wi(struct kvm_vcpu *vcpu) int i; for (i = 0; i < ARRAY_SIZE(raz_wi_reg_ids); i++) { - uint64_t reg_id = raz_wi_reg_ids[i]; - uint64_t val; + u64 reg_id = raz_wi_reg_ids[i]; + u64 val; val = vcpu_get_reg(vcpu, reg_id); TEST_ASSERT_EQ(val, 0); @@ -111,7 +111,7 @@ static void test_user_raz_wi(struct kvm_vcpu *vcpu) } } -static uint64_t raz_invariant_reg_ids[] = { +static u64 raz_invariant_reg_ids[] = { KVM_ARM64_SYS_REG(SYS_ID_AFR0_EL1), KVM_ARM64_SYS_REG(sys_reg(3, 0, 0, 3, 3)), KVM_ARM64_SYS_REG(SYS_ID_DFR1_EL1), @@ -123,8 +123,8 @@ static void test_user_raz_invariant(struct kvm_vcpu *vcpu) int i, r; for (i = 0; i < ARRAY_SIZE(raz_invariant_reg_ids); i++) { - uint64_t reg_id = raz_invariant_reg_ids[i]; - uint64_t val; + u64 reg_id = raz_invariant_reg_ids[i]; + u64 val; val = vcpu_get_reg(vcpu, reg_id); TEST_ASSERT_EQ(val, 0); @@ -142,7 +142,7 @@ static void test_user_raz_invariant(struct kvm_vcpu *vcpu) static bool vcpu_aarch64_only(struct kvm_vcpu *vcpu) { - uint64_t val, el0; + u64 val, el0; val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1)); diff --git a/tools/testing/selftests/kvm/arm64/arch_timer.c b/tools/testing/selftests/kvm/arm64/arch_timer.c index d592a4515399..5fa5c0ec2b3e 100644 --- a/tools/testing/selftests/kvm/arm64/arch_timer.c +++ b/tools/testing/selftests/kvm/arm64/arch_timer.c @@ -56,7 +56,7 @@ static void guest_validate_irq(unsigned int intid, struct test_vcpu_shared_data *shared_data) { enum guest_stage stage = shared_data->guest_stage; - uint64_t xcnt = 0, xcnt_diff_us, cval = 0; + u64 xcnt = 0, xcnt_diff_us, cval = 0; unsigned long xctl = 0; unsigned int timer_irq = 0; unsigned int accessor; @@ -105,7 +105,7 @@ static void guest_validate_irq(unsigned int intid, static void guest_irq_handler(struct ex_regs *regs) { unsigned int intid = gic_get_and_ack_irq(); - uint32_t cpu = guest_get_vcpuid(); + u32 cpu = guest_get_vcpuid(); struct test_vcpu_shared_data *shared_data = &vcpu_shared_data[cpu]; guest_validate_irq(intid, shared_data); @@ -116,7 +116,7 @@ static void guest_irq_handler(struct ex_regs *regs) static void guest_run_stage(struct test_vcpu_shared_data *shared_data, enum guest_stage stage) { - uint32_t irq_iter, config_iter; + u32 irq_iter, config_iter; shared_data->guest_stage = stage; shared_data->nr_iter = 0; @@ -140,7 +140,7 @@ static void guest_run_stage(struct test_vcpu_shared_data *shared_data, static void guest_code(void) { - uint32_t cpu = guest_get_vcpuid(); + u32 cpu = guest_get_vcpuid(); struct test_vcpu_shared_data *shared_data = &vcpu_shared_data[cpu]; local_irq_disable(); diff --git a/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c b/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c index 993c9e38e729..f7625eb711d6 100644 --- a/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c +++ b/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c @@ -23,25 +23,25 @@ #include "vgic.h" /* Depends on counter width. */ -static uint64_t CVAL_MAX; +static u64 CVAL_MAX; /* tval is a signed 32-bit int. */ -static const int32_t TVAL_MAX = INT32_MAX; -static const int32_t TVAL_MIN = INT32_MIN; +static const s32 TVAL_MAX = INT32_MAX; +static const s32 TVAL_MIN = INT32_MIN; /* After how much time we say there is no IRQ. */ -static const uint32_t TIMEOUT_NO_IRQ_US = 50000; +static const u32 TIMEOUT_NO_IRQ_US = 50000; /* Counter value to use as the starting one for most tests. Set to CVAL_MAX/2 */ -static uint64_t DEF_CNT; +static u64 DEF_CNT; /* Number of runs. */ -static const uint32_t NR_TEST_ITERS_DEF = 5; +static const u32 NR_TEST_ITERS_DEF = 5; /* Default wait test time in ms. */ -static const uint32_t WAIT_TEST_MS = 10; +static const u32 WAIT_TEST_MS = 10; /* Default "long" wait test time in ms. */ -static const uint32_t LONG_WAIT_TEST_MS = 100; +static const u32 LONG_WAIT_TEST_MS = 100; /* Shared with IRQ handler. */ struct test_vcpu_shared_data { @@ -53,9 +53,9 @@ struct test_args { /* Virtual or physical timer and counter tests. */ enum arch_timer timer; /* Delay used for most timer tests. */ - uint64_t wait_ms; + u64 wait_ms; /* Delay used in the test_long_timer_delays test. */ - uint64_t long_wait_ms; + u64 long_wait_ms; /* Number of iterations. */ int iterations; /* Whether to test the physical timer. */ @@ -82,12 +82,12 @@ enum sync_cmd { NO_USERSPACE_CMD, }; -typedef void (*sleep_method_t)(enum arch_timer timer, uint64_t usec); +typedef void (*sleep_method_t)(enum arch_timer timer, u64 usec); -static void sleep_poll(enum arch_timer timer, uint64_t usec); -static void sleep_sched_poll(enum arch_timer timer, uint64_t usec); -static void sleep_in_userspace(enum arch_timer timer, uint64_t usec); -static void sleep_migrate(enum arch_timer timer, uint64_t usec); +static void sleep_poll(enum arch_timer timer, u64 usec); +static void sleep_sched_poll(enum arch_timer timer, u64 usec); +static void sleep_in_userspace(enum arch_timer timer, u64 usec); +static void sleep_migrate(enum arch_timer timer, u64 usec); sleep_method_t sleep_method[] = { sleep_poll, @@ -115,14 +115,14 @@ enum timer_view { TIMER_TVAL, }; -static void assert_irqs_handled(uint32_t n) +static void assert_irqs_handled(u32 n) { int h = atomic_read(&shared_data.handled); __GUEST_ASSERT(h == n, "Handled %d IRQS but expected %d", h, n); } -static void userspace_cmd(uint64_t cmd) +static void userspace_cmd(u64 cmd) { GUEST_SYNC_ARGS(cmd, 0, 0, 0, 0); } @@ -132,12 +132,12 @@ static void userspace_migrate_vcpu(void) userspace_cmd(USERSPACE_MIGRATE_SELF); } -static void userspace_sleep(uint64_t usecs) +static void userspace_sleep(u64 usecs) { GUEST_SYNC_ARGS(USERSPACE_USLEEP, usecs, 0, 0, 0); } -static void set_counter(enum arch_timer timer, uint64_t counter) +static void set_counter(enum arch_timer timer, u64 counter) { GUEST_SYNC_ARGS(SET_COUNTER_VALUE, counter, timer, 0, 0); } @@ -146,8 +146,8 @@ static void guest_irq_handler(struct ex_regs *regs) { unsigned int intid = gic_get_and_ack_irq(); enum arch_timer timer; - uint64_t cnt, cval; - uint32_t ctl; + u64 cnt, cval; + u32 ctl; bool timer_condition, istatus; if (intid == IAR_SPURIOUS) { @@ -178,8 +178,8 @@ out: gic_set_eoi(intid); } -static void set_cval_irq(enum arch_timer timer, uint64_t cval_cycles, - uint32_t ctl) +static void set_cval_irq(enum arch_timer timer, u64 cval_cycles, + u32 ctl) { atomic_set(&shared_data.handled, 0); atomic_set(&shared_data.spurious, 0); @@ -187,8 +187,8 @@ static void set_cval_irq(enum arch_timer timer, uint64_t cval_cycles, timer_set_ctl(timer, ctl); } -static void set_tval_irq(enum arch_timer timer, uint64_t tval_cycles, - uint32_t ctl) +static void set_tval_irq(enum arch_timer timer, u64 tval_cycles, + u32 ctl) { atomic_set(&shared_data.handled, 0); atomic_set(&shared_data.spurious, 0); @@ -196,7 +196,7 @@ static void set_tval_irq(enum arch_timer timer, uint64_t tval_cycles, timer_set_ctl(timer, ctl); } -static void set_xval_irq(enum arch_timer timer, uint64_t xval, uint32_t ctl, +static void set_xval_irq(enum arch_timer timer, u64 xval, u32 ctl, enum timer_view tv) { switch (tv) { @@ -275,13 +275,13 @@ static void wait_migrate_poll_for_irq(void) * Sleep for usec microseconds by polling in the guest or in * userspace (e.g. userspace_cmd=USERSPACE_SCHEDULE). */ -static void guest_poll(enum arch_timer test_timer, uint64_t usec, +static void guest_poll(enum arch_timer test_timer, u64 usec, enum sync_cmd usp_cmd) { - uint64_t cycles = usec_to_cycles(usec); + u64 cycles = usec_to_cycles(usec); /* Whichever timer we are testing with, sleep with the other. */ enum arch_timer sleep_timer = 1 - test_timer; - uint64_t start = timer_get_cntct(sleep_timer); + u64 start = timer_get_cntct(sleep_timer); while ((timer_get_cntct(sleep_timer) - start) < cycles) { if (usp_cmd == NO_USERSPACE_CMD) @@ -291,22 +291,22 @@ static void guest_poll(enum arch_timer test_timer, uint64_t usec, } } -static void sleep_poll(enum arch_timer timer, uint64_t usec) +static void sleep_poll(enum arch_timer timer, u64 usec) { guest_poll(timer, usec, NO_USERSPACE_CMD); } -static void sleep_sched_poll(enum arch_timer timer, uint64_t usec) +static void sleep_sched_poll(enum arch_timer timer, u64 usec) { guest_poll(timer, usec, USERSPACE_SCHED_YIELD); } -static void sleep_migrate(enum arch_timer timer, uint64_t usec) +static void sleep_migrate(enum arch_timer timer, u64 usec) { guest_poll(timer, usec, USERSPACE_MIGRATE_SELF); } -static void sleep_in_userspace(enum arch_timer timer, uint64_t usec) +static void sleep_in_userspace(enum arch_timer timer, u64 usec) { userspace_sleep(usec); } @@ -315,15 +315,15 @@ static void sleep_in_userspace(enum arch_timer timer, uint64_t usec) * Reset the timer state to some nice values like the counter not being close * to the edge, and the control register masked and disabled. */ -static void reset_timer_state(enum arch_timer timer, uint64_t cnt) +static void reset_timer_state(enum arch_timer timer, u64 cnt) { set_counter(timer, cnt); timer_set_ctl(timer, CTL_IMASK); } -static void test_timer_xval(enum arch_timer timer, uint64_t xval, +static void test_timer_xval(enum arch_timer timer, u64 xval, enum timer_view tv, irq_wait_method_t wm, bool reset_state, - uint64_t reset_cnt) + u64 reset_cnt) { local_irq_disable(); @@ -348,23 +348,23 @@ static void test_timer_xval(enum arch_timer timer, uint64_t xval, * the "runner", like: tools/testing/selftests/kselftest/runner.sh. */ -static void test_timer_cval(enum arch_timer timer, uint64_t cval, +static void test_timer_cval(enum arch_timer timer, u64 cval, irq_wait_method_t wm, bool reset_state, - uint64_t reset_cnt) + u64 reset_cnt) { test_timer_xval(timer, cval, TIMER_CVAL, wm, reset_state, reset_cnt); } -static void test_timer_tval(enum arch_timer timer, int32_t tval, +static void test_timer_tval(enum arch_timer timer, s32 tval, irq_wait_method_t wm, bool reset_state, - uint64_t reset_cnt) + u64 reset_cnt) { - test_timer_xval(timer, (uint64_t) tval, TIMER_TVAL, wm, reset_state, + test_timer_xval(timer, (u64)tval, TIMER_TVAL, wm, reset_state, reset_cnt); } -static void test_xval_check_no_irq(enum arch_timer timer, uint64_t xval, - uint64_t usec, enum timer_view timer_view, +static void test_xval_check_no_irq(enum arch_timer timer, u64 xval, + u64 usec, enum timer_view timer_view, sleep_method_t guest_sleep) { local_irq_disable(); @@ -379,17 +379,17 @@ static void test_xval_check_no_irq(enum arch_timer timer, uint64_t xval, assert_irqs_handled(0); } -static void test_cval_no_irq(enum arch_timer timer, uint64_t cval, - uint64_t usec, sleep_method_t wm) +static void test_cval_no_irq(enum arch_timer timer, u64 cval, + u64 usec, sleep_method_t wm) { test_xval_check_no_irq(timer, cval, usec, TIMER_CVAL, wm); } -static void test_tval_no_irq(enum arch_timer timer, int32_t tval, uint64_t usec, +static void test_tval_no_irq(enum arch_timer timer, s32 tval, u64 usec, sleep_method_t wm) { - /* tval will be cast to an int32_t in test_xval_check_no_irq */ - test_xval_check_no_irq(timer, (uint64_t) tval, usec, TIMER_TVAL, wm); + /* tval will be cast to an s32 in test_xval_check_no_irq */ + test_xval_check_no_irq(timer, (u64)tval, usec, TIMER_TVAL, wm); } /* Test masking/unmasking a timer using the timer mask (not the IRQ mask). */ @@ -463,7 +463,7 @@ static void test_timers_fired_multiple_times(enum arch_timer timer) * timeout for the wait: we use the wfi instruction. */ static void test_reprogramming_timer(enum arch_timer timer, irq_wait_method_t wm, - int32_t delta_1_ms, int32_t delta_2_ms) + s32 delta_1_ms, s32 delta_2_ms) { local_irq_disable(); reset_timer_state(timer, DEF_CNT); @@ -488,7 +488,7 @@ static void test_reprogramming_timer(enum arch_timer timer, irq_wait_method_t wm static void test_reprogram_timers(enum arch_timer timer) { int i; - uint64_t base_wait = test_args.wait_ms; + u64 base_wait = test_args.wait_ms; for (i = 0; i < ARRAY_SIZE(irq_wait_method); i++) { /* @@ -504,8 +504,8 @@ static void test_reprogram_timers(enum arch_timer timer) static void test_basic_functionality(enum arch_timer timer) { - int32_t tval = (int32_t) msec_to_cycles(test_args.wait_ms); - uint64_t cval = DEF_CNT + msec_to_cycles(test_args.wait_ms); + s32 tval = (s32)msec_to_cycles(test_args.wait_ms); + u64 cval = DEF_CNT + msec_to_cycles(test_args.wait_ms); int i; for (i = 0; i < ARRAY_SIZE(irq_wait_method); i++) { @@ -593,7 +593,7 @@ static void test_set_cnt_after_tval_max(enum arch_timer timer, irq_wait_method_t reset_timer_state(timer, DEF_CNT); set_cval_irq(timer, - (uint64_t) TVAL_MAX + + (u64)TVAL_MAX + msec_to_cycles(test_args.wait_ms) / 2, CTL_ENABLE); set_counter(timer, TVAL_MAX); @@ -608,7 +608,7 @@ static void test_set_cnt_after_tval_max(enum arch_timer timer, irq_wait_method_t /* Test timers set for: cval = now + TVAL_MAX + wait_ms / 2 */ static void test_timers_above_tval_max(enum arch_timer timer) { - uint64_t cval; + u64 cval; int i; /* @@ -638,8 +638,8 @@ static void test_timers_above_tval_max(enum arch_timer timer) * sets the counter to cnt_1, the [c|t]val, the counter to cnt_2, and * then waits for an IRQ. */ -static void test_set_cnt_after_xval(enum arch_timer timer, uint64_t cnt_1, - uint64_t xval, uint64_t cnt_2, +static void test_set_cnt_after_xval(enum arch_timer timer, u64 cnt_1, + u64 xval, u64 cnt_2, irq_wait_method_t wm, enum timer_view tv) { local_irq_disable(); @@ -662,8 +662,8 @@ static void test_set_cnt_after_xval(enum arch_timer timer, uint64_t cnt_1, * then waits for an IRQ. */ static void test_set_cnt_after_xval_no_irq(enum arch_timer timer, - uint64_t cnt_1, uint64_t xval, - uint64_t cnt_2, + u64 cnt_1, u64 xval, + u64 cnt_2, sleep_method_t guest_sleep, enum timer_view tv) { @@ -684,31 +684,31 @@ static void test_set_cnt_after_xval_no_irq(enum arch_timer timer, timer_set_ctl(timer, CTL_IMASK); } -static void test_set_cnt_after_tval(enum arch_timer timer, uint64_t cnt_1, - int32_t tval, uint64_t cnt_2, +static void test_set_cnt_after_tval(enum arch_timer timer, u64 cnt_1, + s32 tval, u64 cnt_2, irq_wait_method_t wm) { test_set_cnt_after_xval(timer, cnt_1, tval, cnt_2, wm, TIMER_TVAL); } -static void test_set_cnt_after_cval(enum arch_timer timer, uint64_t cnt_1, - uint64_t cval, uint64_t cnt_2, +static void test_set_cnt_after_cval(enum arch_timer timer, u64 cnt_1, + u64 cval, u64 cnt_2, irq_wait_method_t wm) { test_set_cnt_after_xval(timer, cnt_1, cval, cnt_2, wm, TIMER_CVAL); } static void test_set_cnt_after_tval_no_irq(enum arch_timer timer, - uint64_t cnt_1, int32_t tval, - uint64_t cnt_2, sleep_method_t wm) + u64 cnt_1, s32 tval, + u64 cnt_2, sleep_method_t wm) { test_set_cnt_after_xval_no_irq(timer, cnt_1, tval, cnt_2, wm, TIMER_TVAL); } static void test_set_cnt_after_cval_no_irq(enum arch_timer timer, - uint64_t cnt_1, uint64_t cval, - uint64_t cnt_2, sleep_method_t wm) + u64 cnt_1, u64 cval, + u64 cnt_2, sleep_method_t wm) { test_set_cnt_after_xval_no_irq(timer, cnt_1, cval, cnt_2, wm, TIMER_CVAL); @@ -718,7 +718,7 @@ static void test_set_cnt_after_cval_no_irq(enum arch_timer timer, static void test_move_counters_ahead_of_timers(enum arch_timer timer) { int i; - int32_t tval; + s32 tval; for (i = 0; i < ARRAY_SIZE(irq_wait_method); i++) { irq_wait_method_t wm = irq_wait_method[i]; @@ -730,8 +730,7 @@ static void test_move_counters_ahead_of_timers(enum arch_timer timer) test_set_cnt_after_tval(timer, 0, -1, DEF_CNT + 1, wm); test_set_cnt_after_tval(timer, 0, -1, TVAL_MAX, wm); tval = TVAL_MAX; - test_set_cnt_after_tval(timer, 0, tval, (uint64_t) tval + 1, - wm); + test_set_cnt_after_tval(timer, 0, tval, (u64)tval + 1, wm); } } @@ -754,8 +753,8 @@ static void test_move_counters_behind_timers(enum arch_timer timer) static void test_timers_in_the_past(enum arch_timer timer) { - int32_t tval = -1 * (int32_t) msec_to_cycles(test_args.wait_ms); - uint64_t cval; + s32 tval = -1 * (s32)msec_to_cycles(test_args.wait_ms); + u64 cval; int i; for (i = 0; i < ARRAY_SIZE(irq_wait_method); i++) { @@ -790,8 +789,8 @@ static void test_timers_in_the_past(enum arch_timer timer) static void test_long_timer_delays(enum arch_timer timer) { - int32_t tval = (int32_t) msec_to_cycles(test_args.long_wait_ms); - uint64_t cval = DEF_CNT + msec_to_cycles(test_args.long_wait_ms); + s32 tval = (s32)msec_to_cycles(test_args.long_wait_ms); + u64 cval = DEF_CNT + msec_to_cycles(test_args.long_wait_ms); int i; for (i = 0; i < ARRAY_SIZE(irq_wait_method); i++) { @@ -846,11 +845,11 @@ static void guest_code(enum arch_timer timer) static cpu_set_t default_cpuset; -static uint32_t next_pcpu(void) +static u32 next_pcpu(void) { - uint32_t max = get_nprocs(); - uint32_t cur = sched_getcpu(); - uint32_t next = cur; + u32 max = get_nprocs(); + u32 cur = sched_getcpu(); + u32 next = cur; cpu_set_t cpuset = default_cpuset; TEST_ASSERT(max > 1, "Need at least two physical cpus"); @@ -862,7 +861,7 @@ static uint32_t next_pcpu(void) return next; } -static void kvm_set_cntxct(struct kvm_vcpu *vcpu, uint64_t cnt, +static void kvm_set_cntxct(struct kvm_vcpu *vcpu, u64 cnt, enum arch_timer timer) { if (timer == PHYSICAL) @@ -874,7 +873,7 @@ static void kvm_set_cntxct(struct kvm_vcpu *vcpu, uint64_t cnt, static void handle_sync(struct kvm_vcpu *vcpu, struct ucall *uc) { enum sync_cmd cmd = uc->args[1]; - uint64_t val = uc->args[2]; + u64 val = uc->args[2]; enum arch_timer timer = uc->args[3]; switch (cmd) { @@ -1018,8 +1017,8 @@ static bool parse_args(int argc, char *argv[]) static void set_counter_defaults(void) { - const uint64_t MIN_ROLLOVER_SECS = 40ULL * 365 * 24 * 3600; - uint64_t freq = read_sysreg(CNTFRQ_EL0); + const u64 MIN_ROLLOVER_SECS = 40ULL * 365 * 24 * 3600; + u64 freq = read_sysreg(CNTFRQ_EL0); int width = ilog2(MIN_ROLLOVER_SECS * freq); width = clamp(width, 56, 64); diff --git a/tools/testing/selftests/kvm/arm64/debug-exceptions.c b/tools/testing/selftests/kvm/arm64/debug-exceptions.c index 1d431de8729c..3eb4b1b6682d 100644 --- a/tools/testing/selftests/kvm/arm64/debug-exceptions.c +++ b/tools/testing/selftests/kvm/arm64/debug-exceptions.c @@ -31,14 +31,14 @@ extern unsigned char sw_bp, sw_bp2, hw_bp, hw_bp2, bp_svc, bp_brk, hw_wp, ss_start, hw_bp_ctx; extern unsigned char iter_ss_begin, iter_ss_end; -static volatile uint64_t sw_bp_addr, hw_bp_addr; -static volatile uint64_t wp_addr, wp_data_addr; -static volatile uint64_t svc_addr; -static volatile uint64_t ss_addr[4], ss_idx; -#define PC(v) ((uint64_t)&(v)) +static volatile u64 sw_bp_addr, hw_bp_addr; +static volatile u64 wp_addr, wp_data_addr; +static volatile u64 svc_addr; +static volatile u64 ss_addr[4], ss_idx; +#define PC(v) ((u64)&(v)) #define GEN_DEBUG_WRITE_REG(reg_name) \ -static void write_##reg_name(int num, uint64_t val) \ +static void write_##reg_name(int num, u64 val) \ { \ switch (num) { \ case 0: \ @@ -102,8 +102,8 @@ GEN_DEBUG_WRITE_REG(dbgwvr) static void reset_debug_state(void) { - uint8_t brps, wrps, i; - uint64_t dfr0; + u8 brps, wrps, i; + u64 dfr0; asm volatile("msr daifset, #8"); @@ -140,7 +140,7 @@ static void enable_os_lock(void) static void enable_monitor_debug_exceptions(void) { - uint64_t mdscr; + u64 mdscr; asm volatile("msr daifclr, #8"); @@ -149,9 +149,9 @@ static void enable_monitor_debug_exceptions(void) isb(); } -static void install_wp(uint8_t wpn, uint64_t addr) +static void install_wp(u8 wpn, u64 addr) { - uint32_t wcr; + u32 wcr; wcr = DBGWCR_LEN8 | DBGWCR_RD | DBGWCR_WR | DBGWCR_EL1 | DBGWCR_E; write_dbgwcr(wpn, wcr); @@ -162,9 +162,9 @@ static void install_wp(uint8_t wpn, uint64_t addr) enable_monitor_debug_exceptions(); } -static void install_hw_bp(uint8_t bpn, uint64_t addr) +static void install_hw_bp(u8 bpn, u64 addr) { - uint32_t bcr; + u32 bcr; bcr = DBGBCR_LEN8 | DBGBCR_EXEC | DBGBCR_EL1 | DBGBCR_E; write_dbgbcr(bpn, bcr); @@ -174,11 +174,10 @@ static void install_hw_bp(uint8_t bpn, uint64_t addr) enable_monitor_debug_exceptions(); } -static void install_wp_ctx(uint8_t addr_wp, uint8_t ctx_bp, uint64_t addr, - uint64_t ctx) +static void install_wp_ctx(u8 addr_wp, u8 ctx_bp, u64 addr, u64 ctx) { - uint32_t wcr; - uint64_t ctx_bcr; + u32 wcr; + u64 ctx_bcr; /* Setup a context-aware breakpoint for Linked Context ID Match */ ctx_bcr = DBGBCR_LEN8 | DBGBCR_EXEC | DBGBCR_EL1 | DBGBCR_E | @@ -188,7 +187,7 @@ static void install_wp_ctx(uint8_t addr_wp, uint8_t ctx_bp, uint64_t addr, /* Setup a linked watchpoint (linked to the context-aware breakpoint) */ wcr = DBGWCR_LEN8 | DBGWCR_RD | DBGWCR_WR | DBGWCR_EL1 | DBGWCR_E | - DBGWCR_WT_LINK | ((uint32_t)ctx_bp << DBGWCR_LBN_SHIFT); + DBGWCR_WT_LINK | ((u32)ctx_bp << DBGWCR_LBN_SHIFT); write_dbgwcr(addr_wp, wcr); write_dbgwvr(addr_wp, addr); isb(); @@ -196,10 +195,9 @@ static void install_wp_ctx(uint8_t addr_wp, uint8_t ctx_bp, uint64_t addr, enable_monitor_debug_exceptions(); } -void install_hw_bp_ctx(uint8_t addr_bp, uint8_t ctx_bp, uint64_t addr, - uint64_t ctx) +void install_hw_bp_ctx(u8 addr_bp, u8 ctx_bp, u64 addr, u64 ctx) { - uint32_t addr_bcr, ctx_bcr; + u32 addr_bcr, ctx_bcr; /* Setup a context-aware breakpoint for Linked Context ID Match */ ctx_bcr = DBGBCR_LEN8 | DBGBCR_EXEC | DBGBCR_EL1 | DBGBCR_E | @@ -213,7 +211,7 @@ void install_hw_bp_ctx(uint8_t addr_bp, uint8_t ctx_bp, uint64_t addr, */ addr_bcr = DBGBCR_LEN8 | DBGBCR_EXEC | DBGBCR_EL1 | DBGBCR_E | DBGBCR_BT_ADDR_LINK_CTX | - ((uint32_t)ctx_bp << DBGBCR_LBN_SHIFT); + ((u32)ctx_bp << DBGBCR_LBN_SHIFT); write_dbgbcr(addr_bp, addr_bcr); write_dbgbvr(addr_bp, addr); isb(); @@ -223,7 +221,7 @@ void install_hw_bp_ctx(uint8_t addr_bp, uint8_t ctx_bp, uint64_t addr, static void install_ss(void) { - uint64_t mdscr; + u64 mdscr; asm volatile("msr daifclr, #8"); @@ -234,9 +232,9 @@ static void install_ss(void) static volatile char write_data; -static void guest_code(uint8_t bpn, uint8_t wpn, uint8_t ctx_bpn) +static void guest_code(u8 bpn, u8 wpn, u8 ctx_bpn) { - uint64_t ctx = 0xabcdef; /* a random context number */ + u64 ctx = 0xabcdef; /* a random context number */ /* Software-breakpoint */ reset_debug_state(); @@ -377,8 +375,8 @@ static void guest_svc_handler(struct ex_regs *regs) static void guest_code_ss(int test_cnt) { - uint64_t i; - uint64_t bvr, wvr, w_bvr, w_wvr; + u64 i; + u64 bvr, wvr, w_bvr, w_wvr; for (i = 0; i < test_cnt; i++) { /* Bits [1:0] of dbg{b,w}vr are RES0 */ @@ -416,12 +414,12 @@ static void guest_code_ss(int test_cnt) GUEST_DONE(); } -static int debug_version(uint64_t id_aa64dfr0) +static int debug_version(u64 id_aa64dfr0) { return FIELD_GET(ID_AA64DFR0_EL1_DebugVer, id_aa64dfr0); } -static void test_guest_debug_exceptions(uint8_t bpn, uint8_t wpn, uint8_t ctx_bpn) +static void test_guest_debug_exceptions(u8 bpn, u8 wpn, u8 ctx_bpn) { struct kvm_vcpu *vcpu; struct kvm_vm *vm; @@ -468,8 +466,8 @@ void test_single_step_from_userspace(int test_cnt) struct kvm_vm *vm; struct ucall uc; struct kvm_run *run; - uint64_t pc, cmd; - uint64_t test_pc = 0; + u64 pc, cmd; + u64 test_pc = 0; bool ss_enable = false; struct kvm_guest_debug debug = {}; @@ -506,7 +504,7 @@ void test_single_step_from_userspace(int test_cnt) "Unexpected pc 0x%lx (expected 0x%lx)", pc, test_pc); - if ((pc + 4) == (uint64_t)&iter_ss_end) { + if ((pc + 4) == (u64)&iter_ss_end) { test_pc = 0; debug.control = KVM_GUESTDBG_ENABLE; ss_enable = false; @@ -519,8 +517,8 @@ void test_single_step_from_userspace(int test_cnt) * iter_ss_end, the pc for the next KVM_EXIT_DEBUG should * be the current pc + 4. */ - if ((pc >= (uint64_t)&iter_ss_begin) && - (pc < (uint64_t)&iter_ss_end)) + if ((pc >= (u64)&iter_ss_begin) && + (pc < (u64)&iter_ss_end)) test_pc = pc + 4; else test_pc = 0; @@ -533,9 +531,9 @@ void test_single_step_from_userspace(int test_cnt) * Run debug testing using the various breakpoint#, watchpoint# and * context-aware breakpoint# with the given ID_AA64DFR0_EL1 configuration. */ -void test_guest_debug_exceptions_all(uint64_t aa64dfr0) +void test_guest_debug_exceptions_all(u64 aa64dfr0) { - uint8_t brp_num, wrp_num, ctx_brp_num, normal_brp_num, ctx_brp_base; + u8 brp_num, wrp_num, ctx_brp_num, normal_brp_num, ctx_brp_base; int b, w, c; /* Number of breakpoints */ @@ -580,7 +578,7 @@ int main(int argc, char *argv[]) struct kvm_vm *vm; int opt; int ss_iteration = 10000; - uint64_t aa64dfr0; + u64 aa64dfr0; vm = vm_create_with_one_vcpu(&vcpu, guest_code); aa64dfr0 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64DFR0_EL1)); diff --git a/tools/testing/selftests/kvm/arm64/hypercalls.c b/tools/testing/selftests/kvm/arm64/hypercalls.c index bf038a0371f4..5d96cdf382c4 100644 --- a/tools/testing/selftests/kvm/arm64/hypercalls.c +++ b/tools/testing/selftests/kvm/arm64/hypercalls.c @@ -29,9 +29,9 @@ #define KVM_REG_ARM_VENDOR_HYP_BMAP_2_RESET_VAL 0 struct kvm_fw_reg_info { - uint64_t reg; /* Register definition */ - uint64_t max_feat_bit; /* Bit that represents the upper limit of the feature-map */ - uint64_t reset_val; /* Reset value for the register */ + u64 reg; /* Register definition */ + u64 max_feat_bit; /* Bit that represents the upper limit of the feature-map */ + u64 reset_val; /* Reset value for the register */ }; #define FW_REG_INFO(r) \ @@ -59,8 +59,8 @@ enum test_stage { static int stage = TEST_STAGE_REG_IFACE; struct test_hvc_info { - uint32_t func_id; - uint64_t arg1; + u32 func_id; + u64 arg1; }; #define TEST_HVC_INFO(f, a1) \ @@ -152,9 +152,9 @@ static void guest_code(void) } struct st_time { - uint32_t rev; - uint32_t attr; - uint64_t st_time; + u32 rev; + u32 attr; + u64 st_time; }; #define STEAL_TIME_SIZE ((sizeof(struct st_time) + 63) & ~63) @@ -162,7 +162,7 @@ struct st_time { static void steal_time_init(struct kvm_vcpu *vcpu) { - uint64_t st_ipa = (ulong)ST_GPA_BASE; + u64 st_ipa = (ulong)ST_GPA_BASE; unsigned int gpages; gpages = vm_calc_num_guest_pages(VM_MODE_DEFAULT, STEAL_TIME_SIZE); @@ -174,13 +174,13 @@ static void steal_time_init(struct kvm_vcpu *vcpu) static void test_fw_regs_before_vm_start(struct kvm_vcpu *vcpu) { - uint64_t val; + u64 val; unsigned int i; int ret; for (i = 0; i < ARRAY_SIZE(fw_reg_info); i++) { const struct kvm_fw_reg_info *reg_info = &fw_reg_info[i]; - uint64_t set_val; + u64 set_val; /* First 'read' should be the reset value for the reg */ val = vcpu_get_reg(vcpu, reg_info->reg); @@ -229,7 +229,7 @@ static void test_fw_regs_before_vm_start(struct kvm_vcpu *vcpu) static void test_fw_regs_after_vm_start(struct kvm_vcpu *vcpu) { - uint64_t val; + u64 val; unsigned int i; int ret; diff --git a/tools/testing/selftests/kvm/arm64/idreg-idst.c b/tools/testing/selftests/kvm/arm64/idreg-idst.c index 9ca9f125abdb..a3e84701d814 100644 --- a/tools/testing/selftests/kvm/arm64/idreg-idst.c +++ b/tools/testing/selftests/kvm/arm64/idreg-idst.c @@ -13,7 +13,7 @@ static volatile bool sys64, undef; #define __check_sr_read(r) \ ({ \ - uint64_t val; \ + u64 val; \ \ sys64 = false; \ undef = false; \ @@ -101,7 +101,7 @@ int main(int argc, char *argv[]) { struct kvm_vcpu *vcpu; struct kvm_vm *vm; - uint64_t mmfr2; + u64 mmfr2; test_disable_default_vgic(); diff --git a/tools/testing/selftests/kvm/arm64/no-vgic.c b/tools/testing/selftests/kvm/arm64/no-vgic.c index b14686ef17d1..25b2e3222f68 100644 --- a/tools/testing/selftests/kvm/arm64/no-vgic.c +++ b/tools/testing/selftests/kvm/arm64/no-vgic.c @@ -15,7 +15,7 @@ static volatile bool handled; #define __check_sr_read(r) \ ({ \ - uint64_t val; \ + u64 val; \ \ handled = false; \ dsb(sy); \ @@ -33,7 +33,7 @@ static volatile bool handled; #define __check_gicv5_gicr_op(r) \ ({ \ - uint64_t val; \ + u64 val; \ \ handled = false; \ dsb(sy); \ @@ -82,7 +82,7 @@ static volatile bool handled; static void guest_code_gicv3(void) { - uint64_t val; + u64 val; /* * Check that we advertise that ID_AA64PFR0_EL1.GIC == 0, having @@ -262,7 +262,7 @@ int main(int argc, char *argv[]) struct kvm_vcpu *vcpu; struct kvm_vm *vm; bool has_v3, has_v5; - uint64_t pfr; + u64 pfr; test_disable_default_vgic(); diff --git a/tools/testing/selftests/kvm/arm64/page_fault_test.c b/tools/testing/selftests/kvm/arm64/page_fault_test.c index 4ccbd389d133..6bb3d82906b2 100644 --- a/tools/testing/selftests/kvm/arm64/page_fault_test.c +++ b/tools/testing/selftests/kvm/arm64/page_fault_test.c @@ -23,7 +23,7 @@ #define TEST_PTE_GVA 0xb0000000 #define TEST_DATA 0x0123456789ABCDEF -static uint64_t *guest_test_memory = (uint64_t *)TEST_GVA; +static u64 *guest_test_memory = (u64 *)TEST_GVA; #define CMD_NONE (0) #define CMD_SKIP_TEST (1ULL << 1) @@ -48,7 +48,7 @@ static struct event_cnt { struct test_desc { const char *name; - uint64_t mem_mark_cmd; + u64 mem_mark_cmd; /* Skip the test if any prepare function returns false */ bool (*guest_prepare[PREPARE_FN_NR])(void); void (*guest_test)(void); @@ -59,8 +59,8 @@ struct test_desc { void (*iabt_handler)(struct ex_regs *regs); void (*mmio_handler)(struct kvm_vm *vm, struct kvm_run *run); void (*fail_vcpu_run_handler)(int ret); - uint32_t pt_memslot_flags; - uint32_t data_memslot_flags; + u32 pt_memslot_flags; + u32 data_memslot_flags; bool skip; struct event_cnt expected_events; }; @@ -70,9 +70,9 @@ struct test_params { struct test_desc *test_desc; }; -static inline void flush_tlb_page(uint64_t vaddr) +static inline void flush_tlb_page(gva_t gva) { - uint64_t page = vaddr >> 12; + gva_t page = gva >> 12; dsb(ishst); asm volatile("tlbi vaae1is, %0" :: "r" (page)); @@ -82,7 +82,7 @@ static inline void flush_tlb_page(uint64_t vaddr) static void guest_write64(void) { - uint64_t val; + u64 val; WRITE_ONCE(*guest_test_memory, TEST_DATA); val = READ_ONCE(*guest_test_memory); @@ -92,8 +92,8 @@ static void guest_write64(void) /* Check the system for atomic instructions. */ static bool guest_check_lse(void) { - uint64_t isar0 = read_sysreg(id_aa64isar0_el1); - uint64_t atomic; + u64 isar0 = read_sysreg(id_aa64isar0_el1); + u64 atomic; atomic = FIELD_GET(ID_AA64ISAR0_EL1_ATOMIC, isar0); return atomic >= 2; @@ -101,8 +101,8 @@ static bool guest_check_lse(void) static bool guest_check_dc_zva(void) { - uint64_t dczid = read_sysreg(dczid_el0); - uint64_t dzp = FIELD_GET(DCZID_EL0_DZP, dczid); + u64 dczid = read_sysreg(dczid_el0); + u64 dzp = FIELD_GET(DCZID_EL0_DZP, dczid); return dzp == 0; } @@ -110,7 +110,7 @@ static bool guest_check_dc_zva(void) /* Compare and swap instruction. */ static void guest_cas(void) { - uint64_t val; + u64 val; GUEST_ASSERT(guest_check_lse()); asm volatile(".arch_extension lse\n" @@ -122,7 +122,7 @@ static void guest_cas(void) static void guest_read64(void) { - uint64_t val; + u64 val; val = READ_ONCE(*guest_test_memory); GUEST_ASSERT_EQ(val, 0); @@ -131,7 +131,7 @@ static void guest_read64(void) /* Address translation instruction */ static void guest_at(void) { - uint64_t par; + u64 par; asm volatile("at s1e1r, %0" :: "r" (guest_test_memory)); isb(); @@ -148,7 +148,7 @@ static void guest_at(void) */ static void guest_dc_zva(void) { - uint16_t val; + u16 val; asm volatile("dc zva, %0" :: "r" (guest_test_memory)); dsb(ish); @@ -164,8 +164,8 @@ static void guest_dc_zva(void) */ static void guest_ld_preidx(void) { - uint64_t val; - uint64_t addr = TEST_GVA - 8; + u64 val; + u64 addr = TEST_GVA - 8; /* * This ends up accessing "TEST_GVA + 8 - 8", where "TEST_GVA - 8" is @@ -179,8 +179,8 @@ static void guest_ld_preidx(void) static void guest_st_preidx(void) { - uint64_t val = TEST_DATA; - uint64_t addr = TEST_GVA - 8; + u64 val = TEST_DATA; + u64 addr = TEST_GVA - 8; asm volatile("str %0, [%1, #8]!" : "+r" (val), "+r" (addr)); @@ -191,8 +191,8 @@ static void guest_st_preidx(void) static bool guest_set_ha(void) { - uint64_t mmfr1 = read_sysreg(id_aa64mmfr1_el1); - uint64_t hadbs, tcr; + u64 mmfr1 = read_sysreg(id_aa64mmfr1_el1); + u64 hadbs, tcr; /* Skip if HA is not supported. */ hadbs = FIELD_GET(ID_AA64MMFR1_EL1_HAFDBS, mmfr1); @@ -208,7 +208,7 @@ static bool guest_set_ha(void) static bool guest_clear_pte_af(void) { - *((uint64_t *)TEST_PTE_GVA) &= ~PTE_AF; + *((u64 *)TEST_PTE_GVA) &= ~PTE_AF; flush_tlb_page(TEST_GVA); return true; @@ -217,7 +217,7 @@ static bool guest_clear_pte_af(void) static void guest_check_pte_af(void) { dsb(ish); - GUEST_ASSERT_EQ(*((uint64_t *)TEST_PTE_GVA) & PTE_AF, PTE_AF); + GUEST_ASSERT_EQ(*((u64 *)TEST_PTE_GVA) & PTE_AF, PTE_AF); } static void guest_check_write_in_dirty_log(void) @@ -302,26 +302,26 @@ static void no_iabt_handler(struct ex_regs *regs) static struct uffd_args { char *copy; void *hva; - uint64_t paging_size; + u64 paging_size; } pt_args, data_args; /* Returns true to continue the test, and false if it should be skipped. */ static int uffd_generic_handler(int uffd_mode, int uffd, struct uffd_msg *msg, struct uffd_args *args) { - uint64_t addr = msg->arg.pagefault.address; - uint64_t flags = msg->arg.pagefault.flags; + u64 addr = msg->arg.pagefault.address; + u64 flags = msg->arg.pagefault.flags; struct uffdio_copy copy; int ret; TEST_ASSERT(uffd_mode == UFFDIO_REGISTER_MODE_MISSING, "The only expected UFFD mode is MISSING"); - TEST_ASSERT_EQ(addr, (uint64_t)args->hva); + TEST_ASSERT_EQ(addr, (u64)args->hva); pr_debug("uffd fault: addr=%p write=%d\n", (void *)addr, !!(flags & UFFD_PAGEFAULT_FLAG_WRITE)); - copy.src = (uint64_t)args->copy; + copy.src = (u64)args->copy; copy.dst = addr; copy.len = args->paging_size; copy.mode = 0; @@ -407,7 +407,7 @@ static bool punch_hole_in_backing_store(struct kvm_vm *vm, struct userspace_mem_region *region) { void *hva = (void *)region->region.userspace_addr; - uint64_t paging_size = region->region.memory_size; + u64 paging_size = region->region.memory_size; int ret, fd = region->fd; if (fd != -1) { @@ -438,7 +438,7 @@ static void mmio_on_test_gpa_handler(struct kvm_vm *vm, struct kvm_run *run) static void mmio_no_handler(struct kvm_vm *vm, struct kvm_run *run) { - uint64_t data; + u64 data; memcpy(&data, run->mmio.data, sizeof(data)); pr_debug("addr=%lld len=%d w=%d data=%lx\n", @@ -449,11 +449,11 @@ static void mmio_no_handler(struct kvm_vm *vm, struct kvm_run *run) static bool check_write_in_dirty_log(struct kvm_vm *vm, struct userspace_mem_region *region, - uint64_t host_pg_nr) + u64 host_pg_nr) { unsigned long *bmap; bool first_page_dirty; - uint64_t size = region->region.memory_size; + u64 size = region->region.memory_size; /* getpage_size() is not always equal to vm->page_size */ bmap = bitmap_zalloc(size / getpagesize()); @@ -468,7 +468,7 @@ static bool handle_cmd(struct kvm_vm *vm, int cmd) { struct userspace_mem_region *data_region, *pt_region; bool continue_test = true; - uint64_t pte_gpa, pte_pg; + u64 pte_gpa, pte_pg; data_region = vm_get_mem_region(vm, MEM_REGION_TEST_DATA); pt_region = vm_get_mem_region(vm, MEM_REGION_PT); @@ -510,7 +510,7 @@ void fail_vcpu_run_mmio_no_syndrome_handler(int ret) events.fail_vcpu_runs += 1; } -typedef uint32_t aarch64_insn_t; +typedef u32 aarch64_insn_t; extern aarch64_insn_t __exec_test[2]; noinline void __return_0x77(void) @@ -525,7 +525,7 @@ noinline void __return_0x77(void) */ static void load_exec_code_for_test(struct kvm_vm *vm) { - uint64_t *code; + u64 *code; struct userspace_mem_region *region; void *hva; @@ -552,7 +552,7 @@ static void setup_abort_handlers(struct kvm_vm *vm, struct kvm_vcpu *vcpu, static void setup_gva_maps(struct kvm_vm *vm) { struct userspace_mem_region *region; - uint64_t pte_gpa; + u64 pte_gpa; region = vm_get_mem_region(vm, MEM_REGION_TEST_DATA); /* Map TEST_GVA first. This will install a new PTE. */ @@ -574,12 +574,12 @@ enum pf_test_memslots { */ static void setup_memslots(struct kvm_vm *vm, struct test_params *p) { - uint64_t backing_src_pagesz = get_backing_src_pagesz(p->src_type); - uint64_t guest_page_size = vm->page_size; - uint64_t max_gfn = vm_compute_max_gfn(vm); + u64 backing_src_pagesz = get_backing_src_pagesz(p->src_type); + u64 guest_page_size = vm->page_size; + u64 max_gfn = vm_compute_max_gfn(vm); /* Enough for 2M of code when using 4K guest pages. */ - uint64_t code_npages = 512; - uint64_t pt_size, data_size, data_gpa; + u64 code_npages = 512; + u64 pt_size, data_size, data_gpa; /* * This test requires 1 pgd, 2 pud, 4 pmd, and 6 pte pages when using diff --git a/tools/testing/selftests/kvm/arm64/psci_test.c b/tools/testing/selftests/kvm/arm64/psci_test.c index 98e49f710aef..e775faf20868 100644 --- a/tools/testing/selftests/kvm/arm64/psci_test.c +++ b/tools/testing/selftests/kvm/arm64/psci_test.c @@ -22,8 +22,7 @@ #define CPU_ON_ENTRY_ADDR 0xfeedf00dul #define CPU_ON_CONTEXT_ID 0xdeadc0deul -static uint64_t psci_cpu_on(uint64_t target_cpu, uint64_t entry_addr, - uint64_t context_id) +static u64 psci_cpu_on(u64 target_cpu, u64 entry_addr, u64 context_id) { struct arm_smccc_res res; @@ -33,8 +32,7 @@ static uint64_t psci_cpu_on(uint64_t target_cpu, uint64_t entry_addr, return res.a0; } -static uint64_t psci_affinity_info(uint64_t target_affinity, - uint64_t lowest_affinity_level) +static u64 psci_affinity_info(u64 target_affinity, u64 lowest_affinity_level) { struct arm_smccc_res res; @@ -44,7 +42,7 @@ static uint64_t psci_affinity_info(uint64_t target_affinity, return res.a0; } -static uint64_t psci_system_suspend(uint64_t entry_addr, uint64_t context_id) +static u64 psci_system_suspend(u64 entry_addr, u64 context_id) { struct arm_smccc_res res; @@ -54,7 +52,7 @@ static uint64_t psci_system_suspend(uint64_t entry_addr, uint64_t context_id) return res.a0; } -static uint64_t psci_system_off2(uint64_t type, uint64_t cookie) +static u64 psci_system_off2(u64 type, u64 cookie) { struct arm_smccc_res res; @@ -63,7 +61,7 @@ static uint64_t psci_system_off2(uint64_t type, uint64_t cookie) return res.a0; } -static uint64_t psci_features(uint32_t func_id) +static u64 psci_features(u32 func_id) { struct arm_smccc_res res; @@ -110,7 +108,7 @@ static void enter_guest(struct kvm_vcpu *vcpu) static void assert_vcpu_reset(struct kvm_vcpu *vcpu) { - uint64_t obs_pc, obs_x0; + u64 obs_pc, obs_x0; obs_pc = vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc)); obs_x0 = vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.regs[0])); @@ -123,9 +121,9 @@ static void assert_vcpu_reset(struct kvm_vcpu *vcpu) obs_x0, CPU_ON_CONTEXT_ID); } -static void guest_test_cpu_on(uint64_t target_cpu) +static void guest_test_cpu_on(u64 target_cpu) { - uint64_t target_state; + u64 target_state; GUEST_ASSERT(!psci_cpu_on(target_cpu, CPU_ON_ENTRY_ADDR, CPU_ON_CONTEXT_ID)); @@ -142,7 +140,7 @@ static void guest_test_cpu_on(uint64_t target_cpu) static void host_test_cpu_on(void) { struct kvm_vcpu *source, *target; - uint64_t target_mpidr; + u64 target_mpidr; struct kvm_vm *vm; struct ucall uc; @@ -166,7 +164,7 @@ static void host_test_cpu_on(void) static void guest_test_system_suspend(void) { - uint64_t ret; + u64 ret; /* assert that SYSTEM_SUSPEND is discoverable */ GUEST_ASSERT(!psci_features(PSCI_1_0_FN_SYSTEM_SUSPEND)); @@ -200,7 +198,7 @@ static void host_test_system_suspend(void) static void guest_test_system_off2(void) { - uint64_t ret; + u64 ret; /* assert that SYSTEM_OFF2 is discoverable */ GUEST_ASSERT(psci_features(PSCI_1_3_FN_SYSTEM_OFF2) & @@ -238,7 +236,7 @@ static void host_test_system_off2(void) { struct kvm_vcpu *source, *target; struct kvm_mp_state mps; - uint64_t psci_version = 0; + u64 psci_version = 0; int nr_shutdowns = 0; struct kvm_run *run; struct ucall uc; diff --git a/tools/testing/selftests/kvm/arm64/sea_to_user.c b/tools/testing/selftests/kvm/arm64/sea_to_user.c index 573dd790aeb8..e96d8982c28b 100644 --- a/tools/testing/selftests/kvm/arm64/sea_to_user.c +++ b/tools/testing/selftests/kvm/arm64/sea_to_user.c @@ -51,18 +51,16 @@ #define EINJ_OFFSET 0x01234badUL #define EINJ_GVA ((START_GVA) + (EINJ_OFFSET)) -static vm_paddr_t einj_gpa; +static gpa_t einj_gpa; static void *einj_hva; -static uint64_t einj_hpa; +static u64 einj_hpa; static bool far_invalid; -static uint64_t translate_to_host_paddr(unsigned long vaddr) +static u64 translate_hva_to_hpa(unsigned long hva) { - uint64_t pinfo; - int64_t offset = vaddr / getpagesize() * sizeof(pinfo); + u64 pinfo; + s64 offset = hva / getpagesize() * sizeof(pinfo); int fd; - uint64_t page_addr; - uint64_t paddr; fd = open("/proc/self/pagemap", O_RDONLY); if (fd < 0) @@ -77,12 +75,11 @@ static uint64_t translate_to_host_paddr(unsigned long vaddr) if ((pinfo & PAGE_PRESENT) == 0) ksft_exit_fail_perror("Page not present"); - page_addr = (pinfo & PAGE_PHYSICAL) << MIN_PAGE_SHIFT; - paddr = page_addr + (vaddr & (getpagesize() - 1)); - return paddr; + return ((pinfo & PAGE_PHYSICAL) << MIN_PAGE_SHIFT) + + (hva & (getpagesize() - 1)); } -static void write_einj_entry(const char *einj_path, uint64_t val) +static void write_einj_entry(const char *einj_path, u64 val) { char cmd[256] = {0}; FILE *cmdfile = NULL; @@ -96,7 +93,7 @@ static void write_einj_entry(const char *einj_path, uint64_t val) ksft_exit_fail_perror("Failed to write EINJ entry"); } -static void inject_uer(uint64_t paddr) +static void inject_uer(u64 hpa) { if (access("/sys/firmware/acpi/tables/EINJ", R_OK) == -1) ksft_test_result_skip("EINJ table no available in firmware"); @@ -106,7 +103,7 @@ static void inject_uer(uint64_t paddr) write_einj_entry(EINJ_ETYPE, ERROR_TYPE_MEMORY_UER); write_einj_entry(EINJ_FLAGS, MASK_MEMORY_UER); - write_einj_entry(EINJ_ADDR, paddr); + write_einj_entry(EINJ_ADDR, hpa); write_einj_entry(EINJ_MASK, ~0x0UL); write_einj_entry(EINJ_NOTRIGGER, 1); write_einj_entry(EINJ_DOIT, 1); @@ -145,10 +142,10 @@ static void setup_sigbus_handler(void) static void guest_code(void) { - uint64_t guest_data; + u64 guest_data; /* Consumes error will cause a SEA. */ - guest_data = *(uint64_t *)EINJ_GVA; + guest_data = *(u64 *)EINJ_GVA; GUEST_FAIL("Poison not protected by SEA: gva=%#lx, guest_data=%#lx\n", EINJ_GVA, guest_data); @@ -253,8 +250,8 @@ static struct kvm_vm *vm_create_with_sea_handler(struct kvm_vcpu **vcpu) size_t backing_page_size; size_t guest_page_size; size_t alignment; - uint64_t num_guest_pages; - vm_paddr_t start_gpa; + u64 num_guest_pages; + gpa_t start_gpa; enum vm_mem_backing_src_type src_type = VM_MEM_SRC_ANONYMOUS_HUGETLB_1GB; struct kvm_vm *vm; @@ -278,7 +275,7 @@ static struct kvm_vm *vm_create_with_sea_handler(struct kvm_vcpu **vcpu) vm_userspace_mem_region_add( /*vm=*/vm, /*src_type=*/src_type, - /*guest_paddr=*/start_gpa, + /*gpa=*/start_gpa, /*slot=*/1, /*npages=*/num_guest_pages, /*flags=*/0); @@ -292,18 +289,18 @@ static struct kvm_vm *vm_create_with_sea_handler(struct kvm_vcpu **vcpu) static void vm_inject_memory_uer(struct kvm_vm *vm) { - uint64_t guest_data; + u64 guest_data; einj_gpa = addr_gva2gpa(vm, EINJ_GVA); einj_hva = addr_gva2hva(vm, EINJ_GVA); /* Populate certain data before injecting UER. */ - *(uint64_t *)einj_hva = 0xBAADCAFE; - guest_data = *(uint64_t *)einj_hva; + *(u64 *)einj_hva = 0xBAADCAFE; + guest_data = *(u64 *)einj_hva; ksft_print_msg("Before EINJect: data=%#lx\n", guest_data); - einj_hpa = translate_to_host_paddr((unsigned long)einj_hva); + einj_hpa = translate_hva_to_hpa((unsigned long)einj_hva); ksft_print_msg("EINJ_GVA=%#lx, einj_gpa=%#lx, einj_hva=%p, einj_hpa=%#lx\n", EINJ_GVA, einj_gpa, einj_hva, einj_hpa); diff --git a/tools/testing/selftests/kvm/arm64/set_id_regs.c b/tools/testing/selftests/kvm/arm64/set_id_regs.c index 3a7e5fe9ae7a..7429a1055df5 100644 --- a/tools/testing/selftests/kvm/arm64/set_id_regs.c +++ b/tools/testing/selftests/kvm/arm64/set_id_regs.c @@ -30,20 +30,20 @@ struct reg_ftr_bits { char *name; bool sign; enum ftr_type type; - uint8_t shift; - uint64_t mask; + u8 shift; + u64 mask; /* * For FTR_EXACT, safe_val is used as the exact safe value. * For FTR_LOWER_SAFE, safe_val is used as the minimal safe value. */ - int64_t safe_val; + s64 safe_val; /* Allowed to be changed by the host after run */ bool mutable; }; struct test_feature_reg { - uint32_t reg; + u32 reg; const struct reg_ftr_bits *ftr_bits; }; @@ -275,9 +275,9 @@ static void guest_code(void) } /* Return a safe value to a given ftr_bits an ftr value */ -uint64_t get_safe_value(const struct reg_ftr_bits *ftr_bits, uint64_t ftr) +u64 get_safe_value(const struct reg_ftr_bits *ftr_bits, u64 ftr) { - uint64_t ftr_max = ftr_bits->mask >> ftr_bits->shift; + u64 ftr_max = ftr_bits->mask >> ftr_bits->shift; TEST_ASSERT(ftr_max > 1, "This test doesn't support single bit features"); @@ -329,16 +329,16 @@ uint64_t get_safe_value(const struct reg_ftr_bits *ftr_bits, uint64_t ftr) } /* Return an invalid value to a given ftr_bits an ftr value */ -uint64_t get_invalid_value(const struct reg_ftr_bits *ftr_bits, uint64_t ftr) +u64 get_invalid_value(const struct reg_ftr_bits *ftr_bits, u64 ftr) { - uint64_t ftr_max = ftr_bits->mask >> ftr_bits->shift; + u64 ftr_max = ftr_bits->mask >> ftr_bits->shift; TEST_ASSERT(ftr_max > 1, "This test doesn't support single bit features"); if (ftr_bits->sign == FTR_UNSIGNED) { switch (ftr_bits->type) { case FTR_EXACT: - ftr = max((uint64_t)ftr_bits->safe_val + 1, ftr + 1); + ftr = max((u64)ftr_bits->safe_val + 1, ftr + 1); break; case FTR_LOWER_SAFE: ftr++; @@ -358,7 +358,7 @@ uint64_t get_invalid_value(const struct reg_ftr_bits *ftr_bits, uint64_t ftr) } else if (ftr != ftr_max) { switch (ftr_bits->type) { case FTR_EXACT: - ftr = max((uint64_t)ftr_bits->safe_val + 1, ftr + 1); + ftr = max((u64)ftr_bits->safe_val + 1, ftr + 1); break; case FTR_LOWER_SAFE: ftr++; @@ -382,12 +382,12 @@ uint64_t get_invalid_value(const struct reg_ftr_bits *ftr_bits, uint64_t ftr) return ftr; } -static uint64_t test_reg_set_success(struct kvm_vcpu *vcpu, uint64_t reg, - const struct reg_ftr_bits *ftr_bits) +static u64 test_reg_set_success(struct kvm_vcpu *vcpu, u64 reg, + const struct reg_ftr_bits *ftr_bits) { - uint8_t shift = ftr_bits->shift; - uint64_t mask = ftr_bits->mask; - uint64_t val, new_val, ftr; + u8 shift = ftr_bits->shift; + u64 mask = ftr_bits->mask; + u64 val, new_val, ftr; val = vcpu_get_reg(vcpu, reg); ftr = (val & mask) >> shift; @@ -405,12 +405,12 @@ static uint64_t test_reg_set_success(struct kvm_vcpu *vcpu, uint64_t reg, return new_val; } -static void test_reg_set_fail(struct kvm_vcpu *vcpu, uint64_t reg, +static void test_reg_set_fail(struct kvm_vcpu *vcpu, u64 reg, const struct reg_ftr_bits *ftr_bits) { - uint8_t shift = ftr_bits->shift; - uint64_t mask = ftr_bits->mask; - uint64_t val, old_val, ftr; + u8 shift = ftr_bits->shift; + u64 mask = ftr_bits->mask; + u64 val, old_val, ftr; int r; val = vcpu_get_reg(vcpu, reg); @@ -431,7 +431,7 @@ static void test_reg_set_fail(struct kvm_vcpu *vcpu, uint64_t reg, TEST_ASSERT_EQ(val, old_val); } -static uint64_t test_reg_vals[KVM_ARM_FEATURE_ID_RANGE_SIZE]; +static u64 test_reg_vals[KVM_ARM_FEATURE_ID_RANGE_SIZE]; #define encoding_to_range_idx(encoding) \ KVM_ARM_FEATURE_ID_RANGE_IDX(sys_reg_Op0(encoding), sys_reg_Op1(encoding), \ @@ -441,7 +441,7 @@ static uint64_t test_reg_vals[KVM_ARM_FEATURE_ID_RANGE_SIZE]; static void test_vm_ftr_id_regs(struct kvm_vcpu *vcpu, bool aarch64_only) { - uint64_t masks[KVM_ARM_FEATURE_ID_RANGE_SIZE]; + u64 masks[KVM_ARM_FEATURE_ID_RANGE_SIZE]; struct reg_mask_range range = { .addr = (__u64)masks, }; @@ -458,8 +458,8 @@ static void test_vm_ftr_id_regs(struct kvm_vcpu *vcpu, bool aarch64_only) for (int i = 0; i < ARRAY_SIZE(test_regs); i++) { const struct reg_ftr_bits *ftr_bits = test_regs[i].ftr_bits; - uint32_t reg_id = test_regs[i].reg; - uint64_t reg = KVM_ARM64_SYS_REG(reg_id); + u32 reg_id = test_regs[i].reg; + u64 reg = KVM_ARM64_SYS_REG(reg_id); int idx; /* Get the index to masks array for the idreg */ @@ -489,11 +489,11 @@ static void test_vm_ftr_id_regs(struct kvm_vcpu *vcpu, bool aarch64_only) #define MPAM_IDREG_TEST 6 static void test_user_set_mpam_reg(struct kvm_vcpu *vcpu) { - uint64_t masks[KVM_ARM_FEATURE_ID_RANGE_SIZE]; + u64 masks[KVM_ARM_FEATURE_ID_RANGE_SIZE]; struct reg_mask_range range = { .addr = (__u64)masks, }; - uint64_t val; + u64 val; int idx, err; /* @@ -584,13 +584,13 @@ static void test_user_set_mpam_reg(struct kvm_vcpu *vcpu) #define MTE_IDREG_TEST 1 static void test_user_set_mte_reg(struct kvm_vcpu *vcpu) { - uint64_t masks[KVM_ARM_FEATURE_ID_RANGE_SIZE]; + u64 masks[KVM_ARM_FEATURE_ID_RANGE_SIZE]; struct reg_mask_range range = { .addr = (__u64)masks, }; - uint64_t val; - uint64_t mte; - uint64_t mte_frac; + u64 val; + u64 mte; + u64 mte_frac; int idx, err; val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR1_EL1)); @@ -644,7 +644,7 @@ static void test_user_set_mte_reg(struct kvm_vcpu *vcpu) ksft_test_result_pass("ID_AA64PFR1_EL1.MTE_frac no longer 0xF\n"); } -static uint64_t reset_mutable_bits(uint32_t id, uint64_t val) +static u64 reset_mutable_bits(u32 id, u64 val) { struct test_feature_reg *reg = NULL; @@ -674,7 +674,7 @@ static void test_guest_reg_read(struct kvm_vcpu *vcpu) struct ucall uc; while (!done) { - uint64_t val; + u64 val; vcpu_run(vcpu); @@ -707,7 +707,7 @@ static void test_guest_reg_read(struct kvm_vcpu *vcpu) static void test_clidr(struct kvm_vcpu *vcpu) { - uint64_t clidr; + u64 clidr; int level; clidr = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_CLIDR_EL1)); @@ -772,10 +772,10 @@ static void test_vcpu_non_ftr_id_regs(struct kvm_vcpu *vcpu) ksft_test_result_pass("%s\n", __func__); } -static void test_assert_id_reg_unchanged(struct kvm_vcpu *vcpu, uint32_t encoding) +static void test_assert_id_reg_unchanged(struct kvm_vcpu *vcpu, u32 encoding) { size_t idx = encoding_to_range_idx(encoding); - uint64_t observed; + u64 observed; observed = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(encoding)); TEST_ASSERT_EQ(reset_mutable_bits(encoding, test_reg_vals[idx]), @@ -808,7 +808,7 @@ int main(void) struct kvm_vcpu *vcpu; struct kvm_vm *vm; bool aarch64_only; - uint64_t val, el0; + u64 val, el0; int test_cnt, i, j; TEST_REQUIRE(kvm_has_cap(KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES)); diff --git a/tools/testing/selftests/kvm/arm64/smccc_filter.c b/tools/testing/selftests/kvm/arm64/smccc_filter.c index 1763b9d45400..21e41880261b 100644 --- a/tools/testing/selftests/kvm/arm64/smccc_filter.c +++ b/tools/testing/selftests/kvm/arm64/smccc_filter.c @@ -37,7 +37,7 @@ static bool test_runs_at_el2(void) for (conduit = test_runs_at_el2() ? SMC_INSN : HVC_INSN; \ conduit <= SMC_INSN; conduit++) -static void guest_main(uint32_t func_id, enum smccc_conduit conduit) +static void guest_main(u32 func_id, enum smccc_conduit conduit) { struct arm_smccc_res res; @@ -49,7 +49,7 @@ static void guest_main(uint32_t func_id, enum smccc_conduit conduit) GUEST_SYNC(res.a0); } -static int __set_smccc_filter(struct kvm_vm *vm, uint32_t start, uint32_t nr_functions, +static int __set_smccc_filter(struct kvm_vm *vm, u32 start, u32 nr_functions, enum kvm_smccc_filter_action action) { struct kvm_smccc_filter filter = { @@ -62,7 +62,7 @@ static int __set_smccc_filter(struct kvm_vm *vm, uint32_t start, uint32_t nr_fun KVM_ARM_VM_SMCCC_FILTER, &filter); } -static void set_smccc_filter(struct kvm_vm *vm, uint32_t start, uint32_t nr_functions, +static void set_smccc_filter(struct kvm_vm *vm, u32 start, u32 nr_functions, enum kvm_smccc_filter_action action) { int ret = __set_smccc_filter(vm, start, nr_functions, action); @@ -112,7 +112,7 @@ static void test_filter_reserved_range(void) { struct kvm_vcpu *vcpu; struct kvm_vm *vm = setup_vm(&vcpu); - uint32_t smc64_fn; + u32 smc64_fn; int r; r = __set_smccc_filter(vm, ARM_SMCCC_ARCH_WORKAROUND_1, @@ -217,7 +217,7 @@ static void test_filter_denied(void) } } -static void expect_call_fwd_to_user(struct kvm_vcpu *vcpu, uint32_t func_id, +static void expect_call_fwd_to_user(struct kvm_vcpu *vcpu, u32 func_id, enum smccc_conduit conduit) { struct kvm_run *run = vcpu->run; diff --git a/tools/testing/selftests/kvm/arm64/vgic_init.c b/tools/testing/selftests/kvm/arm64/vgic_init.c index 8d6d3a4ae4db..47e34b43afb2 100644 --- a/tools/testing/selftests/kvm/arm64/vgic_init.c +++ b/tools/testing/selftests/kvm/arm64/vgic_init.c @@ -19,7 +19,7 @@ #define NR_VCPUS 4 -#define REG_OFFSET(vcpu, offset) (((uint64_t)vcpu << 32) | offset) +#define REG_OFFSET(vcpu, offset) (((u64)vcpu << 32) | offset) #define VGIC_DEV_IS_V2(_d) ((_d) == KVM_DEV_TYPE_ARM_VGIC_V2) #define VGIC_DEV_IS_V3(_d) ((_d) == KVM_DEV_TYPE_ARM_VGIC_V3) @@ -27,10 +27,10 @@ struct vm_gic { struct kvm_vm *vm; int gic_fd; - uint32_t gic_dev_type; + u32 gic_dev_type; }; -static uint64_t max_phys_size; +static u64 max_phys_size; /* * Helpers to access a redistributor register and verify the ioctl() failed or @@ -39,17 +39,17 @@ static uint64_t max_phys_size; static void v3_redist_reg_get_errno(int gicv3_fd, int vcpu, int offset, int want, const char *msg) { - uint32_t ignored_val; + u32 ignored_val; int ret = __kvm_device_attr_get(gicv3_fd, KVM_DEV_ARM_VGIC_GRP_REDIST_REGS, REG_OFFSET(vcpu, offset), &ignored_val); TEST_ASSERT(ret && errno == want, "%s; want errno = %d", msg, want); } -static void v3_redist_reg_get(int gicv3_fd, int vcpu, int offset, uint32_t want, +static void v3_redist_reg_get(int gicv3_fd, int vcpu, int offset, u32 want, const char *msg) { - uint32_t val; + u32 val; kvm_device_attr_get(gicv3_fd, KVM_DEV_ARM_VGIC_GRP_REDIST_REGS, REG_OFFSET(vcpu, offset), &val); @@ -71,8 +71,8 @@ static int run_vcpu(struct kvm_vcpu *vcpu) return __vcpu_run(vcpu) ? -errno : 0; } -static struct vm_gic vm_gic_create_with_vcpus(uint32_t gic_dev_type, - uint32_t nr_vcpus, +static struct vm_gic vm_gic_create_with_vcpus(u32 gic_dev_type, + u32 nr_vcpus, struct kvm_vcpu *vcpus[]) { struct vm_gic v; @@ -84,7 +84,7 @@ static struct vm_gic vm_gic_create_with_vcpus(uint32_t gic_dev_type, return v; } -static struct vm_gic vm_gic_create_barebones(uint32_t gic_dev_type) +static struct vm_gic vm_gic_create_barebones(u32 gic_dev_type) { struct vm_gic v; @@ -103,9 +103,9 @@ static void vm_gic_destroy(struct vm_gic *v) } struct vgic_region_attr { - uint64_t attr; - uint64_t size; - uint64_t alignment; + u64 attr; + u64 size; + u64 alignment; }; struct vgic_region_attr gic_v3_dist_region = { @@ -143,7 +143,7 @@ struct vgic_region_attr gic_v2_cpu_region = { static void subtest_dist_rdist(struct vm_gic *v) { int ret; - uint64_t addr; + u64 addr; struct vgic_region_attr rdist; /* CPU interface in GICv2*/ struct vgic_region_attr dist; @@ -223,7 +223,7 @@ static void subtest_dist_rdist(struct vm_gic *v) /* Test the new REDIST region API */ static void subtest_v3_redist_regions(struct vm_gic *v) { - uint64_t addr, expected_addr; + u64 addr, expected_addr; int ret; ret = __kvm_has_device_attr(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, @@ -332,7 +332,7 @@ static void subtest_v3_redist_regions(struct vm_gic *v) * VGIC KVM device is created and initialized before the secondary CPUs * get created */ -static void test_vgic_then_vcpus(uint32_t gic_dev_type) +static void test_vgic_then_vcpus(u32 gic_dev_type) { struct kvm_vcpu *vcpus[NR_VCPUS]; struct vm_gic v; @@ -353,7 +353,7 @@ static void test_vgic_then_vcpus(uint32_t gic_dev_type) } /* All the VCPUs are created before the VGIC KVM device gets initialized */ -static void test_vcpus_then_vgic(uint32_t gic_dev_type) +static void test_vcpus_then_vgic(u32 gic_dev_type) { struct kvm_vcpu *vcpus[NR_VCPUS]; struct vm_gic v; @@ -408,7 +408,7 @@ static void test_v3_new_redist_regions(void) struct kvm_vcpu *vcpus[NR_VCPUS]; void *dummy = NULL; struct vm_gic v; - uint64_t addr; + u64 addr; int ret; v = vm_gic_create_with_vcpus(KVM_DEV_TYPE_ARM_VGIC_V3, NR_VCPUS, vcpus); @@ -460,7 +460,7 @@ static void test_v3_new_redist_regions(void) static void test_v3_typer_accesses(void) { struct vm_gic v; - uint64_t addr; + u64 addr; int ret, i; v.vm = vm_create(NR_VCPUS); @@ -518,7 +518,7 @@ static void test_v3_typer_accesses(void) } static struct vm_gic vm_gic_v3_create_with_vcpuids(int nr_vcpus, - uint32_t vcpuids[]) + u32 vcpuids[]) { struct vm_gic v; int i; @@ -544,9 +544,9 @@ static struct vm_gic vm_gic_v3_create_with_vcpuids(int nr_vcpus, */ static void test_v3_last_bit_redist_regions(void) { - uint32_t vcpuids[] = { 0, 3, 5, 4, 1, 2 }; + u32 vcpuids[] = { 0, 3, 5, 4, 1, 2 }; struct vm_gic v; - uint64_t addr; + u64 addr; v = vm_gic_v3_create_with_vcpuids(ARRAY_SIZE(vcpuids), vcpuids); @@ -578,9 +578,9 @@ static void test_v3_last_bit_redist_regions(void) /* Test last bit with legacy region */ static void test_v3_last_bit_single_rdist(void) { - uint32_t vcpuids[] = { 0, 3, 5, 4, 1, 2 }; + u32 vcpuids[] = { 0, 3, 5, 4, 1, 2 }; struct vm_gic v; - uint64_t addr; + u64 addr; v = vm_gic_v3_create_with_vcpuids(ARRAY_SIZE(vcpuids), vcpuids); @@ -606,7 +606,7 @@ static void test_v3_redist_ipa_range_check_at_vcpu_run(void) struct kvm_vcpu *vcpus[NR_VCPUS]; struct vm_gic v; int ret, i; - uint64_t addr; + u64 addr; v = vm_gic_create_with_vcpus(KVM_DEV_TYPE_ARM_VGIC_V3, 1, vcpus); @@ -638,7 +638,7 @@ static void test_v3_its_region(void) { struct kvm_vcpu *vcpus[NR_VCPUS]; struct vm_gic v; - uint64_t addr; + u64 addr; int its_fd, ret; v = vm_gic_create_with_vcpus(KVM_DEV_TYPE_ARM_VGIC_V3, NR_VCPUS, vcpus); @@ -717,11 +717,11 @@ static void test_v3_nassgicap(void) /* * Returns 0 if it's possible to create GIC device of a given type (V2 or V3). */ -int test_kvm_device(uint32_t gic_dev_type) +int test_kvm_device(u32 gic_dev_type) { struct kvm_vcpu *vcpus[NR_VCPUS]; struct vm_gic v; - uint32_t other; + u32 other; int ret; v.vm = vm_create_with_vcpus(NR_VCPUS, guest_code, vcpus); @@ -968,7 +968,7 @@ static void test_v3_sysregs(void) kvm_vm_free(vm); } -void run_tests(uint32_t gic_dev_type) +void run_tests(u32 gic_dev_type) { test_vcpus_then_vgic(gic_dev_type); test_vgic_then_vcpus(gic_dev_type); diff --git a/tools/testing/selftests/kvm/arm64/vgic_irq.c b/tools/testing/selftests/kvm/arm64/vgic_irq.c index 2fb2c7939fe9..5e231998617e 100644 --- a/tools/testing/selftests/kvm/arm64/vgic_irq.c +++ b/tools/testing/selftests/kvm/arm64/vgic_irq.c @@ -24,12 +24,12 @@ * function. */ struct test_args { - uint32_t nr_irqs; /* number of KVM supported IRQs. */ + u32 nr_irqs; /* number of KVM supported IRQs. */ bool eoi_split; /* 1 is eoir+dir, 0 is eoir only */ bool level_sensitive; /* 1 is level, 0 is edge */ int kvm_max_routes; /* output of KVM_CAP_IRQ_ROUTING */ bool kvm_supports_irqfd; /* output of KVM_CAP_IRQFD */ - uint32_t shared_data; + u32 shared_data; }; /* @@ -64,15 +64,15 @@ typedef enum { struct kvm_inject_args { kvm_inject_cmd cmd; - uint32_t first_intid; - uint32_t num; + u32 first_intid; + u32 num; int level; bool expect_failure; }; /* Used on the guest side to perform the hypercall. */ -static void kvm_inject_call(kvm_inject_cmd cmd, uint32_t first_intid, - uint32_t num, int level, bool expect_failure); +static void kvm_inject_call(kvm_inject_cmd cmd, u32 first_intid, + u32 num, int level, bool expect_failure); /* Used on the host side to get the hypercall info. */ static void kvm_inject_get_call(struct kvm_vm *vm, struct ucall *uc, @@ -133,8 +133,8 @@ static struct kvm_inject_desc set_active_fns[] = { for_each_supported_inject_fn((args), (t), (f)) /* Shared between the guest main thread and the IRQ handlers. */ -volatile uint64_t irq_handled; -volatile uint32_t irqnr_received[MAX_SPI + 1]; +volatile u64 irq_handled; +volatile u32 irqnr_received[MAX_SPI + 1]; static void reset_stats(void) { @@ -145,25 +145,25 @@ static void reset_stats(void) irqnr_received[i] = 0; } -static uint64_t gic_read_ap1r0(void) +static u64 gic_read_ap1r0(void) { - uint64_t reg = read_sysreg_s(SYS_ICC_AP1R0_EL1); + u64 reg = read_sysreg_s(SYS_ICC_AP1R0_EL1); dsb(sy); return reg; } -static void gic_write_ap1r0(uint64_t val) +static void gic_write_ap1r0(u64 val) { write_sysreg_s(val, SYS_ICC_AP1R0_EL1); isb(); } -static void guest_set_irq_line(uint32_t intid, uint32_t level); +static void guest_set_irq_line(u32 intid, u32 level); static void guest_irq_generic_handler(bool eoi_split, bool level_sensitive) { - uint32_t intid = gic_get_and_ack_irq(); + u32 intid = gic_get_and_ack_irq(); if (intid == IAR_SPURIOUS) return; @@ -189,8 +189,8 @@ static void guest_irq_generic_handler(bool eoi_split, bool level_sensitive) GUEST_ASSERT(!gic_irq_get_pending(intid)); } -static void kvm_inject_call(kvm_inject_cmd cmd, uint32_t first_intid, - uint32_t num, int level, bool expect_failure) +static void kvm_inject_call(kvm_inject_cmd cmd, u32 first_intid, + u32 num, int level, bool expect_failure) { struct kvm_inject_args args = { .cmd = cmd, @@ -204,7 +204,7 @@ static void kvm_inject_call(kvm_inject_cmd cmd, uint32_t first_intid, #define GUEST_ASSERT_IAR_EMPTY() \ do { \ - uint32_t _intid; \ + u32 _intid; \ _intid = gic_get_and_ack_irq(); \ GUEST_ASSERT(_intid == IAR_SPURIOUS); \ } while (0) @@ -237,13 +237,13 @@ static void reset_priorities(struct test_args *args) gic_set_priority(i, IRQ_DEFAULT_PRIO_REG); } -static void guest_set_irq_line(uint32_t intid, uint32_t level) +static void guest_set_irq_line(u32 intid, u32 level) { kvm_inject_call(KVM_SET_IRQ_LINE, intid, 1, level, false); } static void test_inject_fail(struct test_args *args, - uint32_t intid, kvm_inject_cmd cmd) + u32 intid, kvm_inject_cmd cmd) { reset_stats(); @@ -255,10 +255,10 @@ static void test_inject_fail(struct test_args *args, } static void guest_inject(struct test_args *args, - uint32_t first_intid, uint32_t num, - kvm_inject_cmd cmd) + u32 first_intid, u32 num, + kvm_inject_cmd cmd) { - uint32_t i; + u32 i; reset_stats(); @@ -292,10 +292,10 @@ static void guest_inject(struct test_args *args, * deactivated yet. */ static void guest_restore_active(struct test_args *args, - uint32_t first_intid, uint32_t num, - kvm_inject_cmd cmd) + u32 first_intid, u32 num, + kvm_inject_cmd cmd) { - uint32_t prio, intid, ap1r; + u32 prio, intid, ap1r; int i; /* @@ -342,9 +342,9 @@ static void guest_restore_active(struct test_args *args, * This function should only be used in test_inject_preemption (with IRQs * masked). */ -static uint32_t wait_for_and_activate_irq(void) +static u32 wait_for_and_activate_irq(void) { - uint32_t intid; + u32 intid; do { asm volatile("wfi" : : : "memory"); @@ -360,11 +360,11 @@ static uint32_t wait_for_and_activate_irq(void) * interrupts for the whole test. */ static void test_inject_preemption(struct test_args *args, - uint32_t first_intid, int num, + u32 first_intid, int num, const unsigned long *exclude, kvm_inject_cmd cmd) { - uint32_t intid, prio, step = KVM_PRIO_STEPS; + u32 intid, prio, step = KVM_PRIO_STEPS; int i; /* Set the priorities of the first (KVM_NUM_PRIOS - 1) IRQs @@ -379,7 +379,7 @@ static void test_inject_preemption(struct test_args *args, local_irq_disable(); for (i = 0; i < num; i++) { - uint32_t tmp; + u32 tmp; intid = i + first_intid; if (exclude && test_bit(i, exclude)) @@ -431,7 +431,7 @@ static void test_inject_preemption(struct test_args *args, static void test_injection(struct test_args *args, struct kvm_inject_desc *f) { - uint32_t nr_irqs = args->nr_irqs; + u32 nr_irqs = args->nr_irqs; if (f->sgi) { guest_inject(args, MIN_SGI, 1, f->cmd); @@ -451,7 +451,7 @@ static void test_injection(struct test_args *args, struct kvm_inject_desc *f) static void test_injection_failure(struct test_args *args, struct kvm_inject_desc *f) { - uint32_t bad_intid[] = { args->nr_irqs, 1020, 1024, 1120, 5120, ~0U, }; + u32 bad_intid[] = { args->nr_irqs, 1020, 1024, 1120, 5120, ~0U, }; int i; for (i = 0; i < ARRAY_SIZE(bad_intid); i++) @@ -490,7 +490,7 @@ static void test_restore_active(struct test_args *args, struct kvm_inject_desc * static void guest_code(struct test_args *args) { - uint32_t i, nr_irqs = args->nr_irqs; + u32 i, nr_irqs = args->nr_irqs; bool level_sensitive = args->level_sensitive; struct kvm_inject_desc *f, *inject_fns; @@ -529,8 +529,8 @@ static void guest_code(struct test_args *args) GUEST_DONE(); } -static void kvm_irq_line_check(struct kvm_vm *vm, uint32_t intid, int level, - struct test_args *test_args, bool expect_failure) +static void kvm_irq_line_check(struct kvm_vm *vm, u32 intid, int level, + struct test_args *test_args, bool expect_failure) { int ret; @@ -548,8 +548,8 @@ static void kvm_irq_line_check(struct kvm_vm *vm, uint32_t intid, int level, } } -void kvm_irq_set_level_info_check(int gic_fd, uint32_t intid, int level, - bool expect_failure) +void kvm_irq_set_level_info_check(int gic_fd, u32 intid, int level, + bool expect_failure) { if (!expect_failure) { kvm_irq_set_level_info(gic_fd, intid, level); @@ -573,17 +573,18 @@ void kvm_irq_set_level_info_check(int gic_fd, uint32_t intid, int level, } static void kvm_set_gsi_routing_irqchip_check(struct kvm_vm *vm, - uint32_t intid, uint32_t num, uint32_t kvm_max_routes, - bool expect_failure) + u32 intid, u32 num, + u32 kvm_max_routes, + bool expect_failure) { struct kvm_irq_routing *routing; int ret; - uint64_t i; + u64 i; assert(num <= kvm_max_routes && kvm_max_routes <= KVM_MAX_IRQ_ROUTES); routing = kvm_gsi_routing_create(); - for (i = intid; i < (uint64_t)intid + num; i++) + for (i = intid; i < (u64)intid + num; i++) kvm_gsi_routing_irqchip_add(routing, i - MIN_SPI, i - MIN_SPI); if (!expect_failure) { @@ -591,7 +592,7 @@ static void kvm_set_gsi_routing_irqchip_check(struct kvm_vm *vm, } else { ret = _kvm_gsi_routing_write(vm, routing); /* The kernel only checks e->irqchip.pin >= KVM_IRQCHIP_NUM_PINS */ - if (((uint64_t)intid + num - 1 - MIN_SPI) >= KVM_IRQCHIP_NUM_PINS) + if (((u64)intid + num - 1 - MIN_SPI) >= KVM_IRQCHIP_NUM_PINS) TEST_ASSERT(ret != 0 && errno == EINVAL, "Bad intid %u did not cause KVM_SET_GSI_ROUTING " "error: rc: %i errno: %i", intid, ret, errno); @@ -602,7 +603,7 @@ static void kvm_set_gsi_routing_irqchip_check(struct kvm_vm *vm, } } -static void kvm_irq_write_ispendr_check(int gic_fd, uint32_t intid, +static void kvm_irq_write_ispendr_check(int gic_fd, u32 intid, struct kvm_vcpu *vcpu, bool expect_failure) { @@ -618,13 +619,13 @@ static void kvm_irq_write_ispendr_check(int gic_fd, uint32_t intid, } static void kvm_routing_and_irqfd_check(struct kvm_vm *vm, - uint32_t intid, uint32_t num, uint32_t kvm_max_routes, - bool expect_failure) + u32 intid, u32 num, u32 kvm_max_routes, + bool expect_failure) { int fd[MAX_SPI]; - uint64_t val; + u64 val; int ret, f; - uint64_t i; + u64 i; /* * There is no way to try injecting an SGI or PPI as the interface @@ -643,29 +644,29 @@ static void kvm_routing_and_irqfd_check(struct kvm_vm *vm, * that no actual interrupt was injected for those cases. */ - for (f = 0, i = intid; i < (uint64_t)intid + num; i++, f++) + for (f = 0, i = intid; i < (u64)intid + num; i++, f++) fd[f] = kvm_new_eventfd(); - for (f = 0, i = intid; i < (uint64_t)intid + num; i++, f++) { - assert(i <= (uint64_t)UINT_MAX); + for (f = 0, i = intid; i < (u64)intid + num; i++, f++) { + assert(i <= (u64)UINT_MAX); kvm_assign_irqfd(vm, i - MIN_SPI, fd[f]); } - for (f = 0, i = intid; i < (uint64_t)intid + num; i++, f++) { + for (f = 0, i = intid; i < (u64)intid + num; i++, f++) { val = 1; - ret = write(fd[f], &val, sizeof(uint64_t)); - TEST_ASSERT(ret == sizeof(uint64_t), + ret = write(fd[f], &val, sizeof(u64)); + TEST_ASSERT(ret == sizeof(u64), __KVM_SYSCALL_ERROR("write()", ret)); } - for (f = 0, i = intid; i < (uint64_t)intid + num; i++, f++) + for (f = 0, i = intid; i < (u64)intid + num; i++, f++) kvm_close(fd[f]); } /* handles the valid case: intid=0xffffffff num=1 */ #define for_each_intid(first, num, tmp, i) \ for ((tmp) = (i) = (first); \ - (tmp) < (uint64_t)(first) + (uint64_t)(num); \ + (tmp) < (u64)(first) + (u64)(num); \ (tmp)++, (i)++) static void run_guest_cmd(struct kvm_vcpu *vcpu, int gic_fd, @@ -673,13 +674,13 @@ static void run_guest_cmd(struct kvm_vcpu *vcpu, int gic_fd, struct test_args *test_args) { kvm_inject_cmd cmd = inject_args->cmd; - uint32_t intid = inject_args->first_intid; - uint32_t num = inject_args->num; + u32 intid = inject_args->first_intid; + u32 num = inject_args->num; int level = inject_args->level; bool expect_failure = inject_args->expect_failure; struct kvm_vm *vm = vcpu->vm; - uint64_t tmp; - uint32_t i; + u64 tmp; + u32 i; /* handles the valid case: intid=0xffffffff num=1 */ assert(intid < UINT_MAX - num || num == 1); @@ -731,7 +732,7 @@ static void kvm_inject_get_call(struct kvm_vm *vm, struct ucall *uc, struct kvm_inject_args *args) { struct kvm_inject_args *kvm_args_hva; - vm_vaddr_t kvm_args_gva; + gva_t kvm_args_gva; kvm_args_gva = uc->args[1]; kvm_args_hva = (struct kvm_inject_args *)addr_gva2hva(vm, kvm_args_gva); @@ -745,14 +746,14 @@ static void print_args(struct test_args *args) args->eoi_split); } -static void test_vgic(uint32_t nr_irqs, bool level_sensitive, bool eoi_split) +static void test_vgic(u32 nr_irqs, bool level_sensitive, bool eoi_split) { struct ucall uc; int gic_fd; struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct kvm_inject_args inject_args; - vm_vaddr_t args_gva; + gva_t args_gva; struct test_args args = { .nr_irqs = nr_irqs, @@ -770,7 +771,7 @@ static void test_vgic(uint32_t nr_irqs, bool level_sensitive, bool eoi_split) vcpu_init_descriptor_tables(vcpu); /* Setup the guest args page (so it gets the args). */ - args_gva = vm_vaddr_alloc_page(vm); + args_gva = vm_alloc_page(vm); memcpy(addr_gva2hva(vm, args_gva), &args, sizeof(args)); vcpu_args_set(vcpu, 1, args_gva); @@ -810,7 +811,7 @@ static void guest_code_asym_dir(struct test_args *args, int cpuid) gic_set_priority_mask(CPU_PRIO_MASK); if (cpuid == 0) { - uint32_t intid; + u32 intid; local_irq_disable(); @@ -848,7 +849,7 @@ static void guest_code_asym_dir(struct test_args *args, int cpuid) static void guest_code_group_en(struct test_args *args, int cpuid) { - uint32_t intid; + u32 intid; gic_init(GIC_V3, 2); @@ -896,7 +897,7 @@ static void guest_code_group_en(struct test_args *args, int cpuid) static void guest_code_timer_spi(struct test_args *args, int cpuid) { - uint32_t intid; + u32 intid; u64 val; gic_init(GIC_V3, 2); @@ -986,7 +987,7 @@ static void test_vgic_two_cpus(void *gcode) struct kvm_vcpu *vcpus[2]; struct test_args args = {}; struct kvm_vm *vm; - vm_vaddr_t args_gva; + gva_t args_gva; int gic_fd, ret; vm = vm_create_with_vcpus(2, gcode, vcpus); @@ -996,7 +997,7 @@ static void test_vgic_two_cpus(void *gcode) vcpu_init_descriptor_tables(vcpus[1]); /* Setup the guest args page (so it gets the args). */ - args_gva = vm_vaddr_alloc_page(vm); + args_gva = vm_alloc_page(vm); memcpy(addr_gva2hva(vm, args_gva), &args, sizeof(args)); vcpu_args_set(vcpus[0], 2, args_gva, 0); vcpu_args_set(vcpus[1], 2, args_gva, 1); @@ -1033,7 +1034,7 @@ static void help(const char *name) int main(int argc, char **argv) { - uint32_t nr_irqs = 64; + u32 nr_irqs = 64; bool default_args = true; bool level_sensitive = false; int opt; diff --git a/tools/testing/selftests/kvm/arm64/vgic_lpi_stress.c b/tools/testing/selftests/kvm/arm64/vgic_lpi_stress.c index e857a605f577..d64d434d3f06 100644 --- a/tools/testing/selftests/kvm/arm64/vgic_lpi_stress.c +++ b/tools/testing/selftests/kvm/arm64/vgic_lpi_stress.c @@ -23,7 +23,7 @@ #define GIC_LPI_OFFSET 8192 static size_t nr_iterations = 1000; -static vm_paddr_t gpa_base; +static gpa_t gpa_base; static struct kvm_vm *vm; static struct kvm_vcpu **vcpus; @@ -35,14 +35,14 @@ static struct test_data { u32 nr_devices; u32 nr_event_ids; - vm_paddr_t device_table; - vm_paddr_t collection_table; - vm_paddr_t cmdq_base; + gpa_t device_table; + gpa_t collection_table; + gpa_t cmdq_base; void *cmdq_base_va; - vm_paddr_t itt_tables; + gpa_t itt_tables; - vm_paddr_t lpi_prop_table; - vm_paddr_t lpi_pend_tables; + gpa_t lpi_prop_table; + gpa_t lpi_pend_tables; } test_data = { .nr_cpus = 1, .nr_devices = 1, @@ -73,7 +73,7 @@ static void guest_setup_its_mappings(void) /* Round-robin the LPIs to all of the vCPUs in the VM */ coll_id = 0; for (device_id = 0; device_id < nr_devices; device_id++) { - vm_paddr_t itt_base = test_data.itt_tables + (device_id * SZ_64K); + gpa_t itt_base = test_data.itt_tables + (device_id * SZ_64K); its_send_mapd_cmd(test_data.cmdq_base_va, device_id, itt_base, SZ_64K, true); @@ -188,7 +188,7 @@ static void setup_test_data(void) size_t pages_per_64k = vm_calc_num_guest_pages(vm->mode, SZ_64K); u32 nr_devices = test_data.nr_devices; u32 nr_cpus = test_data.nr_cpus; - vm_paddr_t cmdq_base; + gpa_t cmdq_base; test_data.device_table = vm_phy_pages_alloc(vm, pages_per_64k, gpa_base, @@ -224,7 +224,7 @@ static void setup_gic(void) static void signal_lpi(u32 device_id, u32 event_id) { - vm_paddr_t db_addr = GITS_BASE_GPA + GITS_TRANSLATER; + gpa_t db_addr = GITS_BASE_GPA + GITS_TRANSLATER; struct kvm_msi msi = { .address_lo = db_addr, diff --git a/tools/testing/selftests/kvm/arm64/vgic_v5.c b/tools/testing/selftests/kvm/arm64/vgic_v5.c index 3ce6cf37a629..d785b660d847 100644 --- a/tools/testing/selftests/kvm/arm64/vgic_v5.c +++ b/tools/testing/selftests/kvm/arm64/vgic_v5.c @@ -17,10 +17,10 @@ struct vm_gic { struct kvm_vm *vm; int gic_fd; - uint32_t gic_dev_type; + u32 gic_dev_type; }; -static uint64_t max_phys_size; +static u64 max_phys_size; #define GUEST_CMD_IRQ_CDIA 10 #define GUEST_CMD_IRQ_DIEOI 11 @@ -96,7 +96,7 @@ static void vm_gic_destroy(struct vm_gic *v) kvm_vm_free(v->vm); } -static void test_vgic_v5_ppis(uint32_t gic_dev_type) +static void test_vgic_v5_ppis(u32 gic_dev_type) { struct kvm_vcpu *vcpus[NR_VCPUS]; struct ucall uc; @@ -173,7 +173,7 @@ done: /* * Returns 0 if it's possible to create GIC device of a given type (V5). */ -int test_kvm_device(uint32_t gic_dev_type) +int test_kvm_device(u32 gic_dev_type) { struct kvm_vcpu *vcpus[NR_VCPUS]; struct vm_gic v; @@ -199,7 +199,7 @@ int test_kvm_device(uint32_t gic_dev_type) return 0; } -void run_tests(uint32_t gic_dev_type) +void run_tests(u32 gic_dev_type) { pr_info("Test VGICv5 PPIs\n"); test_vgic_v5_ppis(gic_dev_type); diff --git a/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c b/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c index ae36325c022f..22223395969e 100644 --- a/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c +++ b/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c @@ -33,20 +33,20 @@ struct vpmu_vm { static struct vpmu_vm vpmu_vm; struct pmreg_sets { - uint64_t set_reg_id; - uint64_t clr_reg_id; + u64 set_reg_id; + u64 clr_reg_id; }; #define PMREG_SET(set, clr) {.set_reg_id = set, .clr_reg_id = clr} -static uint64_t get_pmcr_n(uint64_t pmcr) +static u64 get_pmcr_n(u64 pmcr) { return FIELD_GET(ARMV8_PMU_PMCR_N, pmcr); } -static uint64_t get_counters_mask(uint64_t n) +static u64 get_counters_mask(u64 n) { - uint64_t mask = BIT(ARMV8_PMU_CYCLE_IDX); + u64 mask = BIT(ARMV8_PMU_CYCLE_IDX); if (n) mask |= GENMASK(n - 1, 0); @@ -89,7 +89,7 @@ static inline void write_sel_evtyper(int sel, unsigned long val) static void pmu_disable_reset(void) { - uint64_t pmcr = read_sysreg(pmcr_el0); + u64 pmcr = read_sysreg(pmcr_el0); /* Reset all counters, disabling them */ pmcr &= ~ARMV8_PMU_PMCR_E; @@ -169,7 +169,7 @@ struct pmc_accessor pmc_accessors[] = { #define GUEST_ASSERT_BITMAP_REG(regname, mask, set_expected) \ { \ - uint64_t _tval = read_sysreg(regname); \ + u64 _tval = read_sysreg(regname); \ \ if (set_expected) \ __GUEST_ASSERT((_tval & mask), \ @@ -185,7 +185,7 @@ struct pmc_accessor pmc_accessors[] = { * Check if @mask bits in {PMCNTEN,PMINTEN,PMOVS}{SET,CLR} registers * are set or cleared as specified in @set_expected. */ -static void check_bitmap_pmu_regs(uint64_t mask, bool set_expected) +static void check_bitmap_pmu_regs(u64 mask, bool set_expected) { GUEST_ASSERT_BITMAP_REG(pmcntenset_el0, mask, set_expected); GUEST_ASSERT_BITMAP_REG(pmcntenclr_el0, mask, set_expected); @@ -207,7 +207,7 @@ static void check_bitmap_pmu_regs(uint64_t mask, bool set_expected) */ static void test_bitmap_pmu_regs(int pmc_idx, bool set_op) { - uint64_t pmcr_n, test_bit = BIT(pmc_idx); + u64 pmcr_n, test_bit = BIT(pmc_idx); bool set_expected = false; if (set_op) { @@ -232,7 +232,7 @@ static void test_bitmap_pmu_regs(int pmc_idx, bool set_op) */ static void test_access_pmc_regs(struct pmc_accessor *acc, int pmc_idx) { - uint64_t write_data, read_data; + u64 write_data, read_data; /* Disable all PMCs and reset all PMCs to zero. */ pmu_disable_reset(); @@ -287,11 +287,11 @@ static void test_access_pmc_regs(struct pmc_accessor *acc, int pmc_idx) } #define INVALID_EC (-1ul) -uint64_t expected_ec = INVALID_EC; +u64 expected_ec = INVALID_EC; static void guest_sync_handler(struct ex_regs *regs) { - uint64_t esr, ec; + u64 esr, ec; esr = read_sysreg(esr_el1); ec = ESR_ELx_EC(esr); @@ -351,9 +351,9 @@ static void test_access_invalid_pmc_regs(struct pmc_accessor *acc, int pmc_idx) * if reading/writing PMU registers for implemented or unimplemented * counters works as expected. */ -static void guest_code(uint64_t expected_pmcr_n) +static void guest_code(u64 expected_pmcr_n) { - uint64_t pmcr, pmcr_n, unimp_mask; + u64 pmcr, pmcr_n, unimp_mask; int i, pmc; __GUEST_ASSERT(expected_pmcr_n <= ARMV8_PMU_MAX_GENERAL_COUNTERS, @@ -402,12 +402,12 @@ static void guest_code(uint64_t expected_pmcr_n) static void create_vpmu_vm(void *guest_code) { struct kvm_vcpu_init init; - uint8_t pmuver, ec; - uint64_t dfr0, irq = 23; + u8 pmuver, ec; + u64 dfr0, irq = 23; struct kvm_device_attr irq_attr = { .group = KVM_ARM_VCPU_PMU_V3_CTRL, .attr = KVM_ARM_VCPU_PMU_V3_IRQ, - .addr = (uint64_t)&irq, + .addr = (u64)&irq, }; /* The test creates the vpmu_vm multiple times. Ensure a clean state */ @@ -443,7 +443,7 @@ static void destroy_vpmu_vm(void) kvm_vm_free(vpmu_vm.vm); } -static void run_vcpu(struct kvm_vcpu *vcpu, uint64_t pmcr_n) +static void run_vcpu(struct kvm_vcpu *vcpu, u64 pmcr_n) { struct ucall uc; @@ -489,9 +489,9 @@ static void test_create_vpmu_vm_with_nr_counters(unsigned int nr_counters, bool * Create a guest with one vCPU, set the PMCR_EL0.N for the vCPU to @pmcr_n, * and run the test. */ -static void run_access_test(uint64_t pmcr_n) +static void run_access_test(u64 pmcr_n) { - uint64_t sp; + u64 sp; struct kvm_vcpu *vcpu; struct kvm_vcpu_init init; @@ -514,7 +514,7 @@ static void run_access_test(uint64_t pmcr_n) aarch64_vcpu_setup(vcpu, &init); vcpu_init_descriptor_tables(vcpu); vcpu_set_reg(vcpu, ctxt_reg_alias(vcpu, SYS_SP_EL1), sp); - vcpu_set_reg(vcpu, ARM64_CORE_REG(regs.pc), (uint64_t)guest_code); + vcpu_set_reg(vcpu, ARM64_CORE_REG(regs.pc), (u64)guest_code); run_vcpu(vcpu, pmcr_n); @@ -531,12 +531,12 @@ static struct pmreg_sets validity_check_reg_sets[] = { * Create a VM, and check if KVM handles the userspace accesses of * the PMU register sets in @validity_check_reg_sets[] correctly. */ -static void run_pmregs_validity_test(uint64_t pmcr_n) +static void run_pmregs_validity_test(u64 pmcr_n) { int i; struct kvm_vcpu *vcpu; - uint64_t set_reg_id, clr_reg_id, reg_val; - uint64_t valid_counters_mask, max_counters_mask; + u64 set_reg_id, clr_reg_id, reg_val; + u64 valid_counters_mask, max_counters_mask; test_create_vpmu_vm_with_nr_counters(pmcr_n, false); vcpu = vpmu_vm.vcpu; @@ -588,7 +588,7 @@ static void run_pmregs_validity_test(uint64_t pmcr_n) * the vCPU to @pmcr_n, which is larger than the host value. * The attempt should fail as @pmcr_n is too big to set for the vCPU. */ -static void run_error_test(uint64_t pmcr_n) +static void run_error_test(u64 pmcr_n) { pr_debug("Error test with pmcr_n %lu (larger than the host)\n", pmcr_n); @@ -600,9 +600,9 @@ static void run_error_test(uint64_t pmcr_n) * Return the default number of implemented PMU event counters excluding * the cycle counter (i.e. PMCR_EL0.N value) for the guest. */ -static uint64_t get_pmcr_n_limit(void) +static u64 get_pmcr_n_limit(void) { - uint64_t pmcr; + u64 pmcr; create_vpmu_vm(guest_code); pmcr = vcpu_get_reg(vpmu_vm.vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0)); @@ -624,7 +624,7 @@ static bool kvm_supports_nr_counters_attr(void) int main(void) { - uint64_t i, pmcr_n; + u64 i, pmcr_n; TEST_REQUIRE(kvm_has_cap(KVM_CAP_ARM_PMU_V3)); TEST_REQUIRE(kvm_supports_vgic_v3()); diff --git a/tools/testing/selftests/kvm/coalesced_io_test.c b/tools/testing/selftests/kvm/coalesced_io_test.c index 60cb25454899..df4ed5e3877c 100644 --- a/tools/testing/selftests/kvm/coalesced_io_test.c +++ b/tools/testing/selftests/kvm/coalesced_io_test.c @@ -14,16 +14,16 @@ struct kvm_coalesced_io { struct kvm_coalesced_mmio_ring *ring; - uint32_t ring_size; - uint64_t mmio_gpa; - uint64_t *mmio; + u32 ring_size; + u64 mmio_gpa; + u64 *mmio; /* * x86-only, but define pio_port for all architectures to minimize the * amount of #ifdeffery and complexity, without having to sacrifice * verbose error messages. */ - uint8_t pio_port; + u8 pio_port; }; static struct kvm_coalesced_io kvm_builtin_io_ring; @@ -70,13 +70,13 @@ static void guest_code(struct kvm_coalesced_io *io) static void vcpu_run_and_verify_io_exit(struct kvm_vcpu *vcpu, struct kvm_coalesced_io *io, - uint32_t ring_start, - uint32_t expected_exit) + u32 ring_start, + u32 expected_exit) { const bool want_pio = expected_exit == KVM_EXIT_IO; struct kvm_coalesced_mmio_ring *ring = io->ring; struct kvm_run *run = vcpu->run; - uint32_t pio_value; + u32 pio_value; WRITE_ONCE(ring->first, ring_start); WRITE_ONCE(ring->last, ring_start); @@ -88,13 +88,13 @@ static void vcpu_run_and_verify_io_exit(struct kvm_vcpu *vcpu, * data_offset is garbage, e.g. an MMIO gpa. */ if (run->exit_reason == KVM_EXIT_IO) - pio_value = *(uint32_t *)((void *)run + run->io.data_offset); + pio_value = *(u32 *)((void *)run + run->io.data_offset); else pio_value = 0; TEST_ASSERT((!want_pio && (run->exit_reason == KVM_EXIT_MMIO && run->mmio.is_write && run->mmio.phys_addr == io->mmio_gpa && run->mmio.len == 8 && - *(uint64_t *)run->mmio.data == io->mmio_gpa + io->ring_size - 1)) || + *(u64 *)run->mmio.data == io->mmio_gpa + io->ring_size - 1)) || (want_pio && (run->exit_reason == KVM_EXIT_IO && run->io.port == io->pio_port && run->io.direction == KVM_EXIT_IO_OUT && run->io.count == 1 && pio_value == io->pio_port + io->ring_size - 1)), @@ -105,14 +105,14 @@ static void vcpu_run_and_verify_io_exit(struct kvm_vcpu *vcpu, want_pio ? (unsigned long long)io->pio_port : io->mmio_gpa, (want_pio ? io->pio_port : io->mmio_gpa) + io->ring_size - 1, run->exit_reason, run->exit_reason == KVM_EXIT_MMIO ? "MMIO" : run->exit_reason == KVM_EXIT_IO ? "PIO" : "other", - run->mmio.phys_addr, run->mmio.is_write, run->mmio.len, *(uint64_t *)run->mmio.data, + run->mmio.phys_addr, run->mmio.is_write, run->mmio.len, *(u64 *)run->mmio.data, run->io.port, run->io.direction, run->io.size, run->io.count, pio_value); } static void vcpu_run_and_verify_coalesced_io(struct kvm_vcpu *vcpu, struct kvm_coalesced_io *io, - uint32_t ring_start, - uint32_t expected_exit) + u32 ring_start, + u32 expected_exit) { struct kvm_coalesced_mmio_ring *ring = io->ring; int i; @@ -124,18 +124,18 @@ static void vcpu_run_and_verify_coalesced_io(struct kvm_vcpu *vcpu, ring->first, ring->last, io->ring_size, ring_start); for (i = 0; i < io->ring_size - 1; i++) { - uint32_t idx = (ring->first + i) % io->ring_size; + u32 idx = (ring->first + i) % io->ring_size; struct kvm_coalesced_mmio *entry = &ring->coalesced_mmio[idx]; #ifdef __x86_64__ if (i & 1) TEST_ASSERT(entry->phys_addr == io->pio_port && entry->len == 4 && entry->pio && - *(uint32_t *)entry->data == io->pio_port + i, + *(u32 *)entry->data == io->pio_port + i, "Wanted 4-byte port I/O 0x%x = 0x%x in entry %u, got %u-byte %s 0x%llx = 0x%x", io->pio_port, io->pio_port + i, i, entry->len, entry->pio ? "PIO" : "MMIO", - entry->phys_addr, *(uint32_t *)entry->data); + entry->phys_addr, *(u32 *)entry->data); else #endif TEST_ASSERT(entry->phys_addr == io->mmio_gpa && @@ -143,12 +143,12 @@ static void vcpu_run_and_verify_coalesced_io(struct kvm_vcpu *vcpu, "Wanted 8-byte MMIO to 0x%lx = %lx in entry %u, got %u-byte %s 0x%llx = 0x%lx", io->mmio_gpa, io->mmio_gpa + i, i, entry->len, entry->pio ? "PIO" : "MMIO", - entry->phys_addr, *(uint64_t *)entry->data); + entry->phys_addr, *(u64 *)entry->data); } } static void test_coalesced_io(struct kvm_vcpu *vcpu, - struct kvm_coalesced_io *io, uint32_t ring_start) + struct kvm_coalesced_io *io, u32 ring_start) { struct kvm_coalesced_mmio_ring *ring = io->ring; @@ -219,11 +219,11 @@ int main(int argc, char *argv[]) * the MMIO GPA identity mapped in the guest. */ .mmio_gpa = 4ull * SZ_1G, - .mmio = (uint64_t *)(4ull * SZ_1G), + .mmio = (u64 *)(4ull * SZ_1G), .pio_port = 0x80, }; - virt_map(vm, (uint64_t)kvm_builtin_io_ring.mmio, kvm_builtin_io_ring.mmio_gpa, 1); + virt_map(vm, (u64)kvm_builtin_io_ring.mmio, kvm_builtin_io_ring.mmio_gpa, 1); sync_global_to_guest(vm, kvm_builtin_io_ring); vcpu_args_set(vcpu, 1, &kvm_builtin_io_ring); diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c index 0202b78f8680..302c4923d093 100644 --- a/tools/testing/selftests/kvm/demand_paging_test.c +++ b/tools/testing/selftests/kvm/demand_paging_test.c @@ -24,7 +24,7 @@ #ifdef __NR_userfaultfd static int nr_vcpus = 1; -static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE; +static u64 guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE; static size_t demand_paging_size; static char *guest_data_prototype; @@ -58,7 +58,7 @@ static int handle_uffd_page_request(int uffd_mode, int uffd, struct uffd_msg *msg) { pid_t tid = syscall(__NR_gettid); - uint64_t addr = msg->arg.pagefault.address; + u64 addr = msg->arg.pagefault.address; struct timespec start; struct timespec ts_diff; int r; @@ -68,7 +68,7 @@ static int handle_uffd_page_request(int uffd_mode, int uffd, if (uffd_mode == UFFDIO_REGISTER_MODE_MISSING) { struct uffdio_copy copy; - copy.src = (uint64_t)guest_data_prototype; + copy.src = (u64)guest_data_prototype; copy.dst = addr; copy.len = demand_paging_size; copy.mode = 0; @@ -138,7 +138,7 @@ struct test_params { bool partition_vcpu_memory_access; }; -static void prefault_mem(void *alias, uint64_t len) +static void prefault_mem(void *alias, u64 len) { size_t p; @@ -154,7 +154,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) struct memstress_vcpu_args *vcpu_args; struct test_params *p = arg; struct uffd_desc **uffd_descs = NULL; - uint64_t uffd_region_size; + u64 uffd_region_size; struct timespec start; struct timespec ts_diff; double vcpu_paging_rate; diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c index 0a1ea1d1e2d8..ef779fa91827 100644 --- a/tools/testing/selftests/kvm/dirty_log_perf_test.c +++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c @@ -24,7 +24,7 @@ #define TEST_HOST_LOOP_N 2UL static int nr_vcpus = 1; -static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE; +static u64 guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE; static bool run_vcpus_while_disabling_dirty_logging; /* Host variables */ @@ -37,7 +37,7 @@ static void vcpu_worker(struct memstress_vcpu_args *vcpu_args) { struct kvm_vcpu *vcpu = vcpu_args->vcpu; int vcpu_idx = vcpu_args->vcpu_idx; - uint64_t pages_count = 0; + u64 pages_count = 0; struct kvm_run *run; struct timespec start; struct timespec ts_diff; @@ -93,11 +93,11 @@ static void vcpu_worker(struct memstress_vcpu_args *vcpu_args) struct test_params { unsigned long iterations; - uint64_t phys_offset; + u64 phys_offset; bool partition_vcpu_memory_access; enum vm_mem_backing_src_type backing_src; int slots; - uint32_t write_percent; + u32 write_percent; bool random_access; }; @@ -106,9 +106,9 @@ static void run_test(enum vm_guest_mode mode, void *arg) struct test_params *p = arg; struct kvm_vm *vm; unsigned long **bitmaps; - uint64_t guest_num_pages; - uint64_t host_num_pages; - uint64_t pages_per_slot; + u64 guest_num_pages; + u64 host_num_pages; + u64 pages_per_slot; struct timespec start; struct timespec ts_diff; struct timespec get_dirty_log_total = (struct timespec){0}; diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index 7627b328f18a..12446a4b6e8d 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -74,11 +74,11 @@ * the host. READ/WRITE_ONCE() should also be used with anything * that may change. */ -static uint64_t host_page_size; -static uint64_t guest_page_size; -static uint64_t guest_num_pages; -static uint64_t iteration; -static uint64_t nr_writes; +static u64 host_page_size; +static u64 guest_page_size; +static u64 guest_num_pages; +static u64 iteration; +static u64 nr_writes; static bool vcpu_stop; /* @@ -86,13 +86,13 @@ static bool vcpu_stop; * This will be set to the topmost valid physical address minus * the test memory size. */ -static uint64_t guest_test_phys_mem; +static u64 guest_test_phys_mem; /* * Guest virtual memory offset of the testing memory slot. * Must not conflict with identity mapped test code. */ -static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM; +static u64 guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM; /* * Continuously write to the first 8 bytes of a random pages within @@ -100,10 +100,10 @@ static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM; */ static void guest_code(void) { - uint64_t addr; + u64 addr; #ifdef __s390x__ - uint64_t i; + u64 i; /* * On s390x, all pages of a 1M segment are initially marked as dirty @@ -113,7 +113,7 @@ static void guest_code(void) */ for (i = 0; i < guest_num_pages; i++) { addr = guest_test_virt_mem + i * guest_page_size; - vcpu_arch_put_guest(*(uint64_t *)addr, READ_ONCE(iteration)); + vcpu_arch_put_guest(*(u64 *)addr, READ_ONCE(iteration)); nr_writes++; } #endif @@ -125,7 +125,7 @@ static void guest_code(void) * guest_page_size; addr = align_down(addr, host_page_size); - vcpu_arch_put_guest(*(uint64_t *)addr, READ_ONCE(iteration)); + vcpu_arch_put_guest(*(u64 *)addr, READ_ONCE(iteration)); nr_writes++; } @@ -138,11 +138,11 @@ static bool host_quit; /* Points to the test VM memory region on which we track dirty logs */ static void *host_test_mem; -static uint64_t host_num_pages; +static u64 host_num_pages; /* For statistics only */ -static uint64_t host_dirty_count; -static uint64_t host_clear_count; +static u64 host_dirty_count; +static u64 host_clear_count; /* Whether dirty ring reset is requested, or finished */ static sem_t sem_vcpu_stop; @@ -169,7 +169,7 @@ static bool dirty_ring_vcpu_ring_full; * dirty gfn we've collected, so that if a mismatch of data found later in the * verifying process, we let it pass. */ -static uint64_t dirty_ring_last_page = -1ULL; +static u64 dirty_ring_last_page = -1ULL; /* * In addition to the above, it is possible (especially if this @@ -213,7 +213,7 @@ static uint64_t dirty_ring_last_page = -1ULL; * and also don't fail when it is reported in the next iteration, together with * an outdated iteration count. */ -static uint64_t dirty_ring_prev_iteration_last_page; +static u64 dirty_ring_prev_iteration_last_page; enum log_mode_t { /* Only use KVM_GET_DIRTY_LOG for logging */ @@ -236,7 +236,7 @@ static enum log_mode_t host_log_mode_option = LOG_MODE_ALL; /* Logging mode for current run */ static enum log_mode_t host_log_mode; static pthread_t vcpu_thread; -static uint32_t test_dirty_ring_count = TEST_DIRTY_RING_COUNT; +static u32 test_dirty_ring_count = TEST_DIRTY_RING_COUNT; static bool clear_log_supported(void) { @@ -255,15 +255,15 @@ static void clear_log_create_vm_done(struct kvm_vm *vm) } static void dirty_log_collect_dirty_pages(struct kvm_vcpu *vcpu, int slot, - void *bitmap, uint32_t num_pages, - uint32_t *unused) + void *bitmap, u32 num_pages, + u32 *unused) { kvm_vm_get_dirty_log(vcpu->vm, slot, bitmap); } static void clear_log_collect_dirty_pages(struct kvm_vcpu *vcpu, int slot, - void *bitmap, uint32_t num_pages, - uint32_t *unused) + void *bitmap, u32 num_pages, + u32 *unused) { kvm_vm_get_dirty_log(vcpu->vm, slot, bitmap); kvm_vm_clear_dirty_log(vcpu->vm, slot, bitmap, 0, num_pages); @@ -297,8 +297,8 @@ static bool dirty_ring_supported(void) static void dirty_ring_create_vm_done(struct kvm_vm *vm) { - uint64_t pages; - uint32_t limit; + u64 pages; + u32 limit; /* * We rely on vcpu exit due to full dirty ring state. Adjust @@ -333,12 +333,12 @@ static inline void dirty_gfn_set_collected(struct kvm_dirty_gfn *gfn) smp_store_release(&gfn->flags, KVM_DIRTY_GFN_F_RESET); } -static uint32_t dirty_ring_collect_one(struct kvm_dirty_gfn *dirty_gfns, - int slot, void *bitmap, - uint32_t num_pages, uint32_t *fetch_index) +static u32 dirty_ring_collect_one(struct kvm_dirty_gfn *dirty_gfns, + int slot, void *bitmap, + u32 num_pages, u32 *fetch_index) { struct kvm_dirty_gfn *cur; - uint32_t count = 0; + u32 count = 0; while (true) { cur = &dirty_gfns[*fetch_index % test_dirty_ring_count]; @@ -359,10 +359,10 @@ static uint32_t dirty_ring_collect_one(struct kvm_dirty_gfn *dirty_gfns, } static void dirty_ring_collect_dirty_pages(struct kvm_vcpu *vcpu, int slot, - void *bitmap, uint32_t num_pages, - uint32_t *ring_buf_idx) + void *bitmap, u32 num_pages, + u32 *ring_buf_idx) { - uint32_t count, cleared; + u32 count, cleared; /* Only have one vcpu */ count = dirty_ring_collect_one(vcpu_map_dirty_ring(vcpu), @@ -404,8 +404,8 @@ struct log_mode { void (*create_vm_done)(struct kvm_vm *vm); /* Hook to collect the dirty pages into the bitmap provided */ void (*collect_dirty_pages) (struct kvm_vcpu *vcpu, int slot, - void *bitmap, uint32_t num_pages, - uint32_t *ring_buf_idx); + void *bitmap, u32 num_pages, + u32 *ring_buf_idx); /* Hook to call when after each vcpu run */ void (*after_vcpu_run)(struct kvm_vcpu *vcpu); } log_modes[LOG_MODE_NUM] = { @@ -459,8 +459,8 @@ static void log_mode_create_vm_done(struct kvm_vm *vm) } static void log_mode_collect_dirty_pages(struct kvm_vcpu *vcpu, int slot, - void *bitmap, uint32_t num_pages, - uint32_t *ring_buf_idx) + void *bitmap, u32 num_pages, + u32 *ring_buf_idx) { struct log_mode *mode = &log_modes[host_log_mode]; @@ -494,11 +494,11 @@ static void *vcpu_worker(void *data) static void vm_dirty_log_verify(enum vm_guest_mode mode, unsigned long **bmap) { - uint64_t page, nr_dirty_pages = 0, nr_clean_pages = 0; - uint64_t step = vm_num_host_pages(mode, 1); + u64 page, nr_dirty_pages = 0, nr_clean_pages = 0; + u64 step = vm_num_host_pages(mode, 1); for (page = 0; page < host_num_pages; page += step) { - uint64_t val = *(uint64_t *)(host_test_mem + page * host_page_size); + u64 val = *(u64 *)(host_test_mem + page * host_page_size); bool bmap0_dirty = __test_and_clear_bit_le(page, bmap[0]); /* @@ -575,7 +575,7 @@ static void vm_dirty_log_verify(enum vm_guest_mode mode, unsigned long **bmap) } static struct kvm_vm *create_vm(enum vm_guest_mode mode, struct kvm_vcpu **vcpu, - uint64_t extra_mem_pages, void *guest_code) + u64 extra_mem_pages, void *guest_code) { struct kvm_vm *vm; @@ -592,7 +592,7 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, struct kvm_vcpu **vcpu, struct test_params { unsigned long iterations; unsigned long interval; - uint64_t phys_offset; + u64 phys_offset; }; static void run_test(enum vm_guest_mode mode, void *arg) @@ -601,7 +601,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) struct kvm_vcpu *vcpu; struct kvm_vm *vm; unsigned long *bmap[2]; - uint32_t ring_buf_idx = 0; + u32 ring_buf_idx = 0; int sem_val; if (!log_mode_supported()) { @@ -667,7 +667,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages); /* Cache the HVA pointer of the region */ - host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)guest_test_phys_mem); + host_test_mem = addr_gpa2hva(vm, (gpa_t)guest_test_phys_mem); /* Export the shared variables to the guest */ sync_global_to_guest(vm, host_page_size); diff --git a/tools/testing/selftests/kvm/get-reg-list.c b/tools/testing/selftests/kvm/get-reg-list.c index f4644c9d2d3b..216f10644c1a 100644 --- a/tools/testing/selftests/kvm/get-reg-list.c +++ b/tools/testing/selftests/kvm/get-reg-list.c @@ -216,7 +216,7 @@ static void run_test(struct vcpu_reg_list *c) * since we don't know the capabilities of any new registers. */ for_each_present_blessed_reg(i) { - uint8_t addr[2048 / 8]; + u8 addr[2048 / 8]; struct kvm_one_reg reg = { .id = reg_list->reg[i], .addr = (__u64)&addr, diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c index ec7644aae999..d6528c6f5e03 100644 --- a/tools/testing/selftests/kvm/guest_memfd_test.c +++ b/tools/testing/selftests/kvm/guest_memfd_test.c @@ -171,7 +171,7 @@ static void test_numa_allocation(int fd, size_t total_size) kvm_munmap(mem, total_size); } -static void test_collapse(int fd, uint64_t flags) +static void test_collapse(int fd, u64 flags) { const size_t pmd_size = get_trans_hugepagesz(); void *reserved_addr; @@ -346,7 +346,7 @@ static void test_invalid_punch_hole(int fd, size_t total_size) } static void test_create_guest_memfd_invalid_sizes(struct kvm_vm *vm, - uint64_t guest_memfd_flags) + u64 guest_memfd_flags) { size_t size; int fd; @@ -389,8 +389,8 @@ static void test_create_guest_memfd_multiple(struct kvm_vm *vm) static void test_guest_memfd_flags(struct kvm_vm *vm) { - uint64_t valid_flags = vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_FLAGS); - uint64_t flag; + u64 valid_flags = vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_FLAGS); + u64 flag; int fd; for (flag = BIT(0); flag; flag <<= 1) { @@ -419,7 +419,7 @@ do { \ #define gmem_test(__test, __vm, __flags) \ __gmem_test(__test, __vm, __flags, page_size * 4) -static void __test_guest_memfd(struct kvm_vm *vm, uint64_t flags) +static void __test_guest_memfd(struct kvm_vm *vm, u64 flags) { test_create_guest_memfd_multiple(vm); test_create_guest_memfd_invalid_sizes(vm, flags); @@ -452,7 +452,7 @@ static void __test_guest_memfd(struct kvm_vm *vm, uint64_t flags) static void test_guest_memfd(unsigned long vm_type) { struct kvm_vm *vm = vm_create_barebones_type(vm_type); - uint64_t flags; + u64 flags; test_guest_memfd_flags(vm); @@ -470,7 +470,7 @@ static void test_guest_memfd(unsigned long vm_type) kvm_vm_free(vm); } -static void guest_code(uint8_t *mem, uint64_t size) +static void guest_code(u8 *mem, u64 size) { size_t i; @@ -489,12 +489,12 @@ static void test_guest_memfd_guest(void) * the guest's code, stack, and page tables, and low memory contains * the PCI hole and other MMIO regions that need to be avoided. */ - const uint64_t gpa = SZ_4G; + const gpa_t gpa = SZ_4G; const int slot = 1; struct kvm_vcpu *vcpu; struct kvm_vm *vm; - uint8_t *mem; + u8 *mem; size_t size; int fd, i; diff --git a/tools/testing/selftests/kvm/guest_print_test.c b/tools/testing/selftests/kvm/guest_print_test.c index bcf582852db9..79d3fc326e91 100644 --- a/tools/testing/selftests/kvm/guest_print_test.c +++ b/tools/testing/selftests/kvm/guest_print_test.c @@ -16,22 +16,22 @@ #include "ucall_common.h" struct guest_vals { - uint64_t a; - uint64_t b; - uint64_t type; + u64 a; + u64 b; + u64 type; }; static struct guest_vals vals; /* GUEST_PRINTF()/GUEST_ASSERT_FMT() does not support float or double. */ #define TYPE_LIST \ -TYPE(test_type_i64, I64, "%ld", int64_t) \ -TYPE(test_type_u64, U64u, "%lu", uint64_t) \ -TYPE(test_type_x64, U64x, "0x%lx", uint64_t) \ -TYPE(test_type_X64, U64X, "0x%lX", uint64_t) \ -TYPE(test_type_u32, U32u, "%u", uint32_t) \ -TYPE(test_type_x32, U32x, "0x%x", uint32_t) \ -TYPE(test_type_X32, U32X, "0x%X", uint32_t) \ +TYPE(test_type_i64, I64, "%ld", s64) \ +TYPE(test_type_u64, U64u, "%lu", u64) \ +TYPE(test_type_x64, U64x, "0x%lx", u64) \ +TYPE(test_type_X64, U64X, "0x%lX", u64) \ +TYPE(test_type_u32, U32u, "%u", u32) \ +TYPE(test_type_x32, U32x, "0x%x", u32) \ +TYPE(test_type_X32, U32X, "0x%X", u32) \ TYPE(test_type_int, INT, "%d", int) \ TYPE(test_type_char, CHAR, "%c", char) \ TYPE(test_type_str, STR, "'%s'", const char *) \ @@ -56,7 +56,7 @@ static void fn(struct kvm_vcpu *vcpu, T a, T b) \ \ snprintf(expected_printf, UCALL_BUFFER_LEN, PRINTF_FMT_##ext, a, b); \ snprintf(expected_assert, UCALL_BUFFER_LEN, ASSERT_FMT_##ext, a, b); \ - vals = (struct guest_vals){ (uint64_t)a, (uint64_t)b, TYPE_##ext }; \ + vals = (struct guest_vals){ (u64)a, (u64)b, TYPE_##ext }; \ sync_global_to_guest(vcpu->vm, vals); \ run_test(vcpu, expected_printf, expected_assert); \ } diff --git a/tools/testing/selftests/kvm/hardware_disable_test.c b/tools/testing/selftests/kvm/hardware_disable_test.c index 94bd6ed24cf3..3147f5c97e94 100644 --- a/tools/testing/selftests/kvm/hardware_disable_test.c +++ b/tools/testing/selftests/kvm/hardware_disable_test.c @@ -80,7 +80,7 @@ static inline void check_join(pthread_t thread, void **retval) TEST_ASSERT(r == 0, "%s: failed to join thread", __func__); } -static void run_test(uint32_t run) +static void run_test(u32 run) { struct kvm_vcpu *vcpu; struct kvm_vm *vm; @@ -88,7 +88,7 @@ static void run_test(uint32_t run) pthread_t threads[VCPU_NUM]; pthread_t throw_away; void *b; - uint32_t i, j; + u32 i, j; CPU_ZERO(&cpu_set); for (i = 0; i < VCPU_NUM; i++) @@ -149,7 +149,7 @@ void wait_for_child_setup(pid_t pid) int main(int argc, char **argv) { - uint32_t i; + u32 i; int s, r; pid_t pid; diff --git a/tools/testing/selftests/kvm/include/arm64/arch_timer.h b/tools/testing/selftests/kvm/include/arm64/arch_timer.h index e2c4e9f0010f..a5836d4ab7ee 100644 --- a/tools/testing/selftests/kvm/include/arm64/arch_timer.h +++ b/tools/testing/selftests/kvm/include/arm64/arch_timer.h @@ -18,20 +18,20 @@ enum arch_timer { #define CTL_ISTATUS (1 << 2) #define msec_to_cycles(msec) \ - (timer_get_cntfrq() * (uint64_t)(msec) / 1000) + (timer_get_cntfrq() * (u64)(msec) / 1000) #define usec_to_cycles(usec) \ - (timer_get_cntfrq() * (uint64_t)(usec) / 1000000) + (timer_get_cntfrq() * (u64)(usec) / 1000000) #define cycles_to_usec(cycles) \ - ((uint64_t)(cycles) * 1000000 / timer_get_cntfrq()) + ((u64)(cycles) * 1000000 / timer_get_cntfrq()) -static inline uint32_t timer_get_cntfrq(void) +static inline u32 timer_get_cntfrq(void) { return read_sysreg(cntfrq_el0); } -static inline uint64_t timer_get_cntct(enum arch_timer timer) +static inline u64 timer_get_cntct(enum arch_timer timer) { isb(); @@ -48,7 +48,7 @@ static inline uint64_t timer_get_cntct(enum arch_timer timer) return 0; } -static inline void timer_set_cval(enum arch_timer timer, uint64_t cval) +static inline void timer_set_cval(enum arch_timer timer, u64 cval) { switch (timer) { case VIRTUAL: @@ -64,7 +64,7 @@ static inline void timer_set_cval(enum arch_timer timer, uint64_t cval) isb(); } -static inline uint64_t timer_get_cval(enum arch_timer timer) +static inline u64 timer_get_cval(enum arch_timer timer) { switch (timer) { case VIRTUAL: @@ -79,7 +79,7 @@ static inline uint64_t timer_get_cval(enum arch_timer timer) return 0; } -static inline void timer_set_tval(enum arch_timer timer, int32_t tval) +static inline void timer_set_tval(enum arch_timer timer, s32 tval) { switch (timer) { case VIRTUAL: @@ -95,7 +95,7 @@ static inline void timer_set_tval(enum arch_timer timer, int32_t tval) isb(); } -static inline int32_t timer_get_tval(enum arch_timer timer) +static inline s32 timer_get_tval(enum arch_timer timer) { isb(); switch (timer) { @@ -111,7 +111,7 @@ static inline int32_t timer_get_tval(enum arch_timer timer) return 0; } -static inline void timer_set_ctl(enum arch_timer timer, uint32_t ctl) +static inline void timer_set_ctl(enum arch_timer timer, u32 ctl) { switch (timer) { case VIRTUAL: @@ -127,7 +127,7 @@ static inline void timer_set_ctl(enum arch_timer timer, uint32_t ctl) isb(); } -static inline uint32_t timer_get_ctl(enum arch_timer timer) +static inline u32 timer_get_ctl(enum arch_timer timer) { switch (timer) { case VIRTUAL: @@ -142,15 +142,15 @@ static inline uint32_t timer_get_ctl(enum arch_timer timer) return 0; } -static inline void timer_set_next_cval_ms(enum arch_timer timer, uint32_t msec) +static inline void timer_set_next_cval_ms(enum arch_timer timer, u32 msec) { - uint64_t now_ct = timer_get_cntct(timer); - uint64_t next_ct = now_ct + msec_to_cycles(msec); + u64 now_ct = timer_get_cntct(timer); + u64 next_ct = now_ct + msec_to_cycles(msec); timer_set_cval(timer, next_ct); } -static inline void timer_set_next_tval_ms(enum arch_timer timer, uint32_t msec) +static inline void timer_set_next_tval_ms(enum arch_timer timer, u32 msec) { timer_set_tval(timer, msec_to_cycles(msec)); } diff --git a/tools/testing/selftests/kvm/include/arm64/delay.h b/tools/testing/selftests/kvm/include/arm64/delay.h index 329e4f5079ea..6a5d4634af2c 100644 --- a/tools/testing/selftests/kvm/include/arm64/delay.h +++ b/tools/testing/selftests/kvm/include/arm64/delay.h @@ -8,10 +8,10 @@ #include "arch_timer.h" -static inline void __delay(uint64_t cycles) +static inline void __delay(u64 cycles) { enum arch_timer timer = VIRTUAL; - uint64_t start = timer_get_cntct(timer); + u64 start = timer_get_cntct(timer); while ((timer_get_cntct(timer) - start) < cycles) cpu_relax(); diff --git a/tools/testing/selftests/kvm/include/arm64/gic.h b/tools/testing/selftests/kvm/include/arm64/gic.h index cc7a7f34ed37..615745093c98 100644 --- a/tools/testing/selftests/kvm/include/arm64/gic.h +++ b/tools/testing/selftests/kvm/include/arm64/gic.h @@ -48,8 +48,8 @@ void gic_set_dir(unsigned int intid); * split is true, EOI drops the priority and deactivates the interrupt. */ void gic_set_eoi_split(bool split); -void gic_set_priority_mask(uint64_t mask); -void gic_set_priority(uint32_t intid, uint32_t prio); +void gic_set_priority_mask(u64 mask); +void gic_set_priority(u32 intid, u32 prio); void gic_irq_set_active(unsigned int intid); void gic_irq_clear_active(unsigned int intid); bool gic_irq_get_active(unsigned int intid); @@ -59,7 +59,7 @@ bool gic_irq_get_pending(unsigned int intid); void gic_irq_set_config(unsigned int intid, bool is_edge); void gic_irq_set_group(unsigned int intid, bool group); -void gic_rdist_enable_lpis(vm_paddr_t cfg_table, size_t cfg_table_size, - vm_paddr_t pend_table); +void gic_rdist_enable_lpis(gpa_t cfg_table, size_t cfg_table_size, + gpa_t pend_table); #endif /* SELFTEST_KVM_GIC_H */ diff --git a/tools/testing/selftests/kvm/include/arm64/gic_v3_its.h b/tools/testing/selftests/kvm/include/arm64/gic_v3_its.h index 58feef3eb386..a43a407e2d5c 100644 --- a/tools/testing/selftests/kvm/include/arm64/gic_v3_its.h +++ b/tools/testing/selftests/kvm/include/arm64/gic_v3_its.h @@ -5,11 +5,10 @@ #include <linux/sizes.h> -void its_init(vm_paddr_t coll_tbl, size_t coll_tbl_sz, - vm_paddr_t device_tbl, size_t device_tbl_sz, - vm_paddr_t cmdq, size_t cmdq_size); +void its_init(gpa_t coll_tbl, size_t coll_tbl_sz, gpa_t device_tbl, + size_t device_tbl_sz, gpa_t cmdq, size_t cmdq_size); -void its_send_mapd_cmd(void *cmdq_base, u32 device_id, vm_paddr_t itt_base, +void its_send_mapd_cmd(void *cmdq_base, u32 device_id, gpa_t itt_base, size_t itt_size, bool valid); void its_send_mapc_cmd(void *cmdq_base, u32 vcpu_id, u32 collection_id, bool valid); void its_send_mapti_cmd(void *cmdq_base, u32 device_id, u32 event_id, diff --git a/tools/testing/selftests/kvm/include/arm64/processor.h b/tools/testing/selftests/kvm/include/arm64/processor.h index ac97a1c436fc..b8a902ba8573 100644 --- a/tools/testing/selftests/kvm/include/arm64/processor.h +++ b/tools/testing/selftests/kvm/include/arm64/processor.h @@ -128,7 +128,7 @@ #define PTE_ADDR_51_50_LPA2_SHIFT 8 void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init); -struct kvm_vcpu *aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, +struct kvm_vcpu *aarch64_vcpu_add(struct kvm_vm *vm, u32 vcpu_id, struct kvm_vcpu_init *init, void *guest_code); struct ex_regs { @@ -167,8 +167,8 @@ enum { (v) == VECTOR_SYNC_LOWER_64 || \ (v) == VECTOR_SYNC_LOWER_32) -void aarch64_get_supported_page_sizes(uint32_t ipa, uint32_t *ipa4k, - uint32_t *ipa16k, uint32_t *ipa64k); +void aarch64_get_supported_page_sizes(u32 ipa, u32 *ipa4k, + u32 *ipa16k, u32 *ipa64k); void vm_init_descriptor_tables(struct kvm_vm *vm); void vcpu_init_descriptor_tables(struct kvm_vcpu *vcpu); @@ -179,8 +179,8 @@ void vm_install_exception_handler(struct kvm_vm *vm, void vm_install_sync_handler(struct kvm_vm *vm, int vector, int ec, handler_fn handler); -uint64_t *virt_get_pte_hva_at_level(struct kvm_vm *vm, vm_vaddr_t gva, int level); -uint64_t *virt_get_pte_hva(struct kvm_vm *vm, vm_vaddr_t gva); +u64 *virt_get_pte_hva_at_level(struct kvm_vm *vm, gva_t gva, int level); +u64 *virt_get_pte_hva(struct kvm_vm *vm, gva_t gva); static inline void cpu_relax(void) { @@ -287,9 +287,9 @@ struct arm_smccc_res { * @res: pointer to write the return values from registers x0-x3 * */ -void smccc_hvc(uint32_t function_id, uint64_t arg0, uint64_t arg1, - uint64_t arg2, uint64_t arg3, uint64_t arg4, uint64_t arg5, - uint64_t arg6, struct arm_smccc_res *res); +void smccc_hvc(u32 function_id, u64 arg0, u64 arg1, + u64 arg2, u64 arg3, u64 arg4, u64 arg5, + u64 arg6, struct arm_smccc_res *res); /** * smccc_smc - Invoke a SMCCC function using the smc conduit @@ -298,9 +298,9 @@ void smccc_hvc(uint32_t function_id, uint64_t arg0, uint64_t arg1, * @res: pointer to write the return values from registers x0-x3 * */ -void smccc_smc(uint32_t function_id, uint64_t arg0, uint64_t arg1, - uint64_t arg2, uint64_t arg3, uint64_t arg4, uint64_t arg5, - uint64_t arg6, struct arm_smccc_res *res); +void smccc_smc(u32 function_id, u64 arg0, u64 arg1, + u64 arg2, u64 arg3, u64 arg4, u64 arg5, + u64 arg6, struct arm_smccc_res *res); /* Execute a Wait For Interrupt instruction. */ void wfi(void); diff --git a/tools/testing/selftests/kvm/include/arm64/ucall.h b/tools/testing/selftests/kvm/include/arm64/ucall.h index 4ec801f37f00..2210d3d94c40 100644 --- a/tools/testing/selftests/kvm/include/arm64/ucall.h +++ b/tools/testing/selftests/kvm/include/arm64/ucall.h @@ -10,9 +10,9 @@ * ucall_exit_mmio_addr holds per-VM values (global data is duplicated by each * VM), it must not be accessed from host code. */ -extern vm_vaddr_t *ucall_exit_mmio_addr; +extern gva_t *ucall_exit_mmio_addr; -static inline void ucall_arch_do_ucall(vm_vaddr_t uc) +static inline void ucall_arch_do_ucall(gva_t uc) { WRITE_ONCE(*ucall_exit_mmio_addr, uc); } diff --git a/tools/testing/selftests/kvm/include/arm64/vgic.h b/tools/testing/selftests/kvm/include/arm64/vgic.h index 688beccc9436..1f8b04373987 100644 --- a/tools/testing/selftests/kvm/include/arm64/vgic.h +++ b/tools/testing/selftests/kvm/include/arm64/vgic.h @@ -11,27 +11,27 @@ #include "kvm_util.h" #define REDIST_REGION_ATTR_ADDR(count, base, flags, index) \ - (((uint64_t)(count) << 52) | \ - ((uint64_t)((base) >> 16) << 16) | \ - ((uint64_t)(flags) << 12) | \ + (((u64)(count) << 52) | \ + ((u64)((base) >> 16) << 16) | \ + ((u64)(flags) << 12) | \ index) bool kvm_supports_vgic_v3(void); -int __vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs); +int __vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, u32 nr_irqs); void __vgic_v3_init(int fd); -int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs); +int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, u32 nr_irqs); #define VGIC_MAX_RESERVED 1023 -void kvm_irq_set_level_info(int gic_fd, uint32_t intid, int level); -int _kvm_irq_set_level_info(int gic_fd, uint32_t intid, int level); +void kvm_irq_set_level_info(int gic_fd, u32 intid, int level); +int _kvm_irq_set_level_info(int gic_fd, u32 intid, int level); -void kvm_arm_irq_line(struct kvm_vm *vm, uint32_t intid, int level); -int _kvm_arm_irq_line(struct kvm_vm *vm, uint32_t intid, int level); +void kvm_arm_irq_line(struct kvm_vm *vm, u32 intid, int level); +int _kvm_arm_irq_line(struct kvm_vm *vm, u32 intid, int level); /* The vcpu arg only applies to private interrupts. */ -void kvm_irq_write_ispendr(int gic_fd, uint32_t intid, struct kvm_vcpu *vcpu); -void kvm_irq_write_isactiver(int gic_fd, uint32_t intid, struct kvm_vcpu *vcpu); +void kvm_irq_write_ispendr(int gic_fd, u32 intid, struct kvm_vcpu *vcpu); +void kvm_irq_write_isactiver(int gic_fd, u32 intid, struct kvm_vcpu *vcpu); #define KVM_IRQCHIP_NUM_PINS (1020 - 32) diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index f861242b4ae8..2ecaaa0e9965 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -58,7 +58,7 @@ struct kvm_binary_stats { struct kvm_vcpu { struct list_head list; - uint32_t id; + u32 id; int fd; struct kvm_vm *vm; struct kvm_run *run; @@ -70,8 +70,8 @@ struct kvm_vcpu { #endif struct kvm_binary_stats stats; struct kvm_dirty_gfn *dirty_gfns; - uint32_t fetch_index; - uint32_t dirty_gfns_count; + u32 fetch_index; + u32 dirty_gfns_count; }; struct userspace_mem_regions { @@ -90,7 +90,7 @@ enum kvm_mem_region_type { struct kvm_mmu { bool pgd_created; - uint64_t pgd; + u64 pgd; int pgtable_levels; struct kvm_mmu_arch arch; @@ -105,16 +105,16 @@ struct kvm_vm { unsigned int page_shift; unsigned int pa_bits; unsigned int va_bits; - uint64_t max_gfn; + u64 max_gfn; struct list_head vcpus; struct userspace_mem_regions regions; struct sparsebit *vpages_valid; struct sparsebit *vpages_mapped; bool has_irqchip; - vm_paddr_t ucall_mmio_addr; - vm_vaddr_t handlers; - uint32_t dirty_ring_size; - uint64_t gpa_tag_mask; + gpa_t ucall_mmio_addr; + gva_t handlers; + u32 dirty_ring_size; + gpa_t gpa_tag_mask; /* * "mmu" is the guest's stage-1, with a short name because the vast @@ -132,7 +132,7 @@ struct kvm_vm { * allocators, e.g., lib/elf uses the memslots[MEM_REGION_CODE] * memslot. */ - uint32_t memslots[NR_MEM_REGIONS]; + u32 memslots[NR_MEM_REGIONS]; }; struct vcpu_reg_sublist { @@ -164,7 +164,7 @@ struct vcpu_reg_list { else struct userspace_mem_region * -memslot2region(struct kvm_vm *vm, uint32_t memslot); +memslot2region(struct kvm_vm *vm, u32 memslot); static inline struct userspace_mem_region *vm_get_mem_region(struct kvm_vm *vm, enum kvm_mem_region_type type) @@ -213,13 +213,13 @@ enum vm_guest_mode { }; struct vm_shape { - uint32_t type; - uint8_t mode; - uint8_t pad0; - uint16_t pad1; + u32 type; + u8 mode; + u8 pad0; + u16 pad1; }; -kvm_static_assert(sizeof(struct vm_shape) == sizeof(uint64_t)); +kvm_static_assert(sizeof(struct vm_shape) == sizeof(u64)); #define VM_TYPE_DEFAULT 0 @@ -404,21 +404,22 @@ static inline int vm_check_cap(struct kvm_vm *vm, long cap) return ret; } -static inline int __vm_enable_cap(struct kvm_vm *vm, uint32_t cap, uint64_t arg0) +static inline int __vm_enable_cap(struct kvm_vm *vm, u32 cap, u64 arg0) { struct kvm_enable_cap enable_cap = { .cap = cap, .args = { arg0 } }; return __vm_ioctl(vm, KVM_ENABLE_CAP, &enable_cap); } -static inline void vm_enable_cap(struct kvm_vm *vm, uint32_t cap, uint64_t arg0) + +static inline void vm_enable_cap(struct kvm_vm *vm, u32 cap, u64 arg0) { struct kvm_enable_cap enable_cap = { .cap = cap, .args = { arg0 } }; vm_ioctl(vm, KVM_ENABLE_CAP, &enable_cap); } -static inline void vm_set_memory_attributes(struct kvm_vm *vm, uint64_t gpa, - uint64_t size, uint64_t attributes) +static inline void vm_set_memory_attributes(struct kvm_vm *vm, gpa_t gpa, + u64 size, u64 attributes) { struct kvm_memory_attributes attr = { .attributes = attributes, @@ -438,35 +439,35 @@ static inline void vm_set_memory_attributes(struct kvm_vm *vm, uint64_t gpa, } -static inline void vm_mem_set_private(struct kvm_vm *vm, uint64_t gpa, - uint64_t size) +static inline void vm_mem_set_private(struct kvm_vm *vm, gpa_t gpa, + u64 size) { vm_set_memory_attributes(vm, gpa, size, KVM_MEMORY_ATTRIBUTE_PRIVATE); } -static inline void vm_mem_set_shared(struct kvm_vm *vm, uint64_t gpa, - uint64_t size) +static inline void vm_mem_set_shared(struct kvm_vm *vm, gpa_t gpa, + u64 size) { vm_set_memory_attributes(vm, gpa, size, 0); } -void vm_guest_mem_fallocate(struct kvm_vm *vm, uint64_t gpa, uint64_t size, +void vm_guest_mem_fallocate(struct kvm_vm *vm, gpa_t gpa, u64 size, bool punch_hole); -static inline void vm_guest_mem_punch_hole(struct kvm_vm *vm, uint64_t gpa, - uint64_t size) +static inline void vm_guest_mem_punch_hole(struct kvm_vm *vm, gpa_t gpa, + u64 size) { vm_guest_mem_fallocate(vm, gpa, size, true); } -static inline void vm_guest_mem_allocate(struct kvm_vm *vm, uint64_t gpa, - uint64_t size) +static inline void vm_guest_mem_allocate(struct kvm_vm *vm, gpa_t gpa, + u64 size) { vm_guest_mem_fallocate(vm, gpa, size, false); } -void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size); -const char *vm_guest_mode_string(uint32_t i); +void vm_enable_dirty_ring(struct kvm_vm *vm, u32 ring_size); +const char *vm_guest_mode_string(u32 i); void kvm_vm_free(struct kvm_vm *vmp); void kvm_vm_restart(struct kvm_vm *vmp); @@ -474,7 +475,7 @@ void kvm_vm_release(struct kvm_vm *vmp); void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename); int kvm_memfd_alloc(size_t size, bool hugepages); -void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent); +void vm_dump(FILE *stream, struct kvm_vm *vm, u8 indent); static inline void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log) { @@ -484,7 +485,7 @@ static inline void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log) } static inline void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log, - uint64_t first_page, uint32_t num_pages) + u64 first_page, u32 num_pages) { struct kvm_clear_dirty_log args = { .dirty_bitmap = log, @@ -496,14 +497,14 @@ static inline void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log vm_ioctl(vm, KVM_CLEAR_DIRTY_LOG, &args); } -static inline uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm) +static inline u32 kvm_vm_reset_dirty_ring(struct kvm_vm *vm) { return __vm_ioctl(vm, KVM_RESET_DIRTY_RINGS, NULL); } static inline void kvm_vm_register_coalesced_io(struct kvm_vm *vm, - uint64_t address, - uint64_t size, bool pio) + u64 address, + u64 size, bool pio) { struct kvm_coalesced_mmio_zone zone = { .addr = address, @@ -515,8 +516,8 @@ static inline void kvm_vm_register_coalesced_io(struct kvm_vm *vm, } static inline void kvm_vm_unregister_coalesced_io(struct kvm_vm *vm, - uint64_t address, - uint64_t size, bool pio) + u64 address, + u64 size, bool pio) { struct kvm_coalesced_mmio_zone zone = { .addr = address, @@ -535,8 +536,8 @@ static inline int vm_get_stats_fd(struct kvm_vm *vm) return fd; } -static inline int __kvm_irqfd(struct kvm_vm *vm, uint32_t gsi, int eventfd, - uint32_t flags) +static inline int __kvm_irqfd(struct kvm_vm *vm, u32 gsi, int eventfd, + u32 flags) { struct kvm_irqfd irqfd = { .fd = eventfd, @@ -548,20 +549,19 @@ static inline int __kvm_irqfd(struct kvm_vm *vm, uint32_t gsi, int eventfd, return __vm_ioctl(vm, KVM_IRQFD, &irqfd); } -static inline void kvm_irqfd(struct kvm_vm *vm, uint32_t gsi, int eventfd, - uint32_t flags) +static inline void kvm_irqfd(struct kvm_vm *vm, u32 gsi, int eventfd, u32 flags) { int ret = __kvm_irqfd(vm, gsi, eventfd, flags); TEST_ASSERT_VM_VCPU_IOCTL(!ret, KVM_IRQFD, ret, vm); } -static inline void kvm_assign_irqfd(struct kvm_vm *vm, uint32_t gsi, int eventfd) +static inline void kvm_assign_irqfd(struct kvm_vm *vm, u32 gsi, int eventfd) { kvm_irqfd(vm, gsi, eventfd, 0); } -static inline void kvm_deassign_irqfd(struct kvm_vm *vm, uint32_t gsi, int eventfd) +static inline void kvm_deassign_irqfd(struct kvm_vm *vm, u32 gsi, int eventfd) { kvm_irqfd(vm, gsi, eventfd, KVM_IRQFD_FLAG_DEASSIGN); } @@ -610,15 +610,15 @@ static inline struct kvm_stats_desc *get_stats_descriptor(struct kvm_stats_desc } void read_stat_data(int stats_fd, struct kvm_stats_header *header, - struct kvm_stats_desc *desc, uint64_t *data, + struct kvm_stats_desc *desc, u64 *data, size_t max_elements); void kvm_get_stat(struct kvm_binary_stats *stats, const char *name, - uint64_t *data, size_t max_elements); + u64 *data, size_t max_elements); #define __get_stat(stats, stat) \ ({ \ - uint64_t data; \ + u64 data; \ \ kvm_get_stat(stats, #stat, &data, 1); \ data; \ @@ -664,8 +664,8 @@ static inline bool is_smt_on(void) void vm_create_irqchip(struct kvm_vm *vm); -static inline int __vm_create_guest_memfd(struct kvm_vm *vm, uint64_t size, - uint64_t flags) +static inline int __vm_create_guest_memfd(struct kvm_vm *vm, u64 size, + u64 flags) { struct kvm_create_guest_memfd guest_memfd = { .size = size, @@ -675,8 +675,8 @@ static inline int __vm_create_guest_memfd(struct kvm_vm *vm, uint64_t size, return __vm_ioctl(vm, KVM_CREATE_GUEST_MEMFD, &guest_memfd); } -static inline int vm_create_guest_memfd(struct kvm_vm *vm, uint64_t size, - uint64_t flags) +static inline int vm_create_guest_memfd(struct kvm_vm *vm, u64 size, + u64 flags) { int fd = __vm_create_guest_memfd(vm, size, flags); @@ -684,24 +684,23 @@ static inline int vm_create_guest_memfd(struct kvm_vm *vm, uint64_t size, return fd; } -void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags, - uint64_t gpa, uint64_t size, void *hva); -int __vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags, - uint64_t gpa, uint64_t size, void *hva); -void vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags, - uint64_t gpa, uint64_t size, void *hva, - uint32_t guest_memfd, uint64_t guest_memfd_offset); -int __vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags, - uint64_t gpa, uint64_t size, void *hva, - uint32_t guest_memfd, uint64_t guest_memfd_offset); +void vm_set_user_memory_region(struct kvm_vm *vm, u32 slot, u32 flags, + gpa_t gpa, u64 size, void *hva); +int __vm_set_user_memory_region(struct kvm_vm *vm, u32 slot, u32 flags, + gpa_t gpa, u64 size, void *hva); +void vm_set_user_memory_region2(struct kvm_vm *vm, u32 slot, u32 flags, + gpa_t gpa, u64 size, void *hva, + u32 guest_memfd, u64 guest_memfd_offset); +int __vm_set_user_memory_region2(struct kvm_vm *vm, u32 slot, u32 flags, + gpa_t gpa, u64 size, void *hva, + u32 guest_memfd, u64 guest_memfd_offset); void vm_userspace_mem_region_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, - uint64_t gpa, uint32_t slot, uint64_t npages, - uint32_t flags); + gpa_t gpa, u32 slot, u64 npages, u32 flags); void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, - uint64_t gpa, uint32_t slot, uint64_t npages, uint32_t flags, - int guest_memfd_fd, uint64_t guest_memfd_offset); + gpa_t gpa, u32 slot, u64 npages, u32 flags, + int guest_memfd_fd, u64 guest_memfd_offset); #ifndef vm_arch_has_protected_memory static inline bool vm_arch_has_protected_memory(struct kvm_vm *vm) @@ -710,36 +709,34 @@ static inline bool vm_arch_has_protected_memory(struct kvm_vm *vm) } #endif -void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags); -void vm_mem_region_reload(struct kvm_vm *vm, uint32_t slot); -void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa); -void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot); -struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id); -void vm_populate_vaddr_bitmap(struct kvm_vm *vm); -vm_vaddr_t vm_vaddr_unused_gap(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min); -vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min); -vm_vaddr_t __vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, - enum kvm_mem_region_type type); -vm_vaddr_t vm_vaddr_alloc_shared(struct kvm_vm *vm, size_t sz, - vm_vaddr_t vaddr_min, - enum kvm_mem_region_type type); -vm_vaddr_t vm_vaddr_alloc_pages(struct kvm_vm *vm, int nr_pages); -vm_vaddr_t __vm_vaddr_alloc_page(struct kvm_vm *vm, - enum kvm_mem_region_type type); -vm_vaddr_t vm_vaddr_alloc_page(struct kvm_vm *vm); - -void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, +void vm_mem_region_set_flags(struct kvm_vm *vm, u32 slot, u32 flags); +void vm_mem_region_reload(struct kvm_vm *vm, u32 slot); +void vm_mem_region_move(struct kvm_vm *vm, u32 slot, u64 new_gpa); +void vm_mem_region_delete(struct kvm_vm *vm, u32 slot); +struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, u32 vcpu_id); +void vm_populate_gva_bitmap(struct kvm_vm *vm); +gva_t vm_unused_gva_gap(struct kvm_vm *vm, size_t sz, gva_t min_gva); +gva_t vm_alloc(struct kvm_vm *vm, size_t sz, gva_t min_gva); +gva_t __vm_alloc(struct kvm_vm *vm, size_t sz, gva_t min_gva, + enum kvm_mem_region_type type); +gva_t vm_alloc_shared(struct kvm_vm *vm, size_t sz, gva_t min_gva, + enum kvm_mem_region_type type); +gva_t vm_alloc_pages(struct kvm_vm *vm, int nr_pages); +gva_t __vm_alloc_page(struct kvm_vm *vm, enum kvm_mem_region_type type); +gva_t vm_alloc_page(struct kvm_vm *vm); + +void virt_map(struct kvm_vm *vm, gva_t gva, gpa_t gpa, unsigned int npages); -void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa); -void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva); -vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva); -void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa); +void *addr_gpa2hva(struct kvm_vm *vm, gpa_t gpa); +void *addr_gva2hva(struct kvm_vm *vm, gva_t gva); +gpa_t addr_hva2gpa(struct kvm_vm *vm, void *hva); +void *addr_gpa2alias(struct kvm_vm *vm, gpa_t gpa); #ifndef vcpu_arch_put_guest #define vcpu_arch_put_guest(mem, val) do { (mem) = (val); } while (0) #endif -static inline vm_paddr_t vm_untag_gpa(struct kvm_vm *vm, vm_paddr_t gpa) +static inline gpa_t vm_untag_gpa(struct kvm_vm *vm, gpa_t gpa) { return gpa & ~vm->gpa_tag_mask; } @@ -755,8 +752,8 @@ static inline int __vcpu_run(struct kvm_vcpu *vcpu) void vcpu_run_complete_io(struct kvm_vcpu *vcpu); struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vcpu *vcpu); -static inline void vcpu_enable_cap(struct kvm_vcpu *vcpu, uint32_t cap, - uint64_t arg0) +static inline void vcpu_enable_cap(struct kvm_vcpu *vcpu, u32 cap, + u64 arg0) { struct kvm_enable_cap enable_cap = { .cap = cap, .args = { arg0 } }; @@ -811,31 +808,34 @@ static inline void vcpu_fpu_set(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) vcpu_ioctl(vcpu, KVM_SET_FPU, fpu); } -static inline int __vcpu_get_reg(struct kvm_vcpu *vcpu, uint64_t id, void *addr) +static inline int __vcpu_get_reg(struct kvm_vcpu *vcpu, u64 id, void *addr) { - struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)addr }; + struct kvm_one_reg reg = { .id = id, .addr = (u64)addr }; return __vcpu_ioctl(vcpu, KVM_GET_ONE_REG, ®); } -static inline int __vcpu_set_reg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t val) + +static inline int __vcpu_set_reg(struct kvm_vcpu *vcpu, u64 id, u64 val) { - struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)&val }; + struct kvm_one_reg reg = { .id = id, .addr = (u64)&val }; return __vcpu_ioctl(vcpu, KVM_SET_ONE_REG, ®); } -static inline uint64_t vcpu_get_reg(struct kvm_vcpu *vcpu, uint64_t id) + +static inline u64 vcpu_get_reg(struct kvm_vcpu *vcpu, u64 id) { - uint64_t val; - struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)&val }; + u64 val; + struct kvm_one_reg reg = { .id = id, .addr = (u64)&val }; TEST_ASSERT(KVM_REG_SIZE(id) <= sizeof(val), "Reg %lx too big", id); vcpu_ioctl(vcpu, KVM_GET_ONE_REG, ®); return val; } -static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t val) + +static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u64 id, u64 val) { - struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)&val }; + struct kvm_one_reg reg = { .id = id, .addr = (u64)&val }; TEST_ASSERT(KVM_REG_SIZE(id) <= sizeof(val), "Reg %lx too big", id); @@ -880,75 +880,75 @@ static inline int vcpu_get_stats_fd(struct kvm_vcpu *vcpu) return fd; } -int __kvm_has_device_attr(int dev_fd, uint32_t group, uint64_t attr); +int __kvm_has_device_attr(int dev_fd, u32 group, u64 attr); -static inline void kvm_has_device_attr(int dev_fd, uint32_t group, uint64_t attr) +static inline void kvm_has_device_attr(int dev_fd, u32 group, u64 attr) { int ret = __kvm_has_device_attr(dev_fd, group, attr); TEST_ASSERT(!ret, "KVM_HAS_DEVICE_ATTR failed, rc: %i errno: %i", ret, errno); } -int __kvm_device_attr_get(int dev_fd, uint32_t group, uint64_t attr, void *val); +int __kvm_device_attr_get(int dev_fd, u32 group, u64 attr, void *val); -static inline void kvm_device_attr_get(int dev_fd, uint32_t group, - uint64_t attr, void *val) +static inline void kvm_device_attr_get(int dev_fd, u32 group, + u64 attr, void *val) { int ret = __kvm_device_attr_get(dev_fd, group, attr, val); TEST_ASSERT(!ret, KVM_IOCTL_ERROR(KVM_GET_DEVICE_ATTR, ret)); } -int __kvm_device_attr_set(int dev_fd, uint32_t group, uint64_t attr, void *val); +int __kvm_device_attr_set(int dev_fd, u32 group, u64 attr, void *val); -static inline void kvm_device_attr_set(int dev_fd, uint32_t group, - uint64_t attr, void *val) +static inline void kvm_device_attr_set(int dev_fd, u32 group, + u64 attr, void *val) { int ret = __kvm_device_attr_set(dev_fd, group, attr, val); TEST_ASSERT(!ret, KVM_IOCTL_ERROR(KVM_SET_DEVICE_ATTR, ret)); } -static inline int __vcpu_has_device_attr(struct kvm_vcpu *vcpu, uint32_t group, - uint64_t attr) +static inline int __vcpu_has_device_attr(struct kvm_vcpu *vcpu, u32 group, + u64 attr) { return __kvm_has_device_attr(vcpu->fd, group, attr); } -static inline void vcpu_has_device_attr(struct kvm_vcpu *vcpu, uint32_t group, - uint64_t attr) +static inline void vcpu_has_device_attr(struct kvm_vcpu *vcpu, u32 group, + u64 attr) { kvm_has_device_attr(vcpu->fd, group, attr); } -static inline int __vcpu_device_attr_get(struct kvm_vcpu *vcpu, uint32_t group, - uint64_t attr, void *val) +static inline int __vcpu_device_attr_get(struct kvm_vcpu *vcpu, u32 group, + u64 attr, void *val) { return __kvm_device_attr_get(vcpu->fd, group, attr, val); } -static inline void vcpu_device_attr_get(struct kvm_vcpu *vcpu, uint32_t group, - uint64_t attr, void *val) +static inline void vcpu_device_attr_get(struct kvm_vcpu *vcpu, u32 group, + u64 attr, void *val) { kvm_device_attr_get(vcpu->fd, group, attr, val); } -static inline int __vcpu_device_attr_set(struct kvm_vcpu *vcpu, uint32_t group, - uint64_t attr, void *val) +static inline int __vcpu_device_attr_set(struct kvm_vcpu *vcpu, u32 group, + u64 attr, void *val) { return __kvm_device_attr_set(vcpu->fd, group, attr, val); } -static inline void vcpu_device_attr_set(struct kvm_vcpu *vcpu, uint32_t group, - uint64_t attr, void *val) +static inline void vcpu_device_attr_set(struct kvm_vcpu *vcpu, u32 group, + u64 attr, void *val) { kvm_device_attr_set(vcpu->fd, group, attr, val); } -int __kvm_test_create_device(struct kvm_vm *vm, uint64_t type); -int __kvm_create_device(struct kvm_vm *vm, uint64_t type); +int __kvm_test_create_device(struct kvm_vm *vm, u64 type); +int __kvm_create_device(struct kvm_vm *vm, u64 type); -static inline int kvm_create_device(struct kvm_vm *vm, uint64_t type) +static inline int kvm_create_device(struct kvm_vm *vm, u64 type) { int fd = __kvm_create_device(vm, type); @@ -964,7 +964,7 @@ void *vcpu_map_dirty_ring(struct kvm_vcpu *vcpu); * Input Args: * vcpu - vCPU * num - number of arguments - * ... - arguments, each of type uint64_t + * ... - arguments, each of type u64 * * Output Args: None * @@ -972,40 +972,38 @@ void *vcpu_map_dirty_ring(struct kvm_vcpu *vcpu); * * Sets the first @num input parameters for the function at @vcpu's entry point, * per the C calling convention of the architecture, to the values given as - * variable args. Each of the variable args is expected to be of type uint64_t. + * variable args. Each of the variable args is expected to be of type u64. * The maximum @num can be is specific to the architecture. */ void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...); -void kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level); -int _kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level); +void kvm_irq_line(struct kvm_vm *vm, u32 irq, int level); +int _kvm_irq_line(struct kvm_vm *vm, u32 irq, int level); #define KVM_MAX_IRQ_ROUTES 4096 struct kvm_irq_routing *kvm_gsi_routing_create(void); void kvm_gsi_routing_irqchip_add(struct kvm_irq_routing *routing, - uint32_t gsi, uint32_t pin); + u32 gsi, u32 pin); int _kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing); void kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing); const char *exit_reason_str(unsigned int exit_reason); -vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min, - uint32_t memslot); -vm_paddr_t __vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, - vm_paddr_t paddr_min, uint32_t memslot, - bool protected); -vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm); +gpa_t vm_phy_page_alloc(struct kvm_vm *vm, gpa_t min_gpa, u32 memslot); +gpa_t __vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, gpa_t min_gpa, + u32 memslot, bool protected); +gpa_t vm_alloc_page_table(struct kvm_vm *vm); -static inline vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, - vm_paddr_t paddr_min, uint32_t memslot) +static inline gpa_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, + gpa_t min_gpa, u32 memslot) { /* * By default, allocate memory as protected for VMs that support * protected memory, as the majority of memory for such VMs is * protected, i.e. using shared memory is effectively opt-in. */ - return __vm_phy_pages_alloc(vm, num, paddr_min, memslot, + return __vm_phy_pages_alloc(vm, num, min_gpa, memslot, vm_arch_has_protected_memory(vm)); } @@ -1016,8 +1014,8 @@ static inline vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, * calculate the amount of memory needed for per-vCPU data, e.g. stacks. */ struct kvm_vm *____vm_create(struct vm_shape shape); -struct kvm_vm *__vm_create(struct vm_shape shape, uint32_t nr_runnable_vcpus, - uint64_t nr_extra_pages); +struct kvm_vm *__vm_create(struct vm_shape shape, u32 nr_runnable_vcpus, + u64 nr_extra_pages); static inline struct kvm_vm *vm_create_barebones(void) { @@ -1034,16 +1032,16 @@ static inline struct kvm_vm *vm_create_barebones_type(unsigned long type) return ____vm_create(shape); } -static inline struct kvm_vm *vm_create(uint32_t nr_runnable_vcpus) +static inline struct kvm_vm *vm_create(u32 nr_runnable_vcpus) { return __vm_create(VM_SHAPE_DEFAULT, nr_runnable_vcpus, 0); } -struct kvm_vm *__vm_create_with_vcpus(struct vm_shape shape, uint32_t nr_vcpus, - uint64_t extra_mem_pages, +struct kvm_vm *__vm_create_with_vcpus(struct vm_shape shape, u32 nr_vcpus, + u64 extra_mem_pages, void *guest_code, struct kvm_vcpu *vcpus[]); -static inline struct kvm_vm *vm_create_with_vcpus(uint32_t nr_vcpus, +static inline struct kvm_vm *vm_create_with_vcpus(u32 nr_vcpus, void *guest_code, struct kvm_vcpu *vcpus[]) { @@ -1054,7 +1052,7 @@ static inline struct kvm_vm *vm_create_with_vcpus(uint32_t nr_vcpus, struct kvm_vm *__vm_create_shape_with_one_vcpu(struct vm_shape shape, struct kvm_vcpu **vcpu, - uint64_t extra_mem_pages, + u64 extra_mem_pages, void *guest_code); /* @@ -1062,7 +1060,7 @@ struct kvm_vm *__vm_create_shape_with_one_vcpu(struct vm_shape shape, * additional pages of guest memory. Returns the VM and vCPU (via out param). */ static inline struct kvm_vm *__vm_create_with_one_vcpu(struct kvm_vcpu **vcpu, - uint64_t extra_mem_pages, + u64 extra_mem_pages, void *guest_code) { return __vm_create_shape_with_one_vcpu(VM_SHAPE_DEFAULT, vcpu, @@ -1084,7 +1082,7 @@ static inline struct kvm_vm *vm_create_shape_with_one_vcpu(struct vm_shape shape struct kvm_vcpu *vm_recreate_with_one_vcpu(struct kvm_vm *vm); -void kvm_set_files_rlimit(uint32_t nr_vcpus); +void kvm_set_files_rlimit(u32 nr_vcpus); int __pin_task_to_cpu(pthread_t task, int cpu); @@ -1115,7 +1113,7 @@ static inline int pin_self_to_any_cpu(void) } void kvm_print_vcpu_pinning_help(void); -void kvm_parse_vcpu_pinning(const char *pcpus_string, uint32_t vcpu_to_pcpu[], +void kvm_parse_vcpu_pinning(const char *pcpus_string, u32 vcpu_to_pcpu[], int nr_vcpus); unsigned long vm_compute_max_gfn(struct kvm_vm *vm); @@ -1131,12 +1129,12 @@ vm_adjust_num_guest_pages(enum vm_guest_mode mode, unsigned int num_guest_pages) } #define sync_global_to_guest(vm, g) ({ \ - typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \ + typeof(g) *_p = addr_gva2hva(vm, (gva_t)&(g)); \ memcpy(_p, &(g), sizeof(g)); \ }) #define sync_global_from_guest(vm, g) ({ \ - typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \ + typeof(g) *_p = addr_gva2hva(vm, (gva_t)&(g)); \ memcpy(&(g), _p, sizeof(g)); \ }) @@ -1147,7 +1145,7 @@ vm_adjust_num_guest_pages(enum vm_guest_mode mode, unsigned int num_guest_pages) * undesirable to change the host's copy of the global. */ #define write_guest_global(vm, g, val) ({ \ - typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \ + typeof(g) *_p = addr_gva2hva(vm, (gva_t)&(g)); \ typeof(g) _val = val; \ \ memcpy(_p, &(_val), sizeof(g)); \ @@ -1156,10 +1154,10 @@ vm_adjust_num_guest_pages(enum vm_guest_mode mode, unsigned int num_guest_pages) void assert_on_unhandled_exception(struct kvm_vcpu *vcpu); void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, - uint8_t indent); + u8 indent); static inline void vcpu_dump(FILE *stream, struct kvm_vcpu *vcpu, - uint8_t indent) + u8 indent) { vcpu_arch_dump(stream, vcpu, indent); } @@ -1171,10 +1169,10 @@ static inline void vcpu_dump(FILE *stream, struct kvm_vcpu *vcpu, * vm - Virtual Machine * vcpu_id - The id of the VCPU to add to the VM. */ -struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id); +struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, u32 vcpu_id); void vcpu_arch_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code); -static inline struct kvm_vcpu *vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, +static inline struct kvm_vcpu *vm_vcpu_add(struct kvm_vm *vm, u32 vcpu_id, void *guest_code) { struct kvm_vcpu *vcpu = vm_arch_vcpu_add(vm, vcpu_id); @@ -1185,10 +1183,10 @@ static inline struct kvm_vcpu *vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, } /* Re-create a vCPU after restarting a VM, e.g. for state save/restore tests. */ -struct kvm_vcpu *vm_arch_vcpu_recreate(struct kvm_vm *vm, uint32_t vcpu_id); +struct kvm_vcpu *vm_arch_vcpu_recreate(struct kvm_vm *vm, u32 vcpu_id); static inline struct kvm_vcpu *vm_vcpu_recreate(struct kvm_vm *vm, - uint32_t vcpu_id) + u32 vcpu_id) { return vm_arch_vcpu_recreate(vm, vcpu_id); } @@ -1203,27 +1201,15 @@ static inline void virt_pgd_alloc(struct kvm_vm *vm) } /* - * VM Virtual Page Map - * - * Input Args: - * vm - Virtual Machine - * vaddr - VM Virtual Address - * paddr - VM Physical Address - * memslot - Memory region slot for new virtual translation tables - * - * Output Args: None - * - * Return: None - * * Within @vm, creates a virtual translation for the page starting - * at @vaddr to the page starting at @paddr. + * at @gva to the page starting at @gpa. */ -void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr); +void virt_arch_pg_map(struct kvm_vm *vm, gva_t gva, gpa_t gpa); -static inline void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) +static inline void virt_pg_map(struct kvm_vm *vm, gva_t gva, gpa_t gpa) { - virt_arch_pg_map(vm, vaddr, paddr); - sparsebit_set(vm->vpages_mapped, vaddr >> vm->page_shift); + virt_arch_pg_map(vm, gva, gpa); + sparsebit_set(vm->vpages_mapped, gva >> vm->page_shift); } @@ -1242,9 +1228,9 @@ static inline void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr * Returns the VM physical address of the translated VM virtual * address given by @gva. */ -vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva); +gpa_t addr_arch_gva2gpa(struct kvm_vm *vm, gva_t gva); -static inline vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) +static inline gpa_t addr_gva2gpa(struct kvm_vm *vm, gva_t gva) { return addr_arch_gva2gpa(vm, gva); } @@ -1264,9 +1250,9 @@ static inline vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) * Dumps to the FILE stream given by @stream, the contents of all the * virtual translation tables for the VM given by @vm. */ -void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent); +void virt_arch_dump(FILE *stream, struct kvm_vm *vm, u8 indent); -static inline void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) +static inline void virt_dump(FILE *stream, struct kvm_vm *vm, u8 indent) { virt_arch_dump(stream, vm, indent); } @@ -1277,7 +1263,7 @@ static inline int __vm_disable_nx_huge_pages(struct kvm_vm *vm) return __vm_enable_cap(vm, KVM_CAP_VM_DISABLE_NX_HUGE_PAGES, 0); } -static inline uint64_t vm_page_align(struct kvm_vm *vm, uint64_t v) +static inline u64 vm_page_align(struct kvm_vm *vm, u64 v) { return (v + vm->page_size - 1) & ~(vm->page_size - 1); } @@ -1293,9 +1279,9 @@ void kvm_arch_vm_post_create(struct kvm_vm *vm, unsigned int nr_vcpus); void kvm_arch_vm_finalize_vcpus(struct kvm_vm *vm); void kvm_arch_vm_release(struct kvm_vm *vm); -bool vm_is_gpa_protected(struct kvm_vm *vm, vm_paddr_t paddr); +bool vm_is_gpa_protected(struct kvm_vm *vm, gpa_t gpa); -uint32_t guest_get_vcpuid(void); +u32 guest_get_vcpuid(void); bool kvm_arch_has_default_irqchip(void); diff --git a/tools/testing/selftests/kvm/include/kvm_util_types.h b/tools/testing/selftests/kvm/include/kvm_util_types.h index 0366e9bce7f9..ed0087e31674 100644 --- a/tools/testing/selftests/kvm/include/kvm_util_types.h +++ b/tools/testing/selftests/kvm/include/kvm_util_types.h @@ -2,6 +2,8 @@ #ifndef SELFTEST_KVM_UTIL_TYPES_H #define SELFTEST_KVM_UTIL_TYPES_H +#include <linux/types.h> + /* * Provide a version of static_assert() that is guaranteed to have an optional * message param. _GNU_SOURCE is defined for all KVM selftests, _GNU_SOURCE @@ -14,9 +16,9 @@ #define __kvm_static_assert(expr, msg, ...) _Static_assert(expr, msg) #define kvm_static_assert(expr, ...) __kvm_static_assert(expr, ##__VA_ARGS__, #expr) -typedef uint64_t vm_paddr_t; /* Virtual Machine (Guest) physical address */ -typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */ +typedef u64 gpa_t; /* Virtual Machine (Guest) physical address */ +typedef u64 gva_t; /* Virtual Machine (Guest) virtual address */ -#define INVALID_GPA (~(uint64_t)0) +#define INVALID_GPA (~(u64)0) #endif /* SELFTEST_KVM_UTIL_TYPES_H */ diff --git a/tools/testing/selftests/kvm/include/loongarch/arch_timer.h b/tools/testing/selftests/kvm/include/loongarch/arch_timer.h index 2ed106b32c81..3888aeeb3524 100644 --- a/tools/testing/selftests/kvm/include/loongarch/arch_timer.h +++ b/tools/testing/selftests/kvm/include/loongarch/arch_timer.h @@ -70,9 +70,9 @@ static inline void timer_set_next_cmp_ms(unsigned int msec, bool period) csr_write(val, LOONGARCH_CSR_TCFG); } -static inline void __delay(uint64_t cycles) +static inline void __delay(u64 cycles) { - uint64_t start = timer_get_cycles(); + u64 start = timer_get_cycles(); while ((timer_get_cycles() - start) < cycles) cpu_relax(); diff --git a/tools/testing/selftests/kvm/include/loongarch/ucall.h b/tools/testing/selftests/kvm/include/loongarch/ucall.h index 4ec801f37f00..2210d3d94c40 100644 --- a/tools/testing/selftests/kvm/include/loongarch/ucall.h +++ b/tools/testing/selftests/kvm/include/loongarch/ucall.h @@ -10,9 +10,9 @@ * ucall_exit_mmio_addr holds per-VM values (global data is duplicated by each * VM), it must not be accessed from host code. */ -extern vm_vaddr_t *ucall_exit_mmio_addr; +extern gva_t *ucall_exit_mmio_addr; -static inline void ucall_arch_do_ucall(vm_vaddr_t uc) +static inline void ucall_arch_do_ucall(gva_t uc) { WRITE_ONCE(*ucall_exit_mmio_addr, uc); } diff --git a/tools/testing/selftests/kvm/include/memstress.h b/tools/testing/selftests/kvm/include/memstress.h index 9071eb6dea60..0d1d6230cc05 100644 --- a/tools/testing/selftests/kvm/include/memstress.h +++ b/tools/testing/selftests/kvm/include/memstress.h @@ -20,9 +20,9 @@ #define MEMSTRESS_MEM_SLOT_INDEX 1 struct memstress_vcpu_args { - uint64_t gpa; - uint64_t gva; - uint64_t pages; + gpa_t gpa; + gva_t gva; + u64 pages; /* Only used by the host userspace part of the vCPU thread */ struct kvm_vcpu *vcpu; @@ -32,11 +32,11 @@ struct memstress_vcpu_args { struct memstress_args { struct kvm_vm *vm; /* The starting address and size of the guest test region. */ - uint64_t gpa; - uint64_t size; - uint64_t guest_page_size; - uint32_t random_seed; - uint32_t write_percent; + gpa_t gpa; + u64 size; + u64 guest_page_size; + u32 random_seed; + u32 write_percent; /* Run vCPUs in L2 instead of L1, if the architecture supports it. */ bool nested; @@ -45,7 +45,7 @@ struct memstress_args { /* True if all vCPUs are pinned to pCPUs */ bool pin_vcpus; /* The vCPU=>pCPU pinning map. Only valid if pin_vcpus is true. */ - uint32_t vcpu_to_pcpu[KVM_MAX_VCPUS]; + u32 vcpu_to_pcpu[KVM_MAX_VCPUS]; /* Test is done, stop running vCPUs. */ bool stop_vcpus; @@ -56,27 +56,27 @@ struct memstress_args { extern struct memstress_args memstress_args; struct kvm_vm *memstress_create_vm(enum vm_guest_mode mode, int nr_vcpus, - uint64_t vcpu_memory_bytes, int slots, + u64 vcpu_memory_bytes, int slots, enum vm_mem_backing_src_type backing_src, bool partition_vcpu_memory_access); void memstress_destroy_vm(struct kvm_vm *vm); -void memstress_set_write_percent(struct kvm_vm *vm, uint32_t write_percent); +void memstress_set_write_percent(struct kvm_vm *vm, u32 write_percent); void memstress_set_random_access(struct kvm_vm *vm, bool random_access); void memstress_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct memstress_vcpu_args *)); void memstress_join_vcpu_threads(int vcpus); -void memstress_guest_code(uint32_t vcpu_id); +void memstress_guest_code(u32 vcpu_id); -uint64_t memstress_nested_pages(int nr_vcpus); +u64 memstress_nested_pages(int nr_vcpus); void memstress_setup_nested(struct kvm_vm *vm, int nr_vcpus, struct kvm_vcpu *vcpus[]); void memstress_enable_dirty_logging(struct kvm_vm *vm, int slots); void memstress_disable_dirty_logging(struct kvm_vm *vm, int slots); void memstress_get_dirty_log(struct kvm_vm *vm, unsigned long *bitmaps[], int slots); void memstress_clear_dirty_log(struct kvm_vm *vm, unsigned long *bitmaps[], - int slots, uint64_t pages_per_slot); -unsigned long **memstress_alloc_bitmaps(int slots, uint64_t pages_per_slot); + int slots, u64 pages_per_slot); +unsigned long **memstress_alloc_bitmaps(int slots, u64 pages_per_slot); void memstress_free_bitmaps(unsigned long *bitmaps[], int slots); #endif /* SELFTEST_KVM_MEMSTRESS_H */ diff --git a/tools/testing/selftests/kvm/include/riscv/arch_timer.h b/tools/testing/selftests/kvm/include/riscv/arch_timer.h index 225d81dad064..28ffc014da2a 100644 --- a/tools/testing/selftests/kvm/include/riscv/arch_timer.h +++ b/tools/testing/selftests/kvm/include/riscv/arch_timer.h @@ -14,25 +14,25 @@ static unsigned long timer_freq; #define msec_to_cycles(msec) \ - ((timer_freq) * (uint64_t)(msec) / 1000) + ((timer_freq) * (u64)(msec) / 1000) #define usec_to_cycles(usec) \ - ((timer_freq) * (uint64_t)(usec) / 1000000) + ((timer_freq) * (u64)(usec) / 1000000) #define cycles_to_usec(cycles) \ - ((uint64_t)(cycles) * 1000000 / (timer_freq)) + ((u64)(cycles) * 1000000 / (timer_freq)) -static inline uint64_t timer_get_cycles(void) +static inline u64 timer_get_cycles(void) { return csr_read(CSR_TIME); } -static inline void timer_set_cmp(uint64_t cval) +static inline void timer_set_cmp(u64 cval) { csr_write(CSR_STIMECMP, cval); } -static inline uint64_t timer_get_cmp(void) +static inline u64 timer_get_cmp(void) { return csr_read(CSR_STIMECMP); } @@ -47,17 +47,17 @@ static inline void timer_irq_disable(void) csr_clear(CSR_SIE, IE_TIE); } -static inline void timer_set_next_cmp_ms(uint32_t msec) +static inline void timer_set_next_cmp_ms(u32 msec) { - uint64_t now_ct = timer_get_cycles(); - uint64_t next_ct = now_ct + msec_to_cycles(msec); + u64 now_ct = timer_get_cycles(); + u64 next_ct = now_ct + msec_to_cycles(msec); timer_set_cmp(next_ct); } -static inline void __delay(uint64_t cycles) +static inline void __delay(u64 cycles) { - uint64_t start = timer_get_cycles(); + u64 start = timer_get_cycles(); while ((timer_get_cycles() - start) < cycles) cpu_relax(); diff --git a/tools/testing/selftests/kvm/include/riscv/processor.h b/tools/testing/selftests/kvm/include/riscv/processor.h index 4dade8c4d18e..e3acf2ae9881 100644 --- a/tools/testing/selftests/kvm/include/riscv/processor.h +++ b/tools/testing/selftests/kvm/include/riscv/processor.h @@ -25,8 +25,7 @@ #define GET_RM(insn) (((insn) & INSN_MASK_FUNCT3) >> INSN_SHIFT_FUNCT3) #define GET_CSR_NUM(insn) (((insn) & INSN_CSR_MASK) >> INSN_CSR_SHIFT) -static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t subtype, - uint64_t idx, uint64_t size) +static inline u64 __kvm_reg_id(u64 type, u64 subtype, u64 idx, u64 size) { return KVM_REG_RISCV | type | subtype | idx | size; } @@ -62,14 +61,14 @@ static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t subtype, KVM_REG_RISCV_SBI_SINGLE, \ idx, KVM_REG_SIZE_ULONG) -bool __vcpu_has_ext(struct kvm_vcpu *vcpu, uint64_t ext); +bool __vcpu_has_ext(struct kvm_vcpu *vcpu, u64 ext); -static inline bool __vcpu_has_isa_ext(struct kvm_vcpu *vcpu, uint64_t isa_ext) +static inline bool __vcpu_has_isa_ext(struct kvm_vcpu *vcpu, u64 isa_ext) { return __vcpu_has_ext(vcpu, RISCV_ISA_EXT_REG(isa_ext)); } -static inline bool __vcpu_has_sbi_ext(struct kvm_vcpu *vcpu, uint64_t sbi_ext) +static inline bool __vcpu_has_sbi_ext(struct kvm_vcpu *vcpu, u64 sbi_ext) { return __vcpu_has_ext(vcpu, RISCV_SBI_EXT_REG(sbi_ext)); } diff --git a/tools/testing/selftests/kvm/include/riscv/ucall.h b/tools/testing/selftests/kvm/include/riscv/ucall.h index a695ae36f3e0..2de7c6a36096 100644 --- a/tools/testing/selftests/kvm/include/riscv/ucall.h +++ b/tools/testing/selftests/kvm/include/riscv/ucall.h @@ -7,11 +7,11 @@ #define UCALL_EXIT_REASON KVM_EXIT_RISCV_SBI -static inline void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa) +static inline void ucall_arch_init(struct kvm_vm *vm, gpa_t mmio_gpa) { } -static inline void ucall_arch_do_ucall(vm_vaddr_t uc) +static inline void ucall_arch_do_ucall(gva_t uc) { sbi_ecall(KVM_RISCV_SELFTESTS_SBI_EXT, KVM_RISCV_SELFTESTS_SBI_UCALL, diff --git a/tools/testing/selftests/kvm/include/s390/diag318_test_handler.h b/tools/testing/selftests/kvm/include/s390/diag318_test_handler.h index b0ed71302722..6deaf18fec22 100644 --- a/tools/testing/selftests/kvm/include/s390/diag318_test_handler.h +++ b/tools/testing/selftests/kvm/include/s390/diag318_test_handler.h @@ -8,6 +8,6 @@ #ifndef SELFTEST_KVM_DIAG318_TEST_HANDLER #define SELFTEST_KVM_DIAG318_TEST_HANDLER -uint64_t get_diag318_info(void); +u64 get_diag318_info(void); #endif diff --git a/tools/testing/selftests/kvm/include/s390/facility.h b/tools/testing/selftests/kvm/include/s390/facility.h index 00a1ced6538b..41a265742666 100644 --- a/tools/testing/selftests/kvm/include/s390/facility.h +++ b/tools/testing/selftests/kvm/include/s390/facility.h @@ -16,7 +16,7 @@ /* alt_stfle_fac_list[16] + stfle_fac_list[16] */ #define NB_STFL_DOUBLEWORDS 32 -extern uint64_t stfl_doublewords[NB_STFL_DOUBLEWORDS]; +extern u64 stfl_doublewords[NB_STFL_DOUBLEWORDS]; extern bool stfle_flag; static inline bool test_bit_inv(unsigned long nr, const unsigned long *ptr) @@ -24,7 +24,7 @@ static inline bool test_bit_inv(unsigned long nr, const unsigned long *ptr) return test_bit(nr ^ (BITS_PER_LONG - 1), ptr); } -static inline void stfle(uint64_t *fac, unsigned int nb_doublewords) +static inline void stfle(u64 *fac, unsigned int nb_doublewords) { register unsigned long r0 asm("0") = nb_doublewords - 1; diff --git a/tools/testing/selftests/kvm/include/s390/ucall.h b/tools/testing/selftests/kvm/include/s390/ucall.h index 8035a872a351..3907d629304f 100644 --- a/tools/testing/selftests/kvm/include/s390/ucall.h +++ b/tools/testing/selftests/kvm/include/s390/ucall.h @@ -6,11 +6,11 @@ #define UCALL_EXIT_REASON KVM_EXIT_S390_SIEIC -static inline void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa) +static inline void ucall_arch_init(struct kvm_vm *vm, gpa_t mmio_gpa) { } -static inline void ucall_arch_do_ucall(vm_vaddr_t uc) +static inline void ucall_arch_do_ucall(gva_t uc) { /* Exit via DIAGNOSE 0x501 (normally used for breakpoints) */ asm volatile ("diag 0,%0,0x501" : : "a"(uc) : "memory"); diff --git a/tools/testing/selftests/kvm/include/sparsebit.h b/tools/testing/selftests/kvm/include/sparsebit.h index bc760761e1a3..e027e5790946 100644 --- a/tools/testing/selftests/kvm/include/sparsebit.h +++ b/tools/testing/selftests/kvm/include/sparsebit.h @@ -6,7 +6,7 @@ * * Header file that describes API to the sparsebit library. * This library provides a memory efficient means of storing - * the settings of bits indexed via a uint64_t. Memory usage + * the settings of bits indexed via a u64. Memory usage * is reasonable, significantly less than (2^64 / 8) bytes, as * long as bits that are mostly set or mostly cleared are close * to each other. This library is efficient in memory usage @@ -25,8 +25,8 @@ extern "C" { #endif struct sparsebit; -typedef uint64_t sparsebit_idx_t; -typedef uint64_t sparsebit_num_t; +typedef u64 sparsebit_idx_t; +typedef u64 sparsebit_num_t; struct sparsebit *sparsebit_alloc(void); void sparsebit_free(struct sparsebit **sbitp); diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index b4872ba8ed12..d9b433b834f1 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -22,6 +22,8 @@ #include <sys/mman.h> #include "kselftest.h" +#include <linux/types.h> + #define msecs_to_usecs(msec) ((msec) * 1000ULL) static inline __printf(1, 2) int _no_printf(const char *format, ...) { return 0; } @@ -99,25 +101,25 @@ do { \ size_t parse_size(const char *size); -int64_t timespec_to_ns(struct timespec ts); -struct timespec timespec_add_ns(struct timespec ts, int64_t ns); +s64 timespec_to_ns(struct timespec ts); +struct timespec timespec_add_ns(struct timespec ts, s64 ns); struct timespec timespec_add(struct timespec ts1, struct timespec ts2); struct timespec timespec_sub(struct timespec ts1, struct timespec ts2); struct timespec timespec_elapsed(struct timespec start); struct timespec timespec_div(struct timespec ts, int divisor); struct guest_random_state { - uint32_t seed; + u32 seed; }; -extern uint32_t guest_random_seed; +extern u32 guest_random_seed; extern struct guest_random_state guest_rng; -struct guest_random_state new_guest_random_state(uint32_t seed); -uint32_t guest_random_u32(struct guest_random_state *state); +struct guest_random_state new_guest_random_state(u32 seed); +u32 guest_random_u32(struct guest_random_state *state); static inline bool __guest_random_bool(struct guest_random_state *state, - uint8_t percent) + u8 percent) { return (guest_random_u32(state) % 100) < percent; } @@ -127,9 +129,9 @@ static inline bool guest_random_bool(struct guest_random_state *state) return __guest_random_bool(state, 50); } -static inline uint64_t guest_random_u64(struct guest_random_state *state) +static inline u64 guest_random_u64(struct guest_random_state *state) { - return ((uint64_t)guest_random_u32(state) << 32) | guest_random_u32(state); + return ((u64)guest_random_u32(state) << 32) | guest_random_u32(state); } enum vm_mem_backing_src_type { @@ -158,7 +160,7 @@ enum vm_mem_backing_src_type { struct vm_mem_backing_src_alias { const char *name; - uint32_t flag; + u32 flag; }; #define MIN_RUN_DELAY_NS 200000UL @@ -166,9 +168,9 @@ struct vm_mem_backing_src_alias { bool thp_configured(void); size_t get_trans_hugepagesz(void); size_t get_def_hugetlb_pagesz(void); -const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i); -size_t get_backing_src_pagesz(uint32_t i); -bool is_backing_src_hugetlb(uint32_t i); +const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(u32 i); +size_t get_backing_src_pagesz(u32 i); +bool is_backing_src_hugetlb(u32 i); void backing_src_help(const char *flag); enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name); long get_run_delay(void); @@ -189,18 +191,18 @@ static inline bool backing_src_can_be_huge(enum vm_mem_backing_src_type t) } /* Aligns x up to the next multiple of size. Size must be a power of 2. */ -static inline uint64_t align_up(uint64_t x, uint64_t size) +static inline u64 align_up(u64 x, u64 size) { - uint64_t mask = size - 1; + u64 mask = size - 1; TEST_ASSERT(size != 0 && !(size & (size - 1)), "size not a power of 2: %lu", size); return ((x + mask) & ~mask); } -static inline uint64_t align_down(uint64_t x, uint64_t size) +static inline u64 align_down(u64 x, u64 size) { - uint64_t x_aligned_up = align_up(x, size); + u64 x_aligned_up = align_up(x, size); if (x == x_aligned_up) return x; @@ -215,7 +217,7 @@ static inline void *align_ptr_up(void *x, size_t size) int atoi_paranoid(const char *num_str); -static inline uint32_t atoi_positive(const char *name, const char *num_str) +static inline u32 atoi_positive(const char *name, const char *num_str) { int num = atoi_paranoid(num_str); @@ -223,7 +225,7 @@ static inline uint32_t atoi_positive(const char *name, const char *num_str) return num; } -static inline uint32_t atoi_non_negative(const char *name, const char *num_str) +static inline u32 atoi_non_negative(const char *name, const char *num_str) { int num = atoi_paranoid(num_str); diff --git a/tools/testing/selftests/kvm/include/timer_test.h b/tools/testing/selftests/kvm/include/timer_test.h index 9b6edaafe6d4..b7d5d2c84701 100644 --- a/tools/testing/selftests/kvm/include/timer_test.h +++ b/tools/testing/selftests/kvm/include/timer_test.h @@ -18,21 +18,21 @@ /* Timer test cmdline parameters */ struct test_args { - uint32_t nr_vcpus; - uint32_t nr_iter; - uint32_t timer_period_ms; - uint32_t migration_freq_ms; - uint32_t timer_err_margin_us; + u32 nr_vcpus; + u32 nr_iter; + u32 timer_period_ms; + u32 migration_freq_ms; + u32 timer_err_margin_us; /* Members of struct kvm_arm_counter_offset */ - uint64_t counter_offset; - uint64_t reserved; + u64 counter_offset; + u64 reserved; }; /* Shared variables between host and guest */ struct test_vcpu_shared_data { - uint32_t nr_iter; + u32 nr_iter; int guest_stage; - uint64_t xcnt; + u64 xcnt; }; extern struct test_args test_args; diff --git a/tools/testing/selftests/kvm/include/ucall_common.h b/tools/testing/selftests/kvm/include/ucall_common.h index d9d6581b8d4f..cbdcb0a50c4f 100644 --- a/tools/testing/selftests/kvm/include/ucall_common.h +++ b/tools/testing/selftests/kvm/include/ucall_common.h @@ -21,26 +21,26 @@ enum { #define UCALL_BUFFER_LEN 1024 struct ucall { - uint64_t cmd; - uint64_t args[UCALL_MAX_ARGS]; + u64 cmd; + u64 args[UCALL_MAX_ARGS]; char buffer[UCALL_BUFFER_LEN]; /* Host virtual address of this struct. */ struct ucall *hva; }; -void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa); -void ucall_arch_do_ucall(vm_vaddr_t uc); +void ucall_arch_init(struct kvm_vm *vm, gpa_t mmio_gpa); +void ucall_arch_do_ucall(gva_t uc); void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu); -void ucall(uint64_t cmd, int nargs, ...); -__printf(2, 3) void ucall_fmt(uint64_t cmd, const char *fmt, ...); -__printf(5, 6) void ucall_assert(uint64_t cmd, const char *exp, +void ucall(u64 cmd, int nargs, ...); +__printf(2, 3) void ucall_fmt(u64 cmd, const char *fmt, ...); +__printf(5, 6) void ucall_assert(u64 cmd, const char *exp, const char *file, unsigned int line, const char *fmt, ...); -uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc); -void ucall_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa); -int ucall_nr_pages_required(uint64_t page_size); +u64 get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc); +void ucall_init(struct kvm_vm *vm, gpa_t mmio_gpa); +int ucall_nr_pages_required(u64 page_size); /* * Perform userspace call without any associated data. This bare call avoids @@ -48,7 +48,7 @@ int ucall_nr_pages_required(uint64_t page_size); * the full ucall() are problematic and/or unwanted. Note, this will come out * as UCALL_NONE on the backend. */ -#define GUEST_UCALL_NONE() ucall_arch_do_ucall((vm_vaddr_t)NULL) +#define GUEST_UCALL_NONE() ucall_arch_do_ucall((gva_t)NULL) #define GUEST_SYNC_ARGS(stage, arg1, arg2, arg3, arg4) \ ucall(UCALL_SYNC, 6, "hello", stage, arg1, arg2, arg3, arg4) diff --git a/tools/testing/selftests/kvm/include/userfaultfd_util.h b/tools/testing/selftests/kvm/include/userfaultfd_util.h index 60f7f9d435dc..0bc1dc16600e 100644 --- a/tools/testing/selftests/kvm/include/userfaultfd_util.h +++ b/tools/testing/selftests/kvm/include/userfaultfd_util.h @@ -25,7 +25,7 @@ struct uffd_reader_args { struct uffd_desc { int uffd; - uint64_t num_readers; + u64 num_readers; /* Holds the write ends of the pipes for killing the readers. */ int *pipefds; pthread_t *readers; @@ -33,8 +33,8 @@ struct uffd_desc { }; struct uffd_desc *uffd_setup_demand_paging(int uffd_mode, useconds_t delay, - void *hva, uint64_t len, - uint64_t num_readers, + void *hva, u64 len, + u64 num_readers, uffd_handler_t handler); void uffd_stop_demand_paging(struct uffd_desc *uffd); diff --git a/tools/testing/selftests/kvm/include/x86/apic.h b/tools/testing/selftests/kvm/include/x86/apic.h index 5ca6bacbd70e..31887bdc3d6c 100644 --- a/tools/testing/selftests/kvm/include/x86/apic.h +++ b/tools/testing/selftests/kvm/include/x86/apic.h @@ -79,42 +79,42 @@ void apic_disable(void); void xapic_enable(void); void x2apic_enable(void); -static inline uint32_t get_bsp_flag(void) +static inline u32 get_bsp_flag(void) { return rdmsr(MSR_IA32_APICBASE) & MSR_IA32_APICBASE_BSP; } -static inline uint32_t xapic_read_reg(unsigned int reg) +static inline u32 xapic_read_reg(unsigned int reg) { - return ((volatile uint32_t *)APIC_DEFAULT_GPA)[reg >> 2]; + return ((volatile u32 *)APIC_DEFAULT_GPA)[reg >> 2]; } -static inline void xapic_write_reg(unsigned int reg, uint32_t val) +static inline void xapic_write_reg(unsigned int reg, u32 val) { - ((volatile uint32_t *)APIC_DEFAULT_GPA)[reg >> 2] = val; + ((volatile u32 *)APIC_DEFAULT_GPA)[reg >> 2] = val; } -static inline uint64_t x2apic_read_reg(unsigned int reg) +static inline u64 x2apic_read_reg(unsigned int reg) { return rdmsr(APIC_BASE_MSR + (reg >> 4)); } -static inline uint8_t x2apic_write_reg_safe(unsigned int reg, uint64_t value) +static inline u8 x2apic_write_reg_safe(unsigned int reg, u64 value) { return wrmsr_safe(APIC_BASE_MSR + (reg >> 4), value); } -static inline void x2apic_write_reg(unsigned int reg, uint64_t value) +static inline void x2apic_write_reg(unsigned int reg, u64 value) { - uint8_t fault = x2apic_write_reg_safe(reg, value); + u8 fault = x2apic_write_reg_safe(reg, value); __GUEST_ASSERT(!fault, "Unexpected fault 0x%x on WRMSR(%x) = %lx\n", fault, APIC_BASE_MSR + (reg >> 4), value); } -static inline void x2apic_write_reg_fault(unsigned int reg, uint64_t value) +static inline void x2apic_write_reg_fault(unsigned int reg, u64 value) { - uint8_t fault = x2apic_write_reg_safe(reg, value); + u8 fault = x2apic_write_reg_safe(reg, value); __GUEST_ASSERT(fault == GP_VECTOR, "Wanted #GP on WRMSR(%x) = %lx, got 0x%x\n", diff --git a/tools/testing/selftests/kvm/include/x86/evmcs.h b/tools/testing/selftests/kvm/include/x86/evmcs.h index 5a74bb30e2f8..be79bda024bf 100644 --- a/tools/testing/selftests/kvm/include/x86/evmcs.h +++ b/tools/testing/selftests/kvm/include/x86/evmcs.h @@ -10,9 +10,9 @@ #include "hyperv.h" #include "vmx.h" -#define u16 uint16_t -#define u32 uint32_t -#define u64 uint64_t +#define u16 u16 +#define u32 u32 +#define u64 u64 #define EVMCS_VERSION 1 @@ -245,7 +245,7 @@ static inline void evmcs_enable(void) enable_evmcs = true; } -static inline int evmcs_vmptrld(uint64_t vmcs_pa, void *vmcs) +static inline int evmcs_vmptrld(u64 vmcs_pa, void *vmcs) { current_vp_assist->current_nested_vmcs = vmcs_pa; current_vp_assist->enlighten_vmentry = 1; @@ -265,7 +265,7 @@ static inline bool load_evmcs(struct hyperv_test_pages *hv) return true; } -static inline int evmcs_vmptrst(uint64_t *value) +static inline int evmcs_vmptrst(u64 *value) { *value = current_vp_assist->current_nested_vmcs & ~HV_X64_MSR_VP_ASSIST_PAGE_ENABLE; @@ -273,7 +273,7 @@ static inline int evmcs_vmptrst(uint64_t *value) return 0; } -static inline int evmcs_vmread(uint64_t encoding, uint64_t *value) +static inline int evmcs_vmread(u64 encoding, u64 *value) { switch (encoding) { case GUEST_RIP: @@ -672,7 +672,7 @@ static inline int evmcs_vmread(uint64_t encoding, uint64_t *value) return 0; } -static inline int evmcs_vmwrite(uint64_t encoding, uint64_t value) +static inline int evmcs_vmwrite(u64 encoding, u64 value) { switch (encoding) { case GUEST_RIP: @@ -1226,9 +1226,9 @@ static inline int evmcs_vmlaunch(void) "pop %%rbp;" : [ret]"=&a"(ret) : [host_rsp]"r" - ((uint64_t)¤t_evmcs->host_rsp), + ((u64)¤t_evmcs->host_rsp), [host_rip]"r" - ((uint64_t)¤t_evmcs->host_rip) + ((u64)¤t_evmcs->host_rip) : "memory", "cc", "rbx", "r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15"); return ret; @@ -1265,9 +1265,9 @@ static inline int evmcs_vmresume(void) "pop %%rbp;" : [ret]"=&a"(ret) : [host_rsp]"r" - ((uint64_t)¤t_evmcs->host_rsp), + ((u64)¤t_evmcs->host_rsp), [host_rip]"r" - ((uint64_t)¤t_evmcs->host_rip) + ((u64)¤t_evmcs->host_rip) : "memory", "cc", "rbx", "r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15"); return ret; diff --git a/tools/testing/selftests/kvm/include/x86/hyperv.h b/tools/testing/selftests/kvm/include/x86/hyperv.h index f13e532be240..78003f5a22f3 100644 --- a/tools/testing/selftests/kvm/include/x86/hyperv.h +++ b/tools/testing/selftests/kvm/include/x86/hyperv.h @@ -254,12 +254,12 @@ * Issue a Hyper-V hypercall. Returns exception vector raised or 0, 'hv_status' * is set to the hypercall status (if no exception occurred). */ -static inline uint8_t __hyperv_hypercall(u64 control, vm_vaddr_t input_address, - vm_vaddr_t output_address, - uint64_t *hv_status) +static inline u8 __hyperv_hypercall(u64 control, gva_t input_address, + gva_t output_address, + u64 *hv_status) { - uint64_t error_code; - uint8_t vector; + u64 error_code; + u8 vector; /* Note both the hypercall and the "asm safe" clobber r9-r11. */ asm volatile("mov %[output_address], %%r8\n\t" @@ -274,11 +274,11 @@ static inline uint8_t __hyperv_hypercall(u64 control, vm_vaddr_t input_address, } /* Issue a Hyper-V hypercall and assert that it succeeded. */ -static inline void hyperv_hypercall(u64 control, vm_vaddr_t input_address, - vm_vaddr_t output_address) +static inline void hyperv_hypercall(u64 control, gva_t input_address, + gva_t output_address) { - uint64_t hv_status; - uint8_t vector; + u64 hv_status; + u8 vector; vector = __hyperv_hypercall(control, input_address, output_address, &hv_status); @@ -327,27 +327,27 @@ struct hv_vp_assist_page { extern struct hv_vp_assist_page *current_vp_assist; -int enable_vp_assist(uint64_t vp_assist_pa, void *vp_assist); +int enable_vp_assist(u64 vp_assist_pa, void *vp_assist); struct hyperv_test_pages { /* VP assist page */ void *vp_assist_hva; - uint64_t vp_assist_gpa; + u64 vp_assist_gpa; void *vp_assist; /* Partition assist page */ void *partition_assist_hva; - uint64_t partition_assist_gpa; + u64 partition_assist_gpa; void *partition_assist; /* Enlightened VMCS */ void *enlightened_vmcs_hva; - uint64_t enlightened_vmcs_gpa; + u64 enlightened_vmcs_gpa; void *enlightened_vmcs; }; struct hyperv_test_pages *vcpu_alloc_hyperv_test_pages(struct kvm_vm *vm, - vm_vaddr_t *p_hv_pages_gva); + gva_t *p_hv_pages_gva); /* HV_X64_MSR_TSC_INVARIANT_CONTROL bits */ #define HV_INVARIANT_TSC_EXPOSED BIT_ULL(0) diff --git a/tools/testing/selftests/kvm/include/x86/kvm_util_arch.h b/tools/testing/selftests/kvm/include/x86/kvm_util_arch.h index be35d26bb320..c33ab6e04171 100644 --- a/tools/testing/selftests/kvm/include/x86/kvm_util_arch.h +++ b/tools/testing/selftests/kvm/include/x86/kvm_util_arch.h @@ -11,19 +11,19 @@ extern bool is_forced_emulation_enabled; struct pte_masks { - uint64_t present; - uint64_t writable; - uint64_t user; - uint64_t readable; - uint64_t executable; - uint64_t accessed; - uint64_t dirty; - uint64_t huge; - uint64_t nx; - uint64_t c; - uint64_t s; + u64 present; + u64 writable; + u64 user; + u64 readable; + u64 executable; + u64 accessed; + u64 dirty; + u64 huge; + u64 nx; + u64 c; + u64 s; - uint64_t always_set; + u64 always_set; }; struct kvm_mmu_arch { @@ -33,12 +33,12 @@ struct kvm_mmu_arch { struct kvm_mmu; struct kvm_vm_arch { - vm_vaddr_t gdt; - vm_vaddr_t tss; - vm_vaddr_t idt; + gva_t gdt; + gva_t tss; + gva_t idt; - uint64_t c_bit; - uint64_t s_bit; + u64 c_bit; + u64 s_bit; int sev_fd; bool is_pt_protected; }; @@ -62,7 +62,7 @@ do { \ : "+m" (mem) \ : "r" (val) : "memory"); \ } else { \ - uint64_t __old = READ_ONCE(mem); \ + u64 __old = READ_ONCE(mem); \ \ __asm__ __volatile__(KVM_FEP LOCK_PREFIX "cmpxchg %[new], %[ptr]" \ : [ptr] "+m" (mem), [old] "+a" (__old) \ diff --git a/tools/testing/selftests/kvm/include/x86/pmu.h b/tools/testing/selftests/kvm/include/x86/pmu.h index 72575eadb63a..98537cc8840d 100644 --- a/tools/testing/selftests/kvm/include/x86/pmu.h +++ b/tools/testing/selftests/kvm/include/x86/pmu.h @@ -6,8 +6,8 @@ #define SELFTEST_KVM_PMU_H #include <stdbool.h> -#include <stdint.h> +#include <linux/types.h> #include <linux/bits.h> #define KVM_PMU_EVENT_FILTER_MAX_EVENTS 300 @@ -104,14 +104,15 @@ enum amd_pmu_zen_events { NR_AMD_ZEN_EVENTS, }; -extern const uint64_t intel_pmu_arch_events[]; -extern const uint64_t amd_pmu_zen_events[]; +extern const u64 intel_pmu_arch_events[]; +extern const u64 amd_pmu_zen_events[]; enum pmu_errata { INSTRUCTIONS_RETIRED_OVERCOUNT, BRANCHES_RETIRED_OVERCOUNT, }; -extern uint64_t pmu_errata_mask; + +extern u64 pmu_errata_mask; void kvm_init_pmu_errata(void); diff --git a/tools/testing/selftests/kvm/include/x86/processor.h b/tools/testing/selftests/kvm/include/x86/processor.h index d8634a760a60..77f576ee7789 100644 --- a/tools/testing/selftests/kvm/include/x86/processor.h +++ b/tools/testing/selftests/kvm/include/x86/processor.h @@ -23,7 +23,7 @@ extern bool host_cpu_is_intel; extern bool host_cpu_is_amd; extern bool host_cpu_is_hygon; extern bool host_cpu_is_amd_compatible; -extern uint64_t guest_tsc_khz; +extern u64 guest_tsc_khz; #ifndef MAX_NR_CPUID_ENTRIES #define MAX_NR_CPUID_ENTRIES 100 @@ -399,17 +399,17 @@ struct gpr64_regs { }; struct desc64 { - uint16_t limit0; - uint16_t base0; + u16 limit0; + u16 base0; unsigned base1:8, type:4, s:1, dpl:2, p:1; unsigned limit1:4, avl:1, l:1, db:1, g:1, base2:8; - uint32_t base3; - uint32_t zero1; + u32 base3; + u32 zero1; } __attribute__((packed)); struct desc_ptr { - uint16_t size; - uint64_t address; + u16 size; + u64 address; } __attribute__((packed)); struct kvm_x86_state { @@ -427,18 +427,18 @@ struct kvm_x86_state { struct kvm_msrs msrs; }; -static inline uint64_t get_desc64_base(const struct desc64 *desc) +static inline u64 get_desc64_base(const struct desc64 *desc) { - return (uint64_t)desc->base3 << 32 | - (uint64_t)desc->base2 << 24 | - (uint64_t)desc->base1 << 16 | - (uint64_t)desc->base0; + return (u64)desc->base3 << 32 | + (u64)desc->base2 << 24 | + (u64)desc->base1 << 16 | + (u64)desc->base0; } -static inline uint64_t rdtsc(void) +static inline u64 rdtsc(void) { - uint32_t eax, edx; - uint64_t tsc_val; + u32 eax, edx; + u64 tsc_val; /* * The lfence is to wait (on Intel CPUs) until all previous * instructions have been executed. If software requires RDTSC to be @@ -446,39 +446,39 @@ static inline uint64_t rdtsc(void) * execute LFENCE immediately after RDTSC */ __asm__ __volatile__("lfence; rdtsc; lfence" : "=a"(eax), "=d"(edx)); - tsc_val = ((uint64_t)edx) << 32 | eax; + tsc_val = ((u64)edx) << 32 | eax; return tsc_val; } -static inline uint64_t rdtscp(uint32_t *aux) +static inline u64 rdtscp(u32 *aux) { - uint32_t eax, edx; + u32 eax, edx; __asm__ __volatile__("rdtscp" : "=a"(eax), "=d"(edx), "=c"(*aux)); - return ((uint64_t)edx) << 32 | eax; + return ((u64)edx) << 32 | eax; } -static inline uint64_t rdmsr(uint32_t msr) +static inline u64 rdmsr(u32 msr) { - uint32_t a, d; + u32 a, d; __asm__ __volatile__("rdmsr" : "=a"(a), "=d"(d) : "c"(msr) : "memory"); - return a | ((uint64_t) d << 32); + return a | ((u64)d << 32); } -static inline void wrmsr(uint32_t msr, uint64_t value) +static inline void wrmsr(u32 msr, u64 value) { - uint32_t a = value; - uint32_t d = value >> 32; + u32 a = value; + u32 d = value >> 32; __asm__ __volatile__("wrmsr" :: "a"(a), "d"(d), "c"(msr) : "memory"); } -static inline uint16_t inw(uint16_t port) +static inline u16 inw(u16 port) { - uint16_t tmp; + u16 tmp; __asm__ __volatile__("in %%dx, %%ax" : /* output */ "=a" (tmp) @@ -487,120 +487,120 @@ static inline uint16_t inw(uint16_t port) return tmp; } -static inline uint16_t get_es(void) +static inline u16 get_es(void) { - uint16_t es; + u16 es; __asm__ __volatile__("mov %%es, %[es]" : /* output */ [es]"=rm"(es)); return es; } -static inline uint16_t get_cs(void) +static inline u16 get_cs(void) { - uint16_t cs; + u16 cs; __asm__ __volatile__("mov %%cs, %[cs]" : /* output */ [cs]"=rm"(cs)); return cs; } -static inline uint16_t get_ss(void) +static inline u16 get_ss(void) { - uint16_t ss; + u16 ss; __asm__ __volatile__("mov %%ss, %[ss]" : /* output */ [ss]"=rm"(ss)); return ss; } -static inline uint16_t get_ds(void) +static inline u16 get_ds(void) { - uint16_t ds; + u16 ds; __asm__ __volatile__("mov %%ds, %[ds]" : /* output */ [ds]"=rm"(ds)); return ds; } -static inline uint16_t get_fs(void) +static inline u16 get_fs(void) { - uint16_t fs; + u16 fs; __asm__ __volatile__("mov %%fs, %[fs]" : /* output */ [fs]"=rm"(fs)); return fs; } -static inline uint16_t get_gs(void) +static inline u16 get_gs(void) { - uint16_t gs; + u16 gs; __asm__ __volatile__("mov %%gs, %[gs]" : /* output */ [gs]"=rm"(gs)); return gs; } -static inline uint16_t get_tr(void) +static inline u16 get_tr(void) { - uint16_t tr; + u16 tr; __asm__ __volatile__("str %[tr]" : /* output */ [tr]"=rm"(tr)); return tr; } -static inline uint64_t get_cr0(void) +static inline u64 get_cr0(void) { - uint64_t cr0; + u64 cr0; __asm__ __volatile__("mov %%cr0, %[cr0]" : /* output */ [cr0]"=r"(cr0)); return cr0; } -static inline void set_cr0(uint64_t val) +static inline void set_cr0(u64 val) { __asm__ __volatile__("mov %0, %%cr0" : : "r" (val) : "memory"); } -static inline uint64_t get_cr3(void) +static inline u64 get_cr3(void) { - uint64_t cr3; + u64 cr3; __asm__ __volatile__("mov %%cr3, %[cr3]" : /* output */ [cr3]"=r"(cr3)); return cr3; } -static inline void set_cr3(uint64_t val) +static inline void set_cr3(u64 val) { __asm__ __volatile__("mov %0, %%cr3" : : "r" (val) : "memory"); } -static inline uint64_t get_cr4(void) +static inline u64 get_cr4(void) { - uint64_t cr4; + u64 cr4; __asm__ __volatile__("mov %%cr4, %[cr4]" : /* output */ [cr4]"=r"(cr4)); return cr4; } -static inline void set_cr4(uint64_t val) +static inline void set_cr4(u64 val) { __asm__ __volatile__("mov %0, %%cr4" : : "r" (val) : "memory"); } -static inline uint64_t get_cr8(void) +static inline u64 get_cr8(void) { - uint64_t cr8; + u64 cr8; __asm__ __volatile__("mov %%cr8, %[cr8]" : [cr8]"=r"(cr8)); return cr8; } -static inline void set_cr8(uint64_t val) +static inline void set_cr8(u64 val) { __asm__ __volatile__("mov %0, %%cr8" : : "r" (val) : "memory"); } @@ -651,14 +651,14 @@ static inline struct desc_ptr get_idt(void) return idt; } -static inline void outl(uint16_t port, uint32_t value) +static inline void outl(u16 port, u32 value) { __asm__ __volatile__("outl %%eax, %%dx" : : "d"(port), "a"(value)); } -static inline void __cpuid(uint32_t function, uint32_t index, - uint32_t *eax, uint32_t *ebx, - uint32_t *ecx, uint32_t *edx) +static inline void __cpuid(u32 function, u32 index, + u32 *eax, u32 *ebx, + u32 *ecx, u32 *edx) { *eax = function; *ecx = index; @@ -672,35 +672,35 @@ static inline void __cpuid(uint32_t function, uint32_t index, : "memory"); } -static inline void cpuid(uint32_t function, - uint32_t *eax, uint32_t *ebx, - uint32_t *ecx, uint32_t *edx) +static inline void cpuid(u32 function, + u32 *eax, u32 *ebx, + u32 *ecx, u32 *edx) { return __cpuid(function, 0, eax, ebx, ecx, edx); } -static inline uint32_t this_cpu_fms(void) +static inline u32 this_cpu_fms(void) { - uint32_t eax, ebx, ecx, edx; + u32 eax, ebx, ecx, edx; cpuid(1, &eax, &ebx, &ecx, &edx); return eax; } -static inline uint32_t this_cpu_family(void) +static inline u32 this_cpu_family(void) { return x86_family(this_cpu_fms()); } -static inline uint32_t this_cpu_model(void) +static inline u32 this_cpu_model(void) { return x86_model(this_cpu_fms()); } static inline bool this_cpu_vendor_string_is(const char *vendor) { - const uint32_t *chunk = (const uint32_t *)vendor; - uint32_t eax, ebx, ecx, edx; + const u32 *chunk = (const u32 *)vendor; + u32 eax, ebx, ecx, edx; cpuid(0, &eax, &ebx, &ecx, &edx); return (ebx == chunk[0] && edx == chunk[1] && ecx == chunk[2]); @@ -724,10 +724,9 @@ static inline bool this_cpu_is_hygon(void) return this_cpu_vendor_string_is("HygonGenuine"); } -static inline uint32_t __this_cpu_has(uint32_t function, uint32_t index, - uint8_t reg, uint8_t lo, uint8_t hi) +static inline u32 __this_cpu_has(u32 function, u32 index, u8 reg, u8 lo, u8 hi) { - uint32_t gprs[4]; + u32 gprs[4]; __cpuid(function, index, &gprs[KVM_CPUID_EAX], &gprs[KVM_CPUID_EBX], @@ -742,7 +741,7 @@ static inline bool this_cpu_has(struct kvm_x86_cpu_feature feature) feature.reg, feature.bit, feature.bit); } -static inline uint32_t this_cpu_property(struct kvm_x86_cpu_property property) +static inline u32 this_cpu_property(struct kvm_x86_cpu_property property) { return __this_cpu_has(property.function, property.index, property.reg, property.lo_bit, property.hi_bit); @@ -750,7 +749,7 @@ static inline uint32_t this_cpu_property(struct kvm_x86_cpu_property property) static __always_inline bool this_cpu_has_p(struct kvm_x86_cpu_property property) { - uint32_t max_leaf; + u32 max_leaf; switch (property.function & 0xc0000000) { case 0: @@ -770,7 +769,7 @@ static __always_inline bool this_cpu_has_p(struct kvm_x86_cpu_property property) static inline bool this_pmu_has(struct kvm_x86_pmu_feature feature) { - uint32_t nr_bits; + u32 nr_bits; if (feature.f.reg == KVM_CPUID_EBX) { nr_bits = this_cpu_property(X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH); @@ -782,13 +781,13 @@ static inline bool this_pmu_has(struct kvm_x86_pmu_feature feature) return nr_bits > feature.f.bit || this_cpu_has(feature.f); } -static __always_inline uint64_t this_cpu_supported_xcr0(void) +static __always_inline u64 this_cpu_supported_xcr0(void) { if (!this_cpu_has_p(X86_PROPERTY_SUPPORTED_XCR0_LO)) return 0; return this_cpu_property(X86_PROPERTY_SUPPORTED_XCR0_LO) | - ((uint64_t)this_cpu_property(X86_PROPERTY_SUPPORTED_XCR0_HI) << 32); + ((u64)this_cpu_property(X86_PROPERTY_SUPPORTED_XCR0_HI) << 32); } typedef u32 __attribute__((vector_size(16))) sse128_t; @@ -867,7 +866,7 @@ static inline void cpu_relax(void) static inline void udelay(unsigned long usec) { - uint64_t start, now, cycles; + u64 start, now, cycles; GUEST_ASSERT(guest_tsc_khz); cycles = guest_tsc_khz / 1000 * usec; @@ -898,8 +897,8 @@ void kvm_x86_state_cleanup(struct kvm_x86_state *state); const struct kvm_msr_list *kvm_get_msr_index_list(void); const struct kvm_msr_list *kvm_get_feature_msr_index_list(void); -bool kvm_msr_is_in_save_restore_list(uint32_t msr_index); -uint64_t kvm_get_feature_msr(uint64_t msr_index); +bool kvm_msr_is_in_save_restore_list(u32 msr_index); +u64 kvm_get_feature_msr(u64 msr_index); static inline void vcpu_msrs_get(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs) @@ -954,20 +953,20 @@ static inline void vcpu_xcrs_set(struct kvm_vcpu *vcpu, struct kvm_xcrs *xcrs) } const struct kvm_cpuid_entry2 *get_cpuid_entry(const struct kvm_cpuid2 *cpuid, - uint32_t function, uint32_t index); + u32 function, u32 index); const struct kvm_cpuid2 *kvm_get_supported_cpuid(void); -static inline uint32_t kvm_cpu_fms(void) +static inline u32 kvm_cpu_fms(void) { return get_cpuid_entry(kvm_get_supported_cpuid(), 0x1, 0)->eax; } -static inline uint32_t kvm_cpu_family(void) +static inline u32 kvm_cpu_family(void) { return x86_family(kvm_cpu_fms()); } -static inline uint32_t kvm_cpu_model(void) +static inline u32 kvm_cpu_model(void) { return x86_model(kvm_cpu_fms()); } @@ -980,17 +979,17 @@ static inline bool kvm_cpu_has(struct kvm_x86_cpu_feature feature) return kvm_cpuid_has(kvm_get_supported_cpuid(), feature); } -uint32_t kvm_cpuid_property(const struct kvm_cpuid2 *cpuid, - struct kvm_x86_cpu_property property); +u32 kvm_cpuid_property(const struct kvm_cpuid2 *cpuid, + struct kvm_x86_cpu_property property); -static inline uint32_t kvm_cpu_property(struct kvm_x86_cpu_property property) +static inline u32 kvm_cpu_property(struct kvm_x86_cpu_property property) { return kvm_cpuid_property(kvm_get_supported_cpuid(), property); } static __always_inline bool kvm_cpu_has_p(struct kvm_x86_cpu_property property) { - uint32_t max_leaf; + u32 max_leaf; switch (property.function & 0xc0000000) { case 0: @@ -1010,7 +1009,7 @@ static __always_inline bool kvm_cpu_has_p(struct kvm_x86_cpu_property property) static inline bool kvm_pmu_has(struct kvm_x86_pmu_feature feature) { - uint32_t nr_bits; + u32 nr_bits; if (feature.f.reg == KVM_CPUID_EBX) { nr_bits = kvm_cpu_property(X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH); @@ -1022,13 +1021,13 @@ static inline bool kvm_pmu_has(struct kvm_x86_pmu_feature feature) return nr_bits > feature.f.bit || kvm_cpu_has(feature.f); } -static __always_inline uint64_t kvm_cpu_supported_xcr0(void) +static __always_inline u64 kvm_cpu_supported_xcr0(void) { if (!kvm_cpu_has_p(X86_PROPERTY_SUPPORTED_XCR0_LO)) return 0; return kvm_cpu_property(X86_PROPERTY_SUPPORTED_XCR0_LO) | - ((uint64_t)kvm_cpu_property(X86_PROPERTY_SUPPORTED_XCR0_HI) << 32); + ((u64)kvm_cpu_property(X86_PROPERTY_SUPPORTED_XCR0_HI) << 32); } static inline size_t kvm_cpuid2_size(int nr_entries) @@ -1062,8 +1061,8 @@ static inline void vcpu_get_cpuid(struct kvm_vcpu *vcpu) } static inline struct kvm_cpuid_entry2 *__vcpu_get_cpuid_entry(struct kvm_vcpu *vcpu, - uint32_t function, - uint32_t index) + u32 function, + u32 index) { TEST_ASSERT(vcpu->cpuid, "Must do vcpu_init_cpuid() first (or equivalent)"); @@ -1074,7 +1073,7 @@ static inline struct kvm_cpuid_entry2 *__vcpu_get_cpuid_entry(struct kvm_vcpu *v } static inline struct kvm_cpuid_entry2 *vcpu_get_cpuid_entry(struct kvm_vcpu *vcpu, - uint32_t function) + u32 function) { return __vcpu_get_cpuid_entry(vcpu, function, 0); } @@ -1104,10 +1103,10 @@ static inline void vcpu_set_cpuid(struct kvm_vcpu *vcpu) void vcpu_set_cpuid_property(struct kvm_vcpu *vcpu, struct kvm_x86_cpu_property property, - uint32_t value); -void vcpu_set_cpuid_maxphyaddr(struct kvm_vcpu *vcpu, uint8_t maxphyaddr); + u32 value); +void vcpu_set_cpuid_maxphyaddr(struct kvm_vcpu *vcpu, u8 maxphyaddr); -void vcpu_clear_cpuid_entry(struct kvm_vcpu *vcpu, uint32_t function); +void vcpu_clear_cpuid_entry(struct kvm_vcpu *vcpu, u32 function); static inline bool vcpu_cpuid_has(struct kvm_vcpu *vcpu, struct kvm_x86_cpu_feature feature) @@ -1135,8 +1134,8 @@ static inline void vcpu_clear_cpuid_feature(struct kvm_vcpu *vcpu, vcpu_set_or_clear_cpuid_feature(vcpu, feature, false); } -uint64_t vcpu_get_msr(struct kvm_vcpu *vcpu, uint64_t msr_index); -int _vcpu_set_msr(struct kvm_vcpu *vcpu, uint64_t msr_index, uint64_t msr_value); +u64 vcpu_get_msr(struct kvm_vcpu *vcpu, u64 msr_index); +int _vcpu_set_msr(struct kvm_vcpu *vcpu, u64 msr_index, u64 msr_value); /* * Assert on an MSR access(es) and pretty print the MSR name when possible. @@ -1161,14 +1160,14 @@ do { \ * is changing, etc. This is NOT an exhaustive list! The intent is to filter * out MSRs that are not durable _and_ that a selftest wants to write. */ -static inline bool is_durable_msr(uint32_t msr) +static inline bool is_durable_msr(u32 msr) { return msr != MSR_IA32_TSC; } #define vcpu_set_msr(vcpu, msr, val) \ do { \ - uint64_t r, v = val; \ + u64 r, v = val; \ \ TEST_ASSERT_MSR(_vcpu_set_msr(vcpu, msr, v) == 1, \ "KVM_SET_MSRS failed on %s, value = 0x%lx", msr, #msr, v); \ @@ -1182,28 +1181,28 @@ void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits); void kvm_init_vm_address_properties(struct kvm_vm *vm); struct ex_regs { - uint64_t rax, rcx, rdx, rbx; - uint64_t rbp, rsi, rdi; - uint64_t r8, r9, r10, r11; - uint64_t r12, r13, r14, r15; - uint64_t vector; - uint64_t error_code; - uint64_t rip; - uint64_t cs; - uint64_t rflags; + u64 rax, rcx, rdx, rbx; + u64 rbp, rsi, rdi; + u64 r8, r9, r10, r11; + u64 r12, r13, r14, r15; + u64 vector; + u64 error_code; + u64 rip; + u64 cs; + u64 rflags; }; struct idt_entry { - uint16_t offset0; - uint16_t selector; - uint16_t ist : 3; - uint16_t : 5; - uint16_t type : 4; - uint16_t : 1; - uint16_t dpl : 2; - uint16_t p : 1; - uint16_t offset1; - uint32_t offset2; uint32_t reserved; + u16 offset0; + u16 selector; + u16 ist : 3; + u16 : 5; + u16 type : 4; + u16 : 1; + u16 dpl : 2; + u16 p : 1; + u16 offset1; + u32 offset2; u32 reserved; }; void vm_install_exception_handler(struct kvm_vm *vm, int vector, @@ -1262,8 +1261,8 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector, #define kvm_asm_safe(insn, inputs...) \ ({ \ - uint64_t ign_error_code; \ - uint8_t vector; \ + u64 ign_error_code; \ + u8 vector; \ \ asm volatile(KVM_ASM_SAFE(insn) \ : KVM_ASM_SAFE_OUTPUTS(vector, ign_error_code) \ @@ -1274,7 +1273,7 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector, #define kvm_asm_safe_ec(insn, error_code, inputs...) \ ({ \ - uint8_t vector; \ + u8 vector; \ \ asm volatile(KVM_ASM_SAFE(insn) \ : KVM_ASM_SAFE_OUTPUTS(vector, error_code) \ @@ -1285,8 +1284,8 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector, #define kvm_asm_safe_fep(insn, inputs...) \ ({ \ - uint64_t ign_error_code; \ - uint8_t vector; \ + u64 ign_error_code; \ + u8 vector; \ \ asm volatile(KVM_ASM_SAFE_FEP(insn) \ : KVM_ASM_SAFE_OUTPUTS(vector, ign_error_code) \ @@ -1297,7 +1296,7 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector, #define kvm_asm_safe_ec_fep(insn, error_code, inputs...) \ ({ \ - uint8_t vector; \ + u8 vector; \ \ asm volatile(KVM_ASM_SAFE_FEP(insn) \ : KVM_ASM_SAFE_OUTPUTS(vector, error_code) \ @@ -1307,11 +1306,11 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector, }) #define BUILD_READ_U64_SAFE_HELPER(insn, _fep, _FEP) \ -static inline uint8_t insn##_safe ##_fep(uint32_t idx, uint64_t *val) \ +static inline u8 insn##_safe ##_fep(u32 idx, u64 *val) \ { \ - uint64_t error_code; \ - uint8_t vector; \ - uint32_t a, d; \ + u64 error_code; \ + u8 vector; \ + u32 a, d; \ \ asm volatile(KVM_ASM_SAFE##_FEP(#insn) \ : "=a"(a), "=d"(d), \ @@ -1319,7 +1318,7 @@ static inline uint8_t insn##_safe ##_fep(uint32_t idx, uint64_t *val) \ : "c"(idx) \ : KVM_ASM_SAFE_CLOBBERS); \ \ - *val = (uint64_t)a | ((uint64_t)d << 32); \ + *val = (u64)a | ((u64)d << 32); \ return vector; \ } @@ -1335,12 +1334,12 @@ BUILD_READ_U64_SAFE_HELPERS(rdmsr) BUILD_READ_U64_SAFE_HELPERS(rdpmc) BUILD_READ_U64_SAFE_HELPERS(xgetbv) -static inline uint8_t wrmsr_safe(uint32_t msr, uint64_t val) +static inline u8 wrmsr_safe(u32 msr, u64 val) { return kvm_asm_safe("wrmsr", "a"(val & -1u), "d"(val >> 32), "c"(msr)); } -static inline uint8_t xsetbv_safe(uint32_t index, uint64_t value) +static inline u8 xsetbv_safe(u32 index, u64 value) { u32 eax = value; u32 edx = value >> 32; @@ -1395,23 +1394,20 @@ static inline bool kvm_is_lbrv_enabled(void) return !!get_kvm_amd_param_integer("lbrv"); } -uint64_t *vm_get_pte(struct kvm_vm *vm, uint64_t vaddr); +u64 *vm_get_pte(struct kvm_vm *vm, gva_t gva); -uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2, - uint64_t a3); -uint64_t __xen_hypercall(uint64_t nr, uint64_t a0, void *a1); -void xen_hypercall(uint64_t nr, uint64_t a0, void *a1); +u64 kvm_hypercall(u64 nr, u64 a0, u64 a1, u64 a2, u64 a3); +u64 __xen_hypercall(u64 nr, u64 a0, void *a1); +void xen_hypercall(u64 nr, u64 a0, void *a1); -static inline uint64_t __kvm_hypercall_map_gpa_range(uint64_t gpa, - uint64_t size, uint64_t flags) +static inline u64 __kvm_hypercall_map_gpa_range(gpa_t gpa, u64 size, u64 flags) { return kvm_hypercall(KVM_HC_MAP_GPA_RANGE, gpa, size >> PAGE_SHIFT, flags, 0); } -static inline void kvm_hypercall_map_gpa_range(uint64_t gpa, uint64_t size, - uint64_t flags) +static inline void kvm_hypercall_map_gpa_range(gpa_t gpa, u64 size, u64 flags) { - uint64_t ret = __kvm_hypercall_map_gpa_range(gpa, size, flags); + u64 ret = __kvm_hypercall_map_gpa_range(gpa, size, flags); GUEST_ASSERT(!ret); } @@ -1456,7 +1452,7 @@ static inline void cli(void) asm volatile ("cli"); } -void __vm_xsave_require_permission(uint64_t xfeature, const char *name); +void __vm_xsave_require_permission(u64 xfeature, const char *name); #define vm_xsave_require_permission(xfeature) \ __vm_xsave_require_permission(xfeature, #xfeature) @@ -1511,17 +1507,17 @@ enum pg_level { void tdp_mmu_init(struct kvm_vm *vm, int pgtable_levels, struct pte_masks *pte_masks); -void __virt_pg_map(struct kvm_vm *vm, struct kvm_mmu *mmu, uint64_t vaddr, - uint64_t paddr, int level); -void virt_map_level(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, - uint64_t nr_bytes, int level); +void __virt_pg_map(struct kvm_vm *vm, struct kvm_mmu *mmu, gva_t gva, + gpa_t gpa, int level); +void virt_map_level(struct kvm_vm *vm, gva_t gva, gpa_t gpa, + u64 nr_bytes, int level); void vm_enable_tdp(struct kvm_vm *vm); bool kvm_cpu_has_tdp(void); -void tdp_map(struct kvm_vm *vm, uint64_t nested_paddr, uint64_t paddr, uint64_t size); +void tdp_map(struct kvm_vm *vm, gpa_t l2_gpa, gpa_t gpa, u64 size); void tdp_identity_map_default_memslots(struct kvm_vm *vm); -void tdp_identity_map_1g(struct kvm_vm *vm, uint64_t addr, uint64_t size); -uint64_t *tdp_get_pte(struct kvm_vm *vm, uint64_t l2_gpa); +void tdp_identity_map_1g(struct kvm_vm *vm, u64 addr, u64 size); +u64 *tdp_get_pte(struct kvm_vm *vm, u64 l2_gpa); /* * Basic CPU control in CR0 diff --git a/tools/testing/selftests/kvm/include/x86/sev.h b/tools/testing/selftests/kvm/include/x86/sev.h index 008b4169f5e2..1af44c151d60 100644 --- a/tools/testing/selftests/kvm/include/x86/sev.h +++ b/tools/testing/selftests/kvm/include/x86/sev.h @@ -46,16 +46,16 @@ static inline bool is_sev_vm(struct kvm_vm *vm) return is_sev_es_vm(vm) || vm->type == KVM_X86_SEV_VM; } -void sev_vm_launch(struct kvm_vm *vm, uint32_t policy); -void sev_vm_launch_measure(struct kvm_vm *vm, uint8_t *measurement); +void sev_vm_launch(struct kvm_vm *vm, u32 policy); +void sev_vm_launch_measure(struct kvm_vm *vm, u8 *measurement); void sev_vm_launch_finish(struct kvm_vm *vm); -void snp_vm_launch_start(struct kvm_vm *vm, uint64_t policy); +void snp_vm_launch_start(struct kvm_vm *vm, u64 policy); void snp_vm_launch_update(struct kvm_vm *vm); void snp_vm_launch_finish(struct kvm_vm *vm); -struct kvm_vm *vm_sev_create_with_one_vcpu(uint32_t type, void *guest_code, +struct kvm_vm *vm_sev_create_with_one_vcpu(u32 type, void *guest_code, struct kvm_vcpu **cpu); -void vm_sev_launch(struct kvm_vm *vm, uint64_t policy, uint8_t *measurement); +void vm_sev_launch(struct kvm_vm *vm, u64 policy, u8 *measurement); kvm_static_assert(SEV_RET_SUCCESS == 0); @@ -85,7 +85,7 @@ static inline u64 snp_default_policy(void) unsigned long raw; \ } sev_cmd = { .c = { \ .id = (cmd), \ - .data = (uint64_t)(arg), \ + .data = (u64)(arg), \ .sev_fd = (vm)->arch.sev_fd, \ } }; \ \ @@ -120,8 +120,8 @@ static inline void sev_register_encrypted_memory(struct kvm_vm *vm, vm_ioctl(vm, KVM_MEMORY_ENCRYPT_REG_REGION, &range); } -static inline void sev_launch_update_data(struct kvm_vm *vm, vm_paddr_t gpa, - uint64_t size) +static inline void sev_launch_update_data(struct kvm_vm *vm, gpa_t gpa, + u64 size) { struct kvm_sev_launch_update_data update_data = { .uaddr = (unsigned long)addr_gpa2hva(vm, gpa), @@ -131,8 +131,8 @@ static inline void sev_launch_update_data(struct kvm_vm *vm, vm_paddr_t gpa, vm_sev_ioctl(vm, KVM_SEV_LAUNCH_UPDATE_DATA, &update_data); } -static inline void snp_launch_update_data(struct kvm_vm *vm, vm_paddr_t gpa, - uint64_t hva, uint64_t size, uint8_t type) +static inline void snp_launch_update_data(struct kvm_vm *vm, gpa_t gpa, + u64 hva, u64 size, u8 type) { struct kvm_sev_snp_launch_update update_data = { .uaddr = hva, diff --git a/tools/testing/selftests/kvm/include/x86/smm.h b/tools/testing/selftests/kvm/include/x86/smm.h index 19337c34f13e..2d1afa09819b 100644 --- a/tools/testing/selftests/kvm/include/x86/smm.h +++ b/tools/testing/selftests/kvm/include/x86/smm.h @@ -8,8 +8,7 @@ #define SMRAM_MEMSLOT ((1 << 16) | 1) #define SMRAM_PAGES (SMRAM_SIZE / PAGE_SIZE) -void setup_smram(struct kvm_vm *vm, struct kvm_vcpu *vcpu, - uint64_t smram_gpa, +void setup_smram(struct kvm_vm *vm, struct kvm_vcpu *vcpu, u64 smram_gpa, const void *smi_handler, size_t handler_size); void inject_smi(struct kvm_vcpu *vcpu); diff --git a/tools/testing/selftests/kvm/include/x86/svm_util.h b/tools/testing/selftests/kvm/include/x86/svm_util.h index 5d7c42534bc4..6c013eb838be 100644 --- a/tools/testing/selftests/kvm/include/x86/svm_util.h +++ b/tools/testing/selftests/kvm/include/x86/svm_util.h @@ -16,20 +16,20 @@ struct svm_test_data { /* VMCB */ struct vmcb *vmcb; /* gva */ void *vmcb_hva; - uint64_t vmcb_gpa; + u64 vmcb_gpa; /* host state-save area */ struct vmcb_save_area *save_area; /* gva */ void *save_area_hva; - uint64_t save_area_gpa; + u64 save_area_gpa; /* MSR-Bitmap */ void *msr; /* gva */ void *msr_hva; - uint64_t msr_gpa; + u64 msr_gpa; /* NPT */ - uint64_t ncr3_gpa; + u64 ncr3_gpa; }; static inline void vmmcall(void) @@ -56,9 +56,9 @@ static inline void vmmcall(void) "clgi\n" \ ) -struct svm_test_data *vcpu_alloc_svm(struct kvm_vm *vm, vm_vaddr_t *p_svm_gva); +struct svm_test_data *vcpu_alloc_svm(struct kvm_vm *vm, gva_t *p_svm_gva); void generic_svm_setup(struct svm_test_data *svm, void *guest_rip, void *guest_rsp); -void run_guest(struct vmcb *vmcb, uint64_t vmcb_gpa); +void run_guest(struct vmcb *vmcb, u64 vmcb_gpa); static inline bool kvm_cpu_has_npt(void) { diff --git a/tools/testing/selftests/kvm/include/x86/ucall.h b/tools/testing/selftests/kvm/include/x86/ucall.h index d3825dcc3cd9..0e4950041e3e 100644 --- a/tools/testing/selftests/kvm/include/x86/ucall.h +++ b/tools/testing/selftests/kvm/include/x86/ucall.h @@ -6,7 +6,7 @@ #define UCALL_EXIT_REASON KVM_EXIT_IO -static inline void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa) +static inline void ucall_arch_init(struct kvm_vm *vm, gpa_t mmio_gpa) { } diff --git a/tools/testing/selftests/kvm/include/x86/vmx.h b/tools/testing/selftests/kvm/include/x86/vmx.h index 92b918700d24..90fffaf91595 100644 --- a/tools/testing/selftests/kvm/include/x86/vmx.h +++ b/tools/testing/selftests/kvm/include/x86/vmx.h @@ -285,16 +285,16 @@ enum vmcs_field { }; struct vmx_msr_entry { - uint32_t index; - uint32_t reserved; - uint64_t value; + u32 index; + u32 reserved; + u64 value; } __attribute__ ((aligned(16))); #include "evmcs.h" -static inline int vmxon(uint64_t phys) +static inline int vmxon(u64 phys) { - uint8_t ret; + u8 ret; __asm__ __volatile__ ("vmxon %[pa]; setna %[ret]" : [ret]"=rm"(ret) @@ -309,9 +309,9 @@ static inline void vmxoff(void) __asm__ __volatile__("vmxoff"); } -static inline int vmclear(uint64_t vmcs_pa) +static inline int vmclear(u64 vmcs_pa) { - uint8_t ret; + u8 ret; __asm__ __volatile__ ("vmclear %[pa]; setna %[ret]" : [ret]"=rm"(ret) @@ -321,9 +321,9 @@ static inline int vmclear(uint64_t vmcs_pa) return ret; } -static inline int vmptrld(uint64_t vmcs_pa) +static inline int vmptrld(u64 vmcs_pa) { - uint8_t ret; + u8 ret; if (enable_evmcs) return -1; @@ -336,10 +336,10 @@ static inline int vmptrld(uint64_t vmcs_pa) return ret; } -static inline int vmptrst(uint64_t *value) +static inline int vmptrst(u64 *value) { - uint64_t tmp; - uint8_t ret; + u64 tmp; + u8 ret; if (enable_evmcs) return evmcs_vmptrst(value); @@ -356,9 +356,9 @@ static inline int vmptrst(uint64_t *value) * A wrapper around vmptrst that ignores errors and returns zero if the * vmptrst instruction fails. */ -static inline uint64_t vmptrstz(void) +static inline u64 vmptrstz(void) { - uint64_t value = 0; + u64 value = 0; vmptrst(&value); return value; } @@ -391,8 +391,8 @@ static inline int vmlaunch(void) "pop %%rcx;" "pop %%rbp;" : [ret]"=&a"(ret) - : [host_rsp]"r"((uint64_t)HOST_RSP), - [host_rip]"r"((uint64_t)HOST_RIP) + : [host_rsp]"r"((u64)HOST_RSP), + [host_rip]"r"((u64)HOST_RIP) : "memory", "cc", "rbx", "r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15"); return ret; @@ -426,8 +426,8 @@ static inline int vmresume(void) "pop %%rcx;" "pop %%rbp;" : [ret]"=&a"(ret) - : [host_rsp]"r"((uint64_t)HOST_RSP), - [host_rip]"r"((uint64_t)HOST_RIP) + : [host_rsp]"r"((u64)HOST_RSP), + [host_rip]"r"((u64)HOST_RIP) : "memory", "cc", "rbx", "r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15"); return ret; @@ -447,10 +447,10 @@ static inline void vmcall(void) "r10", "r11", "r12", "r13", "r14", "r15"); } -static inline int vmread(uint64_t encoding, uint64_t *value) +static inline int vmread(u64 encoding, u64 *value) { - uint64_t tmp; - uint8_t ret; + u64 tmp; + u8 ret; if (enable_evmcs) return evmcs_vmread(encoding, value); @@ -468,16 +468,16 @@ static inline int vmread(uint64_t encoding, uint64_t *value) * A wrapper around vmread that ignores errors and returns zero if the * vmread instruction fails. */ -static inline uint64_t vmreadz(uint64_t encoding) +static inline u64 vmreadz(u64 encoding) { - uint64_t value = 0; + u64 value = 0; vmread(encoding, &value); return value; } -static inline int vmwrite(uint64_t encoding, uint64_t value) +static inline int vmwrite(u64 encoding, u64 value) { - uint8_t ret; + u8 ret; if (enable_evmcs) return evmcs_vmwrite(encoding, value); @@ -490,41 +490,41 @@ static inline int vmwrite(uint64_t encoding, uint64_t value) return ret; } -static inline uint32_t vmcs_revision(void) +static inline u32 vmcs_revision(void) { return rdmsr(MSR_IA32_VMX_BASIC); } struct vmx_pages { void *vmxon_hva; - uint64_t vmxon_gpa; + u64 vmxon_gpa; void *vmxon; void *vmcs_hva; - uint64_t vmcs_gpa; + u64 vmcs_gpa; void *vmcs; void *msr_hva; - uint64_t msr_gpa; + u64 msr_gpa; void *msr; void *shadow_vmcs_hva; - uint64_t shadow_vmcs_gpa; + u64 shadow_vmcs_gpa; void *shadow_vmcs; void *vmread_hva; - uint64_t vmread_gpa; + u64 vmread_gpa; void *vmread; void *vmwrite_hva; - uint64_t vmwrite_gpa; + u64 vmwrite_gpa; void *vmwrite; void *apic_access_hva; - uint64_t apic_access_gpa; + u64 apic_access_gpa; void *apic_access; - uint64_t eptp_gpa; + u64 eptp_gpa; }; union vmx_basic { @@ -550,7 +550,7 @@ union vmx_ctrl_msr { }; }; -struct vmx_pages *vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva); +struct vmx_pages *vcpu_alloc_vmx(struct kvm_vm *vm, gva_t *p_vmx_gva); bool prepare_for_vmx_operation(struct vmx_pages *vmx); void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp); bool load_vmcs(struct vmx_pages *vmx); diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c index c60a24a92829..fc5242fb956f 100644 --- a/tools/testing/selftests/kvm/kvm_page_table_test.c +++ b/tools/testing/selftests/kvm/kvm_page_table_test.c @@ -46,12 +46,12 @@ static const char * const test_stage_string[] = { struct test_args { struct kvm_vm *vm; - uint64_t guest_test_virt_mem; - uint64_t host_page_size; - uint64_t host_num_pages; - uint64_t large_page_size; - uint64_t large_num_pages; - uint64_t host_pages_per_lpage; + u64 guest_test_virt_mem; + u64 host_page_size; + u64 host_num_pages; + u64 large_page_size; + u64 large_num_pages; + u64 host_pages_per_lpage; enum vm_mem_backing_src_type src_type; struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; }; @@ -63,7 +63,7 @@ struct test_args { static enum test_stage guest_test_stage; /* Host variables */ -static uint32_t nr_vcpus = 1; +static u32 nr_vcpus = 1; static struct test_args test_args; static enum test_stage *current_stage; static bool host_quit; @@ -77,19 +77,19 @@ static sem_t test_stage_completed; * This will be set to the topmost valid physical address minus * the test memory size. */ -static uint64_t guest_test_phys_mem; +static u64 guest_test_phys_mem; /* * Guest virtual memory offset of the testing memory slot. * Must not conflict with identity mapped test code. */ -static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM; +static u64 guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM; static void guest_code(bool do_write) { struct test_args *p = &test_args; enum test_stage *current_stage = &guest_test_stage; - uint64_t addr; + u64 addr; int i, j; while (true) { @@ -113,9 +113,9 @@ static void guest_code(bool do_write) case KVM_CREATE_MAPPINGS: for (i = 0; i < p->large_num_pages; i++) { if (do_write) - *(uint64_t *)addr = 0x0123456789ABCDEF; + *(u64 *)addr = 0x0123456789ABCDEF; else - READ_ONCE(*(uint64_t *)addr); + READ_ONCE(*(u64 *)addr); addr += p->large_page_size; } @@ -131,7 +131,7 @@ static void guest_code(bool do_write) case KVM_UPDATE_MAPPINGS: if (p->src_type == VM_MEM_SRC_ANONYMOUS) { for (i = 0; i < p->host_num_pages; i++) { - *(uint64_t *)addr = 0x0123456789ABCDEF; + *(u64 *)addr = 0x0123456789ABCDEF; addr += p->host_page_size; } break; @@ -142,7 +142,7 @@ static void guest_code(bool do_write) * Write to the first host page in each large * page region, and triger break of large pages. */ - *(uint64_t *)addr = 0x0123456789ABCDEF; + *(u64 *)addr = 0x0123456789ABCDEF; /* * Access the middle host pages in each large @@ -152,7 +152,7 @@ static void guest_code(bool do_write) */ addr += p->large_page_size / 2; for (j = 0; j < p->host_pages_per_lpage / 2; j++) { - READ_ONCE(*(uint64_t *)addr); + READ_ONCE(*(u64 *)addr); addr += p->host_page_size; } } @@ -167,7 +167,7 @@ static void guest_code(bool do_write) */ case KVM_ADJUST_MAPPINGS: for (i = 0; i < p->host_num_pages; i++) { - READ_ONCE(*(uint64_t *)addr); + READ_ONCE(*(u64 *)addr); addr += p->host_page_size; } break; @@ -227,8 +227,8 @@ static void *vcpu_worker(void *data) } struct test_params { - uint64_t phys_offset; - uint64_t test_mem_size; + u64 phys_offset; + u64 test_mem_size; enum vm_mem_backing_src_type src_type; }; @@ -237,12 +237,12 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg) int ret; struct test_params *p = arg; enum vm_mem_backing_src_type src_type = p->src_type; - uint64_t large_page_size = get_backing_src_pagesz(src_type); - uint64_t guest_page_size = vm_guest_mode_params[mode].page_size; - uint64_t host_page_size = getpagesize(); - uint64_t test_mem_size = p->test_mem_size; - uint64_t guest_num_pages; - uint64_t alignment; + u64 large_page_size = get_backing_src_pagesz(src_type); + u64 guest_page_size = vm_guest_mode_params[mode].page_size; + u64 host_page_size = getpagesize(); + u64 test_mem_size = p->test_mem_size; + u64 guest_num_pages; + u64 alignment; void *host_test_mem; struct kvm_vm *vm; @@ -281,7 +281,7 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg) virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages); /* Cache the HVA pointer of the region */ - host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)guest_test_phys_mem); + host_test_mem = addr_gpa2hva(vm, (gpa_t)guest_test_phys_mem); /* Export shared structure test_args to guest */ sync_global_to_guest(vm, test_args); @@ -292,7 +292,7 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg) ret = sem_init(&test_stage_completed, 0, 0); TEST_ASSERT(ret == 0, "Error in sem_init"); - current_stage = addr_gva2hva(vm, (vm_vaddr_t)(&guest_test_stage)); + current_stage = addr_gva2hva(vm, (gva_t)(&guest_test_stage)); *current_stage = NUM_TEST_STAGES; pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode)); @@ -304,7 +304,7 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg) pr_info("Guest physical test memory offset: 0x%lx\n", guest_test_phys_mem); pr_info("Host virtual test memory offset: 0x%lx\n", - (uint64_t)host_test_mem); + (u64)host_test_mem); pr_info("Number of testing vCPUs: %d\n", nr_vcpus); return vm; diff --git a/tools/testing/selftests/kvm/lib/arm64/gic.c b/tools/testing/selftests/kvm/lib/arm64/gic.c index b023868fe0b8..011dfe1dfcb3 100644 --- a/tools/testing/selftests/kvm/lib/arm64/gic.c +++ b/tools/testing/selftests/kvm/lib/arm64/gic.c @@ -50,7 +50,7 @@ static void gic_dist_init(enum gic_type type, unsigned int nr_cpus) void gic_init(enum gic_type type, unsigned int nr_cpus) { - uint32_t cpu = guest_get_vcpuid(); + u32 cpu = guest_get_vcpuid(); GUEST_ASSERT(type < GIC_TYPE_MAX); GUEST_ASSERT(nr_cpus); @@ -73,7 +73,7 @@ void gic_irq_disable(unsigned int intid) unsigned int gic_get_and_ack_irq(void) { - uint64_t irqstat; + u64 irqstat; unsigned int intid; GUEST_ASSERT(gic_common_ops); @@ -102,7 +102,7 @@ void gic_set_eoi_split(bool split) gic_common_ops->gic_set_eoi_split(split); } -void gic_set_priority_mask(uint64_t pmr) +void gic_set_priority_mask(u64 pmr) { GUEST_ASSERT(gic_common_ops); gic_common_ops->gic_set_priority_mask(pmr); diff --git a/tools/testing/selftests/kvm/lib/arm64/gic_private.h b/tools/testing/selftests/kvm/lib/arm64/gic_private.h index b6a7e30c3eb1..6d393f5c5685 100644 --- a/tools/testing/selftests/kvm/lib/arm64/gic_private.h +++ b/tools/testing/selftests/kvm/lib/arm64/gic_private.h @@ -12,20 +12,20 @@ struct gic_common_ops { void (*gic_cpu_init)(unsigned int cpu); void (*gic_irq_enable)(unsigned int intid); void (*gic_irq_disable)(unsigned int intid); - uint64_t (*gic_read_iar)(void); - void (*gic_write_eoir)(uint32_t irq); - void (*gic_write_dir)(uint32_t irq); + u64 (*gic_read_iar)(void); + void (*gic_write_eoir)(u32 irq); + void (*gic_write_dir)(u32 irq); void (*gic_set_eoi_split)(bool split); - void (*gic_set_priority_mask)(uint64_t mask); - void (*gic_set_priority)(uint32_t intid, uint32_t prio); - void (*gic_irq_set_active)(uint32_t intid); - void (*gic_irq_clear_active)(uint32_t intid); - bool (*gic_irq_get_active)(uint32_t intid); - void (*gic_irq_set_pending)(uint32_t intid); - void (*gic_irq_clear_pending)(uint32_t intid); - bool (*gic_irq_get_pending)(uint32_t intid); - void (*gic_irq_set_config)(uint32_t intid, bool is_edge); - void (*gic_irq_set_group)(uint32_t intid, bool group); + void (*gic_set_priority_mask)(u64 mask); + void (*gic_set_priority)(u32 intid, u32 prio); + void (*gic_irq_set_active)(u32 intid); + void (*gic_irq_clear_active)(u32 intid); + bool (*gic_irq_get_active)(u32 intid); + void (*gic_irq_set_pending)(u32 intid); + void (*gic_irq_clear_pending)(u32 intid); + bool (*gic_irq_get_pending)(u32 intid); + void (*gic_irq_set_config)(u32 intid, bool is_edge); + void (*gic_irq_set_group)(u32 intid, bool group); }; extern const struct gic_common_ops gicv3_ops; diff --git a/tools/testing/selftests/kvm/lib/arm64/gic_v3.c b/tools/testing/selftests/kvm/lib/arm64/gic_v3.c index 50754a27f493..a99a53accfe9 100644 --- a/tools/testing/selftests/kvm/lib/arm64/gic_v3.c +++ b/tools/testing/selftests/kvm/lib/arm64/gic_v3.c @@ -50,13 +50,13 @@ static void gicv3_gicd_wait_for_rwp(void) } } -static inline volatile void *gicr_base_cpu(uint32_t cpu) +static inline volatile void *gicr_base_cpu(u32 cpu) { /* Align all the redistributors sequentially */ return GICR_BASE_GVA + cpu * SZ_64K * 2; } -static void gicv3_gicr_wait_for_rwp(uint32_t cpu) +static void gicv3_gicr_wait_for_rwp(u32 cpu) { unsigned int count = 100000; /* 1s */ @@ -66,7 +66,7 @@ static void gicv3_gicr_wait_for_rwp(uint32_t cpu) } } -static void gicv3_wait_for_rwp(uint32_t cpu_or_dist) +static void gicv3_wait_for_rwp(u32 cpu_or_dist) { if (cpu_or_dist & DIST_BIT) gicv3_gicd_wait_for_rwp(); @@ -91,34 +91,34 @@ static enum gicv3_intid_range get_intid_range(unsigned int intid) return INVALID_RANGE; } -static uint64_t gicv3_read_iar(void) +static u64 gicv3_read_iar(void) { - uint64_t irqstat = read_sysreg_s(SYS_ICC_IAR1_EL1); + u64 irqstat = read_sysreg_s(SYS_ICC_IAR1_EL1); dsb(sy); return irqstat; } -static void gicv3_write_eoir(uint32_t irq) +static void gicv3_write_eoir(u32 irq) { write_sysreg_s(irq, SYS_ICC_EOIR1_EL1); isb(); } -static void gicv3_write_dir(uint32_t irq) +static void gicv3_write_dir(u32 irq) { write_sysreg_s(irq, SYS_ICC_DIR_EL1); isb(); } -static void gicv3_set_priority_mask(uint64_t mask) +static void gicv3_set_priority_mask(u64 mask) { write_sysreg_s(mask, SYS_ICC_PMR_EL1); } static void gicv3_set_eoi_split(bool split) { - uint32_t val; + u32 val; /* * All other fields are read-only, so no need to read CTLR first. In @@ -129,29 +129,29 @@ static void gicv3_set_eoi_split(bool split) isb(); } -uint32_t gicv3_reg_readl(uint32_t cpu_or_dist, uint64_t offset) +u32 gicv3_reg_readl(u32 cpu_or_dist, u64 offset) { volatile void *base = cpu_or_dist & DIST_BIT ? GICD_BASE_GVA : sgi_base_from_redist(gicr_base_cpu(cpu_or_dist)); return readl(base + offset); } -void gicv3_reg_writel(uint32_t cpu_or_dist, uint64_t offset, uint32_t reg_val) +void gicv3_reg_writel(u32 cpu_or_dist, u64 offset, u32 reg_val) { volatile void *base = cpu_or_dist & DIST_BIT ? GICD_BASE_GVA : sgi_base_from_redist(gicr_base_cpu(cpu_or_dist)); writel(reg_val, base + offset); } -uint32_t gicv3_getl_fields(uint32_t cpu_or_dist, uint64_t offset, uint32_t mask) +u32 gicv3_getl_fields(u32 cpu_or_dist, u64 offset, u32 mask) { return gicv3_reg_readl(cpu_or_dist, offset) & mask; } -void gicv3_setl_fields(uint32_t cpu_or_dist, uint64_t offset, - uint32_t mask, uint32_t reg_val) +void gicv3_setl_fields(u32 cpu_or_dist, u64 offset, + u32 mask, u32 reg_val) { - uint32_t tmp = gicv3_reg_readl(cpu_or_dist, offset) & ~mask; + u32 tmp = gicv3_reg_readl(cpu_or_dist, offset) & ~mask; tmp |= (reg_val & mask); gicv3_reg_writel(cpu_or_dist, offset, tmp); @@ -165,14 +165,14 @@ void gicv3_setl_fields(uint32_t cpu_or_dist, uint64_t offset, * map that doesn't implement it; like GICR_WAKER's offset of 0x0014 being * marked as "Reserved" in the Distributor map. */ -static void gicv3_access_reg(uint32_t intid, uint64_t offset, - uint32_t reg_bits, uint32_t bits_per_field, - bool write, uint32_t *val) +static void gicv3_access_reg(u32 intid, u64 offset, + u32 reg_bits, u32 bits_per_field, + bool write, u32 *val) { - uint32_t cpu = guest_get_vcpuid(); + u32 cpu = guest_get_vcpuid(); enum gicv3_intid_range intid_range = get_intid_range(intid); - uint32_t fields_per_reg, index, mask, shift; - uint32_t cpu_or_dist; + u32 fields_per_reg, index, mask, shift; + u32 cpu_or_dist; GUEST_ASSERT(bits_per_field <= reg_bits); GUEST_ASSERT(!write || *val < (1U << bits_per_field)); @@ -197,32 +197,32 @@ static void gicv3_access_reg(uint32_t intid, uint64_t offset, *val = gicv3_getl_fields(cpu_or_dist, offset, mask) >> shift; } -static void gicv3_write_reg(uint32_t intid, uint64_t offset, - uint32_t reg_bits, uint32_t bits_per_field, uint32_t val) +static void gicv3_write_reg(u32 intid, u64 offset, + u32 reg_bits, u32 bits_per_field, u32 val) { gicv3_access_reg(intid, offset, reg_bits, bits_per_field, true, &val); } -static uint32_t gicv3_read_reg(uint32_t intid, uint64_t offset, - uint32_t reg_bits, uint32_t bits_per_field) +static u32 gicv3_read_reg(u32 intid, u64 offset, + u32 reg_bits, u32 bits_per_field) { - uint32_t val; + u32 val; gicv3_access_reg(intid, offset, reg_bits, bits_per_field, false, &val); return val; } -static void gicv3_set_priority(uint32_t intid, uint32_t prio) +static void gicv3_set_priority(u32 intid, u32 prio) { gicv3_write_reg(intid, GICD_IPRIORITYR, 32, 8, prio); } /* Sets the intid to be level-sensitive or edge-triggered. */ -static void gicv3_irq_set_config(uint32_t intid, bool is_edge) +static void gicv3_irq_set_config(u32 intid, bool is_edge) { - uint32_t val; + u32 val; /* N/A for private interrupts. */ GUEST_ASSERT(get_intid_range(intid) == SPI_RANGE); @@ -230,57 +230,57 @@ static void gicv3_irq_set_config(uint32_t intid, bool is_edge) gicv3_write_reg(intid, GICD_ICFGR, 32, 2, val); } -static void gicv3_irq_enable(uint32_t intid) +static void gicv3_irq_enable(u32 intid) { bool is_spi = get_intid_range(intid) == SPI_RANGE; - uint32_t cpu = guest_get_vcpuid(); + u32 cpu = guest_get_vcpuid(); gicv3_write_reg(intid, GICD_ISENABLER, 32, 1, 1); gicv3_wait_for_rwp(is_spi ? DIST_BIT : cpu); } -static void gicv3_irq_disable(uint32_t intid) +static void gicv3_irq_disable(u32 intid) { bool is_spi = get_intid_range(intid) == SPI_RANGE; - uint32_t cpu = guest_get_vcpuid(); + u32 cpu = guest_get_vcpuid(); gicv3_write_reg(intid, GICD_ICENABLER, 32, 1, 1); gicv3_wait_for_rwp(is_spi ? DIST_BIT : cpu); } -static void gicv3_irq_set_active(uint32_t intid) +static void gicv3_irq_set_active(u32 intid) { gicv3_write_reg(intid, GICD_ISACTIVER, 32, 1, 1); } -static void gicv3_irq_clear_active(uint32_t intid) +static void gicv3_irq_clear_active(u32 intid) { gicv3_write_reg(intid, GICD_ICACTIVER, 32, 1, 1); } -static bool gicv3_irq_get_active(uint32_t intid) +static bool gicv3_irq_get_active(u32 intid) { return gicv3_read_reg(intid, GICD_ISACTIVER, 32, 1); } -static void gicv3_irq_set_pending(uint32_t intid) +static void gicv3_irq_set_pending(u32 intid) { gicv3_write_reg(intid, GICD_ISPENDR, 32, 1, 1); } -static void gicv3_irq_clear_pending(uint32_t intid) +static void gicv3_irq_clear_pending(u32 intid) { gicv3_write_reg(intid, GICD_ICPENDR, 32, 1, 1); } -static bool gicv3_irq_get_pending(uint32_t intid) +static bool gicv3_irq_get_pending(u32 intid) { return gicv3_read_reg(intid, GICD_ISPENDR, 32, 1); } static void gicv3_enable_redist(volatile void *redist_base) { - uint32_t val = readl(redist_base + GICR_WAKER); + u32 val = readl(redist_base + GICR_WAKER); unsigned int count = 100000; /* 1s */ val &= ~GICR_WAKER_ProcessorSleep; @@ -293,10 +293,10 @@ static void gicv3_enable_redist(volatile void *redist_base) } } -static void gicv3_set_group(uint32_t intid, bool grp) +static void gicv3_set_group(u32 intid, bool grp) { - uint32_t cpu_or_dist; - uint32_t val; + u32 cpu_or_dist; + u32 val; cpu_or_dist = (get_intid_range(intid) == SPI_RANGE) ? DIST_BIT : guest_get_vcpuid(); val = gicv3_reg_readl(cpu_or_dist, GICD_IGROUPR + (intid / 32) * 4); @@ -424,8 +424,8 @@ const struct gic_common_ops gicv3_ops = { .gic_irq_set_group = gicv3_set_group, }; -void gic_rdist_enable_lpis(vm_paddr_t cfg_table, size_t cfg_table_size, - vm_paddr_t pend_table) +void gic_rdist_enable_lpis(gpa_t cfg_table, size_t cfg_table_size, + gpa_t pend_table) { volatile void *rdist_base = gicr_base_cpu(guest_get_vcpuid()); diff --git a/tools/testing/selftests/kvm/lib/arm64/gic_v3_its.c b/tools/testing/selftests/kvm/lib/arm64/gic_v3_its.c index 7f9fdcf42ae6..1188b578121d 100644 --- a/tools/testing/selftests/kvm/lib/arm64/gic_v3_its.c +++ b/tools/testing/selftests/kvm/lib/arm64/gic_v3_its.c @@ -54,7 +54,7 @@ static unsigned long its_find_baser(unsigned int type) return -1; } -static void its_install_table(unsigned int type, vm_paddr_t base, size_t size) +static void its_install_table(unsigned int type, gpa_t base, size_t size) { unsigned long offset = its_find_baser(type); u64 baser; @@ -69,7 +69,7 @@ static void its_install_table(unsigned int type, vm_paddr_t base, size_t size) its_write_u64(offset, baser); } -static void its_install_cmdq(vm_paddr_t base, size_t size) +static void its_install_cmdq(gpa_t base, size_t size) { u64 cbaser; @@ -82,9 +82,8 @@ static void its_install_cmdq(vm_paddr_t base, size_t size) its_write_u64(GITS_CBASER, cbaser); } -void its_init(vm_paddr_t coll_tbl, size_t coll_tbl_sz, - vm_paddr_t device_tbl, size_t device_tbl_sz, - vm_paddr_t cmdq, size_t cmdq_size) +void its_init(gpa_t coll_tbl, size_t coll_tbl_sz, gpa_t device_tbl, + size_t device_tbl_sz, gpa_t cmdq, size_t cmdq_size) { u32 ctlr; @@ -204,7 +203,7 @@ static void its_send_cmd(void *cmdq_base, struct its_cmd_block *cmd) } } -void its_send_mapd_cmd(void *cmdq_base, u32 device_id, vm_paddr_t itt_base, +void its_send_mapd_cmd(void *cmdq_base, u32 device_id, gpa_t itt_base, size_t itt_size, bool valid) { struct its_cmd_block cmd = {}; diff --git a/tools/testing/selftests/kvm/lib/arm64/processor.c b/tools/testing/selftests/kvm/lib/arm64/processor.c index 43ea40edc533..01325bf4d36f 100644 --- a/tools/testing/selftests/kvm/lib/arm64/processor.c +++ b/tools/testing/selftests/kvm/lib/arm64/processor.c @@ -19,20 +19,20 @@ #define DEFAULT_ARM64_GUEST_STACK_VADDR_MIN 0xac0000 -static vm_vaddr_t exception_handlers; +static gva_t exception_handlers; -static uint64_t pgd_index(struct kvm_vm *vm, vm_vaddr_t gva) +static u64 pgd_index(struct kvm_vm *vm, gva_t gva) { unsigned int shift = (vm->mmu.pgtable_levels - 1) * (vm->page_shift - 3) + vm->page_shift; - uint64_t mask = (1UL << (vm->va_bits - shift)) - 1; + u64 mask = (1UL << (vm->va_bits - shift)) - 1; return (gva >> shift) & mask; } -static uint64_t pud_index(struct kvm_vm *vm, vm_vaddr_t gva) +static u64 pud_index(struct kvm_vm *vm, gva_t gva) { unsigned int shift = 2 * (vm->page_shift - 3) + vm->page_shift; - uint64_t mask = (1UL << (vm->page_shift - 3)) - 1; + u64 mask = (1UL << (vm->page_shift - 3)) - 1; TEST_ASSERT(vm->mmu.pgtable_levels == 4, "Mode %d does not have 4 page table levels", vm->mode); @@ -40,10 +40,10 @@ static uint64_t pud_index(struct kvm_vm *vm, vm_vaddr_t gva) return (gva >> shift) & mask; } -static uint64_t pmd_index(struct kvm_vm *vm, vm_vaddr_t gva) +static u64 pmd_index(struct kvm_vm *vm, gva_t gva) { unsigned int shift = (vm->page_shift - 3) + vm->page_shift; - uint64_t mask = (1UL << (vm->page_shift - 3)) - 1; + u64 mask = (1UL << (vm->page_shift - 3)) - 1; TEST_ASSERT(vm->mmu.pgtable_levels >= 3, "Mode %d does not have >= 3 page table levels", vm->mode); @@ -51,9 +51,9 @@ static uint64_t pmd_index(struct kvm_vm *vm, vm_vaddr_t gva) return (gva >> shift) & mask; } -static uint64_t pte_index(struct kvm_vm *vm, vm_vaddr_t gva) +static u64 pte_index(struct kvm_vm *vm, gva_t gva) { - uint64_t mask = (1UL << (vm->page_shift - 3)) - 1; + u64 mask = (1UL << (vm->page_shift - 3)) - 1; return (gva >> vm->page_shift) & mask; } @@ -63,9 +63,9 @@ static inline bool use_lpa2_pte_format(struct kvm_vm *vm) (vm->pa_bits > 48 || vm->va_bits > 48); } -static uint64_t addr_pte(struct kvm_vm *vm, uint64_t pa, uint64_t attrs) +static u64 addr_pte(struct kvm_vm *vm, u64 pa, u64 attrs) { - uint64_t pte; + u64 pte; if (use_lpa2_pte_format(vm)) { pte = pa & PTE_ADDR_MASK_LPA2(vm->page_shift); @@ -81,9 +81,9 @@ static uint64_t addr_pte(struct kvm_vm *vm, uint64_t pa, uint64_t attrs) return pte; } -static uint64_t pte_addr(struct kvm_vm *vm, uint64_t pte) +static u64 pte_addr(struct kvm_vm *vm, u64 pte) { - uint64_t pa; + u64 pa; if (use_lpa2_pte_format(vm)) { pa = pte & PTE_ADDR_MASK_LPA2(vm->page_shift); @@ -97,13 +97,13 @@ static uint64_t pte_addr(struct kvm_vm *vm, uint64_t pte) return pa; } -static uint64_t ptrs_per_pgd(struct kvm_vm *vm) +static u64 ptrs_per_pgd(struct kvm_vm *vm) { unsigned int shift = (vm->mmu.pgtable_levels - 1) * (vm->page_shift - 3) + vm->page_shift; return 1 << (vm->va_bits - shift); } -static uint64_t __maybe_unused ptrs_per_pte(struct kvm_vm *vm) +static u64 __maybe_unused ptrs_per_pte(struct kvm_vm *vm) { return 1 << (vm->page_shift - 3); } @@ -121,47 +121,46 @@ void virt_arch_pgd_alloc(struct kvm_vm *vm) vm->mmu.pgd_created = true; } -static void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, - uint64_t flags) +static void _virt_pg_map(struct kvm_vm *vm, gva_t gva, gpa_t gpa, + u64 flags) { - uint8_t attr_idx = flags & (PTE_ATTRINDX_MASK >> PTE_ATTRINDX_SHIFT); - uint64_t pg_attr; - uint64_t *ptep; + u8 attr_idx = flags & (PTE_ATTRINDX_MASK >> PTE_ATTRINDX_SHIFT); + u64 pg_attr; + u64 *ptep; - TEST_ASSERT((vaddr % vm->page_size) == 0, + TEST_ASSERT((gva % vm->page_size) == 0, "Virtual address not on page boundary,\n" - " vaddr: 0x%lx vm->page_size: 0x%x", vaddr, vm->page_size); - TEST_ASSERT(sparsebit_is_set(vm->vpages_valid, - (vaddr >> vm->page_shift)), - "Invalid virtual address, vaddr: 0x%lx", vaddr); - TEST_ASSERT((paddr % vm->page_size) == 0, - "Physical address not on page boundary,\n" - " paddr: 0x%lx vm->page_size: 0x%x", paddr, vm->page_size); - TEST_ASSERT((paddr >> vm->page_shift) <= vm->max_gfn, - "Physical address beyond beyond maximum supported,\n" - " paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x", - paddr, vm->max_gfn, vm->page_size); - - ptep = addr_gpa2hva(vm, vm->mmu.pgd) + pgd_index(vm, vaddr) * 8; + " gva: 0x%lx vm->page_size: 0x%x", gva, vm->page_size); + TEST_ASSERT(sparsebit_is_set(vm->vpages_valid, (gva >> vm->page_shift)), + "Invalid virtual address, gva: 0x%lx", gva); + TEST_ASSERT((gpa % vm->page_size) == 0, + "Physical address not on page boundary,\n" + " gpa: 0x%lx vm->page_size: 0x%x", gpa, vm->page_size); + TEST_ASSERT((gpa >> vm->page_shift) <= vm->max_gfn, + "Physical address beyond beyond maximum supported,\n" + " gpa: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x", + gpa, vm->max_gfn, vm->page_size); + + ptep = addr_gpa2hva(vm, vm->mmu.pgd) + pgd_index(vm, gva) * 8; if (!*ptep) *ptep = addr_pte(vm, vm_alloc_page_table(vm), PGD_TYPE_TABLE | PTE_VALID); switch (vm->mmu.pgtable_levels) { case 4: - ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pud_index(vm, vaddr) * 8; + ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pud_index(vm, gva) * 8; if (!*ptep) *ptep = addr_pte(vm, vm_alloc_page_table(vm), PUD_TYPE_TABLE | PTE_VALID); /* fall through */ case 3: - ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pmd_index(vm, vaddr) * 8; + ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pmd_index(vm, gva) * 8; if (!*ptep) *ptep = addr_pte(vm, vm_alloc_page_table(vm), PMD_TYPE_TABLE | PTE_VALID); /* fall through */ case 2: - ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pte_index(vm, vaddr) * 8; + ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pte_index(vm, gva) * 8; break; default: TEST_FAIL("Page table levels must be 2, 3, or 4"); @@ -171,19 +170,19 @@ static void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, if (!use_lpa2_pte_format(vm)) pg_attr |= PTE_SHARED; - *ptep = addr_pte(vm, paddr, pg_attr); + *ptep = addr_pte(vm, gpa, pg_attr); } -void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) +void virt_arch_pg_map(struct kvm_vm *vm, gva_t gva, gpa_t gpa) { - uint64_t attr_idx = MT_NORMAL; + u64 attr_idx = MT_NORMAL; - _virt_pg_map(vm, vaddr, paddr, attr_idx); + _virt_pg_map(vm, gva, gpa, attr_idx); } -uint64_t *virt_get_pte_hva_at_level(struct kvm_vm *vm, vm_vaddr_t gva, int level) +u64 *virt_get_pte_hva_at_level(struct kvm_vm *vm, gva_t gva, int level) { - uint64_t *ptep; + u64 *ptep; if (!vm->mmu.pgd_created) goto unmapped_gva; @@ -225,23 +224,23 @@ unmapped_gva: exit(EXIT_FAILURE); } -uint64_t *virt_get_pte_hva(struct kvm_vm *vm, vm_vaddr_t gva) +u64 *virt_get_pte_hva(struct kvm_vm *vm, gva_t gva) { return virt_get_pte_hva_at_level(vm, gva, 3); } -vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) +gpa_t addr_arch_gva2gpa(struct kvm_vm *vm, gva_t gva) { - uint64_t *ptep = virt_get_pte_hva(vm, gva); + u64 *ptep = virt_get_pte_hva(vm, gva); return pte_addr(vm, *ptep) + (gva & (vm->page_size - 1)); } -static void pte_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent, uint64_t page, int level) +static void pte_dump(FILE *stream, struct kvm_vm *vm, u8 indent, u64 page, int level) { #ifdef DEBUG static const char * const type[] = { "", "pud", "pmd", "pte" }; - uint64_t pte, *ptep; + u64 pte, *ptep; if (level == 4) return; @@ -256,10 +255,10 @@ static void pte_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent, uint64_t p #endif } -void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) +void virt_arch_dump(FILE *stream, struct kvm_vm *vm, u8 indent) { int level = 4 - (vm->mmu.pgtable_levels - 1); - uint64_t pgd, *ptep; + u64 pgd, *ptep; if (!vm->mmu.pgd_created) return; @@ -298,7 +297,7 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init) { struct kvm_vcpu_init default_init = { .target = -1, }; struct kvm_vm *vm = vcpu->vm; - uint64_t sctlr_el1, tcr_el1, ttbr0_el1; + u64 sctlr_el1, tcr_el1, ttbr0_el1; if (!init) { kvm_get_default_vcpu_target(vm, &default_init); @@ -397,9 +396,9 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init) HCR_EL2_RW | HCR_EL2_TGE | HCR_EL2_E2H); } -void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, uint8_t indent) +void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, u8 indent) { - uint64_t pstate, pc; + u64 pstate, pc; pstate = vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pstate)); pc = vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc)); @@ -410,29 +409,29 @@ void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, uint8_t indent) void vcpu_arch_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code) { - vcpu_set_reg(vcpu, ARM64_CORE_REG(regs.pc), (uint64_t)guest_code); + vcpu_set_reg(vcpu, ARM64_CORE_REG(regs.pc), (u64)guest_code); } -static struct kvm_vcpu *__aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, +static struct kvm_vcpu *__aarch64_vcpu_add(struct kvm_vm *vm, u32 vcpu_id, struct kvm_vcpu_init *init) { size_t stack_size; - uint64_t stack_vaddr; + gva_t stack_gva; struct kvm_vcpu *vcpu = __vm_vcpu_add(vm, vcpu_id); stack_size = vm->page_size == 4096 ? DEFAULT_STACK_PGS * vm->page_size : vm->page_size; - stack_vaddr = __vm_vaddr_alloc(vm, stack_size, - DEFAULT_ARM64_GUEST_STACK_VADDR_MIN, - MEM_REGION_DATA); + stack_gva = __vm_alloc(vm, stack_size, + DEFAULT_ARM64_GUEST_STACK_VADDR_MIN, + MEM_REGION_DATA); aarch64_vcpu_setup(vcpu, init); - vcpu_set_reg(vcpu, ctxt_reg_alias(vcpu, SYS_SP_EL1), stack_vaddr + stack_size); + vcpu_set_reg(vcpu, ctxt_reg_alias(vcpu, SYS_SP_EL1), stack_gva + stack_size); return vcpu; } -struct kvm_vcpu *aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, +struct kvm_vcpu *aarch64_vcpu_add(struct kvm_vm *vm, u32 vcpu_id, struct kvm_vcpu_init *init, void *guest_code) { struct kvm_vcpu *vcpu = __aarch64_vcpu_add(vm, vcpu_id, init); @@ -442,7 +441,7 @@ struct kvm_vcpu *aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, return vcpu; } -struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id) +struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, u32 vcpu_id) { return __aarch64_vcpu_add(vm, vcpu_id, NULL); } @@ -459,13 +458,13 @@ void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...) for (i = 0; i < num; i++) { vcpu_set_reg(vcpu, ARM64_CORE_REG(regs.regs[i]), - va_arg(ap, uint64_t)); + va_arg(ap, u64)); } va_end(ap); } -void kvm_exit_unexpected_exception(int vector, uint64_t ec, bool valid_ec) +void kvm_exit_unexpected_exception(int vector, u64 ec, bool valid_ec) { ucall(UCALL_UNHANDLED, 3, vector, ec, valid_ec); while (1) @@ -498,7 +497,7 @@ void vcpu_init_descriptor_tables(struct kvm_vcpu *vcpu) { extern char vectors; - vcpu_set_reg(vcpu, ctxt_reg_alias(vcpu, SYS_VBAR_EL1), (uint64_t)&vectors); + vcpu_set_reg(vcpu, ctxt_reg_alias(vcpu, SYS_VBAR_EL1), (u64)&vectors); } void route_exception(struct ex_regs *regs, int vector) @@ -536,10 +535,10 @@ unexpected_exception: void vm_init_descriptor_tables(struct kvm_vm *vm) { - vm->handlers = __vm_vaddr_alloc(vm, sizeof(struct handlers), - vm->page_size, MEM_REGION_DATA); + vm->handlers = __vm_alloc(vm, sizeof(struct handlers), vm->page_size, + MEM_REGION_DATA); - *(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers; + *(gva_t *)addr_gva2hva(vm, (gva_t)(&exception_handlers)) = vm->handlers; } void vm_install_sync_handler(struct kvm_vm *vm, int vector, int ec, @@ -563,13 +562,13 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector, handlers->exception_handlers[vector][0] = handler; } -uint32_t guest_get_vcpuid(void) +u32 guest_get_vcpuid(void) { return read_sysreg(tpidr_el1); } -static uint32_t max_ipa_for_page_size(uint32_t vm_ipa, uint32_t gran, - uint32_t not_sup_val, uint32_t ipa52_min_val) +static u32 max_ipa_for_page_size(u32 vm_ipa, u32 gran, + u32 not_sup_val, u32 ipa52_min_val) { if (gran == not_sup_val) return 0; @@ -579,16 +578,16 @@ static uint32_t max_ipa_for_page_size(uint32_t vm_ipa, uint32_t gran, return min(vm_ipa, 48U); } -void aarch64_get_supported_page_sizes(uint32_t ipa, uint32_t *ipa4k, - uint32_t *ipa16k, uint32_t *ipa64k) +void aarch64_get_supported_page_sizes(u32 ipa, u32 *ipa4k, + u32 *ipa16k, u32 *ipa64k) { struct kvm_vcpu_init preferred_init; int kvm_fd, vm_fd, vcpu_fd, err; - uint64_t val; - uint32_t gran; + u64 val; + u32 gran; struct kvm_one_reg reg = { .id = KVM_ARM64_SYS_REG(SYS_ID_AA64MMFR0_EL1), - .addr = (uint64_t)&val, + .addr = (u64)&val, }; kvm_fd = open_kvm_dev_path_or_exit(); @@ -646,17 +645,17 @@ void aarch64_get_supported_page_sizes(uint32_t ipa, uint32_t *ipa4k, : "x0", "x1", "x2", "x3", "x4", "x5", "x6", "x7") -void smccc_hvc(uint32_t function_id, uint64_t arg0, uint64_t arg1, - uint64_t arg2, uint64_t arg3, uint64_t arg4, uint64_t arg5, - uint64_t arg6, struct arm_smccc_res *res) +void smccc_hvc(u32 function_id, u64 arg0, u64 arg1, + u64 arg2, u64 arg3, u64 arg4, u64 arg5, + u64 arg6, struct arm_smccc_res *res) { __smccc_call(hvc, function_id, arg0, arg1, arg2, arg3, arg4, arg5, arg6, res); } -void smccc_smc(uint32_t function_id, uint64_t arg0, uint64_t arg1, - uint64_t arg2, uint64_t arg3, uint64_t arg4, uint64_t arg5, - uint64_t arg6, struct arm_smccc_res *res) +void smccc_smc(u32 function_id, u64 arg0, u64 arg1, + u64 arg2, u64 arg3, u64 arg4, u64 arg5, + u64 arg6, struct arm_smccc_res *res) { __smccc_call(smc, function_id, arg0, arg1, arg2, arg3, arg4, arg5, arg6, res); @@ -671,7 +670,7 @@ void kvm_selftest_arch_init(void) guest_modes_append_default(); } -void vm_vaddr_populate_bitmap(struct kvm_vm *vm) +void vm_populate_gva_bitmap(struct kvm_vm *vm) { /* * arm64 selftests use only TTBR0_EL1, meaning that the valid VA space diff --git a/tools/testing/selftests/kvm/lib/arm64/ucall.c b/tools/testing/selftests/kvm/lib/arm64/ucall.c index ddab0ce89d4d..e0550ad5aa75 100644 --- a/tools/testing/selftests/kvm/lib/arm64/ucall.c +++ b/tools/testing/selftests/kvm/lib/arm64/ucall.c @@ -6,17 +6,17 @@ */ #include "kvm_util.h" -vm_vaddr_t *ucall_exit_mmio_addr; +gva_t *ucall_exit_mmio_addr; -void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa) +void ucall_arch_init(struct kvm_vm *vm, gpa_t mmio_gpa) { - vm_vaddr_t mmio_gva = vm_vaddr_unused_gap(vm, vm->page_size, KVM_UTIL_MIN_VADDR); + gva_t mmio_gva = vm_unused_gva_gap(vm, vm->page_size, KVM_UTIL_MIN_VADDR); virt_map(vm, mmio_gva, mmio_gpa, 1); vm->ucall_mmio_addr = mmio_gpa; - write_guest_global(vm, ucall_exit_mmio_addr, (vm_vaddr_t *)mmio_gva); + write_guest_global(vm, ucall_exit_mmio_addr, (gva_t *)mmio_gva); } void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu) @@ -25,9 +25,9 @@ void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu) if (run->exit_reason == KVM_EXIT_MMIO && run->mmio.phys_addr == vcpu->vm->ucall_mmio_addr) { - TEST_ASSERT(run->mmio.is_write && run->mmio.len == sizeof(uint64_t), + TEST_ASSERT(run->mmio.is_write && run->mmio.len == sizeof(u64), "Unexpected ucall exit mmio address access"); - return (void *)(*((uint64_t *)run->mmio.data)); + return (void *)(*((u64 *)run->mmio.data)); } return NULL; diff --git a/tools/testing/selftests/kvm/lib/arm64/vgic.c b/tools/testing/selftests/kvm/lib/arm64/vgic.c index d0f7bd0984b8..4ecebf3146a2 100644 --- a/tools/testing/selftests/kvm/lib/arm64/vgic.c +++ b/tools/testing/selftests/kvm/lib/arm64/vgic.c @@ -41,10 +41,10 @@ bool kvm_supports_vgic_v3(void) * redistributor regions of the guest. Since it depends on the number of * vCPUs for the VM, it must be called after all the vCPUs have been created. */ -int __vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs) +int __vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, u32 nr_irqs) { int gic_fd; - uint64_t attr; + u64 attr; unsigned int nr_gic_pages; /* Distributor setup */ @@ -77,7 +77,7 @@ void __vgic_v3_init(int fd) KVM_DEV_ARM_VGIC_CTRL_INIT, NULL); } -int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs) +int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, u32 nr_irqs) { unsigned int nr_vcpus_created = 0; struct list_head *iter; @@ -104,11 +104,11 @@ int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs) } /* should only work for level sensitive interrupts */ -int _kvm_irq_set_level_info(int gic_fd, uint32_t intid, int level) +int _kvm_irq_set_level_info(int gic_fd, u32 intid, int level) { - uint64_t attr = 32 * (intid / 32); - uint64_t index = intid % 32; - uint64_t val; + u64 attr = 32 * (intid / 32); + u64 index = intid % 32; + u64 val; int ret; ret = __kvm_device_attr_get(gic_fd, KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO, @@ -122,16 +122,16 @@ int _kvm_irq_set_level_info(int gic_fd, uint32_t intid, int level) return ret; } -void kvm_irq_set_level_info(int gic_fd, uint32_t intid, int level) +void kvm_irq_set_level_info(int gic_fd, u32 intid, int level) { int ret = _kvm_irq_set_level_info(gic_fd, intid, level); TEST_ASSERT(!ret, KVM_IOCTL_ERROR(KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO, ret)); } -int _kvm_arm_irq_line(struct kvm_vm *vm, uint32_t intid, int level) +int _kvm_arm_irq_line(struct kvm_vm *vm, u32 intid, int level) { - uint32_t irq = intid & KVM_ARM_IRQ_NUM_MASK; + u32 irq = intid & KVM_ARM_IRQ_NUM_MASK; TEST_ASSERT(!INTID_IS_SGI(intid), "KVM_IRQ_LINE's interface itself " "doesn't allow injecting SGIs. There's no mask for it."); @@ -144,23 +144,23 @@ int _kvm_arm_irq_line(struct kvm_vm *vm, uint32_t intid, int level) return _kvm_irq_line(vm, irq, level); } -void kvm_arm_irq_line(struct kvm_vm *vm, uint32_t intid, int level) +void kvm_arm_irq_line(struct kvm_vm *vm, u32 intid, int level) { int ret = _kvm_arm_irq_line(vm, intid, level); TEST_ASSERT(!ret, KVM_IOCTL_ERROR(KVM_IRQ_LINE, ret)); } -static void vgic_poke_irq(int gic_fd, uint32_t intid, struct kvm_vcpu *vcpu, - uint64_t reg_off) +static void vgic_poke_irq(int gic_fd, u32 intid, struct kvm_vcpu *vcpu, + u64 reg_off) { - uint64_t reg = intid / 32; - uint64_t index = intid % 32; - uint64_t attr = reg_off + reg * 4; - uint64_t val; + u64 reg = intid / 32; + u64 index = intid % 32; + u64 attr = reg_off + reg * 4; + u64 val; bool intid_is_private = INTID_IS_SGI(intid) || INTID_IS_PPI(intid); - uint32_t group = intid_is_private ? KVM_DEV_ARM_VGIC_GRP_REDIST_REGS + u32 group = intid_is_private ? KVM_DEV_ARM_VGIC_GRP_REDIST_REGS : KVM_DEV_ARM_VGIC_GRP_DIST_REGS; if (intid_is_private) { @@ -183,12 +183,12 @@ static void vgic_poke_irq(int gic_fd, uint32_t intid, struct kvm_vcpu *vcpu, kvm_device_attr_set(gic_fd, group, attr, &val); } -void kvm_irq_write_ispendr(int gic_fd, uint32_t intid, struct kvm_vcpu *vcpu) +void kvm_irq_write_ispendr(int gic_fd, u32 intid, struct kvm_vcpu *vcpu) { vgic_poke_irq(gic_fd, intid, vcpu, GICD_ISPENDR); } -void kvm_irq_write_isactiver(int gic_fd, uint32_t intid, struct kvm_vcpu *vcpu) +void kvm_irq_write_isactiver(int gic_fd, u32 intid, struct kvm_vcpu *vcpu) { vgic_poke_irq(gic_fd, intid, vcpu, GICD_ISACTIVER); } diff --git a/tools/testing/selftests/kvm/lib/elf.c b/tools/testing/selftests/kvm/lib/elf.c index f34d926d9735..b689c4df4a01 100644 --- a/tools/testing/selftests/kvm/lib/elf.c +++ b/tools/testing/selftests/kvm/lib/elf.c @@ -156,21 +156,20 @@ void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename) TEST_ASSERT(phdr.p_memsz > 0, "Unexpected loadable segment " "memsize of 0,\n" " phdr index: %u p_memsz: 0x%" PRIx64, - n1, (uint64_t) phdr.p_memsz); - vm_vaddr_t seg_vstart = align_down(phdr.p_vaddr, vm->page_size); - vm_vaddr_t seg_vend = phdr.p_vaddr + phdr.p_memsz - 1; + n1, (u64)phdr.p_memsz); + gva_t seg_vstart = align_down(phdr.p_vaddr, vm->page_size); + gva_t seg_vend = phdr.p_vaddr + phdr.p_memsz - 1; seg_vend |= vm->page_size - 1; size_t seg_size = seg_vend - seg_vstart + 1; - vm_vaddr_t vaddr = __vm_vaddr_alloc(vm, seg_size, seg_vstart, - MEM_REGION_CODE); - TEST_ASSERT(vaddr == seg_vstart, "Unable to allocate " + gva_t gva = __vm_alloc(vm, seg_size, seg_vstart, MEM_REGION_CODE); + TEST_ASSERT(gva == seg_vstart, "Unable to allocate " "virtual memory for segment at requested min addr,\n" " segment idx: %u\n" " seg_vstart: 0x%lx\n" - " vaddr: 0x%lx", - n1, seg_vstart, vaddr); - memset(addr_gva2hva(vm, vaddr), 0, seg_size); + " gva: 0x%lx", + n1, seg_vstart, gva); + memset(addr_gva2hva(vm, gva), 0, seg_size); /* TODO(lhuemill): Set permissions of each memory segment * based on the least-significant 3 bits of phdr.p_flags. */ diff --git a/tools/testing/selftests/kvm/lib/guest_modes.c b/tools/testing/selftests/kvm/lib/guest_modes.c index ce3099630397..7a96c43b5704 100644 --- a/tools/testing/selftests/kvm/lib/guest_modes.c +++ b/tools/testing/selftests/kvm/lib/guest_modes.c @@ -20,7 +20,7 @@ void guest_modes_append_default(void) #ifdef __aarch64__ { unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE); - uint32_t ipa4k, ipa16k, ipa64k; + u32 ipa4k, ipa16k, ipa64k; int i; aarch64_get_supported_page_sizes(limit, &ipa4k, &ipa16k, &ipa64k); diff --git a/tools/testing/selftests/kvm/lib/guest_sprintf.c b/tools/testing/selftests/kvm/lib/guest_sprintf.c index 74627514c4d4..7a33965349a7 100644 --- a/tools/testing/selftests/kvm/lib/guest_sprintf.c +++ b/tools/testing/selftests/kvm/lib/guest_sprintf.c @@ -35,8 +35,8 @@ static int skip_atoi(const char **s) ({ \ int __res; \ \ - __res = ((uint64_t) n) % (uint32_t) base; \ - n = ((uint64_t) n) / (uint32_t) base; \ + __res = ((u64)n) % (u32)base; \ + n = ((u64)n) / (u32)base; \ __res; \ }) @@ -119,7 +119,7 @@ int guest_vsnprintf(char *buf, int n, const char *fmt, va_list args) { char *str, *end; const char *s; - uint64_t num; + u64 num; int i, base; int len; @@ -216,7 +216,7 @@ repeat: while (--field_width > 0) APPEND_BUFFER_SAFE(str, end, ' '); APPEND_BUFFER_SAFE(str, end, - (uint8_t)va_arg(args, int)); + (u8)va_arg(args, int)); while (--field_width > 0) APPEND_BUFFER_SAFE(str, end, ' '); continue; @@ -240,7 +240,7 @@ repeat: flags |= SPECIAL | SMALL | ZEROPAD; } str = number(str, end, - (uint64_t)va_arg(args, void *), 16, + (u64)va_arg(args, void *), 16, field_width, precision, flags); continue; @@ -284,15 +284,15 @@ repeat: continue; } if (qualifier == 'l') - num = va_arg(args, uint64_t); + num = va_arg(args, u64); else if (qualifier == 'h') { - num = (uint16_t)va_arg(args, int); + num = (u16)va_arg(args, int); if (flags & SIGN) - num = (int16_t)num; + num = (s16)num; } else if (flags & SIGN) num = va_arg(args, int); else - num = va_arg(args, uint32_t); + num = va_arg(args, u32); str = number(str, end, num, base, field_width, precision, flags); } diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index f5e076591c64..2a76eca7029d 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -20,9 +20,9 @@ #define KVM_UTIL_MIN_PFN 2 -uint32_t guest_random_seed; +u32 guest_random_seed; struct guest_random_state guest_rng; -static uint32_t last_guest_seed; +static u32 last_guest_seed; static size_t vcpu_mmap_sz(void); @@ -165,7 +165,7 @@ unsigned int kvm_check_cap(long cap) return (unsigned int)ret; } -void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size) +void vm_enable_dirty_ring(struct kvm_vm *vm, u32 ring_size) { if (vm_check_cap(vm, KVM_CAP_DIRTY_LOG_RING_ACQ_REL)) vm_enable_cap(vm, KVM_CAP_DIRTY_LOG_RING_ACQ_REL, ring_size); @@ -189,7 +189,7 @@ static void vm_open(struct kvm_vm *vm) vm->stats.fd = -1; } -const char *vm_guest_mode_string(uint32_t i) +const char *vm_guest_mode_string(u32 i) { static const char * const strings[] = { [VM_MODE_P52V48_4K] = "PA-bits:52, VA-bits:48, 4K pages", @@ -267,7 +267,7 @@ _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) * based on the MSB of the VA. On architectures with this behavior * the VA region spans [0, 2^(va_bits - 1)), [-(2^(va_bits - 1), -1]. */ -__weak void vm_vaddr_populate_bitmap(struct kvm_vm *vm) +__weak void vm_populate_gva_bitmap(struct kvm_vm *vm) { sparsebit_set_num(vm->vpages_valid, 0, (1ULL << (vm->va_bits - 1)) >> vm->page_shift); @@ -385,7 +385,7 @@ struct kvm_vm *____vm_create(struct vm_shape shape) /* Limit to VA-bit canonical virtual addresses. */ vm->vpages_valid = sparsebit_alloc(); - vm_vaddr_populate_bitmap(vm); + vm_populate_gva_bitmap(vm); /* Limit physical addresses to PA-bits. */ vm->max_gfn = vm_compute_max_gfn(vm); @@ -396,12 +396,12 @@ struct kvm_vm *____vm_create(struct vm_shape shape) return vm; } -static uint64_t vm_nr_pages_required(enum vm_guest_mode mode, - uint32_t nr_runnable_vcpus, - uint64_t extra_mem_pages) +static u64 vm_nr_pages_required(enum vm_guest_mode mode, + u32 nr_runnable_vcpus, + u64 extra_mem_pages) { - uint64_t page_size = vm_guest_mode_params[mode].page_size; - uint64_t nr_pages; + u64 page_size = vm_guest_mode_params[mode].page_size; + u64 nr_pages; TEST_ASSERT(nr_runnable_vcpus, "Use vm_create_barebones() for VMs that _never_ have vCPUs"); @@ -435,7 +435,7 @@ static uint64_t vm_nr_pages_required(enum vm_guest_mode mode, return vm_adjust_num_guest_pages(mode, nr_pages); } -void kvm_set_files_rlimit(uint32_t nr_vcpus) +void kvm_set_files_rlimit(u32 nr_vcpus) { /* * Each vCPU will open two file descriptors: the vCPU itself and the @@ -476,10 +476,10 @@ static bool is_guest_memfd_required(struct vm_shape shape) #endif } -struct kvm_vm *__vm_create(struct vm_shape shape, uint32_t nr_runnable_vcpus, - uint64_t nr_extra_pages) +struct kvm_vm *__vm_create(struct vm_shape shape, u32 nr_runnable_vcpus, + u64 nr_extra_pages) { - uint64_t nr_pages = vm_nr_pages_required(shape.mode, nr_runnable_vcpus, + u64 nr_pages = vm_nr_pages_required(shape.mode, nr_runnable_vcpus, nr_extra_pages); struct userspace_mem_region *slot0; struct kvm_vm *vm; @@ -546,8 +546,8 @@ struct kvm_vm *__vm_create(struct vm_shape shape, uint32_t nr_runnable_vcpus, * extra_mem_pages is only used to calculate the maximum page table size, * no real memory allocation for non-slot0 memory in this function. */ -struct kvm_vm *__vm_create_with_vcpus(struct vm_shape shape, uint32_t nr_vcpus, - uint64_t extra_mem_pages, +struct kvm_vm *__vm_create_with_vcpus(struct vm_shape shape, u32 nr_vcpus, + u64 extra_mem_pages, void *guest_code, struct kvm_vcpu *vcpus[]) { struct kvm_vm *vm; @@ -566,7 +566,7 @@ struct kvm_vm *__vm_create_with_vcpus(struct vm_shape shape, uint32_t nr_vcpus, struct kvm_vm *__vm_create_shape_with_one_vcpu(struct vm_shape shape, struct kvm_vcpu **vcpu, - uint64_t extra_mem_pages, + u64 extra_mem_pages, void *guest_code) { struct kvm_vcpu *vcpus[1]; @@ -614,7 +614,7 @@ void kvm_vm_restart(struct kvm_vm *vmp) } __weak struct kvm_vcpu *vm_arch_vcpu_recreate(struct kvm_vm *vm, - uint32_t vcpu_id) + u32 vcpu_id) { return __vm_vcpu_add(vm, vcpu_id); } @@ -636,9 +636,9 @@ int __pin_task_to_cpu(pthread_t task, int cpu) return pthread_setaffinity_np(task, sizeof(cpuset), &cpuset); } -static uint32_t parse_pcpu(const char *cpu_str, const cpu_set_t *allowed_mask) +static u32 parse_pcpu(const char *cpu_str, const cpu_set_t *allowed_mask) { - uint32_t pcpu = atoi_non_negative("CPU number", cpu_str); + u32 pcpu = atoi_non_negative("CPU number", cpu_str); TEST_ASSERT(CPU_ISSET(pcpu, allowed_mask), "Not allowed to run on pCPU '%d', check cgroups?", pcpu); @@ -662,7 +662,7 @@ void kvm_print_vcpu_pinning_help(void) " (default: no pinning)\n", name, name); } -void kvm_parse_vcpu_pinning(const char *pcpus_string, uint32_t vcpu_to_pcpu[], +void kvm_parse_vcpu_pinning(const char *pcpus_string, u32 vcpu_to_pcpu[], int nr_vcpus) { cpu_set_t allowed_mask; @@ -715,15 +715,15 @@ void kvm_parse_vcpu_pinning(const char *pcpus_string, uint32_t vcpu_to_pcpu[], * region exists. */ static struct userspace_mem_region * -userspace_mem_region_find(struct kvm_vm *vm, uint64_t start, uint64_t end) +userspace_mem_region_find(struct kvm_vm *vm, u64 start, u64 end) { struct rb_node *node; for (node = vm->regions.gpa_tree.rb_node; node; ) { struct userspace_mem_region *region = container_of(node, struct userspace_mem_region, gpa_node); - uint64_t existing_start = region->region.guest_phys_addr; - uint64_t existing_end = region->region.guest_phys_addr + u64 existing_start = region->region.guest_phys_addr; + u64 existing_end = region->region.guest_phys_addr + region->region.memory_size - 1; if (start <= existing_end && end >= existing_start) return region; @@ -918,8 +918,8 @@ static void vm_userspace_mem_region_hva_insert(struct rb_root *hva_tree, } -int __vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags, - uint64_t gpa, uint64_t size, void *hva) +int __vm_set_user_memory_region(struct kvm_vm *vm, u32 slot, u32 flags, + gpa_t gpa, u64 size, void *hva) { struct kvm_userspace_memory_region region = { .slot = slot, @@ -932,8 +932,8 @@ int __vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags return ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, ®ion); } -void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags, - uint64_t gpa, uint64_t size, void *hva) +void vm_set_user_memory_region(struct kvm_vm *vm, u32 slot, u32 flags, + gpa_t gpa, u64 size, void *hva) { int ret = __vm_set_user_memory_region(vm, slot, flags, gpa, size, hva); @@ -945,9 +945,9 @@ void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags, __TEST_REQUIRE(kvm_has_cap(KVM_CAP_USER_MEMORY2), \ "KVM selftests now require KVM_SET_USER_MEMORY_REGION2 (introduced in v6.8)") -int __vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags, - uint64_t gpa, uint64_t size, void *hva, - uint32_t guest_memfd, uint64_t guest_memfd_offset) +int __vm_set_user_memory_region2(struct kvm_vm *vm, u32 slot, u32 flags, + gpa_t gpa, u64 size, void *hva, + u32 guest_memfd, u64 guest_memfd_offset) { struct kvm_userspace_memory_region2 region = { .slot = slot, @@ -964,9 +964,9 @@ int __vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flag return ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION2, ®ion); } -void vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags, - uint64_t gpa, uint64_t size, void *hva, - uint32_t guest_memfd, uint64_t guest_memfd_offset) +void vm_set_user_memory_region2(struct kvm_vm *vm, u32 slot, u32 flags, + gpa_t gpa, u64 size, void *hva, + u32 guest_memfd, u64 guest_memfd_offset) { int ret = __vm_set_user_memory_region2(vm, slot, flags, gpa, size, hva, guest_memfd, guest_memfd_offset); @@ -978,8 +978,8 @@ void vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags /* FIXME: This thing needs to be ripped apart and rewritten. */ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, - uint64_t gpa, uint32_t slot, uint64_t npages, uint32_t flags, - int guest_memfd, uint64_t guest_memfd_offset) + gpa_t gpa, u32 slot, u64 npages, u32 flags, + int guest_memfd, u64 guest_memfd_offset) { int ret; struct userspace_mem_region *region; @@ -1016,8 +1016,8 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, " requested gpa: 0x%lx npages: 0x%lx page_size: 0x%x\n" " existing gpa: 0x%lx size: 0x%lx", gpa, npages, vm->page_size, - (uint64_t) region->region.guest_phys_addr, - (uint64_t) region->region.memory_size); + (u64)region->region.guest_phys_addr, + (u64)region->region.memory_size); /* Confirm no region with the requested slot already exists. */ hash_for_each_possible(vm->regions.slot_hash, region, slot_node, @@ -1027,11 +1027,11 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, TEST_FAIL("A mem region with the requested slot " "already exists.\n" - " requested slot: %u paddr: 0x%lx npages: 0x%lx\n" - " existing slot: %u paddr: 0x%lx size: 0x%lx", + " requested slot: %u gpa: 0x%lx npages: 0x%lx\n" + " existing slot: %u gpa: 0x%lx size: 0x%lx", slot, gpa, npages, region->region.slot, - (uint64_t) region->region.guest_phys_addr, - (uint64_t) region->region.memory_size); + (u64)region->region.guest_phys_addr, + (u64)region->region.memory_size); } /* Allocate and initialize new mem region structure. */ @@ -1085,7 +1085,7 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, if (flags & KVM_MEM_GUEST_MEMFD) { if (guest_memfd < 0) { - uint32_t guest_memfd_flags = 0; + u32 guest_memfd_flags = 0; TEST_ASSERT(!guest_memfd_offset, "Offset must be zero when creating new guest_memfd"); guest_memfd = vm_create_guest_memfd(vm, mem_size, guest_memfd_flags); @@ -1141,8 +1141,7 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, void vm_userspace_mem_region_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, - uint64_t gpa, uint32_t slot, uint64_t npages, - uint32_t flags) + gpa_t gpa, u32 slot, u64 npages, u32 flags) { vm_mem_add(vm, src_type, gpa, slot, npages, flags, -1, 0); } @@ -1163,7 +1162,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, * memory slot ID). */ struct userspace_mem_region * -memslot2region(struct kvm_vm *vm, uint32_t memslot) +memslot2region(struct kvm_vm *vm, u32 memslot) { struct userspace_mem_region *region; @@ -1194,7 +1193,7 @@ memslot2region(struct kvm_vm *vm, uint32_t memslot) * Sets the flags of the memory region specified by the value of slot, * to the values given by flags. */ -void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags) +void vm_mem_region_set_flags(struct kvm_vm *vm, u32 slot, u32 flags) { int ret; struct userspace_mem_region *region; @@ -1210,7 +1209,7 @@ void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags) ret, errno, slot, flags); } -void vm_mem_region_reload(struct kvm_vm *vm, uint32_t slot) +void vm_mem_region_reload(struct kvm_vm *vm, u32 slot) { struct userspace_mem_region *region = memslot2region(vm, slot); struct kvm_userspace_memory_region2 tmp = region->region; @@ -1234,7 +1233,7 @@ void vm_mem_region_reload(struct kvm_vm *vm, uint32_t slot) * * Change the gpa of a memory region. */ -void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa) +void vm_mem_region_move(struct kvm_vm *vm, u32 slot, u64 new_gpa) { struct userspace_mem_region *region; int ret; @@ -1263,7 +1262,7 @@ void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa) * * Delete a memory region. */ -void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot) +void vm_mem_region_delete(struct kvm_vm *vm, u32 slot) { struct userspace_mem_region *region = memslot2region(vm, slot); @@ -1273,18 +1272,18 @@ void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot) __vm_mem_region_delete(vm, region); } -void vm_guest_mem_fallocate(struct kvm_vm *vm, uint64_t base, uint64_t size, +void vm_guest_mem_fallocate(struct kvm_vm *vm, u64 base, u64 size, bool punch_hole) { const int mode = FALLOC_FL_KEEP_SIZE | (punch_hole ? FALLOC_FL_PUNCH_HOLE : 0); struct userspace_mem_region *region; - uint64_t end = base + size; - uint64_t gpa, len; + u64 end = base + size; + gpa_t gpa, len; off_t fd_offset; int ret; for (gpa = base; gpa < end; gpa += len) { - uint64_t offset; + u64 offset; region = userspace_mem_region_find(vm, gpa, gpa); TEST_ASSERT(region && region->region.flags & KVM_MEM_GUEST_MEMFD, @@ -1292,7 +1291,7 @@ void vm_guest_mem_fallocate(struct kvm_vm *vm, uint64_t base, uint64_t size, offset = gpa - region->region.guest_phys_addr; fd_offset = region->region.guest_memfd_offset + offset; - len = min_t(uint64_t, end - gpa, region->region.memory_size - offset); + len = min_t(u64, end - gpa, region->region.memory_size - offset); ret = fallocate(region->region.guest_memfd, mode, fd_offset, len); TEST_ASSERT(!ret, "fallocate() failed to %s at %lx (len = %lu), fd = %d, mode = %x, offset = %lx", @@ -1317,7 +1316,7 @@ static size_t vcpu_mmap_sz(void) return ret; } -static bool vcpu_exists(struct kvm_vm *vm, uint32_t vcpu_id) +static bool vcpu_exists(struct kvm_vm *vm, u32 vcpu_id) { struct kvm_vcpu *vcpu; @@ -1333,7 +1332,7 @@ static bool vcpu_exists(struct kvm_vm *vm, uint32_t vcpu_id) * Adds a virtual CPU to the VM specified by vm with the ID given by vcpu_id. * No additional vCPU setup is done. Returns the vCPU. */ -struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id) +struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, u32 vcpu_id) { struct kvm_vcpu *vcpu; @@ -1367,33 +1366,18 @@ struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id) } /* - * VM Virtual Address Unused Gap - * - * Input Args: - * vm - Virtual Machine - * sz - Size (bytes) - * vaddr_min - Minimum Virtual Address - * - * Output Args: None - * - * Return: - * Lowest virtual address at or above vaddr_min, with at least - * sz unused bytes. TEST_ASSERT failure if no area of at least - * size sz is available. - * - * Within the VM specified by vm, locates the lowest starting virtual - * address >= vaddr_min, that has at least sz unallocated bytes. A + * Within the VM specified by @vm, locates the lowest starting guest virtual + * address >= @min_gva, that has at least @sz unallocated bytes. A * TEST_ASSERT failure occurs for invalid input or no area of at least - * sz unallocated bytes >= vaddr_min is available. + * @sz unallocated bytes >= @min_gva is available. */ -vm_vaddr_t vm_vaddr_unused_gap(struct kvm_vm *vm, size_t sz, - vm_vaddr_t vaddr_min) +gva_t vm_unused_gva_gap(struct kvm_vm *vm, size_t sz, gva_t min_gva) { - uint64_t pages = (sz + vm->page_size - 1) >> vm->page_shift; + u64 pages = (sz + vm->page_size - 1) >> vm->page_shift; /* Determine lowest permitted virtual page index. */ - uint64_t pgidx_start = (vaddr_min + vm->page_size - 1) >> vm->page_shift; - if ((pgidx_start * vm->page_size) < vaddr_min) + u64 pgidx_start = (min_gva + vm->page_size - 1) >> vm->page_shift; + if ((pgidx_start * vm->page_size) < min_gva) goto no_va_found; /* Loop over section with enough valid virtual page indexes. */ @@ -1430,7 +1414,7 @@ vm_vaddr_t vm_vaddr_unused_gap(struct kvm_vm *vm, size_t sz, } while (pgidx_start != 0); no_va_found: - TEST_FAIL("No vaddr of specified pages available, pages: 0x%lx", pages); + TEST_FAIL("No gva of specified pages available, pages: 0x%lx", pages); /* NOT REACHED */ return -1; @@ -1452,145 +1436,91 @@ va_found: return pgidx_start * vm->page_size; } -static vm_vaddr_t ____vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, - vm_vaddr_t vaddr_min, - enum kvm_mem_region_type type, - bool protected) +static gva_t ____vm_alloc(struct kvm_vm *vm, size_t sz, gva_t min_gva, + enum kvm_mem_region_type type, bool protected) { - uint64_t pages = (sz >> vm->page_shift) + ((sz % vm->page_size) != 0); + u64 pages = (sz >> vm->page_shift) + ((sz % vm->page_size) != 0); virt_pgd_alloc(vm); - vm_paddr_t paddr = __vm_phy_pages_alloc(vm, pages, - KVM_UTIL_MIN_PFN * vm->page_size, - vm->memslots[type], protected); + gpa_t gpa = __vm_phy_pages_alloc(vm, pages, + KVM_UTIL_MIN_PFN * vm->page_size, + vm->memslots[type], protected); /* * Find an unused range of virtual page addresses of at least * pages in length. */ - vm_vaddr_t vaddr_start = vm_vaddr_unused_gap(vm, sz, vaddr_min); + gva_t gva_start = vm_unused_gva_gap(vm, sz, min_gva); /* Map the virtual pages. */ - for (vm_vaddr_t vaddr = vaddr_start; pages > 0; - pages--, vaddr += vm->page_size, paddr += vm->page_size) { + for (gva_t gva = gva_start; pages > 0; + pages--, gva += vm->page_size, gpa += vm->page_size) { - virt_pg_map(vm, vaddr, paddr); + virt_pg_map(vm, gva, gpa); } - return vaddr_start; + return gva_start; } -vm_vaddr_t __vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, - enum kvm_mem_region_type type) +gva_t __vm_alloc(struct kvm_vm *vm, size_t sz, gva_t min_gva, + enum kvm_mem_region_type type) { - return ____vm_vaddr_alloc(vm, sz, vaddr_min, type, - vm_arch_has_protected_memory(vm)); + return ____vm_alloc(vm, sz, min_gva, type, + vm_arch_has_protected_memory(vm)); } -vm_vaddr_t vm_vaddr_alloc_shared(struct kvm_vm *vm, size_t sz, - vm_vaddr_t vaddr_min, - enum kvm_mem_region_type type) +gva_t vm_alloc_shared(struct kvm_vm *vm, size_t sz, gva_t min_gva, + enum kvm_mem_region_type type) { - return ____vm_vaddr_alloc(vm, sz, vaddr_min, type, false); + return ____vm_alloc(vm, sz, min_gva, type, false); } /* - * VM Virtual Address Allocate - * - * Input Args: - * vm - Virtual Machine - * sz - Size in bytes - * vaddr_min - Minimum starting virtual address - * - * Output Args: None - * - * Return: - * Starting guest virtual address - * - * Allocates at least sz bytes within the virtual address space of the vm - * given by vm. The allocated bytes are mapped to a virtual address >= - * the address given by vaddr_min. Note that each allocation uses a - * a unique set of pages, with the minimum real allocation being at least - * a page. The allocated physical space comes from the TEST_DATA memory region. + * Allocates at least sz bytes within the virtual address space of the VM + * given by @vm. The allocated bytes are mapped to a virtual address >= the + * address given by @min_gva. Note that each allocation uses a a unique set + * of pages, with the minimum real allocation being at least a page. The + * allocated physical space comes from the TEST_DATA memory region. */ -vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min) +gva_t vm_alloc(struct kvm_vm *vm, size_t sz, gva_t min_gva) { - return __vm_vaddr_alloc(vm, sz, vaddr_min, MEM_REGION_TEST_DATA); + return __vm_alloc(vm, sz, min_gva, MEM_REGION_TEST_DATA); } -/* - * VM Virtual Address Allocate Pages - * - * Input Args: - * vm - Virtual Machine - * - * Output Args: None - * - * Return: - * Starting guest virtual address - * - * Allocates at least N system pages worth of bytes within the virtual address - * space of the vm. - */ -vm_vaddr_t vm_vaddr_alloc_pages(struct kvm_vm *vm, int nr_pages) +gva_t vm_alloc_pages(struct kvm_vm *vm, int nr_pages) { - return vm_vaddr_alloc(vm, nr_pages * getpagesize(), KVM_UTIL_MIN_VADDR); + return vm_alloc(vm, nr_pages * getpagesize(), KVM_UTIL_MIN_VADDR); } -vm_vaddr_t __vm_vaddr_alloc_page(struct kvm_vm *vm, enum kvm_mem_region_type type) +gva_t __vm_alloc_page(struct kvm_vm *vm, enum kvm_mem_region_type type) { - return __vm_vaddr_alloc(vm, getpagesize(), KVM_UTIL_MIN_VADDR, type); + return __vm_alloc(vm, getpagesize(), KVM_UTIL_MIN_VADDR, type); } -/* - * VM Virtual Address Allocate Page - * - * Input Args: - * vm - Virtual Machine - * - * Output Args: None - * - * Return: - * Starting guest virtual address - * - * Allocates at least one system page worth of bytes within the virtual address - * space of the vm. - */ -vm_vaddr_t vm_vaddr_alloc_page(struct kvm_vm *vm) +gva_t vm_alloc_page(struct kvm_vm *vm) { - return vm_vaddr_alloc_pages(vm, 1); + return vm_alloc_pages(vm, 1); } /* - * Map a range of VM virtual address to the VM's physical address - * - * Input Args: - * vm - Virtual Machine - * vaddr - Virtuall address to map - * paddr - VM Physical Address - * npages - The number of pages to map + * Map a range of VM virtual address to the VM's physical address. * - * Output Args: None - * - * Return: None - * - * Within the VM given by @vm, creates a virtual translation for - * @npages starting at @vaddr to the page range starting at @paddr. + * Within the VM given by @vm, creates a virtual translation for @npages + * starting at @gva to the page range starting at @gpa. */ -void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, - unsigned int npages) +void virt_map(struct kvm_vm *vm, gva_t gva, gpa_t gpa, unsigned int npages) { size_t page_size = vm->page_size; size_t size = npages * page_size; - TEST_ASSERT(vaddr + size > vaddr, "Vaddr overflow"); - TEST_ASSERT(paddr + size > paddr, "Paddr overflow"); + TEST_ASSERT(gva + size > gva, "Vaddr overflow"); + TEST_ASSERT(gpa + size > gpa, "Paddr overflow"); while (npages--) { - virt_pg_map(vm, vaddr, paddr); + virt_pg_map(vm, gva, gpa); - vaddr += page_size; - paddr += page_size; + gva += page_size; + gpa += page_size; } } @@ -1611,7 +1541,7 @@ void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, * address providing the memory to the vm physical address is returned. * A TEST_ASSERT failure occurs if no region containing gpa exists. */ -void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa) +void *addr_gpa2hva(struct kvm_vm *vm, gpa_t gpa) { struct userspace_mem_region *region; @@ -1644,7 +1574,7 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa) * VM physical address is returned. A TEST_ASSERT failure occurs if no * region containing hva exists. */ -vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva) +gpa_t addr_hva2gpa(struct kvm_vm *vm, void *hva) { struct rb_node *node; @@ -1655,7 +1585,7 @@ vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva) if (hva >= region->host_mem) { if (hva <= (region->host_mem + region->region.memory_size - 1)) - return (vm_paddr_t)((uintptr_t) + return (gpa_t)((uintptr_t) region->region.guest_phys_addr + (hva - (uintptr_t)region->host_mem)); @@ -1687,7 +1617,7 @@ vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva) * memory without mapping said memory in the guest's address space. And, for * userfaultfd-based demand paging, to do so without triggering userfaults. */ -void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa) +void *addr_gpa2alias(struct kvm_vm *vm, gpa_t gpa) { struct userspace_mem_region *region; uintptr_t offset; @@ -1781,8 +1711,8 @@ struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vcpu *vcpu) void *vcpu_map_dirty_ring(struct kvm_vcpu *vcpu) { - uint32_t page_size = getpagesize(); - uint32_t size = vcpu->vm->dirty_ring_size; + u32 page_size = getpagesize(); + u32 size = vcpu->vm->dirty_ring_size; TEST_ASSERT(size > 0, "Should enable dirty ring first"); @@ -1811,7 +1741,7 @@ void *vcpu_map_dirty_ring(struct kvm_vcpu *vcpu) * Device Ioctl */ -int __kvm_has_device_attr(int dev_fd, uint32_t group, uint64_t attr) +int __kvm_has_device_attr(int dev_fd, u32 group, u64 attr) { struct kvm_device_attr attribute = { .group = group, @@ -1822,7 +1752,7 @@ int __kvm_has_device_attr(int dev_fd, uint32_t group, uint64_t attr) return ioctl(dev_fd, KVM_HAS_DEVICE_ATTR, &attribute); } -int __kvm_test_create_device(struct kvm_vm *vm, uint64_t type) +int __kvm_test_create_device(struct kvm_vm *vm, u64 type) { struct kvm_create_device create_dev = { .type = type, @@ -1832,7 +1762,7 @@ int __kvm_test_create_device(struct kvm_vm *vm, uint64_t type) return __vm_ioctl(vm, KVM_CREATE_DEVICE, &create_dev); } -int __kvm_create_device(struct kvm_vm *vm, uint64_t type) +int __kvm_create_device(struct kvm_vm *vm, u64 type) { struct kvm_create_device create_dev = { .type = type, @@ -1846,7 +1776,7 @@ int __kvm_create_device(struct kvm_vm *vm, uint64_t type) return err ? : create_dev.fd; } -int __kvm_device_attr_get(int dev_fd, uint32_t group, uint64_t attr, void *val) +int __kvm_device_attr_get(int dev_fd, u32 group, u64 attr, void *val) { struct kvm_device_attr kvmattr = { .group = group, @@ -1858,7 +1788,7 @@ int __kvm_device_attr_get(int dev_fd, uint32_t group, uint64_t attr, void *val) return __kvm_ioctl(dev_fd, KVM_GET_DEVICE_ATTR, &kvmattr); } -int __kvm_device_attr_set(int dev_fd, uint32_t group, uint64_t attr, void *val) +int __kvm_device_attr_set(int dev_fd, u32 group, u64 attr, void *val) { struct kvm_device_attr kvmattr = { .group = group, @@ -1874,7 +1804,7 @@ int __kvm_device_attr_set(int dev_fd, uint32_t group, uint64_t attr, void *val) * IRQ related functions. */ -int _kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level) +int _kvm_irq_line(struct kvm_vm *vm, u32 irq, int level) { struct kvm_irq_level irq_level = { .irq = irq, @@ -1884,7 +1814,7 @@ int _kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level) return __vm_ioctl(vm, KVM_IRQ_LINE, &irq_level); } -void kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level) +void kvm_irq_line(struct kvm_vm *vm, u32 irq, int level) { int ret = _kvm_irq_line(vm, irq, level); @@ -1906,7 +1836,7 @@ struct kvm_irq_routing *kvm_gsi_routing_create(void) } void kvm_gsi_routing_irqchip_add(struct kvm_irq_routing *routing, - uint32_t gsi, uint32_t pin) + u32 gsi, u32 pin) { int i; @@ -1956,7 +1886,7 @@ void kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing) * Dumps the current state of the VM given by vm, to the FILE stream * given by stream. */ -void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) +void vm_dump(FILE *stream, struct kvm_vm *vm, u8 indent) { int ctr; struct userspace_mem_region *region; @@ -1969,8 +1899,8 @@ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) hash_for_each(vm->regions.slot_hash, ctr, region, slot_node) { fprintf(stream, "%*sguest_phys: 0x%lx size: 0x%lx " "host_virt: %p\n", indent + 2, "", - (uint64_t) region->region.guest_phys_addr, - (uint64_t) region->region.memory_size, + (u64)region->region.guest_phys_addr, + (u64)region->region.memory_size, region->host_mem); fprintf(stream, "%*sunused_phy_pages: ", indent + 2, ""); sparsebit_dump(stream, region->unused_phy_pages, 0); @@ -2077,7 +2007,7 @@ const char *exit_reason_str(unsigned int exit_reason) * Input Args: * vm - Virtual Machine * num - number of pages - * paddr_min - Physical address minimum + * min_gpa - Physical address minimum * memslot - Memory region to allocate page from * protected - True if the pages will be used as protected/private memory * @@ -2087,29 +2017,29 @@ const char *exit_reason_str(unsigned int exit_reason) * Starting physical address * * Within the VM specified by vm, locates a range of available physical - * pages at or above paddr_min. If found, the pages are marked as in use + * pages at or above min_gpa. If found, the pages are marked as in use * and their base address is returned. A TEST_ASSERT failure occurs if - * not enough pages are available at or above paddr_min. + * not enough pages are available at or above min_gpa. */ -vm_paddr_t __vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, - vm_paddr_t paddr_min, uint32_t memslot, - bool protected) +gpa_t __vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, + gpa_t min_gpa, u32 memslot, + bool protected) { struct userspace_mem_region *region; sparsebit_idx_t pg, base; TEST_ASSERT(num > 0, "Must allocate at least one page"); - TEST_ASSERT((paddr_min % vm->page_size) == 0, "Min physical address " + TEST_ASSERT((min_gpa % vm->page_size) == 0, "Min physical address " "not divisible by page size.\n" - " paddr_min: 0x%lx page_size: 0x%x", - paddr_min, vm->page_size); + " min_gpa: 0x%lx page_size: 0x%x", + min_gpa, vm->page_size); region = memslot2region(vm, memslot); TEST_ASSERT(!protected || region->protected_phy_pages, "Region doesn't support protected memory"); - base = pg = paddr_min >> vm->page_shift; + base = pg = min_gpa >> vm->page_shift; do { for (; pg < base + num; ++pg) { if (!sparsebit_is_set(region->unused_phy_pages, pg)) { @@ -2121,8 +2051,8 @@ vm_paddr_t __vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, if (pg == 0) { fprintf(stderr, "No guest physical page available, " - "paddr_min: 0x%lx page_size: 0x%x memslot: %u\n", - paddr_min, vm->page_size, memslot); + "min_gpa: 0x%lx page_size: 0x%x memslot: %u\n", + min_gpa, vm->page_size, memslot); fputs("---- vm dump ----\n", stderr); vm_dump(stderr, vm, 2); abort(); @@ -2137,13 +2067,12 @@ vm_paddr_t __vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, return base * vm->page_size; } -vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min, - uint32_t memslot) +gpa_t vm_phy_page_alloc(struct kvm_vm *vm, gpa_t min_gpa, u32 memslot) { - return vm_phy_pages_alloc(vm, 1, paddr_min, memslot); + return vm_phy_pages_alloc(vm, 1, min_gpa, memslot); } -vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm) +gpa_t vm_alloc_page_table(struct kvm_vm *vm) { return vm_phy_page_alloc(vm, KVM_GUEST_PAGE_TABLE_MIN_PADDR, vm->memslots[MEM_REGION_PT]); @@ -2161,7 +2090,7 @@ vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm) * Return: * Equivalent host virtual address */ -void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva) +void *addr_gva2hva(struct kvm_vm *vm, gva_t gva) { return addr_gpa2hva(vm, addr_gva2gpa(vm, gva)); } @@ -2259,7 +2188,7 @@ struct kvm_stats_desc *read_stats_descriptors(int stats_fd, * Read the data values of a specified stat from the binary stats interface. */ void read_stat_data(int stats_fd, struct kvm_stats_header *header, - struct kvm_stats_desc *desc, uint64_t *data, + struct kvm_stats_desc *desc, u64 *data, size_t max_elements) { size_t nr_elements = min_t(ssize_t, desc->size, max_elements); @@ -2280,7 +2209,7 @@ void read_stat_data(int stats_fd, struct kvm_stats_header *header, } void kvm_get_stat(struct kvm_binary_stats *stats, const char *name, - uint64_t *data, size_t max_elements) + u64 *data, size_t max_elements) { struct kvm_stats_desc *desc; size_t size_desc; @@ -2357,7 +2286,7 @@ void __attribute((constructor)) kvm_selftest_init(void) kvm_selftest_arch_init(); } -bool vm_is_gpa_protected(struct kvm_vm *vm, vm_paddr_t paddr) +bool vm_is_gpa_protected(struct kvm_vm *vm, gpa_t gpa) { sparsebit_idx_t pg = 0; struct userspace_mem_region *region; @@ -2365,10 +2294,10 @@ bool vm_is_gpa_protected(struct kvm_vm *vm, vm_paddr_t paddr) if (!vm_arch_has_protected_memory(vm)) return false; - region = userspace_mem_region_find(vm, paddr, paddr); - TEST_ASSERT(region, "No vm physical memory at 0x%lx", paddr); + region = userspace_mem_region_find(vm, gpa, gpa); + TEST_ASSERT(region, "No vm physical memory at 0x%lx", gpa); - pg = paddr >> vm->page_shift; + pg = gpa >> vm->page_shift; return sparsebit_is_set(region->protected_phy_pages, pg); } diff --git a/tools/testing/selftests/kvm/lib/loongarch/processor.c b/tools/testing/selftests/kvm/lib/loongarch/processor.c index ee4ad3b1d2a4..64d91fb76522 100644 --- a/tools/testing/selftests/kvm/lib/loongarch/processor.c +++ b/tools/testing/selftests/kvm/lib/loongarch/processor.c @@ -12,32 +12,32 @@ #define LOONGARCH_PAGE_TABLE_PHYS_MIN 0x200000 #define LOONGARCH_GUEST_STACK_VADDR_MIN 0x200000 -static vm_paddr_t invalid_pgtable[4]; -static vm_vaddr_t exception_handlers; +static gpa_t invalid_pgtable[4]; +static gva_t exception_handlers; -static uint64_t virt_pte_index(struct kvm_vm *vm, vm_vaddr_t gva, int level) +static u64 virt_pte_index(struct kvm_vm *vm, gva_t gva, int level) { unsigned int shift; - uint64_t mask; + u64 mask; shift = level * (vm->page_shift - 3) + vm->page_shift; mask = (1UL << (vm->page_shift - 3)) - 1; return (gva >> shift) & mask; } -static uint64_t pte_addr(struct kvm_vm *vm, uint64_t entry) +static u64 pte_addr(struct kvm_vm *vm, u64 entry) { return entry & ~((0x1UL << vm->page_shift) - 1); } -static uint64_t ptrs_per_pte(struct kvm_vm *vm) +static u64 ptrs_per_pte(struct kvm_vm *vm) { return 1 << (vm->page_shift - 3); } -static void virt_set_pgtable(struct kvm_vm *vm, vm_paddr_t table, vm_paddr_t child) +static void virt_set_pgtable(struct kvm_vm *vm, gpa_t table, gpa_t child) { - uint64_t *ptep; + u64 *ptep; int i, ptrs_per_pte; ptep = addr_gpa2hva(vm, table); @@ -49,7 +49,7 @@ static void virt_set_pgtable(struct kvm_vm *vm, vm_paddr_t table, vm_paddr_t chi void virt_arch_pgd_alloc(struct kvm_vm *vm) { int i; - vm_paddr_t child, table; + gpa_t child, table; if (vm->mmu.pgd_created) return; @@ -67,16 +67,16 @@ void virt_arch_pgd_alloc(struct kvm_vm *vm) vm->mmu.pgd_created = true; } -static int virt_pte_none(uint64_t *ptep, int level) +static int virt_pte_none(u64 *ptep, int level) { return *ptep == invalid_pgtable[level]; } -static uint64_t *virt_populate_pte(struct kvm_vm *vm, vm_vaddr_t gva, int alloc) +static u64 *virt_populate_pte(struct kvm_vm *vm, gva_t gva, int alloc) { int level; - uint64_t *ptep; - vm_paddr_t child; + u64 *ptep; + gpa_t child; if (!vm->mmu.pgd_created) goto unmapped_gva; @@ -106,43 +106,42 @@ unmapped_gva: exit(EXIT_FAILURE); } -vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) +gpa_t addr_arch_gva2gpa(struct kvm_vm *vm, gva_t gva) { - uint64_t *ptep; + u64 *ptep; ptep = virt_populate_pte(vm, gva, 0); - TEST_ASSERT(*ptep != 0, "Virtual address vaddr: 0x%lx not mapped\n", gva); + TEST_ASSERT(*ptep != 0, "Virtual address gva: 0x%lx not mapped\n", gva); return pte_addr(vm, *ptep) + (gva & (vm->page_size - 1)); } -void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) +void virt_arch_pg_map(struct kvm_vm *vm, gva_t gva, gpa_t gpa) { - uint32_t prot_bits; - uint64_t *ptep; + u32 prot_bits; + u64 *ptep; - TEST_ASSERT((vaddr % vm->page_size) == 0, + TEST_ASSERT((gva % vm->page_size) == 0, "Virtual address not on page boundary,\n" - "vaddr: 0x%lx vm->page_size: 0x%x", vaddr, vm->page_size); - TEST_ASSERT(sparsebit_is_set(vm->vpages_valid, - (vaddr >> vm->page_shift)), - "Invalid virtual address, vaddr: 0x%lx", vaddr); - TEST_ASSERT((paddr % vm->page_size) == 0, + "gva: 0x%lx vm->page_size: 0x%x", gva, vm->page_size); + TEST_ASSERT(sparsebit_is_set(vm->vpages_valid, (gva >> vm->page_shift)), + "Invalid virtual address, gva: 0x%lx", gva); + TEST_ASSERT((gpa % vm->page_size) == 0, "Physical address not on page boundary,\n" - "paddr: 0x%lx vm->page_size: 0x%x", paddr, vm->page_size); - TEST_ASSERT((paddr >> vm->page_shift) <= vm->max_gfn, + "gpa: 0x%lx vm->page_size: 0x%x", gpa, vm->page_size); + TEST_ASSERT((gpa >> vm->page_shift) <= vm->max_gfn, "Physical address beyond maximum supported,\n" - "paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x", - paddr, vm->max_gfn, vm->page_size); + "gpa: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x", + gpa, vm->max_gfn, vm->page_size); - ptep = virt_populate_pte(vm, vaddr, 1); + ptep = virt_populate_pte(vm, gva, 1); prot_bits = _PAGE_PRESENT | __READABLE | __WRITEABLE | _CACHE_CC | _PAGE_USER; - WRITE_ONCE(*ptep, paddr | prot_bits); + WRITE_ONCE(*ptep, gpa | prot_bits); } -static void pte_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent, uint64_t page, int level) +static void pte_dump(FILE *stream, struct kvm_vm *vm, u8 indent, u64 page, int level) { - uint64_t pte, *ptep; + u64 pte, *ptep; static const char * const type[] = { "pte", "pmd", "pud", "pgd"}; if (level < 0) @@ -158,7 +157,7 @@ static void pte_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent, uint64_t p } } -void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) +void virt_arch_dump(FILE *stream, struct kvm_vm *vm, u8 indent) { int level; @@ -169,7 +168,7 @@ void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) pte_dump(stream, vm, indent, vm->mmu.pgd, level); } -void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, uint8_t indent) +void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, u8 indent) { } @@ -206,8 +205,9 @@ void vm_init_descriptor_tables(struct kvm_vm *vm) { void *addr; - vm->handlers = __vm_vaddr_alloc(vm, sizeof(struct handlers), - LOONGARCH_GUEST_STACK_VADDR_MIN, MEM_REGION_DATA); + vm->handlers = __vm_alloc(vm, sizeof(struct handlers), + LOONGARCH_GUEST_STACK_VADDR_MIN, + MEM_REGION_DATA); addr = addr_gva2hva(vm, vm->handlers); memset(addr, 0, vm->page_size); @@ -223,7 +223,7 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector, handler_fn hand handlers->exception_handlers[vector] = handler; } -uint32_t guest_get_vcpuid(void) +u32 guest_get_vcpuid(void) { return csr_read(LOONGARCH_CSR_CPUID); } @@ -241,36 +241,36 @@ void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...) va_start(ap, num); for (i = 0; i < num; i++) - regs.gpr[i + 4] = va_arg(ap, uint64_t); + regs.gpr[i + 4] = va_arg(ap, u64); va_end(ap); vcpu_regs_set(vcpu, ®s); } -static void loongarch_set_reg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t val) +static void loongarch_set_reg(struct kvm_vcpu *vcpu, u64 id, u64 val) { __vcpu_set_reg(vcpu, id, val); } -static void loongarch_set_cpucfg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t val) +static void loongarch_set_cpucfg(struct kvm_vcpu *vcpu, u64 id, u64 val) { - uint64_t cfgid; + u64 cfgid; cfgid = KVM_REG_LOONGARCH_CPUCFG | KVM_REG_SIZE_U64 | 8 * id; __vcpu_set_reg(vcpu, cfgid, val); } -static void loongarch_get_csr(struct kvm_vcpu *vcpu, uint64_t id, void *addr) +static void loongarch_get_csr(struct kvm_vcpu *vcpu, u64 id, void *addr) { - uint64_t csrid; + u64 csrid; csrid = KVM_REG_LOONGARCH_CSR | KVM_REG_SIZE_U64 | 8 * id; __vcpu_get_reg(vcpu, csrid, addr); } -static void loongarch_set_csr(struct kvm_vcpu *vcpu, uint64_t id, uint64_t val) +static void loongarch_set_csr(struct kvm_vcpu *vcpu, u64 id, u64 val) { - uint64_t csrid; + u64 csrid; csrid = KVM_REG_LOONGARCH_CSR | KVM_REG_SIZE_U64 | 8 * id; __vcpu_set_reg(vcpu, csrid, val); @@ -354,8 +354,8 @@ void loongarch_vcpu_setup(struct kvm_vcpu *vcpu) loongarch_set_csr(vcpu, LOONGARCH_CSR_STLBPGSIZE, PS_DEFAULT_SIZE); /* LOONGARCH_CSR_KS1 is used for exception stack */ - val = __vm_vaddr_alloc(vm, vm->page_size, - LOONGARCH_GUEST_STACK_VADDR_MIN, MEM_REGION_DATA); + val = __vm_alloc(vm, vm->page_size, LOONGARCH_GUEST_STACK_VADDR_MIN, + MEM_REGION_DATA); TEST_ASSERT(val != 0, "No memory for exception stack"); val = val + vm->page_size; loongarch_set_csr(vcpu, LOONGARCH_CSR_KS1, val); @@ -369,23 +369,23 @@ void loongarch_vcpu_setup(struct kvm_vcpu *vcpu) loongarch_set_csr(vcpu, LOONGARCH_CSR_TMID, vcpu->id); } -struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id) +struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, u32 vcpu_id) { size_t stack_size; - uint64_t stack_vaddr; + u64 stack_gva; struct kvm_regs regs; struct kvm_vcpu *vcpu; vcpu = __vm_vcpu_add(vm, vcpu_id); stack_size = vm->page_size; - stack_vaddr = __vm_vaddr_alloc(vm, stack_size, - LOONGARCH_GUEST_STACK_VADDR_MIN, MEM_REGION_DATA); - TEST_ASSERT(stack_vaddr != 0, "No memory for vm stack"); + stack_gva = __vm_alloc(vm, stack_size, + LOONGARCH_GUEST_STACK_VADDR_MIN, MEM_REGION_DATA); + TEST_ASSERT(stack_gva != 0, "No memory for vm stack"); loongarch_vcpu_setup(vcpu); /* Setup guest general purpose registers */ vcpu_regs_get(vcpu, ®s); - regs.gpr[3] = stack_vaddr + stack_size; + regs.gpr[3] = stack_gva + stack_size; vcpu_regs_set(vcpu, ®s); return vcpu; @@ -397,6 +397,6 @@ void vcpu_arch_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code) /* Setup guest PC register */ vcpu_regs_get(vcpu, ®s); - regs.pc = (uint64_t)guest_code; + regs.pc = (u64)guest_code; vcpu_regs_set(vcpu, ®s); } diff --git a/tools/testing/selftests/kvm/lib/loongarch/ucall.c b/tools/testing/selftests/kvm/lib/loongarch/ucall.c index fc6cbb50573f..cd49a3440ead 100644 --- a/tools/testing/selftests/kvm/lib/loongarch/ucall.c +++ b/tools/testing/selftests/kvm/lib/loongarch/ucall.c @@ -9,17 +9,17 @@ * ucall_exit_mmio_addr holds per-VM values (global data is duplicated by each * VM), it must not be accessed from host code. */ -vm_vaddr_t *ucall_exit_mmio_addr; +gva_t *ucall_exit_mmio_addr; -void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa) +void ucall_arch_init(struct kvm_vm *vm, gpa_t mmio_gpa) { - vm_vaddr_t mmio_gva = vm_vaddr_unused_gap(vm, vm->page_size, KVM_UTIL_MIN_VADDR); + gva_t mmio_gva = vm_unused_gva_gap(vm, vm->page_size, KVM_UTIL_MIN_VADDR); virt_map(vm, mmio_gva, mmio_gpa, 1); vm->ucall_mmio_addr = mmio_gpa; - write_guest_global(vm, ucall_exit_mmio_addr, (vm_vaddr_t *)mmio_gva); + write_guest_global(vm, ucall_exit_mmio_addr, (gva_t *)mmio_gva); } void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu) @@ -28,10 +28,10 @@ void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu) if (run->exit_reason == KVM_EXIT_MMIO && run->mmio.phys_addr == vcpu->vm->ucall_mmio_addr) { - TEST_ASSERT(run->mmio.is_write && run->mmio.len == sizeof(uint64_t), + TEST_ASSERT(run->mmio.is_write && run->mmio.len == sizeof(u64), "Unexpected ucall exit mmio address access"); - return (void *)(*((uint64_t *)run->mmio.data)); + return (void *)(*((u64 *)run->mmio.data)); } return NULL; diff --git a/tools/testing/selftests/kvm/lib/memstress.c b/tools/testing/selftests/kvm/lib/memstress.c index 1ea735d66e15..6dcd15910a06 100644 --- a/tools/testing/selftests/kvm/lib/memstress.c +++ b/tools/testing/selftests/kvm/lib/memstress.c @@ -16,7 +16,7 @@ struct memstress_args memstress_args; * Guest virtual memory offset of the testing memory slot. * Must not conflict with identity mapped test code. */ -static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM; +static u64 guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM; struct vcpu_thread { /* The index of the vCPU. */ @@ -44,15 +44,15 @@ static struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; * Continuously write to the first 8 bytes of each page in the * specified region. */ -void memstress_guest_code(uint32_t vcpu_idx) +void memstress_guest_code(u32 vcpu_idx) { struct memstress_args *args = &memstress_args; struct memstress_vcpu_args *vcpu_args = &args->vcpu_args[vcpu_idx]; struct guest_random_state rand_state; - uint64_t gva; - uint64_t pages; - uint64_t addr; - uint64_t page; + gva_t gva; + u64 pages; + u64 addr; + u64 page; int i; rand_state = new_guest_random_state(guest_random_seed + vcpu_idx); @@ -76,9 +76,9 @@ void memstress_guest_code(uint32_t vcpu_idx) addr = gva + (page * args->guest_page_size); if (__guest_random_bool(&rand_state, args->write_percent)) - *(uint64_t *)addr = 0x0123456789ABCDEF; + *(u64 *)addr = 0x0123456789ABCDEF; else - READ_ONCE(*(uint64_t *)addr); + READ_ONCE(*(u64 *)addr); } GUEST_SYNC(1); @@ -87,7 +87,7 @@ void memstress_guest_code(uint32_t vcpu_idx) void memstress_setup_vcpus(struct kvm_vm *vm, int nr_vcpus, struct kvm_vcpu *vcpus[], - uint64_t vcpu_memory_bytes, + u64 vcpu_memory_bytes, bool partition_vcpu_memory_access) { struct memstress_args *args = &memstress_args; @@ -122,15 +122,15 @@ void memstress_setup_vcpus(struct kvm_vm *vm, int nr_vcpus, } struct kvm_vm *memstress_create_vm(enum vm_guest_mode mode, int nr_vcpus, - uint64_t vcpu_memory_bytes, int slots, + u64 vcpu_memory_bytes, int slots, enum vm_mem_backing_src_type backing_src, bool partition_vcpu_memory_access) { struct memstress_args *args = &memstress_args; struct kvm_vm *vm; - uint64_t guest_num_pages, slot0_pages = 0; - uint64_t backing_src_pagesz = get_backing_src_pagesz(backing_src); - uint64_t region_end_gfn; + u64 guest_num_pages, slot0_pages = 0; + u64 backing_src_pagesz = get_backing_src_pagesz(backing_src); + u64 region_end_gfn; int i; pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode)); @@ -202,8 +202,8 @@ struct kvm_vm *memstress_create_vm(enum vm_guest_mode mode, int nr_vcpus, /* Add extra memory slots for testing */ for (i = 0; i < slots; i++) { - uint64_t region_pages = guest_num_pages / slots; - vm_paddr_t region_start = args->gpa + region_pages * args->guest_page_size * i; + u64 region_pages = guest_num_pages / slots; + gpa_t region_start = args->gpa + region_pages * args->guest_page_size * i; vm_userspace_mem_region_add(vm, backing_src, region_start, MEMSTRESS_MEM_SLOT_INDEX + i, @@ -232,7 +232,7 @@ void memstress_destroy_vm(struct kvm_vm *vm) kvm_vm_free(vm); } -void memstress_set_write_percent(struct kvm_vm *vm, uint32_t write_percent) +void memstress_set_write_percent(struct kvm_vm *vm, u32 write_percent) { memstress_args.write_percent = write_percent; sync_global_to_guest(vm, memstress_args.write_percent); @@ -244,7 +244,7 @@ void memstress_set_random_access(struct kvm_vm *vm, bool random_access) sync_global_to_guest(vm, memstress_args.random_access); } -uint64_t __weak memstress_nested_pages(int nr_vcpus) +u64 __weak memstress_nested_pages(int nr_vcpus) { return 0; } @@ -349,7 +349,7 @@ void memstress_get_dirty_log(struct kvm_vm *vm, unsigned long *bitmaps[], int sl } void memstress_clear_dirty_log(struct kvm_vm *vm, unsigned long *bitmaps[], - int slots, uint64_t pages_per_slot) + int slots, u64 pages_per_slot) { int i; @@ -360,7 +360,7 @@ void memstress_clear_dirty_log(struct kvm_vm *vm, unsigned long *bitmaps[], } } -unsigned long **memstress_alloc_bitmaps(int slots, uint64_t pages_per_slot) +unsigned long **memstress_alloc_bitmaps(int slots, u64 pages_per_slot) { unsigned long **bitmaps; int i; diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c index 067c6b2c15b0..ded5429f3448 100644 --- a/tools/testing/selftests/kvm/lib/riscv/processor.c +++ b/tools/testing/selftests/kvm/lib/riscv/processor.c @@ -15,9 +15,9 @@ #define DEFAULT_RISCV_GUEST_STACK_VADDR_MIN 0xac0000 -static vm_vaddr_t exception_handlers; +static gva_t exception_handlers; -bool __vcpu_has_ext(struct kvm_vcpu *vcpu, uint64_t ext) +bool __vcpu_has_ext(struct kvm_vcpu *vcpu, u64 ext) { unsigned long value = 0; int ret; @@ -27,32 +27,32 @@ bool __vcpu_has_ext(struct kvm_vcpu *vcpu, uint64_t ext) return !ret && !!value; } -static uint64_t pte_addr(struct kvm_vm *vm, uint64_t entry) +static u64 pte_addr(struct kvm_vm *vm, u64 entry) { return ((entry & PGTBL_PTE_ADDR_MASK) >> PGTBL_PTE_ADDR_SHIFT) << PGTBL_PAGE_SIZE_SHIFT; } -static uint64_t ptrs_per_pte(struct kvm_vm *vm) +static u64 ptrs_per_pte(struct kvm_vm *vm) { - return PGTBL_PAGE_SIZE / sizeof(uint64_t); + return PGTBL_PAGE_SIZE / sizeof(u64); } -static uint64_t pte_index_mask[] = { +static u64 pte_index_mask[] = { PGTBL_L0_INDEX_MASK, PGTBL_L1_INDEX_MASK, PGTBL_L2_INDEX_MASK, PGTBL_L3_INDEX_MASK, }; -static uint32_t pte_index_shift[] = { +static u32 pte_index_shift[] = { PGTBL_L0_INDEX_SHIFT, PGTBL_L1_INDEX_SHIFT, PGTBL_L2_INDEX_SHIFT, PGTBL_L3_INDEX_SHIFT, }; -static uint64_t pte_index(struct kvm_vm *vm, vm_vaddr_t gva, int level) +static u64 pte_index(struct kvm_vm *vm, gva_t gva, int level) { TEST_ASSERT(level > -1, "Negative page table level (%d) not possible", level); @@ -75,26 +75,25 @@ void virt_arch_pgd_alloc(struct kvm_vm *vm) vm->mmu.pgd_created = true; } -void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) +void virt_arch_pg_map(struct kvm_vm *vm, gva_t gva, gpa_t gpa) { - uint64_t *ptep, next_ppn; + u64 *ptep, next_ppn; int level = vm->mmu.pgtable_levels - 1; - TEST_ASSERT((vaddr % vm->page_size) == 0, + TEST_ASSERT((gva % vm->page_size) == 0, "Virtual address not on page boundary,\n" - " vaddr: 0x%lx vm->page_size: 0x%x", vaddr, vm->page_size); - TEST_ASSERT(sparsebit_is_set(vm->vpages_valid, - (vaddr >> vm->page_shift)), - "Invalid virtual address, vaddr: 0x%lx", vaddr); - TEST_ASSERT((paddr % vm->page_size) == 0, + " gva: 0x%lx vm->page_size: 0x%x", gva, vm->page_size); + TEST_ASSERT(sparsebit_is_set(vm->vpages_valid, (gva >> vm->page_shift)), + "Invalid virtual address, gva: 0x%lx", gva); + TEST_ASSERT((gpa % vm->page_size) == 0, "Physical address not on page boundary,\n" - " paddr: 0x%lx vm->page_size: 0x%x", paddr, vm->page_size); - TEST_ASSERT((paddr >> vm->page_shift) <= vm->max_gfn, + " gpa: 0x%lx vm->page_size: 0x%x", gpa, vm->page_size); + TEST_ASSERT((gpa >> vm->page_shift) <= vm->max_gfn, "Physical address beyond maximum supported,\n" - " paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x", - paddr, vm->max_gfn, vm->page_size); + " gpa: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x", + gpa, vm->max_gfn, vm->page_size); - ptep = addr_gpa2hva(vm, vm->mmu.pgd) + pte_index(vm, vaddr, level) * 8; + ptep = addr_gpa2hva(vm, vm->mmu.pgd) + pte_index(vm, gva, level) * 8; if (!*ptep) { next_ppn = vm_alloc_page_table(vm) >> PGTBL_PAGE_SIZE_SHIFT; *ptep = (next_ppn << PGTBL_PTE_ADDR_SHIFT) | @@ -104,7 +103,7 @@ void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) while (level > -1) { ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + - pte_index(vm, vaddr, level) * 8; + pte_index(vm, gva, level) * 8; if (!*ptep && level > 0) { next_ppn = vm_alloc_page_table(vm) >> PGTBL_PAGE_SIZE_SHIFT; @@ -114,14 +113,14 @@ void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) level--; } - paddr = paddr >> PGTBL_PAGE_SIZE_SHIFT; - *ptep = (paddr << PGTBL_PTE_ADDR_SHIFT) | + gpa = gpa >> PGTBL_PAGE_SIZE_SHIFT; + *ptep = (gpa << PGTBL_PTE_ADDR_SHIFT) | PGTBL_PTE_PERM_MASK | PGTBL_PTE_VALID_MASK; } -vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) +gpa_t addr_arch_gva2gpa(struct kvm_vm *vm, gva_t gva) { - uint64_t *ptep; + u64 *ptep; int level = vm->mmu.pgtable_levels - 1; if (!vm->mmu.pgd_created) @@ -148,12 +147,12 @@ unmapped_gva: exit(1); } -static void pte_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent, - uint64_t page, int level) +static void pte_dump(FILE *stream, struct kvm_vm *vm, u8 indent, + u64 page, int level) { #ifdef DEBUG static const char *const type[] = { "pte", "pmd", "pud", "p4d"}; - uint64_t pte, *ptep; + u64 pte, *ptep; if (level < 0) return; @@ -170,11 +169,11 @@ static void pte_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent, #endif } -void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) +void virt_arch_dump(FILE *stream, struct kvm_vm *vm, u8 indent) { struct kvm_mmu *mmu = &vm->mmu; int level = mmu->pgtable_levels - 1; - uint64_t pgd, *ptep; + u64 pgd, *ptep; if (!mmu->pgd_created) return; @@ -233,7 +232,7 @@ void riscv_vcpu_mmu_setup(struct kvm_vcpu *vcpu) vcpu_set_reg(vcpu, RISCV_GENERAL_CSR_REG(satp), satp); } -void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, uint8_t indent) +void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, u8 indent) { struct kvm_riscv_core core; @@ -311,20 +310,20 @@ void vcpu_arch_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code) vcpu_set_reg(vcpu, RISCV_CORE_REG(regs.pc), (unsigned long)guest_code); } -struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id) +struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, u32 vcpu_id) { int r; size_t stack_size; - unsigned long stack_vaddr; + unsigned long stack_gva; unsigned long current_gp = 0; struct kvm_mp_state mps; struct kvm_vcpu *vcpu; stack_size = vm->page_size == 4096 ? DEFAULT_STACK_PGS * vm->page_size : vm->page_size; - stack_vaddr = __vm_vaddr_alloc(vm, stack_size, - DEFAULT_RISCV_GUEST_STACK_VADDR_MIN, - MEM_REGION_DATA); + stack_gva = __vm_alloc(vm, stack_size, + DEFAULT_RISCV_GUEST_STACK_VADDR_MIN, + MEM_REGION_DATA); vcpu = __vm_vcpu_add(vm, vcpu_id); riscv_vcpu_mmu_setup(vcpu); @@ -344,7 +343,7 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id) vcpu_set_reg(vcpu, RISCV_CORE_REG(regs.gp), current_gp); /* Setup stack pointer and program counter of guest */ - vcpu_set_reg(vcpu, RISCV_CORE_REG(regs.sp), stack_vaddr + stack_size); + vcpu_set_reg(vcpu, RISCV_CORE_REG(regs.sp), stack_gva + stack_size); /* Setup sscratch for guest_get_vcpuid() */ vcpu_set_reg(vcpu, RISCV_GENERAL_CSR_REG(sscratch), vcpu_id); @@ -358,7 +357,7 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id) void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...) { va_list ap; - uint64_t id = RISCV_CORE_REG(regs.a0); + u64 id = RISCV_CORE_REG(regs.a0); int i; TEST_ASSERT(num >= 1 && num <= 8, "Unsupported number of args,\n" @@ -393,7 +392,7 @@ void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...) id = RISCV_CORE_REG(regs.a7); break; } - vcpu_set_reg(vcpu, id, va_arg(ap, uint64_t)); + vcpu_set_reg(vcpu, id, va_arg(ap, u64)); } va_end(ap); @@ -449,10 +448,10 @@ void vcpu_init_vector_tables(struct kvm_vcpu *vcpu) void vm_init_vector_tables(struct kvm_vm *vm) { - vm->handlers = __vm_vaddr_alloc(vm, sizeof(struct handlers), - vm->page_size, MEM_REGION_DATA); + vm->handlers = __vm_alloc(vm, sizeof(struct handlers), vm->page_size, + MEM_REGION_DATA); - *(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers; + *(gva_t *)addr_gva2hva(vm, (gva_t)(&exception_handlers)) = vm->handlers; } void vm_install_exception_handler(struct kvm_vm *vm, int vector, exception_handler_fn handler) @@ -470,7 +469,7 @@ void vm_install_interrupt_handler(struct kvm_vm *vm, exception_handler_fn handle handlers->exception_handlers[1][0] = handler; } -uint32_t guest_get_vcpuid(void) +u32 guest_get_vcpuid(void) { return csr_read(CSR_SSCRATCH); } @@ -544,10 +543,10 @@ void kvm_selftest_arch_init(void) unsigned long riscv64_get_satp_mode(void) { int kvm_fd, vm_fd, vcpu_fd, err; - uint64_t val; + u64 val; struct kvm_one_reg reg = { .id = RISCV_CONFIG_REG(satp_mode), - .addr = (uint64_t)&val, + .addr = (u64)&val, }; kvm_fd = open_kvm_dev_path_or_exit(); diff --git a/tools/testing/selftests/kvm/lib/s390/diag318_test_handler.c b/tools/testing/selftests/kvm/lib/s390/diag318_test_handler.c index 2c432fa164f1..f5480473f192 100644 --- a/tools/testing/selftests/kvm/lib/s390/diag318_test_handler.c +++ b/tools/testing/selftests/kvm/lib/s390/diag318_test_handler.c @@ -13,7 +13,7 @@ static void guest_code(void) { - uint64_t diag318_info = 0x12345678; + u64 diag318_info = 0x12345678; asm volatile ("diag %0,0,0x318\n" : : "d" (diag318_info)); } @@ -23,13 +23,13 @@ static void guest_code(void) * we create an ad-hoc VM here to handle the instruction then extract the * necessary data. It is up to the caller to decide what to do with that data. */ -static uint64_t diag318_handler(void) +static u64 diag318_handler(void) { struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct kvm_run *run; - uint64_t reg; - uint64_t diag318_info; + u64 reg; + u64 diag318_info; vm = vm_create_with_one_vcpu(&vcpu, guest_code); vcpu_run(vcpu); @@ -51,9 +51,9 @@ static uint64_t diag318_handler(void) return diag318_info; } -uint64_t get_diag318_info(void) +u64 get_diag318_info(void) { - static uint64_t diag318_info; + static u64 diag318_info; static bool printed_skip; /* diff --git a/tools/testing/selftests/kvm/lib/s390/facility.c b/tools/testing/selftests/kvm/lib/s390/facility.c index d540812d911a..9a778054f07f 100644 --- a/tools/testing/selftests/kvm/lib/s390/facility.c +++ b/tools/testing/selftests/kvm/lib/s390/facility.c @@ -10,5 +10,5 @@ #include "facility.h" -uint64_t stfl_doublewords[NB_STFL_DOUBLEWORDS]; +u64 stfl_doublewords[NB_STFL_DOUBLEWORDS]; bool stfle_flag; diff --git a/tools/testing/selftests/kvm/lib/s390/processor.c b/tools/testing/selftests/kvm/lib/s390/processor.c index 6a9a660413a7..a9adb3782b35 100644 --- a/tools/testing/selftests/kvm/lib/s390/processor.c +++ b/tools/testing/selftests/kvm/lib/s390/processor.c @@ -12,7 +12,7 @@ void virt_arch_pgd_alloc(struct kvm_vm *vm) { - vm_paddr_t paddr; + gpa_t gpa; TEST_ASSERT(vm->page_size == PAGE_SIZE, "Unsupported page size: 0x%x", vm->page_size); @@ -20,12 +20,12 @@ void virt_arch_pgd_alloc(struct kvm_vm *vm) if (vm->mmu.pgd_created) return; - paddr = vm_phy_pages_alloc(vm, PAGES_PER_REGION, + gpa = vm_phy_pages_alloc(vm, PAGES_PER_REGION, KVM_GUEST_PAGE_TABLE_MIN_PADDR, vm->memslots[MEM_REGION_PT]); - memset(addr_gpa2hva(vm, paddr), 0xff, PAGES_PER_REGION * vm->page_size); + memset(addr_gpa2hva(vm, gpa), 0xff, PAGES_PER_REGION * vm->page_size); - vm->mmu.pgd = paddr; + vm->mmu.pgd = gpa; vm->mmu.pgd_created = true; } @@ -34,9 +34,9 @@ void virt_arch_pgd_alloc(struct kvm_vm *vm) * a page table (ri == 4). Returns a suitable region/segment table entry * which points to the freshly allocated pages. */ -static uint64_t virt_alloc_region(struct kvm_vm *vm, int ri) +static u64 virt_alloc_region(struct kvm_vm *vm, int ri) { - uint64_t taddr; + u64 taddr; taddr = vm_phy_pages_alloc(vm, ri < 4 ? PAGES_PER_REGION : 1, KVM_GUEST_PAGE_TABLE_MIN_PADDR, 0); @@ -47,26 +47,24 @@ static uint64_t virt_alloc_region(struct kvm_vm *vm, int ri) | ((ri < 4 ? (PAGES_PER_REGION - 1) : 0) & REGION_ENTRY_LENGTH); } -void virt_arch_pg_map(struct kvm_vm *vm, uint64_t gva, uint64_t gpa) +void virt_arch_pg_map(struct kvm_vm *vm, gva_t gva, gpa_t gpa) { int ri, idx; - uint64_t *entry; + u64 *entry; TEST_ASSERT((gva % vm->page_size) == 0, - "Virtual address not on page boundary,\n" - " vaddr: 0x%lx vm->page_size: 0x%x", - gva, vm->page_size); - TEST_ASSERT(sparsebit_is_set(vm->vpages_valid, - (gva >> vm->page_shift)), - "Invalid virtual address, vaddr: 0x%lx", - gva); + "Virtual address not on page boundary,\n" + " gva: 0x%lx vm->page_size: 0x%x", + gva, vm->page_size); + TEST_ASSERT(sparsebit_is_set(vm->vpages_valid, (gva >> vm->page_shift)), + "Invalid virtual address, gva: 0x%lx", gva); TEST_ASSERT((gpa % vm->page_size) == 0, "Physical address not on page boundary,\n" - " paddr: 0x%lx vm->page_size: 0x%x", + " gpa: 0x%lx vm->page_size: 0x%x", gva, vm->page_size); TEST_ASSERT((gpa >> vm->page_shift) <= vm->max_gfn, "Physical address beyond beyond maximum supported,\n" - " paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x", + " gpa: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x", gva, vm->max_gfn, vm->page_size); /* Walk through region and segment tables */ @@ -86,10 +84,10 @@ void virt_arch_pg_map(struct kvm_vm *vm, uint64_t gva, uint64_t gpa) entry[idx] = gpa; } -vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) +gpa_t addr_arch_gva2gpa(struct kvm_vm *vm, gva_t gva) { int ri, idx; - uint64_t *entry; + u64 *entry; TEST_ASSERT(vm->page_size == PAGE_SIZE, "Unsupported page size: 0x%x", vm->page_size); @@ -111,10 +109,10 @@ vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) return (entry[idx] & ~0xffful) + (gva & 0xffful); } -static void virt_dump_ptes(FILE *stream, struct kvm_vm *vm, uint8_t indent, - uint64_t ptea_start) +static void virt_dump_ptes(FILE *stream, struct kvm_vm *vm, u8 indent, + u64 ptea_start) { - uint64_t *pte, ptea; + u64 *pte, ptea; for (ptea = ptea_start; ptea < ptea_start + 0x100 * 8; ptea += 8) { pte = addr_gpa2hva(vm, ptea); @@ -125,10 +123,10 @@ static void virt_dump_ptes(FILE *stream, struct kvm_vm *vm, uint8_t indent, } } -static void virt_dump_region(FILE *stream, struct kvm_vm *vm, uint8_t indent, - uint64_t reg_tab_addr) +static void virt_dump_region(FILE *stream, struct kvm_vm *vm, u8 indent, + u64 reg_tab_addr) { - uint64_t addr, *entry; + u64 addr, *entry; for (addr = reg_tab_addr; addr < reg_tab_addr + 0x400 * 8; addr += 8) { entry = addr_gpa2hva(vm, addr); @@ -147,7 +145,7 @@ static void virt_dump_region(FILE *stream, struct kvm_vm *vm, uint8_t indent, } } -void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) +void virt_arch_dump(FILE *stream, struct kvm_vm *vm, u8 indent) { if (!vm->mmu.pgd_created) return; @@ -160,10 +158,10 @@ void vcpu_arch_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code) vcpu->run->psw_addr = (uintptr_t)guest_code; } -struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id) +struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, u32 vcpu_id) { size_t stack_size = DEFAULT_STACK_PGS * getpagesize(); - uint64_t stack_vaddr; + u64 stack_gva; struct kvm_regs regs; struct kvm_sregs sregs; struct kvm_vcpu *vcpu; @@ -171,15 +169,14 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id) TEST_ASSERT(vm->page_size == PAGE_SIZE, "Unsupported page size: 0x%x", vm->page_size); - stack_vaddr = __vm_vaddr_alloc(vm, stack_size, - DEFAULT_GUEST_STACK_VADDR_MIN, - MEM_REGION_DATA); + stack_gva = __vm_alloc(vm, stack_size, DEFAULT_GUEST_STACK_VADDR_MIN, + MEM_REGION_DATA); vcpu = __vm_vcpu_add(vm, vcpu_id); /* Setup guest registers */ vcpu_regs_get(vcpu, ®s); - regs.gprs[15] = stack_vaddr + (DEFAULT_STACK_PGS * getpagesize()) - 160; + regs.gprs[15] = stack_gva + (DEFAULT_STACK_PGS * getpagesize()) - 160; vcpu_regs_set(vcpu, ®s); vcpu_sregs_get(vcpu, &sregs); @@ -206,13 +203,13 @@ void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...) vcpu_regs_get(vcpu, ®s); for (i = 0; i < num; i++) - regs.gprs[i + 2] = va_arg(ap, uint64_t); + regs.gprs[i + 2] = va_arg(ap, u64); vcpu_regs_set(vcpu, ®s); va_end(ap); } -void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, uint8_t indent) +void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, u8 indent) { fprintf(stream, "%*spstate: psw: 0x%.16llx:0x%.16llx\n", indent, "", vcpu->run->psw_mask, vcpu->run->psw_addr); diff --git a/tools/testing/selftests/kvm/lib/sparsebit.c b/tools/testing/selftests/kvm/lib/sparsebit.c index a99188f87a38..4d845000de15 100644 --- a/tools/testing/selftests/kvm/lib/sparsebit.c +++ b/tools/testing/selftests/kvm/lib/sparsebit.c @@ -76,11 +76,11 @@ * the use of a binary-search tree, where each node contains at least * the following members: * - * typedef uint64_t sparsebit_idx_t; - * typedef uint64_t sparsebit_num_t; + * typedef u64 sparsebit_idx_t; + * typedef u64 sparsebit_num_t; * * sparsebit_idx_t idx; - * uint32_t mask; + * u32 mask; * sparsebit_num_t num_after; * * The idx member contains the bit index of the first bit described by this @@ -162,7 +162,7 @@ #define DUMP_LINE_MAX 100 /* Does not include indent amount */ -typedef uint32_t mask_t; +typedef u32 mask_t; #define MASK_BITS (sizeof(mask_t) * CHAR_BIT) struct node { @@ -2056,9 +2056,9 @@ unsigned char get8(void) return ch; } -uint64_t get64(void) +u64 get64(void) { - uint64_t x; + u64 x; x = get8(); x = (x << 8) | get8(); @@ -2074,9 +2074,9 @@ int main(void) { s = sparsebit_alloc(); for (;;) { - uint8_t op = get8() & 0xf; - uint64_t first = get64(); - uint64_t last = get64(); + u8 op = get8() & 0xf; + u64 first = get64(); + u64 last = get64(); operate(op, first, last); } diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c index 8a1848586a85..bab1bd2b775b 100644 --- a/tools/testing/selftests/kvm/lib/test_util.c +++ b/tools/testing/selftests/kvm/lib/test_util.c @@ -30,15 +30,15 @@ void __attribute__((used)) expect_sigbus_handler(int signum) * Park-Miller LCG using standard constants. */ -struct guest_random_state new_guest_random_state(uint32_t seed) +struct guest_random_state new_guest_random_state(u32 seed) { struct guest_random_state s = {.seed = seed}; return s; } -uint32_t guest_random_u32(struct guest_random_state *state) +u32 guest_random_u32(struct guest_random_state *state) { - state->seed = (uint64_t)state->seed * 48271 % ((uint32_t)(1 << 31) - 1); + state->seed = (u64)state->seed * 48271 % ((u32)(1 << 31) - 1); return state->seed; } @@ -83,12 +83,12 @@ size_t parse_size(const char *size) return base << shift; } -int64_t timespec_to_ns(struct timespec ts) +s64 timespec_to_ns(struct timespec ts) { - return (int64_t)ts.tv_nsec + 1000000000LL * (int64_t)ts.tv_sec; + return (s64)ts.tv_nsec + 1000000000LL * (s64)ts.tv_sec; } -struct timespec timespec_add_ns(struct timespec ts, int64_t ns) +struct timespec timespec_add_ns(struct timespec ts, s64 ns) { struct timespec res; @@ -101,15 +101,15 @@ struct timespec timespec_add_ns(struct timespec ts, int64_t ns) struct timespec timespec_add(struct timespec ts1, struct timespec ts2) { - int64_t ns1 = timespec_to_ns(ts1); - int64_t ns2 = timespec_to_ns(ts2); + s64 ns1 = timespec_to_ns(ts1); + s64 ns2 = timespec_to_ns(ts2); return timespec_add_ns((struct timespec){0}, ns1 + ns2); } struct timespec timespec_sub(struct timespec ts1, struct timespec ts2) { - int64_t ns1 = timespec_to_ns(ts1); - int64_t ns2 = timespec_to_ns(ts2); + s64 ns1 = timespec_to_ns(ts1); + s64 ns2 = timespec_to_ns(ts2); return timespec_add_ns((struct timespec){0}, ns1 - ns2); } @@ -123,7 +123,7 @@ struct timespec timespec_elapsed(struct timespec start) struct timespec timespec_div(struct timespec ts, int divisor) { - int64_t ns = timespec_to_ns(ts) / divisor; + s64 ns = timespec_to_ns(ts) / divisor; return timespec_add_ns((struct timespec){0}, ns); } @@ -225,7 +225,7 @@ size_t get_def_hugetlb_pagesz(void) #define ANON_FLAGS (MAP_PRIVATE | MAP_ANONYMOUS) #define ANON_HUGE_FLAGS (ANON_FLAGS | MAP_HUGETLB) -const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i) +const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(u32 i) { static const struct vm_mem_backing_src_alias aliases[] = { [VM_MEM_SRC_ANONYMOUS] = { @@ -317,9 +317,9 @@ const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i) #define MAP_HUGE_PAGE_SIZE(x) (1ULL << ((x >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK)) -size_t get_backing_src_pagesz(uint32_t i) +size_t get_backing_src_pagesz(u32 i) { - uint32_t flag = vm_mem_backing_src_alias(i)->flag; + u32 flag = vm_mem_backing_src_alias(i)->flag; switch (i) { case VM_MEM_SRC_ANONYMOUS: @@ -335,7 +335,7 @@ size_t get_backing_src_pagesz(uint32_t i) } } -bool is_backing_src_hugetlb(uint32_t i) +bool is_backing_src_hugetlb(u32 i) { return !!(vm_mem_backing_src_alias(i)->flag & MAP_HUGETLB); } diff --git a/tools/testing/selftests/kvm/lib/ucall_common.c b/tools/testing/selftests/kvm/lib/ucall_common.c index 42151e571953..029ce21f9f2f 100644 --- a/tools/testing/selftests/kvm/lib/ucall_common.c +++ b/tools/testing/selftests/kvm/lib/ucall_common.c @@ -14,7 +14,7 @@ struct ucall_header { struct ucall ucalls[KVM_MAX_VCPUS]; }; -int ucall_nr_pages_required(uint64_t page_size) +int ucall_nr_pages_required(u64 page_size) { return align_up(sizeof(struct ucall_header), page_size) / page_size; } @@ -25,16 +25,16 @@ int ucall_nr_pages_required(uint64_t page_size) */ static struct ucall_header *ucall_pool; -void ucall_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa) +void ucall_init(struct kvm_vm *vm, gpa_t mmio_gpa) { struct ucall_header *hdr; struct ucall *uc; - vm_vaddr_t vaddr; + gva_t gva; int i; - vaddr = vm_vaddr_alloc_shared(vm, sizeof(*hdr), KVM_UTIL_MIN_VADDR, - MEM_REGION_DATA); - hdr = (struct ucall_header *)addr_gva2hva(vm, vaddr); + gva = vm_alloc_shared(vm, sizeof(*hdr), KVM_UTIL_MIN_VADDR, + MEM_REGION_DATA); + hdr = (struct ucall_header *)addr_gva2hva(vm, gva); memset(hdr, 0, sizeof(*hdr)); for (i = 0; i < KVM_MAX_VCPUS; ++i) { @@ -42,7 +42,7 @@ void ucall_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa) uc->hva = uc; } - write_guest_global(vm, ucall_pool, (struct ucall_header *)vaddr); + write_guest_global(vm, ucall_pool, (struct ucall_header *)gva); ucall_arch_init(vm, mmio_gpa); } @@ -79,7 +79,7 @@ static void ucall_free(struct ucall *uc) clear_bit(uc - ucall_pool->ucalls, ucall_pool->in_use); } -void ucall_assert(uint64_t cmd, const char *exp, const char *file, +void ucall_assert(u64 cmd, const char *exp, const char *file, unsigned int line, const char *fmt, ...) { struct ucall *uc; @@ -88,20 +88,20 @@ void ucall_assert(uint64_t cmd, const char *exp, const char *file, uc = ucall_alloc(); uc->cmd = cmd; - WRITE_ONCE(uc->args[GUEST_ERROR_STRING], (uint64_t)(exp)); - WRITE_ONCE(uc->args[GUEST_FILE], (uint64_t)(file)); + WRITE_ONCE(uc->args[GUEST_ERROR_STRING], (u64)(exp)); + WRITE_ONCE(uc->args[GUEST_FILE], (u64)(file)); WRITE_ONCE(uc->args[GUEST_LINE], line); va_start(va, fmt); guest_vsnprintf(uc->buffer, UCALL_BUFFER_LEN, fmt, va); va_end(va); - ucall_arch_do_ucall((vm_vaddr_t)uc->hva); + ucall_arch_do_ucall((gva_t)uc->hva); ucall_free(uc); } -void ucall_fmt(uint64_t cmd, const char *fmt, ...) +void ucall_fmt(u64 cmd, const char *fmt, ...) { struct ucall *uc; va_list va; @@ -113,12 +113,12 @@ void ucall_fmt(uint64_t cmd, const char *fmt, ...) guest_vsnprintf(uc->buffer, UCALL_BUFFER_LEN, fmt, va); va_end(va); - ucall_arch_do_ucall((vm_vaddr_t)uc->hva); + ucall_arch_do_ucall((gva_t)uc->hva); ucall_free(uc); } -void ucall(uint64_t cmd, int nargs, ...) +void ucall(u64 cmd, int nargs, ...) { struct ucall *uc; va_list va; @@ -132,15 +132,15 @@ void ucall(uint64_t cmd, int nargs, ...) va_start(va, nargs); for (i = 0; i < nargs; ++i) - WRITE_ONCE(uc->args[i], va_arg(va, uint64_t)); + WRITE_ONCE(uc->args[i], va_arg(va, u64)); va_end(va); - ucall_arch_do_ucall((vm_vaddr_t)uc->hva); + ucall_arch_do_ucall((gva_t)uc->hva); ucall_free(uc); } -uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc) +u64 get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc) { struct ucall ucall; void *addr; diff --git a/tools/testing/selftests/kvm/lib/userfaultfd_util.c b/tools/testing/selftests/kvm/lib/userfaultfd_util.c index 5bde176cedd5..ef8d76f71f83 100644 --- a/tools/testing/selftests/kvm/lib/userfaultfd_util.c +++ b/tools/testing/selftests/kvm/lib/userfaultfd_util.c @@ -27,7 +27,7 @@ static void *uffd_handler_thread_fn(void *arg) { struct uffd_reader_args *reader_args = (struct uffd_reader_args *)arg; int uffd = reader_args->uffd; - int64_t pages = 0; + s64 pages = 0; struct timespec start; struct timespec ts_diff; struct epoll_event evt; @@ -100,8 +100,8 @@ static void *uffd_handler_thread_fn(void *arg) } struct uffd_desc *uffd_setup_demand_paging(int uffd_mode, useconds_t delay, - void *hva, uint64_t len, - uint64_t num_readers, + void *hva, u64 len, + u64 num_readers, uffd_handler_t handler) { struct uffd_desc *uffd_desc; @@ -109,7 +109,7 @@ struct uffd_desc *uffd_setup_demand_paging(int uffd_mode, useconds_t delay, int uffd; struct uffdio_api uffdio_api; struct uffdio_register uffdio_register; - uint64_t expected_ioctls = ((uint64_t) 1) << _UFFDIO_COPY; + u64 expected_ioctls = ((u64)1) << _UFFDIO_COPY; int ret, i; PER_PAGE_DEBUG("Userfaultfd %s mode, faults resolved with %s\n", @@ -132,7 +132,7 @@ struct uffd_desc *uffd_setup_demand_paging(int uffd_mode, useconds_t delay, /* In order to get minor faults, prefault via the alias. */ if (is_minor) - expected_ioctls = ((uint64_t) 1) << _UFFDIO_CONTINUE; + expected_ioctls = ((u64)1) << _UFFDIO_CONTINUE; uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK); TEST_ASSERT(uffd >= 0, "uffd creation failed, errno: %d", errno); @@ -141,9 +141,9 @@ struct uffd_desc *uffd_setup_demand_paging(int uffd_mode, useconds_t delay, uffdio_api.features = 0; TEST_ASSERT(ioctl(uffd, UFFDIO_API, &uffdio_api) != -1, "ioctl UFFDIO_API failed: %" PRIu64, - (uint64_t)uffdio_api.api); + (u64)uffdio_api.api); - uffdio_register.range.start = (uint64_t)hva; + uffdio_register.range.start = (u64)hva; uffdio_register.range.len = len; uffdio_register.mode = uffd_mode; TEST_ASSERT(ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) != -1, diff --git a/tools/testing/selftests/kvm/lib/x86/apic.c b/tools/testing/selftests/kvm/lib/x86/apic.c index 89153a333e83..5182fd0d6a76 100644 --- a/tools/testing/selftests/kvm/lib/x86/apic.c +++ b/tools/testing/selftests/kvm/lib/x86/apic.c @@ -14,7 +14,7 @@ void apic_disable(void) void xapic_enable(void) { - uint64_t val = rdmsr(MSR_IA32_APICBASE); + u64 val = rdmsr(MSR_IA32_APICBASE); /* Per SDM: to enable xAPIC when in x2APIC must first disable APIC */ if (val & MSR_IA32_APICBASE_EXTD) { diff --git a/tools/testing/selftests/kvm/lib/x86/hyperv.c b/tools/testing/selftests/kvm/lib/x86/hyperv.c index 15bc8cd583aa..d200c5c26e2e 100644 --- a/tools/testing/selftests/kvm/lib/x86/hyperv.c +++ b/tools/testing/selftests/kvm/lib/x86/hyperv.c @@ -76,23 +76,23 @@ bool kvm_hv_cpu_has(struct kvm_x86_cpu_feature feature) } struct hyperv_test_pages *vcpu_alloc_hyperv_test_pages(struct kvm_vm *vm, - vm_vaddr_t *p_hv_pages_gva) + gva_t *p_hv_pages_gva) { - vm_vaddr_t hv_pages_gva = vm_vaddr_alloc_page(vm); + gva_t hv_pages_gva = vm_alloc_page(vm); struct hyperv_test_pages *hv = addr_gva2hva(vm, hv_pages_gva); /* Setup of a region of guest memory for the VP Assist page. */ - hv->vp_assist = (void *)vm_vaddr_alloc_page(vm); + hv->vp_assist = (void *)vm_alloc_page(vm); hv->vp_assist_hva = addr_gva2hva(vm, (uintptr_t)hv->vp_assist); hv->vp_assist_gpa = addr_gva2gpa(vm, (uintptr_t)hv->vp_assist); /* Setup of a region of guest memory for the partition assist page. */ - hv->partition_assist = (void *)vm_vaddr_alloc_page(vm); + hv->partition_assist = (void *)vm_alloc_page(vm); hv->partition_assist_hva = addr_gva2hva(vm, (uintptr_t)hv->partition_assist); hv->partition_assist_gpa = addr_gva2gpa(vm, (uintptr_t)hv->partition_assist); /* Setup of a region of guest memory for the enlightened VMCS. */ - hv->enlightened_vmcs = (void *)vm_vaddr_alloc_page(vm); + hv->enlightened_vmcs = (void *)vm_alloc_page(vm); hv->enlightened_vmcs_hva = addr_gva2hva(vm, (uintptr_t)hv->enlightened_vmcs); hv->enlightened_vmcs_gpa = addr_gva2gpa(vm, (uintptr_t)hv->enlightened_vmcs); @@ -100,9 +100,9 @@ struct hyperv_test_pages *vcpu_alloc_hyperv_test_pages(struct kvm_vm *vm, return hv; } -int enable_vp_assist(uint64_t vp_assist_pa, void *vp_assist) +int enable_vp_assist(u64 vp_assist_pa, void *vp_assist) { - uint64_t val = (vp_assist_pa & HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK) | + u64 val = (vp_assist_pa & HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK) | HV_X64_MSR_VP_ASSIST_PAGE_ENABLE; wrmsr(HV_X64_MSR_VP_ASSIST_PAGE, val); diff --git a/tools/testing/selftests/kvm/lib/x86/memstress.c b/tools/testing/selftests/kvm/lib/x86/memstress.c index f53414ba7103..61cf952cd2dc 100644 --- a/tools/testing/selftests/kvm/lib/x86/memstress.c +++ b/tools/testing/selftests/kvm/lib/x86/memstress.c @@ -16,7 +16,7 @@ #include "svm_util.h" #include "vmx.h" -void memstress_l2_guest_code(uint64_t vcpu_id) +void memstress_l2_guest_code(u64 vcpu_id) { memstress_guest_code(vcpu_id); vmcall(); @@ -32,7 +32,7 @@ __asm__( #define L2_GUEST_STACK_SIZE 64 -static void l1_vmx_code(struct vmx_pages *vmx, uint64_t vcpu_id) +static void l1_vmx_code(struct vmx_pages *vmx, u64 vcpu_id) { unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; unsigned long *rsp; @@ -51,7 +51,7 @@ static void l1_vmx_code(struct vmx_pages *vmx, uint64_t vcpu_id) GUEST_DONE(); } -static void l1_svm_code(struct svm_test_data *svm, uint64_t vcpu_id) +static void l1_svm_code(struct svm_test_data *svm, u64 vcpu_id) { unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; unsigned long *rsp; @@ -67,7 +67,7 @@ static void l1_svm_code(struct svm_test_data *svm, uint64_t vcpu_id) } -static void memstress_l1_guest_code(void *data, uint64_t vcpu_id) +static void memstress_l1_guest_code(void *data, u64 vcpu_id) { if (this_cpu_has(X86_FEATURE_VMX)) l1_vmx_code(data, vcpu_id); @@ -75,7 +75,7 @@ static void memstress_l1_guest_code(void *data, uint64_t vcpu_id) l1_svm_code(data, vcpu_id); } -uint64_t memstress_nested_pages(int nr_vcpus) +u64 memstress_nested_pages(int nr_vcpus) { /* * 513 page tables is enough to identity-map 256 TiB of L2 with 1G @@ -87,7 +87,7 @@ uint64_t memstress_nested_pages(int nr_vcpus) static void memstress_setup_ept_mappings(struct kvm_vm *vm) { - uint64_t start, end; + u64 start, end; /* * Identity map the first 4G and the test region with 1G pages so that @@ -104,7 +104,7 @@ static void memstress_setup_ept_mappings(struct kvm_vm *vm) void memstress_setup_nested(struct kvm_vm *vm, int nr_vcpus, struct kvm_vcpu *vcpus[]) { struct kvm_regs regs; - vm_vaddr_t nested_gva; + gva_t nested_gva; int vcpu_id; TEST_REQUIRE(kvm_cpu_has_tdp()); diff --git a/tools/testing/selftests/kvm/lib/x86/pmu.c b/tools/testing/selftests/kvm/lib/x86/pmu.c index 34cb57d1d671..0851b74b4e46 100644 --- a/tools/testing/selftests/kvm/lib/x86/pmu.c +++ b/tools/testing/selftests/kvm/lib/x86/pmu.c @@ -11,7 +11,7 @@ #include "processor.h" #include "pmu.h" -const uint64_t intel_pmu_arch_events[] = { +const u64 intel_pmu_arch_events[] = { INTEL_ARCH_CPU_CYCLES, INTEL_ARCH_INSTRUCTIONS_RETIRED, INTEL_ARCH_REFERENCE_CYCLES, @@ -28,7 +28,7 @@ const uint64_t intel_pmu_arch_events[] = { }; kvm_static_assert(ARRAY_SIZE(intel_pmu_arch_events) == NR_INTEL_ARCH_EVENTS); -const uint64_t amd_pmu_zen_events[] = { +const u64 amd_pmu_zen_events[] = { AMD_ZEN_CORE_CYCLES, AMD_ZEN_INSTRUCTIONS_RETIRED, AMD_ZEN_BRANCHES_RETIRED, @@ -50,7 +50,7 @@ kvm_static_assert(ARRAY_SIZE(amd_pmu_zen_events) == NR_AMD_ZEN_EVENTS); * be overcounted on these certain instructions, but for Clearwater Forest * only "Instruction Retired" event is overcounted on these instructions. */ -static uint64_t get_pmu_errata(void) +static u64 get_pmu_errata(void) { if (!this_cpu_is_intel()) return 0; @@ -72,7 +72,7 @@ static uint64_t get_pmu_errata(void) } } -uint64_t pmu_errata_mask; +u64 pmu_errata_mask; void kvm_init_pmu_errata(void) { diff --git a/tools/testing/selftests/kvm/lib/x86/processor.c b/tools/testing/selftests/kvm/lib/x86/processor.c index 01f0f97d4430..b51467d70f6e 100644 --- a/tools/testing/selftests/kvm/lib/x86/processor.c +++ b/tools/testing/selftests/kvm/lib/x86/processor.c @@ -21,13 +21,13 @@ #define KERNEL_DS 0x10 #define KERNEL_TSS 0x18 -vm_vaddr_t exception_handlers; +gva_t exception_handlers; bool host_cpu_is_amd; bool host_cpu_is_intel; bool host_cpu_is_hygon; bool host_cpu_is_amd_compatible; bool is_forced_emulation_enabled; -uint64_t guest_tsc_khz; +u64 guest_tsc_khz; const char *ex_str(int vector) { @@ -62,7 +62,7 @@ const char *ex_str(int vector) } } -static void regs_dump(FILE *stream, struct kvm_regs *regs, uint8_t indent) +static void regs_dump(FILE *stream, struct kvm_regs *regs, u8 indent) { fprintf(stream, "%*srax: 0x%.16llx rbx: 0x%.16llx " "rcx: 0x%.16llx rdx: 0x%.16llx\n", @@ -86,7 +86,7 @@ static void regs_dump(FILE *stream, struct kvm_regs *regs, uint8_t indent) } static void segment_dump(FILE *stream, struct kvm_segment *segment, - uint8_t indent) + u8 indent) { fprintf(stream, "%*sbase: 0x%.16llx limit: 0x%.8x " "selector: 0x%.4x type: 0x%.2x\n", @@ -103,7 +103,7 @@ static void segment_dump(FILE *stream, struct kvm_segment *segment, } static void dtable_dump(FILE *stream, struct kvm_dtable *dtable, - uint8_t indent) + u8 indent) { fprintf(stream, "%*sbase: 0x%.16llx limit: 0x%.4x " "padding: 0x%.4x 0x%.4x 0x%.4x\n", @@ -111,7 +111,7 @@ static void dtable_dump(FILE *stream, struct kvm_dtable *dtable, dtable->padding[0], dtable->padding[1], dtable->padding[2]); } -static void sregs_dump(FILE *stream, struct kvm_sregs *sregs, uint8_t indent) +static void sregs_dump(FILE *stream, struct kvm_sregs *sregs, u8 indent) { unsigned int i; @@ -207,37 +207,37 @@ void tdp_mmu_init(struct kvm_vm *vm, int pgtable_levels, } static void *virt_get_pte(struct kvm_vm *vm, struct kvm_mmu *mmu, - uint64_t *parent_pte, uint64_t vaddr, int level) + u64 *parent_pte, gva_t gva, int level) { - uint64_t pt_gpa = PTE_GET_PA(*parent_pte); - uint64_t *page_table = addr_gpa2hva(vm, pt_gpa); - int index = (vaddr >> PG_LEVEL_SHIFT(level)) & 0x1ffu; + u64 pt_gpa = PTE_GET_PA(*parent_pte); + u64 *page_table = addr_gpa2hva(vm, pt_gpa); + int index = (gva >> PG_LEVEL_SHIFT(level)) & 0x1ffu; TEST_ASSERT((*parent_pte == mmu->pgd) || is_present_pte(mmu, parent_pte), "Parent PTE (level %d) not PRESENT for gva: 0x%08lx", - level + 1, vaddr); + level + 1, gva); return &page_table[index]; } -static uint64_t *virt_create_upper_pte(struct kvm_vm *vm, - struct kvm_mmu *mmu, - uint64_t *parent_pte, - uint64_t vaddr, - uint64_t paddr, - int current_level, - int target_level) +static u64 *virt_create_upper_pte(struct kvm_vm *vm, + struct kvm_mmu *mmu, + u64 *parent_pte, + gva_t gva, + gpa_t gpa, + int current_level, + int target_level) { - uint64_t *pte = virt_get_pte(vm, mmu, parent_pte, vaddr, current_level); + u64 *pte = virt_get_pte(vm, mmu, parent_pte, gva, current_level); - paddr = vm_untag_gpa(vm, paddr); + gpa = vm_untag_gpa(vm, gpa); if (!is_present_pte(mmu, pte)) { *pte = PTE_PRESENT_MASK(mmu) | PTE_READABLE_MASK(mmu) | PTE_WRITABLE_MASK(mmu) | PTE_EXECUTABLE_MASK(mmu) | PTE_ALWAYS_SET_MASK(mmu); if (current_level == target_level) - *pte |= PTE_HUGE_MASK(mmu) | (paddr & PHYSICAL_PAGE_MASK); + *pte |= PTE_HUGE_MASK(mmu) | (gpa & PHYSICAL_PAGE_MASK); else *pte |= vm_alloc_page_table(vm) & PHYSICAL_PAGE_MASK; } else { @@ -247,39 +247,39 @@ static uint64_t *virt_create_upper_pte(struct kvm_vm *vm, * this level. */ TEST_ASSERT(current_level != target_level, - "Cannot create hugepage at level: %u, vaddr: 0x%lx", - current_level, vaddr); + "Cannot create hugepage at level: %u, gva: 0x%lx", + current_level, gva); TEST_ASSERT(!is_huge_pte(mmu, pte), - "Cannot create page table at level: %u, vaddr: 0x%lx", - current_level, vaddr); + "Cannot create page table at level: %u, gva: 0x%lx", + current_level, gva); } return pte; } -void __virt_pg_map(struct kvm_vm *vm, struct kvm_mmu *mmu, uint64_t vaddr, - uint64_t paddr, int level) +void __virt_pg_map(struct kvm_vm *vm, struct kvm_mmu *mmu, gva_t gva, + gpa_t gpa, int level) { - const uint64_t pg_size = PG_LEVEL_SIZE(level); - uint64_t *pte = &mmu->pgd; + const u64 pg_size = PG_LEVEL_SIZE(level); + u64 *pte = &mmu->pgd; int current_level; TEST_ASSERT(vm->mode == VM_MODE_PXXVYY_4K, "Unknown or unsupported guest mode: 0x%x", vm->mode); - TEST_ASSERT((vaddr % pg_size) == 0, + TEST_ASSERT((gva % pg_size) == 0, "Virtual address not aligned,\n" - "vaddr: 0x%lx page size: 0x%lx", vaddr, pg_size); - TEST_ASSERT(sparsebit_is_set(vm->vpages_valid, (vaddr >> vm->page_shift)), - "Invalid virtual address, vaddr: 0x%lx", vaddr); - TEST_ASSERT((paddr % pg_size) == 0, + "gva: 0x%lx page size: 0x%lx", gva, pg_size); + TEST_ASSERT(sparsebit_is_set(vm->vpages_valid, (gva >> vm->page_shift)), + "Invalid virtual address, gva: 0x%lx", gva); + TEST_ASSERT((gpa % pg_size) == 0, "Physical address not aligned,\n" - " paddr: 0x%lx page size: 0x%lx", paddr, pg_size); - TEST_ASSERT((paddr >> vm->page_shift) <= vm->max_gfn, + " gpa: 0x%lx page size: 0x%lx", gpa, pg_size); + TEST_ASSERT((gpa >> vm->page_shift) <= vm->max_gfn, "Physical address beyond maximum supported,\n" - " paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x", - paddr, vm->max_gfn, vm->page_size); - TEST_ASSERT(vm_untag_gpa(vm, paddr) == paddr, - "Unexpected bits in paddr: %lx", paddr); + " gpa: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x", + gpa, vm->max_gfn, vm->page_size); + TEST_ASSERT(vm_untag_gpa(vm, gpa) == gpa, + "Unexpected bits in gpa: %lx", gpa); TEST_ASSERT(!PTE_EXECUTABLE_MASK(mmu) || !PTE_NX_MASK(mmu), "X and NX bit masks cannot be used simultaneously"); @@ -291,40 +291,40 @@ void __virt_pg_map(struct kvm_vm *vm, struct kvm_mmu *mmu, uint64_t vaddr, for (current_level = mmu->pgtable_levels; current_level > PG_LEVEL_4K; current_level--) { - pte = virt_create_upper_pte(vm, mmu, pte, vaddr, paddr, + pte = virt_create_upper_pte(vm, mmu, pte, gva, gpa, current_level, level); if (is_huge_pte(mmu, pte)) return; } /* Fill in page table entry. */ - pte = virt_get_pte(vm, mmu, pte, vaddr, PG_LEVEL_4K); + pte = virt_get_pte(vm, mmu, pte, gva, PG_LEVEL_4K); TEST_ASSERT(!is_present_pte(mmu, pte), - "PTE already present for 4k page at vaddr: 0x%lx", vaddr); + "PTE already present for 4k page at gva: 0x%lx", gva); *pte = PTE_PRESENT_MASK(mmu) | PTE_READABLE_MASK(mmu) | PTE_WRITABLE_MASK(mmu) | PTE_EXECUTABLE_MASK(mmu) | - PTE_ALWAYS_SET_MASK(mmu) | (paddr & PHYSICAL_PAGE_MASK); + PTE_ALWAYS_SET_MASK(mmu) | (gpa & PHYSICAL_PAGE_MASK); /* * Neither SEV nor TDX supports shared page tables, so only the final * leaf PTE needs manually set the C/S-bit. */ - if (vm_is_gpa_protected(vm, paddr)) + if (vm_is_gpa_protected(vm, gpa)) *pte |= PTE_C_BIT_MASK(mmu); else *pte |= PTE_S_BIT_MASK(mmu); } -void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) +void virt_arch_pg_map(struct kvm_vm *vm, gva_t gva, gpa_t gpa) { - __virt_pg_map(vm, &vm->mmu, vaddr, paddr, PG_LEVEL_4K); + __virt_pg_map(vm, &vm->mmu, gva, gpa, PG_LEVEL_4K); } -void virt_map_level(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, - uint64_t nr_bytes, int level) +void virt_map_level(struct kvm_vm *vm, gva_t gva, gpa_t gpa, + u64 nr_bytes, int level) { - uint64_t pg_size = PG_LEVEL_SIZE(level); - uint64_t nr_pages = nr_bytes / pg_size; + u64 pg_size = PG_LEVEL_SIZE(level); + u64 nr_pages = nr_bytes / pg_size; int i; TEST_ASSERT(nr_bytes % pg_size == 0, @@ -332,16 +332,16 @@ void virt_map_level(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, nr_bytes, pg_size); for (i = 0; i < nr_pages; i++) { - __virt_pg_map(vm, &vm->mmu, vaddr, paddr, level); - sparsebit_set_num(vm->vpages_mapped, vaddr >> vm->page_shift, + __virt_pg_map(vm, &vm->mmu, gva, gpa, level); + sparsebit_set_num(vm->vpages_mapped, gva >> vm->page_shift, nr_bytes / PAGE_SIZE); - vaddr += pg_size; - paddr += pg_size; + gva += pg_size; + gpa += pg_size; } } -static bool vm_is_target_pte(struct kvm_mmu *mmu, uint64_t *pte, +static bool vm_is_target_pte(struct kvm_mmu *mmu, u64 *pte, int *level, int current_level) { if (is_huge_pte(mmu, pte)) { @@ -354,13 +354,13 @@ static bool vm_is_target_pte(struct kvm_mmu *mmu, uint64_t *pte, return *level == current_level; } -static uint64_t *__vm_get_page_table_entry(struct kvm_vm *vm, - struct kvm_mmu *mmu, - uint64_t vaddr, - int *level) +static u64 *__vm_get_page_table_entry(struct kvm_vm *vm, + struct kvm_mmu *mmu, + gva_t gva, + int *level) { int va_width = 12 + (mmu->pgtable_levels) * 9; - uint64_t *pte = &mmu->pgd; + u64 *pte = &mmu->pgd; int current_level; TEST_ASSERT(!vm->arch.is_pt_protected, @@ -371,49 +371,46 @@ static uint64_t *__vm_get_page_table_entry(struct kvm_vm *vm, TEST_ASSERT(vm->mode == VM_MODE_PXXVYY_4K, "Unknown or unsupported guest mode: 0x%x", vm->mode); - TEST_ASSERT(sparsebit_is_set(vm->vpages_valid, - (vaddr >> vm->page_shift)), - "Invalid virtual address, vaddr: 0x%lx", - vaddr); + TEST_ASSERT(sparsebit_is_set(vm->vpages_valid, (gva >> vm->page_shift)), + "Invalid virtual address, gva: 0x%lx", gva); /* - * Check that the vaddr is a sign-extended va_width value. + * Check that the gva is a sign-extended va_width value. */ - TEST_ASSERT(vaddr == - (((int64_t)vaddr << (64 - va_width) >> (64 - va_width))), + TEST_ASSERT(gva == (((s64)gva << (64 - va_width) >> (64 - va_width))), "Canonical check failed. The virtual address is invalid."); for (current_level = mmu->pgtable_levels; current_level > PG_LEVEL_4K; current_level--) { - pte = virt_get_pte(vm, mmu, pte, vaddr, current_level); + pte = virt_get_pte(vm, mmu, pte, gva, current_level); if (vm_is_target_pte(mmu, pte, level, current_level)) return pte; } - return virt_get_pte(vm, mmu, pte, vaddr, PG_LEVEL_4K); + return virt_get_pte(vm, mmu, pte, gva, PG_LEVEL_4K); } -uint64_t *tdp_get_pte(struct kvm_vm *vm, uint64_t l2_gpa) +u64 *tdp_get_pte(struct kvm_vm *vm, u64 l2_gpa) { int level = PG_LEVEL_4K; return __vm_get_page_table_entry(vm, &vm->stage2_mmu, l2_gpa, &level); } -uint64_t *vm_get_pte(struct kvm_vm *vm, uint64_t vaddr) +u64 *vm_get_pte(struct kvm_vm *vm, gva_t gva) { int level = PG_LEVEL_4K; - return __vm_get_page_table_entry(vm, &vm->mmu, vaddr, &level); + return __vm_get_page_table_entry(vm, &vm->mmu, gva, &level); } -void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) +void virt_arch_dump(FILE *stream, struct kvm_vm *vm, u8 indent) { struct kvm_mmu *mmu = &vm->mmu; - uint64_t *pml4e, *pml4e_start; - uint64_t *pdpe, *pdpe_start; - uint64_t *pde, *pde_start; - uint64_t *pte, *pte_start; + u64 *pml4e, *pml4e_start; + u64 *pdpe, *pdpe_start; + u64 *pde, *pde_start; + u64 *pte, *pte_start; if (!mmu->pgd_created) return; @@ -423,8 +420,8 @@ void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) fprintf(stream, "%*s index hvaddr gpaddr " "addr w exec dirty\n", indent, ""); - pml4e_start = (uint64_t *) addr_gpa2hva(vm, mmu->pgd); - for (uint16_t n1 = 0; n1 <= 0x1ffu; n1++) { + pml4e_start = (u64 *)addr_gpa2hva(vm, mmu->pgd); + for (u16 n1 = 0; n1 <= 0x1ffu; n1++) { pml4e = &pml4e_start[n1]; if (!is_present_pte(mmu, pml4e)) continue; @@ -436,7 +433,7 @@ void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) is_writable_pte(mmu, pml4e), is_nx_pte(mmu, pml4e)); pdpe_start = addr_gpa2hva(vm, *pml4e & PHYSICAL_PAGE_MASK); - for (uint16_t n2 = 0; n2 <= 0x1ffu; n2++) { + for (u16 n2 = 0; n2 <= 0x1ffu; n2++) { pdpe = &pdpe_start[n2]; if (!is_present_pte(mmu, pdpe)) continue; @@ -449,7 +446,7 @@ void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) is_nx_pte(mmu, pdpe)); pde_start = addr_gpa2hva(vm, *pdpe & PHYSICAL_PAGE_MASK); - for (uint16_t n3 = 0; n3 <= 0x1ffu; n3++) { + for (u16 n3 = 0; n3 <= 0x1ffu; n3++) { pde = &pde_start[n3]; if (!is_present_pte(mmu, pde)) continue; @@ -461,7 +458,7 @@ void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) is_nx_pte(mmu, pde)); pte_start = addr_gpa2hva(vm, *pde & PHYSICAL_PAGE_MASK); - for (uint16_t n4 = 0; n4 <= 0x1ffu; n4++) { + for (u16 n4 = 0; n4 <= 0x1ffu; n4++) { pte = &pte_start[n4]; if (!is_present_pte(mmu, pte)) continue; @@ -475,10 +472,10 @@ void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) is_writable_pte(mmu, pte), is_nx_pte(mmu, pte), is_dirty_pte(mmu, pte), - ((uint64_t) n1 << 27) - | ((uint64_t) n2 << 18) - | ((uint64_t) n3 << 9) - | ((uint64_t) n4)); + ((u64)n1 << 27) + | ((u64)n2 << 18) + | ((u64)n3 << 9) + | ((u64)n4)); } } } @@ -498,26 +495,24 @@ bool kvm_cpu_has_tdp(void) return kvm_cpu_has_ept() || kvm_cpu_has_npt(); } -void __tdp_map(struct kvm_vm *vm, uint64_t nested_paddr, uint64_t paddr, - uint64_t size, int level) +void __tdp_map(struct kvm_vm *vm, gpa_t l2_gpa, gpa_t gpa, u64 size, int level) { size_t page_size = PG_LEVEL_SIZE(level); size_t npages = size / page_size; - TEST_ASSERT(nested_paddr + size > nested_paddr, "Vaddr overflow"); - TEST_ASSERT(paddr + size > paddr, "Paddr overflow"); + TEST_ASSERT(l2_gpa + size > l2_gpa, "L2 GPA overflow"); + TEST_ASSERT(gpa + size > gpa, "GPA overflow"); while (npages--) { - __virt_pg_map(vm, &vm->stage2_mmu, nested_paddr, paddr, level); - nested_paddr += page_size; - paddr += page_size; + __virt_pg_map(vm, &vm->stage2_mmu, l2_gpa, gpa, level); + l2_gpa += page_size; + gpa += page_size; } } -void tdp_map(struct kvm_vm *vm, uint64_t nested_paddr, uint64_t paddr, - uint64_t size) +void tdp_map(struct kvm_vm *vm, gpa_t l2_gpa, gpa_t gpa, u64 size) { - __tdp_map(vm, nested_paddr, paddr, size, PG_LEVEL_4K); + __tdp_map(vm, l2_gpa, gpa, size, PG_LEVEL_4K); } /* Prepare an identity extended page table that maps all the @@ -525,7 +520,7 @@ void tdp_map(struct kvm_vm *vm, uint64_t nested_paddr, uint64_t paddr, */ void tdp_identity_map_default_memslots(struct kvm_vm *vm) { - uint32_t s, memslot = 0; + u32 s, memslot = 0; sparsebit_idx_t i, last; struct userspace_mem_region *region = memslot2region(vm, memslot); @@ -540,13 +535,13 @@ void tdp_identity_map_default_memslots(struct kvm_vm *vm) if (i > last) break; - tdp_map(vm, (uint64_t)i << vm->page_shift, - (uint64_t)i << vm->page_shift, 1 << vm->page_shift); + tdp_map(vm, (u64)i << vm->page_shift, + (u64)i << vm->page_shift, 1 << vm->page_shift); } } /* Identity map a region with 1GiB Pages. */ -void tdp_identity_map_1g(struct kvm_vm *vm, uint64_t addr, uint64_t size) +void tdp_identity_map_1g(struct kvm_vm *vm, u64 addr, u64 size) { __tdp_map(vm, addr, addr, size, PG_LEVEL_1G); } @@ -618,10 +613,10 @@ static void kvm_seg_set_kernel_data_64bit(struct kvm_segment *segp) segp->present = true; } -vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) +gpa_t addr_arch_gva2gpa(struct kvm_vm *vm, gva_t gva) { int level = PG_LEVEL_NONE; - uint64_t *pte = __vm_get_page_table_entry(vm, &vm->mmu, gva, &level); + u64 *pte = __vm_get_page_table_entry(vm, &vm->mmu, gva, &level); TEST_ASSERT(is_present_pte(&vm->mmu, pte), "Leaf PTE not PRESENT for gva: 0x%08lx", gva); @@ -633,7 +628,7 @@ vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) return vm_untag_gpa(vm, PTE_GET_PA(*pte)) | (gva & ~HUGEPAGE_MASK(level)); } -static void kvm_seg_set_tss_64bit(vm_vaddr_t base, struct kvm_segment *segp) +static void kvm_seg_set_tss_64bit(gva_t base, struct kvm_segment *segp) { memset(segp, 0, sizeof(*segp)); segp->base = base; @@ -746,16 +741,16 @@ static void vm_init_descriptor_tables(struct kvm_vm *vm) struct kvm_segment seg; int i; - vm->arch.gdt = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA); - vm->arch.idt = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA); - vm->handlers = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA); - vm->arch.tss = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA); + vm->arch.gdt = __vm_alloc_page(vm, MEM_REGION_DATA); + vm->arch.idt = __vm_alloc_page(vm, MEM_REGION_DATA); + vm->handlers = __vm_alloc_page(vm, MEM_REGION_DATA); + vm->arch.tss = __vm_alloc_page(vm, MEM_REGION_DATA); /* Handlers have the same address in both address spaces.*/ for (i = 0; i < NUM_INTERRUPTS; i++) set_idt_entry(vm, i, (unsigned long)(&idt_handlers)[i], 0, KERNEL_CS); - *(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers; + *(gva_t *)addr_gva2hva(vm, (gva_t)(&exception_handlers)) = vm->handlers; kvm_seg_set_kernel_code_64bit(&seg); kvm_seg_fill_gdt_64bit(vm, &seg); @@ -770,9 +765,9 @@ static void vm_init_descriptor_tables(struct kvm_vm *vm) void vm_install_exception_handler(struct kvm_vm *vm, int vector, void (*handler)(struct ex_regs *)) { - vm_vaddr_t *handlers = (vm_vaddr_t *)addr_gva2hva(vm, vm->handlers); + gva_t *handlers = (gva_t *)addr_gva2hva(vm, vm->handlers); - handlers[vector] = (vm_vaddr_t)handler; + handlers[vector] = (gva_t)handler; } void assert_on_unhandled_exception(struct kvm_vcpu *vcpu) @@ -821,18 +816,17 @@ void vcpu_arch_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code) vcpu_regs_set(vcpu, ®s); } -struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id) +struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, u32 vcpu_id) { struct kvm_mp_state mp_state; struct kvm_regs regs; - vm_vaddr_t stack_vaddr; + gva_t stack_gva; struct kvm_vcpu *vcpu; - stack_vaddr = __vm_vaddr_alloc(vm, DEFAULT_STACK_PGS * getpagesize(), - DEFAULT_GUEST_STACK_VADDR_MIN, - MEM_REGION_DATA); + stack_gva = __vm_alloc(vm, DEFAULT_STACK_PGS * getpagesize(), + DEFAULT_GUEST_STACK_VADDR_MIN, MEM_REGION_DATA); - stack_vaddr += DEFAULT_STACK_PGS * getpagesize(); + stack_gva += DEFAULT_STACK_PGS * getpagesize(); /* * Align stack to match calling sequence requirements in section "The @@ -843,9 +837,9 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id) * If this code is ever used to launch a vCPU with 32-bit entry point it * may need to subtract 4 bytes instead of 8 bytes. */ - TEST_ASSERT(IS_ALIGNED(stack_vaddr, PAGE_SIZE), - "__vm_vaddr_alloc() did not provide a page-aligned address"); - stack_vaddr -= 8; + TEST_ASSERT(IS_ALIGNED(stack_gva, PAGE_SIZE), + "__vm_alloc() did not provide a page-aligned address"); + stack_gva -= 8; vcpu = __vm_vcpu_add(vm, vcpu_id); vcpu_init_cpuid(vcpu, kvm_get_supported_cpuid()); @@ -855,7 +849,7 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id) /* Setup guest general purpose registers */ vcpu_regs_get(vcpu, ®s); regs.rflags = regs.rflags | 0x2; - regs.rsp = stack_vaddr; + regs.rsp = stack_gva; vcpu_regs_set(vcpu, ®s); /* Setup the MP state */ @@ -872,7 +866,7 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id) return vcpu; } -struct kvm_vcpu *vm_arch_vcpu_recreate(struct kvm_vm *vm, uint32_t vcpu_id) +struct kvm_vcpu *vm_arch_vcpu_recreate(struct kvm_vm *vm, u32 vcpu_id) { struct kvm_vcpu *vcpu = __vm_vcpu_add(vm, vcpu_id); @@ -907,9 +901,9 @@ const struct kvm_cpuid2 *kvm_get_supported_cpuid(void) return kvm_supported_cpuid; } -static uint32_t __kvm_cpu_has(const struct kvm_cpuid2 *cpuid, - uint32_t function, uint32_t index, - uint8_t reg, uint8_t lo, uint8_t hi) +static u32 __kvm_cpu_has(const struct kvm_cpuid2 *cpuid, + u32 function, u32 index, + u8 reg, u8 lo, u8 hi) { const struct kvm_cpuid_entry2 *entry; int i; @@ -936,14 +930,14 @@ bool kvm_cpuid_has(const struct kvm_cpuid2 *cpuid, feature.reg, feature.bit, feature.bit); } -uint32_t kvm_cpuid_property(const struct kvm_cpuid2 *cpuid, - struct kvm_x86_cpu_property property) +u32 kvm_cpuid_property(const struct kvm_cpuid2 *cpuid, + struct kvm_x86_cpu_property property) { return __kvm_cpu_has(cpuid, property.function, property.index, property.reg, property.lo_bit, property.hi_bit); } -uint64_t kvm_get_feature_msr(uint64_t msr_index) +u64 kvm_get_feature_msr(u64 msr_index) { struct { struct kvm_msrs header; @@ -962,7 +956,7 @@ uint64_t kvm_get_feature_msr(uint64_t msr_index) return buffer.entry.data; } -void __vm_xsave_require_permission(uint64_t xfeature, const char *name) +void __vm_xsave_require_permission(u64 xfeature, const char *name) { int kvm_fd; u64 bitmask; @@ -1019,7 +1013,7 @@ void vcpu_init_cpuid(struct kvm_vcpu *vcpu, const struct kvm_cpuid2 *cpuid) void vcpu_set_cpuid_property(struct kvm_vcpu *vcpu, struct kvm_x86_cpu_property property, - uint32_t value) + u32 value) { struct kvm_cpuid_entry2 *entry; @@ -1034,7 +1028,7 @@ void vcpu_set_cpuid_property(struct kvm_vcpu *vcpu, TEST_ASSERT_EQ(kvm_cpuid_property(vcpu->cpuid, property), value); } -void vcpu_clear_cpuid_entry(struct kvm_vcpu *vcpu, uint32_t function) +void vcpu_clear_cpuid_entry(struct kvm_vcpu *vcpu, u32 function) { struct kvm_cpuid_entry2 *entry = vcpu_get_cpuid_entry(vcpu, function); @@ -1063,7 +1057,7 @@ void vcpu_set_or_clear_cpuid_feature(struct kvm_vcpu *vcpu, vcpu_set_cpuid(vcpu); } -uint64_t vcpu_get_msr(struct kvm_vcpu *vcpu, uint64_t msr_index) +u64 vcpu_get_msr(struct kvm_vcpu *vcpu, u64 msr_index) { struct { struct kvm_msrs header; @@ -1078,7 +1072,7 @@ uint64_t vcpu_get_msr(struct kvm_vcpu *vcpu, uint64_t msr_index) return buffer.entry.data; } -int _vcpu_set_msr(struct kvm_vcpu *vcpu, uint64_t msr_index, uint64_t msr_value) +int _vcpu_set_msr(struct kvm_vcpu *vcpu, u64 msr_index, u64 msr_value) { struct { struct kvm_msrs header; @@ -1106,28 +1100,28 @@ void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...) vcpu_regs_get(vcpu, ®s); if (num >= 1) - regs.rdi = va_arg(ap, uint64_t); + regs.rdi = va_arg(ap, u64); if (num >= 2) - regs.rsi = va_arg(ap, uint64_t); + regs.rsi = va_arg(ap, u64); if (num >= 3) - regs.rdx = va_arg(ap, uint64_t); + regs.rdx = va_arg(ap, u64); if (num >= 4) - regs.rcx = va_arg(ap, uint64_t); + regs.rcx = va_arg(ap, u64); if (num >= 5) - regs.r8 = va_arg(ap, uint64_t); + regs.r8 = va_arg(ap, u64); if (num >= 6) - regs.r9 = va_arg(ap, uint64_t); + regs.r9 = va_arg(ap, u64); vcpu_regs_set(vcpu, ®s); va_end(ap); } -void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, uint8_t indent) +void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, u8 indent) { struct kvm_regs regs; struct kvm_sregs sregs; @@ -1196,7 +1190,7 @@ const struct kvm_msr_list *kvm_get_feature_msr_index_list(void) return list; } -bool kvm_msr_is_in_save_restore_list(uint32_t msr_index) +bool kvm_msr_is_in_save_restore_list(u32 msr_index) { const struct kvm_msr_list *list = kvm_get_msr_index_list(); int i; @@ -1327,7 +1321,7 @@ void kvm_init_vm_address_properties(struct kvm_vm *vm) } const struct kvm_cpuid_entry2 *get_cpuid_entry(const struct kvm_cpuid2 *cpuid, - uint32_t function, uint32_t index) + u32 function, u32 index) { int i; @@ -1344,7 +1338,7 @@ const struct kvm_cpuid_entry2 *get_cpuid_entry(const struct kvm_cpuid2 *cpuid, #define X86_HYPERCALL(inputs...) \ ({ \ - uint64_t r; \ + u64 r; \ \ asm volatile("test %[use_vmmcall], %[use_vmmcall]\n\t" \ "jnz 1f\n\t" \ @@ -1359,18 +1353,17 @@ const struct kvm_cpuid_entry2 *get_cpuid_entry(const struct kvm_cpuid2 *cpuid, r; \ }) -uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2, - uint64_t a3) +u64 kvm_hypercall(u64 nr, u64 a0, u64 a1, u64 a2, u64 a3) { return X86_HYPERCALL("a"(nr), "b"(a0), "c"(a1), "d"(a2), "S"(a3)); } -uint64_t __xen_hypercall(uint64_t nr, uint64_t a0, void *a1) +u64 __xen_hypercall(u64 nr, u64 a0, void *a1) { return X86_HYPERCALL("a"(nr), "D"(a0), "S"(a1)); } -void xen_hypercall(uint64_t nr, uint64_t a0, void *a1) +void xen_hypercall(u64 nr, u64 a0, void *a1) { GUEST_ASSERT(!__xen_hypercall(nr, a0, a1)); } @@ -1379,7 +1372,7 @@ unsigned long vm_compute_max_gfn(struct kvm_vm *vm) { const unsigned long num_ht_pages = 12 << (30 - vm->page_shift); /* 12 GiB */ unsigned long ht_gfn, max_gfn, max_pfn; - uint8_t maxphyaddr, guest_maxphyaddr; + u8 maxphyaddr, guest_maxphyaddr; /* * Use "guest MAXPHYADDR" from KVM if it's available. Guest MAXPHYADDR @@ -1453,8 +1446,7 @@ bool kvm_arch_has_default_irqchip(void) return true; } -void setup_smram(struct kvm_vm *vm, struct kvm_vcpu *vcpu, - uint64_t smram_gpa, +void setup_smram(struct kvm_vm *vm, struct kvm_vcpu *vcpu, u64 smram_gpa, const void *smi_handler, size_t handler_size) { vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, smram_gpa, diff --git a/tools/testing/selftests/kvm/lib/x86/sev.c b/tools/testing/selftests/kvm/lib/x86/sev.c index c3a9838f4806..93f916903461 100644 --- a/tools/testing/selftests/kvm/lib/x86/sev.c +++ b/tools/testing/selftests/kvm/lib/x86/sev.c @@ -15,10 +15,10 @@ * expression would cause us to quit the loop. */ static void encrypt_region(struct kvm_vm *vm, struct userspace_mem_region *region, - uint8_t page_type, bool private) + u8 page_type, bool private) { const struct sparsebit *protected_phy_pages = region->protected_phy_pages; - const vm_paddr_t gpa_base = region->region.guest_phys_addr; + const gpa_t gpa_base = region->region.guest_phys_addr; const sparsebit_idx_t lowest_page_in_region = gpa_base >> vm->page_shift; sparsebit_idx_t i, j; @@ -29,15 +29,15 @@ static void encrypt_region(struct kvm_vm *vm, struct userspace_mem_region *regio sev_register_encrypted_memory(vm, region); sparsebit_for_each_set_range(protected_phy_pages, i, j) { - const uint64_t size = (j - i + 1) * vm->page_size; - const uint64_t offset = (i - lowest_page_in_region) * vm->page_size; + const u64 size = (j - i + 1) * vm->page_size; + const u64 offset = (i - lowest_page_in_region) * vm->page_size; if (private) vm_mem_set_private(vm, gpa_base + offset, size); if (is_sev_snp_vm(vm)) snp_launch_update_data(vm, gpa_base + offset, - (uint64_t)addr_gpa2hva(vm, gpa_base + offset), + (u64)addr_gpa2hva(vm, gpa_base + offset), size, page_type); else sev_launch_update_data(vm, gpa_base + offset, size); @@ -79,7 +79,7 @@ void snp_vm_init(struct kvm_vm *vm) vm_sev_ioctl(vm, KVM_SEV_INIT2, &init); } -void sev_vm_launch(struct kvm_vm *vm, uint32_t policy) +void sev_vm_launch(struct kvm_vm *vm, u32 policy) { struct kvm_sev_launch_start launch_start = { .policy = policy, @@ -103,7 +103,7 @@ void sev_vm_launch(struct kvm_vm *vm, uint32_t policy) vm->arch.is_pt_protected = true; } -void sev_vm_launch_measure(struct kvm_vm *vm, uint8_t *measurement) +void sev_vm_launch_measure(struct kvm_vm *vm, u8 *measurement) { struct kvm_sev_launch_measure launch_measure; struct kvm_sev_guest_status guest_status; @@ -131,7 +131,7 @@ void sev_vm_launch_finish(struct kvm_vm *vm) TEST_ASSERT_EQ(status.state, SEV_GUEST_STATE_RUNNING); } -void snp_vm_launch_start(struct kvm_vm *vm, uint64_t policy) +void snp_vm_launch_start(struct kvm_vm *vm, u64 policy) { struct kvm_sev_snp_launch_start launch_start = { .policy = policy, @@ -158,7 +158,7 @@ void snp_vm_launch_finish(struct kvm_vm *vm) vm_sev_ioctl(vm, KVM_SEV_SNP_LAUNCH_FINISH, &launch_finish); } -struct kvm_vm *vm_sev_create_with_one_vcpu(uint32_t type, void *guest_code, +struct kvm_vm *vm_sev_create_with_one_vcpu(u32 type, void *guest_code, struct kvm_vcpu **cpu) { struct vm_shape shape = { @@ -174,7 +174,7 @@ struct kvm_vm *vm_sev_create_with_one_vcpu(uint32_t type, void *guest_code, return vm; } -void vm_sev_launch(struct kvm_vm *vm, uint64_t policy, uint8_t *measurement) +void vm_sev_launch(struct kvm_vm *vm, u64 policy, u8 *measurement) { if (is_sev_snp_vm(vm)) { vm_enable_cap(vm, KVM_CAP_EXIT_HYPERCALL, BIT(KVM_HC_MAP_GPA_RANGE)); diff --git a/tools/testing/selftests/kvm/lib/x86/svm.c b/tools/testing/selftests/kvm/lib/x86/svm.c index eb20b00112c7..3b01605ab016 100644 --- a/tools/testing/selftests/kvm/lib/x86/svm.c +++ b/tools/testing/selftests/kvm/lib/x86/svm.c @@ -28,20 +28,20 @@ u64 rflags; * Pointer to structure with the addresses of the SVM areas. */ struct svm_test_data * -vcpu_alloc_svm(struct kvm_vm *vm, vm_vaddr_t *p_svm_gva) +vcpu_alloc_svm(struct kvm_vm *vm, gva_t *p_svm_gva) { - vm_vaddr_t svm_gva = vm_vaddr_alloc_page(vm); + gva_t svm_gva = vm_alloc_page(vm); struct svm_test_data *svm = addr_gva2hva(vm, svm_gva); - svm->vmcb = (void *)vm_vaddr_alloc_page(vm); + svm->vmcb = (void *)vm_alloc_page(vm); svm->vmcb_hva = addr_gva2hva(vm, (uintptr_t)svm->vmcb); svm->vmcb_gpa = addr_gva2gpa(vm, (uintptr_t)svm->vmcb); - svm->save_area = (void *)vm_vaddr_alloc_page(vm); + svm->save_area = (void *)vm_alloc_page(vm); svm->save_area_hva = addr_gva2hva(vm, (uintptr_t)svm->save_area); svm->save_area_gpa = addr_gva2gpa(vm, (uintptr_t)svm->save_area); - svm->msr = (void *)vm_vaddr_alloc_page(vm); + svm->msr = (void *)vm_alloc_page(vm); svm->msr_hva = addr_gva2hva(vm, (uintptr_t)svm->msr); svm->msr_gpa = addr_gva2gpa(vm, (uintptr_t)svm->msr); memset(svm->msr_hva, 0, getpagesize()); @@ -84,14 +84,14 @@ void vm_enable_npt(struct kvm_vm *vm) void generic_svm_setup(struct svm_test_data *svm, void *guest_rip, void *guest_rsp) { struct vmcb *vmcb = svm->vmcb; - uint64_t vmcb_gpa = svm->vmcb_gpa; + u64 vmcb_gpa = svm->vmcb_gpa; struct vmcb_save_area *save = &vmcb->save; struct vmcb_control_area *ctrl = &vmcb->control; u32 data_seg_attr = 3 | SVM_SELECTOR_S_MASK | SVM_SELECTOR_P_MASK | SVM_SELECTOR_DB_MASK | SVM_SELECTOR_G_MASK; u32 code_seg_attr = 9 | SVM_SELECTOR_S_MASK | SVM_SELECTOR_P_MASK | SVM_SELECTOR_L_MASK | SVM_SELECTOR_G_MASK; - uint64_t efer; + u64 efer; efer = rdmsr(MSR_EFER); wrmsr(MSR_EFER, efer | EFER_SVME); @@ -158,7 +158,7 @@ void generic_svm_setup(struct svm_test_data *svm, void *guest_rip, void *guest_r * for now. registers involved in LOAD/SAVE_GPR_C are eventually * unmodified so they do not need to be in the clobber list. */ -void run_guest(struct vmcb *vmcb, uint64_t vmcb_gpa) +void run_guest(struct vmcb *vmcb, u64 vmcb_gpa) { asm volatile ( "vmload %[vmcb_gpa]\n\t" diff --git a/tools/testing/selftests/kvm/lib/x86/ucall.c b/tools/testing/selftests/kvm/lib/x86/ucall.c index 1265cecc7dd1..e7dd5791959b 100644 --- a/tools/testing/selftests/kvm/lib/x86/ucall.c +++ b/tools/testing/selftests/kvm/lib/x86/ucall.c @@ -6,9 +6,9 @@ */ #include "kvm_util.h" -#define UCALL_PIO_PORT ((uint16_t)0x1000) +#define UCALL_PIO_PORT ((u16)0x1000) -void ucall_arch_do_ucall(vm_vaddr_t uc) +void ucall_arch_do_ucall(gva_t uc) { /* * FIXME: Revert this hack (the entire commit that added it) once nVMX diff --git a/tools/testing/selftests/kvm/lib/x86/vmx.c b/tools/testing/selftests/kvm/lib/x86/vmx.c index c87b340362a9..67642759e4a0 100644 --- a/tools/testing/selftests/kvm/lib/x86/vmx.c +++ b/tools/testing/selftests/kvm/lib/x86/vmx.c @@ -27,7 +27,7 @@ struct hv_vp_assist_page *current_vp_assist; int vcpu_enable_evmcs(struct kvm_vcpu *vcpu) { - uint16_t evmcs_ver; + u16 evmcs_ver; vcpu_enable_cap(vcpu, KVM_CAP_HYPERV_ENLIGHTENED_VMCS, (unsigned long)&evmcs_ver); @@ -79,39 +79,39 @@ void vm_enable_ept(struct kvm_vm *vm) * Pointer to structure with the addresses of the VMX areas. */ struct vmx_pages * -vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva) +vcpu_alloc_vmx(struct kvm_vm *vm, gva_t *p_vmx_gva) { - vm_vaddr_t vmx_gva = vm_vaddr_alloc_page(vm); + gva_t vmx_gva = vm_alloc_page(vm); struct vmx_pages *vmx = addr_gva2hva(vm, vmx_gva); /* Setup of a region of guest memory for the vmxon region. */ - vmx->vmxon = (void *)vm_vaddr_alloc_page(vm); + vmx->vmxon = (void *)vm_alloc_page(vm); vmx->vmxon_hva = addr_gva2hva(vm, (uintptr_t)vmx->vmxon); vmx->vmxon_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmxon); /* Setup of a region of guest memory for a vmcs. */ - vmx->vmcs = (void *)vm_vaddr_alloc_page(vm); + vmx->vmcs = (void *)vm_alloc_page(vm); vmx->vmcs_hva = addr_gva2hva(vm, (uintptr_t)vmx->vmcs); vmx->vmcs_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmcs); /* Setup of a region of guest memory for the MSR bitmap. */ - vmx->msr = (void *)vm_vaddr_alloc_page(vm); + vmx->msr = (void *)vm_alloc_page(vm); vmx->msr_hva = addr_gva2hva(vm, (uintptr_t)vmx->msr); vmx->msr_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->msr); memset(vmx->msr_hva, 0, getpagesize()); /* Setup of a region of guest memory for the shadow VMCS. */ - vmx->shadow_vmcs = (void *)vm_vaddr_alloc_page(vm); + vmx->shadow_vmcs = (void *)vm_alloc_page(vm); vmx->shadow_vmcs_hva = addr_gva2hva(vm, (uintptr_t)vmx->shadow_vmcs); vmx->shadow_vmcs_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->shadow_vmcs); /* Setup of a region of guest memory for the VMREAD and VMWRITE bitmaps. */ - vmx->vmread = (void *)vm_vaddr_alloc_page(vm); + vmx->vmread = (void *)vm_alloc_page(vm); vmx->vmread_hva = addr_gva2hva(vm, (uintptr_t)vmx->vmread); vmx->vmread_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmread); memset(vmx->vmread_hva, 0, getpagesize()); - vmx->vmwrite = (void *)vm_vaddr_alloc_page(vm); + vmx->vmwrite = (void *)vm_alloc_page(vm); vmx->vmwrite_hva = addr_gva2hva(vm, (uintptr_t)vmx->vmwrite); vmx->vmwrite_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmwrite); memset(vmx->vmwrite_hva, 0, getpagesize()); @@ -125,8 +125,8 @@ vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva) bool prepare_for_vmx_operation(struct vmx_pages *vmx) { - uint64_t feature_control; - uint64_t required; + u64 feature_control; + u64 required; unsigned long cr0; unsigned long cr4; @@ -160,7 +160,7 @@ bool prepare_for_vmx_operation(struct vmx_pages *vmx) wrmsr(MSR_IA32_FEAT_CTL, feature_control | required); /* Enter VMX root operation. */ - *(uint32_t *)(vmx->vmxon) = vmcs_revision(); + *(u32 *)(vmx->vmxon) = vmcs_revision(); if (vmxon(vmx->vmxon_gpa)) return false; @@ -170,7 +170,7 @@ bool prepare_for_vmx_operation(struct vmx_pages *vmx) bool load_vmcs(struct vmx_pages *vmx) { /* Load a VMCS. */ - *(uint32_t *)(vmx->vmcs) = vmcs_revision(); + *(u32 *)(vmx->vmcs) = vmcs_revision(); if (vmclear(vmx->vmcs_gpa)) return false; @@ -178,14 +178,14 @@ bool load_vmcs(struct vmx_pages *vmx) return false; /* Setup shadow VMCS, do not load it yet. */ - *(uint32_t *)(vmx->shadow_vmcs) = vmcs_revision() | 0x80000000ul; + *(u32 *)(vmx->shadow_vmcs) = vmcs_revision() | 0x80000000ul; if (vmclear(vmx->shadow_vmcs_gpa)) return false; return true; } -static bool ept_vpid_cap_supported(uint64_t mask) +static bool ept_vpid_cap_supported(u64 mask) { return rdmsr(MSR_IA32_VMX_EPT_VPID_CAP) & mask; } @@ -200,7 +200,7 @@ bool ept_1g_pages_supported(void) */ static inline void init_vmcs_control_fields(struct vmx_pages *vmx) { - uint32_t sec_exec_ctl = 0; + u32 sec_exec_ctl = 0; vmwrite(VIRTUAL_PROCESSOR_ID, 0); vmwrite(POSTED_INTR_NV, 0); @@ -208,7 +208,7 @@ static inline void init_vmcs_control_fields(struct vmx_pages *vmx) vmwrite(PIN_BASED_VM_EXEC_CONTROL, rdmsr(MSR_IA32_VMX_TRUE_PINBASED_CTLS)); if (vmx->eptp_gpa) { - uint64_t eptp = vmx->eptp_gpa | EPTP_WB | EPTP_PWL_4; + u64 eptp = vmx->eptp_gpa | EPTP_WB | EPTP_PWL_4; TEST_ASSERT((vmx->eptp_gpa & ~PHYSICAL_PAGE_MASK) == 0, "Illegal bits set in vmx->eptp_gpa"); @@ -259,7 +259,7 @@ static inline void init_vmcs_control_fields(struct vmx_pages *vmx) */ static inline void init_vmcs_host_state(void) { - uint32_t exit_controls = vmreadz(VM_EXIT_CONTROLS); + u32 exit_controls = vmreadz(VM_EXIT_CONTROLS); vmwrite(HOST_ES_SELECTOR, get_es()); vmwrite(HOST_CS_SELECTOR, get_cs()); @@ -358,8 +358,8 @@ static inline void init_vmcs_guest_state(void *rip, void *rsp) vmwrite(GUEST_GDTR_BASE, vmreadz(HOST_GDTR_BASE)); vmwrite(GUEST_IDTR_BASE, vmreadz(HOST_IDTR_BASE)); vmwrite(GUEST_DR7, 0x400); - vmwrite(GUEST_RSP, (uint64_t)rsp); - vmwrite(GUEST_RIP, (uint64_t)rip); + vmwrite(GUEST_RSP, (u64)rsp); + vmwrite(GUEST_RIP, (u64)rip); vmwrite(GUEST_RFLAGS, 2); vmwrite(GUEST_PENDING_DBG_EXCEPTIONS, 0); vmwrite(GUEST_SYSENTER_ESP, vmreadz(HOST_IA32_SYSENTER_ESP)); @@ -375,7 +375,7 @@ void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp) bool kvm_cpu_has_ept(void) { - uint64_t ctrl; + u64 ctrl; if (!kvm_cpu_has(X86_FEATURE_VMX)) return false; @@ -390,7 +390,7 @@ bool kvm_cpu_has_ept(void) void prepare_virtualize_apic_accesses(struct vmx_pages *vmx, struct kvm_vm *vm) { - vmx->apic_access = (void *)vm_vaddr_alloc_page(vm); + vmx->apic_access = (void *)vm_alloc_page(vm); vmx->apic_access_hva = addr_gva2hva(vm, (uintptr_t)vmx->apic_access); vmx->apic_access_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->apic_access); } diff --git a/tools/testing/selftests/kvm/loongarch/arch_timer.c b/tools/testing/selftests/kvm/loongarch/arch_timer.c index 355ecac30954..a7279ded8518 100644 --- a/tools/testing/selftests/kvm/loongarch/arch_timer.c +++ b/tools/testing/selftests/kvm/loongarch/arch_timer.c @@ -27,8 +27,8 @@ static void do_idle(void) static void guest_irq_handler(struct ex_regs *regs) { unsigned int intid; - uint32_t cpu = guest_get_vcpuid(); - uint64_t xcnt, val, cfg, xcnt_diff_us; + u32 cpu = guest_get_vcpuid(); + u64 xcnt, val, cfg, xcnt_diff_us; struct test_vcpu_shared_data *shared_data = &vcpu_shared_data[cpu]; intid = !!(regs->estat & BIT(INT_TI)); @@ -62,10 +62,10 @@ static void guest_irq_handler(struct ex_regs *regs) WRITE_ONCE(shared_data->nr_iter, shared_data->nr_iter + 1); } -static void guest_test_period_timer(uint32_t cpu) +static void guest_test_period_timer(u32 cpu) { - uint32_t irq_iter, config_iter; - uint64_t us; + u32 irq_iter, config_iter; + u64 us; struct test_vcpu_shared_data *shared_data = &vcpu_shared_data[cpu]; shared_data->nr_iter = test_args.nr_iter; @@ -86,10 +86,10 @@ static void guest_test_period_timer(uint32_t cpu) irq_iter); } -static void guest_test_oneshot_timer(uint32_t cpu) +static void guest_test_oneshot_timer(u32 cpu) { - uint32_t irq_iter, config_iter; - uint64_t us; + u32 irq_iter, config_iter; + u64 us; struct test_vcpu_shared_data *shared_data = &vcpu_shared_data[cpu]; shared_data->nr_iter = 0; @@ -112,10 +112,10 @@ static void guest_test_oneshot_timer(uint32_t cpu) } } -static void guest_test_emulate_timer(uint32_t cpu) +static void guest_test_emulate_timer(u32 cpu) { - uint32_t config_iter; - uint64_t xcnt_diff_us, us; + u32 config_iter; + u64 xcnt_diff_us, us; struct test_vcpu_shared_data *shared_data = &vcpu_shared_data[cpu]; local_irq_disable(); @@ -136,9 +136,9 @@ static void guest_test_emulate_timer(uint32_t cpu) local_irq_enable(); } -static void guest_time_count_test(uint32_t cpu) +static void guest_time_count_test(u32 cpu) { - uint32_t config_iter; + u32 config_iter; unsigned long start, end, prev, us; /* Assuming that test case starts to run in 1 second */ @@ -165,7 +165,7 @@ static void guest_time_count_test(uint32_t cpu) static void guest_code(void) { - uint32_t cpu = guest_get_vcpuid(); + u32 cpu = guest_get_vcpuid(); /* must run at first */ guest_time_count_test(cpu); diff --git a/tools/testing/selftests/kvm/loongarch/pmu_test.c b/tools/testing/selftests/kvm/loongarch/pmu_test.c index 88bb530e336e..ec3fefb9ea97 100644 --- a/tools/testing/selftests/kvm/loongarch/pmu_test.c +++ b/tools/testing/selftests/kvm/loongarch/pmu_test.c @@ -15,7 +15,7 @@ static int pmu_irq_count; /* Check PMU support */ static bool has_pmu_support(void) { - uint32_t cfg6; + u32 cfg6; /* Read CPUCFG6 to check PMU */ cfg6 = read_cpucfg(LOONGARCH_CPUCFG6); @@ -34,7 +34,7 @@ static bool has_pmu_support(void) /* Dump PMU capabilities */ static void dump_pmu_caps(void) { - uint32_t cfg6; + u32 cfg6; int nr_counters, counter_bits; cfg6 = read_cpucfg(LOONGARCH_CPUCFG6); @@ -51,8 +51,8 @@ static void dump_pmu_caps(void) static void guest_pmu_base_test(void) { int i; - uint32_t cfg6, pmnum; - uint64_t cnt[4]; + u32 cfg6, pmnum; + u64 cnt[4]; cfg6 = read_cpucfg(LOONGARCH_CPUCFG6); pmnum = (cfg6 >> 4) & 0xf; @@ -114,7 +114,7 @@ static void guest_irq_handler(struct ex_regs *regs) static void guest_pmu_interrupt_test(void) { - uint64_t cnt; + u64 cnt; csr_write(PMU_OVERFLOW - 1, LOONGARCH_CSR_PERFCNTR0); csr_write(PMU_ENVENT_ENABLED | CSR_PERFCTRL_PMIE | LOONGARCH_PMU_EVENT_CYCLES, LOONGARCH_CSR_PERFCTRL0); diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c index 3cdfa3b19b85..9c7578a098c3 100644 --- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c +++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c @@ -30,7 +30,7 @@ static int nr_vcpus = 1; -static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE; +static u64 guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE; static void vcpu_worker(struct memstress_vcpu_args *vcpu_args) { @@ -55,10 +55,10 @@ static void vcpu_worker(struct memstress_vcpu_args *vcpu_args) } static void add_remove_memslot(struct kvm_vm *vm, useconds_t delay, - uint64_t nr_modifications) + u64 nr_modifications) { - uint64_t pages = max_t(int, vm->page_size, getpagesize()) / vm->page_size; - uint64_t gpa; + u64 pages = max_t(int, vm->page_size, getpagesize()) / vm->page_size; + gpa_t gpa; int i; /* @@ -78,7 +78,7 @@ static void add_remove_memslot(struct kvm_vm *vm, useconds_t delay, struct test_params { useconds_t delay; - uint64_t nr_iterations; + u64 nr_iterations; bool partition_vcpu_memory_access; bool disable_slot_zap_quirk; }; diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c index 5087d082c4b0..3d02db371422 100644 --- a/tools/testing/selftests/kvm/memslot_perf_test.c +++ b/tools/testing/selftests/kvm/memslot_perf_test.c @@ -85,17 +85,17 @@ struct vm_data { struct kvm_vm *vm; struct kvm_vcpu *vcpu; pthread_t vcpu_thread; - uint32_t nslots; - uint64_t npages; - uint64_t pages_per_slot; + u32 nslots; + u64 npages; + u64 pages_per_slot; void **hva_slots; bool mmio_ok; - uint64_t mmio_gpa_min; - uint64_t mmio_gpa_max; + u64 mmio_gpa_min; + u64 mmio_gpa_max; }; struct sync_area { - uint32_t guest_page_size; + u32 guest_page_size; atomic_bool start_flag; atomic_bool exit_flag; atomic_bool sync_flag; @@ -186,12 +186,12 @@ static void wait_for_vcpu(void) "sem_timedwait() failed: %d", errno); } -static void *vm_gpa2hva(struct vm_data *data, uint64_t gpa, uint64_t *rempages) +static void *vm_gpa2hva(struct vm_data *data, gpa_t gpa, u64 *rempages) { - uint64_t gpage, pgoffs; - uint32_t slot, slotoffs; + gpa_t gpage, pgoffs; + u32 slot, slotoffs; void *base; - uint32_t guest_page_size = data->vm->page_size; + u32 guest_page_size = data->vm->page_size; TEST_ASSERT(gpa >= MEM_GPA, "Too low gpa to translate"); TEST_ASSERT(gpa < MEM_GPA + data->npages * guest_page_size, @@ -200,11 +200,11 @@ static void *vm_gpa2hva(struct vm_data *data, uint64_t gpa, uint64_t *rempages) gpage = gpa / guest_page_size; pgoffs = gpa % guest_page_size; - slot = min(gpage / data->pages_per_slot, (uint64_t)data->nslots - 1); + slot = min(gpage / data->pages_per_slot, (u64)data->nslots - 1); slotoffs = gpage - (slot * data->pages_per_slot); if (rempages) { - uint64_t slotpages; + u64 slotpages; if (slot == data->nslots - 1) slotpages = data->npages - slot * data->pages_per_slot; @@ -217,12 +217,12 @@ static void *vm_gpa2hva(struct vm_data *data, uint64_t gpa, uint64_t *rempages) } base = data->hva_slots[slot]; - return (uint8_t *)base + slotoffs * guest_page_size + pgoffs; + return (u8 *)base + slotoffs * guest_page_size + pgoffs; } -static uint64_t vm_slot2gpa(struct vm_data *data, uint32_t slot) +static u64 vm_slot2gpa(struct vm_data *data, u32 slot) { - uint32_t guest_page_size = data->vm->page_size; + u32 guest_page_size = data->vm->page_size; TEST_ASSERT(slot < data->nslots, "Too high slot number"); @@ -243,8 +243,8 @@ static struct vm_data *alloc_vm(void) return data; } -static bool check_slot_pages(uint32_t host_page_size, uint32_t guest_page_size, - uint64_t pages_per_slot, uint64_t rempages) +static bool check_slot_pages(u32 host_page_size, u32 guest_page_size, + u64 pages_per_slot, u64 rempages) { if (!pages_per_slot) return false; @@ -259,11 +259,11 @@ static bool check_slot_pages(uint32_t host_page_size, uint32_t guest_page_size, } -static uint64_t get_max_slots(struct vm_data *data, uint32_t host_page_size) +static u64 get_max_slots(struct vm_data *data, u32 host_page_size) { - uint32_t guest_page_size = data->vm->page_size; - uint64_t mempages, pages_per_slot, rempages; - uint64_t slots; + u32 guest_page_size = data->vm->page_size; + u64 mempages, pages_per_slot, rempages; + u64 slots; mempages = data->npages; slots = data->nslots; @@ -281,13 +281,13 @@ static uint64_t get_max_slots(struct vm_data *data, uint32_t host_page_size) return 0; } -static bool prepare_vm(struct vm_data *data, int nslots, uint64_t *maxslots, - void *guest_code, uint64_t mem_size, +static bool prepare_vm(struct vm_data *data, int nslots, u64 *maxslots, + void *guest_code, u64 mem_size, struct timespec *slot_runtime) { - uint64_t mempages, rempages; - uint64_t guest_addr; - uint32_t slot, host_page_size, guest_page_size; + u64 mempages, rempages; + u64 guest_addr; + u32 slot, host_page_size, guest_page_size; struct timespec tstart; struct sync_area *sync; @@ -317,7 +317,7 @@ static bool prepare_vm(struct vm_data *data, int nslots, uint64_t *maxslots, clock_gettime(CLOCK_MONOTONIC, &tstart); for (slot = 1, guest_addr = MEM_GPA; slot <= data->nslots; slot++) { - uint64_t npages; + u64 npages; npages = data->pages_per_slot; if (slot == data->nslots) @@ -331,8 +331,8 @@ static bool prepare_vm(struct vm_data *data, int nslots, uint64_t *maxslots, *slot_runtime = timespec_elapsed(tstart); for (slot = 1, guest_addr = MEM_GPA; slot <= data->nslots; slot++) { - uint64_t npages; - uint64_t gpa; + u64 npages; + gpa_t gpa; npages = data->pages_per_slot; if (slot == data->nslots) @@ -448,7 +448,7 @@ static bool guest_perform_sync(void) static void guest_code_test_memslot_move(void) { struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA; - uint32_t page_size = (typeof(page_size))READ_ONCE(sync->guest_page_size); + u32 page_size = (typeof(page_size))READ_ONCE(sync->guest_page_size); uintptr_t base = (typeof(base))READ_ONCE(sync->move_area_ptr); GUEST_SYNC(0); @@ -460,7 +460,7 @@ static void guest_code_test_memslot_move(void) for (ptr = base; ptr < base + MEM_TEST_MOVE_SIZE; ptr += page_size) - *(uint64_t *)ptr = MEM_TEST_VAL_1; + *(u64 *)ptr = MEM_TEST_VAL_1; /* * No host sync here since the MMIO exits are so expensive @@ -477,7 +477,7 @@ static void guest_code_test_memslot_move(void) static void guest_code_test_memslot_map(void) { struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA; - uint32_t page_size = (typeof(page_size))READ_ONCE(sync->guest_page_size); + u32 page_size = (typeof(page_size))READ_ONCE(sync->guest_page_size); GUEST_SYNC(0); @@ -489,7 +489,7 @@ static void guest_code_test_memslot_map(void) for (ptr = MEM_TEST_GPA; ptr < MEM_TEST_GPA + MEM_TEST_MAP_SIZE / 2; ptr += page_size) - *(uint64_t *)ptr = MEM_TEST_VAL_1; + *(u64 *)ptr = MEM_TEST_VAL_1; if (!guest_perform_sync()) break; @@ -497,7 +497,7 @@ static void guest_code_test_memslot_map(void) for (ptr = MEM_TEST_GPA + MEM_TEST_MAP_SIZE / 2; ptr < MEM_TEST_GPA + MEM_TEST_MAP_SIZE; ptr += page_size) - *(uint64_t *)ptr = MEM_TEST_VAL_2; + *(u64 *)ptr = MEM_TEST_VAL_2; if (!guest_perform_sync()) break; @@ -526,13 +526,13 @@ static void guest_code_test_memslot_unmap(void) * * Just access a single page to be on the safe side. */ - *(uint64_t *)ptr = MEM_TEST_VAL_1; + *(u64 *)ptr = MEM_TEST_VAL_1; if (!guest_perform_sync()) break; ptr += MEM_TEST_UNMAP_SIZE / 2; - *(uint64_t *)ptr = MEM_TEST_VAL_2; + *(u64 *)ptr = MEM_TEST_VAL_2; if (!guest_perform_sync()) break; @@ -544,7 +544,7 @@ static void guest_code_test_memslot_unmap(void) static void guest_code_test_memslot_rw(void) { struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA; - uint32_t page_size = (typeof(page_size))READ_ONCE(sync->guest_page_size); + u32 page_size = (typeof(page_size))READ_ONCE(sync->guest_page_size); GUEST_SYNC(0); @@ -555,17 +555,17 @@ static void guest_code_test_memslot_rw(void) for (ptr = MEM_TEST_GPA; ptr < MEM_TEST_GPA + MEM_TEST_SIZE; ptr += page_size) - *(uint64_t *)ptr = MEM_TEST_VAL_1; + *(u64 *)ptr = MEM_TEST_VAL_1; if (!guest_perform_sync()) break; for (ptr = MEM_TEST_GPA + page_size / 2; ptr < MEM_TEST_GPA + MEM_TEST_SIZE; ptr += page_size) { - uint64_t val = *(uint64_t *)ptr; + u64 val = *(u64 *)ptr; GUEST_ASSERT_EQ(val, MEM_TEST_VAL_2); - *(uint64_t *)ptr = 0; + *(u64 *)ptr = 0; } if (!guest_perform_sync()) @@ -577,10 +577,10 @@ static void guest_code_test_memslot_rw(void) static bool test_memslot_move_prepare(struct vm_data *data, struct sync_area *sync, - uint64_t *maxslots, bool isactive) + u64 *maxslots, bool isactive) { - uint32_t guest_page_size = data->vm->page_size; - uint64_t movesrcgpa, movetestgpa; + u32 guest_page_size = data->vm->page_size; + u64 movesrcgpa, movetestgpa; #ifdef __x86_64__ if (disable_slot_zap_quirk) @@ -590,7 +590,7 @@ static bool test_memslot_move_prepare(struct vm_data *data, movesrcgpa = vm_slot2gpa(data, data->nslots - 1); if (isactive) { - uint64_t lastpages; + u64 lastpages; vm_gpa2hva(data, movesrcgpa, &lastpages); if (lastpages * guest_page_size < MEM_TEST_MOVE_SIZE / 2) { @@ -613,21 +613,21 @@ static bool test_memslot_move_prepare(struct vm_data *data, static bool test_memslot_move_prepare_active(struct vm_data *data, struct sync_area *sync, - uint64_t *maxslots) + u64 *maxslots) { return test_memslot_move_prepare(data, sync, maxslots, true); } static bool test_memslot_move_prepare_inactive(struct vm_data *data, struct sync_area *sync, - uint64_t *maxslots) + u64 *maxslots) { return test_memslot_move_prepare(data, sync, maxslots, false); } static void test_memslot_move_loop(struct vm_data *data, struct sync_area *sync) { - uint64_t movesrcgpa; + u64 movesrcgpa; movesrcgpa = vm_slot2gpa(data, data->nslots - 1); vm_mem_region_move(data->vm, data->nslots - 1 + 1, @@ -636,13 +636,13 @@ static void test_memslot_move_loop(struct vm_data *data, struct sync_area *sync) } static void test_memslot_do_unmap(struct vm_data *data, - uint64_t offsp, uint64_t count) + u64 offsp, u64 count) { - uint64_t gpa, ctr; - uint32_t guest_page_size = data->vm->page_size; + gpa_t gpa, ctr; + u32 guest_page_size = data->vm->page_size; for (gpa = MEM_TEST_GPA + offsp * guest_page_size, ctr = 0; ctr < count; ) { - uint64_t npages; + u64 npages; void *hva; int ret; @@ -661,11 +661,11 @@ static void test_memslot_do_unmap(struct vm_data *data, } static void test_memslot_map_unmap_check(struct vm_data *data, - uint64_t offsp, uint64_t valexp) + u64 offsp, u64 valexp) { - uint64_t gpa; - uint64_t *val; - uint32_t guest_page_size = data->vm->page_size; + gpa_t gpa; + u64 *val; + u32 guest_page_size = data->vm->page_size; if (!map_unmap_verify) return; @@ -680,8 +680,8 @@ static void test_memslot_map_unmap_check(struct vm_data *data, static void test_memslot_map_loop(struct vm_data *data, struct sync_area *sync) { - uint32_t guest_page_size = data->vm->page_size; - uint64_t guest_pages = MEM_TEST_MAP_SIZE / guest_page_size; + u32 guest_page_size = data->vm->page_size; + u64 guest_pages = MEM_TEST_MAP_SIZE / guest_page_size; /* * Unmap the second half of the test area while guest writes to (maps) @@ -718,11 +718,11 @@ static void test_memslot_map_loop(struct vm_data *data, struct sync_area *sync) static void test_memslot_unmap_loop_common(struct vm_data *data, struct sync_area *sync, - uint64_t chunk) + u64 chunk) { - uint32_t guest_page_size = data->vm->page_size; - uint64_t guest_pages = MEM_TEST_UNMAP_SIZE / guest_page_size; - uint64_t ctr; + u32 guest_page_size = data->vm->page_size; + u64 guest_pages = MEM_TEST_UNMAP_SIZE / guest_page_size; + u64 ctr; /* * Wait for the guest to finish mapping page(s) in the first half @@ -746,9 +746,9 @@ static void test_memslot_unmap_loop_common(struct vm_data *data, static void test_memslot_unmap_loop(struct vm_data *data, struct sync_area *sync) { - uint32_t host_page_size = getpagesize(); - uint32_t guest_page_size = data->vm->page_size; - uint64_t guest_chunk_pages = guest_page_size >= host_page_size ? + u32 host_page_size = getpagesize(); + u32 guest_page_size = data->vm->page_size; + u64 guest_chunk_pages = guest_page_size >= host_page_size ? 1 : host_page_size / guest_page_size; test_memslot_unmap_loop_common(data, sync, guest_chunk_pages); @@ -757,27 +757,27 @@ static void test_memslot_unmap_loop(struct vm_data *data, static void test_memslot_unmap_loop_chunked(struct vm_data *data, struct sync_area *sync) { - uint32_t guest_page_size = data->vm->page_size; - uint64_t guest_chunk_pages = MEM_TEST_UNMAP_CHUNK_SIZE / guest_page_size; + u32 guest_page_size = data->vm->page_size; + u64 guest_chunk_pages = MEM_TEST_UNMAP_CHUNK_SIZE / guest_page_size; test_memslot_unmap_loop_common(data, sync, guest_chunk_pages); } static void test_memslot_rw_loop(struct vm_data *data, struct sync_area *sync) { - uint64_t gptr; - uint32_t guest_page_size = data->vm->page_size; + u64 gptr; + u32 guest_page_size = data->vm->page_size; for (gptr = MEM_TEST_GPA + guest_page_size / 2; gptr < MEM_TEST_GPA + MEM_TEST_SIZE; gptr += guest_page_size) - *(uint64_t *)vm_gpa2hva(data, gptr, NULL) = MEM_TEST_VAL_2; + *(u64 *)vm_gpa2hva(data, gptr, NULL) = MEM_TEST_VAL_2; host_perform_sync(sync); for (gptr = MEM_TEST_GPA; gptr < MEM_TEST_GPA + MEM_TEST_SIZE; gptr += guest_page_size) { - uint64_t *vptr = (typeof(vptr))vm_gpa2hva(data, gptr, NULL); - uint64_t val = *vptr; + u64 *vptr = (typeof(vptr))vm_gpa2hva(data, gptr, NULL); + u64 val = *vptr; TEST_ASSERT(val == MEM_TEST_VAL_1, "Guest written values should read back correctly (is %"PRIu64" @ %"PRIx64")", @@ -790,21 +790,21 @@ static void test_memslot_rw_loop(struct vm_data *data, struct sync_area *sync) struct test_data { const char *name; - uint64_t mem_size; + u64 mem_size; void (*guest_code)(void); bool (*prepare)(struct vm_data *data, struct sync_area *sync, - uint64_t *maxslots); + u64 *maxslots); void (*loop)(struct vm_data *data, struct sync_area *sync); }; -static bool test_execute(int nslots, uint64_t *maxslots, +static bool test_execute(int nslots, u64 *maxslots, unsigned int maxtime, const struct test_data *tdata, - uint64_t *nloops, + u64 *nloops, struct timespec *slot_runtime, struct timespec *guest_runtime) { - uint64_t mem_size = tdata->mem_size ? : MEM_SIZE; + u64 mem_size = tdata->mem_size ? : MEM_SIZE; struct vm_data *data; struct sync_area *sync; struct timespec tstart; @@ -924,8 +924,8 @@ static void help(char *name, struct test_args *targs) static bool check_memory_sizes(void) { - uint32_t host_page_size = getpagesize(); - uint32_t guest_page_size = vm_guest_mode_params[VM_MODE_DEFAULT].page_size; + u32 host_page_size = getpagesize(); + u32 guest_page_size = vm_guest_mode_params[VM_MODE_DEFAULT].page_size; if (host_page_size > SZ_64K || guest_page_size > SZ_64K) { pr_info("Unsupported page size on host (0x%x) or guest (0x%x)\n", @@ -961,7 +961,7 @@ static bool check_memory_sizes(void) static bool parse_args(int argc, char *argv[], struct test_args *targs) { - uint32_t max_mem_slots; + u32 max_mem_slots; int opt; while ((opt = getopt(argc, argv, "hvdqs:f:e:l:r:")) != -1) { @@ -1040,8 +1040,8 @@ static bool parse_args(int argc, char *argv[], struct test_result { struct timespec slot_runtime, guest_runtime, iter_runtime; - int64_t slottimens, runtimens; - uint64_t nloops; + s64 slottimens, runtimens; + u64 nloops; }; static bool test_loop(const struct test_data *data, @@ -1049,7 +1049,7 @@ static bool test_loop(const struct test_data *data, struct test_result *rbestslottime, struct test_result *rbestruntime) { - uint64_t maxslots; + u64 maxslots; struct test_result result = {}; if (!test_execute(targs->nslots, &maxslots, targs->seconds, data, diff --git a/tools/testing/selftests/kvm/mmu_stress_test.c b/tools/testing/selftests/kvm/mmu_stress_test.c index 51c070556f3e..54d281419d31 100644 --- a/tools/testing/selftests/kvm/mmu_stress_test.c +++ b/tools/testing/selftests/kvm/mmu_stress_test.c @@ -20,19 +20,19 @@ static bool mprotect_ro_done; static bool all_vcpus_hit_ro_fault; -static void guest_code(uint64_t start_gpa, uint64_t end_gpa, uint64_t stride) +static void guest_code(u64 start_gpa, u64 end_gpa, u64 stride) { - uint64_t gpa; + gpa_t gpa; int i; for (i = 0; i < 2; i++) { for (gpa = start_gpa; gpa < end_gpa; gpa += stride) - vcpu_arch_put_guest(*((volatile uint64_t *)gpa), gpa); + vcpu_arch_put_guest(*((volatile u64 *)gpa), gpa); GUEST_SYNC(i); } for (gpa = start_gpa; gpa < end_gpa; gpa += stride) - *((volatile uint64_t *)gpa); + *((volatile u64 *)gpa); GUEST_SYNC(2); /* @@ -55,7 +55,7 @@ static void guest_code(uint64_t start_gpa, uint64_t end_gpa, uint64_t stride) #elif defined(__aarch64__) asm volatile("str %0, [%0]" :: "r" (gpa) : "memory"); #else - vcpu_arch_put_guest(*((volatile uint64_t *)gpa), gpa); + vcpu_arch_put_guest(*((volatile u64 *)gpa), gpa); #endif } while (!READ_ONCE(mprotect_ro_done) || !READ_ONCE(all_vcpus_hit_ro_fault)); @@ -68,7 +68,7 @@ static void guest_code(uint64_t start_gpa, uint64_t end_gpa, uint64_t stride) #endif for (gpa = start_gpa; gpa < end_gpa; gpa += stride) - vcpu_arch_put_guest(*((volatile uint64_t *)gpa), gpa); + vcpu_arch_put_guest(*((volatile u64 *)gpa), gpa); GUEST_SYNC(4); GUEST_ASSERT(0); @@ -76,8 +76,8 @@ static void guest_code(uint64_t start_gpa, uint64_t end_gpa, uint64_t stride) struct vcpu_info { struct kvm_vcpu *vcpu; - uint64_t start_gpa; - uint64_t end_gpa; + u64 start_gpa; + u64 end_gpa; }; static int nr_vcpus; @@ -203,10 +203,10 @@ static void *vcpu_worker(void *data) } static pthread_t *spawn_workers(struct kvm_vm *vm, struct kvm_vcpu **vcpus, - uint64_t start_gpa, uint64_t end_gpa) + u64 start_gpa, u64 end_gpa) { struct vcpu_info *info; - uint64_t gpa, nr_bytes; + gpa_t gpa, nr_bytes; pthread_t *threads; int i; @@ -217,7 +217,7 @@ static pthread_t *spawn_workers(struct kvm_vm *vm, struct kvm_vcpu **vcpus, TEST_ASSERT(info, "Failed to allocate vCPU gpa ranges"); nr_bytes = ((end_gpa - start_gpa) / nr_vcpus) & - ~((uint64_t)vm->page_size - 1); + ~((u64)vm->page_size - 1); TEST_ASSERT(nr_bytes, "C'mon, no way you have %d CPUs", nr_vcpus); for (i = 0, gpa = start_gpa; i < nr_vcpus; i++, gpa += nr_bytes) { @@ -278,11 +278,11 @@ int main(int argc, char *argv[]) * just below the 4gb boundary. This test could create memory at * 1gb-3gb,but it's simpler to skip straight to 4gb. */ - const uint64_t start_gpa = SZ_4G; + const u64 start_gpa = SZ_4G; const int first_slot = 1; struct timespec time_start, time_run1, time_reset, time_run2, time_ro, time_rw; - uint64_t max_gpa, gpa, slot_size, max_mem, i; + u64 max_gpa, gpa, slot_size, max_mem, i; int max_slots, slot, opt, fd; bool hugepages = false; struct kvm_vcpu **vcpus; @@ -347,7 +347,7 @@ int main(int argc, char *argv[]) /* Pre-fault the memory to avoid taking mmap_sem on guest page faults. */ for (i = 0; i < slot_size; i += vm->page_size) - ((uint8_t *)mem)[i] = 0xaa; + ((u8 *)mem)[i] = 0xaa; gpa = 0; for (slot = first_slot; slot < max_slots; slot++) { diff --git a/tools/testing/selftests/kvm/pre_fault_memory_test.c b/tools/testing/selftests/kvm/pre_fault_memory_test.c index f3de0386ba7b..fcb57fd034e6 100644 --- a/tools/testing/selftests/kvm/pre_fault_memory_test.c +++ b/tools/testing/selftests/kvm/pre_fault_memory_test.c @@ -17,13 +17,13 @@ #define TEST_NPAGES (TEST_SIZE / PAGE_SIZE) #define TEST_SLOT 10 -static void guest_code(uint64_t base_gva) +static void guest_code(u64 base_gva) { - volatile uint64_t val __used; + volatile u64 val __used; int i; for (i = 0; i < TEST_NPAGES; i++) { - uint64_t *src = (uint64_t *)(base_gva + i * PAGE_SIZE); + u64 *src = (u64 *)(base_gva + i * PAGE_SIZE); val = *src; } @@ -33,8 +33,8 @@ static void guest_code(uint64_t base_gva) struct slot_worker_data { struct kvm_vm *vm; - u64 gpa; - uint32_t flags; + gpa_t gpa; + u32 flags; bool worker_ready; bool prefault_ready; bool recreate_slot; @@ -161,7 +161,7 @@ static void pre_fault_memory(struct kvm_vcpu *vcpu, u64 base_gpa, u64 offset, static void __test_pre_fault_memory(unsigned long vm_type, bool private) { - uint64_t gpa, gva, alignment, guest_page_size; + gpa_t gpa, gva, alignment, guest_page_size; const struct vm_shape shape = { .mode = VM_MODE_DEFAULT, .type = vm_type, diff --git a/tools/testing/selftests/kvm/riscv/arch_timer.c b/tools/testing/selftests/kvm/riscv/arch_timer.c index f962fefc48fa..d67c918ee310 100644 --- a/tools/testing/selftests/kvm/riscv/arch_timer.c +++ b/tools/testing/selftests/kvm/riscv/arch_timer.c @@ -17,9 +17,9 @@ static int timer_irq = IRQ_S_TIMER; static void guest_irq_handler(struct pt_regs *regs) { - uint64_t xcnt, xcnt_diff_us, cmp; + u64 xcnt, xcnt_diff_us, cmp; unsigned int intid = regs->cause & ~CAUSE_IRQ_FLAG; - uint32_t cpu = guest_get_vcpuid(); + u32 cpu = guest_get_vcpuid(); struct test_vcpu_shared_data *shared_data = &vcpu_shared_data[cpu]; timer_irq_disable(); @@ -40,7 +40,7 @@ static void guest_irq_handler(struct pt_regs *regs) static void guest_run(struct test_vcpu_shared_data *shared_data) { - uint32_t irq_iter, config_iter; + u32 irq_iter, config_iter; shared_data->nr_iter = 0; shared_data->guest_stage = 0; @@ -66,7 +66,7 @@ static void guest_run(struct test_vcpu_shared_data *shared_data) static void guest_code(void) { - uint32_t cpu = guest_get_vcpuid(); + u32 cpu = guest_get_vcpuid(); struct test_vcpu_shared_data *shared_data = &vcpu_shared_data[cpu]; timer_irq_disable(); diff --git a/tools/testing/selftests/kvm/riscv/ebreak_test.c b/tools/testing/selftests/kvm/riscv/ebreak_test.c index 739d17befb5a..3f44b045a22e 100644 --- a/tools/testing/selftests/kvm/riscv/ebreak_test.c +++ b/tools/testing/selftests/kvm/riscv/ebreak_test.c @@ -8,10 +8,10 @@ #include "kvm_util.h" #include "ucall_common.h" -#define LABEL_ADDRESS(v) ((uint64_t)&(v)) +#define LABEL_ADDRESS(v) ((u64)&(v)) extern unsigned char sw_bp_1, sw_bp_2; -static uint64_t sw_bp_addr; +static u64 sw_bp_addr; static void guest_code(void) { @@ -37,7 +37,7 @@ int main(void) { struct kvm_vm *vm; struct kvm_vcpu *vcpu; - uint64_t pc; + u64 pc; struct kvm_guest_debug debug = { .control = KVM_GUESTDBG_ENABLE, }; diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c index 8d6b951434eb..8d6fdb5d38b8 100644 --- a/tools/testing/selftests/kvm/riscv/get-reg-list.c +++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c @@ -162,7 +162,7 @@ bool check_reject_set(int err) } static int override_vector_reg_size(struct kvm_vcpu *vcpu, struct vcpu_reg_sublist *s, - uint64_t feature) + u64 feature) { unsigned long vlenb_reg = 0; int rc; @@ -197,7 +197,7 @@ void finalize_vcpu(struct kvm_vcpu *vcpu, struct vcpu_reg_list *c) { unsigned long isa_ext_state[KVM_RISCV_ISA_EXT_MAX] = { 0 }; struct vcpu_reg_sublist *s; - uint64_t feature; + u64 feature; int rc; for (int i = 0; i < KVM_RISCV_ISA_EXT_MAX; i++) diff --git a/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c b/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c index cec1621ace23..e56a3dd6a51e 100644 --- a/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c +++ b/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c @@ -24,7 +24,7 @@ union sbi_pmu_ctr_info ctrinfo_arr[RISCV_MAX_PMU_COUNTERS]; /* Snapshot shared memory data */ #define PMU_SNAPSHOT_GPA_BASE BIT(30) static void *snapshot_gva; -static vm_paddr_t snapshot_gpa; +static gpa_t snapshot_gpa; static int vcpu_shared_irq_count; static int counter_in_use; @@ -86,7 +86,7 @@ unsigned long pmu_csr_read_num(int csr_num) #undef switchcase_csr_read } -static inline void dummy_func_loop(uint64_t iter) +static inline void dummy_func_loop(u64 iter) { int i = 0; @@ -259,7 +259,7 @@ static inline void verify_sbi_requirement_assert(void) __GUEST_ASSERT(0, "SBI implementation version doesn't support PMU Snapshot"); } -static void snapshot_set_shmem(vm_paddr_t gpa, unsigned long flags) +static void snapshot_set_shmem(gpa_t gpa, unsigned long flags) { unsigned long lo = (unsigned long)gpa; #if __riscv_xlen == 32 @@ -610,7 +610,7 @@ static void test_vm_setup_snapshot_mem(struct kvm_vm *vm, struct kvm_vcpu *vcpu) virt_map(vm, PMU_SNAPSHOT_GPA_BASE, PMU_SNAPSHOT_GPA_BASE, 1); snapshot_gva = (void *)(PMU_SNAPSHOT_GPA_BASE); - snapshot_gpa = addr_gva2gpa(vcpu->vm, (vm_vaddr_t)snapshot_gva); + snapshot_gpa = addr_gva2gpa(vcpu->vm, (gva_t)snapshot_gva); sync_global_to_guest(vcpu->vm, snapshot_gva); sync_global_to_guest(vcpu->vm, snapshot_gpa); } diff --git a/tools/testing/selftests/kvm/s390/debug_test.c b/tools/testing/selftests/kvm/s390/debug_test.c index ad8095968601..751c61c0f056 100644 --- a/tools/testing/selftests/kvm/s390/debug_test.c +++ b/tools/testing/selftests/kvm/s390/debug_test.c @@ -17,7 +17,7 @@ asm("int_handler:\n" "j .\n"); static struct kvm_vm *test_step_int_1(struct kvm_vcpu **vcpu, void *guest_code, - size_t new_psw_off, uint64_t *new_psw) + size_t new_psw_off, u64 *new_psw) { struct kvm_guest_debug debug = {}; struct kvm_regs regs; @@ -27,7 +27,7 @@ static struct kvm_vm *test_step_int_1(struct kvm_vcpu **vcpu, void *guest_code, vm = vm_create_with_one_vcpu(vcpu, guest_code); lowcore = addr_gpa2hva(vm, 0); new_psw[0] = (*vcpu)->run->psw_mask; - new_psw[1] = (uint64_t)int_handler; + new_psw[1] = (u64)int_handler; memcpy(lowcore + new_psw_off, new_psw, 16); vcpu_regs_get(*vcpu, ®s); regs.gprs[2] = -1; @@ -42,7 +42,7 @@ static struct kvm_vm *test_step_int_1(struct kvm_vcpu **vcpu, void *guest_code, static void test_step_int(void *guest_code, size_t new_psw_off) { struct kvm_vcpu *vcpu; - uint64_t new_psw[2]; + u64 new_psw[2]; struct kvm_vm *vm; vm = test_step_int_1(&vcpu, guest_code, new_psw_off, new_psw); @@ -79,7 +79,7 @@ static void test_step_pgm_diag(void) .u.pgm.code = PGM_SPECIFICATION, }; struct kvm_vcpu *vcpu; - uint64_t new_psw[2]; + u64 new_psw[2]; struct kvm_vm *vm; vm = test_step_int_1(&vcpu, test_step_pgm_diag_guest_code, diff --git a/tools/testing/selftests/kvm/s390/irq_routing.c b/tools/testing/selftests/kvm/s390/irq_routing.c index 7819a0af19a8..f3839284ac08 100644 --- a/tools/testing/selftests/kvm/s390/irq_routing.c +++ b/tools/testing/selftests/kvm/s390/irq_routing.c @@ -27,7 +27,7 @@ static void test(void) struct kvm_irq_routing *routing; struct kvm_vcpu *vcpu; struct kvm_vm *vm; - vm_paddr_t mem; + gpa_t mem; int ret; struct kvm_irq_routing_entry ue = { diff --git a/tools/testing/selftests/kvm/s390/memop.c b/tools/testing/selftests/kvm/s390/memop.c index 4374b4cd2a80..0244848621b3 100644 --- a/tools/testing/selftests/kvm/s390/memop.c +++ b/tools/testing/selftests/kvm/s390/memop.c @@ -34,7 +34,7 @@ enum mop_access_mode { struct mop_desc { uintptr_t gaddr; uintptr_t gaddr_v; - uint64_t set_flags; + u64 set_flags; unsigned int f_check : 1; unsigned int f_inject : 1; unsigned int f_key : 1; @@ -42,19 +42,19 @@ struct mop_desc { unsigned int _set_flags : 1; unsigned int _sida_offset : 1; unsigned int _ar : 1; - uint32_t size; + u32 size; enum mop_target target; enum mop_access_mode mode; void *buf; - uint32_t sida_offset; + u32 sida_offset; void *old; - uint8_t old_value[16]; + u8 old_value[16]; bool *cmpxchg_success; - uint8_t ar; - uint8_t key; + u8 ar; + u8 key; }; -const uint8_t NO_KEY = 0xff; +const u8 NO_KEY = 0xff; static struct kvm_s390_mem_op ksmo_from_desc(struct mop_desc *desc) { @@ -85,7 +85,7 @@ static struct kvm_s390_mem_op ksmo_from_desc(struct mop_desc *desc) ksmo.op = KVM_S390_MEMOP_ABSOLUTE_WRITE; if (desc->mode == CMPXCHG) { ksmo.op = KVM_S390_MEMOP_ABSOLUTE_CMPXCHG; - ksmo.old_addr = (uint64_t)desc->old; + ksmo.old_addr = (u64)desc->old; memcpy(desc->old_value, desc->old, desc->size); } break; @@ -230,8 +230,8 @@ static void memop_ioctl(struct test_info info, struct kvm_s390_mem_op *ksmo, #define CR0_FETCH_PROTECTION_OVERRIDE (1UL << (63 - 38)) #define CR0_STORAGE_PROTECTION_OVERRIDE (1UL << (63 - 39)) -static uint8_t __aligned(PAGE_SIZE) mem1[65536]; -static uint8_t __aligned(PAGE_SIZE) mem2[65536]; +static u8 __aligned(PAGE_SIZE) mem1[65536]; +static u8 __aligned(PAGE_SIZE) mem2[65536]; struct test_default { struct kvm_vm *kvm_vm; @@ -296,7 +296,7 @@ static void prepare_mem12(void) TEST_ASSERT(!memcmp(p1, p2, size), "Memory contents do not match!") static void default_write_read(struct test_info copy_cpu, struct test_info mop_cpu, - enum mop_target mop_target, uint32_t size, uint8_t key) + enum mop_target mop_target, u32 size, u8 key) { prepare_mem12(); CHECK_N_DO(MOP, mop_cpu, mop_target, WRITE, mem1, size, @@ -308,7 +308,7 @@ static void default_write_read(struct test_info copy_cpu, struct test_info mop_c } static void default_read(struct test_info copy_cpu, struct test_info mop_cpu, - enum mop_target mop_target, uint32_t size, uint8_t key) + enum mop_target mop_target, u32 size, u8 key) { prepare_mem12(); CHECK_N_DO(MOP, mop_cpu, mop_target, WRITE, mem1, size, GADDR_V(mem1)); @@ -318,12 +318,12 @@ static void default_read(struct test_info copy_cpu, struct test_info mop_cpu, ASSERT_MEM_EQ(mem1, mem2, size); } -static void default_cmpxchg(struct test_default *test, uint8_t key) +static void default_cmpxchg(struct test_default *test, u8 key) { for (int size = 1; size <= 16; size *= 2) { for (int offset = 0; offset < 16; offset += size) { - uint8_t __aligned(16) new[16] = {}; - uint8_t __aligned(16) old[16]; + u8 __aligned(16) new[16] = {}; + u8 __aligned(16) old[16]; bool succ; prepare_mem12(); @@ -400,7 +400,7 @@ static void test_copy_access_register(void) kvm_vm_free(t.kvm_vm); } -static void set_storage_key_range(void *addr, size_t len, uint8_t key) +static void set_storage_key_range(void *addr, size_t len, u8 key) { uintptr_t _addr, abs, i; int not_mapped = 0; @@ -483,13 +483,13 @@ static __uint128_t cut_to_size(int size, __uint128_t val) { switch (size) { case 1: - return (uint8_t)val; + return (u8)val; case 2: - return (uint16_t)val; + return (u16)val; case 4: - return (uint32_t)val; + return (u32)val; case 8: - return (uint64_t)val; + return (u64)val; case 16: return val; } @@ -501,10 +501,10 @@ static bool popcount_eq(__uint128_t a, __uint128_t b) { unsigned int count_a, count_b; - count_a = __builtin_popcountl((uint64_t)(a >> 64)) + - __builtin_popcountl((uint64_t)a); - count_b = __builtin_popcountl((uint64_t)(b >> 64)) + - __builtin_popcountl((uint64_t)b); + count_a = __builtin_popcountl((u64)(a >> 64)) + + __builtin_popcountl((u64)a); + count_b = __builtin_popcountl((u64)(b >> 64)) + + __builtin_popcountl((u64)b); return count_a == count_b; } @@ -553,7 +553,7 @@ static __uint128_t permutate_bits(bool guest, int i, int size, __uint128_t old) if (swap) { int i, j; __uint128_t new; - uint8_t byte0, byte1; + u8 byte0, byte1; rand = rand * 3 + 1; i = rand % size; @@ -585,28 +585,28 @@ static bool _cmpxchg(int size, void *target, __uint128_t *old_addr, __uint128_t switch (size) { case 4: { - uint32_t old = *old_addr; + u32 old = *old_addr; asm volatile ("cs %[old],%[new],%[address]" : [old] "+d" (old), - [address] "+Q" (*(uint32_t *)(target)) - : [new] "d" ((uint32_t)new) + [address] "+Q" (*(u32 *)(target)) + : [new] "d" ((u32)new) : "cc" ); - ret = old == (uint32_t)*old_addr; + ret = old == (u32)*old_addr; *old_addr = old; return ret; } case 8: { - uint64_t old = *old_addr; + u64 old = *old_addr; asm volatile ("csg %[old],%[new],%[address]" : [old] "+d" (old), - [address] "+Q" (*(uint64_t *)(target)) - : [new] "d" ((uint64_t)new) + [address] "+Q" (*(u64 *)(target)) + : [new] "d" ((u64)new) : "cc" ); - ret = old == (uint64_t)*old_addr; + ret = old == (u64)*old_addr; *old_addr = old; return ret; } @@ -811,10 +811,10 @@ static void test_errors_cmpxchg_key(void) static void test_termination(void) { struct test_default t = test_default_init(guest_error_key); - uint64_t prefix; - uint64_t teid; - uint64_t teid_mask = BIT(63 - 56) | BIT(63 - 60) | BIT(63 - 61); - uint64_t psw[2]; + u64 prefix; + u64 teid; + u64 teid_mask = BIT(63 - 56) | BIT(63 - 60) | BIT(63 - 61); + u64 psw[2]; HOST_SYNC(t.vcpu, STAGE_INITED); HOST_SYNC(t.vcpu, STAGE_SKEYS_SET); @@ -855,7 +855,7 @@ static void test_errors_key_storage_prot_override(void) kvm_vm_free(t.kvm_vm); } -const uint64_t last_page_addr = -PAGE_SIZE; +const u64 last_page_addr = -PAGE_SIZE; static void guest_copy_key_fetch_prot_override(void) { @@ -878,10 +878,10 @@ static void guest_copy_key_fetch_prot_override(void) static void test_copy_key_fetch_prot_override(void) { struct test_default t = test_default_init(guest_copy_key_fetch_prot_override); - vm_vaddr_t guest_0_page, guest_last_page; + gva_t guest_0_page, guest_last_page; - guest_0_page = vm_vaddr_alloc(t.kvm_vm, PAGE_SIZE, 0); - guest_last_page = vm_vaddr_alloc(t.kvm_vm, PAGE_SIZE, last_page_addr); + guest_0_page = vm_alloc(t.kvm_vm, PAGE_SIZE, 0); + guest_last_page = vm_alloc(t.kvm_vm, PAGE_SIZE, last_page_addr); if (guest_0_page != 0 || guest_last_page != last_page_addr) { print_skip("did not allocate guest pages at required positions"); goto out; @@ -917,10 +917,10 @@ out: static void test_errors_key_fetch_prot_override_not_enabled(void) { struct test_default t = test_default_init(guest_copy_key_fetch_prot_override); - vm_vaddr_t guest_0_page, guest_last_page; + gva_t guest_0_page, guest_last_page; - guest_0_page = vm_vaddr_alloc(t.kvm_vm, PAGE_SIZE, 0); - guest_last_page = vm_vaddr_alloc(t.kvm_vm, PAGE_SIZE, last_page_addr); + guest_0_page = vm_alloc(t.kvm_vm, PAGE_SIZE, 0); + guest_last_page = vm_alloc(t.kvm_vm, PAGE_SIZE, last_page_addr); if (guest_0_page != 0 || guest_last_page != last_page_addr) { print_skip("did not allocate guest pages at required positions"); goto out; @@ -938,10 +938,10 @@ out: static void test_errors_key_fetch_prot_override_enabled(void) { struct test_default t = test_default_init(guest_copy_key_fetch_prot_override); - vm_vaddr_t guest_0_page, guest_last_page; + gva_t guest_0_page, guest_last_page; - guest_0_page = vm_vaddr_alloc(t.kvm_vm, PAGE_SIZE, 0); - guest_last_page = vm_vaddr_alloc(t.kvm_vm, PAGE_SIZE, last_page_addr); + guest_0_page = vm_alloc(t.kvm_vm, PAGE_SIZE, 0); + guest_last_page = vm_alloc(t.kvm_vm, PAGE_SIZE, last_page_addr); if (guest_0_page != 0 || guest_last_page != last_page_addr) { print_skip("did not allocate guest pages at required positions"); goto out; diff --git a/tools/testing/selftests/kvm/s390/resets.c b/tools/testing/selftests/kvm/s390/resets.c index b58f75b381e5..e3c7a2f148f9 100644 --- a/tools/testing/selftests/kvm/s390/resets.c +++ b/tools/testing/selftests/kvm/s390/resets.c @@ -20,7 +20,7 @@ struct kvm_s390_irq buf[ARBITRARY_NON_ZERO_VCPU_ID + LOCAL_IRQS]; -static uint8_t regs_null[512]; +static u8 regs_null[512]; static void guest_code_initial(void) { @@ -57,9 +57,9 @@ static void guest_code_initial(void) ); } -static void test_one_reg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t value) +static void test_one_reg(struct kvm_vcpu *vcpu, u64 id, u64 value) { - uint64_t eval_reg; + u64 eval_reg; eval_reg = vcpu_get_reg(vcpu, id); TEST_ASSERT(eval_reg == value, "value == 0x%lx", value); diff --git a/tools/testing/selftests/kvm/s390/shared_zeropage_test.c b/tools/testing/selftests/kvm/s390/shared_zeropage_test.c index bba0d9a6dcc8..a9e5a01200b8 100644 --- a/tools/testing/selftests/kvm/s390/shared_zeropage_test.c +++ b/tools/testing/selftests/kvm/s390/shared_zeropage_test.c @@ -13,7 +13,7 @@ #include "kselftest.h" #include "ucall_common.h" -static void set_storage_key(void *addr, uint8_t skey) +static void set_storage_key(void *addr, u8 skey) { asm volatile("sske %0,%1" : : "d" (skey), "a" (addr)); } diff --git a/tools/testing/selftests/kvm/s390/tprot.c b/tools/testing/selftests/kvm/s390/tprot.c index 12d5e1cb62e3..8054d2b178f0 100644 --- a/tools/testing/selftests/kvm/s390/tprot.c +++ b/tools/testing/selftests/kvm/s390/tprot.c @@ -14,12 +14,12 @@ #define CR0_FETCH_PROTECTION_OVERRIDE (1UL << (63 - 38)) #define CR0_STORAGE_PROTECTION_OVERRIDE (1UL << (63 - 39)) -static __aligned(PAGE_SIZE) uint8_t pages[2][PAGE_SIZE]; -static uint8_t *const page_store_prot = pages[0]; -static uint8_t *const page_fetch_prot = pages[1]; +static __aligned(PAGE_SIZE) u8 pages[2][PAGE_SIZE]; +static u8 *const page_store_prot = pages[0]; +static u8 *const page_fetch_prot = pages[1]; /* Nonzero return value indicates that address not mapped */ -static int set_storage_key(void *addr, uint8_t key) +static int set_storage_key(void *addr, u8 key) { int not_mapped = 0; @@ -44,9 +44,9 @@ enum permission { TRANSL_UNAVAIL = 3, }; -static enum permission test_protection(void *addr, uint8_t key) +static enum permission test_protection(void *addr, u8 key) { - uint64_t mask; + u64 mask; asm volatile ( "tprot %[addr], 0(%[key])\n" @@ -72,7 +72,7 @@ enum stage { struct test { enum stage stage; void *addr; - uint8_t key; + u8 key; enum permission expected; } tests[] = { /* @@ -146,7 +146,7 @@ static enum stage perform_next_stage(int *i, bool mapped_0) /* * Some fetch protection override tests require that page 0 * be mapped, however, when the hosts tries to map that page via - * vm_vaddr_alloc, it may happen that some other page gets mapped + * vm_alloc, it may happen that some other page gets mapped * instead. * In order to skip these tests we detect this inside the guest */ @@ -207,7 +207,7 @@ int main(int argc, char *argv[]) struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct kvm_run *run; - vm_vaddr_t guest_0_page; + gva_t guest_0_page; ksft_print_header(); ksft_set_plan(STAGE_END); @@ -216,10 +216,10 @@ int main(int argc, char *argv[]) run = vcpu->run; HOST_SYNC(vcpu, STAGE_INIT_SIMPLE); - mprotect(addr_gva2hva(vm, (vm_vaddr_t)pages), PAGE_SIZE * 2, PROT_READ); + mprotect(addr_gva2hva(vm, (gva_t)pages), PAGE_SIZE * 2, PROT_READ); HOST_SYNC(vcpu, TEST_SIMPLE); - guest_0_page = vm_vaddr_alloc(vm, PAGE_SIZE, 0); + guest_0_page = vm_alloc(vm, PAGE_SIZE, 0); if (guest_0_page != 0) { /* Use NO_TAP so we don't get a PASS print */ HOST_SYNC_NO_TAP(vcpu, STAGE_INIT_FETCH_PROT_OVERRIDE); @@ -229,7 +229,7 @@ int main(int argc, char *argv[]) HOST_SYNC(vcpu, STAGE_INIT_FETCH_PROT_OVERRIDE); } if (guest_0_page == 0) - mprotect(addr_gva2hva(vm, (vm_vaddr_t)0), PAGE_SIZE, PROT_READ); + mprotect(addr_gva2hva(vm, (gva_t)0), PAGE_SIZE, PROT_READ); run->s.regs.crs[0] |= CR0_FETCH_PROTECTION_OVERRIDE; run->kvm_dirty_regs = KVM_SYNC_CRS; HOST_SYNC(vcpu, TEST_FETCH_PROT_OVERRIDE); diff --git a/tools/testing/selftests/kvm/s390/ucontrol_test.c b/tools/testing/selftests/kvm/s390/ucontrol_test.c index 50bc1c38225a..b8c6f37b53e0 100644 --- a/tools/testing/selftests/kvm/s390/ucontrol_test.c +++ b/tools/testing/selftests/kvm/s390/ucontrol_test.c @@ -111,7 +111,7 @@ FIXTURE(uc_kvm) uintptr_t base_hva; uintptr_t code_hva; int kvm_run_size; - vm_paddr_t pgd; + gpa_t pgd; void *vm_mem; int vcpu_fd; int kvm_fd; @@ -269,7 +269,7 @@ TEST(uc_cap_hpage) } /* calculate host virtual addr from guest physical addr */ -static void *gpa2hva(FIXTURE_DATA(uc_kvm) *self, u64 gpa) +static void *gpa2hva(FIXTURE_DATA(uc_kvm) *self, gpa_t gpa) { return (void *)(self->base_hva - self->base_gpa + gpa); } @@ -571,7 +571,7 @@ TEST_F(uc_kvm, uc_skey) { struct kvm_s390_sie_block *sie_block = self->sie_block; struct kvm_sync_regs *sync_regs = &self->run->s.regs; - u64 test_vaddr = VM_MEM_SIZE - (SZ_1M / 2); + u64 test_gva = VM_MEM_SIZE - (SZ_1M / 2); struct kvm_run *run = self->run; const u8 skeyvalue = 0x34; @@ -583,7 +583,7 @@ TEST_F(uc_kvm, uc_skey) /* set register content for test_skey_asm to access not mapped memory */ sync_regs->gprs[1] = skeyvalue; sync_regs->gprs[5] = self->base_gpa; - sync_regs->gprs[6] = test_vaddr; + sync_regs->gprs[6] = test_gva; run->kvm_dirty_regs |= KVM_SYNC_GPRS; /* DAT disabled + 64 bit mode */ diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c index a398dc3a8c4b..9b919a231c93 100644 --- a/tools/testing/selftests/kvm/set_memory_region_test.c +++ b/tools/testing/selftests/kvm/set_memory_region_test.c @@ -30,19 +30,19 @@ #define MEM_REGION_GPA 0xc0000000 #define MEM_REGION_SLOT 10 -static const uint64_t MMIO_VAL = 0xbeefull; +static const u64 MMIO_VAL = 0xbeefull; -extern const uint64_t final_rip_start; -extern const uint64_t final_rip_end; +extern const u64 final_rip_start; +extern const u64 final_rip_end; static sem_t vcpu_ready; -static inline uint64_t guest_spin_on_val(uint64_t spin_val) +static inline u64 guest_spin_on_val(u64 spin_val) { - uint64_t val; + u64 val; do { - val = READ_ONCE(*((uint64_t *)MEM_REGION_GPA)); + val = READ_ONCE(*((u64 *)MEM_REGION_GPA)); } while (val == spin_val); GUEST_SYNC(0); @@ -54,7 +54,7 @@ static void *vcpu_worker(void *data) struct kvm_vcpu *vcpu = data; struct kvm_run *run = vcpu->run; struct ucall uc; - uint64_t cmd; + u64 cmd; /* * Loop until the guest is done. Re-enter the guest on all MMIO exits, @@ -111,8 +111,8 @@ static struct kvm_vm *spawn_vm(struct kvm_vcpu **vcpu, pthread_t *vcpu_thread, void *guest_code) { struct kvm_vm *vm; - uint64_t *hva; - uint64_t gpa; + u64 *hva; + gpa_t gpa; vm = vm_create_with_one_vcpu(vcpu, guest_code); @@ -144,7 +144,7 @@ static struct kvm_vm *spawn_vm(struct kvm_vcpu **vcpu, pthread_t *vcpu_thread, static void guest_code_move_memory_region(void) { - uint64_t val; + u64 val; GUEST_SYNC(0); @@ -180,7 +180,7 @@ static void test_move_memory_region(bool disable_slot_zap_quirk) pthread_t vcpu_thread; struct kvm_vcpu *vcpu; struct kvm_vm *vm; - uint64_t *hva; + u64 *hva; vm = spawn_vm(&vcpu, &vcpu_thread, guest_code_move_memory_region); @@ -224,7 +224,7 @@ static void test_move_memory_region(bool disable_slot_zap_quirk) static void guest_code_delete_memory_region(void) { struct desc_ptr idt; - uint64_t val; + u64 val; /* * Clobber the IDT so that a #PF due to the memory region being deleted @@ -345,8 +345,8 @@ static void test_zero_memory_regions(void) static void test_invalid_memory_region_flags(void) { - uint32_t supported_flags = KVM_MEM_LOG_DIRTY_PAGES; - const uint32_t v2_only_flags = KVM_MEM_GUEST_MEMFD; + u32 supported_flags = KVM_MEM_LOG_DIRTY_PAGES; + const u32 v2_only_flags = KVM_MEM_GUEST_MEMFD; struct kvm_vm *vm; int r, i; @@ -410,8 +410,8 @@ static void test_add_max_memory_regions(void) { int ret; struct kvm_vm *vm; - uint32_t max_mem_slots; - uint32_t slot; + u32 max_mem_slots; + u32 slot; void *mem, *mem_aligned, *mem_extra; size_t alignment = 1; @@ -434,16 +434,16 @@ static void test_add_max_memory_regions(void) for (slot = 0; slot < max_mem_slots; slot++) vm_set_user_memory_region(vm, slot, 0, - ((uint64_t)slot * MEM_REGION_SIZE), + ((u64)slot * MEM_REGION_SIZE), MEM_REGION_SIZE, - mem_aligned + (uint64_t)slot * MEM_REGION_SIZE); + mem_aligned + (u64)slot * MEM_REGION_SIZE); /* Check it cannot be added memory slots beyond the limit */ mem_extra = kvm_mmap(MEM_REGION_SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1); ret = __vm_set_user_memory_region(vm, max_mem_slots, 0, - (uint64_t)max_mem_slots * MEM_REGION_SIZE, + (u64)max_mem_slots * MEM_REGION_SIZE, MEM_REGION_SIZE, mem_extra); TEST_ASSERT(ret == -1 && errno == EINVAL, "Adding one more memory slot should fail with EINVAL"); @@ -556,7 +556,7 @@ static void guest_code_mmio_during_vectoring(void) set_idt(&idt_desc); /* Generate a #GP by dereferencing a non-canonical address */ - *((uint8_t *)NONCANONICAL) = 0x1; + *((u8 *)NONCANONICAL) = 0x1; GUEST_ASSERT(0); } diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c index efe56a10d13e..7df2bc8eec02 100644 --- a/tools/testing/selftests/kvm/steal_time.c +++ b/tools/testing/selftests/kvm/steal_time.c @@ -25,7 +25,7 @@ #define ST_GPA_BASE (1 << 30) static void *st_gva[NR_VCPUS]; -static uint64_t guest_stolen_time[NR_VCPUS]; +static u64 guest_stolen_time[NR_VCPUS]; #if defined(__x86_64__) @@ -42,9 +42,9 @@ static void check_status(struct kvm_steal_time *st) static void guest_code(int cpu) { struct kvm_steal_time *st = st_gva[cpu]; - uint32_t version; + u32 version; - GUEST_ASSERT_EQ(rdmsr(MSR_KVM_STEAL_TIME), ((uint64_t)st_gva[cpu] | KVM_MSR_ENABLED)); + GUEST_ASSERT_EQ(rdmsr(MSR_KVM_STEAL_TIME), ((u64)st_gva[cpu] | KVM_MSR_ENABLED)); memset(st, 0, sizeof(*st)); GUEST_SYNC(0); @@ -67,7 +67,7 @@ static bool is_steal_time_supported(struct kvm_vcpu *vcpu) return kvm_cpu_has(X86_FEATURE_KVM_STEAL_TIME); } -static void steal_time_init(struct kvm_vcpu *vcpu, uint32_t i) +static void steal_time_init(struct kvm_vcpu *vcpu, u32 i) { /* ST_GPA_BASE is identity mapped */ st_gva[i] = (void *)(ST_GPA_BASE + i * STEAL_TIME_SIZE); @@ -76,7 +76,7 @@ static void steal_time_init(struct kvm_vcpu *vcpu, uint32_t i) vcpu_set_msr(vcpu, MSR_KVM_STEAL_TIME, (ulong)st_gva[i] | KVM_MSR_ENABLED); } -static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpu_idx) +static void steal_time_dump(struct kvm_vm *vm, u32 vcpu_idx) { struct kvm_steal_time *st = addr_gva2hva(vm, (ulong)st_gva[vcpu_idx]); @@ -118,12 +118,12 @@ static void check_steal_time_uapi(void) #define PV_TIME_ST 0xc5000021 struct st_time { - uint32_t rev; - uint32_t attr; - uint64_t st_time; + u32 rev; + u32 attr; + u64 st_time; }; -static int64_t smccc(uint32_t func, uint64_t arg) +static s64 smccc(u32 func, u64 arg) { struct arm_smccc_res res; @@ -140,7 +140,7 @@ static void check_status(struct st_time *st) static void guest_code(int cpu) { struct st_time *st; - int64_t status; + s64 status; status = smccc(SMCCC_ARCH_FEATURES, PV_TIME_FEATURES); GUEST_ASSERT_EQ(status, 0); @@ -175,15 +175,15 @@ static bool is_steal_time_supported(struct kvm_vcpu *vcpu) return !__vcpu_ioctl(vcpu, KVM_HAS_DEVICE_ATTR, &dev); } -static void steal_time_init(struct kvm_vcpu *vcpu, uint32_t i) +static void steal_time_init(struct kvm_vcpu *vcpu, u32 i) { struct kvm_vm *vm = vcpu->vm; - uint64_t st_ipa; + u64 st_ipa; struct kvm_device_attr dev = { .group = KVM_ARM_VCPU_PVTIME_CTRL, .attr = KVM_ARM_VCPU_PVTIME_IPA, - .addr = (uint64_t)&st_ipa, + .addr = (u64)&st_ipa, }; /* ST_GPA_BASE is identity mapped */ @@ -194,7 +194,7 @@ static void steal_time_init(struct kvm_vcpu *vcpu, uint32_t i) vcpu_ioctl(vcpu, KVM_SET_DEVICE_ATTR, &dev); } -static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpu_idx) +static void steal_time_dump(struct kvm_vm *vm, u32 vcpu_idx) { struct st_time *st = addr_gva2hva(vm, (ulong)st_gva[vcpu_idx]); @@ -208,7 +208,7 @@ static void check_steal_time_uapi(void) { struct kvm_vm *vm; struct kvm_vcpu *vcpu; - uint64_t st_ipa; + u64 st_ipa; int ret; vm = vm_create_with_one_vcpu(&vcpu, NULL); @@ -216,7 +216,7 @@ static void check_steal_time_uapi(void) struct kvm_device_attr dev = { .group = KVM_ARM_VCPU_PVTIME_CTRL, .attr = KVM_ARM_VCPU_PVTIME_IPA, - .addr = (uint64_t)&st_ipa, + .addr = (u64)&st_ipa, }; vcpu_ioctl(vcpu, KVM_HAS_DEVICE_ATTR, &dev); @@ -239,17 +239,17 @@ static void check_steal_time_uapi(void) /* SBI STA shmem must have 64-byte alignment */ #define STEAL_TIME_SIZE ((sizeof(struct sta_struct) + 63) & ~63) -static vm_paddr_t st_gpa[NR_VCPUS]; +static gpa_t st_gpa[NR_VCPUS]; struct sta_struct { - uint32_t sequence; - uint32_t flags; - uint64_t steal; - uint8_t preempted; - uint8_t pad[47]; + u32 sequence; + u32 flags; + u64 steal; + u8 preempted; + u8 pad[47]; } __packed; -static void sta_set_shmem(vm_paddr_t gpa, unsigned long flags) +static void sta_set_shmem(gpa_t gpa, unsigned long flags) { unsigned long lo = (unsigned long)gpa; #if __riscv_xlen == 32 @@ -272,7 +272,7 @@ static void check_status(struct sta_struct *st) static void guest_code(int cpu) { struct sta_struct *st = st_gva[cpu]; - uint32_t sequence; + u32 sequence; long out_val = 0; bool probe; @@ -297,7 +297,7 @@ static void guest_code(int cpu) static bool is_steal_time_supported(struct kvm_vcpu *vcpu) { - uint64_t id = RISCV_SBI_EXT_REG(KVM_RISCV_SBI_EXT_STA); + u64 id = RISCV_SBI_EXT_REG(KVM_RISCV_SBI_EXT_STA); unsigned long enabled = vcpu_get_reg(vcpu, id); TEST_ASSERT(enabled == 0 || enabled == 1, "Expected boolean result"); @@ -305,16 +305,16 @@ static bool is_steal_time_supported(struct kvm_vcpu *vcpu) return enabled; } -static void steal_time_init(struct kvm_vcpu *vcpu, uint32_t i) +static void steal_time_init(struct kvm_vcpu *vcpu, u32 i) { /* ST_GPA_BASE is identity mapped */ st_gva[i] = (void *)(ST_GPA_BASE + i * STEAL_TIME_SIZE); - st_gpa[i] = addr_gva2gpa(vcpu->vm, (vm_vaddr_t)st_gva[i]); + st_gpa[i] = addr_gva2gpa(vcpu->vm, (gva_t)st_gva[i]); sync_global_to_guest(vcpu->vm, st_gva[i]); sync_global_to_guest(vcpu->vm, st_gpa[i]); } -static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpu_idx) +static void steal_time_dump(struct kvm_vm *vm, u32 vcpu_idx) { struct sta_struct *st = addr_gva2hva(vm, (ulong)st_gva[vcpu_idx]); int i; @@ -335,7 +335,7 @@ static void check_steal_time_uapi(void) struct kvm_vm *vm; struct kvm_vcpu *vcpu; struct kvm_one_reg reg; - uint64_t shmem; + u64 shmem; int ret; vm = vm_create_with_one_vcpu(&vcpu, NULL); @@ -345,7 +345,7 @@ static void check_steal_time_uapi(void) KVM_REG_RISCV_SBI_STATE | KVM_REG_RISCV_SBI_STA | KVM_REG_RISCV_SBI_STA_REG(shmem_lo); - reg.addr = (uint64_t)&shmem; + reg.addr = (u64)&shmem; shmem = ST_GPA_BASE + 1; ret = __vcpu_ioctl(vcpu, KVM_SET_ONE_REG, ®); @@ -388,7 +388,7 @@ static void check_status(struct kvm_steal_time *st) static void guest_code(int cpu) { - uint32_t version; + u32 version; struct kvm_steal_time *st = st_gva[cpu]; memset(st, 0, sizeof(*st)); @@ -410,11 +410,11 @@ static void guest_code(int cpu) static bool is_steal_time_supported(struct kvm_vcpu *vcpu) { int err; - uint64_t val; + u64 val; struct kvm_device_attr attr = { .group = KVM_LOONGARCH_VCPU_CPUCFG, .attr = CPUCFG_KVM_FEATURE, - .addr = (uint64_t)&val, + .addr = (u64)&val, }; err = __vcpu_ioctl(vcpu, KVM_HAS_DEVICE_ATTR, &attr); @@ -428,15 +428,15 @@ static bool is_steal_time_supported(struct kvm_vcpu *vcpu) return val & BIT(KVM_FEATURE_STEAL_TIME); } -static void steal_time_init(struct kvm_vcpu *vcpu, uint32_t i) +static void steal_time_init(struct kvm_vcpu *vcpu, u32 i) { int err; - uint64_t st_gpa; + u64 st_gpa; struct kvm_vm *vm = vcpu->vm; struct kvm_device_attr attr = { .group = KVM_LOONGARCH_VCPU_PVTIME_CTRL, .attr = KVM_LOONGARCH_VCPU_PVTIME_GPA, - .addr = (uint64_t)&st_gpa, + .addr = (u64)&st_gpa, }; /* ST_GPA_BASE is identity mapped */ @@ -451,7 +451,7 @@ static void steal_time_init(struct kvm_vcpu *vcpu, uint32_t i) TEST_ASSERT(err == 0, "Fail to set PV stealtime GPA"); } -static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpu_idx) +static void steal_time_dump(struct kvm_vm *vm, u32 vcpu_idx) { struct kvm_steal_time *st = addr_gva2hva(vm, (ulong)st_gva[vcpu_idx]); @@ -461,6 +461,11 @@ static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpu_idx) ksft_print_msg(" version: %d\n", st->version); ksft_print_msg(" preempted: %d\n", st->preempted); } + +static void check_steal_time_uapi(void) +{ + +} #endif static void *do_steal_time(void *arg) diff --git a/tools/testing/selftests/kvm/system_counter_offset_test.c b/tools/testing/selftests/kvm/system_counter_offset_test.c index 513d421a9bff..dc5e30b7b77f 100644 --- a/tools/testing/selftests/kvm/system_counter_offset_test.c +++ b/tools/testing/selftests/kvm/system_counter_offset_test.c @@ -17,7 +17,7 @@ #ifdef __x86_64__ struct test_case { - uint64_t tsc_offset; + u64 tsc_offset; }; static struct test_case test_cases[] = { @@ -39,12 +39,12 @@ static void setup_system_counter(struct kvm_vcpu *vcpu, struct test_case *test) &test->tsc_offset); } -static uint64_t guest_read_system_counter(struct test_case *test) +static u64 guest_read_system_counter(struct test_case *test) { return rdtsc(); } -static uint64_t host_read_guest_system_counter(struct test_case *test) +static u64 host_read_guest_system_counter(struct test_case *test) { return rdtsc() + test->tsc_offset; } @@ -69,9 +69,9 @@ static void guest_main(void) } } -static void handle_sync(struct ucall *uc, uint64_t start, uint64_t end) +static void handle_sync(struct ucall *uc, u64 start, u64 end) { - uint64_t obs = uc->args[2]; + u64 obs = uc->args[2]; TEST_ASSERT(start <= obs && obs <= end, "unexpected system counter value: %"PRIu64" expected range: [%"PRIu64", %"PRIu64"]", @@ -88,7 +88,7 @@ static void handle_abort(struct ucall *uc) static void enter_guest(struct kvm_vcpu *vcpu) { - uint64_t start, end; + u64 start, end; struct ucall uc; int i; diff --git a/tools/testing/selftests/kvm/x86/amx_test.c b/tools/testing/selftests/kvm/x86/amx_test.c index 37b166260ee3..4e63da2b1889 100644 --- a/tools/testing/selftests/kvm/x86/amx_test.c +++ b/tools/testing/selftests/kvm/x86/amx_test.c @@ -80,10 +80,10 @@ static inline void __tilerelease(void) asm volatile(".byte 0xc4, 0xe2, 0x78, 0x49, 0xc0" ::); } -static inline void __xsavec(struct xstate *xstate, uint64_t rfbm) +static inline void __xsavec(struct xstate *xstate, u64 rfbm) { - uint32_t rfbm_lo = rfbm; - uint32_t rfbm_hi = rfbm >> 32; + u32 rfbm_lo = rfbm; + u32 rfbm_hi = rfbm >> 32; asm volatile("xsavec (%%rdi)" : : "D" (xstate), "a" (rfbm_lo), "d" (rfbm_hi) @@ -236,7 +236,7 @@ int main(int argc, char *argv[]) struct kvm_x86_state *state; struct kvm_x86_state *tile_state = NULL; int xsave_restore_size; - vm_vaddr_t amx_cfg, tiledata, xstate; + gva_t amx_cfg, tiledata, xstate; struct ucall uc; int ret; @@ -263,15 +263,15 @@ int main(int argc, char *argv[]) vcpu_regs_get(vcpu, ®s1); /* amx cfg for guest_code */ - amx_cfg = vm_vaddr_alloc_page(vm); + amx_cfg = vm_alloc_page(vm); memset(addr_gva2hva(vm, amx_cfg), 0x0, getpagesize()); /* amx tiledata for guest_code */ - tiledata = vm_vaddr_alloc_pages(vm, 2); + tiledata = vm_alloc_pages(vm, 2); memset(addr_gva2hva(vm, tiledata), rand() | 1, 2 * getpagesize()); /* XSAVE state for guest_code */ - xstate = vm_vaddr_alloc_pages(vm, DIV_ROUND_UP(XSAVE_SIZE, PAGE_SIZE)); + xstate = vm_alloc_pages(vm, DIV_ROUND_UP(XSAVE_SIZE, PAGE_SIZE)); memset(addr_gva2hva(vm, xstate), 0, PAGE_SIZE * DIV_ROUND_UP(XSAVE_SIZE, PAGE_SIZE)); vcpu_args_set(vcpu, 3, amx_cfg, tiledata, xstate); diff --git a/tools/testing/selftests/kvm/x86/aperfmperf_test.c b/tools/testing/selftests/kvm/x86/aperfmperf_test.c index 8b15a13df939..c91660103137 100644 --- a/tools/testing/selftests/kvm/x86/aperfmperf_test.c +++ b/tools/testing/selftests/kvm/x86/aperfmperf_test.c @@ -35,9 +35,9 @@ static int open_dev_msr(int cpu) return open_path_or_exit(path, O_RDONLY); } -static uint64_t read_dev_msr(int msr_fd, uint32_t msr) +static u64 read_dev_msr(int msr_fd, u32 msr) { - uint64_t data; + u64 data; ssize_t rc; rc = pread(msr_fd, &data, sizeof(data), msr); @@ -107,8 +107,8 @@ static void guest_code(void *nested_test_data) static void guest_no_aperfmperf(void) { - uint64_t msr_val; - uint8_t vector; + u64 msr_val; + u8 vector; vector = rdmsr_safe(MSR_IA32_APERF, &msr_val); GUEST_ASSERT(vector == GP_VECTOR); @@ -122,8 +122,8 @@ static void guest_no_aperfmperf(void) int main(int argc, char *argv[]) { const bool has_nested = kvm_cpu_has(X86_FEATURE_SVM) || kvm_cpu_has(X86_FEATURE_VMX); - uint64_t host_aperf_before, host_mperf_before; - vm_vaddr_t nested_test_data_gva; + u64 host_aperf_before, host_mperf_before; + gva_t nested_test_data_gva; struct kvm_vcpu *vcpu; struct kvm_vm *vm; int msr_fd, cpu, i; @@ -166,8 +166,8 @@ int main(int argc, char *argv[]) host_mperf_before = read_dev_msr(msr_fd, MSR_IA32_MPERF); for (i = 0; i <= NUM_ITERATIONS * (1 + has_nested); i++) { - uint64_t host_aperf_after, host_mperf_after; - uint64_t guest_aperf, guest_mperf; + u64 host_aperf_after, host_mperf_after; + u64 guest_aperf, guest_mperf; struct ucall uc; vcpu_run(vcpu); diff --git a/tools/testing/selftests/kvm/x86/apic_bus_clock_test.c b/tools/testing/selftests/kvm/x86/apic_bus_clock_test.c index f8916bb34405..404f0028e110 100644 --- a/tools/testing/selftests/kvm/x86/apic_bus_clock_test.c +++ b/tools/testing/selftests/kvm/x86/apic_bus_clock_test.c @@ -19,8 +19,8 @@ * timer frequency. */ static const struct { - const uint32_t tdcr; - const uint32_t divide_count; + const u32 tdcr; + const u32 divide_count; } tdcrs[] = { {0x0, 2}, {0x1, 4}, @@ -42,12 +42,12 @@ static void apic_enable(void) xapic_enable(); } -static uint32_t apic_read_reg(unsigned int reg) +static u32 apic_read_reg(unsigned int reg) { return is_x2apic ? x2apic_read_reg(reg) : xapic_read_reg(reg); } -static void apic_write_reg(unsigned int reg, uint32_t val) +static void apic_write_reg(unsigned int reg, u32 val) { if (is_x2apic) x2apic_write_reg(reg, val); @@ -55,12 +55,12 @@ static void apic_write_reg(unsigned int reg, uint32_t val) xapic_write_reg(reg, val); } -static void apic_guest_code(uint64_t apic_hz, uint64_t delay_ms) +static void apic_guest_code(u64 apic_hz, u64 delay_ms) { - uint64_t tsc_hz = guest_tsc_khz * 1000; - const uint32_t tmict = ~0u; - uint64_t tsc0, tsc1, freq; - uint32_t tmcct; + u64 tsc_hz = guest_tsc_khz * 1000; + const u32 tmict = ~0u; + u64 tsc0, tsc1, freq; + u32 tmcct; int i; apic_enable(); @@ -121,7 +121,7 @@ static void test_apic_bus_clock(struct kvm_vcpu *vcpu) } } -static void run_apic_bus_clock_test(uint64_t apic_hz, uint64_t delay_ms, +static void run_apic_bus_clock_test(u64 apic_hz, u64 delay_ms, bool x2apic) { struct kvm_vcpu *vcpu; @@ -168,8 +168,8 @@ int main(int argc, char *argv[]) * Arbitrarilty default to 25MHz for the APIC bus frequency, which is * different enough from the default 1GHz to be interesting. */ - uint64_t apic_hz = 25 * 1000 * 1000; - uint64_t delay_ms = 100; + u64 apic_hz = 25 * 1000 * 1000; + u64 delay_ms = 100; int opt; TEST_REQUIRE(kvm_has_cap(KVM_CAP_X86_APIC_BUS_CYCLES_NS)); diff --git a/tools/testing/selftests/kvm/x86/cpuid_test.c b/tools/testing/selftests/kvm/x86/cpuid_test.c index f9ed14996977..ef0ddd240887 100644 --- a/tools/testing/selftests/kvm/x86/cpuid_test.c +++ b/tools/testing/selftests/kvm/x86/cpuid_test.c @@ -140,10 +140,10 @@ static void run_vcpu(struct kvm_vcpu *vcpu, int stage) } } -struct kvm_cpuid2 *vcpu_alloc_cpuid(struct kvm_vm *vm, vm_vaddr_t *p_gva, struct kvm_cpuid2 *cpuid) +struct kvm_cpuid2 *vcpu_alloc_cpuid(struct kvm_vm *vm, gva_t *p_gva, struct kvm_cpuid2 *cpuid) { int size = sizeof(*cpuid) + cpuid->nent * sizeof(cpuid->entries[0]); - vm_vaddr_t gva = vm_vaddr_alloc(vm, size, KVM_UTIL_MIN_VADDR); + gva_t gva = vm_alloc(vm, size, KVM_UTIL_MIN_VADDR); struct kvm_cpuid2 *guest_cpuids = addr_gva2hva(vm, gva); memcpy(guest_cpuids, cpuid, size); @@ -217,7 +217,7 @@ static void test_get_cpuid2(struct kvm_vcpu *vcpu) int main(void) { struct kvm_vcpu *vcpu; - vm_vaddr_t cpuid_gva; + gva_t cpuid_gva; struct kvm_vm *vm; int stage; diff --git a/tools/testing/selftests/kvm/x86/debug_regs.c b/tools/testing/selftests/kvm/x86/debug_regs.c index 2d814c1d1dc4..0dfaf03cd0a0 100644 --- a/tools/testing/selftests/kvm/x86/debug_regs.c +++ b/tools/testing/selftests/kvm/x86/debug_regs.c @@ -16,7 +16,7 @@ #define IRQ_VECTOR 0xAA /* For testing data access debug BP */ -uint32_t guest_value; +u32 guest_value; extern unsigned char sw_bp, hw_bp, write_data, ss_start, bd_start; @@ -86,7 +86,7 @@ int main(void) struct kvm_run *run; struct kvm_vm *vm; struct ucall uc; - uint64_t cmd; + u64 cmd; int i; /* Instruction lengths starting at ss_start */ int ss_size[6] = { diff --git a/tools/testing/selftests/kvm/x86/dirty_log_page_splitting_test.c b/tools/testing/selftests/kvm/x86/dirty_log_page_splitting_test.c index b0d2b04a7ff2..388ba4101f97 100644 --- a/tools/testing/selftests/kvm/x86/dirty_log_page_splitting_test.c +++ b/tools/testing/selftests/kvm/x86/dirty_log_page_splitting_test.c @@ -23,7 +23,7 @@ #define SLOTS 2 #define ITERATIONS 2 -static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE; +static u64 guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE; static enum vm_mem_backing_src_type backing_src = VM_MEM_SRC_ANONYMOUS_HUGETLB; @@ -33,10 +33,10 @@ static int iteration; static int vcpu_last_completed_iteration[KVM_MAX_VCPUS]; struct kvm_page_stats { - uint64_t pages_4k; - uint64_t pages_2m; - uint64_t pages_1g; - uint64_t hugepages; + u64 pages_4k; + u64 pages_2m; + u64 pages_1g; + u64 hugepages; }; static void get_page_stats(struct kvm_vm *vm, struct kvm_page_stats *stats, const char *stage) @@ -89,9 +89,9 @@ static void run_test(enum vm_guest_mode mode, void *unused) { struct kvm_vm *vm; unsigned long **bitmaps; - uint64_t guest_num_pages; - uint64_t host_num_pages; - uint64_t pages_per_slot; + u64 guest_num_pages; + u64 host_num_pages; + u64 pages_per_slot; int i; struct kvm_page_stats stats_populated; struct kvm_page_stats stats_dirty_logging_enabled; diff --git a/tools/testing/selftests/kvm/x86/evmcs_smm_controls_test.c b/tools/testing/selftests/kvm/x86/evmcs_smm_controls_test.c index af7c90103396..5b3aef109cfc 100644 --- a/tools/testing/selftests/kvm/x86/evmcs_smm_controls_test.c +++ b/tools/testing/selftests/kvm/x86/evmcs_smm_controls_test.c @@ -29,13 +29,13 @@ * SMI handler: runs in real-address mode. * Reports SMRAM_STAGE via port IO, then does RSM. */ -static uint8_t smi_handler[] = { +static u8 smi_handler[] = { 0xb0, SMRAM_STAGE, /* mov $SMRAM_STAGE, %al */ 0xe4, SYNC_PORT, /* in $SYNC_PORT, %al */ 0x0f, 0xaa, /* rsm */ }; -static inline void sync_with_host(uint64_t phase) +static inline void sync_with_host(u64 phase) { asm volatile("in $" XSTR(SYNC_PORT) ", %%al \n" : "+a" (phase)); @@ -73,7 +73,7 @@ static void guest_code(struct vmx_pages *vmx_pages, int main(int argc, char *argv[]) { - vm_vaddr_t vmx_pages_gva = 0, hv_pages_gva = 0; + gva_t vmx_pages_gva = 0, hv_pages_gva = 0; struct hyperv_test_pages *hv; struct hv_enlightened_vmcs *evmcs; struct kvm_vcpu *vcpu; diff --git a/tools/testing/selftests/kvm/x86/fastops_test.c b/tools/testing/selftests/kvm/x86/fastops_test.c index 8926cfe0e209..c0d30ccd8767 100644 --- a/tools/testing/selftests/kvm/x86/fastops_test.c +++ b/tools/testing/selftests/kvm/x86/fastops_test.c @@ -15,7 +15,7 @@ "pop %[flags]\n\t" #define flags_constraint(flags_val) [flags]"=r"(flags_val) -#define bt_constraint(__bt_val) [bt_val]"rm"((uint32_t)__bt_val) +#define bt_constraint(__bt_val) [bt_val]"rm"((u32)__bt_val) #define guest_execute_fastop_1(FEP, insn, __val, __flags) \ ({ \ @@ -28,17 +28,17 @@ #define guest_test_fastop_1(insn, type_t, __val) \ ({ \ type_t val = __val, ex_val = __val, input = __val; \ - uint64_t flags, ex_flags; \ + u64 flags, ex_flags; \ \ guest_execute_fastop_1("", insn, ex_val, ex_flags); \ guest_execute_fastop_1(KVM_FEP, insn, val, flags); \ \ __GUEST_ASSERT(val == ex_val, \ "Wanted 0x%lx for '%s 0x%lx', got 0x%lx", \ - (uint64_t)ex_val, insn, (uint64_t)input, (uint64_t)val); \ + (u64)ex_val, insn, (u64)input, (u64)val); \ __GUEST_ASSERT(flags == ex_flags, \ "Wanted flags 0x%lx for '%s 0x%lx', got 0x%lx", \ - ex_flags, insn, (uint64_t)input, flags); \ + ex_flags, insn, (u64)input, flags); \ }) #define guest_execute_fastop_2(FEP, insn, __input, __output, __flags) \ @@ -52,18 +52,18 @@ #define guest_test_fastop_2(insn, type_t, __val1, __val2) \ ({ \ type_t input = __val1, input2 = __val2, output = __val2, ex_output = __val2; \ - uint64_t flags, ex_flags; \ + u64 flags, ex_flags; \ \ guest_execute_fastop_2("", insn, input, ex_output, ex_flags); \ guest_execute_fastop_2(KVM_FEP, insn, input, output, flags); \ \ __GUEST_ASSERT(output == ex_output, \ "Wanted 0x%lx for '%s 0x%lx 0x%lx', got 0x%lx", \ - (uint64_t)ex_output, insn, (uint64_t)input, \ - (uint64_t)input2, (uint64_t)output); \ + (u64)ex_output, insn, (u64)input, \ + (u64)input2, (u64)output); \ __GUEST_ASSERT(flags == ex_flags, \ "Wanted flags 0x%lx for '%s 0x%lx, 0x%lx', got 0x%lx", \ - ex_flags, insn, (uint64_t)input, (uint64_t)input2, flags); \ + ex_flags, insn, (u64)input, (u64)input2, flags); \ }) #define guest_execute_fastop_cl(FEP, insn, __shift, __output, __flags) \ @@ -77,25 +77,25 @@ #define guest_test_fastop_cl(insn, type_t, __val1, __val2) \ ({ \ type_t output = __val2, ex_output = __val2, input = __val2; \ - uint8_t shift = __val1; \ - uint64_t flags, ex_flags; \ + u8 shift = __val1; \ + u64 flags, ex_flags; \ \ guest_execute_fastop_cl("", insn, shift, ex_output, ex_flags); \ guest_execute_fastop_cl(KVM_FEP, insn, shift, output, flags); \ \ __GUEST_ASSERT(output == ex_output, \ "Wanted 0x%lx for '%s 0x%x, 0x%lx', got 0x%lx", \ - (uint64_t)ex_output, insn, shift, (uint64_t)input, \ - (uint64_t)output); \ + (u64)ex_output, insn, shift, (u64)input, \ + (u64)output); \ __GUEST_ASSERT(flags == ex_flags, \ "Wanted flags 0x%lx for '%s 0x%x, 0x%lx', got 0x%lx", \ - ex_flags, insn, shift, (uint64_t)input, flags); \ + ex_flags, insn, shift, (u64)input, flags); \ }) #define guest_execute_fastop_div(__KVM_ASM_SAFE, insn, __a, __d, __rm, __flags) \ ({ \ - uint64_t ign_error_code; \ - uint8_t vector; \ + u64 ign_error_code; \ + u8 vector; \ \ __asm__ __volatile__(fastop(__KVM_ASM_SAFE(insn " %[denom]")) \ : "+a"(__a), "+d"(__d), flags_constraint(__flags), \ @@ -109,8 +109,8 @@ ({ \ type_t _a = __val1, _d = __val1, rm = __val2; \ type_t a = _a, d = _d, ex_a = _a, ex_d = _d; \ - uint64_t flags, ex_flags; \ - uint8_t v, ex_v; \ + u64 flags, ex_flags; \ + u8 v, ex_v; \ \ ex_v = guest_execute_fastop_div(KVM_ASM_SAFE, insn, ex_a, ex_d, rm, ex_flags); \ v = guest_execute_fastop_div(KVM_ASM_SAFE_FEP, insn, a, d, rm, flags); \ @@ -118,17 +118,17 @@ GUEST_ASSERT_EQ(v, ex_v); \ __GUEST_ASSERT(v == ex_v, \ "Wanted vector 0x%x for '%s 0x%lx:0x%lx/0x%lx', got 0x%x", \ - ex_v, insn, (uint64_t)_a, (uint64_t)_d, (uint64_t)rm, v); \ + ex_v, insn, (u64)_a, (u64)_d, (u64)rm, v); \ __GUEST_ASSERT(a == ex_a && d == ex_d, \ "Wanted 0x%lx:0x%lx for '%s 0x%lx:0x%lx/0x%lx', got 0x%lx:0x%lx",\ - (uint64_t)ex_a, (uint64_t)ex_d, insn, (uint64_t)_a, \ - (uint64_t)_d, (uint64_t)rm, (uint64_t)a, (uint64_t)d); \ + (u64)ex_a, (u64)ex_d, insn, (u64)_a, \ + (u64)_d, (u64)rm, (u64)a, (u64)d); \ __GUEST_ASSERT(v || ex_v || (flags == ex_flags), \ "Wanted flags 0x%lx for '%s 0x%lx:0x%lx/0x%lx', got 0x%lx", \ - ex_flags, insn, (uint64_t)_a, (uint64_t)_d, (uint64_t)rm, flags);\ + ex_flags, insn, (u64)_a, (u64)_d, (u64)rm, flags);\ }) -static const uint64_t vals[] = { +static const u64 vals[] = { 0, 1, 2, @@ -185,10 +185,10 @@ if (sizeof(type_t) != 1) { \ static void guest_code(void) { - guest_test_fastops(uint8_t, "b"); - guest_test_fastops(uint16_t, "w"); - guest_test_fastops(uint32_t, "l"); - guest_test_fastops(uint64_t, "q"); + guest_test_fastops(u8, "b"); + guest_test_fastops(u16, "w"); + guest_test_fastops(u32, "l"); + guest_test_fastops(u64, "q"); GUEST_DONE(); } diff --git a/tools/testing/selftests/kvm/x86/feature_msrs_test.c b/tools/testing/selftests/kvm/x86/feature_msrs_test.c index a72f13ae2edb..158550701771 100644 --- a/tools/testing/selftests/kvm/x86/feature_msrs_test.c +++ b/tools/testing/selftests/kvm/x86/feature_msrs_test.c @@ -12,7 +12,7 @@ #include "kvm_util.h" #include "processor.h" -static bool is_kvm_controlled_msr(uint32_t msr) +static bool is_kvm_controlled_msr(u32 msr) { return msr == MSR_IA32_VMX_CR0_FIXED1 || msr == MSR_IA32_VMX_CR4_FIXED1; } @@ -21,7 +21,7 @@ static bool is_kvm_controlled_msr(uint32_t msr) * For VMX MSRs with a "true" variant, KVM requires userspace to set the "true" * MSR, and doesn't allow setting the hidden version. */ -static bool is_hidden_vmx_msr(uint32_t msr) +static bool is_hidden_vmx_msr(u32 msr) { switch (msr) { case MSR_IA32_VMX_PINBASED_CTLS: @@ -34,15 +34,15 @@ static bool is_hidden_vmx_msr(uint32_t msr) } } -static bool is_quirked_msr(uint32_t msr) +static bool is_quirked_msr(u32 msr) { return msr != MSR_AMD64_DE_CFG; } -static void test_feature_msr(uint32_t msr) +static void test_feature_msr(u32 msr) { - const uint64_t supported_mask = kvm_get_feature_msr(msr); - uint64_t reset_value = is_quirked_msr(msr) ? supported_mask : 0; + const u64 supported_mask = kvm_get_feature_msr(msr); + u64 reset_value = is_quirked_msr(msr) ? supported_mask : 0; struct kvm_vcpu *vcpu; struct kvm_vm *vm; diff --git a/tools/testing/selftests/kvm/x86/fix_hypercall_test.c b/tools/testing/selftests/kvm/x86/fix_hypercall_test.c index 00b6e85735dd..753a0e730ea8 100644 --- a/tools/testing/selftests/kvm/x86/fix_hypercall_test.c +++ b/tools/testing/selftests/kvm/x86/fix_hypercall_test.c @@ -26,18 +26,18 @@ static void guest_ud_handler(struct ex_regs *regs) regs->rip += HYPERCALL_INSN_SIZE; } -static const uint8_t vmx_vmcall[HYPERCALL_INSN_SIZE] = { 0x0f, 0x01, 0xc1 }; -static const uint8_t svm_vmmcall[HYPERCALL_INSN_SIZE] = { 0x0f, 0x01, 0xd9 }; +static const u8 vmx_vmcall[HYPERCALL_INSN_SIZE] = { 0x0f, 0x01, 0xc1 }; +static const u8 svm_vmmcall[HYPERCALL_INSN_SIZE] = { 0x0f, 0x01, 0xd9 }; -extern uint8_t hypercall_insn[HYPERCALL_INSN_SIZE]; -static uint64_t do_sched_yield(uint8_t apic_id) +extern u8 hypercall_insn[HYPERCALL_INSN_SIZE]; +static u64 do_sched_yield(u8 apic_id) { - uint64_t ret; + u64 ret; asm volatile("hypercall_insn:\n\t" ".byte 0xcc,0xcc,0xcc\n\t" : "=a"(ret) - : "a"((uint64_t)KVM_HC_SCHED_YIELD), "b"((uint64_t)apic_id) + : "a"((u64)KVM_HC_SCHED_YIELD), "b"((u64)apic_id) : "memory"); return ret; @@ -45,9 +45,9 @@ static uint64_t do_sched_yield(uint8_t apic_id) static void guest_main(void) { - const uint8_t *native_hypercall_insn; - const uint8_t *other_hypercall_insn; - uint64_t ret; + const u8 *native_hypercall_insn; + const u8 *other_hypercall_insn; + u64 ret; if (host_cpu_is_intel) { native_hypercall_insn = vmx_vmcall; @@ -72,7 +72,7 @@ static void guest_main(void) * the "right" hypercall. */ if (quirk_disabled) { - GUEST_ASSERT(ret == (uint64_t)-EFAULT); + GUEST_ASSERT(ret == (u64)-EFAULT); GUEST_ASSERT(!memcmp(other_hypercall_insn, hypercall_insn, HYPERCALL_INSN_SIZE)); } else { diff --git a/tools/testing/selftests/kvm/x86/flds_emulation.h b/tools/testing/selftests/kvm/x86/flds_emulation.h index 37b1a9f52864..fd6b6c67199a 100644 --- a/tools/testing/selftests/kvm/x86/flds_emulation.h +++ b/tools/testing/selftests/kvm/x86/flds_emulation.h @@ -12,7 +12,7 @@ * KVM to emulate the instruction (e.g. by providing an MMIO address) to * exercise emulation failures. */ -static inline void flds(uint64_t address) +static inline void flds(u64 address) { __asm__ __volatile__(FLDS_MEM_EAX :: "a"(address)); } @@ -21,8 +21,8 @@ static inline void handle_flds_emulation_failure_exit(struct kvm_vcpu *vcpu) { struct kvm_run *run = vcpu->run; struct kvm_regs regs; - uint8_t *insn_bytes; - uint64_t flags; + u8 *insn_bytes; + u64 flags; TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_INTERNAL_ERROR); diff --git a/tools/testing/selftests/kvm/x86/hwcr_msr_test.c b/tools/testing/selftests/kvm/x86/hwcr_msr_test.c index 10b1b0ba374e..8e20a03b3329 100644 --- a/tools/testing/selftests/kvm/x86/hwcr_msr_test.c +++ b/tools/testing/selftests/kvm/x86/hwcr_msr_test.c @@ -10,11 +10,11 @@ void test_hwcr_bit(struct kvm_vcpu *vcpu, unsigned int bit) { - const uint64_t ignored = BIT_ULL(3) | BIT_ULL(6) | BIT_ULL(8); - const uint64_t valid = BIT_ULL(18) | BIT_ULL(24); - const uint64_t legal = ignored | valid; - uint64_t val = BIT_ULL(bit); - uint64_t actual; + const u64 ignored = BIT_ULL(3) | BIT_ULL(6) | BIT_ULL(8); + const u64 valid = BIT_ULL(18) | BIT_ULL(24); + const u64 legal = ignored | valid; + u64 val = BIT_ULL(bit); + u64 actual; int r; r = _vcpu_set_msr(vcpu, MSR_K7_HWCR, val); diff --git a/tools/testing/selftests/kvm/x86/hyperv_clock.c b/tools/testing/selftests/kvm/x86/hyperv_clock.c index e058bc676cd6..c083cea546dc 100644 --- a/tools/testing/selftests/kvm/x86/hyperv_clock.c +++ b/tools/testing/selftests/kvm/x86/hyperv_clock.c @@ -98,7 +98,7 @@ static inline void check_tsc_msr_tsc_page(struct ms_hyperv_tsc_page *tsc_page) GUEST_ASSERT(r2 >= t1 && r2 - t2 < 100000); } -static void guest_main(struct ms_hyperv_tsc_page *tsc_page, vm_paddr_t tsc_page_gpa) +static void guest_main(struct ms_hyperv_tsc_page *tsc_page, gpa_t tsc_page_gpa) { u64 tsc_scale, tsc_offset; @@ -208,7 +208,7 @@ int main(void) struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct ucall uc; - vm_vaddr_t tsc_page_gva; + gva_t tsc_page_gva; int stage; TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_TIME)); @@ -218,7 +218,7 @@ int main(void) vcpu_set_hv_cpuid(vcpu); - tsc_page_gva = vm_vaddr_alloc_page(vm); + tsc_page_gva = vm_alloc_page(vm); memset(addr_gva2hva(vm, tsc_page_gva), 0x0, getpagesize()); TEST_ASSERT((addr_gva2gpa(vm, tsc_page_gva) & (getpagesize() - 1)) == 0, "TSC page has to be page aligned"); diff --git a/tools/testing/selftests/kvm/x86/hyperv_evmcs.c b/tools/testing/selftests/kvm/x86/hyperv_evmcs.c index 74cf19661309..c7fa114aee20 100644 --- a/tools/testing/selftests/kvm/x86/hyperv_evmcs.c +++ b/tools/testing/selftests/kvm/x86/hyperv_evmcs.c @@ -30,7 +30,7 @@ static void guest_nmi_handler(struct ex_regs *regs) { } -static inline void rdmsr_from_l2(uint32_t msr) +static inline void rdmsr_from_l2(u32 msr) { /* Currently, L1 doesn't preserve GPRs during vmexits. */ __asm__ __volatile__ ("rdmsr" : : "c"(msr) : @@ -76,7 +76,7 @@ void l2_guest_code(void) } void guest_code(struct vmx_pages *vmx_pages, struct hyperv_test_pages *hv_pages, - vm_vaddr_t hv_hcall_page_gpa) + gpa_t hv_hcall_page_gpa) { #define L2_GUEST_STACK_SIZE 64 unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; @@ -231,8 +231,8 @@ static struct kvm_vcpu *save_restore_vm(struct kvm_vm *vm, int main(int argc, char *argv[]) { - vm_vaddr_t vmx_pages_gva = 0, hv_pages_gva = 0; - vm_vaddr_t hcall_page; + gva_t vmx_pages_gva = 0, hv_pages_gva = 0; + gva_t hcall_page; struct kvm_vcpu *vcpu; struct kvm_vm *vm; @@ -246,7 +246,7 @@ int main(int argc, char *argv[]) vm = vm_create_with_one_vcpu(&vcpu, guest_code); - hcall_page = vm_vaddr_alloc_pages(vm, 1); + hcall_page = vm_alloc_pages(vm, 1); memset(addr_gva2hva(vm, hcall_page), 0x0, getpagesize()); vcpu_set_hv_cpuid(vcpu); diff --git a/tools/testing/selftests/kvm/x86/hyperv_extended_hypercalls.c b/tools/testing/selftests/kvm/x86/hyperv_extended_hypercalls.c index 949e08e98f31..ae047db7b1be 100644 --- a/tools/testing/selftests/kvm/x86/hyperv_extended_hypercalls.c +++ b/tools/testing/selftests/kvm/x86/hyperv_extended_hypercalls.c @@ -15,19 +15,19 @@ /* Any value is fine */ #define EXT_CAPABILITIES 0xbull -static void guest_code(vm_paddr_t in_pg_gpa, vm_paddr_t out_pg_gpa, - vm_vaddr_t out_pg_gva) +static void guest_code(gpa_t in_pg_gpa, gpa_t out_pg_gpa, + gva_t out_pg_gva) { - uint64_t *output_gva; + u64 *output_gva; wrmsr(HV_X64_MSR_GUEST_OS_ID, HYPERV_LINUX_OS_ID); wrmsr(HV_X64_MSR_HYPERCALL, in_pg_gpa); - output_gva = (uint64_t *)out_pg_gva; + output_gva = (u64 *)out_pg_gva; hyperv_hypercall(HV_EXT_CALL_QUERY_CAPABILITIES, in_pg_gpa, out_pg_gpa); - /* TLFS states output will be a uint64_t value */ + /* TLFS states output will be a u64 value */ GUEST_ASSERT_EQ(*output_gva, EXT_CAPABILITIES); GUEST_DONE(); @@ -35,12 +35,12 @@ static void guest_code(vm_paddr_t in_pg_gpa, vm_paddr_t out_pg_gpa, int main(void) { - vm_vaddr_t hcall_out_page; - vm_vaddr_t hcall_in_page; + gva_t hcall_out_page; + gva_t hcall_in_page; struct kvm_vcpu *vcpu; struct kvm_run *run; struct kvm_vm *vm; - uint64_t *outval; + u64 *outval; struct ucall uc; TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_CPUID)); @@ -57,11 +57,11 @@ int main(void) vcpu_set_hv_cpuid(vcpu); /* Hypercall input */ - hcall_in_page = vm_vaddr_alloc_pages(vm, 1); + hcall_in_page = vm_alloc_pages(vm, 1); memset(addr_gva2hva(vm, hcall_in_page), 0x0, vm->page_size); /* Hypercall output */ - hcall_out_page = vm_vaddr_alloc_pages(vm, 1); + hcall_out_page = vm_alloc_pages(vm, 1); memset(addr_gva2hva(vm, hcall_out_page), 0x0, vm->page_size); vcpu_args_set(vcpu, 3, addr_gva2gpa(vm, hcall_in_page), diff --git a/tools/testing/selftests/kvm/x86/hyperv_features.c b/tools/testing/selftests/kvm/x86/hyperv_features.c index 130b9ce7e5dd..7347f1fe5157 100644 --- a/tools/testing/selftests/kvm/x86/hyperv_features.c +++ b/tools/testing/selftests/kvm/x86/hyperv_features.c @@ -22,27 +22,27 @@ KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EBX, 0) struct msr_data { - uint32_t idx; + u32 idx; bool fault_expected; bool write; u64 write_val; }; struct hcall_data { - uint64_t control; - uint64_t expect; + u64 control; + u64 expect; bool ud_expected; }; -static bool is_write_only_msr(uint32_t msr) +static bool is_write_only_msr(u32 msr) { return msr == HV_X64_MSR_EOI; } static void guest_msr(struct msr_data *msr) { - uint8_t vector = 0; - uint64_t msr_val = 0; + u8 vector = 0; + u64 msr_val = 0; GUEST_ASSERT(msr->idx); @@ -82,10 +82,10 @@ done: GUEST_DONE(); } -static void guest_hcall(vm_vaddr_t pgs_gpa, struct hcall_data *hcall) +static void guest_hcall(gpa_t pgs_gpa, struct hcall_data *hcall) { u64 res, input, output; - uint8_t vector; + u8 vector; GUEST_ASSERT_NE(hcall->control, 0); @@ -134,14 +134,14 @@ static void guest_test_msrs_access(void) struct kvm_vm *vm; struct ucall uc; int stage = 0; - vm_vaddr_t msr_gva; + gva_t msr_gva; struct msr_data *msr; bool has_invtsc = kvm_cpu_has(X86_FEATURE_INVTSC); while (true) { vm = vm_create_with_one_vcpu(&vcpu, guest_msr); - msr_gva = vm_vaddr_alloc_page(vm); + msr_gva = vm_alloc_page(vm); memset(addr_gva2hva(vm, msr_gva), 0x0, getpagesize()); msr = addr_gva2hva(vm, msr_gva); @@ -523,17 +523,17 @@ static void guest_test_hcalls_access(void) struct kvm_vm *vm; struct ucall uc; int stage = 0; - vm_vaddr_t hcall_page, hcall_params; + gva_t hcall_page, hcall_params; struct hcall_data *hcall; while (true) { vm = vm_create_with_one_vcpu(&vcpu, guest_hcall); /* Hypercall input/output */ - hcall_page = vm_vaddr_alloc_pages(vm, 2); + hcall_page = vm_alloc_pages(vm, 2); memset(addr_gva2hva(vm, hcall_page), 0x0, 2 * getpagesize()); - hcall_params = vm_vaddr_alloc_page(vm); + hcall_params = vm_alloc_page(vm); memset(addr_gva2hva(vm, hcall_params), 0x0, getpagesize()); hcall = addr_gva2hva(vm, hcall_params); diff --git a/tools/testing/selftests/kvm/x86/hyperv_ipi.c b/tools/testing/selftests/kvm/x86/hyperv_ipi.c index ca61836c4e32..771535f9aad3 100644 --- a/tools/testing/selftests/kvm/x86/hyperv_ipi.c +++ b/tools/testing/selftests/kvm/x86/hyperv_ipi.c @@ -18,7 +18,7 @@ #define IPI_VECTOR 0xfe -static volatile uint64_t ipis_rcvd[RECEIVER_VCPU_ID_2 + 1]; +static volatile u64 ipis_rcvd[RECEIVER_VCPU_ID_2 + 1]; struct hv_vpset { u64 format; @@ -45,13 +45,13 @@ struct hv_send_ipi_ex { struct hv_vpset vp_set; }; -static inline void hv_init(vm_vaddr_t pgs_gpa) +static inline void hv_init(gpa_t pgs_gpa) { wrmsr(HV_X64_MSR_GUEST_OS_ID, HYPERV_LINUX_OS_ID); wrmsr(HV_X64_MSR_HYPERCALL, pgs_gpa); } -static void receiver_code(void *hcall_page, vm_vaddr_t pgs_gpa) +static void receiver_code(void *hcall_page, gpa_t pgs_gpa) { u32 vcpu_id; @@ -85,7 +85,7 @@ static inline void nop_loop(void) asm volatile("nop"); } -static void sender_guest_code(void *hcall_page, vm_vaddr_t pgs_gpa) +static void sender_guest_code(void *hcall_page, gpa_t pgs_gpa) { struct hv_send_ipi *ipi = (struct hv_send_ipi *)hcall_page; struct hv_send_ipi_ex *ipi_ex = (struct hv_send_ipi_ex *)hcall_page; @@ -243,7 +243,7 @@ int main(int argc, char *argv[]) { struct kvm_vm *vm; struct kvm_vcpu *vcpu[3]; - vm_vaddr_t hcall_page; + gva_t hcall_page; pthread_t threads[2]; int stage = 1, r; struct ucall uc; @@ -253,7 +253,7 @@ int main(int argc, char *argv[]) vm = vm_create_with_one_vcpu(&vcpu[0], sender_guest_code); /* Hypercall input/output */ - hcall_page = vm_vaddr_alloc_pages(vm, 2); + hcall_page = vm_alloc_pages(vm, 2); memset(addr_gva2hva(vm, hcall_page), 0x0, 2 * getpagesize()); diff --git a/tools/testing/selftests/kvm/x86/hyperv_svm_test.c b/tools/testing/selftests/kvm/x86/hyperv_svm_test.c index 0ddb63229bcb..7a62f6a9d606 100644 --- a/tools/testing/selftests/kvm/x86/hyperv_svm_test.c +++ b/tools/testing/selftests/kvm/x86/hyperv_svm_test.c @@ -21,7 +21,7 @@ #define L2_GUEST_STACK_SIZE 256 /* Exit to L1 from L2 with RDMSR instruction */ -static inline void rdmsr_from_l2(uint32_t msr) +static inline void rdmsr_from_l2(u32 msr) { /* Currently, L1 doesn't preserve GPRs during vmexits. */ __asm__ __volatile__ ("rdmsr" : : "c"(msr) : @@ -67,7 +67,7 @@ void l2_guest_code(void) static void __attribute__((__flatten__)) guest_code(struct svm_test_data *svm, struct hyperv_test_pages *hv_pages, - vm_vaddr_t pgs_gpa) + gpa_t pgs_gpa) { unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; struct vmcb *vmcb = svm->vmcb; @@ -149,8 +149,8 @@ static void __attribute__((__flatten__)) guest_code(struct svm_test_data *svm, int main(int argc, char *argv[]) { - vm_vaddr_t nested_gva = 0, hv_pages_gva = 0; - vm_vaddr_t hcall_page; + gva_t nested_gva = 0, hv_pages_gva = 0; + gva_t hcall_page; struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct ucall uc; @@ -165,7 +165,7 @@ int main(int argc, char *argv[]) vcpu_alloc_svm(vm, &nested_gva); vcpu_alloc_hyperv_test_pages(vm, &hv_pages_gva); - hcall_page = vm_vaddr_alloc_pages(vm, 1); + hcall_page = vm_alloc_pages(vm, 1); memset(addr_gva2hva(vm, hcall_page), 0x0, getpagesize()); vcpu_args_set(vcpu, 3, nested_gva, hv_pages_gva, addr_gva2gpa(vm, hcall_page)); diff --git a/tools/testing/selftests/kvm/x86/hyperv_tlb_flush.c b/tools/testing/selftests/kvm/x86/hyperv_tlb_flush.c index c542cc4762b1..15ee8b7bfc11 100644 --- a/tools/testing/selftests/kvm/x86/hyperv_tlb_flush.c +++ b/tools/testing/selftests/kvm/x86/hyperv_tlb_flush.c @@ -61,14 +61,14 @@ struct hv_tlb_flush_ex { * - GVAs of the test pages' PTEs */ struct test_data { - vm_vaddr_t hcall_gva; - vm_paddr_t hcall_gpa; - vm_vaddr_t test_pages; - vm_vaddr_t test_pages_pte[NTEST_PAGES]; + gva_t hcall_gva; + gpa_t hcall_gpa; + gva_t test_pages; + gva_t test_pages_pte[NTEST_PAGES]; }; /* 'Worker' vCPU code checking the contents of the test page */ -static void worker_guest_code(vm_vaddr_t test_data) +static void worker_guest_code(gva_t test_data) { struct test_data *data = (struct test_data *)test_data; u32 vcpu_id = rdmsr(HV_X64_MSR_VP_INDEX); @@ -133,12 +133,12 @@ static void set_expected_val(void *addr, u64 val, int vcpu_id) * Update PTEs swapping two test pages. * TODO: use swap()/xchg() when these are provided. */ -static void swap_two_test_pages(vm_paddr_t pte_gva1, vm_paddr_t pte_gva2) +static void swap_two_test_pages(gpa_t pte_gva1, gpa_t pte_gva2) { - uint64_t tmp = *(uint64_t *)pte_gva1; + u64 tmp = *(u64 *)pte_gva1; - *(uint64_t *)pte_gva1 = *(uint64_t *)pte_gva2; - *(uint64_t *)pte_gva2 = tmp; + *(u64 *)pte_gva1 = *(u64 *)pte_gva2; + *(u64 *)pte_gva2 = tmp; } /* @@ -196,12 +196,12 @@ static inline void post_test(struct test_data *data, u64 exp1, u64 exp2) #define TESTVAL2 0x0202020202020202 /* Main vCPU doing the test */ -static void sender_guest_code(vm_vaddr_t test_data) +static void sender_guest_code(gva_t test_data) { struct test_data *data = (struct test_data *)test_data; struct hv_tlb_flush *flush = (struct hv_tlb_flush *)data->hcall_gva; struct hv_tlb_flush_ex *flush_ex = (struct hv_tlb_flush_ex *)data->hcall_gva; - vm_paddr_t hcall_gpa = data->hcall_gpa; + gpa_t hcall_gpa = data->hcall_gpa; int i, stage = 1; wrmsr(HV_X64_MSR_GUEST_OS_ID, HYPERV_LINUX_OS_ID); @@ -581,9 +581,9 @@ int main(int argc, char *argv[]) struct kvm_vm *vm; struct kvm_vcpu *vcpu[3]; pthread_t threads[2]; - vm_vaddr_t test_data_page, gva; - vm_paddr_t gpa; - uint64_t *pte; + gva_t test_data_page, gva; + gpa_t gpa; + u64 *pte; struct test_data *data; struct ucall uc; int stage = 1, r, i; @@ -593,11 +593,11 @@ int main(int argc, char *argv[]) vm = vm_create_with_one_vcpu(&vcpu[0], sender_guest_code); /* Test data page */ - test_data_page = vm_vaddr_alloc_page(vm); + test_data_page = vm_alloc_page(vm); data = (struct test_data *)addr_gva2hva(vm, test_data_page); /* Hypercall input/output */ - data->hcall_gva = vm_vaddr_alloc_pages(vm, 2); + data->hcall_gva = vm_alloc_pages(vm, 2); data->hcall_gpa = addr_gva2gpa(vm, data->hcall_gva); memset(addr_gva2hva(vm, data->hcall_gva), 0x0, 2 * PAGE_SIZE); @@ -606,7 +606,7 @@ int main(int argc, char *argv[]) * and the test will swap their mappings. The third page keeps the indication * about the current state of mappings. */ - data->test_pages = vm_vaddr_alloc_pages(vm, NTEST_PAGES + 1); + data->test_pages = vm_alloc_pages(vm, NTEST_PAGES + 1); for (i = 0; i < NTEST_PAGES; i++) memset(addr_gva2hva(vm, data->test_pages + PAGE_SIZE * i), (u8)(i + 1), PAGE_SIZE); @@ -617,7 +617,7 @@ int main(int argc, char *argv[]) * Get PTE pointers for test pages and map them inside the guest. * Use separate page for each PTE for simplicity. */ - gva = vm_vaddr_unused_gap(vm, NTEST_PAGES * PAGE_SIZE, KVM_UTIL_MIN_VADDR); + gva = vm_unused_gva_gap(vm, NTEST_PAGES * PAGE_SIZE, KVM_UTIL_MIN_VADDR); for (i = 0; i < NTEST_PAGES; i++) { pte = vm_get_pte(vm, data->test_pages + i * PAGE_SIZE); gpa = addr_hva2gpa(vm, pte); diff --git a/tools/testing/selftests/kvm/x86/kvm_buslock_test.c b/tools/testing/selftests/kvm/x86/kvm_buslock_test.c index d88500c118eb..52014a3210c8 100644 --- a/tools/testing/selftests/kvm/x86/kvm_buslock_test.c +++ b/tools/testing/selftests/kvm/x86/kvm_buslock_test.c @@ -73,7 +73,7 @@ static void guest_code(void *test_data) int main(int argc, char *argv[]) { const bool has_nested = kvm_cpu_has(X86_FEATURE_SVM) || kvm_cpu_has(X86_FEATURE_VMX); - vm_vaddr_t nested_test_data_gva; + gva_t nested_test_data_gva; struct kvm_vcpu *vcpu; struct kvm_run *run; struct kvm_vm *vm; diff --git a/tools/testing/selftests/kvm/x86/kvm_clock_test.c b/tools/testing/selftests/kvm/x86/kvm_clock_test.c index 5bc12222d87a..5ad4aeb8e373 100644 --- a/tools/testing/selftests/kvm/x86/kvm_clock_test.c +++ b/tools/testing/selftests/kvm/x86/kvm_clock_test.c @@ -17,8 +17,8 @@ #include "processor.h" struct test_case { - uint64_t kvmclock_base; - int64_t realtime_offset; + u64 kvmclock_base; + s64 realtime_offset; }; static struct test_case test_cases[] = { @@ -31,7 +31,7 @@ static struct test_case test_cases[] = { #define GUEST_SYNC_CLOCK(__stage, __val) \ GUEST_SYNC_ARGS(__stage, __val, 0, 0, 0) -static void guest_main(vm_paddr_t pvti_pa, struct pvclock_vcpu_time_info *pvti) +static void guest_main(gpa_t pvti_pa, struct pvclock_vcpu_time_info *pvti) { int i; @@ -52,7 +52,7 @@ static inline void assert_flags(struct kvm_clock_data *data) static void handle_sync(struct ucall *uc, struct kvm_clock_data *start, struct kvm_clock_data *end) { - uint64_t obs, exp_lo, exp_hi; + u64 obs, exp_lo, exp_hi; obs = uc->args[2]; exp_lo = start->clock; @@ -135,8 +135,8 @@ static void enter_guest(struct kvm_vcpu *vcpu) int main(void) { struct kvm_vcpu *vcpu; - vm_vaddr_t pvti_gva; - vm_paddr_t pvti_gpa; + gva_t pvti_gva; + gpa_t pvti_gpa; struct kvm_vm *vm; int flags; @@ -147,7 +147,7 @@ int main(void) vm = vm_create_with_one_vcpu(&vcpu, guest_main); - pvti_gva = vm_vaddr_alloc(vm, getpagesize(), 0x10000); + pvti_gva = vm_alloc(vm, getpagesize(), 0x10000); pvti_gpa = addr_gva2gpa(vm, pvti_gva); vcpu_args_set(vcpu, 2, pvti_gpa, pvti_gva); diff --git a/tools/testing/selftests/kvm/x86/kvm_pv_test.c b/tools/testing/selftests/kvm/x86/kvm_pv_test.c index 1b805cbdb47b..8ed5fa635021 100644 --- a/tools/testing/selftests/kvm/x86/kvm_pv_test.c +++ b/tools/testing/selftests/kvm/x86/kvm_pv_test.c @@ -13,7 +13,7 @@ #include "processor.h" struct msr_data { - uint32_t idx; + u32 idx; const char *name; }; @@ -40,8 +40,8 @@ static struct msr_data msrs_to_test[] = { static void test_msr(struct msr_data *msr) { - uint64_t ignored; - uint8_t vector; + u64 ignored; + u8 vector; PR_MSR(msr); @@ -53,7 +53,7 @@ static void test_msr(struct msr_data *msr) } struct hcall_data { - uint64_t nr; + u64 nr; const char *name; }; @@ -73,7 +73,7 @@ static struct hcall_data hcalls_to_test[] = { static void test_hcall(struct hcall_data *hc) { - uint64_t r; + u64 r; PR_HCALL(hc); r = kvm_hypercall(hc->nr, 0, 0, 0, 0); diff --git a/tools/testing/selftests/kvm/x86/monitor_mwait_test.c b/tools/testing/selftests/kvm/x86/monitor_mwait_test.c index e45c028d2a7e..9c156cf7db0e 100644 --- a/tools/testing/selftests/kvm/x86/monitor_mwait_test.c +++ b/tools/testing/selftests/kvm/x86/monitor_mwait_test.c @@ -67,7 +67,7 @@ static void guest_monitor_wait(void *arg) int main(int argc, char *argv[]) { - uint64_t disabled_quirks; + u64 disabled_quirks; struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct ucall uc; diff --git a/tools/testing/selftests/kvm/x86/nested_close_kvm_test.c b/tools/testing/selftests/kvm/x86/nested_close_kvm_test.c index f001cb836bfa..761fec293408 100644 --- a/tools/testing/selftests/kvm/x86/nested_close_kvm_test.c +++ b/tools/testing/selftests/kvm/x86/nested_close_kvm_test.c @@ -67,7 +67,7 @@ static void l1_guest_code(void *data) int main(int argc, char *argv[]) { - vm_vaddr_t guest_gva; + gva_t guest_gva; struct kvm_vcpu *vcpu; struct kvm_vm *vm; diff --git a/tools/testing/selftests/kvm/x86/nested_dirty_log_test.c b/tools/testing/selftests/kvm/x86/nested_dirty_log_test.c index 619229bbd693..0e67cce83570 100644 --- a/tools/testing/selftests/kvm/x86/nested_dirty_log_test.c +++ b/tools/testing/selftests/kvm/x86/nested_dirty_log_test.c @@ -47,10 +47,10 @@ #define TEST_SYNC_WRITE_FAULT BIT(1) #define TEST_SYNC_NO_FAULT BIT(2) -static void l2_guest_code(vm_vaddr_t base) +static void l2_guest_code(gva_t base) { - vm_vaddr_t page0 = TEST_GUEST_ADDR(base, 0); - vm_vaddr_t page1 = TEST_GUEST_ADDR(base, 1); + gva_t page0 = TEST_GUEST_ADDR(base, 0); + gva_t page1 = TEST_GUEST_ADDR(base, 1); READ_ONCE(*(u64 *)page0); GUEST_SYNC(page0 | TEST_SYNC_READ_FAULT); @@ -143,7 +143,7 @@ static void l1_guest_code(void *data) static void test_handle_ucall_sync(struct kvm_vm *vm, u64 arg, unsigned long *bmap) { - vm_vaddr_t gva = arg & ~(PAGE_SIZE - 1); + gva_t gva = arg & ~(PAGE_SIZE - 1); int page_nr, i; /* @@ -198,7 +198,7 @@ static void test_handle_ucall_sync(struct kvm_vm *vm, u64 arg, static void test_dirty_log(bool nested_tdp) { - vm_vaddr_t nested_gva = 0; + gva_t nested_gva = 0; unsigned long *bmap; struct kvm_vcpu *vcpu; struct kvm_vm *vm; diff --git a/tools/testing/selftests/kvm/x86/nested_emulation_test.c b/tools/testing/selftests/kvm/x86/nested_emulation_test.c index abc824dba04f..fb7dcbe53ac7 100644 --- a/tools/testing/selftests/kvm/x86/nested_emulation_test.c +++ b/tools/testing/selftests/kvm/x86/nested_emulation_test.c @@ -13,8 +13,8 @@ enum { struct emulated_instruction { const char name[32]; - uint8_t opcode[15]; - uint32_t exit_reason[NR_VIRTUALIZATION_FLAVORS]; + u8 opcode[15]; + u32 exit_reason[NR_VIRTUALIZATION_FLAVORS]; }; static struct emulated_instruction instructions[] = { @@ -32,13 +32,13 @@ static struct emulated_instruction instructions[] = { }, }; -static uint8_t kvm_fep[] = { 0x0f, 0x0b, 0x6b, 0x76, 0x6d }; /* ud2 ; .ascii "kvm" */ -static uint8_t l2_guest_code[sizeof(kvm_fep) + 15]; -static uint8_t *l2_instruction = &l2_guest_code[sizeof(kvm_fep)]; +static u8 kvm_fep[] = { 0x0f, 0x0b, 0x6b, 0x76, 0x6d }; /* ud2 ; .ascii "kvm" */ +static u8 l2_guest_code[sizeof(kvm_fep) + 15]; +static u8 *l2_instruction = &l2_guest_code[sizeof(kvm_fep)]; -static uint32_t get_instruction_length(struct emulated_instruction *insn) +static u32 get_instruction_length(struct emulated_instruction *insn) { - uint32_t i; + u32 i; for (i = 0; i < ARRAY_SIZE(insn->opcode) && insn->opcode[i]; i++) ; @@ -81,8 +81,8 @@ static void guest_code(void *test_data) for (i = 0; i < ARRAY_SIZE(instructions); i++) { struct emulated_instruction *insn = &instructions[i]; - uint32_t insn_len = get_instruction_length(insn); - uint32_t exit_insn_len; + u32 insn_len = get_instruction_length(insn); + u32 exit_insn_len; u32 exit_reason; /* @@ -122,7 +122,7 @@ static void guest_code(void *test_data) int main(int argc, char *argv[]) { - vm_vaddr_t nested_test_data_gva; + gva_t nested_test_data_gva; struct kvm_vcpu *vcpu; struct kvm_vm *vm; diff --git a/tools/testing/selftests/kvm/x86/nested_exceptions_test.c b/tools/testing/selftests/kvm/x86/nested_exceptions_test.c index 3641a42934ac..186e980aa8ee 100644 --- a/tools/testing/selftests/kvm/x86/nested_exceptions_test.c +++ b/tools/testing/selftests/kvm/x86/nested_exceptions_test.c @@ -72,7 +72,7 @@ static void l2_ss_injected_tf_test(void) } static void svm_run_l2(struct svm_test_data *svm, void *l2_code, int vector, - uint32_t error_code) + u32 error_code) { struct vmcb *vmcb = svm->vmcb; struct vmcb_control_area *ctrl = &vmcb->control; @@ -111,7 +111,7 @@ static void l1_svm_code(struct svm_test_data *svm) GUEST_DONE(); } -static void vmx_run_l2(void *l2_code, int vector, uint32_t error_code) +static void vmx_run_l2(void *l2_code, int vector, u32 error_code) { GUEST_ASSERT(!vmwrite(GUEST_RIP, (u64)l2_code)); @@ -216,7 +216,7 @@ static void queue_ss_exception(struct kvm_vcpu *vcpu, bool inject) */ int main(int argc, char *argv[]) { - vm_vaddr_t nested_test_data_gva; + gva_t nested_test_data_gva; struct kvm_vcpu_events events; struct kvm_vcpu *vcpu; struct kvm_vm *vm; diff --git a/tools/testing/selftests/kvm/x86/nested_invalid_cr3_test.c b/tools/testing/selftests/kvm/x86/nested_invalid_cr3_test.c index a6b6da9cf7fe..11fd2467d823 100644 --- a/tools/testing/selftests/kvm/x86/nested_invalid_cr3_test.c +++ b/tools/testing/selftests/kvm/x86/nested_invalid_cr3_test.c @@ -78,7 +78,7 @@ int main(int argc, char *argv[]) { struct kvm_vcpu *vcpu; struct kvm_vm *vm; - vm_vaddr_t guest_gva = 0; + gva_t guest_gva = 0; TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX) || kvm_cpu_has(X86_FEATURE_SVM)); diff --git a/tools/testing/selftests/kvm/x86/nested_set_state_test.c b/tools/testing/selftests/kvm/x86/nested_set_state_test.c index 0f2102b43629..831380732671 100644 --- a/tools/testing/selftests/kvm/x86/nested_set_state_test.c +++ b/tools/testing/selftests/kvm/x86/nested_set_state_test.c @@ -250,14 +250,14 @@ void test_vmx_nested_state(struct kvm_vcpu *vcpu) static void vcpu_efer_enable_svm(struct kvm_vcpu *vcpu) { - uint64_t old_efer = vcpu_get_msr(vcpu, MSR_EFER); + u64 old_efer = vcpu_get_msr(vcpu, MSR_EFER); vcpu_set_msr(vcpu, MSR_EFER, old_efer | EFER_SVME); } static void vcpu_efer_disable_svm(struct kvm_vcpu *vcpu) { - uint64_t old_efer = vcpu_get_msr(vcpu, MSR_EFER); + u64 old_efer = vcpu_get_msr(vcpu, MSR_EFER); vcpu_set_msr(vcpu, MSR_EFER, old_efer & ~EFER_SVME); } diff --git a/tools/testing/selftests/kvm/x86/nested_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86/nested_tsc_adjust_test.c index 2839f650e5c9..f0e4adac4751 100644 --- a/tools/testing/selftests/kvm/x86/nested_tsc_adjust_test.c +++ b/tools/testing/selftests/kvm/x86/nested_tsc_adjust_test.c @@ -53,9 +53,9 @@ enum { /* The virtual machine object. */ static struct kvm_vm *vm; -static void check_ia32_tsc_adjust(int64_t max) +static void check_ia32_tsc_adjust(s64 max) { - int64_t adjust; + s64 adjust; adjust = rdmsr(MSR_IA32_TSC_ADJUST); GUEST_SYNC(adjust); @@ -64,7 +64,7 @@ static void check_ia32_tsc_adjust(int64_t max) static void l2_guest_code(void) { - uint64_t l1_tsc = rdtsc() - TSC_OFFSET_VALUE; + u64 l1_tsc = rdtsc() - TSC_OFFSET_VALUE; wrmsr(MSR_IA32_TSC, l1_tsc - TSC_ADJUST_VALUE); check_ia32_tsc_adjust(-2 * TSC_ADJUST_VALUE); @@ -88,7 +88,7 @@ static void l1_guest_code(void *data) */ if (this_cpu_has(X86_FEATURE_VMX)) { struct vmx_pages *vmx_pages = data; - uint32_t control; + u32 control; GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages)); GUEST_ASSERT(load_vmcs(vmx_pages)); @@ -117,7 +117,7 @@ static void l1_guest_code(void *data) GUEST_DONE(); } -static void report(int64_t val) +static void report(s64 val) { pr_info("IA32_TSC_ADJUST is %ld (%lld * TSC_ADJUST_VALUE + %lld).\n", val, val / TSC_ADJUST_VALUE, val % TSC_ADJUST_VALUE); @@ -125,7 +125,7 @@ static void report(int64_t val) int main(int argc, char *argv[]) { - vm_vaddr_t nested_gva; + gva_t nested_gva; struct kvm_vcpu *vcpu; TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX) || diff --git a/tools/testing/selftests/kvm/x86/nested_tsc_scaling_test.c b/tools/testing/selftests/kvm/x86/nested_tsc_scaling_test.c index 4260c9e4f489..190e93af20a1 100644 --- a/tools/testing/selftests/kvm/x86/nested_tsc_scaling_test.c +++ b/tools/testing/selftests/kvm/x86/nested_tsc_scaling_test.c @@ -19,7 +19,7 @@ /* L2 is scaled up (from L1's perspective) by this factor */ #define L2_SCALE_FACTOR 4ULL -#define TSC_OFFSET_L2 ((uint64_t) -33125236320908) +#define TSC_OFFSET_L2 ((u64)-33125236320908) #define TSC_MULTIPLIER_L2 (L2_SCALE_FACTOR << 48) #define L2_GUEST_STACK_SIZE 64 @@ -35,9 +35,9 @@ enum { USLEEP, UCHECK_L1, UCHECK_L2 }; * measurements, a difference of 1% between the actual and the expected value * is tolerated. */ -static void compare_tsc_freq(uint64_t actual, uint64_t expected) +static void compare_tsc_freq(u64 actual, u64 expected) { - uint64_t tolerance, thresh_low, thresh_high; + u64 tolerance, thresh_low, thresh_high; tolerance = expected / 100; thresh_low = expected - tolerance; @@ -55,7 +55,7 @@ static void compare_tsc_freq(uint64_t actual, uint64_t expected) static void check_tsc_freq(int level) { - uint64_t tsc_start, tsc_end, tsc_freq; + u64 tsc_start, tsc_end, tsc_freq; /* * Reading the TSC twice with about a second's difference should give @@ -106,7 +106,7 @@ static void l1_svm_code(struct svm_test_data *svm) static void l1_vmx_code(struct vmx_pages *vmx_pages) { unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; - uint32_t control; + u32 control; /* check that L1's frequency looks alright before launching L2 */ check_tsc_freq(UCHECK_L1); @@ -152,14 +152,14 @@ int main(int argc, char *argv[]) { struct kvm_vcpu *vcpu; struct kvm_vm *vm; - vm_vaddr_t guest_gva = 0; - - uint64_t tsc_start, tsc_end; - uint64_t tsc_khz; - uint64_t l1_scale_factor; - uint64_t l0_tsc_freq = 0; - uint64_t l1_tsc_freq = 0; - uint64_t l2_tsc_freq = 0; + gva_t guest_gva = 0; + + u64 tsc_start, tsc_end; + u64 tsc_khz; + u64 l1_scale_factor; + u64 l0_tsc_freq = 0; + u64 l1_tsc_freq = 0; + u64 l2_tsc_freq = 0; TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX) || kvm_cpu_has(X86_FEATURE_SVM)); diff --git a/tools/testing/selftests/kvm/x86/nested_vmsave_vmload_test.c b/tools/testing/selftests/kvm/x86/nested_vmsave_vmload_test.c index 71717118d692..85d3f4cc76f3 100644 --- a/tools/testing/selftests/kvm/x86/nested_vmsave_vmload_test.c +++ b/tools/testing/selftests/kvm/x86/nested_vmsave_vmload_test.c @@ -128,7 +128,7 @@ static void l1_guest_code(struct svm_test_data *svm) int main(int argc, char *argv[]) { - vm_vaddr_t nested_gva = 0; + gva_t nested_gva = 0; struct vmcb *test_vmcb[2]; struct kvm_vcpu *vcpu; struct kvm_vm *vm; diff --git a/tools/testing/selftests/kvm/x86/nx_huge_pages_test.c b/tools/testing/selftests/kvm/x86/nx_huge_pages_test.c index c0d84827f736..70950067b989 100644 --- a/tools/testing/selftests/kvm/x86/nx_huge_pages_test.c +++ b/tools/testing/selftests/kvm/x86/nx_huge_pages_test.c @@ -32,7 +32,7 @@ #define RETURN_OPCODE 0xC3 /* Call the specified memory address. */ -static void guest_do_CALL(uint64_t target) +static void guest_do_CALL(u64 target) { ((void (*)(void)) target)(); } @@ -46,14 +46,14 @@ static void guest_do_CALL(uint64_t target) */ void guest_code(void) { - uint64_t hpage_1 = HPAGE_GVA; - uint64_t hpage_2 = hpage_1 + (PAGE_SIZE * 512); - uint64_t hpage_3 = hpage_2 + (PAGE_SIZE * 512); + u64 hpage_1 = HPAGE_GVA; + u64 hpage_2 = hpage_1 + (PAGE_SIZE * 512); + u64 hpage_3 = hpage_2 + (PAGE_SIZE * 512); - READ_ONCE(*(uint64_t *)hpage_1); + READ_ONCE(*(u64 *)hpage_1); GUEST_SYNC(1); - READ_ONCE(*(uint64_t *)hpage_2); + READ_ONCE(*(u64 *)hpage_2); GUEST_SYNC(2); guest_do_CALL(hpage_1); @@ -62,10 +62,10 @@ void guest_code(void) guest_do_CALL(hpage_3); GUEST_SYNC(4); - READ_ONCE(*(uint64_t *)hpage_1); + READ_ONCE(*(u64 *)hpage_1); GUEST_SYNC(5); - READ_ONCE(*(uint64_t *)hpage_3); + READ_ONCE(*(u64 *)hpage_3); GUEST_SYNC(6); } @@ -107,7 +107,7 @@ void run_test(int reclaim_period_ms, bool disable_nx_huge_pages, { struct kvm_vcpu *vcpu; struct kvm_vm *vm; - uint64_t nr_bytes; + u64 nr_bytes; void *hva; int r; diff --git a/tools/testing/selftests/kvm/x86/platform_info_test.c b/tools/testing/selftests/kvm/x86/platform_info_test.c index 9cbf283ebc55..80bb07e6531c 100644 --- a/tools/testing/selftests/kvm/x86/platform_info_test.c +++ b/tools/testing/selftests/kvm/x86/platform_info_test.c @@ -23,8 +23,8 @@ static void guest_code(void) { - uint64_t msr_platform_info; - uint8_t vector; + u64 msr_platform_info; + u8 vector; GUEST_SYNC(true); msr_platform_info = rdmsr(MSR_PLATFORM_INFO); @@ -42,7 +42,7 @@ int main(int argc, char *argv[]) { struct kvm_vcpu *vcpu; struct kvm_vm *vm; - uint64_t msr_platform_info; + u64 msr_platform_info; struct ucall uc; TEST_REQUIRE(kvm_has_cap(KVM_CAP_MSR_PLATFORM_INFO)); diff --git a/tools/testing/selftests/kvm/x86/pmu_counters_test.c b/tools/testing/selftests/kvm/x86/pmu_counters_test.c index 3eaa216b96c0..dc6afac3aa91 100644 --- a/tools/testing/selftests/kvm/x86/pmu_counters_test.c +++ b/tools/testing/selftests/kvm/x86/pmu_counters_test.c @@ -30,9 +30,9 @@ #define NUM_INSNS_RETIRED (NUM_LOOPS * NUM_INSNS_PER_LOOP + NUM_EXTRA_INSNS) /* Track which architectural events are supported by hardware. */ -static uint32_t hardware_pmu_arch_events; +static u32 hardware_pmu_arch_events; -static uint8_t kvm_pmu_version; +static u8 kvm_pmu_version; static bool kvm_has_perf_caps; #define X86_PMU_FEATURE_NULL \ @@ -57,7 +57,7 @@ struct kvm_intel_pmu_event { * kvm_x86_pmu_feature use syntax that's only valid in function scope, and the * compiler often thinks the feature definitions aren't compile-time constants. */ -static struct kvm_intel_pmu_event intel_event_to_feature(uint8_t idx) +static struct kvm_intel_pmu_event intel_event_to_feature(u8 idx) { const struct kvm_intel_pmu_event __intel_event_to_feature[] = { [INTEL_ARCH_CPU_CYCLES_INDEX] = { X86_PMU_FEATURE_CPU_CYCLES, X86_PMU_FEATURE_CPU_CYCLES_FIXED }, @@ -89,8 +89,8 @@ static struct kvm_intel_pmu_event intel_event_to_feature(uint8_t idx) static struct kvm_vm *pmu_vm_create_with_one_vcpu(struct kvm_vcpu **vcpu, void *guest_code, - uint8_t pmu_version, - uint64_t perf_capabilities) + u8 pmu_version, + u64 perf_capabilities) { struct kvm_vm *vm; @@ -132,7 +132,7 @@ static void run_vcpu(struct kvm_vcpu *vcpu) } while (uc.cmd != UCALL_DONE); } -static uint8_t guest_get_pmu_version(void) +static u8 guest_get_pmu_version(void) { /* * Return the effective PMU version, i.e. the minimum between what KVM @@ -141,7 +141,7 @@ static uint8_t guest_get_pmu_version(void) * supported by KVM to verify KVM doesn't freak out and do something * bizarre with an architecturally valid, but unsupported, version. */ - return min_t(uint8_t, kvm_pmu_version, this_cpu_property(X86_PROPERTY_PMU_VERSION)); + return min_t(u8, kvm_pmu_version, this_cpu_property(X86_PROPERTY_PMU_VERSION)); } /* @@ -153,9 +153,9 @@ static uint8_t guest_get_pmu_version(void) * Sanity check that in all cases, the event doesn't count when it's disabled, * and that KVM correctly emulates the write of an arbitrary value. */ -static void guest_assert_event_count(uint8_t idx, uint32_t pmc, uint32_t pmc_msr) +static void guest_assert_event_count(u8 idx, u32 pmc, u32 pmc_msr) { - uint64_t count; + u64 count; count = _rdpmc(pmc); if (!(hardware_pmu_arch_events & BIT(idx))) @@ -236,7 +236,7 @@ do { \ FEP "xor %%eax, %%eax\n\t" \ FEP "xor %%edx, %%edx\n\t" \ "wrmsr\n\t" \ - :: "a"((uint32_t)_value), "d"(_value >> 32), \ + :: "a"((u32)_value), "d"(_value >> 32), \ "c"(_msr), "D"(_msr), [m]"m"(kvm_pmu_version) \ ); \ } while (0) @@ -255,8 +255,8 @@ do { \ guest_assert_event_count(_idx, _pmc, _pmc_msr); \ } while (0) -static void __guest_test_arch_event(uint8_t idx, uint32_t pmc, uint32_t pmc_msr, - uint32_t ctrl_msr, uint64_t ctrl_msr_value) +static void __guest_test_arch_event(u8 idx, u32 pmc, u32 pmc_msr, + u32 ctrl_msr, u64 ctrl_msr_value) { GUEST_TEST_EVENT(idx, pmc, pmc_msr, ctrl_msr, ctrl_msr_value, ""); @@ -264,14 +264,14 @@ static void __guest_test_arch_event(uint8_t idx, uint32_t pmc, uint32_t pmc_msr, GUEST_TEST_EVENT(idx, pmc, pmc_msr, ctrl_msr, ctrl_msr_value, KVM_FEP); } -static void guest_test_arch_event(uint8_t idx) +static void guest_test_arch_event(u8 idx) { - uint32_t nr_gp_counters = this_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS); - uint32_t pmu_version = guest_get_pmu_version(); + u32 nr_gp_counters = this_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS); + u32 pmu_version = guest_get_pmu_version(); /* PERF_GLOBAL_CTRL exists only for Architectural PMU Version 2+. */ bool guest_has_perf_global_ctrl = pmu_version >= 2; struct kvm_x86_pmu_feature gp_event, fixed_event; - uint32_t base_pmc_msr; + u32 base_pmc_msr; unsigned int i; /* The host side shouldn't invoke this without a guest PMU. */ @@ -289,7 +289,7 @@ static void guest_test_arch_event(uint8_t idx) GUEST_ASSERT(nr_gp_counters); for (i = 0; i < nr_gp_counters; i++) { - uint64_t eventsel = ARCH_PERFMON_EVENTSEL_OS | + u64 eventsel = ARCH_PERFMON_EVENTSEL_OS | ARCH_PERFMON_EVENTSEL_ENABLE | intel_pmu_arch_events[idx]; @@ -320,7 +320,7 @@ static void guest_test_arch_event(uint8_t idx) static void guest_test_arch_events(void) { - uint8_t i; + u8 i; for (i = 0; i < NR_INTEL_ARCH_EVENTS; i++) guest_test_arch_event(i); @@ -328,8 +328,8 @@ static void guest_test_arch_events(void) GUEST_DONE(); } -static void test_arch_events(uint8_t pmu_version, uint64_t perf_capabilities, - uint8_t length, uint32_t unavailable_mask) +static void test_arch_events(u8 pmu_version, u64 perf_capabilities, + u8 length, u32 unavailable_mask) { struct kvm_vcpu *vcpu; struct kvm_vm *vm; @@ -373,11 +373,11 @@ __GUEST_ASSERT(expect_gp ? vector == GP_VECTOR : !vector, \ "Expected " #insn "(0x%x) to yield 0x%lx, got 0x%lx", \ msr, expected, val); -static void guest_test_rdpmc(uint32_t rdpmc_idx, bool expect_success, - uint64_t expected_val) +static void guest_test_rdpmc(u32 rdpmc_idx, bool expect_success, + u64 expected_val) { - uint8_t vector; - uint64_t val; + u8 vector; + u64 val; vector = rdpmc_safe(rdpmc_idx, &val); GUEST_ASSERT_PMC_MSR_ACCESS(RDPMC, rdpmc_idx, !expect_success, vector); @@ -393,19 +393,19 @@ static void guest_test_rdpmc(uint32_t rdpmc_idx, bool expect_success, GUEST_ASSERT_PMC_VALUE(RDPMC, rdpmc_idx, val, expected_val); } -static void guest_rd_wr_counters(uint32_t base_msr, uint8_t nr_possible_counters, - uint8_t nr_counters, uint32_t or_mask) +static void guest_rd_wr_counters(u32 base_msr, u8 nr_possible_counters, + u8 nr_counters, u32 or_mask) { const bool pmu_has_fast_mode = !guest_get_pmu_version(); - uint8_t i; + u8 i; for (i = 0; i < nr_possible_counters; i++) { /* * TODO: Test a value that validates full-width writes and the * width of the counters. */ - const uint64_t test_val = 0xffff; - const uint32_t msr = base_msr + i; + const u64 test_val = 0xffff; + const u32 msr = base_msr + i; /* * Fixed counters are supported if the counter is less than the @@ -418,12 +418,12 @@ static void guest_rd_wr_counters(uint32_t base_msr, uint8_t nr_possible_counters * KVM drops writes to MSR_P6_PERFCTR[0|1] if the counters are * unsupported, i.e. doesn't #GP and reads back '0'. */ - const uint64_t expected_val = expect_success ? test_val : 0; + const u64 expected_val = expect_success ? test_val : 0; const bool expect_gp = !expect_success && msr != MSR_P6_PERFCTR0 && msr != MSR_P6_PERFCTR1; - uint32_t rdpmc_idx; - uint8_t vector; - uint64_t val; + u32 rdpmc_idx; + u8 vector; + u64 val; vector = wrmsr_safe(msr, test_val); GUEST_ASSERT_PMC_MSR_ACCESS(WRMSR, msr, expect_gp, vector); @@ -461,9 +461,9 @@ static void guest_rd_wr_counters(uint32_t base_msr, uint8_t nr_possible_counters static void guest_test_gp_counters(void) { - uint8_t pmu_version = guest_get_pmu_version(); - uint8_t nr_gp_counters = 0; - uint32_t base_msr; + u8 pmu_version = guest_get_pmu_version(); + u8 nr_gp_counters = 0; + u32 base_msr; if (pmu_version) nr_gp_counters = this_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS); @@ -477,7 +477,7 @@ static void guest_test_gp_counters(void) * counters, of which there are none. */ if (pmu_version > 1) { - uint64_t global_ctrl = rdmsr(MSR_CORE_PERF_GLOBAL_CTRL); + u64 global_ctrl = rdmsr(MSR_CORE_PERF_GLOBAL_CTRL); if (nr_gp_counters) GUEST_ASSERT_EQ(global_ctrl, GENMASK_ULL(nr_gp_counters - 1, 0)); @@ -495,8 +495,8 @@ static void guest_test_gp_counters(void) GUEST_DONE(); } -static void test_gp_counters(uint8_t pmu_version, uint64_t perf_capabilities, - uint8_t nr_gp_counters) +static void test_gp_counters(u8 pmu_version, u64 perf_capabilities, + u8 nr_gp_counters) { struct kvm_vcpu *vcpu; struct kvm_vm *vm; @@ -514,9 +514,9 @@ static void test_gp_counters(uint8_t pmu_version, uint64_t perf_capabilities, static void guest_test_fixed_counters(void) { - uint64_t supported_bitmask = 0; - uint8_t nr_fixed_counters = 0; - uint8_t i; + u64 supported_bitmask = 0; + u8 nr_fixed_counters = 0; + u8 i; /* Fixed counters require Architectural vPMU Version 2+. */ if (guest_get_pmu_version() >= 2) @@ -533,8 +533,8 @@ static void guest_test_fixed_counters(void) nr_fixed_counters, supported_bitmask); for (i = 0; i < MAX_NR_FIXED_COUNTERS; i++) { - uint8_t vector; - uint64_t val; + u8 vector; + u64 val; if (i >= nr_fixed_counters && !(supported_bitmask & BIT_ULL(i))) { vector = wrmsr_safe(MSR_CORE_PERF_FIXED_CTR_CTRL, @@ -561,9 +561,8 @@ static void guest_test_fixed_counters(void) GUEST_DONE(); } -static void test_fixed_counters(uint8_t pmu_version, uint64_t perf_capabilities, - uint8_t nr_fixed_counters, - uint32_t supported_bitmask) +static void test_fixed_counters(u8 pmu_version, u64 perf_capabilities, + u8 nr_fixed_counters, u32 supported_bitmask) { struct kvm_vcpu *vcpu; struct kvm_vm *vm; @@ -583,14 +582,14 @@ static void test_fixed_counters(uint8_t pmu_version, uint64_t perf_capabilities, static void test_intel_counters(void) { - uint8_t nr_fixed_counters = kvm_cpu_property(X86_PROPERTY_PMU_NR_FIXED_COUNTERS); - uint8_t nr_gp_counters = kvm_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS); - uint8_t pmu_version = kvm_cpu_property(X86_PROPERTY_PMU_VERSION); + u8 nr_fixed_counters = kvm_cpu_property(X86_PROPERTY_PMU_NR_FIXED_COUNTERS); + u8 nr_gp_counters = kvm_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS); + u8 pmu_version = kvm_cpu_property(X86_PROPERTY_PMU_VERSION); unsigned int i; - uint8_t v, j; - uint32_t k; + u8 v, j; + u32 k; - const uint64_t perf_caps[] = { + const u64 perf_caps[] = { 0, PMU_CAP_FW_WRITES, }; @@ -602,7 +601,7 @@ static void test_intel_counters(void) * as alternating bit sequencues, e.g. to detect if KVM is checking the * wrong bit(s). */ - const uint32_t unavailable_masks[] = { + const u32 unavailable_masks[] = { 0x0, 0xffffffffu, 0xaaaaaaaau, @@ -620,7 +619,7 @@ static void test_intel_counters(void) * Intel, i.e. is the last version that is guaranteed to be backwards * compatible with KVM's existing behavior. */ - uint8_t max_pmu_version = max_t(typeof(pmu_version), pmu_version, 5); + u8 max_pmu_version = max_t(typeof(pmu_version), pmu_version, 5); /* * Detect the existence of events that aren't supported by selftests. diff --git a/tools/testing/selftests/kvm/x86/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86/pmu_event_filter_test.c index 93b61c077991..c1232344fda8 100644 --- a/tools/testing/selftests/kvm/x86/pmu_event_filter_test.c +++ b/tools/testing/selftests/kvm/x86/pmu_event_filter_test.c @@ -53,11 +53,11 @@ static const struct __kvm_pmu_event_filter base_event_filter = { }; struct { - uint64_t loads; - uint64_t stores; - uint64_t loads_stores; - uint64_t branches_retired; - uint64_t instructions_retired; + u64 loads; + u64 stores; + u64 loads_stores; + u64 branches_retired; + u64 instructions_retired; } pmc_results; /* @@ -75,9 +75,9 @@ static void guest_gp_handler(struct ex_regs *regs) * * Return on success. GUEST_SYNC(0) on error. */ -static void check_msr(uint32_t msr, uint64_t bits_to_flip) +static void check_msr(u32 msr, u64 bits_to_flip) { - uint64_t v = rdmsr(msr) ^ bits_to_flip; + u64 v = rdmsr(msr) ^ bits_to_flip; wrmsr(msr, v); if (rdmsr(msr) != v) @@ -89,10 +89,10 @@ static void check_msr(uint32_t msr, uint64_t bits_to_flip) GUEST_SYNC(-EIO); } -static void run_and_measure_loop(uint32_t msr_base) +static void run_and_measure_loop(u32 msr_base) { - const uint64_t branches_retired = rdmsr(msr_base + 0); - const uint64_t insn_retired = rdmsr(msr_base + 1); + const u64 branches_retired = rdmsr(msr_base + 0); + const u64 insn_retired = rdmsr(msr_base + 1); __asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES})); @@ -147,7 +147,7 @@ static void amd_guest_code(void) * Run the VM to the next GUEST_SYNC(value), and return the value passed * to the sync. Any other exit from the guest is fatal. */ -static uint64_t run_vcpu_to_sync(struct kvm_vcpu *vcpu) +static u64 run_vcpu_to_sync(struct kvm_vcpu *vcpu) { struct ucall uc; @@ -161,7 +161,7 @@ static uint64_t run_vcpu_to_sync(struct kvm_vcpu *vcpu) static void run_vcpu_and_sync_pmc_results(struct kvm_vcpu *vcpu) { - uint64_t r; + u64 r; memset(&pmc_results, 0, sizeof(pmc_results)); sync_global_to_guest(vcpu->vm, pmc_results); @@ -182,7 +182,7 @@ static void run_vcpu_and_sync_pmc_results(struct kvm_vcpu *vcpu) */ static bool sanity_check_pmu(struct kvm_vcpu *vcpu) { - uint64_t r; + u64 r; vm_install_exception_handler(vcpu->vm, GP_VECTOR, guest_gp_handler); r = run_vcpu_to_sync(vcpu); @@ -195,7 +195,7 @@ static bool sanity_check_pmu(struct kvm_vcpu *vcpu) * Remove the first occurrence of 'event' (if any) from the filter's * event list. */ -static void remove_event(struct __kvm_pmu_event_filter *f, uint64_t event) +static void remove_event(struct __kvm_pmu_event_filter *f, u64 event) { bool found = false; int i; @@ -212,8 +212,8 @@ static void remove_event(struct __kvm_pmu_event_filter *f, uint64_t event) #define ASSERT_PMC_COUNTING_INSTRUCTIONS() \ do { \ - uint64_t br = pmc_results.branches_retired; \ - uint64_t ir = pmc_results.instructions_retired; \ + u64 br = pmc_results.branches_retired; \ + u64 ir = pmc_results.instructions_retired; \ bool br_matched = this_pmu_has_errata(BRANCHES_RETIRED_OVERCOUNT) ? \ br >= NUM_BRANCHES : br == NUM_BRANCHES; \ \ @@ -228,8 +228,8 @@ do { \ #define ASSERT_PMC_NOT_COUNTING_INSTRUCTIONS() \ do { \ - uint64_t br = pmc_results.branches_retired; \ - uint64_t ir = pmc_results.instructions_retired; \ + u64 br = pmc_results.branches_retired; \ + u64 ir = pmc_results.instructions_retired; \ \ TEST_ASSERT(!br, "%s: Branch instructions retired = %lu (expected 0)", \ __func__, br); \ @@ -378,7 +378,7 @@ static bool use_amd_pmu(void) static bool supports_event_mem_inst_retired(void) { - uint32_t eax, ebx, ecx, edx; + u32 eax, ebx, ecx, edx; cpuid(1, &eax, &ebx, &ecx, &edx); if (x86_family(eax) == 0x6) { @@ -415,15 +415,15 @@ static bool supports_event_mem_inst_retired(void) #define EXCLUDE_MASKED_ENTRY(event_select, mask, match) \ KVM_PMU_ENCODE_MASKED_ENTRY(event_select, mask, match, true) -static void masked_events_guest_test(uint32_t msr_base) +static void masked_events_guest_test(u32 msr_base) { /* * The actual value of the counters don't determine the outcome of * the test. Only that they are zero or non-zero. */ - const uint64_t loads = rdmsr(msr_base + 0); - const uint64_t stores = rdmsr(msr_base + 1); - const uint64_t loads_stores = rdmsr(msr_base + 2); + const u64 loads = rdmsr(msr_base + 0); + const u64 stores = rdmsr(msr_base + 1); + const u64 loads_stores = rdmsr(msr_base + 2); int val; @@ -476,7 +476,7 @@ static void amd_masked_events_guest_code(void) } static void run_masked_events_test(struct kvm_vcpu *vcpu, - const uint64_t masked_events[], + const u64 masked_events[], const int nmasked_events) { struct __kvm_pmu_event_filter f = { @@ -485,7 +485,7 @@ static void run_masked_events_test(struct kvm_vcpu *vcpu, .flags = KVM_PMU_EVENT_FLAG_MASKED_EVENTS, }; - memcpy(f.events, masked_events, sizeof(uint64_t) * nmasked_events); + memcpy(f.events, masked_events, sizeof(u64) * nmasked_events); test_with_filter(vcpu, &f); } @@ -494,12 +494,12 @@ static void run_masked_events_test(struct kvm_vcpu *vcpu, #define ALLOW_LOADS_STORES BIT(2) struct masked_events_test { - uint64_t intel_events[MAX_TEST_EVENTS]; - uint64_t intel_event_end; - uint64_t amd_events[MAX_TEST_EVENTS]; - uint64_t amd_event_end; + u64 intel_events[MAX_TEST_EVENTS]; + u64 intel_event_end; + u64 amd_events[MAX_TEST_EVENTS]; + u64 amd_event_end; const char *msg; - uint32_t flags; + u32 flags; }; /* @@ -582,9 +582,9 @@ const struct masked_events_test test_cases[] = { }; static int append_test_events(const struct masked_events_test *test, - uint64_t *events, int nevents) + u64 *events, int nevents) { - const uint64_t *evts; + const u64 *evts; int i; evts = use_intel_pmu() ? test->intel_events : test->amd_events; @@ -603,7 +603,7 @@ static bool bool_eq(bool a, bool b) return a == b; } -static void run_masked_events_tests(struct kvm_vcpu *vcpu, uint64_t *events, +static void run_masked_events_tests(struct kvm_vcpu *vcpu, u64 *events, int nevents) { int ntests = ARRAY_SIZE(test_cases); @@ -630,7 +630,7 @@ static void run_masked_events_tests(struct kvm_vcpu *vcpu, uint64_t *events, } } -static void add_dummy_events(uint64_t *events, int nevents) +static void add_dummy_events(u64 *events, int nevents) { int i; @@ -650,7 +650,7 @@ static void add_dummy_events(uint64_t *events, int nevents) static void test_masked_events(struct kvm_vcpu *vcpu) { int nevents = KVM_PMU_EVENT_FILTER_MAX_EVENTS - MAX_TEST_EVENTS; - uint64_t events[KVM_PMU_EVENT_FILTER_MAX_EVENTS]; + u64 events[KVM_PMU_EVENT_FILTER_MAX_EVENTS]; /* Run the test cases against a sparse PMU event filter. */ run_masked_events_tests(vcpu, events, 0); @@ -668,8 +668,8 @@ static int set_pmu_event_filter(struct kvm_vcpu *vcpu, return __vm_ioctl(vcpu->vm, KVM_SET_PMU_EVENT_FILTER, f); } -static int set_pmu_single_event_filter(struct kvm_vcpu *vcpu, uint64_t event, - uint32_t flags, uint32_t action) +static int set_pmu_single_event_filter(struct kvm_vcpu *vcpu, u64 event, + u32 flags, u32 action) { struct __kvm_pmu_event_filter f = { .nevents = 1, @@ -685,9 +685,9 @@ static int set_pmu_single_event_filter(struct kvm_vcpu *vcpu, uint64_t event, static void test_filter_ioctl(struct kvm_vcpu *vcpu) { - uint8_t nr_fixed_counters = kvm_cpu_property(X86_PROPERTY_PMU_NR_FIXED_COUNTERS); + u8 nr_fixed_counters = kvm_cpu_property(X86_PROPERTY_PMU_NR_FIXED_COUNTERS); struct __kvm_pmu_event_filter f; - uint64_t e = ~0ul; + u64 e = ~0ul; int r; /* @@ -729,7 +729,7 @@ static void test_filter_ioctl(struct kvm_vcpu *vcpu) TEST_ASSERT(!r, "Masking non-existent fixed counters should be allowed"); } -static void intel_run_fixed_counter_guest_code(uint8_t idx) +static void intel_run_fixed_counter_guest_code(u8 idx) { for (;;) { wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0); @@ -745,8 +745,8 @@ static void intel_run_fixed_counter_guest_code(uint8_t idx) } } -static uint64_t test_with_fixed_counter_filter(struct kvm_vcpu *vcpu, - uint32_t action, uint32_t bitmap) +static u64 test_with_fixed_counter_filter(struct kvm_vcpu *vcpu, + u32 action, u32 bitmap) { struct __kvm_pmu_event_filter f = { .action = action, @@ -757,9 +757,9 @@ static uint64_t test_with_fixed_counter_filter(struct kvm_vcpu *vcpu, return run_vcpu_to_sync(vcpu); } -static uint64_t test_set_gp_and_fixed_event_filter(struct kvm_vcpu *vcpu, - uint32_t action, - uint32_t bitmap) +static u64 test_set_gp_and_fixed_event_filter(struct kvm_vcpu *vcpu, + u32 action, + u32 bitmap) { struct __kvm_pmu_event_filter f = base_event_filter; @@ -770,12 +770,12 @@ static uint64_t test_set_gp_and_fixed_event_filter(struct kvm_vcpu *vcpu, return run_vcpu_to_sync(vcpu); } -static void __test_fixed_counter_bitmap(struct kvm_vcpu *vcpu, uint8_t idx, - uint8_t nr_fixed_counters) +static void __test_fixed_counter_bitmap(struct kvm_vcpu *vcpu, u8 idx, + u8 nr_fixed_counters) { unsigned int i; - uint32_t bitmap; - uint64_t count; + u32 bitmap; + u64 count; TEST_ASSERT(nr_fixed_counters < sizeof(bitmap) * 8, "Invalid nr_fixed_counters"); @@ -815,10 +815,10 @@ static void __test_fixed_counter_bitmap(struct kvm_vcpu *vcpu, uint8_t idx, static void test_fixed_counter_bitmap(void) { - uint8_t nr_fixed_counters = kvm_cpu_property(X86_PROPERTY_PMU_NR_FIXED_COUNTERS); + u8 nr_fixed_counters = kvm_cpu_property(X86_PROPERTY_PMU_NR_FIXED_COUNTERS); struct kvm_vm *vm; struct kvm_vcpu *vcpu; - uint8_t idx; + u8 idx; /* * Check that pmu_event_filter works as expected when it's applied to diff --git a/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c b/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c index 1969f4ab9b28..1d2f5d4fd45d 100644 --- a/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c +++ b/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c @@ -23,13 +23,13 @@ #include <processor.h> #define BASE_DATA_SLOT 10 -#define BASE_DATA_GPA ((uint64_t)(1ull << 32)) -#define PER_CPU_DATA_SIZE ((uint64_t)(SZ_2M + PAGE_SIZE)) +#define BASE_DATA_GPA ((u64)(1ull << 32)) +#define PER_CPU_DATA_SIZE ((u64)(SZ_2M + PAGE_SIZE)) /* Horrific macro so that the line info is captured accurately :-( */ #define memcmp_g(gpa, pattern, size) \ do { \ - uint8_t *mem = (uint8_t *)gpa; \ + u8 *mem = (u8 *)gpa; \ size_t i; \ \ for (i = 0; i < size; i++) \ @@ -38,7 +38,7 @@ do { \ pattern, i, gpa + i, mem[i]); \ } while (0) -static void memcmp_h(uint8_t *mem, uint64_t gpa, uint8_t pattern, size_t size) +static void memcmp_h(u8 *mem, gpa_t gpa, u8 pattern, size_t size) { size_t i; @@ -70,13 +70,13 @@ enum ucall_syncs { SYNC_PRIVATE, }; -static void guest_sync_shared(uint64_t gpa, uint64_t size, - uint8_t current_pattern, uint8_t new_pattern) +static void guest_sync_shared(gpa_t gpa, u64 size, + u8 current_pattern, u8 new_pattern) { GUEST_SYNC5(SYNC_SHARED, gpa, size, current_pattern, new_pattern); } -static void guest_sync_private(uint64_t gpa, uint64_t size, uint8_t pattern) +static void guest_sync_private(gpa_t gpa, u64 size, u8 pattern) { GUEST_SYNC4(SYNC_PRIVATE, gpa, size, pattern); } @@ -86,10 +86,10 @@ static void guest_sync_private(uint64_t gpa, uint64_t size, uint8_t pattern) #define MAP_GPA_SHARED BIT(1) #define MAP_GPA_DO_FALLOCATE BIT(2) -static void guest_map_mem(uint64_t gpa, uint64_t size, bool map_shared, +static void guest_map_mem(gpa_t gpa, u64 size, bool map_shared, bool do_fallocate) { - uint64_t flags = MAP_GPA_SET_ATTRIBUTES; + u64 flags = MAP_GPA_SET_ATTRIBUTES; if (map_shared) flags |= MAP_GPA_SHARED; @@ -98,19 +98,19 @@ static void guest_map_mem(uint64_t gpa, uint64_t size, bool map_shared, kvm_hypercall_map_gpa_range(gpa, size, flags); } -static void guest_map_shared(uint64_t gpa, uint64_t size, bool do_fallocate) +static void guest_map_shared(gpa_t gpa, u64 size, bool do_fallocate) { guest_map_mem(gpa, size, true, do_fallocate); } -static void guest_map_private(uint64_t gpa, uint64_t size, bool do_fallocate) +static void guest_map_private(gpa_t gpa, u64 size, bool do_fallocate) { guest_map_mem(gpa, size, false, do_fallocate); } struct { - uint64_t offset; - uint64_t size; + u64 offset; + u64 size; } static const test_ranges[] = { GUEST_STAGE(0, PAGE_SIZE), GUEST_STAGE(0, SZ_2M), @@ -119,11 +119,11 @@ struct { GUEST_STAGE(SZ_2M, PAGE_SIZE), }; -static void guest_test_explicit_conversion(uint64_t base_gpa, bool do_fallocate) +static void guest_test_explicit_conversion(u64 base_gpa, bool do_fallocate) { - const uint8_t def_p = 0xaa; - const uint8_t init_p = 0xcc; - uint64_t j; + const u8 def_p = 0xaa; + const u8 init_p = 0xcc; + u64 j; int i; /* Memory should be shared by default. */ @@ -134,12 +134,12 @@ static void guest_test_explicit_conversion(uint64_t base_gpa, bool do_fallocate) memcmp_g(base_gpa, init_p, PER_CPU_DATA_SIZE); for (i = 0; i < ARRAY_SIZE(test_ranges); i++) { - uint64_t gpa = base_gpa + test_ranges[i].offset; - uint64_t size = test_ranges[i].size; - uint8_t p1 = 0x11; - uint8_t p2 = 0x22; - uint8_t p3 = 0x33; - uint8_t p4 = 0x44; + gpa_t gpa = base_gpa + test_ranges[i].offset; + u64 size = test_ranges[i].size; + u8 p1 = 0x11; + u8 p2 = 0x22; + u8 p3 = 0x33; + u8 p4 = 0x44; /* * Set the test region to pattern one to differentiate it from @@ -214,10 +214,10 @@ skip: } } -static void guest_punch_hole(uint64_t gpa, uint64_t size) +static void guest_punch_hole(gpa_t gpa, u64 size) { /* "Mapping" memory shared via fallocate() is done via PUNCH_HOLE. */ - uint64_t flags = MAP_GPA_SHARED | MAP_GPA_DO_FALLOCATE; + u64 flags = MAP_GPA_SHARED | MAP_GPA_DO_FALLOCATE; kvm_hypercall_map_gpa_range(gpa, size, flags); } @@ -227,9 +227,9 @@ static void guest_punch_hole(uint64_t gpa, uint64_t size) * proper conversion. Freeing (PUNCH_HOLE) should zap SPTEs, and reallocating * (subsequent fault) should zero memory. */ -static void guest_test_punch_hole(uint64_t base_gpa, bool precise) +static void guest_test_punch_hole(u64 base_gpa, bool precise) { - const uint8_t init_p = 0xcc; + const u8 init_p = 0xcc; int i; /* @@ -239,8 +239,8 @@ static void guest_test_punch_hole(uint64_t base_gpa, bool precise) guest_map_private(base_gpa, PER_CPU_DATA_SIZE, false); for (i = 0; i < ARRAY_SIZE(test_ranges); i++) { - uint64_t gpa = base_gpa + test_ranges[i].offset; - uint64_t size = test_ranges[i].size; + gpa_t gpa = base_gpa + test_ranges[i].offset; + u64 size = test_ranges[i].size; /* * Free all memory before each iteration, even for the !precise @@ -268,7 +268,7 @@ static void guest_test_punch_hole(uint64_t base_gpa, bool precise) } } -static void guest_code(uint64_t base_gpa) +static void guest_code(u64 base_gpa) { /* * Run the conversion test twice, with and without doing fallocate() on @@ -289,8 +289,8 @@ static void guest_code(uint64_t base_gpa) static void handle_exit_hypercall(struct kvm_vcpu *vcpu) { struct kvm_run *run = vcpu->run; - uint64_t gpa = run->hypercall.args[0]; - uint64_t size = run->hypercall.args[1] * PAGE_SIZE; + gpa_t gpa = run->hypercall.args[0]; + u64 size = run->hypercall.args[1] * PAGE_SIZE; bool set_attributes = run->hypercall.args[2] & MAP_GPA_SET_ATTRIBUTES; bool map_shared = run->hypercall.args[2] & MAP_GPA_SHARED; bool do_fallocate = run->hypercall.args[2] & MAP_GPA_DO_FALLOCATE; @@ -337,7 +337,7 @@ static void *__test_mem_conversions(void *__vcpu) case UCALL_ABORT: REPORT_GUEST_ASSERT(uc); case UCALL_SYNC: { - uint64_t gpa = uc.args[1]; + gpa_t gpa = uc.args[1]; size_t size = uc.args[2]; size_t i; @@ -347,7 +347,7 @@ static void *__test_mem_conversions(void *__vcpu) for (i = 0; i < size; i += vm->page_size) { size_t nr_bytes = min_t(size_t, vm->page_size, size - i); - uint8_t *hva = addr_gpa2hva(vm, gpa + i); + u8 *hva = addr_gpa2hva(vm, gpa + i); /* In all cases, the host should observe the shared data. */ memcmp_h(hva, gpa + i, uc.args[3], nr_bytes); @@ -366,8 +366,8 @@ static void *__test_mem_conversions(void *__vcpu) } } -static void test_mem_conversions(enum vm_mem_backing_src_type src_type, uint32_t nr_vcpus, - uint32_t nr_memslots) +static void test_mem_conversions(enum vm_mem_backing_src_type src_type, u32 nr_vcpus, + u32 nr_memslots) { /* * Allocate enough memory so that each vCPU's chunk of memory can be @@ -402,7 +402,7 @@ static void test_mem_conversions(enum vm_mem_backing_src_type src_type, uint32_t KVM_MEM_GUEST_MEMFD, memfd, slot_size * i); for (i = 0; i < nr_vcpus; i++) { - uint64_t gpa = BASE_DATA_GPA + i * per_cpu_size; + gpa_t gpa = BASE_DATA_GPA + i * per_cpu_size; vcpu_args_set(vcpus[i], 1, gpa); @@ -450,8 +450,8 @@ static void usage(const char *cmd) int main(int argc, char *argv[]) { enum vm_mem_backing_src_type src_type = DEFAULT_VM_MEM_SRC; - uint32_t nr_memslots = 1; - uint32_t nr_vcpus = 1; + u32 nr_memslots = 1; + u32 nr_vcpus = 1; int opt; TEST_REQUIRE(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM)); diff --git a/tools/testing/selftests/kvm/x86/private_mem_kvm_exits_test.c b/tools/testing/selftests/kvm/x86/private_mem_kvm_exits_test.c index 13e72fcec8dd..10db9fe6d906 100644 --- a/tools/testing/selftests/kvm/x86/private_mem_kvm_exits_test.c +++ b/tools/testing/selftests/kvm/x86/private_mem_kvm_exits_test.c @@ -17,17 +17,17 @@ #define EXITS_TEST_SIZE (EXITS_TEST_NPAGES * PAGE_SIZE) #define EXITS_TEST_SLOT 10 -static uint64_t guest_repeatedly_read(void) +static u64 guest_repeatedly_read(void) { - volatile uint64_t value; + volatile u64 value; while (true) - value = *((uint64_t *) EXITS_TEST_GVA); + value = *((u64 *)EXITS_TEST_GVA); return value; } -static uint32_t run_vcpu_get_exit_reason(struct kvm_vcpu *vcpu) +static u32 run_vcpu_get_exit_reason(struct kvm_vcpu *vcpu) { int r; @@ -50,7 +50,7 @@ static void test_private_access_memslot_deleted(void) struct kvm_vcpu *vcpu; pthread_t vm_thread; void *thread_return; - uint32_t exit_reason; + u32 exit_reason; vm = vm_create_shape_with_one_vcpu(protected_vm_shape, &vcpu, guest_repeatedly_read); @@ -72,7 +72,7 @@ static void test_private_access_memslot_deleted(void) vm_mem_region_delete(vm, EXITS_TEST_SLOT); pthread_join(vm_thread, &thread_return); - exit_reason = (uint32_t)(uint64_t)thread_return; + exit_reason = (u32)(u64)thread_return; TEST_ASSERT_EQ(exit_reason, KVM_EXIT_MEMORY_FAULT); TEST_ASSERT_EQ(vcpu->run->memory_fault.flags, KVM_MEMORY_EXIT_FLAG_PRIVATE); @@ -86,7 +86,7 @@ static void test_private_access_memslot_not_private(void) { struct kvm_vm *vm; struct kvm_vcpu *vcpu; - uint32_t exit_reason; + u32 exit_reason; vm = vm_create_shape_with_one_vcpu(protected_vm_shape, &vcpu, guest_repeatedly_read); diff --git a/tools/testing/selftests/kvm/x86/set_boot_cpu_id.c b/tools/testing/selftests/kvm/x86/set_boot_cpu_id.c index 49913784bc82..8e3898646c69 100644 --- a/tools/testing/selftests/kvm/x86/set_boot_cpu_id.c +++ b/tools/testing/selftests/kvm/x86/set_boot_cpu_id.c @@ -86,11 +86,11 @@ static void run_vcpu(struct kvm_vcpu *vcpu) } } -static struct kvm_vm *create_vm(uint32_t nr_vcpus, uint32_t bsp_vcpu_id, +static struct kvm_vm *create_vm(u32 nr_vcpus, u32 bsp_vcpu_id, struct kvm_vcpu *vcpus[]) { struct kvm_vm *vm; - uint32_t i; + u32 i; vm = vm_create(nr_vcpus); @@ -104,7 +104,7 @@ static struct kvm_vm *create_vm(uint32_t nr_vcpus, uint32_t bsp_vcpu_id, return vm; } -static void run_vm_bsp(uint32_t bsp_vcpu_id) +static void run_vm_bsp(u32 bsp_vcpu_id) { struct kvm_vcpu *vcpus[2]; struct kvm_vm *vm; diff --git a/tools/testing/selftests/kvm/x86/set_sregs_test.c b/tools/testing/selftests/kvm/x86/set_sregs_test.c index f4095a3d1278..8e654cc9ab16 100644 --- a/tools/testing/selftests/kvm/x86/set_sregs_test.c +++ b/tools/testing/selftests/kvm/x86/set_sregs_test.c @@ -46,9 +46,9 @@ do { \ X86_CR4_MCE | X86_CR4_PGE | X86_CR4_PCE | \ X86_CR4_OSFXSR | X86_CR4_OSXMMEXCPT) -static uint64_t calc_supported_cr4_feature_bits(void) +static u64 calc_supported_cr4_feature_bits(void) { - uint64_t cr4 = KVM_ALWAYS_ALLOWED_CR4; + u64 cr4 = KVM_ALWAYS_ALLOWED_CR4; if (kvm_cpu_has(X86_FEATURE_UMIP)) cr4 |= X86_CR4_UMIP; @@ -74,7 +74,7 @@ static uint64_t calc_supported_cr4_feature_bits(void) return cr4; } -static void test_cr_bits(struct kvm_vcpu *vcpu, uint64_t cr4) +static void test_cr_bits(struct kvm_vcpu *vcpu, u64 cr4) { struct kvm_sregs sregs; int rc, i; diff --git a/tools/testing/selftests/kvm/x86/sev_init2_tests.c b/tools/testing/selftests/kvm/x86/sev_init2_tests.c index b238615196ad..8eeba2327c7c 100644 --- a/tools/testing/selftests/kvm/x86/sev_init2_tests.c +++ b/tools/testing/selftests/kvm/x86/sev_init2_tests.c @@ -34,7 +34,7 @@ static int __sev_ioctl(int vm_fd, int cmd_id, void *data) { struct kvm_sev_cmd cmd = { .id = cmd_id, - .data = (uint64_t)data, + .data = (u64)data, .sev_fd = open_sev_dev_path_or_exit(), }; int ret; @@ -94,7 +94,7 @@ void test_vm_types(void) "VM type is KVM_X86_SW_PROTECTED_VM"); } -void test_flags(uint32_t vm_type) +void test_flags(u32 vm_type) { int i; @@ -104,7 +104,7 @@ void test_flags(uint32_t vm_type) "invalid flag"); } -void test_features(uint32_t vm_type, uint64_t supported_features) +void test_features(u32 vm_type, u64 supported_features) { int i; diff --git a/tools/testing/selftests/kvm/x86/sev_smoke_test.c b/tools/testing/selftests/kvm/x86/sev_smoke_test.c index 8bd37a476f15..1a49ee391586 100644 --- a/tools/testing/selftests/kvm/x86/sev_smoke_test.c +++ b/tools/testing/selftests/kvm/x86/sev_smoke_test.c @@ -13,9 +13,9 @@ #include "linux/psp-sev.h" #include "sev.h" -static void guest_sev_test_msr(uint32_t msr) +static void guest_sev_test_msr(u32 msr) { - uint64_t val = rdmsr(msr); + u64 val = rdmsr(msr); wrmsr(msr, val); GUEST_ASSERT(val == rdmsr(msr)); @@ -23,7 +23,7 @@ static void guest_sev_test_msr(uint32_t msr) #define guest_sev_test_reg(reg) \ do { \ - uint64_t val = get_##reg(); \ + u64 val = get_##reg(); \ \ set_##reg(val); \ GUEST_ASSERT(val == get_##reg()); \ @@ -42,7 +42,7 @@ static void guest_sev_test_regs(void) static void guest_snp_code(void) { - uint64_t sev_msr = rdmsr(MSR_AMD64_SEV); + u64 sev_msr = rdmsr(MSR_AMD64_SEV); GUEST_ASSERT(sev_msr & MSR_AMD64_SEV_ENABLED); GUEST_ASSERT(sev_msr & MSR_AMD64_SEV_ES_ENABLED); @@ -104,19 +104,19 @@ static void compare_xsave(u8 *from_host, u8 *from_guest) abort(); } -static void test_sync_vmsa(uint32_t type, uint64_t policy) +static void test_sync_vmsa(u32 type, u64 policy) { struct kvm_vcpu *vcpu; struct kvm_vm *vm; - vm_vaddr_t gva; + gva_t gva; void *hva; double x87val = M_PI; struct kvm_xsave __attribute__((aligned(64))) xsave = { 0 }; vm = vm_sev_create_with_one_vcpu(type, guest_code_xsave, &vcpu); - gva = vm_vaddr_alloc_shared(vm, PAGE_SIZE, KVM_UTIL_MIN_VADDR, - MEM_REGION_TEST_DATA); + gva = vm_alloc_shared(vm, PAGE_SIZE, KVM_UTIL_MIN_VADDR, + MEM_REGION_TEST_DATA); hva = addr_gva2hva(vm, gva); vcpu_args_set(vcpu, 1, gva); @@ -150,7 +150,7 @@ static void test_sync_vmsa(uint32_t type, uint64_t policy) kvm_vm_free(vm); } -static void test_sev(void *guest_code, uint32_t type, uint64_t policy) +static void test_sev(void *guest_code, u32 type, u64 policy) { struct kvm_vcpu *vcpu; struct kvm_vm *vm; @@ -201,7 +201,7 @@ static void guest_shutdown_code(void) __asm__ __volatile__("ud2"); } -static void test_sev_shutdown(uint32_t type, uint64_t policy) +static void test_sev_shutdown(u32 type, u64 policy) { struct kvm_vcpu *vcpu; struct kvm_vm *vm; @@ -218,7 +218,7 @@ static void test_sev_shutdown(uint32_t type, uint64_t policy) kvm_vm_free(vm); } -static void test_sev_smoke(void *guest, uint32_t type, uint64_t policy) +static void test_sev_smoke(void *guest, u32 type, u64 policy) { const u64 xf_mask = XFEATURE_MASK_X87_AVX; diff --git a/tools/testing/selftests/kvm/x86/smaller_maxphyaddr_emulation_test.c b/tools/testing/selftests/kvm/x86/smaller_maxphyaddr_emulation_test.c index 0e8aec568010..3dca85e95478 100644 --- a/tools/testing/selftests/kvm/x86/smaller_maxphyaddr_emulation_test.c +++ b/tools/testing/selftests/kvm/x86/smaller_maxphyaddr_emulation_test.c @@ -20,8 +20,8 @@ static void guest_code(bool tdp_enabled) { - uint64_t error_code; - uint64_t vector; + u64 error_code; + u64 vector; vector = kvm_asm_safe_ec(FLDS_MEM_EAX, error_code, "a"(MEM_REGION_GVA)); @@ -47,8 +47,8 @@ int main(int argc, char *argv[]) struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct ucall uc; - uint64_t *hva; - uint64_t gpa; + u64 *hva; + gpa_t gpa; int rc; TEST_REQUIRE(kvm_has_cap(KVM_CAP_SMALLER_MAXPHYADDR)); diff --git a/tools/testing/selftests/kvm/x86/smm_test.c b/tools/testing/selftests/kvm/x86/smm_test.c index ade8412bf94a..740051167dbd 100644 --- a/tools/testing/selftests/kvm/x86/smm_test.c +++ b/tools/testing/selftests/kvm/x86/smm_test.c @@ -34,13 +34,13 @@ * independent subset of asm here. * SMI handler always report back fixed stage SMRAM_STAGE. */ -uint8_t smi_handler[] = { +u8 smi_handler[] = { 0xb0, SMRAM_STAGE, /* mov $SMRAM_STAGE, %al */ 0xe4, SYNC_PORT, /* in $SYNC_PORT, %al */ 0x0f, 0xaa, /* rsm */ }; -static inline void sync_with_host(uint64_t phase) +static inline void sync_with_host(u64 phase) { asm volatile("in $" XSTR(SYNC_PORT)", %%al \n" : "+a" (phase)); @@ -65,7 +65,7 @@ static void guest_code(void *arg) { #define L2_GUEST_STACK_SIZE 64 unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; - uint64_t apicbase = rdmsr(MSR_IA32_APICBASE); + u64 apicbase = rdmsr(MSR_IA32_APICBASE); struct svm_test_data *svm = arg; struct vmx_pages *vmx_pages = arg; @@ -113,7 +113,7 @@ static void guest_code(void *arg) int main(int argc, char *argv[]) { - vm_vaddr_t nested_gva = 0; + gva_t nested_gva = 0; struct kvm_vcpu *vcpu; struct kvm_regs regs; diff --git a/tools/testing/selftests/kvm/x86/state_test.c b/tools/testing/selftests/kvm/x86/state_test.c index 992a52504a4a..409c6cc9f921 100644 --- a/tools/testing/selftests/kvm/x86/state_test.c +++ b/tools/testing/selftests/kvm/x86/state_test.c @@ -144,8 +144,8 @@ static void __attribute__((__flatten__)) guest_code(void *arg) GUEST_SYNC(1); if (this_cpu_has(X86_FEATURE_XSAVE)) { - uint64_t supported_xcr0 = this_cpu_supported_xcr0(); - uint8_t buffer[PAGE_SIZE]; + u64 supported_xcr0 = this_cpu_supported_xcr0(); + u8 buffer[PAGE_SIZE]; memset(buffer, 0xcc, sizeof(buffer)); @@ -172,8 +172,8 @@ static void __attribute__((__flatten__)) guest_code(void *arg) } if (this_cpu_has(X86_FEATURE_MPX)) { - uint64_t bounds[2] = { 10, 0xffffffffull }; - uint64_t output[2] = { }; + u64 bounds[2] = { 10, 0xffffffffull }; + u64 output[2] = { }; GUEST_ASSERT(supported_xcr0 & XFEATURE_MASK_BNDREGS); GUEST_ASSERT(supported_xcr0 & XFEATURE_MASK_BNDCSR); @@ -257,8 +257,8 @@ void check_nested_state(int stage, struct kvm_x86_state *state) int main(int argc, char *argv[]) { - uint64_t *xstate_bv, saved_xstate_bv; - vm_vaddr_t nested_gva = 0; + u64 *xstate_bv, saved_xstate_bv; + gva_t nested_gva = 0; struct kvm_cpuid2 empty_cpuid = {}; struct kvm_regs regs1, regs2; struct kvm_vcpu *vcpu, *vcpuN; @@ -331,7 +331,7 @@ int main(int argc, char *argv[]) * supported features, even if something goes awry in saving * the original snapshot. */ - xstate_bv = (void *)&((uint8_t *)state->xsave->region)[512]; + xstate_bv = (void *)&((u8 *)state->xsave->region)[512]; saved_xstate_bv = *xstate_bv; vcpuN = __vm_vcpu_add(vm, vcpu->id + 1); diff --git a/tools/testing/selftests/kvm/x86/svm_int_ctl_test.c b/tools/testing/selftests/kvm/x86/svm_int_ctl_test.c index 917b6066cfc1..d3cc5e4f7883 100644 --- a/tools/testing/selftests/kvm/x86/svm_int_ctl_test.c +++ b/tools/testing/selftests/kvm/x86/svm_int_ctl_test.c @@ -82,7 +82,7 @@ static void l1_guest_code(struct svm_test_data *svm) int main(int argc, char *argv[]) { struct kvm_vcpu *vcpu; - vm_vaddr_t svm_gva; + gva_t svm_gva; struct kvm_vm *vm; struct ucall uc; diff --git a/tools/testing/selftests/kvm/x86/svm_lbr_nested_state.c b/tools/testing/selftests/kvm/x86/svm_lbr_nested_state.c index ff99438824d3..7fbfaa054c95 100644 --- a/tools/testing/selftests/kvm/x86/svm_lbr_nested_state.c +++ b/tools/testing/selftests/kvm/x86/svm_lbr_nested_state.c @@ -97,9 +97,9 @@ void test_lbrv_nested_state(bool nested_lbrv) { struct kvm_x86_state *state = NULL; struct kvm_vcpu *vcpu; - vm_vaddr_t svm_gva; struct kvm_vm *vm; struct ucall uc; + gva_t svm_gva; pr_info("Testing with nested LBRV %s\n", nested_lbrv ? "enabled" : "disabled"); diff --git a/tools/testing/selftests/kvm/x86/svm_nested_clear_efer_svme.c b/tools/testing/selftests/kvm/x86/svm_nested_clear_efer_svme.c index a521a9eed061..6a89eaffc657 100644 --- a/tools/testing/selftests/kvm/x86/svm_nested_clear_efer_svme.c +++ b/tools/testing/selftests/kvm/x86/svm_nested_clear_efer_svme.c @@ -38,7 +38,7 @@ int main(int argc, char *argv[]) { struct kvm_vcpu *vcpu; struct kvm_vm *vm; - vm_vaddr_t nested_gva = 0; + gva_t nested_gva = 0; TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM)); diff --git a/tools/testing/selftests/kvm/x86/svm_nested_shutdown_test.c b/tools/testing/selftests/kvm/x86/svm_nested_shutdown_test.c index 00135cbba35e..c6ea3d609a62 100644 --- a/tools/testing/selftests/kvm/x86/svm_nested_shutdown_test.c +++ b/tools/testing/selftests/kvm/x86/svm_nested_shutdown_test.c @@ -42,7 +42,7 @@ static void l1_guest_code(struct svm_test_data *svm, struct idt_entry *idt) int main(int argc, char *argv[]) { struct kvm_vcpu *vcpu; - vm_vaddr_t svm_gva; + gva_t svm_gva; struct kvm_vm *vm; TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM)); diff --git a/tools/testing/selftests/kvm/x86/svm_nested_soft_inject_test.c b/tools/testing/selftests/kvm/x86/svm_nested_soft_inject_test.c index 4bd1655f9e6d..f72f11d4c4f8 100644 --- a/tools/testing/selftests/kvm/x86/svm_nested_soft_inject_test.c +++ b/tools/testing/selftests/kvm/x86/svm_nested_soft_inject_test.c @@ -76,7 +76,7 @@ static void l2_guest_code_nmi(void) ud2(); } -static void l1_guest_code(struct svm_test_data *svm, uint64_t is_nmi, uint64_t idt_alt) +static void l1_guest_code(struct svm_test_data *svm, u64 is_nmi, u64 idt_alt) { #define L2_GUEST_STACK_SIZE 64 unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; @@ -144,8 +144,8 @@ static void run_test(bool is_nmi) { struct kvm_vcpu *vcpu; struct kvm_vm *vm; - vm_vaddr_t svm_gva; - vm_vaddr_t idt_alt_vm; + gva_t svm_gva; + gva_t idt_alt_vm; struct kvm_guest_debug debug; pr_info("Running %s test\n", is_nmi ? "NMI" : "soft int"); @@ -161,14 +161,14 @@ static void run_test(bool is_nmi) if (!is_nmi) { void *idt, *idt_alt; - idt_alt_vm = vm_vaddr_alloc_page(vm); + idt_alt_vm = vm_alloc_page(vm); idt_alt = addr_gva2hva(vm, idt_alt_vm); idt = addr_gva2hva(vm, vm->arch.idt); memcpy(idt_alt, idt, getpagesize()); } else { idt_alt_vm = 0; } - vcpu_args_set(vcpu, 3, svm_gva, (uint64_t)is_nmi, (uint64_t)idt_alt_vm); + vcpu_args_set(vcpu, 3, svm_gva, (u64)is_nmi, (u64)idt_alt_vm); memset(&debug, 0, sizeof(debug)); vcpu_guest_debug_set(vcpu, &debug); diff --git a/tools/testing/selftests/kvm/x86/svm_nested_vmcb12_gpa.c b/tools/testing/selftests/kvm/x86/svm_nested_vmcb12_gpa.c index 569869bed20b..a4935ce2fb99 100644 --- a/tools/testing/selftests/kvm/x86/svm_nested_vmcb12_gpa.c +++ b/tools/testing/selftests/kvm/x86/svm_nested_vmcb12_gpa.c @@ -28,28 +28,28 @@ static void l2_code(void) vmcall(); } -static void l1_vmrun(struct svm_test_data *svm, u64 gpa) +static void l1_vmrun(struct svm_test_data *svm, gpa_t gpa) { generic_svm_setup(svm, l2_code, &l2_guest_stack[L2_GUEST_STACK_SIZE]); asm volatile ("vmrun %[gpa]" : : [gpa] "a" (gpa) : "memory"); } -static void l1_vmload(struct svm_test_data *svm, u64 gpa) +static void l1_vmload(struct svm_test_data *svm, gpa_t gpa) { generic_svm_setup(svm, l2_code, &l2_guest_stack[L2_GUEST_STACK_SIZE]); asm volatile ("vmload %[gpa]" : : [gpa] "a" (gpa) : "memory"); } -static void l1_vmsave(struct svm_test_data *svm, u64 gpa) +static void l1_vmsave(struct svm_test_data *svm, gpa_t gpa) { generic_svm_setup(svm, l2_code, &l2_guest_stack[L2_GUEST_STACK_SIZE]); asm volatile ("vmsave %[gpa]" : : [gpa] "a" (gpa) : "memory"); } -static void l1_vmexit(struct svm_test_data *svm, u64 gpa) +static void l1_vmexit(struct svm_test_data *svm, gpa_t gpa) { generic_svm_setup(svm, l2_code, &l2_guest_stack[L2_GUEST_STACK_SIZE]); @@ -74,7 +74,7 @@ static u64 unmappable_gpa(struct kvm_vcpu *vcpu) static void test_invalid_vmcb12(struct kvm_vcpu *vcpu) { - vm_vaddr_t nested_gva = 0; + gva_t nested_gva = 0; struct ucall uc; @@ -90,7 +90,7 @@ static void test_invalid_vmcb12(struct kvm_vcpu *vcpu) static void test_unmappable_vmcb12(struct kvm_vcpu *vcpu) { - vm_vaddr_t nested_gva = 0; + gva_t nested_gva = 0; vcpu_alloc_svm(vcpu->vm, &nested_gva); vcpu_args_set(vcpu, 2, nested_gva, unmappable_gpa(vcpu)); @@ -103,7 +103,7 @@ static void test_unmappable_vmcb12(struct kvm_vcpu *vcpu) static void test_unmappable_vmcb12_vmexit(struct kvm_vcpu *vcpu) { struct kvm_x86_state *state; - vm_vaddr_t nested_gva = 0; + gva_t nested_gva = 0; struct ucall uc; /* diff --git a/tools/testing/selftests/kvm/x86/svm_vmcall_test.c b/tools/testing/selftests/kvm/x86/svm_vmcall_test.c index 8a62cca28cfb..b1887242f3b8 100644 --- a/tools/testing/selftests/kvm/x86/svm_vmcall_test.c +++ b/tools/testing/selftests/kvm/x86/svm_vmcall_test.c @@ -36,7 +36,7 @@ static void l1_guest_code(struct svm_test_data *svm) int main(int argc, char *argv[]) { struct kvm_vcpu *vcpu; - vm_vaddr_t svm_gva; + gva_t svm_gva; struct kvm_vm *vm; TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM)); diff --git a/tools/testing/selftests/kvm/x86/sync_regs_test.c b/tools/testing/selftests/kvm/x86/sync_regs_test.c index 8fa3948b0170..e0c52321f87c 100644 --- a/tools/testing/selftests/kvm/x86/sync_regs_test.c +++ b/tools/testing/selftests/kvm/x86/sync_regs_test.c @@ -20,7 +20,7 @@ #include "kvm_util.h" #include "processor.h" -#define UCALL_PIO_PORT ((uint16_t)0x1000) +#define UCALL_PIO_PORT ((u16)0x1000) struct ucall uc_none = { .cmd = UCALL_NONE, diff --git a/tools/testing/selftests/kvm/x86/triple_fault_event_test.c b/tools/testing/selftests/kvm/x86/triple_fault_event_test.c index 56306a19144a..f1c488e0d497 100644 --- a/tools/testing/selftests/kvm/x86/triple_fault_event_test.c +++ b/tools/testing/selftests/kvm/x86/triple_fault_event_test.c @@ -72,13 +72,13 @@ int main(void) if (has_vmx) { - vm_vaddr_t vmx_pages_gva; + gva_t vmx_pages_gva; vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code_vmx); vcpu_alloc_vmx(vm, &vmx_pages_gva); vcpu_args_set(vcpu, 1, vmx_pages_gva); } else { - vm_vaddr_t svm_gva; + gva_t svm_gva; vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code_svm); vcpu_alloc_svm(vm, &svm_gva); diff --git a/tools/testing/selftests/kvm/x86/tsc_msrs_test.c b/tools/testing/selftests/kvm/x86/tsc_msrs_test.c index 12b0964f4f13..91583969a14f 100644 --- a/tools/testing/selftests/kvm/x86/tsc_msrs_test.c +++ b/tools/testing/selftests/kvm/x86/tsc_msrs_test.c @@ -95,7 +95,7 @@ int main(void) { struct kvm_vcpu *vcpu; struct kvm_vm *vm; - uint64_t val; + u64 val; ksft_print_header(); ksft_set_plan(5); diff --git a/tools/testing/selftests/kvm/x86/tsc_scaling_sync.c b/tools/testing/selftests/kvm/x86/tsc_scaling_sync.c index 59c7304f805e..59da8d4da607 100644 --- a/tools/testing/selftests/kvm/x86/tsc_scaling_sync.c +++ b/tools/testing/selftests/kvm/x86/tsc_scaling_sync.c @@ -21,10 +21,10 @@ pthread_spinlock_t create_lock; #define TEST_TSC_KHZ 2345678UL #define TEST_TSC_OFFSET 200000000 -uint64_t tsc_sync; +u64 tsc_sync; static void guest_code(void) { - uint64_t start_tsc, local_tsc, tmp; + u64 start_tsc, local_tsc, tmp; start_tsc = rdtsc(); do { diff --git a/tools/testing/selftests/kvm/x86/ucna_injection_test.c b/tools/testing/selftests/kvm/x86/ucna_injection_test.c index 1e5e564523b3..df1ec8209c76 100644 --- a/tools/testing/selftests/kvm/x86/ucna_injection_test.c +++ b/tools/testing/selftests/kvm/x86/ucna_injection_test.c @@ -45,7 +45,7 @@ #define MCI_CTL2_RESERVED_BIT BIT_ULL(29) -static uint64_t supported_mcg_caps; +static u64 supported_mcg_caps; /* * Record states about the injected UCNA. @@ -53,30 +53,30 @@ static uint64_t supported_mcg_caps; * handler. Variables without the 'i_' prefixes are recorded in guest main * execution thread. */ -static volatile uint64_t i_ucna_rcvd; -static volatile uint64_t i_ucna_addr; -static volatile uint64_t ucna_addr; -static volatile uint64_t ucna_addr2; +static volatile u64 i_ucna_rcvd; +static volatile u64 i_ucna_addr; +static volatile u64 ucna_addr; +static volatile u64 ucna_addr2; struct thread_params { struct kvm_vcpu *vcpu; - uint64_t *p_i_ucna_rcvd; - uint64_t *p_i_ucna_addr; - uint64_t *p_ucna_addr; - uint64_t *p_ucna_addr2; + u64 *p_i_ucna_rcvd; + u64 *p_i_ucna_addr; + u64 *p_ucna_addr; + u64 *p_ucna_addr2; }; static void verify_apic_base_addr(void) { - uint64_t msr = rdmsr(MSR_IA32_APICBASE); - uint64_t base = GET_APIC_BASE(msr); + u64 msr = rdmsr(MSR_IA32_APICBASE); + u64 base = GET_APIC_BASE(msr); GUEST_ASSERT(base == APIC_DEFAULT_GPA); } static void ucna_injection_guest_code(void) { - uint64_t ctl2; + u64 ctl2; verify_apic_base_addr(); xapic_enable(); @@ -106,7 +106,7 @@ static void ucna_injection_guest_code(void) static void cmci_disabled_guest_code(void) { - uint64_t ctl2 = rdmsr(MSR_IA32_MCx_CTL2(UCNA_BANK)); + u64 ctl2 = rdmsr(MSR_IA32_MCx_CTL2(UCNA_BANK)); wrmsr(MSR_IA32_MCx_CTL2(UCNA_BANK), ctl2 | MCI_CTL2_CMCI_EN); GUEST_DONE(); @@ -114,7 +114,7 @@ static void cmci_disabled_guest_code(void) static void cmci_enabled_guest_code(void) { - uint64_t ctl2 = rdmsr(MSR_IA32_MCx_CTL2(UCNA_BANK)); + u64 ctl2 = rdmsr(MSR_IA32_MCx_CTL2(UCNA_BANK)); wrmsr(MSR_IA32_MCx_CTL2(UCNA_BANK), ctl2 | MCI_CTL2_RESERVED_BIT); GUEST_DONE(); @@ -145,14 +145,15 @@ static void run_vcpu_expect_gp(struct kvm_vcpu *vcpu) printf("vCPU received GP in guest.\n"); } -static void inject_ucna(struct kvm_vcpu *vcpu, uint64_t addr) { +static void inject_ucna(struct kvm_vcpu *vcpu, u64 addr) +{ /* * A UCNA error is indicated with VAL=1, UC=1, PCC=0, S=0 and AR=0 in * the IA32_MCi_STATUS register. * MSCOD=1 (BIT[16] - MscodDataRdErr). * MCACOD=0x0090 (Memory controller error format, channel 0) */ - uint64_t status = MCI_STATUS_VAL | MCI_STATUS_UC | MCI_STATUS_EN | + u64 status = MCI_STATUS_VAL | MCI_STATUS_UC | MCI_STATUS_EN | MCI_STATUS_MISCV | MCI_STATUS_ADDRV | 0x10090; struct kvm_x86_mce mce = {}; mce.status = status; @@ -216,10 +217,10 @@ static void test_ucna_injection(struct kvm_vcpu *vcpu, struct thread_params *par { struct kvm_vm *vm = vcpu->vm; params->vcpu = vcpu; - params->p_i_ucna_rcvd = (uint64_t *)addr_gva2hva(vm, (uint64_t)&i_ucna_rcvd); - params->p_i_ucna_addr = (uint64_t *)addr_gva2hva(vm, (uint64_t)&i_ucna_addr); - params->p_ucna_addr = (uint64_t *)addr_gva2hva(vm, (uint64_t)&ucna_addr); - params->p_ucna_addr2 = (uint64_t *)addr_gva2hva(vm, (uint64_t)&ucna_addr2); + params->p_i_ucna_rcvd = (u64 *)addr_gva2hva(vm, (u64)&i_ucna_rcvd); + params->p_i_ucna_addr = (u64 *)addr_gva2hva(vm, (u64)&i_ucna_addr); + params->p_ucna_addr = (u64 *)addr_gva2hva(vm, (u64)&ucna_addr); + params->p_ucna_addr2 = (u64 *)addr_gva2hva(vm, (u64)&ucna_addr2); run_ucna_injection(params); @@ -242,7 +243,7 @@ static void test_ucna_injection(struct kvm_vcpu *vcpu, struct thread_params *par static void setup_mce_cap(struct kvm_vcpu *vcpu, bool enable_cmci_p) { - uint64_t mcg_caps = MCG_CTL_P | MCG_SER_P | MCG_LMCE_P | KVM_MAX_MCE_BANKS; + u64 mcg_caps = MCG_CTL_P | MCG_SER_P | MCG_LMCE_P | KVM_MAX_MCE_BANKS; if (enable_cmci_p) mcg_caps |= MCG_CMCI_P; @@ -250,7 +251,7 @@ static void setup_mce_cap(struct kvm_vcpu *vcpu, bool enable_cmci_p) vcpu_ioctl(vcpu, KVM_X86_SETUP_MCE, &mcg_caps); } -static struct kvm_vcpu *create_vcpu_with_mce_cap(struct kvm_vm *vm, uint32_t vcpuid, +static struct kvm_vcpu *create_vcpu_with_mce_cap(struct kvm_vm *vm, u32 vcpuid, bool enable_cmci_p, void *guest_code) { struct kvm_vcpu *vcpu = vm_vcpu_add(vm, vcpuid, guest_code); diff --git a/tools/testing/selftests/kvm/x86/userspace_io_test.c b/tools/testing/selftests/kvm/x86/userspace_io_test.c index be7d72f3c029..9c5a87576c2e 100644 --- a/tools/testing/selftests/kvm/x86/userspace_io_test.c +++ b/tools/testing/selftests/kvm/x86/userspace_io_test.c @@ -10,7 +10,7 @@ #include "kvm_util.h" #include "processor.h" -static void guest_ins_port80(uint8_t *buffer, unsigned int count) +static void guest_ins_port80(u8 *buffer, unsigned int count) { unsigned long end; @@ -26,7 +26,7 @@ static void guest_ins_port80(uint8_t *buffer, unsigned int count) static void guest_code(void) { - uint8_t buffer[8192]; + u8 buffer[8192]; int i; /* diff --git a/tools/testing/selftests/kvm/x86/userspace_msr_exit_test.c b/tools/testing/selftests/kvm/x86/userspace_msr_exit_test.c index 8463a9956410..2808ce727e5f 100644 --- a/tools/testing/selftests/kvm/x86/userspace_msr_exit_test.c +++ b/tools/testing/selftests/kvm/x86/userspace_msr_exit_test.c @@ -23,21 +23,21 @@ struct kvm_msr_filter filter_allow = { .nmsrs = 1, /* Test an MSR the kernel knows about. */ .base = MSR_IA32_XSS, - .bitmap = (uint8_t*)&deny_bits, + .bitmap = (u8 *)&deny_bits, }, { .flags = KVM_MSR_FILTER_READ | KVM_MSR_FILTER_WRITE, .nmsrs = 1, /* Test an MSR the kernel doesn't know about. */ .base = MSR_IA32_FLUSH_CMD, - .bitmap = (uint8_t*)&deny_bits, + .bitmap = (u8 *)&deny_bits, }, { .flags = KVM_MSR_FILTER_READ | KVM_MSR_FILTER_WRITE, .nmsrs = 1, /* Test a fabricated MSR that no one knows about. */ .base = MSR_NON_EXISTENT, - .bitmap = (uint8_t*)&deny_bits, + .bitmap = (u8 *)&deny_bits, }, }, }; @@ -49,7 +49,7 @@ struct kvm_msr_filter filter_fs = { .flags = KVM_MSR_FILTER_READ, .nmsrs = 1, .base = MSR_FS_BASE, - .bitmap = (uint8_t*)&deny_bits, + .bitmap = (u8 *)&deny_bits, }, }, }; @@ -61,12 +61,12 @@ struct kvm_msr_filter filter_gs = { .flags = KVM_MSR_FILTER_READ, .nmsrs = 1, .base = MSR_GS_BASE, - .bitmap = (uint8_t*)&deny_bits, + .bitmap = (u8 *)&deny_bits, }, }, }; -static uint64_t msr_non_existent_data; +static u64 msr_non_existent_data; static int guest_exception_count; static u32 msr_reads, msr_writes; @@ -77,7 +77,7 @@ static u8 bitmap_c0000000[KVM_MSR_FILTER_MAX_BITMAP_SIZE]; static u8 bitmap_c0000000_read[KVM_MSR_FILTER_MAX_BITMAP_SIZE]; static u8 bitmap_deadbeef[1] = { 0x1 }; -static void deny_msr(uint8_t *bitmap, u32 msr) +static void deny_msr(u8 *bitmap, u32 msr) { u32 idx = msr & (KVM_MSR_FILTER_MAX_BITMAP_SIZE - 1); @@ -142,26 +142,26 @@ struct kvm_msr_filter no_filter_deny = { * Note: Force test_rdmsr() to not be inlined to prevent the labels, * rdmsr_start and rdmsr_end, from being defined multiple times. */ -static noinline uint64_t test_rdmsr(uint32_t msr) +static noinline u64 test_rdmsr(u32 msr) { - uint32_t a, d; + u32 a, d; guest_exception_count = 0; __asm__ __volatile__("rdmsr_start: rdmsr; rdmsr_end:" : "=a"(a), "=d"(d) : "c"(msr) : "memory"); - return a | ((uint64_t) d << 32); + return a | ((u64)d << 32); } /* * Note: Force test_wrmsr() to not be inlined to prevent the labels, * wrmsr_start and wrmsr_end, from being defined multiple times. */ -static noinline void test_wrmsr(uint32_t msr, uint64_t value) +static noinline void test_wrmsr(u32 msr, u64 value) { - uint32_t a = value; - uint32_t d = value >> 32; + u32 a = value; + u32 d = value >> 32; guest_exception_count = 0; @@ -176,26 +176,26 @@ extern char wrmsr_start, wrmsr_end; * Note: Force test_em_rdmsr() to not be inlined to prevent the labels, * rdmsr_start and rdmsr_end, from being defined multiple times. */ -static noinline uint64_t test_em_rdmsr(uint32_t msr) +static noinline u64 test_em_rdmsr(u32 msr) { - uint32_t a, d; + u32 a, d; guest_exception_count = 0; __asm__ __volatile__(KVM_FEP "em_rdmsr_start: rdmsr; em_rdmsr_end:" : "=a"(a), "=d"(d) : "c"(msr) : "memory"); - return a | ((uint64_t) d << 32); + return a | ((u64)d << 32); } /* * Note: Force test_em_wrmsr() to not be inlined to prevent the labels, * wrmsr_start and wrmsr_end, from being defined multiple times. */ -static noinline void test_em_wrmsr(uint32_t msr, uint64_t value) +static noinline void test_em_wrmsr(u32 msr, u64 value) { - uint32_t a = value; - uint32_t d = value >> 32; + u32 a = value; + u32 d = value >> 32; guest_exception_count = 0; @@ -208,7 +208,7 @@ extern char em_wrmsr_start, em_wrmsr_end; static void guest_code_filter_allow(void) { - uint64_t data; + u64 data; /* * Test userspace intercepting rdmsr / wrmsr for MSR_IA32_XSS. @@ -328,7 +328,7 @@ static void guest_code_filter_deny(void) static void guest_code_permission_bitmap(void) { - uint64_t data; + u64 data; data = test_rdmsr(MSR_FS_BASE); GUEST_ASSERT(data == MSR_FS_BASE); @@ -391,7 +391,7 @@ static void check_for_guest_assert(struct kvm_vcpu *vcpu) } } -static void process_rdmsr(struct kvm_vcpu *vcpu, uint32_t msr_index) +static void process_rdmsr(struct kvm_vcpu *vcpu, u32 msr_index) { struct kvm_run *run = vcpu->run; @@ -423,7 +423,7 @@ static void process_rdmsr(struct kvm_vcpu *vcpu, uint32_t msr_index) } } -static void process_wrmsr(struct kvm_vcpu *vcpu, uint32_t msr_index) +static void process_wrmsr(struct kvm_vcpu *vcpu, u32 msr_index) { struct kvm_run *run = vcpu->run; @@ -464,7 +464,7 @@ static void process_ucall_done(struct kvm_vcpu *vcpu) uc.cmd, UCALL_DONE); } -static uint64_t process_ucall(struct kvm_vcpu *vcpu) +static u64 process_ucall(struct kvm_vcpu *vcpu) { struct ucall uc = {}; @@ -489,20 +489,20 @@ static uint64_t process_ucall(struct kvm_vcpu *vcpu) } static void run_guest_then_process_rdmsr(struct kvm_vcpu *vcpu, - uint32_t msr_index) + u32 msr_index) { vcpu_run(vcpu); process_rdmsr(vcpu, msr_index); } static void run_guest_then_process_wrmsr(struct kvm_vcpu *vcpu, - uint32_t msr_index) + u32 msr_index) { vcpu_run(vcpu); process_wrmsr(vcpu, msr_index); } -static uint64_t run_guest_then_process_ucall(struct kvm_vcpu *vcpu) +static u64 run_guest_then_process_ucall(struct kvm_vcpu *vcpu) { vcpu_run(vcpu); return process_ucall(vcpu); @@ -519,7 +519,7 @@ KVM_ONE_VCPU_TEST_SUITE(user_msr); KVM_ONE_VCPU_TEST(user_msr, msr_filter_allow, guest_code_filter_allow) { struct kvm_vm *vm = vcpu->vm; - uint64_t cmd; + u64 cmd; int rc; rc = kvm_check_cap(KVM_CAP_X86_USER_SPACE_MSR); @@ -732,7 +732,7 @@ static void run_msr_filter_flag_test(struct kvm_vm *vm) .flags = KVM_MSR_FILTER_READ, .nmsrs = 1, .base = 0, - .bitmap = (uint8_t *)&deny_bits, + .bitmap = (u8 *)&deny_bits, }, }, }; diff --git a/tools/testing/selftests/kvm/x86/vmx_apic_access_test.c b/tools/testing/selftests/kvm/x86/vmx_apic_access_test.c index a81a24761aac..1720113eae79 100644 --- a/tools/testing/selftests/kvm/x86/vmx_apic_access_test.c +++ b/tools/testing/selftests/kvm/x86/vmx_apic_access_test.c @@ -38,7 +38,7 @@ static void l1_guest_code(struct vmx_pages *vmx_pages, unsigned long high_gpa) { #define L2_GUEST_STACK_SIZE 64 unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; - uint32_t control; + u32 control; GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages)); GUEST_ASSERT(load_vmcs(vmx_pages)); @@ -72,7 +72,7 @@ static void l1_guest_code(struct vmx_pages *vmx_pages, unsigned long high_gpa) int main(int argc, char *argv[]) { unsigned long apic_access_addr = ~0ul; - vm_vaddr_t vmx_pages_gva; + gva_t vmx_pages_gva; unsigned long high_gpa; struct vmx_pages *vmx; bool done = false; diff --git a/tools/testing/selftests/kvm/x86/vmx_apicv_updates_test.c b/tools/testing/selftests/kvm/x86/vmx_apicv_updates_test.c index 337c53fddeff..80a4fd1e5bbb 100644 --- a/tools/testing/selftests/kvm/x86/vmx_apicv_updates_test.c +++ b/tools/testing/selftests/kvm/x86/vmx_apicv_updates_test.c @@ -33,7 +33,7 @@ static void l1_guest_code(struct vmx_pages *vmx_pages) { #define L2_GUEST_STACK_SIZE 64 unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; - uint32_t control; + u32 control; GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages)); GUEST_ASSERT(load_vmcs(vmx_pages)); @@ -110,7 +110,7 @@ static void l1_guest_code(struct vmx_pages *vmx_pages) int main(int argc, char *argv[]) { - vm_vaddr_t vmx_pages_gva; + gva_t vmx_pages_gva; struct vmx_pages *vmx; struct kvm_vcpu *vcpu; struct kvm_vm *vm; diff --git a/tools/testing/selftests/kvm/x86/vmx_invalid_nested_guest_state.c b/tools/testing/selftests/kvm/x86/vmx_invalid_nested_guest_state.c index a100ee5f0009..a2eaceed9ad5 100644 --- a/tools/testing/selftests/kvm/x86/vmx_invalid_nested_guest_state.c +++ b/tools/testing/selftests/kvm/x86/vmx_invalid_nested_guest_state.c @@ -52,7 +52,7 @@ static void l1_guest_code(struct vmx_pages *vmx_pages) int main(int argc, char *argv[]) { - vm_vaddr_t vmx_pages_gva; + gva_t vmx_pages_gva; struct kvm_sregs sregs; struct kvm_vcpu *vcpu; struct kvm_run *run; diff --git a/tools/testing/selftests/kvm/x86/vmx_msrs_test.c b/tools/testing/selftests/kvm/x86/vmx_msrs_test.c index 90720b6205f4..c1e8632a1bb6 100644 --- a/tools/testing/selftests/kvm/x86/vmx_msrs_test.c +++ b/tools/testing/selftests/kvm/x86/vmx_msrs_test.c @@ -12,11 +12,10 @@ #include "kvm_util.h" #include "vmx.h" -static void vmx_fixed1_msr_test(struct kvm_vcpu *vcpu, uint32_t msr_index, - uint64_t mask) +static void vmx_fixed1_msr_test(struct kvm_vcpu *vcpu, u32 msr_index, u64 mask) { - uint64_t val = vcpu_get_msr(vcpu, msr_index); - uint64_t bit; + u64 val = vcpu_get_msr(vcpu, msr_index); + u64 bit; mask &= val; @@ -26,11 +25,10 @@ static void vmx_fixed1_msr_test(struct kvm_vcpu *vcpu, uint32_t msr_index, } } -static void vmx_fixed0_msr_test(struct kvm_vcpu *vcpu, uint32_t msr_index, - uint64_t mask) +static void vmx_fixed0_msr_test(struct kvm_vcpu *vcpu, u32 msr_index, u64 mask) { - uint64_t val = vcpu_get_msr(vcpu, msr_index); - uint64_t bit; + u64 val = vcpu_get_msr(vcpu, msr_index); + u64 bit; mask = ~mask | val; @@ -40,7 +38,7 @@ static void vmx_fixed0_msr_test(struct kvm_vcpu *vcpu, uint32_t msr_index, } } -static void vmx_fixed0and1_msr_test(struct kvm_vcpu *vcpu, uint32_t msr_index) +static void vmx_fixed0and1_msr_test(struct kvm_vcpu *vcpu, u32 msr_index) { vmx_fixed0_msr_test(vcpu, msr_index, GENMASK_ULL(31, 0)); vmx_fixed1_msr_test(vcpu, msr_index, GENMASK_ULL(63, 32)); @@ -68,10 +66,10 @@ static void vmx_save_restore_msrs_test(struct kvm_vcpu *vcpu) } static void __ia32_feature_control_msr_test(struct kvm_vcpu *vcpu, - uint64_t msr_bit, + u64 msr_bit, struct kvm_x86_cpu_feature feature) { - uint64_t val; + u64 val; vcpu_clear_cpuid_feature(vcpu, feature); @@ -90,7 +88,7 @@ static void __ia32_feature_control_msr_test(struct kvm_vcpu *vcpu, static void ia32_feature_control_msr_test(struct kvm_vcpu *vcpu) { - uint64_t supported_bits = FEAT_CTL_LOCKED | + u64 supported_bits = FEAT_CTL_LOCKED | FEAT_CTL_VMX_ENABLED_INSIDE_SMX | FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX | FEAT_CTL_SGX_LC_ENABLED | diff --git a/tools/testing/selftests/kvm/x86/vmx_nested_la57_state_test.c b/tools/testing/selftests/kvm/x86/vmx_nested_la57_state_test.c index 915c42001dba..f13dee317383 100644 --- a/tools/testing/selftests/kvm/x86/vmx_nested_la57_state_test.c +++ b/tools/testing/selftests/kvm/x86/vmx_nested_la57_state_test.c @@ -30,7 +30,7 @@ static void l1_guest_code(struct vmx_pages *vmx_pages) #define L2_GUEST_STACK_SIZE 64 unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; u64 guest_cr4; - vm_paddr_t pml5_pa, pml4_pa; + gpa_t pml5_pa, pml4_pa; u64 *pml5; u64 exit_reason; @@ -73,7 +73,7 @@ void guest_code(struct vmx_pages *vmx_pages) int main(int argc, char *argv[]) { - vm_vaddr_t vmx_pages_gva = 0; + gva_t vmx_pages_gva = 0; struct kvm_vm *vm; struct kvm_vcpu *vcpu; struct kvm_x86_state *state; diff --git a/tools/testing/selftests/kvm/x86/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86/vmx_pmu_caps_test.c index 7ff6f62e20a3..d004108dbdc6 100644 --- a/tools/testing/selftests/kvm/x86/vmx_pmu_caps_test.c +++ b/tools/testing/selftests/kvm/x86/vmx_pmu_caps_test.c @@ -52,16 +52,16 @@ static const union perf_capabilities format_caps = { .pebs_format = -1, }; -static void guest_test_perf_capabilities_gp(uint64_t val) +static void guest_test_perf_capabilities_gp(u64 val) { - uint8_t vector = wrmsr_safe(MSR_IA32_PERF_CAPABILITIES, val); + u8 vector = wrmsr_safe(MSR_IA32_PERF_CAPABILITIES, val); __GUEST_ASSERT(vector == GP_VECTOR, "Expected #GP for value '0x%lx', got %s", val, ex_str(vector)); } -static void guest_code(uint64_t current_val) +static void guest_code(u64 current_val) { int i; @@ -129,7 +129,7 @@ KVM_ONE_VCPU_TEST(vmx_pmu_caps, basic_perf_capabilities, guest_code) KVM_ONE_VCPU_TEST(vmx_pmu_caps, fungible_perf_capabilities, guest_code) { - const uint64_t fungible_caps = host_cap.capabilities & ~immutable_caps.capabilities; + const u64 fungible_caps = host_cap.capabilities & ~immutable_caps.capabilities; int bit; for_each_set_bit(bit, &fungible_caps, 64) { @@ -148,7 +148,7 @@ KVM_ONE_VCPU_TEST(vmx_pmu_caps, fungible_perf_capabilities, guest_code) */ KVM_ONE_VCPU_TEST(vmx_pmu_caps, immutable_perf_capabilities, guest_code) { - const uint64_t reserved_caps = (~host_cap.capabilities | + const u64 reserved_caps = (~host_cap.capabilities | immutable_caps.capabilities) & ~format_caps.capabilities; union perf_capabilities val = host_cap; @@ -210,7 +210,7 @@ KVM_ONE_VCPU_TEST(vmx_pmu_caps, lbr_perf_capabilities, guest_code) KVM_ONE_VCPU_TEST(vmx_pmu_caps, perf_capabilities_unsupported, guest_code) { - uint64_t val; + u64 val; int i, r; vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities); diff --git a/tools/testing/selftests/kvm/x86/vmx_preemption_timer_test.c b/tools/testing/selftests/kvm/x86/vmx_preemption_timer_test.c index 00dd2ac07a61..1b7b6ba23de7 100644 --- a/tools/testing/selftests/kvm/x86/vmx_preemption_timer_test.c +++ b/tools/testing/selftests/kvm/x86/vmx_preemption_timer_test.c @@ -152,7 +152,7 @@ void guest_code(struct vmx_pages *vmx_pages) int main(int argc, char *argv[]) { - vm_vaddr_t vmx_pages_gva = 0; + gva_t vmx_pages_gva = 0; struct kvm_regs regs1, regs2; struct kvm_vm *vm; diff --git a/tools/testing/selftests/kvm/x86/xapic_ipi_test.c b/tools/testing/selftests/kvm/x86/xapic_ipi_test.c index ae4a4b6c05ca..39ce9a9369f5 100644 --- a/tools/testing/selftests/kvm/x86/xapic_ipi_test.c +++ b/tools/testing/selftests/kvm/x86/xapic_ipi_test.c @@ -48,20 +48,20 @@ * Incremented in the IPI handler. Provides evidence to the sender that the IPI * arrived at the destination */ -static volatile uint64_t ipis_rcvd; +static volatile u64 ipis_rcvd; /* Data struct shared between host main thread and vCPUs */ struct test_data_page { - uint32_t halter_apic_id; - volatile uint64_t hlt_count; - volatile uint64_t wake_count; - uint64_t ipis_sent; - uint64_t migrations_attempted; - uint64_t migrations_completed; - uint32_t icr; - uint32_t icr2; - uint32_t halter_tpr; - uint32_t halter_ppr; + u32 halter_apic_id; + volatile u64 hlt_count; + volatile u64 wake_count; + u64 ipis_sent; + u64 migrations_attempted; + u64 migrations_completed; + u32 icr; + u32 icr2; + u32 halter_tpr; + u32 halter_ppr; /* * Record local version register as a cross-check that APIC access @@ -69,19 +69,19 @@ struct test_data_page { * arch/x86/kvm/lapic.c). If test is failing, check that values match * to determine whether APIC access exits are working. */ - uint32_t halter_lvr; + u32 halter_lvr; }; struct thread_params { struct test_data_page *data; struct kvm_vcpu *vcpu; - uint64_t *pipis_rcvd; /* host address of ipis_rcvd global */ + u64 *pipis_rcvd; /* host address of ipis_rcvd global */ }; void verify_apic_base_addr(void) { - uint64_t msr = rdmsr(MSR_IA32_APICBASE); - uint64_t base = GET_APIC_BASE(msr); + u64 msr = rdmsr(MSR_IA32_APICBASE); + u64 base = GET_APIC_BASE(msr); GUEST_ASSERT(base == APIC_DEFAULT_GPA); } @@ -125,12 +125,12 @@ static void guest_ipi_handler(struct ex_regs *regs) static void sender_guest_code(struct test_data_page *data) { - uint64_t last_wake_count; - uint64_t last_hlt_count; - uint64_t last_ipis_rcvd_count; - uint32_t icr_val; - uint32_t icr2_val; - uint64_t tsc_start; + u64 last_wake_count; + u64 last_hlt_count; + u64 last_ipis_rcvd_count; + u32 icr_val; + u32 icr2_val; + u64 tsc_start; verify_apic_base_addr(); xapic_enable(); @@ -248,7 +248,7 @@ static void cancel_join_vcpu_thread(pthread_t thread, struct kvm_vcpu *vcpu) } void do_migrations(struct test_data_page *data, int run_secs, int delay_usecs, - uint64_t *pipis_rcvd) + u64 *pipis_rcvd) { long pages_not_moved; unsigned long nodemask = 0; @@ -259,9 +259,9 @@ void do_migrations(struct test_data_page *data, int run_secs, int delay_usecs, int i; int from, to; unsigned long bit; - uint64_t hlt_count; - uint64_t wake_count; - uint64_t ipis_sent; + u64 hlt_count; + u64 wake_count; + u64 ipis_sent; fprintf(stderr, "Calling migrate_pages every %d microseconds\n", delay_usecs); @@ -393,12 +393,12 @@ int main(int argc, char *argv[]) int run_secs = 0; int delay_usecs = 0; struct test_data_page *data; - vm_vaddr_t test_data_page_vaddr; + gva_t test_data_page_gva; bool migrate = false; pthread_t threads[2]; struct thread_params params[2]; struct kvm_vm *vm; - uint64_t *pipis_rcvd; + u64 *pipis_rcvd; get_cmdline_args(argc, argv, &run_secs, &migrate, &delay_usecs); if (run_secs <= 0) @@ -414,16 +414,16 @@ int main(int argc, char *argv[]) params[1].vcpu = vm_vcpu_add(vm, 1, sender_guest_code); - test_data_page_vaddr = vm_vaddr_alloc_page(vm); - data = addr_gva2hva(vm, test_data_page_vaddr); + test_data_page_gva = vm_alloc_page(vm); + data = addr_gva2hva(vm, test_data_page_gva); memset(data, 0, sizeof(*data)); params[0].data = data; params[1].data = data; - vcpu_args_set(params[0].vcpu, 1, test_data_page_vaddr); - vcpu_args_set(params[1].vcpu, 1, test_data_page_vaddr); + vcpu_args_set(params[0].vcpu, 1, test_data_page_gva); + vcpu_args_set(params[1].vcpu, 1, test_data_page_gva); - pipis_rcvd = (uint64_t *)addr_gva2hva(vm, (uint64_t)&ipis_rcvd); + pipis_rcvd = (u64 *)addr_gva2hva(vm, (u64)&ipis_rcvd); params[0].pipis_rcvd = pipis_rcvd; params[1].pipis_rcvd = pipis_rcvd; diff --git a/tools/testing/selftests/kvm/x86/xapic_state_test.c b/tools/testing/selftests/kvm/x86/xapic_state_test.c index 0c5e12f5f14e..637bb90c1d93 100644 --- a/tools/testing/selftests/kvm/x86/xapic_state_test.c +++ b/tools/testing/selftests/kvm/x86/xapic_state_test.c @@ -23,7 +23,7 @@ static void xapic_guest_code(void) xapic_enable(); while (1) { - uint64_t val = (u64)xapic_read_reg(APIC_IRR) | + u64 val = (u64)xapic_read_reg(APIC_IRR) | (u64)xapic_read_reg(APIC_IRR + 0x10) << 32; xapic_write_reg(APIC_ICR2, val >> 32); @@ -43,7 +43,7 @@ static void x2apic_guest_code(void) x2apic_enable(); do { - uint64_t val = x2apic_read_reg(APIC_IRR) | + u64 val = x2apic_read_reg(APIC_IRR) | x2apic_read_reg(APIC_IRR + 0x10) << 32; if (val & X2APIC_RSVD_BITS_MASK) { @@ -56,12 +56,12 @@ static void x2apic_guest_code(void) } while (1); } -static void ____test_icr(struct xapic_vcpu *x, uint64_t val) +static void ____test_icr(struct xapic_vcpu *x, u64 val) { struct kvm_vcpu *vcpu = x->vcpu; struct kvm_lapic_state xapic; struct ucall uc; - uint64_t icr; + u64 icr; /* * Tell the guest what ICR value to write. Use the IRR to pass info, @@ -93,7 +93,7 @@ static void ____test_icr(struct xapic_vcpu *x, uint64_t val) TEST_ASSERT_EQ(icr, val & ~APIC_ICR_BUSY); } -static void __test_icr(struct xapic_vcpu *x, uint64_t val) +static void __test_icr(struct xapic_vcpu *x, u64 val) { /* * The BUSY bit is reserved on both AMD and Intel, but only AMD treats @@ -109,7 +109,7 @@ static void __test_icr(struct xapic_vcpu *x, uint64_t val) static void test_icr(struct xapic_vcpu *x) { struct kvm_vcpu *vcpu = x->vcpu; - uint64_t icr, i, j; + u64 icr, i, j; icr = APIC_DEST_SELF | APIC_INT_ASSERT | APIC_DM_FIXED; for (i = 0; i <= 0xff; i++) @@ -142,9 +142,9 @@ static void test_icr(struct xapic_vcpu *x) __test_icr(x, -1ull & ~APIC_DM_FIXED_MASK); } -static void __test_apic_id(struct kvm_vcpu *vcpu, uint64_t apic_base) +static void __test_apic_id(struct kvm_vcpu *vcpu, u64 apic_base) { - uint32_t apic_id, expected; + u32 apic_id, expected; struct kvm_lapic_state xapic; vcpu_set_msr(vcpu, MSR_IA32_APICBASE, apic_base); @@ -170,9 +170,9 @@ static void __test_apic_id(struct kvm_vcpu *vcpu, uint64_t apic_base) */ static void test_apic_id(void) { - const uint32_t NR_VCPUS = 3; + const u32 NR_VCPUS = 3; struct kvm_vcpu *vcpus[NR_VCPUS]; - uint64_t apic_base; + u64 apic_base; struct kvm_vm *vm; int i; diff --git a/tools/testing/selftests/kvm/x86/xapic_tpr_test.c b/tools/testing/selftests/kvm/x86/xapic_tpr_test.c index 3862134d9d40..ab25db2235d5 100644 --- a/tools/testing/selftests/kvm/x86/xapic_tpr_test.c +++ b/tools/testing/selftests/kvm/x86/xapic_tpr_test.c @@ -58,7 +58,7 @@ static void tpr_guest_irq_queue(void) if (is_x2apic) { x2apic_write_reg(APIC_SELF_IPI, IRQ_VECTOR); } else { - uint32_t icr, icr2; + u32 icr, icr2; icr = APIC_DEST_SELF | APIC_DEST_PHYSICAL | APIC_DM_FIXED | IRQ_VECTOR; @@ -69,9 +69,9 @@ static void tpr_guest_irq_queue(void) } } -static uint8_t tpr_guest_tpr_get(void) +static u8 tpr_guest_tpr_get(void) { - uint32_t taskpri; + u32 taskpri; if (is_x2apic) taskpri = x2apic_read_reg(APIC_TASKPRI); @@ -81,9 +81,9 @@ static uint8_t tpr_guest_tpr_get(void) return GET_APIC_PRI(taskpri); } -static uint8_t tpr_guest_ppr_get(void) +static u8 tpr_guest_ppr_get(void) { - uint32_t procpri; + u32 procpri; if (is_x2apic) procpri = x2apic_read_reg(APIC_PROCPRI); @@ -93,9 +93,9 @@ static uint8_t tpr_guest_ppr_get(void) return GET_APIC_PRI(procpri); } -static uint8_t tpr_guest_cr8_get(void) +static u8 tpr_guest_cr8_get(void) { - uint64_t cr8; + u64 cr8; asm volatile ("mov %%cr8, %[cr8]\n\t" : [cr8] "=r"(cr8)); @@ -104,7 +104,7 @@ static uint8_t tpr_guest_cr8_get(void) static void tpr_guest_check_tpr_ppr_cr8_equal(void) { - uint8_t tpr; + u8 tpr; tpr = tpr_guest_tpr_get(); @@ -157,19 +157,19 @@ static void tpr_guest_code(void) GUEST_DONE(); } -static uint8_t lapic_tpr_get(struct kvm_lapic_state *xapic) +static u8 lapic_tpr_get(struct kvm_lapic_state *xapic) { return GET_APIC_PRI(*((u32 *)&xapic->regs[APIC_TASKPRI])); } -static void lapic_tpr_set(struct kvm_lapic_state *xapic, uint8_t val) +static void lapic_tpr_set(struct kvm_lapic_state *xapic, u8 val) { u32 *taskpri = (u32 *)&xapic->regs[APIC_TASKPRI]; *taskpri = SET_APIC_PRI(*taskpri, val); } -static uint8_t sregs_tpr(struct kvm_sregs *sregs) +static u8 sregs_tpr(struct kvm_sregs *sregs) { return sregs->cr8 & GENMASK(3, 0); } @@ -197,7 +197,7 @@ static void test_tpr_check_tpr_cr8_equal(struct kvm_vcpu *vcpu) static void test_tpr_set_tpr_for_irq(struct kvm_vcpu *vcpu, bool mask) { struct kvm_lapic_state xapic; - uint8_t tpr; + u8 tpr; static_assert(IRQ_VECTOR >= 16, "invalid IRQ vector number"); tpr = IRQ_VECTOR / 16; diff --git a/tools/testing/selftests/kvm/x86/xcr0_cpuid_test.c b/tools/testing/selftests/kvm/x86/xcr0_cpuid_test.c index d038c1571729..40dc9e6b3fad 100644 --- a/tools/testing/selftests/kvm/x86/xcr0_cpuid_test.c +++ b/tools/testing/selftests/kvm/x86/xcr0_cpuid_test.c @@ -21,7 +21,7 @@ */ #define ASSERT_XFEATURE_DEPENDENCIES(supported_xcr0, xfeatures, dependencies) \ do { \ - uint64_t __supported = (supported_xcr0) & ((xfeatures) | (dependencies)); \ + u64 __supported = (supported_xcr0) & ((xfeatures) | (dependencies)); \ \ __GUEST_ASSERT((__supported & (xfeatures)) != (xfeatures) || \ __supported == ((xfeatures) | (dependencies)), \ @@ -39,7 +39,7 @@ do { \ */ #define ASSERT_ALL_OR_NONE_XFEATURE(supported_xcr0, xfeatures) \ do { \ - uint64_t __supported = (supported_xcr0) & (xfeatures); \ + u64 __supported = (supported_xcr0) & (xfeatures); \ \ __GUEST_ASSERT(!__supported || __supported == (xfeatures), \ "supported = 0x%lx, xfeatures = 0x%llx", \ @@ -48,8 +48,8 @@ do { \ static void guest_code(void) { - uint64_t initial_xcr0; - uint64_t supported_xcr0; + u64 initial_xcr0; + u64 supported_xcr0; int i, vector; set_cr4(get_cr4() | X86_CR4_OSXSAVE); diff --git a/tools/testing/selftests/kvm/x86/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86/xen_shinfo_test.c index 23909b501ac2..5076f6a75455 100644 --- a/tools/testing/selftests/kvm/x86/xen_shinfo_test.c +++ b/tools/testing/selftests/kvm/x86/xen_shinfo_test.c @@ -116,15 +116,15 @@ struct pvclock_wall_clock { } __attribute__((__packed__)); struct vcpu_runstate_info { - uint32_t state; - uint64_t state_entry_time; - uint64_t time[5]; /* Extra field for overrun check */ + u32 state; + u64 state_entry_time; + u64 time[5]; /* Extra field for overrun check */ }; struct compat_vcpu_runstate_info { - uint32_t state; - uint64_t state_entry_time; - uint64_t time[5]; + u32 state; + u64 state_entry_time; + u64 time[5]; } __attribute__((__packed__)); struct arch_vcpu_info { @@ -133,8 +133,8 @@ struct arch_vcpu_info { }; struct vcpu_info { - uint8_t evtchn_upcall_pending; - uint8_t evtchn_upcall_mask; + u8 evtchn_upcall_pending; + u8 evtchn_upcall_mask; unsigned long evtchn_pending_sel; struct arch_vcpu_info arch; struct pvclock_vcpu_time_info time; @@ -145,7 +145,7 @@ struct shared_info { unsigned long evtchn_pending[64]; unsigned long evtchn_mask[64]; struct pvclock_wall_clock wc; - uint32_t wc_sec_hi; + u32 wc_sec_hi; /* arch_shared_info here */ }; @@ -658,7 +658,7 @@ int main(int argc, char *argv[]) printf("Testing RUNSTATE_ADJUST\n"); rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST; memset(&rst.u, 0, sizeof(rst.u)); - rst.u.runstate.state = (uint64_t)-1; + rst.u.runstate.state = (u64)-1; rst.u.runstate.time_blocked = 0x5a - rs->time[RUNSTATE_blocked]; rst.u.runstate.time_offline = @@ -1113,7 +1113,7 @@ int main(int argc, char *argv[]) /* Don't change the address, just trigger a write */ struct kvm_xen_vcpu_attr adj = { .type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST, - .u.runstate.state = (uint64_t)-1 + .u.runstate.state = (u64)-1 }; vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &adj); diff --git a/tools/testing/selftests/kvm/x86/xss_msr_test.c b/tools/testing/selftests/kvm/x86/xss_msr_test.c index f331a4e9bae3..12c63df6bbce 100644 --- a/tools/testing/selftests/kvm/x86/xss_msr_test.c +++ b/tools/testing/selftests/kvm/x86/xss_msr_test.c @@ -17,7 +17,7 @@ int main(int argc, char *argv[]) bool xss_in_msr_list; struct kvm_vm *vm; struct kvm_vcpu *vcpu; - uint64_t xss_val; + u64 xss_val; int i, r; /* Create VM */ diff --git a/tools/testing/selftests/mm/config b/tools/testing/selftests/mm/config index 1dbe2b4558ab..06f78bd232e2 100644 --- a/tools/testing/selftests/mm/config +++ b/tools/testing/selftests/mm/config @@ -13,3 +13,4 @@ CONFIG_PROFILING=y CONFIG_UPROBES=y CONFIG_MEMORY_FAILURE=y CONFIG_HWPOISON_INJECT=m +CONFIG_PROC_MEM_ALWAYS_FORCE=y diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index a275ed584026..f3da38c54d27 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -96,6 +96,7 @@ TEST_PROGS := \ srv6_hl2encap_red_l2vpn_test.sh \ srv6_iptunnel_cache.sh \ stress_reuseport_listen.sh \ + tcp_ecmp_failover.sh \ tcp_fastopen_backup_key.sh \ test_bpf.sh \ test_bridge_backup_port.sh \ diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index 5fea7e7df628..989a5975dcea 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -474,20 +474,24 @@ mptcp_lib_wait_local_port_listen() { wait_local_port_listen "${@}" "tcp" } +# $1: error file, $2: cmd, $3: expected msg, [$4: expected error] mptcp_lib_check_output() { local err="${1}" local cmd="${2}" local expected="${3}" + local exp_error="${4:-0}" local cmd_ret=0 local out - if ! out=$(${cmd} 2>"${err}"); then - cmd_ret=${?} - fi + out=$(${cmd} 2>"${err}") || cmd_ret=1 - if [ ${cmd_ret} -ne 0 ]; then - mptcp_lib_pr_fail "command execution '${cmd}' stderr" - cat "${err}" + if [ "${cmd_ret}" != "${exp_error}" ]; then + mptcp_lib_pr_fail "unexpected returned code for '${cmd}', info:" + if [ "${exp_error}" = 0 ]; then + cat "${err}" + else + echo "${out}" + fi return 2 elif [ "${out}" = "${expected}" ]; then return 0 diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index 123d9d7a0278..04594dfc22b1 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -122,10 +122,12 @@ check() local cmd="$1" local expected="$2" local msg="$3" + local exp_error="$4" local rc=0 mptcp_lib_print_title "$msg" - mptcp_lib_check_output "${err}" "${cmd}" "${expected}" || rc=${?} + mptcp_lib_check_output "${err}" "${cmd}" "${expected}" "${exp_error}" || + rc=${?} if [ ${rc} -eq 2 ]; then mptcp_lib_result_fail "${msg} # error ${rc}" ret=${KSFT_FAIL} @@ -158,13 +160,13 @@ check "show_endpoints" \ "3,10.0.1.3,signal backup")" "dump addrs" del_endpoint 2 -check "get_endpoint 2" "" "simple del addr" +check "get_endpoint 2" "" "simple del addr" 1 check "show_endpoints" \ "$(format_endpoints "1,10.0.1.1" \ "3,10.0.1.3,signal backup")" "dump addrs after del" add_endpoint 10.0.1.3 2>/dev/null -check "get_endpoint 4" "" "duplicate addr" +check "get_endpoint 4" "" "duplicate addr" 1 add_endpoint 10.0.1.4 flags signal check "get_endpoint 4" "$(format_endpoints "4,10.0.1.4,signal")" "id addr increment" @@ -173,7 +175,7 @@ for i in $(seq 5 9); do add_endpoint "10.0.1.${i}" flags signal >/dev/null 2>&1 done check "get_endpoint 9" "$(format_endpoints "9,10.0.1.9,signal")" "hard addr limit" -check "get_endpoint 10" "" "above hard addr limit" +check "get_endpoint 10" "" "above hard addr limit" 1 del_endpoint 9 for i in $(seq 10 255); do @@ -192,9 +194,13 @@ check "show_endpoints" \ flush_endpoint check "show_endpoints" "" "flush addrs" -add_endpoint 10.0.1.1 flags unknown -check "show_endpoints" "$(format_endpoints "1,10.0.1.1")" "ignore unknown flags" -flush_endpoint +# "unknown" flag is only supported by pm_nl_ctl +if ! mptcp_lib_is_ip_mptcp; then + add_endpoint 10.0.1.1 flags unknown + check "show_endpoints" "$(format_endpoints "1,10.0.1.1")" \ + "ignore unknown flags" + flush_endpoint +fi set_limits 9 1 2>/dev/null check "get_limits" "${default_limits}" "rcv addrs above hard limit" diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh index b327d3061ed5..3cdd953f6813 100755 --- a/tools/testing/selftests/net/openvswitch/openvswitch.sh +++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh @@ -26,6 +26,7 @@ tests=" netlink_checks ovsnl: validate netlink attrs and settings upcall_interfaces ovs: test the upcall interfaces tunnel_metadata ovs: test extraction of tunnel metadata + tunnel_refcount ovs: test tunnel vport reference cleanup drop_reason drop: test drop reasons are emitted psample psample: Sampling packets with psample" @@ -830,6 +831,42 @@ test_tunnel_metadata() { return 0 } +test_tunnel_refcount() { + sbxname="test_tunnel_refcount" + sbx_add "${sbxname}" || return 1 + + ovs_sbx "${sbxname}" ip netns add trefns || return 1 + on_exit "ovs_sbx ${sbxname} ip netns del trefns" + + for tun_type in gre vxlan geneve; do + info "testing ${tun_type} tunnel vport refcount" + + ovs_sbx "${sbxname}" ip netns exec trefns \ + python3 $ovs_base/ovs-dpctl.py \ + add-dp dp-${tun_type} || return 1 + + ovs_sbx "${sbxname}" ip netns exec trefns \ + python3 $ovs_base/ovs-dpctl.py \ + add-if --no-lwt -t ${tun_type} \ + dp-${tun_type} ovs-${tun_type}0 || return 1 + + ovs_wait ip -netns trefns link show \ + ovs-${tun_type}0 >/dev/null 2>&1 || return 1 + + info "deleting dp - may hang if reference counting is broken" + ovs_sbx "${sbxname}" ip netns exec trefns \ + python3 $ovs_base/ovs-dpctl.py \ + del-dp dp-${tun_type} & + + dev_removed() { + ! ip -netns trefns link show "$1" >/dev/null 2>&1 + } + ovs_wait dev_removed dp-${tun_type} || return 1 + ovs_wait dev_removed ovs-${tun_type}0 || return 1 + done + return 0 +} + run_test() { ( tname="$1" diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py index 848f61fdcee0..bbe35e2718d2 100644 --- a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py +++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py @@ -11,7 +11,6 @@ import logging import math import multiprocessing import re -import socket import struct import sys import time @@ -2069,7 +2068,7 @@ class OvsVport(GenericNetlinkSocket): elif vport_type == "internal": return OvsVport.OVS_VPORT_TYPE_INTERNAL elif vport_type == "gre": - return OvsVport.OVS_VPORT_TYPE_INTERNAL + return OvsVport.OVS_VPORT_TYPE_GRE elif vport_type == "vxlan": return OvsVport.OVS_VPORT_TYPE_VXLAN elif vport_type == "geneve": @@ -2121,6 +2120,7 @@ class OvsVport(GenericNetlinkSocket): ) TUNNEL_DEFAULTS = [("geneve", 6081), + ("gre", 0), ("vxlan", 4789)] for tnl in TUNNEL_DEFAULTS: @@ -2129,9 +2129,13 @@ class OvsVport(GenericNetlinkSocket): dport = tnl[1] if not lwt: + if tnl[0] == "gre": + # GRE tunnels have no options. + break + vportopt = OvsVport.ovs_vport_msg.vportopts() vportopt["attrs"].append( - ["OVS_TUNNEL_ATTR_DST_PORT", socket.htons(dport)] + ["OVS_TUNNEL_ATTR_DST_PORT", dport] ) msg["attrs"].append( ["OVS_VPORT_ATTR_OPTIONS", vportopt] @@ -2145,6 +2149,9 @@ class OvsVport(GenericNetlinkSocket): geneve_port=dport, geneve_collect_metadata=True, geneve_udp_zero_csum6_rx=1) + elif tnl[0] == "gre": + ipr.link("add", ifname=vport_ifname, kind="gretap", + gre_collect_metadata=True) elif tnl[0] == "vxlan": ipr.link("add", ifname=vport_ifname, kind=tnl[0], vxlan_learning=0, vxlan_collect_metadata=1, @@ -2563,7 +2570,7 @@ def print_ovsdp_full(dp_lookup_rep, ifindex, ndb=NDB(), vpl=OvsVport()): if vpo: dpo = vpo.get_attr("OVS_TUNNEL_ATTR_DST_PORT") if dpo: - opts += " tnl-dport:%s" % socket.ntohs(dpo) + opts += " tnl-dport:%s" % dpo print( " port %d: %s (%s%s)" % ( @@ -2632,7 +2639,7 @@ def main(argv): "--ptype", type=str, default="netdev", - choices=["netdev", "internal", "geneve", "vxlan"], + choices=["netdev", "internal", "gre", "geneve", "vxlan"], help="Interface type (default netdev)", ) addifcmd.add_argument( @@ -2645,7 +2652,7 @@ def main(argv): addifcmd.add_argument( "-l", "--lwt", - type=bool, + action=argparse.BooleanOptionalAction, default=True, help="Use LWT infrastructure instead of vport (default true)." ) diff --git a/tools/testing/selftests/net/ovpn/test.sh b/tools/testing/selftests/net/ovpn/test.sh index b50dbe45a4d0..c06e3135fbef 100755 --- a/tools/testing/selftests/net/ovpn/test.sh +++ b/tools/testing/selftests/net/ovpn/test.sh @@ -98,10 +98,10 @@ ovpn_run_basic_traffic() { sleep 0.3 ovpn_cmd_ok "send baseline traffic to peer ${p}" \ ip netns exec ovpn_peer0 \ - ping -qfc 500 -w 3 5.5.5.$((p + 1)) + ping -qfc 100 -w 3 5.5.5.$((p + 1)) ovpn_cmd_ok "send large-payload traffic to peer ${p}" \ ip netns exec ovpn_peer0 \ - ping -qfc 500 -s 3000 -w 3 5.5.5.$((p + 1)) + ping -qfc 100 -s 3000 -w 3 5.5.5.$((p + 1)) wait "${tcpdump_pid1}" || return 1 wait "${tcpdump_pid2}" || return 1 diff --git a/tools/testing/selftests/net/tcp_ecmp_failover.sh b/tools/testing/selftests/net/tcp_ecmp_failover.sh new file mode 100755 index 000000000000..5768aa8bff6a --- /dev/null +++ b/tools/testing/selftests/net/tcp_ecmp_failover.sh @@ -0,0 +1,216 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright 2026 Google LLC. +# +# This test verifies TCP flow failover between ECMP routes +# upon carrier loss on the active device. +# +# socat -----------------------------> socat +# | +# .-- veth-c1 -|- veth-s1 --. +# dummy0 -| | |-- dummy0 +# '-- veth-c2 -|- veth-s2 --' +# | +# + +REQUIRE_JQ=no +REQUIRE_MZ=no +NUM_NETIFS=0 + +source forwarding/lib.sh + +CLIENT_IP="10.0.59.1" +SERVER_IP="10.0.92.1" +CLIENT_IP6="2001:db8:5a9a::1" +SERVER_IP6="2001:db8:9292::1" + +setup_server() +{ + IP="ip -n $server" + NS_EXEC="ip netns exec $server" + + $IP link add dummy0 type dummy + $IP link set dummy0 up + + $IP -4 addr add $SERVER_IP/32 dev dummy0 + $IP -6 addr add $SERVER_IP6/128 dev dummy0 nodad + + $IP link set veth-s1 up + $IP link set veth-s2 up + + $IP -4 addr add 192.168.1.2/24 dev veth-s1 + $IP -4 addr add 192.168.2.2/24 dev veth-s2 + + $IP -4 route add $CLIENT_IP/32 \ + nexthop via 192.168.1.1 dev veth-s1 weight 1 \ + nexthop via 192.168.2.1 dev veth-s2 weight 1 + + $IP -6 addr add 2001:db8:1::2/64 dev veth-s1 nodad + $IP -6 addr add 2001:db8:2::2/64 dev veth-s2 nodad + + $IP -6 route add $CLIENT_IP6/128 \ + nexthop via 2001:db8:1::1 dev veth-s1 weight 1 \ + nexthop via 2001:db8:2::1 dev veth-s2 weight 1 +} + +setup_client() +{ + IP="ip -n $client" + NS_EXEC="ip netns exec $client" + + $IP link add dummy0 type dummy + $IP link set dummy0 up + + $IP -4 addr add $CLIENT_IP/32 dev dummy0 + $IP -6 addr add $CLIENT_IP6/128 dev dummy0 nodad + + $IP link set veth-c1 up + $IP link set veth-c2 up + + $IP -4 addr add 192.168.1.1/24 dev veth-c1 + $IP -4 addr add 192.168.2.1/24 dev veth-c2 + + $IP -4 route add $SERVER_IP/32 \ + nexthop via 192.168.1.2 dev veth-c1 weight 1 \ + nexthop via 192.168.2.2 dev veth-c2 weight 1 + + $IP -6 addr add 2001:db8:1::1/64 dev veth-c1 nodad + $IP -6 addr add 2001:db8:2::1/64 dev veth-c2 nodad + + $IP -6 route add $SERVER_IP6/128 \ + nexthop via 2001:db8:1::2 dev veth-c1 weight 1 \ + nexthop via 2001:db8:2::2 dev veth-c2 weight 1 + + # By default, tcp_retries1=3 triggers a route refresh + # after 3 retransmits (~5s). Ensure this never occurs + # for test stability. + $NS_EXEC sysctl -qw net.ipv4.tcp_retries1=100 + + # When NETDEV_CHANGE is issued for a dev tied to an ECMP + # route, RTNH_F_LINKDOWN is flagged and the sernum is + # bumped to invalidate the route via sk_dst_check(). + # + # Without ignore_routes_with_linkdown=1, subsequent + # lookups may still select the same RTNH_F_LINKDOWN route. + $NS_EXEC sysctl -qw net.ipv4.conf.veth-c1.ignore_routes_with_linkdown=1 + $NS_EXEC sysctl -qw net.ipv4.conf.veth-c2.ignore_routes_with_linkdown=1 + + $NS_EXEC sysctl -qw net.ipv6.conf.veth-c1.ignore_routes_with_linkdown=1 + $NS_EXEC sysctl -qw net.ipv6.conf.veth-c2.ignore_routes_with_linkdown=1 +} + +setup() +{ + setup_ns client server + + ip -n "$client" link add veth-c1 type veth peer veth-s1 netns "$server" + ip -n "$client" link add veth-c2 type veth peer veth-s2 netns "$server" + + setup_server + setup_client +} + +cleanup() +{ + cleanup_all_ns > /dev/null 2>&1 +} + +tcp_ecmp_failover() +{ + local pf=$1; shift + local server_ip=$1; shift + local client_ip=$1; shift + + RET=0 + + tcpdump_start veth-s1 "$server" + tcpdump_start veth-s2 "$server" + + ip netns exec "$server" \ + socat -u TCP-LISTEN:8080,pf="$pf",bind="$server_ip",reuseaddr /dev/null & + server_pid=$! + + # Wait for server to start listening. + # Sometimes client fails without this sleep. + sleep 1 + + ip netns exec "$client" \ + socat -u /dev/zero TCP:"$server_ip":8080,pf="$pf",bind="$client_ip" & + client_pid=$! + + # To capture enough packets. + sleep 3 + + tcpdump_stop veth-s1 + tcpdump_stop veth-s2 + + pkts_s1=$(tcpdump_show veth-s1 | wc -l) + pkts_s2=$(tcpdump_show veth-s2 | wc -l) + + tcpdump_cleanup veth-s1 + tcpdump_cleanup veth-s2 + + # Detect the device chosen by the client + if [ "$pkts_s1" -gt "$pkts_s2" ]; then + veth_down=veth-s1 + veth_up=veth-s2 + else + veth_down=veth-s2 + veth_up=veth-s1 + fi + + # Taking down $veth_down causes its peer to lose carrier, + # triggering NETDEV_CHANGE. This flags RTNH_F_LINKDOWN + # and bumps the sernum for the route associated with that + # peer, invalidating the cached dst in the TCP socket. + # + # Consequently, sk_dst_check() fails, forcing the subsequent + # lookup to select the remaining healthy route via $veth_up. + ip -n "$server" link set "$veth_down" down + + tcpdump_start "$veth_up" "$server" + + # To capture enough packets. + sleep 3 + + tcpdump_stop "$veth_up" + + kill -9 "$client_pid" > /dev/null 2>&1 + kill -9 "$server_pid" > /dev/null 2>&1 + wait 2> /dev/null + + pkts=$(tcpdump_show $veth_up | wc -l) + + tcpdump_cleanup "$veth_up" + + if [ "$pkts" -lt 1000 ]; then + RET=$ksft_fail + fi +} + +test_ipv4() +{ + setup + tcp_ecmp_failover IPv4 $SERVER_IP $CLIENT_IP + log_test "TCP IPv4 failover" + cleanup +} + +test_ipv6() +{ + setup + tcp_ecmp_failover IPv6 "[$SERVER_IP6]" "[$CLIENT_IP6]" + log_test "TCP IPv6 failover" + cleanup +} + +require_command socat +require_command tcpdump + +trap cleanup EXIT + +test_ipv4 +test_ipv6 + +exit "$EXIT_STATUS" diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 9e2ccea13d70..30a236b8e9f7 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -946,6 +946,49 @@ TEST_F(tls, peek_and_splice) EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); } +TEST_F(tls, splice_to_pipe_small) +{ + int send_len = TLS_PAYLOAD_MAX_LEN; + char mem_send[TLS_PAYLOAD_MAX_LEN]; + char mem_recv[TLS_PAYLOAD_MAX_LEN]; + size_t total = 0; + int p[2]; + + memrnd(mem_send, sizeof(mem_send)); + + ASSERT_GE(pipe(p), 0); + + /* Shrink pipe to 1 page (typically 4096 bytes) to force multiple + * splice iterations for a 16384-byte TLS record. + */ + EXPECT_GE(fcntl(p[1], F_SETPIPE_SZ, 4096), 4096); + + EXPECT_EQ(send(self->fd, mem_send, send_len, 0), send_len); + + while (total < (size_t)send_len) { + ssize_t spliced, drained; + + spliced = splice(self->cfd, NULL, p[1], NULL, + send_len - total, 0); + EXPECT_GT(spliced, 0); + if (spliced <= 0) + break; + + drained = read(p[0], mem_recv + total, spliced); + EXPECT_EQ(drained, spliced); + if (drained <= 0) + break; + + total += drained; + } + + EXPECT_EQ(total, (size_t)send_len); + EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); + + close(p[0]); + close(p[1]); +} + #define MAX_FRAGS 48 TEST_F(tls, splice_short) { diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile index 789037be44c7..5d2dffca0e91 100644 --- a/tools/testing/selftests/sched_ext/Makefile +++ b/tools/testing/selftests/sched_ext/Makefile @@ -175,6 +175,7 @@ auto-test-targets := \ maximal \ maybe_null \ minimal \ + non_scx_kfunc_deny \ numa \ allowed_cpus \ peek_dsq \ diff --git a/tools/testing/selftests/sched_ext/non_scx_kfunc_deny.bpf.c b/tools/testing/selftests/sched_ext/non_scx_kfunc_deny.bpf.c new file mode 100644 index 000000000000..9f16d39255e7 --- /dev/null +++ b/tools/testing/selftests/sched_ext/non_scx_kfunc_deny.bpf.c @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Verify that context-sensitive SCX kfuncs (even "unlocked" ones) are + * restricted to only SCX struct_ops programs. Non-SCX struct_ops programs, + * such as TCP congestion control programs, should be rejected by the BPF + * verifier when attempting to call these kfuncs. + * + * Copyright (C) 2026 Ching-Chun (Jim) Huang <jserv@ccns.ncku.edu.tw> + * Copyright (C) 2026 Cheng-Yang Chou <yphbchou0911@gmail.com> + */ + +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +/* SCX kfunc from scx_kfunc_ids_any set */ +void scx_bpf_kick_cpu(s32 cpu, u64 flags) __ksym; + +SEC("struct_ops/ssthresh") +__u32 BPF_PROG(tcp_ca_ssthresh, struct sock *sk) +{ + /* + * This call should be rejected by the verifier because this is a + * TCP congestion control program (non-SCX struct_ops). + */ + scx_bpf_kick_cpu(0, 0); + return 2; +} + +SEC("struct_ops/cong_avoid") +void BPF_PROG(tcp_ca_cong_avoid, struct sock *sk, __u32 ack, __u32 acked) {} + +SEC("struct_ops/undo_cwnd") +__u32 BPF_PROG(tcp_ca_undo_cwnd, struct sock *sk) { return 2; } + +SEC(".struct_ops") +struct tcp_congestion_ops tcp_non_scx_ca = { + .ssthresh = (void *)tcp_ca_ssthresh, + .cong_avoid = (void *)tcp_ca_cong_avoid, + .undo_cwnd = (void *)tcp_ca_undo_cwnd, + .name = "tcp_kfunc_deny", +}; + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/sched_ext/non_scx_kfunc_deny.c b/tools/testing/selftests/sched_ext/non_scx_kfunc_deny.c new file mode 100644 index 000000000000..1c031575fb87 --- /dev/null +++ b/tools/testing/selftests/sched_ext/non_scx_kfunc_deny.c @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Verify that context-sensitive SCX kfuncs (even "unlocked" ones) are + * restricted to only SCX struct_ops programs. Non-SCX struct_ops programs, + * such as TCP congestion control programs, should be rejected by the BPF + * verifier when attempting to call these kfuncs. + * + * Copyright (C) 2026 Ching-Chun (Jim) Huang <jserv@ccns.ncku.edu.tw> + * Copyright (C) 2026 Cheng-Yang Chou <yphbchou0911@gmail.com> + */ + +#include <bpf/bpf.h> +#include <scx/common.h> +#include <unistd.h> +#include <errno.h> +#include <stdio.h> +#include "non_scx_kfunc_deny.bpf.skel.h" +#include "scx_test.h" + +static enum scx_test_status run(void *ctx) +{ + struct non_scx_kfunc_deny *skel; + int err; + + skel = non_scx_kfunc_deny__open(); + if (!skel) { + SCX_ERR("Failed to open skel"); + return SCX_TEST_FAIL; + } + + err = non_scx_kfunc_deny__load(skel); + non_scx_kfunc_deny__destroy(skel); + + if (err == 0) { + SCX_ERR("non-SCX BPF program loaded when it should have been rejected"); + return SCX_TEST_FAIL; + } + + return SCX_TEST_PASS; +} + +struct scx_test non_scx_kfunc_deny = { + .name = "non_scx_kfunc_deny", + .description = "Verify that non-SCX struct_ops programs cannot call SCX kfuncs", + .run = run, +}; +REGISTER_SCX_TEST(&non_scx_kfunc_deny) diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json index eefadd0546d3..b1f856cf62c1 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json +++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json @@ -1136,5 +1136,153 @@ "teardown": [ "$TC qdisc del dev $DUMMY handle 1: root" ] + }, + { + "id": "7a5f", + "name": "Force red to dequeue from its child's gso_skb with qfq leaf", + "category": [ + "qdisc", + "tbf", + "red", + "qfq" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.11.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: tbf rate 88bit burst 1661b peakrate 2257333 minburst 1024 limit 7b", + "$TC qdisc add dev $DUMMY parent 1: handle 2: red limit 757 min 16 max 24 avpkt 16", + "$TC qdisc add dev $DUMMY parent 2: handle 3: qfq", + "$TC class add dev $DUMMY classid 3:1 parent 3: qfq maxpkt 512 weight 1", + "$TC filter add dev $DUMMY parent 3: protocol ip prio 1 matchall classid 3:1 action ok" + ], + "cmdUnderTest": "ping -c 1 10.10.10.1 -W0.01 -I$DUMMY || true", + "expExitCode": "0", + "verifyCmd": "$TC -s -j qdisc ls dev $DUMMY parent 1:", + "matchJSON": [ + { + "kind": "red", + "handle": "2:", + "bytes": 98, + "packets": 1, + "backlog": 0, + "qlen": 0 + } + ], + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "cdae", + "name": "Force sfb to dequeue from its child's gso_skb with qfq leaf", + "category": [ + "qdisc", + "tbf", + "sfb", + "qfq" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.11.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: tbf rate 88bit burst 1661b peakrate 2257333 minburst 1024 limit 7b", + "$TC qdisc add dev $DUMMY parent 1: handle 2: sfb", + "$TC qdisc add dev $DUMMY parent 2: handle 3: qfq", + "$TC class add dev $DUMMY classid 3:1 parent 3: qfq maxpkt 512 weight 1", + "$TC filter add dev $DUMMY parent 3: protocol ip prio 1 matchall classid 3:1 action ok" + ], + "cmdUnderTest": "ping -c 1 10.10.10.1 -W0.01 -I$DUMMY || true", + "expExitCode": "0", + "verifyCmd": "$TC -s -j qdisc ls dev $DUMMY parent 1:", + "matchJSON": [ + { + "kind": "sfb", + "handle": "2:", + "bytes": 98, + "packets": 1, + "backlog": 0, + "qlen": 0 + } + ], + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "291d", + "name": "Force red to dequeue from its child's gso_skb with dualpi2 leaf", + "category": [ + "qdisc", + "tbf", + "red", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.11.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: tbf rate 88bit burst 1661b peakrate 2257333 minburst 1024 limit 7b", + "$TC qdisc add dev $DUMMY parent 1: handle 2: red limit 757 min 16 max 24 avpkt 16", + "$TC qdisc add dev $DUMMY parent 2: handle 3: dualpi2" + ], + "cmdUnderTest": "ping -c 1 10.10.10.1 -W0.01 -I$DUMMY || true", + "expExitCode": "0", + "verifyCmd": "$TC -s -j qdisc ls dev $DUMMY parent 1:", + "matchJSON": [ + { + "kind": "red", + "handle": "2:", + "bytes": 98, + "packets": 1, + "backlog": 0, + "qlen": 0 + } + ], + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "9c6d", + "name": "Force sfb to dequeue from its child's gso_skb with dualpi2 leaf", + "category": [ + "qdisc", + "tbf", + "sfb", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.11.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: tbf rate 88bit burst 1661b peakrate 2257333 minburst 1024 limit 7b", + "$TC qdisc add dev $DUMMY parent 1: handle 2: sfb", + "$TC qdisc add dev $DUMMY parent 2: handle 3: dualpi2" + ], + "cmdUnderTest": "ping -c 1 10.10.10.1 -W0.01 -I$DUMMY || true", + "expExitCode": "0", + "verifyCmd": "$TC -s -j qdisc ls dev $DUMMY parent 1:", + "matchJSON": [ + { + "kind": "sfb", + "handle": "2:", + "bytes": 98, + "packets": 1, + "backlog": 0, + "qlen": 0 + } + ], + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json index 557fb074acf0..cd19d05925e4 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json @@ -302,5 +302,31 @@ "$TC qdisc del dev $ETH root", "echo \"1\" > /sys/bus/netdevsim/del_device" ] + }, + { + "id": "c7e1", + "name": "Class dump after graft and delete of explicit child qdisc", + "category": [ + "qdisc", + "taprio" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "echo \"1 1 8\" > /sys/bus/netdevsim/new_device", + "$TC qdisc replace dev $ETH handle 8001: parent root taprio num_tc 8 map 0 1 2 3 4 5 6 7 queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 base-time 0 sched-entry S ff 20000000 clockid CLOCK_TAI", + "$TC qdisc add dev $ETH parent 8001:1 handle 8002: pfifo", + "$TC qdisc del dev $ETH parent 8001:1 handle 8002:" + ], + "cmdUnderTest": "$TC class show dev $ETH", + "expExitCode": "0", + "verifyCmd": "$TC class show dev $ETH", + "matchPattern": "class taprio 8001:[0-9]+ root", + "matchCount": "8", + "teardown": [ + "$TC qdisc del dev $ETH root", + "echo \"1\" > /sys/bus/netdevsim/del_device" + ] } ] diff --git a/tools/testing/vma/include/dup.h b/tools/testing/vma/include/dup.h index b4864aad2db0..9e0dfd3a85b0 100644 --- a/tools/testing/vma/include/dup.h +++ b/tools/testing/vma/include/dup.h @@ -1330,7 +1330,7 @@ static inline int __compat_vma_mmap(struct vm_area_desc *desc, /* Update the VMA from the descriptor. */ compat_set_vma_from_desc(vma, desc); /* Complete any specified mmap actions. */ - return mmap_action_complete(vma, &desc->action); + return mmap_action_complete(vma, &desc->action, /*is_compat=*/true); } static inline int compat_vma_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/tools/testing/vma/include/stubs.h b/tools/testing/vma/include/stubs.h index a30b8bc84955..64164e25658f 100644 --- a/tools/testing/vma/include/stubs.h +++ b/tools/testing/vma/include/stubs.h @@ -87,7 +87,8 @@ static inline int mmap_action_prepare(struct vm_area_desc *desc) } static inline int mmap_action_complete(struct vm_area_struct *vma, - struct mmap_action *action) + struct mmap_action *action, + bool is_compat) { return 0; } |