diff options
395 files changed, 6534 insertions, 2631 deletions
@@ -19,7 +19,8 @@ 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> +Aditya Garg <aditya.garg@linux.dev> <gargaditya08@live.com> +Aditya Garg <aditya.garg@linux.dev> <gargaditya08@proton.me> Adriana Reus <adi.reus@gmail.com> <adriana.reus@intel.com> Adrian Bunk <bunk@stusta.de> Ajay Kaher <ajay.kaher@broadcom.com> <akaher@vmware.com> @@ -699,6 +700,7 @@ Oliver Hartkopp <socketcan@hartkopp.net> <oliver.hartkopp@volkswagen.de> Oliver Hartkopp <socketcan@hartkopp.net> <oliver@hartkopp.net> Oliver Upton <oupton@kernel.org> <oupton@google.com> Oliver Upton <oupton@kernel.org> <oliver.upton@linux.dev> +Ondrej Mosnáček <omosnacek@gmail.com> <omosnace@redhat.com> Ondřej Jirman <megi@xff.cz> <megous@megous.com> Oza Pawandeep <quic_poza@quicinc.com> <poza@codeaurora.org> Pali Rohár <pali@kernel.org> <pali.rohar@gmail.com> @@ -898,7 +900,8 @@ Thomas Graf <tgraf@suug.ch> Thomas Gleixner <tglx@kernel.org> <tglx@linutronix.de> Thomas Körper <socketcan@esd.eu> <thomas.koerper@esd.eu> Thomas Pedersen <twp@codeaurora.org> -Thorsten Blum <thorsten.blum@linux.dev> <thorsten.blum@toblux.com> +Thorsten Blum <blum@kernel.org> <thorsten.blum@toblux.com> +Thorsten Blum <blum@kernel.org> <thorsten.blum@linux.dev> Tiezhu Yang <yangtiezhu@loongson.cn> <kernelpatch@126.com> Tingwei Zhang <quic_tingwei@quicinc.com> <tingwei@codeaurora.org> Tirupathi Reddy <quic_tirupath@quicinc.com> <tirupath@codeaurora.org> @@ -1512,6 +1512,10 @@ N: Andy Gross E: agross@kernel.org D: Qualcomm SoC subsystem and drivers +N: Mark Gross +E: markgross@kernel.org +D: x86/mellanox platform maintenance and various x86 specific drivers + N: Grant Grundler E: grantgrundler@gmail.com W: http://obmouse.sourceforge.net/ diff --git a/Documentation/ABI/testing/ima_policy b/Documentation/ABI/testing/ima_policy index 19258471b7b2..b8a763e4c9fb 100644 --- a/Documentation/ABI/testing/ima_policy +++ b/Documentation/ABI/testing/ima_policy @@ -108,6 +108,9 @@ Description: # NSFS_MAGIC dont_measure fsmagic=0x6e736673 dont_appraise fsmagic=0x6e736673 + # CONFIGFS_MAGIC + dont_measure fsmagic=0x62656570 + dont_appraise fsmagic=0x62656570 measure func=BPRM_CHECK measure func=FILE_MMAP mask=MAY_EXEC diff --git a/Documentation/admin-guide/cgroup-v1/memory.rst b/Documentation/admin-guide/cgroup-v1/memory.rst index 7db63c002922..7d2a44af52c9 100644 --- a/Documentation/admin-guide/cgroup-v1/memory.rst +++ b/Documentation/admin-guide/cgroup-v1/memory.rst @@ -47,7 +47,6 @@ Features: - pages are linked to per-memcg LRU exclusively, and there is no global LRU. - optionally, memory+swap usage can be accounted and limited. - hierarchical accounting - - soft limit - moving (recharging) account at moving a task is selectable. - usage threshold notifier - memory pressure notifier @@ -76,10 +75,9 @@ Brief summary of control files. memory.memsw.failcnt show the number of memory+Swap hits limits memory.max_usage_in_bytes show max memory usage recorded memory.memsw.max_usage_in_bytes show max memory+Swap usage recorded - memory.soft_limit_in_bytes set/show soft limit of memory usage - This knob is not available on CONFIG_PREEMPT_RT systems. - This knob is deprecated and shouldn't be - used. + memory.soft_limit_in_bytes This knob is deprecated and has no effect. + Writes are ignored and reads always + return the maximum value. memory.stat show various statistics memory.use_hierarchy set/show hierarchical account enabled This knob is deprecated and shouldn't be @@ -340,9 +338,6 @@ memory.kmem.usage_in_bytes, or in a separate counter when it makes sense. The main "kmem" counter is fed into the main counter, so kmem charges will also be visible from the user counter. -Currently no soft limit is implemented for kernel memory. It is future work -to trigger slab reclaim when those limits are reached. - 2.7.1 Current Kernel Memory resources accounted ----------------------------------------------- @@ -710,42 +705,10 @@ For compatibility reasons writing 1 to memory.use_hierarchy will always pass:: THIS IS DEPRECATED! -Soft limits allow for greater sharing of memory. The idea behind soft limits -is to allow control groups to use as much of the memory as needed, provided - -a. There is no memory contention -b. They do not exceed their hard limit - -When the system detects memory contention or low memory, control groups -are pushed back to their soft limits. If the soft limit of each control -group is very high, they are pushed back as much as possible to make -sure that one control group does not starve the others of memory. - -Please note that soft limits is a best-effort feature; it comes with -no guarantees, but it does its best to make sure that when memory is -heavily contended for, memory is allocated based on the soft limit -hints/setup. Currently soft limit based reclaim is set up such that -it gets invoked from balance_pgdat (kswapd). - -7.1 Interface -------------- - -Soft limits can be setup by using the following commands (in this example we -assume a soft limit of 256 MiB):: - - # echo 256M > memory.soft_limit_in_bytes - -If we want to change this to 1G, we can at any time use:: +Writing to memory.soft_limit_in_bytes has no effect and reading it will +always return the maximum value. - # echo 1G > memory.soft_limit_in_bytes - -.. note:: - Soft limits take effect over a long period of time, since they involve - reclaiming memory for balancing between memory cgroups - -.. note:: - It is recommended to set the soft limit always below the hard limit, - otherwise the hard limit will take precedence. +Use memory.low and memory.min in cgroup v2 instead. .. _cgroup-v1-memory-move-charges: diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 7c2a8ed80071..86a2a0099178 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1130,9 +1130,9 @@ policy and the underlying scheduler. From the point of view of the cpu controlle processes can be categorized as follows: * Processes under the fair-class scheduler -* Processes under a BPF scheduler with the ``cgroup_set_weight`` callback +* Processes under a BPF scheduler with the corresponding ``cgroup_set_*`` callback * Everything else: ``SCHED_{FIFO,RR,DEADLINE}`` and processes under a BPF scheduler - without the ``cgroup_set_weight`` callback + without the corresponding ``cgroup_set_*`` callback For details on when a process is under the fair-class scheduler or a BPF scheduler, check out :ref:`Documentation/scheduler/sched-ext.rst <sched-ext>`. @@ -1223,7 +1223,9 @@ will be referred to. All time durations are in microseconds. $PERIOD duration. "max" for $MAX indicates no limit. If only one number is written, $MAX is updated. - This file affects only processes under the fair-class scheduler. + This file affects only processes under the fair-class scheduler and a BPF + scheduler with the ``cgroup_set_bandwidth`` callback depending on what + the callback actually does. cpu.max.burst A read-write single value file which exists on non-root @@ -1231,7 +1233,9 @@ will be referred to. All time durations are in microseconds. The burst in the range [0, $MAX]. - This file affects only processes under the fair-class scheduler. + This file affects only processes under the fair-class scheduler and a BPF + scheduler with the ``cgroup_set_bandwidth`` callback depending on what + the callback actually does. cpu.pressure A read-write nested-keyed file. @@ -1283,7 +1287,9 @@ will be referred to. All time durations are in microseconds. own relative priorities, but the cgroup itself will be treated as very low priority relative to its peers. - This file affects only processes under the fair-class scheduler. + This file affects only processes under the fair-class scheduler and a BPF + scheduler with the ``cgroup_set_idle`` callback depending on what the + callback actually does. Memory ------ @@ -3064,7 +3070,7 @@ resources (res_a and res_b) are registered then: change in this file generates a file modified event. All fields in this file are hierarchical. - max + <res>.max The number of times the cgroup's resource usage was about to go over the max boundary. diff --git a/Documentation/fault-injection/nvme-fault-injection.rst b/Documentation/fault-injection/nvme-fault-injection.rst index 1d4427890d75..09730acf0163 100644 --- a/Documentation/fault-injection/nvme-fault-injection.rst +++ b/Documentation/fault-injection/nvme-fault-injection.rst @@ -176,3 +176,68 @@ Message from dmesg:: secondary_startup_64+0xa4/0xb0 nvme nvme0: Could not set queue count (16385) nvme nvme0: IO queues not created + +Example 4: Inject an error into the first write command +------------------------------------------------------- + +:: + + echo 0x01 > /sys/kernel/debug/nvme0n1/fault_inject/opcode + echo 1 > /sys/kernel/debug/nvme0n1/fault_inject/times + echo 100 > /sys/kernel/debug/nvme0n1/fault_inject/probability + dd if=/dev/zero of=/dev/nvme0n1 oflag=direct bs=512 count=1 + +Expected Result:: + + The first write command sent to nvme0n1 fails + +Message from dmesg:: + + FAULT_INJECTION: forcing a failure. + name fault_inject, interval 1, probability 100, space 0, times 1 + CPU: 4 UID: 0 PID: 0 Comm: swapper/4 Not tainted 7.1.0+ #5 PREEMPT(full) + Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-20240910_120124-localhost 04/01/2014 + Call Trace: + <IRQ> + dump_stack_lvl+0x6e/0xa0 + dump_stack+0x10/0x16 + should_fail_ex+0x461/0x510 + should_fail+0xb/0x20 + nvme_should_fail+0x11b/0x240 [nvme_core] + nvme_poll_cq+0x6ad/0xb30 [nvme] + nvme_irq+0x84/0xe0 [nvme] + ? __pfx_nvme_irq+0x10/0x10 [nvme] + ? rcu_core+0xa40/0xa90 + ? __pfx_sched_balance_softirq+0x10/0x10 + ? debug_smp_processor_id+0x17/0x20 + ? rcu_is_watching+0x13/0xa0 + __handle_irq_event_percpu+0x396/0x610 + handle_irq_event_percpu+0xf/0x90 + handle_irq_event+0xab/0x110 + handle_edge_irq+0x1a3/0x210 + __common_interrupt+0xff/0x170 + common_interrupt+0x90/0xc0 + </IRQ> + <TASK> + asm_common_interrupt+0x27/0x40 + RIP: 0010:pv_native_safe_halt+0x13/0x20 + Code: 1f 84 00 00 00 00 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 8b 05 0a 2a 58 01 85 c0 7e 07 0f 00 2d ff cc 0d 00 fb f4 <c3> cc 0 + RSP: 0018:ffff888100a67e40 EFLAGS: 00000242 + RAX: 0000000000000001 RBX: ffff888100a49c40 RCX: ffffed102b6c645b + RDX: ffffed102b6c645b RSI: ffffffff82a0d3c0 RDI: ffffffff81428b9b + RBP: ffff888100a67e48 R08: ffffed102b6c645b R09: 0000000000000004 + R10: ffffed102b6c645a R11: 0000000000000001 R12: 0000000000000000 + R13: 0000000000000000 R14: ffffed1020149388 R15: dffffc0000000000 + ? do_idle+0x19b/0x2c0 + ? default_idle+0x9/0x20 + arch_cpu_idle+0x9/0x10 + default_idle_call+0x6b/0xa0 + do_idle+0x19b/0x2c0 + ? __pfx_do_idle+0x10/0x10 + ? complete_with_flags+0x63/0x70 + cpu_startup_entry+0x55/0x60 + start_secondary+0x1df/0x1e0 + common_startup_64+0x13e/0x158 + </TASK> + nvme0n1: Write(0x1) @ LBA 0, 1 blocks, Invalid Command Opcode (sct 0x0 / sc 0x1) DNR + operation not supported error, dev nvme0n1, sector 0 op 0x1:(WRITE) flags 0x8800 phys_seg 1 prio class 2 diff --git a/Documentation/netlink/specs/conntrack.yaml b/Documentation/netlink/specs/conntrack.yaml index db7cddcda50a..b1eb102ab843 100644 --- a/Documentation/netlink/specs/conntrack.yaml +++ b/Documentation/netlink/specs/conntrack.yaml @@ -361,6 +361,17 @@ attribute-sets: type: u32 byte-order: big-endian - + name: filter-attrs + attributes: + - + name: orig-flags + type: u32 + doc: bitmask of tuple fields to filter on, original direction + - + name: reply-flags + type: u32 + doc: bitmask of tuple fields to filter on, reply direction + - name: conntrack-attrs attributes: - @@ -466,7 +477,7 @@ attribute-sets: - name: filter type: nest - nested-attributes: tuple-attrs + nested-attributes: filter-attrs - name: status-mask type: u32 @@ -591,10 +602,14 @@ operations: request: value: 0x101 attributes: - - mark - - filter + - tuple-orig + - tuple-reply - status + - mark - zone + - mark-mask + - filter + - status-mask reply: value: 0x100 attributes: diff --git a/Documentation/scheduler/sched-ext.rst b/Documentation/scheduler/sched-ext.rst index 0e97fd019994..794ae80b3ba3 100644 --- a/Documentation/scheduler/sched-ext.rst +++ b/Documentation/scheduler/sched-ext.rst @@ -230,7 +230,7 @@ optional. The following modified excerpt is from void BPF_STRUCT_OPS(simple_exit, struct scx_exit_info *ei) { - exit_type = ei->type; + exit_type = ei->kind; } SEC(".struct_ops") @@ -242,6 +242,21 @@ optional. The following modified excerpt is from .name = "simple", }; +Scheduler-Dependent Knobs +------------------------- + +The fair-class scheduler enforces CPU controller settings such as +``cpu.max``, ``cpu.weight`` and ``cpu.idle``. For sched_ext tasks, the +scheduler core communicates these settings to the BPF scheduler +through ``ops.cgroup_init()`` and reports subsequent changes through +the corresponding ``ops.cgroup_set_*()`` callbacks. Similarly, per-task +nice changes are converted to weights and reported through +``ops.set_weight()``. + +Each BPF scheduler is responsible for implementing the scheduling +semantics of these settings and may choose to ignore them. Consult the +loaded scheduler's documentation before relying on these controls. + Dispatch Queues --------------- diff --git a/MAINTAINERS b/MAINTAINERS index 3a19da74d00c..c9f866debdf0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8039,7 +8039,7 @@ F: drivers/gpu/drm/sun4i/sun8i* DRM DRIVER FOR APPLE TOUCH BARS M: Aun-Ali Zaidi <admin@kodeit.net> -M: Aditya Garg <gargaditya08@proton.me> +M: Aditya Garg <aditya.garg@linux.dev> L: dri-devel@lists.freedesktop.org S: Maintained T: git https://gitlab.freedesktop.org/drm/misc/kernel.git @@ -9387,9 +9387,8 @@ S: Maintained F: drivers/edac/octeon_edac* EDAC-CAVIUM THUNDERX -M: Robert Richter <rric@kernel.org> L: linux-edac@vger.kernel.org -S: Odd Fixes +S: Orphan F: drivers/edac/thunderx_edac* EDAC-CORE @@ -9416,9 +9415,8 @@ S: Supported F: drivers/edac/dmc520_edac.c EDAC-E752X -M: Mark Gross <markgross@kernel.org> L: linux-edac@vger.kernel.org -S: Maintained +S: Orphan F: drivers/edac/e752x_edac.c EDAC-E7XXX @@ -9493,9 +9491,8 @@ S: Maintained F: drivers/edac/igen6_edac.c EDAC-MPC85XX -M: Johannes Thumshirn <morbidrsa@gmail.com> L: linux-edac@vger.kernel.org -S: Maintained +S: Orphan F: drivers/edac/mpc85xx_edac.[ch] EDAC-NPCM @@ -12224,7 +12221,7 @@ F: drivers/tty/hvc/ HUNG TASK DETECTOR M: Andrew Morton <akpm@linux-foundation.org> -R: Lance Yang <lance.yang@linux.dev> +M: Lance Yang <lance.yang@linux.dev> R: Masami Hiramatsu <mhiramat@kernel.org> R: Petr Mladek <pmladek@suse.com> L: linux-kernel@vger.kernel.org @@ -13283,7 +13280,6 @@ F: drivers/crypto/intel/keembay/ocs-aes.h INTEL KEEM BAY OCS ECC CRYPTO DRIVER M: Prabhjot Khurana <prabhjot.khurana@intel.com> -M: Mark Gross <mgross@linux.intel.com> S: Maintained F: Documentation/devicetree/bindings/crypto/intel,keembay-ocs-ecc.yaml F: drivers/crypto/intel/keembay/Kconfig @@ -14240,8 +14236,6 @@ F: tools/testing/selftests/ KERNEL SMB3 SERVER (KSMBD) M: Namjae Jeon <linkinjeon@kernel.org> M: Namjae Jeon <linkinjeon@samba.org> -M: Steve French <smfrench@gmail.com> -M: Steve French <sfrench@samba.org> R: Sergey Senozhatsky <senozhatsky@chromium.org> R: Tom Talpey <tom@talpey.com> R: ChenXiaoSong <chenxiaosong@chenxiaosong.com> @@ -17416,7 +17410,6 @@ F: mm/swapfile.c MEMORY MANAGEMENT - THP (TRANSPARENT HUGE PAGE) M: Andrew Morton <akpm@linux-foundation.org> 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@infradead.org> @@ -17426,6 +17419,7 @@ R: Dev Jain <dev.jain@arm.com> R: Barry Song <baohua@kernel.org> R: Lance Yang <lance.yang@linux.dev> R: Usama Arif <usama.arif@linux.dev> +R: Kiryl Shutsemau <kas@kernel.org> L: linux-mm@kvack.org S: Maintained W: http://www.linux-mm.org @@ -17698,7 +17692,7 @@ F: Documentation/devicetree/bindings/serial/atmel,at91-usart.yaml F: drivers/spi/spi-at91-usart.c MICROCHIP ATSHA204A DRIVER -M: Thorsten Blum <thorsten.blum@linux.dev> +M: Thorsten Blum <blum@kernel.org> L: linux-crypto@vger.kernel.org S: Maintained F: drivers/crypto/atmel-sha204a.c @@ -17722,7 +17716,7 @@ F: Documentation/devicetree/bindings/media/microchip,csi2dc.yaml F: drivers/media/platform/microchip/microchip-csi2dc.c MICROCHIP ECC DRIVER -M: Thorsten Blum <thorsten.blum@linux.dev> +M: Thorsten Blum <blum@kernel.org> L: linux-crypto@vger.kernel.org S: Maintained F: drivers/crypto/atmel-ecc.c @@ -19569,7 +19563,7 @@ F: include/linux/platform_data/x86/nvidia-wmi-ec-backlight.h NVM EXPRESS DRIVER M: Keith Busch <kbusch@kernel.org> -M: Jens Axboe <axboe@fb.com> +M: Jens Axboe <axboe@kernel.dk> M: Christoph Hellwig <hch@lst.de> M: Sagi Grimberg <sagi@grimberg.me> L: linux-nvme@lists.infradead.org @@ -24778,7 +24772,7 @@ K: \bsecurity_[a-z_0-9]\+\b SELINUX SECURITY MODULE M: Paul Moore <paul@paul-moore.com> M: Stephen Smalley <stephen.smalley.work@gmail.com> -R: Ondrej Mosnacek <omosnace@redhat.com> +R: Ondrej Mosnáček <omosnacek@gmail.com> L: selinux@vger.kernel.org S: Supported W: https://github.com/SELinuxProject @@ -25236,10 +25230,9 @@ F: Documentation/admin-guide/LSM/Smack.rst F: security/smack/ SMBDIRECT (RDMA Stream Transport with Read/Write-Offload, MS-SMBD) -M: Steve French <smfrench@gmail.com> -M: Steve French <sfrench@samba.org> M: Namjae Jeon <linkinjeon@kernel.org> M: Namjae Jeon <linkinjeon@samba.org> +M: Paulo Alcantara <pc@manguebit.org> R: Stefan Metzmacher <metze@samba.org> R: Tom Talpey <tom@talpey.com> L: linux-cifs@vger.kernel.org @@ -25410,7 +25403,7 @@ F: drivers/md/md* F: drivers/md/raid* F: include/linux/raid/ F: include/uapi/linux/raid/ -F: lib/raid/raid6/ +F: lib/raid/ SOLIDRUN CLEARFOG SUPPORT M: Russell King <linux@armlinux.org.uk> @@ -26954,8 +26947,7 @@ S: Maintained F: drivers/net/ethernet/tehuti/tn40* TELECOM CLOCK DRIVER FOR MCPL0010 -M: Mark Gross <markgross@kernel.org> -S: Supported +S: Orphan F: drivers/char/tlclk.c TEMPO SEMICONDUCTOR DRIVERS @@ -29937,12 +29929,14 @@ F: include/uapi/linux/xilinx-v4l2-controls.h XILINX VERSAL EDAC DRIVER M: Shubhrajyoti Datta <shubhrajyoti.datta@amd.com> M: Sai Krishna Potthuri <sai.krishna.potthuri@amd.com> +R: Radhey Shyam Pandey <radhey.shyam.pandey@amd.com> S: Maintained F: Documentation/devicetree/bindings/memory-controllers/xlnx,versal-ddrmc-edac.yaml F: drivers/edac/versal_edac.c XILINX VERSALNET EDAC DRIVER M: Shubhrajyoti Datta <shubhrajyoti.datta@amd.com> +R: Radhey Shyam Pandey <radhey.shyam.pandey@amd.com> S: Maintained F: Documentation/devicetree/bindings/memory-controllers/xlnx,versal-net-ddrmc5.yaml F: drivers/edac/versalnet_edac.c @@ -29988,6 +29982,7 @@ F: include/dt-bindings/dma/xlnx-zynqmp-dpdma.h XILINX ZYNQMP OCM EDAC DRIVER M: Shubhrajyoti Datta <shubhrajyoti.datta@amd.com> M: Sai Krishna Potthuri <sai.krishna.potthuri@amd.com> +R: Radhey Shyam Pandey <radhey.shyam.pandey@amd.com> S: Maintained F: Documentation/devicetree/bindings/memory-controllers/xlnx,zynqmp-ocmc-1.0.yaml F: drivers/edac/zynqmp_edac.c diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h index 71493b760b83..3c008821219c 100644 --- a/arch/arm64/include/asm/cpu.h +++ b/arch/arm64/include/asm/cpu.h @@ -78,5 +78,6 @@ void __init cpuinfo_store_boot_cpu(void); void __init init_cpu_features(struct cpuinfo_arm64 *info); void update_cpu_features(int cpu, struct cpuinfo_arm64 *info, struct cpuinfo_arm64 *boot); +bool gmid_el1_accessible(const struct cpuinfo_arm64 *info); #endif /* __ASM_CPU_H */ diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 7404a6e83a93..4f04ad82ea34 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -627,13 +627,6 @@ static inline bool id_aa64pfr1_mpamfrac(u64 pfr1) return val > 0; } -static inline bool id_aa64pfr1_mte(u64 pfr1) -{ - u32 val = cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_EL1_MTE_SHIFT); - - return val >= ID_AA64PFR1_EL1_MTE_MTE2; -} - void __init setup_boot_cpu_features(void); void __init setup_system_features(void); void __init setup_user_features(void); diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 5db8f0619e4b..b33dccfafaf8 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -82,7 +82,7 @@ is_affected_midr_range(const struct arm64_cpu_capabilities *entry, int scope) for (i = 0; i < target_impl_cpu_num; i++) { if (__is_affected_midr_range(entry, target_impl_cpus[i].midr, - target_impl_cpus[i].midr)) + target_impl_cpus[i].revidr)) return true; } return false; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 17b83a2518a8..32102c3912fa 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1178,6 +1178,33 @@ static bool detect_ftr_has_mpam(void) return id_aa64pfr0_mpam(pfr0) || id_aa64pfr1_mpamfrac(pfr1); } +bool gmid_el1_accessible(const struct cpuinfo_arm64 *info) +{ + const struct arm64_ftr_bits *ftrp; + s64 mte, ovr; + u64 ftr_mask; + + /* No ID register reflects CONFIG_ARM64_MTE. */ + if (!IS_ENABLED(CONFIG_ARM64_MTE)) + return false; + + for (ftrp = ftr_id_aa64pfr1; ftrp->width; ftrp++) { + if (ftrp->shift == ID_AA64PFR1_EL1_MTE_SHIFT) + break; + } + + ftr_mask = arm64_ftr_mask(ftrp); + mte = arm64_ftr_value(ftrp, info->reg_id_aa64pfr1); + + /* The boot CPU runs before init_cpu_ftr_reg() strips unsafe overrides. */ + if ((id_aa64pfr1_override.mask & ftr_mask) == ftr_mask) { + ovr = arm64_ftr_value(ftrp, id_aa64pfr1_override.val); + mte = arm64_ftr_safe_value(ftrp, ovr, mte); + } + + return mte >= ID_AA64PFR1_EL1_MTE_MTE2; +} + void __init init_cpu_features(struct cpuinfo_arm64 *info) { /* Before we start using the tables, make sure it is sorted */ @@ -1230,7 +1257,7 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info) init_cpu_ftr_reg(SYS_MPAMIDR_EL1, info->reg_mpamidr); } - if (id_aa64pfr1_mte(info->reg_id_aa64pfr1)) + if (gmid_el1_accessible(info)) init_cpu_ftr_reg(SYS_GMID_EL1, info->reg_gmid); } @@ -1492,11 +1519,9 @@ void update_cpu_features(int cpu, * they read/write depends on the GMID_EL1.BS field. Check that the * value is the same on all CPUs. */ - if (IS_ENABLED(CONFIG_ARM64_MTE) && - id_aa64pfr1_mte(info->reg_id_aa64pfr1)) { + if (gmid_el1_accessible(info)) taint |= check_update_ftr_reg(SYS_GMID_EL1, cpu, info->reg_gmid, boot->reg_gmid); - } /* * If we don't have AArch32 at all then skip the checks entirely diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index d50e2a9b066b..45c63f3d75c5 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -502,7 +502,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info) info->reg_id_aa64smfr0 = read_cpuid(ID_AA64SMFR0_EL1); info->reg_id_aa64fpfr0 = read_cpuid(ID_AA64FPFR0_EL1); - if (id_aa64pfr1_mte(info->reg_id_aa64pfr1)) + if (gmid_el1_accessible(info)) info->reg_gmid = read_cpuid(GMID_EL1); if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0)) diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c index c5693a32e49b..8f9bc2327dc8 100644 --- a/arch/arm64/kernel/machine_kexec.c +++ b/arch/arm64/kernel/machine_kexec.c @@ -129,7 +129,8 @@ int machine_kexec_post_load(struct kimage *kimage) } /* Create a copy of the linear map */ - rc = trans_pgd_create_copy(&info, &trans_pgd, PAGE_OFFSET, PAGE_END); + rc = trans_pgd_create_copy(&info, &trans_pgd, + _PAGE_OFFSET(vabits_actual), PAGE_END); if (rc) return rc; kimage->arch.ttbr1 = __pa(trans_pgd); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 0b52557652be..75c3e463df2e 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -16,6 +16,7 @@ #include <linux/mm.h> #include <linux/hardirq.h> #include <linux/init.h> +#include <linux/irqflags.h> #include <linux/kasan.h> #include <linux/kprobes.h> #include <linux/uaccess.h> @@ -154,6 +155,9 @@ static void show_pte(unsigned long addr) pr_alert("%s pgtable: %luk pages, %llu-bit VAs, pgdp=%016lx\n", mm == &init_mm ? "swapper" : "user", PAGE_SIZE / SZ_1K, vabits_actual, mm_to_pgd_phys(mm)); + + guard(irqsave)(); + pgdp = pgd_offset(mm, addr); pgd = READ_ONCE(*pgdp); pr_alert("[%016lx] pgd=%016llx", addr, pgd_val(pgd)); @@ -167,25 +171,25 @@ static void show_pte(unsigned long addr) if (pgd_none(pgd) || pgd_bad(pgd)) break; - p4dp = p4d_offset(pgdp, addr); + p4dp = p4d_offset_lockless(pgdp, pgd, addr); p4d = READ_ONCE(*p4dp); pr_cont(", p4d=%016llx", p4d_val(p4d)); if (p4d_none(p4d) || p4d_bad(p4d)) break; - pudp = pud_offset(p4dp, addr); + pudp = pud_offset_lockless(p4dp, p4d, addr); pud = READ_ONCE(*pudp); pr_cont(", pud=%016llx", pud_val(pud)); if (pud_none(pud) || pud_bad(pud)) break; - pmdp = pmd_offset(pudp, addr); + pmdp = pmd_offset_lockless(pudp, pud, addr); pmd = READ_ONCE(*pmdp); pr_cont(", pmd=%016llx", pmd_val(pmd)); if (pmd_none(pmd) || pmd_bad(pmd)) break; - ptep = pte_offset_map(pmdp, addr); + ptep = pte_offset_map(&pmd, addr); if (!ptep) break; diff --git a/arch/s390/boot/alternative.c b/arch/s390/boot/alternative.c index 19ea7934b918..77e8bad560c5 100644 --- a/arch/s390/boot/alternative.c +++ b/arch/s390/boot/alternative.c @@ -45,11 +45,12 @@ static void alt_debug_modify(int type, unsigned int nr, bool clear) static char *alt_debug_parse(int type, char *str) { - unsigned long val, endval; + unsigned long val, endval, limit; char *endp; bool clear; int i; + limit = type == ALT_TYPE_FACILITY ? MAX_FACILITY_BIT : MAX_MFEATURE_BIT; if (*str == ':') { str++; } else { @@ -73,7 +74,7 @@ static char *alt_debug_parse(int type, char *str) if (str == endp) break; str = endp; - while (val <= endval) { + while (val <= endval && val < limit) { alt_debug_modify(type, val, clear); val++; } diff --git a/arch/s390/boot/ipl_parm.c b/arch/s390/boot/ipl_parm.c index 6bc950b92be7..c1b43e5e688a 100644 --- a/arch/s390/boot/ipl_parm.c +++ b/arch/s390/boot/ipl_parm.c @@ -23,6 +23,7 @@ struct parmarea parmarea __section(".parmarea") = { }; char __bootdata(early_command_line)[COMMAND_LINE_SIZE]; +static char command_line_buf[COMMAND_LINE_SIZE]; unsigned int __bootdata_preserved(zlib_dfltcc_support) = ZLIB_DFLTCC_FULL; struct ipl_parameter_block __bootdata_preserved(ipl_block); @@ -135,31 +136,29 @@ out: static void append_ipl_block_parm(void) { - char *parm, *delim; - size_t len, rc = 0; + size_t len, extra = 0; + char *delim; len = strlen(early_command_line); - - delim = early_command_line + len; /* '\0' character position */ - parm = early_command_line + len + 1; /* append right after '\0' */ + delim = early_command_line + len; /* '\0' character position */ switch (ipl_block.pb0_hdr.pbt) { case IPL_PBT_CCW: - rc = ipl_block_get_ascii_vmparm( - parm, COMMAND_LINE_SIZE - len - 1, &ipl_block); + extra = ipl_block_get_ascii_vmparm(command_line_buf, sizeof(command_line_buf), &ipl_block); break; case IPL_PBT_FCP: case IPL_PBT_NVME: case IPL_PBT_ECKD: - rc = ipl_block_get_ascii_scpdata( - parm, COMMAND_LINE_SIZE - len - 1, &ipl_block); + extra = ipl_block_get_ascii_scpdata(command_line_buf, sizeof(command_line_buf), &ipl_block); break; } - if (rc) { - if (*parm == '=') - memmove(early_command_line, parm + 1, rc); - else + if (extra) { + if (command_line_buf[0] == '=') { + memmove(early_command_line, command_line_buf + 1, extra); + } else if (len < COMMAND_LINE_SIZE - 2) { *delim = ' '; /* replace '\0' with space */ + sized_strscpy(delim + 1, command_line_buf, COMMAND_LINE_SIZE - len - 1); + } } } @@ -231,7 +230,7 @@ static void modify_fac_list(char *str) if (str == endp) break; str = endp; - while (val <= endval) { + while (val <= endval && val < MAX_FACILITY_BIT) { modify_facility(val, clear); val++; } @@ -245,7 +244,6 @@ static void modify_fac_list(char *str) check_cleared_facilities(); } -static char command_line_buf[COMMAND_LINE_SIZE]; void parse_boot_command_line(void) { char *param, *val; diff --git a/arch/s390/boot/physmem_info.c b/arch/s390/boot/physmem_info.c index 1f2ca5435838..0ebb2174713f 100644 --- a/arch/s390/boot/physmem_info.c +++ b/arch/s390/boot/physmem_info.c @@ -141,7 +141,7 @@ static int tprot(unsigned long addr) static unsigned long search_mem_end(void) { - unsigned long range = 1 << (MAX_PHYSMEM_BITS - 20); /* in 1MB blocks */ + unsigned long range = 1UL << (MAX_PHYSMEM_BITS - 20); /* in 1MB blocks */ unsigned long offset = 0; unsigned long pivot; diff --git a/arch/s390/include/asm/cpacf.h b/arch/s390/include/asm/cpacf.h index a83683169d98..6174552d856d 100644 --- a/arch/s390/include/asm/cpacf.h +++ b/arch/s390/include/asm/cpacf.h @@ -301,6 +301,7 @@ static __always_inline void __cpacf_query(unsigned int opcode, cpacf_mask_t *mask) { __cpacf_query_insn(opcode, mask, CPACF_FC_QUERY); + kmsan_unpoison_memory(mask, sizeof(*mask)); } static __always_inline int __cpacf_check_opcode(unsigned int opcode) @@ -370,6 +371,7 @@ static __always_inline int cpacf_query_func(unsigned int opcode, static __always_inline void __cpacf_qai(unsigned int opcode, cpacf_qai_t *qai) { __cpacf_query_insn(opcode, qai, CPACF_FC_QUERY_AUTH_INFO); + kmsan_unpoison_memory(qai, sizeof(*qai)); } /** @@ -422,6 +424,7 @@ static inline int cpacf_km(unsigned long func, void *param, [opc] "i" (CPACF_KM) : "cc", "memory", "0", "1"); + kmsan_unpoison_memory(dest, src_len - s.odd); return src_len - s.odd; } @@ -454,6 +457,7 @@ static inline int cpacf_kmc(unsigned long func, void *param, [opc] "i" (CPACF_KMC) : "cc", "memory", "0", "1"); + kmsan_unpoison_memory(dest, src_len - s.odd); return src_len - s.odd; } @@ -587,6 +591,7 @@ static inline int cpacf_kmctr(unsigned long func, void *param, u8 *dest, [opc] "i" (CPACF_KMCTR) : "cc", "memory", "0", "1"); + kmsan_unpoison_memory(dest, src_len - s.odd); return src_len - s.odd; } @@ -619,6 +624,7 @@ static inline void cpacf_prno(unsigned long func, void *param, : [fc] "d" (func), [pba] "d" ((unsigned long)param), [seed] "d" (s.pair), [opc] "i" (CPACF_PRNO) : "cc", "memory", "0", "1"); + kmsan_unpoison_memory(dest, dest_len); } /** diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index be8369115f6d..9434c76c25b8 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -46,7 +46,6 @@ struct pcpu { unsigned long ec_mask; /* bit mask for ec_xxx functions */ unsigned long ec_clk; /* sigp timestamp for ec_xxx */ unsigned long flags; /* per CPU flags */ - unsigned long capacity; /* cpu capacity for scheduler */ signed char state; /* physical cpu state */ signed char polarization; /* physical polarization */ u16 address; /* physical cpu address */ diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h index fb2bdbf35da5..a6c621e0491c 100644 --- a/arch/s390/include/asm/smp.h +++ b/arch/s390/include/asm/smp.h @@ -30,7 +30,7 @@ static __always_inline unsigned int raw_smp_processor_id(void) return cpu; } -#define arch_scale_cpu_capacity smp_cpu_get_capacity +#define arch_scale_cpu_capacity topology_get_cpu_scale extern struct mutex smp_cpu_state_mutex; extern unsigned int smp_cpu_mt_shift; @@ -53,9 +53,7 @@ extern void smp_save_dump_secondary_cpus(void); extern void smp_yield_cpu(int cpu); extern void smp_cpu_set_polarization(int cpu, int val); extern int smp_cpu_get_polarization(int cpu); -extern void smp_cpu_set_capacity(int cpu, unsigned long val); extern void smp_set_core_capacity(int cpu, unsigned long val); -extern unsigned long smp_cpu_get_capacity(int cpu); extern int smp_cpu_get_cpu_address(int cpu); extern void smp_fill_possible_mask(void); extern void smp_detect_cpus(void); diff --git a/arch/s390/kernel/diag/diag324.c b/arch/s390/kernel/diag/diag324.c index fe325c2a2d0d..3eec0cc8fb9e 100644 --- a/arch/s390/kernel/diag/diag324.c +++ b/arch/s390/kernel/diag/diag324.c @@ -182,8 +182,7 @@ long diag324_pibbuf(unsigned long arg) goto out; rc = copy_to_user((void __user *)address, data->pib, data->pib->len); rc |= put_user(data->sequence, &udata->sequence); - if (rc) - rc = -EFAULT; + rc = rc ? -EFAULT : data->rc; out: mutex_unlock(&pibmutex); return rc; diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index d74ef30155aa..b1e798f8e1dd 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -1157,6 +1157,8 @@ static struct attribute_group reipl_nss_attr_group = { void set_os_info_reipl_block(void) { + if (!reipl_block_actual) + return; os_info_entry_add_data(OS_INFO_REIPL_BLOCK, reipl_block_actual, reipl_block_actual->hdr.len); } @@ -1927,7 +1929,8 @@ static struct shutdown_action __refdata dump_action = { static void dump_reipl_run(struct shutdown_trigger *trigger) { struct lowcore *abs_lc; - unsigned int csum; + unsigned long ipib = 0; + unsigned int csum = 0; /* * Set REIPL_CLEAR flag in os_info flags entry indicating @@ -1943,9 +1946,12 @@ static void dump_reipl_run(struct shutdown_trigger *trigger) reipl_type == IPL_TYPE_UNKNOWN) os_info_flags |= OS_INFO_FLAG_REIPL_CLEAR; os_info_entry_add_data(OS_INFO_FLAGS_ENTRY, &os_info_flags, sizeof(os_info_flags)); - csum = (__force unsigned int)cksm(reipl_block_actual, reipl_block_actual->hdr.len, 0); + if (reipl_block_actual) { + ipib = __pa(reipl_block_actual); + csum = (__force unsigned int)cksm(reipl_block_actual, reipl_block_actual->hdr.len, 0); + } abs_lc = get_abs_lowcore(); - abs_lc->ipib = __pa(reipl_block_actual); + abs_lc->ipib = ipib; abs_lc->ipib_checksum = csum; put_abs_lowcore(abs_lc); dump_run(trigger); diff --git a/arch/s390/kernel/perf_pai.c b/arch/s390/kernel/perf_pai.c index cdb8006220ca..5c18c8b82ab7 100644 --- a/arch/s390/kernel/perf_pai.c +++ b/arch/s390/kernel/perf_pai.c @@ -464,6 +464,7 @@ static void pai_start(struct perf_event *event, int flags, cpump->event = event; } } + event->hw.state &= ~PERF_HES_STOPPED; } static void paicrypt_start(struct perf_event *event, int flags) @@ -510,6 +511,13 @@ static void pai_stop(struct perf_event *event, int flags) struct pai_mapptr *mp = this_cpu_ptr(pai_root[idx].mapptr); struct pai_map *cpump = mp->mapptr; + /* Cope with multiple invocations: + * 1. perf_event_throttle() --> PMU->stop() + * 2. task schedules out --> PMU->stop() + * Check for event already stopped. + */ + if (event->hw.state & PERF_HES_STOPPED) + return; if (!event->attr.sample_period) { /* Counting */ pai_pmu[idx].pmu->read(event); } else { /* Sampling */ @@ -672,9 +680,9 @@ static void pai_have_samples(int idx) { struct pai_mapptr *mp = this_cpu_ptr(pai_root[idx].mapptr); struct pai_map *cpump = mp->mapptr; - struct perf_event *event; + struct perf_event *event, *e2; - list_for_each_entry(event, &cpump->syswide_list, hw.tp_list) + list_for_each_entry_safe(event, e2, &cpump->syswide_list, hw.tp_list) pai_have_sample(event, cpump); } @@ -691,6 +699,17 @@ static void paicrypt_sched_task(struct perf_event_pmu_context *pmu_ctx, pai_have_samples(PAI_PMU_CRYPTO); } +/* Prevent ioctl(fd, PERF_EVENT_IOC_PERIOD, ...) call. + * It sets perf_event::event_limit to a positive value and causes + * perf_event_overflow() to invoke pai_stop() call back function when + * perf_event::event_limit hits zero. This is not supported because the + * sample events CRYPTO_ALL and NNPA_ALL are always taken at schedule out + * of a task. + */ +static int pai_check_period(struct perf_event *event, u64 value) +{ + return -EINVAL; +} /* ============================= paiext ====================================*/ static void paiext_event_destroy(struct perf_event *event) @@ -804,6 +823,7 @@ static struct pmu paicrypt = { .stop = paicrypt_stop, .read = paicrypt_read, .sched_task = paicrypt_sched_task, + .check_period = pai_check_period, .attr_groups = paicrypt_attr_groups }; @@ -1015,6 +1035,7 @@ static struct pmu paiext = { .stop = paiext_stop, .read = paiext_read, .sched_task = paiext_sched_task, + .check_period = pai_check_period, .attr_groups = paiext_attr_groups, }; @@ -1221,7 +1242,7 @@ static int __init paipmu_setup(void) static int __init pai_init(void) { /* Setup s390dbf facility */ - paidbg = debug_register("pai", 32, 256, 128); + paidbg = debug_register("pai", 1, 1, 128); if (!paidbg) { pr_err("Registration of s390dbf pai failed\n"); return -ENOMEM; diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 167c72803ccf..32499cad86f0 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -659,23 +659,13 @@ int smp_cpu_get_polarization(int cpu) return per_cpu(pcpu_devices, cpu).polarization; } -void smp_cpu_set_capacity(int cpu, unsigned long val) -{ - per_cpu(pcpu_devices, cpu).capacity = val; -} - -unsigned long smp_cpu_get_capacity(int cpu) -{ - return per_cpu(pcpu_devices, cpu).capacity; -} - void smp_set_core_capacity(int cpu, unsigned long val) { int i; cpu = smp_get_base_cpu(cpu); for (i = cpu; (i <= cpu + smp_cpu_mtid) && (i < nr_cpu_ids); i++) - smp_cpu_set_capacity(i, val); + topology_set_cpu_scale(i, val); } int smp_cpu_get_cpu_address(int cpu) @@ -727,7 +717,7 @@ static int smp_add_core(struct sclp_core_entry *core, cpumask_t *avail, else pcpu->state = CPU_STATE_STANDBY; smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN); - smp_cpu_set_capacity(cpu, CPU_CAPACITY_HIGH); + topology_set_cpu_scale(cpu, CPU_CAPACITY_HIGH); set_cpu_present(cpu, true); if (!early && arch_register_cpu(cpu)) set_cpu_present(cpu, false); @@ -967,7 +957,7 @@ void __init smp_prepare_boot_cpu(void) ipl_pcpu->state = CPU_STATE_CONFIGURED; lc->pcpu = (unsigned long)ipl_pcpu; smp_cpu_set_polarization(0, POLARIZATION_UNKNOWN); - smp_cpu_set_capacity(0, CPU_CAPACITY_HIGH); + topology_set_cpu_scale(0, CPU_CAPACITY_HIGH); } void __init smp_setup_processor_id(void) diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index 1377c6f3f670..42fc0294f543 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -147,7 +147,7 @@ static void add_cpus_to_mask(struct topology_core *tl_core, cpumask_set_cpu(cpu, &book->mask); cpumask_set_cpu(cpu, &socket->mask); smp_cpu_set_polarization(cpu, tl_core->pp); - smp_cpu_set_capacity(cpu, CPU_CAPACITY_HIGH); + topology_set_cpu_scale(cpu, CPU_CAPACITY_HIGH); } } } diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index d804e1140c2e..efcbf406f03e 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -32,7 +32,7 @@ static atomic64_t virt_timer_elapsed; DEFINE_PER_CPU(u64, mt_cycles[8]); static DEFINE_PER_CPU(u64, mt_scaling_mult) = { 1 }; static DEFINE_PER_CPU(u64, mt_scaling_div) = { 1 }; -static DEFINE_PER_CPU(u64, mt_scaling_jiffies); +static DEFINE_PER_CPU(unsigned long, mt_scaling_jiffies); static inline void set_vtimer(u64 expires) { @@ -81,7 +81,7 @@ static void update_mt_scaling(void) memcpy(cycles_old, cycles_new, sizeof(u64) * (smp_cpu_mtid + 1)); } - __this_cpu_write(mt_scaling_jiffies, jiffies_64); + __this_cpu_write(mt_scaling_jiffies, jiffies); } static inline u64 update_tsk_timer(unsigned long *tsk_vtime, u64 new) @@ -144,7 +144,7 @@ static int do_account_vtime(struct task_struct *tsk) lc->system_timer += timer; /* Update MT utilization calculation */ - if (smp_cpu_mtid && time_after64(jiffies_64, __this_cpu_read(mt_scaling_jiffies))) + if (smp_cpu_mtid && time_after(jiffies, __this_cpu_read(mt_scaling_jiffies))) update_mt_scaling(); /* Calculate cputime delta */ diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index 9610770fcf6d..4b160eedc5a0 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -55,63 +55,46 @@ static void __crst_table_upgrade(void *arg) int crst_table_upgrade(struct mm_struct *mm, unsigned long end) { - unsigned long *pgd = NULL, *p4d = NULL, *__pgd; - unsigned long asce_limit = mm->context.asce_limit; + unsigned long *table, *pgd; + int rc, notify; mmap_assert_write_locked(mm); - /* upgrade should only happen from 3 to 4, 3 to 5, or 4 to 5 levels */ - VM_BUG_ON(asce_limit < _REGION2_SIZE); - - if (end <= asce_limit) - return 0; - - if (asce_limit == _REGION2_SIZE) { - p4d = crst_table_alloc(mm); - if (unlikely(!p4d)) - goto err_p4d; - crst_table_init(p4d, _REGION2_ENTRY_EMPTY); - pagetable_p4d_ctor(virt_to_ptdesc(p4d)); - } - if (end > _REGION1_SIZE) { - pgd = crst_table_alloc(mm); - if (unlikely(!pgd)) - goto err_pgd; - crst_table_init(pgd, _REGION1_ENTRY_EMPTY); - pagetable_pgd_ctor(virt_to_ptdesc(pgd)); - } - - spin_lock_bh(&mm->page_table_lock); - - if (p4d) { - __pgd = (unsigned long *) mm->pgd; - p4d_populate(mm, (p4d_t *) p4d, (pud_t *) __pgd); - mm->pgd = (pgd_t *) p4d; - mm->context.asce_limit = _REGION1_SIZE; - mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | - _ASCE_USER_BITS | _ASCE_TYPE_REGION2; - mm_inc_nr_puds(mm); - } - if (pgd) { - __pgd = (unsigned long *) mm->pgd; - pgd_populate(mm, (pgd_t *) pgd, (p4d_t *) __pgd); - mm->pgd = (pgd_t *) pgd; - mm->context.asce_limit = TASK_SIZE_MAX; - mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | - _ASCE_USER_BITS | _ASCE_TYPE_REGION1; + VM_BUG_ON(mm->context.asce_limit < _REGION2_SIZE); + rc = 0; + notify = 0; + while (mm->context.asce_limit < end) { + table = crst_table_alloc(mm); + if (!table) { + rc = -ENOMEM; + break; + } + spin_lock_bh(&mm->page_table_lock); + pgd = (unsigned long *)mm->pgd; + if (mm->context.asce_limit == _REGION2_SIZE) { + crst_table_init(table, _REGION2_ENTRY_EMPTY); + p4d_populate(mm, (p4d_t *)table, (pud_t *)pgd); + pagetable_p4d_ctor(virt_to_ptdesc(table)); + mm->pgd = (pgd_t *)table; + mm->context.asce_limit = _REGION1_SIZE; + mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_REGION2; + mm_inc_nr_puds(mm); + } else { + crst_table_init(table, _REGION1_ENTRY_EMPTY); + pgd_populate(mm, (pgd_t *)table, (p4d_t *)pgd); + pagetable_pgd_ctor(virt_to_ptdesc(table)); + mm->pgd = (pgd_t *)table; + mm->context.asce_limit = TASK_SIZE_MAX; + mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_REGION1; + } + notify = 1; + spin_unlock_bh(&mm->page_table_lock); } - - spin_unlock_bh(&mm->page_table_lock); - - on_each_cpu(__crst_table_upgrade, mm, 0); - - return 0; - -err_pgd: - pagetable_dtor(virt_to_ptdesc(p4d)); - crst_table_free(mm, p4d); -err_p4d: - return -ENOMEM; + if (notify) + on_each_cpu(__crst_table_upgrade, mm, 0); + return rc; } unsigned long *page_table_alloc_noprof(struct mm_struct *mm) diff --git a/arch/s390/pci/pci_sysfs.c b/arch/s390/pci/pci_sysfs.c index d98d97df792a..bbb76113a4d0 100644 --- a/arch/s390/pci/pci_sysfs.c +++ b/arch/s390/pci/pci_sysfs.c @@ -153,6 +153,9 @@ static ssize_t report_error_write(struct file *filp, struct kobject *kobj, if (off || (count < sizeof(*report))) return -EINVAL; + if (count < (report->length + sizeof(*report))) + return -EINVAL; + ret = sclp_pci_report(report, zdev->fh, zdev->fid); return ret ? ret : count; diff --git a/block/bio.c b/block/bio.c index 898b2f5ef8c8..f95b63c0604a 100644 --- a/block/bio.c +++ b/block/bio.c @@ -859,6 +859,7 @@ static int __bio_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp) bio->bi_ioprio = bio_src->bi_ioprio; bio->bi_write_hint = bio_src->bi_write_hint; bio->bi_write_stream = bio_src->bi_write_stream; + bio->bi_bvec_gap_bit = bio_src->bi_bvec_gap_bit; bio->bi_iter = bio_src->bi_iter; bio->bi_io_vec = bio_src->bi_io_vec; @@ -1972,6 +1973,14 @@ struct bio *bio_split(struct bio *bio, int sectors, bio_advance(bio, split->bi_iter.bi_size); + /* + * The gap bit is set when splitting to limits and only applies to the + * front bio that was split off. The remaining bio will calcualte its + * gap value when it is subsequently split to limits, so it is safe to + * re-initialize the value back to 0. + */ + bio->bi_bvec_gap_bit = 0; + if (bio_flagged(bio, BIO_TRACE_COMPLETION)) bio_set_flag(split, BIO_TRACE_COMPLETION); diff --git a/block/genhd.c b/block/genhd.c index f1990c7cdfb9..10ca8b4d6eea 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -448,6 +448,13 @@ static int __add_disk(struct device *parent, struct gendisk *disk, } /* + * We do not support partitions with zoned block devices, so do not try + * to scan the partitions table. + */ + if (blk_queue_is_zoned(disk->queue)) + disk->flags |= GENHD_FL_NO_PART; + + /* * If the driver provides an explicit major number it also must provide * the number of minors numbers supported, and those will be used to * setup the gendisk. diff --git a/drivers/accel/amdxdna/aie2_message.c b/drivers/accel/amdxdna/aie2_message.c index dfe0fbdf066d..b4c49259a1a2 100644 --- a/drivers/accel/amdxdna/aie2_message.c +++ b/drivers/accel/amdxdna/aie2_message.c @@ -994,7 +994,7 @@ int aie2_cmdlist_multi_execbuf(struct amdxdna_hwctx *hwctx, } ccnt = payload->command_count; - if (payload_len < struct_size(payload, data, ccnt)) { + if (!ccnt || payload_len < struct_size(payload, data, ccnt)) { XDNA_DBG(xdna, "Invalid command count %d", ccnt); return -EINVAL; } diff --git a/drivers/accel/amdxdna/amdxdna_ctx.c b/drivers/accel/amdxdna/amdxdna_ctx.c index 31a414c3f0d9..888e857ec558 100644 --- a/drivers/accel/amdxdna/amdxdna_ctx.c +++ b/drivers/accel/amdxdna/amdxdna_ctx.c @@ -183,8 +183,10 @@ int amdxdna_cmd_set_error(struct amdxdna_gem_obj *abo, if (!abo) return -EINVAL; cmd = amdxdna_gem_vmap(abo); - if (!cmd) + if (!cmd) { + amdxdna_gem_put_obj(abo); return -ENOMEM; + } } memset(cmd->data, 0xff, abo->mem.size - sizeof(*cmd)); diff --git a/drivers/accel/amdxdna/amdxdna_ctx.h b/drivers/accel/amdxdna/amdxdna_ctx.h index b6bef3af7dab..6e78bab8a02c 100644 --- a/drivers/accel/amdxdna/amdxdna_ctx.h +++ b/drivers/accel/amdxdna/amdxdna_ctx.h @@ -55,7 +55,7 @@ struct amdxdna_cmd_chain { u32 submit_index; u32 error_index; u32 reserved[3]; - u64 data[] __counted_by(command_count); + u64 data[]; }; /* diff --git a/drivers/accel/amdxdna/amdxdna_gem.c b/drivers/accel/amdxdna/amdxdna_gem.c index b01f5d95fac8..4b0d58d0329b 100644 --- a/drivers/accel/amdxdna/amdxdna_gem.c +++ b/drivers/accel/amdxdna/amdxdna_gem.c @@ -1246,6 +1246,9 @@ static int amdxdna_flush_bo(struct amdxdna_gem_obj *abo, u64 offset, u64 size) { u64 end; + if (is_import_bo(abo)) + return -EOPNOTSUPP; + if (offset >= abo->mem.size) return -EINVAL; @@ -1253,9 +1256,10 @@ static int amdxdna_flush_bo(struct amdxdna_gem_obj *abo, u64 offset, u64 size) return -EINVAL; size = min(abo->mem.size, end) - offset; - if (is_import_bo(abo)) - drm_clflush_sg(abo->base.sgt); - else if (amdxdna_gem_vmap(abo)) + if (!size) + return 0; + + if (amdxdna_gem_vmap(abo)) drm_clflush_virt_range(amdxdna_gem_vmap(abo) + offset, size); else if (abo->base.pages) drm_clflush_pages(abo->base.pages, abo->mem.size >> PAGE_SHIFT); diff --git a/drivers/accel/ethosu/ethosu_drv.c b/drivers/accel/ethosu/ethosu_drv.c index d121fb0d7732..1cf284e7f300 100644 --- a/drivers/accel/ethosu/ethosu_drv.c +++ b/drivers/accel/ethosu/ethosu_drv.c @@ -356,6 +356,8 @@ static int ethosu_probe(struct platform_device *pdev) dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(40)); ethosudev->regs = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(ethosudev->regs)) + return PTR_ERR(ethosudev->regs); ethosudev->pmu_regs = ethosudev->regs; ethosudev->num_clks = devm_clk_bulk_get_all(&pdev->dev, ðosudev->clks); diff --git a/drivers/accel/ethosu/ethosu_gem.c b/drivers/accel/ethosu/ethosu_gem.c index d50fed64d4d9..fa37a190e9ff 100644 --- a/drivers/accel/ethosu/ethosu_gem.c +++ b/drivers/accel/ethosu/ethosu_gem.c @@ -204,7 +204,7 @@ static u64 feat_matrix_length(struct ethosu_device *edev, struct feat_matrix *fm, u32 x, u32 y, u32 c, bool ofm) { - u32 element_size, storage = fm->precision >> 14; + u32 element_size, storage = ethosu_is_u65(edev) ? 0 : fm->precision >> 14; int tile = 0; u64 addr; diff --git a/drivers/accel/ethosu/ethosu_job.c b/drivers/accel/ethosu/ethosu_job.c index 6a038c0384cc..4ced44a65f23 100644 --- a/drivers/accel/ethosu/ethosu_job.c +++ b/drivers/accel/ethosu/ethosu_job.c @@ -154,6 +154,13 @@ static void ethosu_job_err_cleanup(struct ethosu_job *job) drm_gem_object_put(job->cmd_bo); + if (job->done_fence) { + if (dma_fence_was_initialized(job->done_fence)) + dma_fence_put(job->done_fence); + else + dma_fence_free(job->done_fence); + } + kfree(job); } @@ -164,7 +171,6 @@ static void ethosu_job_cleanup(struct kref *ref) pm_runtime_put_autosuspend(job->dev->base.dev); - dma_fence_put(job->done_fence); dma_fence_put(job->inference_done_fence); ethosu_job_err_cleanup(job); @@ -415,7 +421,7 @@ static int ethosu_ioctl_submit_job(struct drm_device *dev, struct drm_file *file ejob->done_fence = kzalloc_obj(*ejob->done_fence); if (!ejob->done_fence) { ret = -ENOMEM; - goto out_cleanup_job; + goto out_put_job; } ret = drm_sched_job_init(&ejob->base, diff --git a/drivers/accel/qaic/qaic_control.c b/drivers/accel/qaic/qaic_control.c index 50bf3340e49c..2ccc55486aac 100644 --- a/drivers/accel/qaic/qaic_control.c +++ b/drivers/accel/qaic/qaic_control.c @@ -963,11 +963,13 @@ static int decode_status(struct qaic_device *qdev, void *trans, struct manage_ms static int decode_message(struct qaic_device *qdev, struct manage_msg *user_msg, struct wire_msg *msg, struct ioctl_resources *resources, - struct qaic_user *usr) + struct qaic_user *usr, bool orphaned_deactivate) { + u32 msg_hdr_count = le32_to_cpu(msg->hdr.count); u32 msg_hdr_len = le32_to_cpu(msg->hdr.len); struct wire_trans_hdr *trans_hdr; u32 msg_len = 0; + int trans_type; int ret; int i; @@ -975,10 +977,12 @@ static int decode_message(struct qaic_device *qdev, struct manage_msg *user_msg, msg_hdr_len > QAIC_MANAGE_MAX_MSG_LENGTH) return -EINVAL; - user_msg->len = 0; - user_msg->count = le32_to_cpu(msg->hdr.count); + if (user_msg) { + user_msg->len = 0; + user_msg->count = msg_hdr_count; + } - for (i = 0; i < user_msg->count; ++i) { + for (i = 0; i < msg_hdr_count; ++i) { u32 hdr_len; if (msg_len > msg_hdr_len - sizeof(*trans_hdr)) @@ -990,7 +994,20 @@ static int decode_message(struct qaic_device *qdev, struct manage_msg *user_msg, size_add(msg_len, hdr_len) > msg_hdr_len) return -EINVAL; - switch (le32_to_cpu(trans_hdr->type)) { + trans_type = le32_to_cpu(trans_hdr->type); + /* + * orphaned_deactivate is the case where a deactivate response + * is received from the device after the user owning the DBC, + * and the message requesting deactivation, has gone away. + * In this case, only process QAIC_TRANS_DEACTIVATE_FROM_DEV + * transaction and skip the others. + */ + if (orphaned_deactivate && trans_type != QAIC_TRANS_DEACTIVATE_FROM_DEV) { + msg_len += hdr_len; + continue; + } + + switch (trans_type) { case QAIC_TRANS_PASSTHROUGH_FROM_DEV: ret = decode_passthrough(qdev, trans_hdr, user_msg, &msg_len); break; @@ -1281,7 +1298,7 @@ dma_xfer_continue: goto dma_cont_failed; } - ret = decode_message(qdev, user_msg, rsp, &resources, usr); + ret = decode_message(qdev, user_msg, rsp, &resources, usr, false); dma_cont_failed: free_dbc_buf(qdev, &resources); @@ -1446,22 +1463,7 @@ static void resp_worker(struct work_struct *work) * response to the QAIC_TRANS_TERMINATE_TO_DEV transaction, * otherwise, the user can issue an soc_reset to the device. */ - u32 msg_count = le32_to_cpu(msg->hdr.count); - u32 msg_len = le32_to_cpu(msg->hdr.len); - u32 len = 0; - int j; - - for (j = 0; j < msg_count && len < msg_len; ++j) { - struct wire_trans_hdr *trans_hdr; - - trans_hdr = (struct wire_trans_hdr *)(msg->data + len); - if (le32_to_cpu(trans_hdr->type) == QAIC_TRANS_DEACTIVATE_FROM_DEV) { - if (decode_deactivate(qdev, trans_hdr, &len, NULL)) - len += le32_to_cpu(trans_hdr->len); - } else { - len += le32_to_cpu(trans_hdr->len); - } - } + decode_message(qdev, NULL, msg, NULL, NULL, true); /* request must have timed out, drop packet */ kfree(msg); } diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index f48715ed827c..163a3cccf197 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -28,9 +28,7 @@ #include "internal.h" #include "sleep.h" -#define ACPI_BUS_CLASS "system_bus" #define ACPI_BUS_HID "LNXSYBUS" -#define ACPI_BUS_DEVICE_NAME "System Bus" #define INVALID_ACPI_HANDLE ((acpi_handle)ZERO_PAGE(0)) @@ -1450,8 +1448,6 @@ static void acpi_set_pnp_ids(acpi_handle handle, struct acpi_device_pnp *pnp, acpi_object_is_system_bus(handle)) { /* \_SB, \_TZ, LNXSYBUS */ acpi_add_id(pnp, ACPI_BUS_HID); - strscpy(pnp->device_name, ACPI_BUS_DEVICE_NAME); - strscpy(pnp->device_class, ACPI_BUS_CLASS); } break; diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 58f512f8952a..9b8c0935001c 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -2614,6 +2614,51 @@ static irqreturn_t ahci_thunderx_irq_handler(int irq, void *dev_instance) } #endif +/* + * The Marvell 88SE6111/6121/6145 ("Thor") family stops reporting interrupts + * for a port when HOST_IRQ_STAT is cleared while PxIS still holds bits: PxIS + * keeps its content, HOST_IRQ_STAT reads back as 0, the port is never looked + * at again and the command in flight only ends in a timeout. On a 88SE6121 + * this makes every SATA-2 or SATA-3 disk fail to IDENTIFY, while SATA-1 disks + * happen to win the race often enough to work. + * + * Clearing the host status before servicing the ports avoids it. Marvell's + * own driver for these chips does the same and says so ("clear global before + * channel"), and ahci_xgene handles its broken edge latch the same way. The + * price is at most one spurious interrupt per valid one, which is why this is + * not the generic behaviour - see AHCI 1.1 section 10.6.2. + * + * Link: https://bugzilla.kernel.org/show_bug.cgi?id=216094 + */ +static irqreturn_t ahci_mv_irq_handler(int irq, void *dev_instance) +{ + struct ata_host *host = dev_instance; + struct ahci_host_priv *hpriv = host->private_data; + void __iomem *mmio = hpriv->mmio; + unsigned int rc; + u32 irq_stat, irq_masked; + + irq_stat = readl(mmio + HOST_IRQ_STAT); + if (!irq_stat) + return IRQ_NONE; + + irq_masked = irq_stat & hpriv->port_map; + + spin_lock(&host->lock); + + /* + * Use the unmasked value to clear the interrupt, as a spurious pending + * event on a dummy port might cause a screaming IRQ. + */ + writel(irq_stat, mmio + HOST_IRQ_STAT); + + rc = ahci_handle_port_intr(host, irq_masked); + + spin_unlock(&host->lock); + + return IRQ_RETVAL(rc); +} + static void ahci_remap_check(struct pci_dev *pdev, int bar, struct ahci_host_priv *hpriv) { @@ -2917,6 +2962,10 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) return -ENOMEM; hpriv->flags |= (unsigned long)pi.private_data; + /* the Marvell "Thor" family needs HOST_IRQ_STAT cleared first */ + if (board_id == board_ahci_mv) + hpriv->irq_handler = ahci_mv_irq_handler; + /* MCP65 revision A1 and A2 can't do MSI */ if (board_id == board_ahci_mcp65 && (pdev->revision == 0xa1 || pdev->revision == 0xa2)) diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index a7d667cfcfec..b3666519b648 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -4823,28 +4823,6 @@ ata_scsi_get_phys_element_status_xlat(struct ata_queued_cmd *qc) return 0; } -static void ata_scsi_depop_ua_cap_changed_complete(struct ata_queued_cmd *qc) -{ - struct scsi_cmnd *scmd = qc->scsicmd; - u8 *cdb = scmd->cmnd; - bool is_ata_passthru = cdb[0] == ATA_16 || cdb[0] == ATA_12; - bool is_success = qc->err_mask == 0; - - /* - * For successful non-passthrough commands, raise a UNIT ATTENTION with - * the additional sense code set to CAPACITY DATA HAS CHANGED to be - * raised. Note that this should be done only if the capacity has - * actually changed, which may not be the case if the element that was - * specified for depopulation was already depopulated, or we did not - * restore any removed element. But a capacity change unit attention is - * harmless, so always raise the unit attention. - */ - if (is_success && !is_ata_passthru) - ata_scsi_set_sense(qc->dev, scmd, UNIT_ATTENTION, - UA_CHANGED_ASC, CAPACITY_CHANGED_ASCQ); - ata_scsi_qc_complete(qc); -} - static unsigned int ata_scsi_remove_element_and_truncate_xlat(struct ata_queued_cmd *qc) { @@ -4884,7 +4862,6 @@ ata_scsi_remove_element_and_truncate_xlat(struct ata_queued_cmd *qc) tf->flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE | ATA_TFLAG_LBA48; qc->flags |= ATA_QCFLAG_RESULT_TF; - qc->complete_fn = ata_scsi_depop_ua_cap_changed_complete; return 0; } @@ -4937,7 +4914,6 @@ ata_scsi_restore_elements_and_rebuild_xlat(struct ata_queued_cmd *qc) tf->flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE | ATA_TFLAG_LBA48; qc->flags |= ATA_QCFLAG_RESULT_TF; - qc->complete_fn = ata_scsi_depop_ua_cap_changed_complete; return 0; } diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 6f12976035b0..758c20678bf6 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -458,12 +458,14 @@ static void loop_update_dio_alignment(struct loop_device *lo) * Use the dio alignment of the file system if provided. The incomoing * request's bio_vec is forwarded to the backing file unchanged, so its * required memory alignment becomes the device's dma_alignment when - * used for direct-io. + * used for direct-io. The file system reports zeroed alignments if the + * file can't be used for direct-io at all, so fall back to the block + * device limits in that case. */ if (!vfs_getattr(&file->f_path, &st, STATX_DIOALIGN, 0) && - (st.result_mask & STATX_DIOALIGN)) { + (st.result_mask & STATX_DIOALIGN) && st.dio_mem_align) { lo->lo_min_dio_size = st.dio_offset_align; - lo->lo_dio_mem_align = st.dio_mem_align - 1; + lo->lo_dio_mem_align = min(st.dio_mem_align - 1, PAGE_SIZE - 1); return; } diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 6c5bec7da97c..e5ba07d8d281 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -2653,6 +2653,12 @@ static int ublk_ch_mmap(struct file *filp, struct vm_area_struct *vma) if (vma->vm_flags & VM_WRITE) return -EPERM; + /* + * The per-queue command buffer is kernel-written ABI; prevent + * the daemon from upgrading to writable via mprotect(). + */ + vm_flags_clear(vma, VM_MAYWRITE); + end = UBLKSRV_CMD_BUF_OFFSET + ub->dev_info.nr_hw_queues * max_sz; if (phys_off < UBLKSRV_CMD_BUF_OFFSET || phys_off >= end) return -EINVAL; diff --git a/drivers/block/zloop.c b/drivers/block/zloop.c index 4323ac108cae..f0ca221524db 100644 --- a/drivers/block/zloop.c +++ b/drivers/block/zloop.c @@ -1042,12 +1042,14 @@ static int zloop_get_block_size(struct zloop_device *zlo, * Use the dio alignment of the file system if provided. The incoming * request's bio_vec is forwarded to the backing file unchanged, so its * required memory alignment becomes the device's dma_alignment when - * used for direct-io. + * used for direct-io. The file system reports zeroed alignments if the + * file can't be used for direct-io at all, so fall back to the block + * device limits in that case. */ if (!vfs_getattr(&zone->file->f_path, &st, STATX_DIOALIGN, 0) && - (st.result_mask & STATX_DIOALIGN)) { + (st.result_mask & STATX_DIOALIGN) && st.dio_mem_align) { zlo->block_size = st.dio_offset_align; - zlo->dio_mem_align = st.dio_mem_align - 1; + zlo->dio_mem_align = min(st.dio_mem_align - 1, PAGE_SIZE - 1); } else if (sb_bdev) { zlo->block_size = bdev_physical_block_size(sb_bdev); zlo->dio_mem_align = bdev_dma_alignment(sb_bdev); diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index bcb2514b7bc0..909a265fd906 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -571,12 +571,44 @@ int btintel_version_info_tlv(struct hci_dev *hdev, } EXPORT_SYMBOL_GPL(btintel_version_info_tlv); +static u8 btintel_version_tlv_min_len(u8 type) +{ + switch (type) { + case INTEL_TLV_CNVI_TOP: + case INTEL_TLV_CNVR_TOP: + case INTEL_TLV_CNVI_BT: + case INTEL_TLV_CNVR_BT: + case INTEL_TLV_BUILD_NUM: + case INTEL_TLV_GIT_SHA1: + return sizeof(u32); + case INTEL_TLV_DEV_REV_ID: + case INTEL_TLV_TIME_STAMP: + return sizeof(u16); + case INTEL_TLV_IMAGE_TYPE: + case INTEL_TLV_BUILD_TYPE: + case INTEL_TLV_SECURE_BOOT: + case INTEL_TLV_OTP_LOCK: + case INTEL_TLV_API_LOCK: + case INTEL_TLV_DEBUG_LOCK: + case INTEL_TLV_LIMITED_CCE: + case INTEL_TLV_SBE_TYPE: + return sizeof(u8); + case INTEL_TLV_MIN_FW: + return 3; + case INTEL_TLV_OTP_BDADDR: + return sizeof(bdaddr_t); + default: + return 0; + } +} + int btintel_parse_version_tlv(struct hci_dev *hdev, struct intel_version_tlv *version, struct sk_buff *skb) { /* Consume Command Complete Status field */ - skb_pull(skb, 1); + if (!skb_pull(skb, 1)) + return -EINVAL; /* Event parameters contain multiple TLVs. Read each of them * and only keep the required data. Also, it use existing legacy @@ -596,6 +628,9 @@ int btintel_parse_version_tlv(struct hci_dev *hdev, if (skb->len < tlv->len + sizeof(*tlv)) return -EINVAL; + if (tlv->len < btintel_version_tlv_min_len(tlv->type)) + return -EINVAL; + switch (tlv->type) { case INTEL_TLV_CNVI_TOP: version->cnvi_top = get_unaligned_le32(tlv->val); @@ -667,7 +702,7 @@ int btintel_parse_version_tlv(struct hci_dev *hdev, break; case INTEL_TLV_FW_ID: snprintf(version->fw_id, sizeof(version->fw_id), - "%s", tlv->val); + "%.*s", tlv->len, tlv->val); break; default: /* Ignore rest of information */ @@ -686,6 +721,7 @@ static int btintel_read_version_tlv(struct hci_dev *hdev, { struct sk_buff *skb; const u8 param[1] = { 0xFF }; + int err; if (!version) return -EINVAL; @@ -704,10 +740,10 @@ static int btintel_read_version_tlv(struct hci_dev *hdev, return -EIO; } - btintel_parse_version_tlv(hdev, version, skb); + err = btintel_parse_version_tlv(hdev, version, skb); kfree_skb(skb); - return 0; + return err; } /* ------- REGMAP IBT SUPPORT ------- */ diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c index 005c77a4f5eb..eec95e5f3dbb 100644 --- a/drivers/bluetooth/btintel_pcie.c +++ b/drivers/bluetooth/btintel_pcie.c @@ -1696,6 +1696,9 @@ static irqreturn_t btintel_pcie_irq_msix_handler(int irq, void *dev_id) if (unlikely(!(intr_fh | intr_hw))) { /* Ignore interrupt, inta == 0 */ + bt_warn_ratelimited("Bluetooth: btintel_pcie: Received spurious interrupt\n"); + btintel_pcie_wr_reg32(data, BTINTEL_PCIE_CSR_MSIX_AUTOMASK_ST, + BIT(entry->entry)); return IRQ_NONE; } diff --git a/drivers/bluetooth/hci_mrvl.c b/drivers/bluetooth/hci_mrvl.c index 516b8f74c434..5798a8db016e 100644 --- a/drivers/bluetooth/hci_mrvl.c +++ b/drivers/bluetooth/hci_mrvl.c @@ -307,9 +307,8 @@ static int mrvl_load_firmware(struct hci_dev *hdev, const char *name) err = wait_on_bit_timeout(&mrvl->flags, STATE_FW_REQ_PENDING, TASK_INTERRUPTIBLE, msecs_to_jiffies(2000)); - if (err == 1) { + if (err == -EINTR) { bt_dev_err(hdev, "Firmware load interrupted"); - err = -EINTR; break; } else if (err) { bt_dev_err(hdev, "Firmware request timeout"); diff --git a/drivers/cpuidle/cpuidle-psci.c b/drivers/cpuidle/cpuidle-psci.c index dcf20ea5ef5e..b250d0dde760 100644 --- a/drivers/cpuidle/cpuidle-psci.c +++ b/drivers/cpuidle/cpuidle-psci.c @@ -16,7 +16,7 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/of.h> -#include <linux/device/faux.h> +#include <linux/platform_device.h> #include <linux/psci.h> #include <linux/pm_domain.h> #include <linux/pm_runtime.h> @@ -428,14 +428,14 @@ deinit: * to register cpuidle driver then rollback to cancel all CPUs * registration. */ -static int psci_cpuidle_probe(struct faux_device *fdev) +static int psci_cpuidle_probe(struct platform_device *pdev) { int cpu, ret; struct cpuidle_driver *drv; struct cpuidle_device *dev; for_each_present_cpu(cpu) { - ret = psci_idle_init_cpu(&fdev->dev, cpu); + ret = psci_idle_init_cpu(&pdev->dev, cpu); if (ret) goto out_fail; } @@ -455,36 +455,26 @@ out_fail: return ret; } -static struct faux_device_ops psci_cpuidle_ops = { +static struct platform_driver psci_cpuidle_driver = { .probe = psci_cpuidle_probe, + .driver = { + .name = "psci-cpuidle", + }, }; -static bool __init dt_idle_state_present(void) -{ - struct device_node *cpu_node __free(device_node) = - of_cpu_device_node_get(cpumask_first(cpu_possible_mask)); - if (!cpu_node) - return false; - - struct device_node *state_node __free(device_node) = - of_get_cpu_state_node(cpu_node, 0); - if (!state_node) - return false; - - return !!of_match_node(psci_idle_state_match, state_node); -} - static int __init psci_idle_init(void) { - struct faux_device *fdev; + struct platform_device *pdev; + int ret; - if (!dt_idle_state_present()) - return 0; + ret = platform_driver_register(&psci_cpuidle_driver); + if (ret) + return ret; - fdev = faux_device_create("psci-cpuidle", NULL, &psci_cpuidle_ops); - if (!fdev) { - pr_err("Failed to create psci-cpuidle device\n"); - return -ENODEV; + pdev = platform_device_register_simple("psci-cpuidle", -1, NULL, 0); + if (IS_ERR(pdev)) { + platform_driver_unregister(&psci_cpuidle_driver); + return PTR_ERR(pdev); } return 0; diff --git a/drivers/cpuidle/dt_idle_genpd.c b/drivers/cpuidle/dt_idle_genpd.c index d292975cc468..ed41a90eeeb7 100644 --- a/drivers/cpuidle/dt_idle_genpd.c +++ b/drivers/cpuidle/dt_idle_genpd.c @@ -99,7 +99,7 @@ struct generic_pm_domain *dt_idle_pd_alloc(struct device_node *np, if (!pd) goto out; - pd->name = kasprintf(GFP_KERNEL, "%pOF", np); + pd->name = kstrdup(kbasename(of_node_full_name(np)), GFP_KERNEL); if (!pd->name) goto free_pd; @@ -112,7 +112,6 @@ struct generic_pm_domain *dt_idle_pd_alloc(struct device_node *np, goto free_name; pd->free_states = pd_free_states; - pd->name = kbasename(pd->name); pd->states = states; pd->state_count = state_count; diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index d504c636dc29..4c9add51f9ef 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -804,6 +804,26 @@ int dma_buf_fd(struct dma_buf *dmabuf, int flags) EXPORT_SYMBOL_NS_GPL(dma_buf_fd, "DMA_BUF"); /** + * dma_buf_fd_install - install a reserved fd for a dma-buf + * @dmabuf: [in] pointer to dma_buf + * @fd: [in] fd reserved with get_unused_fd_flags() + * + * Publishes a previously reserved fd into the caller's fd table. + * Must only be called after all fallible work (e.g. copy_to_user) + * has succeeded, as it cannot be undone safely once called. + * + * The caller is responsible for having emitted the trace event + * (via dma_buf_fd() or get_unused_fd_flags() + this function) + * before calling this. + */ +void dma_buf_fd_install(struct dma_buf *dmabuf, int fd) +{ + DMA_BUF_TRACE(trace_dma_buf_fd, dmabuf, fd); + fd_install(fd, dmabuf->file); +} +EXPORT_SYMBOL_NS_GPL(dma_buf_fd_install, "DMA_BUF"); + +/** * dma_buf_get - returns the struct dma_buf related to an fd * @fd: [in] fd associated with the struct dma_buf to be returned * diff --git a/drivers/dma-buf/dma-heap.c b/drivers/dma-buf/dma-heap.c index 3937dd41bb0f..8a6c2b6e0cc6 100644 --- a/drivers/dma-buf/dma-heap.c +++ b/drivers/dma-buf/dma-heap.c @@ -56,33 +56,6 @@ MODULE_PARM_DESC(mem_accounting, "Enable cgroup-based memory accounting for dma-buf heap allocations (default=false)."); EXPORT_SYMBOL_NS_GPL(mem_accounting, "DMA_BUF_HEAP"); -static int dma_heap_buffer_alloc(struct dma_heap *heap, size_t len, - u32 fd_flags, - u64 heap_flags) -{ - struct dma_buf *dmabuf; - int fd; - - /* - * Allocations from all heaps have to begin - * and end on page boundaries. - */ - len = PAGE_ALIGN(len); - if (!len) - return -EINVAL; - - dmabuf = heap->ops->allocate(heap, len, fd_flags, heap_flags); - if (IS_ERR(dmabuf)) - return PTR_ERR(dmabuf); - - fd = dma_buf_fd(dmabuf, fd_flags); - if (fd < 0) { - dma_buf_put(dmabuf); - /* just return, as put will call release and that will free */ - } - return fd; -} - static int dma_heap_open(struct inode *inode, struct file *file) { struct dma_heap *heap; @@ -100,30 +73,42 @@ static int dma_heap_open(struct inode *inode, struct file *file) return 0; } -static long dma_heap_ioctl_allocate(struct file *file, void *data) +static struct dma_buf *dma_heap_ioctl_allocate(struct file *file, void *data) { struct dma_heap_allocation_data *heap_allocation = data; struct dma_heap *heap = file->private_data; + struct dma_buf *dmabuf; int fd; + size_t len; if (heap_allocation->fd) - return -EINVAL; + return ERR_PTR(-EINVAL); if (heap_allocation->fd_flags & ~DMA_HEAP_VALID_FD_FLAGS) - return -EINVAL; + return ERR_PTR(-EINVAL); if (heap_allocation->heap_flags & ~DMA_HEAP_VALID_HEAP_FLAGS) - return -EINVAL; + return ERR_PTR(-EINVAL); + + len = PAGE_ALIGN(heap_allocation->len); + if (!len) + return ERR_PTR(-EINVAL); + + dmabuf = heap->ops->allocate(heap, len, heap_allocation->fd_flags, + heap_allocation->heap_flags); - fd = dma_heap_buffer_alloc(heap, heap_allocation->len, - heap_allocation->fd_flags, - heap_allocation->heap_flags); - if (fd < 0) - return fd; + if (IS_ERR(dmabuf)) + return dmabuf; + + fd = get_unused_fd_flags(heap_allocation->fd_flags); + if (fd < 0) { + dma_buf_put(dmabuf); + return ERR_PTR(fd); + } heap_allocation->fd = fd; - return 0; + return dmabuf; } static unsigned int dma_heap_ioctl_cmds[] = { @@ -139,6 +124,8 @@ static long dma_heap_ioctl(struct file *file, unsigned int ucmd, unsigned int in_size, out_size, drv_size, ksize; int nr = _IOC_NR(ucmd); int ret = 0; + int fd; + struct dma_buf *dmabuf; if (nr >= ARRAY_SIZE(dma_heap_ioctl_cmds)) return -EINVAL; @@ -175,15 +162,28 @@ static long dma_heap_ioctl(struct file *file, unsigned int ucmd, switch (kcmd) { case DMA_HEAP_IOCTL_ALLOC: - ret = dma_heap_ioctl_allocate(file, kdata); + dmabuf = dma_heap_ioctl_allocate(file, kdata); + + if (IS_ERR(dmabuf)) { + ret = PTR_ERR(dmabuf); + break; + } + + fd = ((struct dma_heap_allocation_data *)kdata)->fd; + if (copy_to_user((void __user *)arg, kdata, out_size) != 0) { + put_unused_fd(fd); + dma_buf_put(dmabuf); + ret = -EFAULT; + } else { + dma_buf_fd_install(dmabuf, fd); + } + break; default: ret = -ENOTTY; goto err; } - if (copy_to_user((void __user *)arg, kdata, out_size) != 0) - ret = -EFAULT; err: if (kdata != stack_kdata) kfree(kdata); diff --git a/drivers/edac/al_mc_edac.c b/drivers/edac/al_mc_edac.c index 178b9e581a72..bf6921d8890b 100644 --- a/drivers/edac/al_mc_edac.c +++ b/drivers/edac/al_mc_edac.c @@ -302,12 +302,8 @@ static int al_mc_edac_probe(struct platform_device *pdev) IRQF_SHARED, pdev->name, pdev); - if (ret != 0) { - dev_err(&pdev->dev, - "failed to request UE IRQ %d (%d)\n", - al_mc->irq_ue, ret); + if (ret != 0) return ret; - } } if (al_mc->irq_ce > 0) { @@ -317,12 +313,8 @@ static int al_mc_edac_probe(struct platform_device *pdev) IRQF_SHARED, pdev->name, pdev); - if (ret != 0) { - dev_err(&pdev->dev, - "failed to request CE IRQ %d (%d)\n", - al_mc->irq_ce, ret); + if (ret != 0) return ret; - } } return 0; diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c index 4edd2088c2db..1d1e2b5ca14c 100644 --- a/drivers/edac/altera_edac.c +++ b/drivers/edac/altera_edac.c @@ -1507,6 +1507,7 @@ static int altr_portb_setup(struct altr_edac_device_dev *device) int edac_idx, rc; struct device_node *np; const struct edac_device_prv_data *prv = &a10_sdmmceccb_data; + bool is_s10 = device->edac->is_s10; rc = altr_check_ecc_deps(device); if (rc) @@ -1548,15 +1549,14 @@ static int altr_portb_setup(struct altr_edac_device_dev *device) /* * Update the PortB IRQs - A10 has 4, S10 has 2, Index accordingly - * - * FIXME: Instead of ifdefs with different architectures the driver - * should properly use compatibles. */ -#ifdef CONFIG_64BIT - altdev->sb_irq = irq_of_parse_and_map(np, 1); -#else - altdev->sb_irq = irq_of_parse_and_map(np, 2); -#endif + + /* Using compatibles to determine the IRQ Index */ + if (is_s10) + altdev->sb_irq = irq_of_parse_and_map(np, 1); + else + altdev->sb_irq = irq_of_parse_and_map(np, 2); + if (!altdev->sb_irq) { edac_printk(KERN_ERR, EDAC_DEVICE, "Error PortB SBIRQ alloc\n"); rc = -ENODEV; @@ -1570,29 +1570,28 @@ static int altr_portb_setup(struct altr_edac_device_dev *device) goto err_release_group_1; } -#ifdef CONFIG_64BIT - /* Use IRQ to determine SError origin instead of assigning IRQ */ - rc = of_property_read_u32_index(np, "interrupts", 1, &altdev->db_irq); - if (rc) { - edac_printk(KERN_ERR, EDAC_DEVICE, - "Error PortB DBIRQ alloc\n"); - goto err_release_group_1; - } -#else - altdev->db_irq = irq_of_parse_and_map(np, 3); - if (!altdev->db_irq) { - edac_printk(KERN_ERR, EDAC_DEVICE, "Error PortB DBIRQ alloc\n"); - rc = -ENODEV; - goto err_release_group_1; - } - rc = devm_request_irq(&altdev->ddev, altdev->db_irq, - prv->ecc_irq_handler, IRQF_TRIGGER_HIGH, - ecc_name, altdev); - if (rc) { - edac_printk(KERN_ERR, EDAC_DEVICE, "PortB DBERR IRQ error\n"); - goto err_release_group_1; + if (is_s10) { + /* Use IRQ to determine SError origin instead of assigning IRQ */ + rc = of_property_read_u32_index(np, "interrupts", 1, &altdev->db_irq); + if (rc) { + edac_printk(KERN_ERR, EDAC_DEVICE, "Error PortB DBIRQ alloc\n"); + goto err_release_group_1; + } + } else { + altdev->db_irq = irq_of_parse_and_map(np, 3); + if (!altdev->db_irq) { + edac_printk(KERN_ERR, EDAC_DEVICE, "Error PortB DBIRQ alloc\n"); + rc = -ENODEV; + goto err_release_group_1; + } + rc = devm_request_irq(&altdev->ddev, altdev->db_irq, + prv->ecc_irq_handler, IRQF_TRIGGER_HIGH, + ecc_name, altdev); + if (rc) { + edac_printk(KERN_ERR, EDAC_DEVICE, "PortB DBERR IRQ error\n"); + goto err_release_group_1; + } } -#endif rc = edac_device_add_device(dci); if (rc) { @@ -1974,29 +1973,29 @@ static int altr_edac_a10_device_add(struct altr_arria10_edac *edac, goto err_release_group1; } -#ifdef CONFIG_64BIT - /* Use IRQ to determine SError origin instead of assigning IRQ */ - rc = of_property_read_u32_index(np, "interrupts", 0, &altdev->db_irq); - if (rc) { - edac_printk(KERN_ERR, EDAC_DEVICE, - "Unable to parse DB IRQ index\n"); - goto err_release_group1; - } -#else - altdev->db_irq = irq_of_parse_and_map(np, 1); - if (!altdev->db_irq) { - edac_printk(KERN_ERR, EDAC_DEVICE, "Error allocating DBIRQ\n"); - rc = -ENODEV; - goto err_release_group1; - } - rc = devm_request_irq(edac->dev, altdev->db_irq, prv->ecc_irq_handler, - IRQF_TRIGGER_HIGH, - ecc_name, altdev); - if (rc) { - edac_printk(KERN_ERR, EDAC_DEVICE, "No DBERR IRQ resource\n"); - goto err_release_group1; + if (edac->is_s10) { + /* Use IRQ to determine SError origin instead of assigning IRQ */ + rc = of_property_read_u32_index(np, "interrupts", 0, &altdev->db_irq); + if (rc) { + edac_printk(KERN_ERR, EDAC_DEVICE, + "Unable to parse DB IRQ index\n"); + goto err_release_group1; + } + } else { + altdev->db_irq = irq_of_parse_and_map(np, 1); + if (!altdev->db_irq) { + edac_printk(KERN_ERR, EDAC_DEVICE, "Error allocating DBIRQ\n"); + rc = -ENODEV; + goto err_release_group1; + } + rc = devm_request_irq(edac->dev, altdev->db_irq, prv->ecc_irq_handler, + IRQF_TRIGGER_HIGH, + ecc_name, altdev); + if (rc) { + edac_printk(KERN_ERR, EDAC_DEVICE, "No DBERR IRQ resource\n"); + goto err_release_group1; + } } -#endif rc = edac_device_add_device(dci); if (rc) { @@ -2059,7 +2058,6 @@ static const struct irq_domain_ops a10_eccmgr_ic_ops = { /************** Stratix 10 EDAC Double Bit Error Handler ************/ #define to_a10edac(p, m) container_of(p, struct altr_arria10_edac, m) -#ifdef CONFIG_64BIT /* panic routine issues reboot on non-zero panic_timeout */ extern int panic_timeout; @@ -2106,7 +2104,6 @@ static int s10_edac_dberr_handler(struct notifier_block *this, return NOTIFY_DONE; } -#endif /****************** Arria 10 EDAC Probe Function *********************/ static int altr_edac_a10_probe(struct platform_device *pdev) @@ -2122,6 +2119,8 @@ static int altr_edac_a10_probe(struct platform_device *pdev) platform_set_drvdata(pdev, edac); INIT_LIST_HEAD(&edac->a10_ecc_devices); + edac->is_s10 = !!device_get_match_data(&pdev->dev); + edac->ecc_mgr_map = altr_sysmgr_regmap_lookup_by_phandle(pdev->dev.of_node, "altr,sysmgr-syscon"); @@ -2153,8 +2152,7 @@ static int altr_edac_a10_probe(struct platform_device *pdev) irq_set_chained_handler_and_data(edac->sb_irq, altr_edac_a10_irq_handler, edac); - -#ifdef CONFIG_64BIT + if (edac->is_s10) { int dberror, err_addr; @@ -2177,15 +2175,14 @@ static int altr_edac_a10_probe(struct platform_device *pdev) regmap_write(edac->ecc_mgr_map, S10_SYSMGR_UE_ADDR_OFST, 0); } - } -#else - edac->db_irq = platform_get_irq(pdev, 1); - if (edac->db_irq < 0) - return edac->db_irq; + } else { + edac->db_irq = platform_get_irq(pdev, 1); + if (edac->db_irq < 0) + return edac->db_irq; - irq_set_chained_handler_and_data(edac->db_irq, - altr_edac_a10_irq_handler, edac); -#endif + irq_set_chained_handler_and_data(edac->db_irq, + altr_edac_a10_irq_handler, edac); + } for_each_child_of_node(pdev->dev.of_node, child) { if (!of_device_is_available(child)) @@ -2207,7 +2204,7 @@ static int altr_edac_a10_probe(struct platform_device *pdev) static const struct of_device_id altr_edac_a10_of_match[] = { { .compatible = "altr,socfpga-a10-ecc-manager" }, - { .compatible = "altr,socfpga-s10-ecc-manager" }, + { .compatible = "altr,socfpga-s10-ecc-manager", .data = (void *)1 }, {}, }; MODULE_DEVICE_TABLE(of, altr_edac_a10_of_match); diff --git a/drivers/edac/altera_edac.h b/drivers/edac/altera_edac.h index f3e84172caa9..9387056fd65e 100644 --- a/drivers/edac/altera_edac.h +++ b/drivers/edac/altera_edac.h @@ -394,6 +394,7 @@ struct altr_arria10_edac { struct irq_chip irq_chip; struct list_head a10_ecc_devices; struct notifier_block panic_notifier; + bool is_s10; }; #endif /* #ifndef _ALTERA_EDAC_H */ diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index c6aa69dbd9fb..475235c402e8 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -4173,6 +4173,8 @@ static int __init amd64_edac_init(void) goto err_pci; } + request_module_nowait("amd_atl"); + /* register stuff with EDAC MCE */ if (boot_cpu_data.x86 >= 0x17) { amd_register_ecc_decoder(decode_umc_error); diff --git a/drivers/edac/aspeed_edac.c b/drivers/edac/aspeed_edac.c index dadb8acbee3d..6e069b255595 100644 --- a/drivers/edac/aspeed_edac.c +++ b/drivers/edac/aspeed_edac.c @@ -214,10 +214,8 @@ static int config_irq(void *ctx, struct platform_device *pdev) rc = devm_request_irq(&pdev->dev, irq, mcr_isr, IRQF_TRIGGER_HIGH, DRV_NAME, ctx); - if (rc) { - dev_err(&pdev->dev, "unable to request irq %d\n", irq); + if (rc) return rc; - } /* enable interrupts */ regmap_update_bits(aspeed_regmap, ASPEED_MCR_INTR_CTRL, diff --git a/drivers/edac/debugfs.c b/drivers/edac/debugfs.c index 8195fc9c9354..447d0c620082 100644 --- a/drivers/edac/debugfs.c +++ b/drivers/edac/debugfs.c @@ -1,50 +1,9 @@ // SPDX-License-Identifier: GPL-2.0-only -#include <linux/string_choices.h> - #include "edac_module.h" static struct dentry *edac_debugfs; -static ssize_t edac_fake_inject_write(struct file *file, - const char __user *data, - size_t count, loff_t *ppos) -{ - struct device *dev = file->private_data; - struct mem_ctl_info *mci = to_mci(dev); - static enum hw_event_mc_err_type type; - u16 errcount = mci->fake_inject_count; - - if (!errcount) - errcount = 1; - - type = mci->fake_inject_ue ? HW_EVENT_ERR_UNCORRECTED - : HW_EVENT_ERR_CORRECTED; - - printk(KERN_DEBUG - "Generating %d %s fake error%s to %d.%d.%d to test core handling. NOTE: this won't test the driver-specific decoding logic.\n", - errcount, - (type == HW_EVENT_ERR_UNCORRECTED) ? "UE" : "CE", - str_plural(errcount), - mci->fake_inject_layer[0], - mci->fake_inject_layer[1], - mci->fake_inject_layer[2] - ); - edac_mc_handle_error(type, mci, errcount, 0, 0, 0, - mci->fake_inject_layer[0], - mci->fake_inject_layer[1], - mci->fake_inject_layer[2], - "FAKE ERROR", "for EDAC testing only"); - - return count; -} - -static const struct file_operations debug_fake_inject_fops = { - .open = simple_open, - .write = edac_fake_inject_write, - .llseek = generic_file_llseek, -}; - void __init edac_debugfs_init(void) { edac_debugfs = debugfs_create_dir("edac", NULL); @@ -57,29 +16,7 @@ void edac_debugfs_exit(void) void edac_create_debugfs_nodes(struct mem_ctl_info *mci) { - struct dentry *parent; - char name[80]; - int i; - - parent = debugfs_create_dir(mci->dev.kobj.name, edac_debugfs); - - for (i = 0; i < mci->n_layers; i++) { - sprintf(name, "fake_inject_%s", - edac_layer_name[mci->layers[i].type]); - debugfs_create_u8(name, S_IRUGO | S_IWUSR, parent, - &mci->fake_inject_layer[i]); - } - - debugfs_create_bool("fake_inject_ue", S_IRUGO | S_IWUSR, parent, - &mci->fake_inject_ue); - - debugfs_create_u16("fake_inject_count", S_IRUGO | S_IWUSR, parent, - &mci->fake_inject_count); - - debugfs_create_file("fake_inject", S_IWUSR, parent, &mci->dev, - &debug_fake_inject_fops); - - mci->debugfs = parent; + mci->debugfs = debugfs_create_dir(mci->dev.kobj.name, edac_debugfs); } /* Create a toplevel dir under EDAC's debugfs hierarchy */ diff --git a/drivers/edac/edac_device.c b/drivers/edac/edac_device.c index cf0d3c2dfc04..638be1f47c59 100644 --- a/drivers/edac/edac_device.c +++ b/drivers/edac/edac_device.c @@ -342,14 +342,10 @@ static void edac_device_workq_teardown(struct edac_device_ctl_info *edac_dev) } /* - * edac_device_reset_delay_period - * - * need to stop any outstanding workq queued up at this time - * because we will be resetting the sleep time. - * Then restart the workq on the new delay + * Stop any outstanding workq queued up at this time because sleep time will + * be reset. Then restart the workq on the new delay. */ -void edac_device_reset_delay_period(struct edac_device_ctl_info *edac_dev, - unsigned long msec) +void edac_device_reset_delay_period(struct edac_device_ctl_info *edac_dev, unsigned int msec) { edac_dev->poll_msec = msec; edac_dev->delay = msecs_to_jiffies(msec); diff --git a/drivers/edac/edac_device_sysfs.c b/drivers/edac/edac_device_sysfs.c index b1c2717cd023..6359007701ba 100644 --- a/drivers/edac/edac_device_sysfs.c +++ b/drivers/edac/edac_device_sysfs.c @@ -84,18 +84,23 @@ static ssize_t edac_device_ctl_poll_msec_show(struct edac_device_ctl_info return sprintf(data, "%u\n", ctl_info->poll_msec); } -static ssize_t edac_device_ctl_poll_msec_store(struct edac_device_ctl_info - *ctl_info, const char *data, - size_t count) +static ssize_t edac_device_ctl_poll_msec_store(struct edac_device_ctl_info *ctl_info, + const char *data, size_t count) { - unsigned long value; + unsigned int value; + int ret; - /* get the value and enforce that it is non-zero, must be at least - * one millisecond for the delay period, between scans - * Then cancel last outstanding delay for the work request - * and set a new one. + /* + * Get the value, make sure it is non-zero, must be at least one millisecond + * for the delay period between scans. */ - value = simple_strtoul(data, NULL, 0); + ret = kstrtouint(data, 0, &value); + if (ret < 0) + return ret; + + if (value < 1) + return -EINVAL; + edac_device_reset_delay_period(ctl_info, value); return count; diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c index c2ed6c696e54..9b4b5582fa9f 100644 --- a/drivers/edac/edac_mc_sysfs.c +++ b/drivers/edac/edac_mc_sysfs.c @@ -129,7 +129,7 @@ static ssize_t dimmdev_location_show(struct device *dev, ssize_t count; count = edac_dimm_info_location(dimm, data, PAGE_SIZE); - count += scnprintf(data + count, PAGE_SIZE - count, "\n"); + count += sysfs_emit_at(data, count, "\n"); return count; } diff --git a/drivers/edac/edac_module.h b/drivers/edac/edac_module.h index 47593afdc234..eceef5539186 100644 --- a/drivers/edac/edac_module.h +++ b/drivers/edac/edac_module.h @@ -52,8 +52,7 @@ bool edac_queue_work(struct delayed_work *work, unsigned long delay); bool edac_stop_work(struct delayed_work *work); bool edac_mod_work(struct delayed_work *work, unsigned long delay); -extern void edac_device_reset_delay_period(struct edac_device_ctl_info - *edac_dev, unsigned long msec); +extern void edac_device_reset_delay_period(struct edac_device_ctl_info *edac_dev, unsigned int msec); extern void edac_mc_reset_delay_period(unsigned long value); /* diff --git a/drivers/edac/highbank_mc_edac.c b/drivers/edac/highbank_mc_edac.c index a8879d72d064..68d16cc8298d 100644 --- a/drivers/edac/highbank_mc_edac.c +++ b/drivers/edac/highbank_mc_edac.c @@ -235,10 +235,8 @@ static int highbank_mc_probe(struct platform_device *pdev) irq = platform_get_irq(pdev, 0); res = devm_request_irq(&pdev->dev, irq, highbank_mc_err_handler, 0, dev_name(&pdev->dev), mci); - if (res < 0) { - dev_err(&pdev->dev, "Unable to request irq %d\n", irq); + if (res < 0) goto err2; - } devres_close_group(&pdev->dev, NULL); return 0; diff --git a/drivers/edac/ie31200_edac.c b/drivers/edac/ie31200_edac.c index 94ab80197c2e..6f5fdf43e773 100644 --- a/drivers/edac/ie31200_edac.c +++ b/drivers/edac/ie31200_edac.c @@ -416,7 +416,23 @@ static void populate_dimm_info(struct dimm_data *dd, u32 addr_decode, int dimm, { dd->size = field_get(cfg->reg_mad_dimm_size_mask[dimm], addr_decode) * cfg->reg_mad_dimm_size_granularity; dd->ranks = field_get(cfg->reg_mad_dimm_rank_mask[dimm], addr_decode) + 1; - dd->dtype = field_get(cfg->reg_mad_dimm_width_mask[dimm], addr_decode) + DEV_X8; + + switch (field_get(cfg->reg_mad_dimm_width_mask[dimm], addr_decode)) { + case 0: + dd->dtype = DEV_X8; + break; + case 1: + dd->dtype = DEV_X16; + break; + case 2: + dd->dtype = DEV_X32; + break; + case 3: + dd->dtype = DEV_X64; + break; + default: + dd->dtype = DEV_UNKNOWN; + } } static void ie31200_get_dimm_config(struct mem_ctl_info *mci, void __iomem *window, diff --git a/drivers/edac/igen6_edac.c b/drivers/edac/igen6_edac.c index f1fc20d4ebf6..776c5db2f598 100644 --- a/drivers/edac/igen6_edac.c +++ b/drivers/edac/igen6_edac.c @@ -42,7 +42,8 @@ #define GET_BITFIELD(v, lo, hi) (((v) & GENMASK_ULL(hi, lo)) >> (lo)) -#define NUM_IMC 2 /* Max memory controllers */ +/* Probing upper bound, not a hardware capability limit. */ +#define MAX_IMC_TO_PROBE 8 #define NUM_CHANNELS 2 /* Max channels */ #define NUM_DIMMS 2 /* Max DIMMs per channel */ @@ -122,6 +123,43 @@ #define MEM_SLICE_HASH_MASK(v) (GET_BITFIELD(v, 6, 19) << 6) #define MEM_SLICE_HASH_LSB_MASK_BIT(v) GET_BITFIELD(v, 24, 26) +/* + * A slice represents a portion of memory space participating in an + * interleave relationship within the memory hierarchy. + * + * It can represent in different levels such as: + * + * - a pair of memory controllers + * - a memory controller + * - a memory channel + * - a memory sub-channel / DIMM + * + * +--------+ + * | | + * | Zone 1 | + * | | + * +--------+ +--------+ + * | | | | + * | | | | + * | Zone 0 | | Zone 0 | + * | | | | + * | | | | + * +--------+ +--------+ + * + * Slice L Slice S + * + * Memory space is divided into: + * + * - Zone 0 : Interleaved region + * - Zone 1 : Non-interleaved region (upper part of the large slice). + */ +struct slice { + /* Slice address. */ + u64 addr; + /* Slice that @addr belongs to. */ + int id; +}; + struct igen6_imc { int mc; struct mem_ctl_info *mci; @@ -175,8 +213,6 @@ static struct res_config { /* Set imc->dimm_{l_size,s_size,l_map}[chan]. */ void (*set_dimm_params)(struct igen6_imc *imc, int chan); bool (*ibecc_available)(struct pci_dev *pdev); - /* Extract error address logged in IBECC */ - u64 (*err_addr)(u64 ecclog); /* Convert error address logged in IBECC to system physical address */ u64 (*err_addr_to_sys_addr)(u64 eaddr, int mc); /* Convert error address logged in IBECC to integrated memory controller address */ @@ -184,11 +220,11 @@ static struct res_config { } *res_cfg; static struct igen6_pvt { - struct igen6_imc imc[NUM_IMC]; void __iomem *memss_pma_cr; u64 ms_hash; u64 ms_s_size; int ms_l_map; + struct igen6_imc imc[]; } *igen6_pvt; /* The top of low usable DRAM */ @@ -225,7 +261,8 @@ static char ecclog_buf[ECCLOG_POOL_SIZE]; static struct irq_work ecclog_irq_work; static struct work_struct ecclog_work; -/* Compute die IDs for Elkhart Lake with IBECC */ +/* SoC compute die IDs with IBECC capability. */ +/* Elkhart Lake */ #define DID_EHL_SKU5 0x4514 #define DID_EHL_SKU6 0x4528 #define DID_EHL_SKU7 0x452a @@ -238,22 +275,22 @@ static struct work_struct ecclog_work; #define DID_EHL_SKU14 0x4534 #define DID_EHL_SKU15 0x4536 -/* Compute die IDs for ICL-NNPI with IBECC */ +/* ICL-NNPI */ #define DID_ICL_SKU8 0x4581 #define DID_ICL_SKU10 0x4585 #define DID_ICL_SKU11 0x4589 #define DID_ICL_SKU12 0x458d -/* Compute die IDs for Tiger Lake with IBECC */ +/* Tiger Lake */ #define DID_TGL_SKU 0x9a14 -/* Compute die IDs for Alder Lake with IBECC */ +/* Alder Lake */ #define DID_ADL_SKU1 0x4601 #define DID_ADL_SKU2 0x4602 #define DID_ADL_SKU3 0x4621 #define DID_ADL_SKU4 0x4641 -/* Compute die IDs for Alder Lake-N with IBECC */ +/* Alder Lake-N */ #define DID_ADL_N_SKU1 0x4614 #define DID_ADL_N_SKU2 0x4617 #define DID_ADL_N_SKU3 0x461b @@ -267,38 +304,38 @@ static struct work_struct ecclog_work; #define DID_ADL_N_SKU11 0x467c #define DID_ADL_N_SKU12 0x4632 -/* Compute die IDs for Arizona Beach with IBECC */ +/* Arizona Beach */ #define DID_AZB_SKU1 0x4676 -/* Compute did IDs for Amston Lake with IBECC */ +/* Amston Lake */ #define DID_ASL_SKU1 0x464a #define DID_ASL_SKU2 0x4646 #define DID_ASL_SKU3 0x4652 -/* Compute die IDs for Raptor Lake-P with IBECC */ +/* Raptor Lake-P */ #define DID_RPL_P_SKU1 0xa706 #define DID_RPL_P_SKU2 0xa707 #define DID_RPL_P_SKU3 0xa708 #define DID_RPL_P_SKU4 0xa716 #define DID_RPL_P_SKU5 0xa718 -/* Compute die IDs for Meteor Lake-PS with IBECC */ +/* Meteor Lake-PS */ #define DID_MTL_PS_SKU1 0x7d21 #define DID_MTL_PS_SKU2 0x7d22 #define DID_MTL_PS_SKU3 0x7d23 #define DID_MTL_PS_SKU4 0x7d24 -/* Compute die IDs for Meteor Lake-P with IBECC */ +/* Meteor Lake-P */ #define DID_MTL_P_SKU1 0x7d01 #define DID_MTL_P_SKU2 0x7d02 #define DID_MTL_P_SKU3 0x7d14 -/* Compute die IDs for Arrow Lake-UH with IBECC */ +/* Arrow Lake-UH */ #define DID_ARL_UH_SKU1 0x7d06 #define DID_ARL_UH_SKU2 0x7d20 #define DID_ARL_UH_SKU3 0x7d30 -/* Compute die IDs for Panther Lake-H with IBECC */ +/* Panther Lake-H */ #define DID_PTL_H_SKU1 0xb000 #define DID_PTL_H_SKU2 0xb001 #define DID_PTL_H_SKU3 0xb002 @@ -314,15 +351,114 @@ static struct work_struct ecclog_work; #define DID_PTL_H_SKU13 0xb02a #define DID_PTL_H_SKU14 0xb00a -/* Compute die IDs for Wildcat Lake with IBECC */ +/* Starfire */ +#define DID_STF_SKU1 0xb02b + +/* Wildcat Lake */ #define DID_WCL_SKU1 0xfd00 -/* Compute die IDs for Nova Lake-H/HX with IBECC */ +/* Nova Lake-H/HX */ #define DID_NVL_H_SKU1 0xd701 #define DID_NVL_H_SKU2 0xd702 #define DID_NVL_H_SKU3 0xd704 #define DID_NVL_H_SKU4 0xd705 +/* Remove the interleave bit and shift upper part down to fill gap. */ +static u64 squeeze_addr(u64 addr, int intlv_bit) +{ + u64 slice_addr; + + slice_addr = GET_BITFIELD(addr, intlv_bit + 1, 63) << intlv_bit; + slice_addr |= GET_BITFIELD(addr, 0, intlv_bit - 1); + + return slice_addr; +} + +/* Shift the upper bits up and insert a zero at the @intlv_bit bit position. */ +static u64 inflate_addr(u64 addr, int intlv_bit) +{ + u64 inflated_addr; + + /* Insert a zero at @intlv_bit position. */ + inflated_addr = GET_BITFIELD(addr, intlv_bit, 63) << (intlv_bit + 1); + inflated_addr |= GET_BITFIELD(addr, 0, intlv_bit - 1); + + return inflated_addr; +} + +static u64 compute_hash(u64 addr, u64 hash_mask, u64 hash_base, int intlv_bit) +{ + u64 hash_addr; + int i; + + /* + * In hash mode, @intlv_bit is the lowest selected bit of @addr + * to be XORed. While @mask may or may not include this @intlv_bit, + * we enforce that @mask includes @intlv_bit to ensure @intlv_bit is + * XORed exactly once. + */ + hash_mask |= BIT_ULL(intlv_bit); + hash_addr = addr & hash_mask; + + for (i = 6; i < 20; i++) + hash_base ^= (hash_addr >> i) & 1; + + return hash_base; +} + +/* + * Converts a higher-level address (system / IMC / channel) into a lower-level + * slice address and identifier. + */ +static void translate_to_lower_level(u64 addr, u64 hash_mask, u64 hash_base, + int intlv_bit, u64 s_size, int l_map, + struct slice *slice) +{ + /* In non-interleave zone. */ + if (addr >= 2 * s_size) { + slice->addr = addr - s_size; + slice->id = l_map; + return; + } + + /* In interleave zone. */ + slice->addr = squeeze_addr(addr, intlv_bit); + + /* Non-hash mode. */ + if (!hash_mask) { + slice->id = GET_BITFIELD(addr, intlv_bit, intlv_bit); + return; + } + + /* Hash mode. */ + slice->id = compute_hash(addr, hash_mask, hash_base, intlv_bit); +} + +/* Reconstruct address for upper memory hierarchy level. */ +static u64 translate_to_upper_level(u64 addr, u64 hash_mask, u64 hash_base, + int intlv_bit, u64 s_size) +{ + u64 inflated_addr, hash_val; + + /* In non-interleave zone. */ + if (addr >= s_size) + return addr + s_size; + + /* + * In interleave zone. + * + * Insert a zero at @intlv_bit position. + */ + inflated_addr = inflate_addr(addr, intlv_bit); + + /* + * Reconstruct the removed interleave bit and use it to replace + * the zero at @intlv_bit position. + */ + hash_val = compute_hash(inflated_addr, hash_mask, hash_base, intlv_bit); + return inflated_addr | (hash_val << intlv_bit); +} + static int get_mchbar(struct pci_dev *pdev, u64 *mchbar) { union { @@ -354,6 +490,46 @@ static int get_mchbar(struct pci_dev *pdev, u64 *mchbar) return 0; } +/* Check whether the memory controller is absent. */ +static bool imc_absent(void __iomem *window) +{ + return readl(window + MAD_INTER_CHANNEL_OFFSET) == ~0; +} + +/* Return MMIO base address of the memory controller if it's present, otherwise return NULL. */ +static void __iomem *map_imc_window(u64 mchbar, int pmc) +{ + void __iomem *window; + + window = ioremap(mchbar + pmc * MCHBAR_SIZE, MCHBAR_SIZE); + if (!window) + return NULL; + + if (imc_absent(window)) { + iounmap(window); + return NULL; + } + + return window; +} + +/* Return the number of present memory controllers. */ +static int get_imc_num(u64 mchbar) +{ + void __iomem *window; + int lmc, pmc; + + for (lmc = 0, pmc = 0; pmc < MAX_IMC_TO_PROBE; pmc++) { + window = map_imc_window(mchbar, pmc); + if (window) { + iounmap(window); + lmc++; + } + } + + return lmc; +} + static bool ehl_ibecc_available(struct pci_dev *pdev) { u32 v; @@ -450,21 +626,9 @@ static u64 mem_addr_to_sys_addr(u64 maddr) return maddr; } -static u64 mem_slice_hash(u64 addr, u64 mask, u64 hash_init, int intlv_bit) -{ - u64 hash_addr = addr & mask, hash = hash_init; - u64 intlv = (addr >> intlv_bit) & 1; - int i; - - for (i = 6; i < 20; i++) - hash ^= (hash_addr >> i) & 1; - - return hash ^ intlv; -} - static u64 tgl_err_addr_to_mem_addr(u64 eaddr, int mc) { - u64 maddr, hash, mask, ms_s_size; + u64 mask, ms_s_size; int intlv_bit; u32 ms_hash; @@ -477,12 +641,7 @@ static u64 tgl_err_addr_to_mem_addr(u64 eaddr, int mc) mask = MEM_SLICE_HASH_MASK(ms_hash); intlv_bit = MEM_SLICE_HASH_LSB_MASK_BIT(ms_hash) + 6; - maddr = GET_BITFIELD(eaddr, intlv_bit, 63) << (intlv_bit + 1) | - GET_BITFIELD(eaddr, 0, intlv_bit - 1); - - hash = mem_slice_hash(maddr, mask, mc, intlv_bit); - - return maddr | (hash << intlv_bit); + return translate_to_upper_level(eaddr, mask, mc, intlv_bit, ms_s_size); } static u64 tgl_err_addr_to_sys_addr(u64 eaddr, int mc) @@ -504,8 +663,9 @@ static u64 adl_err_addr_to_sys_addr(u64 eaddr, int mc) static u64 adl_err_addr_to_imc_addr(u64 eaddr, int mc) { - u64 imc_addr, ms_s_size = igen6_pvt->ms_s_size; + u64 ms_s_size = igen6_pvt->ms_s_size; struct igen6_imc *imc = &igen6_pvt->imc[mc]; + struct slice slice; int intlv_bit; u32 mc_hash; @@ -516,15 +676,8 @@ static u64 adl_err_addr_to_imc_addr(u64 eaddr, int mc) intlv_bit = MAC_MC_HASH_LSB(mc_hash) + 6; - imc_addr = GET_BITFIELD(eaddr, intlv_bit + 1, 63) << intlv_bit | - GET_BITFIELD(eaddr, 0, intlv_bit - 1); - - return imc_addr; -} - -static u64 rpl_p_err_addr(u64 ecclog) -{ - return field_get(res_cfg->reg_eccerrlog_addr_mask, ecclog); + translate_to_lower_level(eaddr, 0, 0, intlv_bit, ms_s_size, 0, &slice); + return slice.addr; } static enum mem_type ptl_h_get_mem_type(struct igen6_imc *imc) @@ -686,6 +839,7 @@ static struct res_config tgl_cfg = { .err_addr_to_imc_addr = tgl_err_addr_to_imc_addr, }; +/* Shared by Alder Lake, Alder Lake-N, Arizona Beach, Amston Lake, and Raptor Lake-P */ static struct res_config adl_cfg = { .machine_check = true, .num_imc = 2, @@ -701,37 +855,6 @@ static struct res_config adl_cfg = { .err_addr_to_imc_addr = adl_err_addr_to_imc_addr, }; -static struct res_config adl_n_cfg = { - .machine_check = true, - .num_imc = 1, - .reg_mchbar_mask = GENMASK_ULL(41, 17), - .reg_tom_mask = GENMASK_ULL(41, 20), - .reg_touud_mask = GENMASK_ULL(41, 20), - .reg_eccerrlog_addr_mask = GENMASK_ULL(45, 5), - .imc_base = 0xd800, - .ibecc_base = 0xd400, - .ibecc_error_log_offset = 0x68, - .ibecc_available = tgl_ibecc_available, - .err_addr_to_sys_addr = adl_err_addr_to_sys_addr, - .err_addr_to_imc_addr = adl_err_addr_to_imc_addr, -}; - -static struct res_config rpl_p_cfg = { - .machine_check = true, - .num_imc = 2, - .reg_mchbar_mask = GENMASK_ULL(41, 17), - .reg_tom_mask = GENMASK_ULL(41, 20), - .reg_touud_mask = GENMASK_ULL(41, 20), - .reg_eccerrlog_addr_mask = GENMASK_ULL(45, 5), - .imc_base = 0xd800, - .ibecc_base = 0xd400, - .ibecc_error_log_offset = 0x68, - .ibecc_available = tgl_ibecc_available, - .err_addr = rpl_p_err_addr, - .err_addr_to_sys_addr = adl_err_addr_to_sys_addr, - .err_addr_to_imc_addr = adl_err_addr_to_imc_addr, -}; - static struct res_config mtl_ps_cfg = { .machine_check = true, .num_imc = 2, @@ -749,6 +872,7 @@ static struct res_config mtl_ps_cfg = { .err_addr_to_imc_addr = adl_err_addr_to_imc_addr, }; +/* Shared by Meteor Lake-P, Arrow Lake-UH, and Wildcat Lake */ static struct res_config mtl_p_cfg = { .machine_check = true, .num_imc = 2, @@ -764,6 +888,7 @@ static struct res_config mtl_p_cfg = { .err_addr_to_imc_addr = adl_err_addr_to_imc_addr, }; +/* Shared by Panther Lake-H and Starfire */ static struct res_config ptl_h_cfg = { .machine_check = true, .num_imc = 2, @@ -794,21 +919,6 @@ static struct res_config ptl_h_cfg = { .err_addr_to_imc_addr = adl_err_addr_to_imc_addr, }; -static struct res_config wcl_cfg = { - .machine_check = true, - .num_imc = 1, - .reg_mchbar_mask = GENMASK_ULL(41, 17), - .reg_tom_mask = GENMASK_ULL(41, 20), - .reg_touud_mask = GENMASK_ULL(41, 20), - .reg_eccerrlog_addr_mask = GENMASK_ULL(38, 5), - .imc_base = 0xd800, - .ibecc_base = 0xd400, - .ibecc_error_log_offset = 0x170, - .ibecc_available = mtl_p_ibecc_available, - .err_addr_to_sys_addr = adl_err_addr_to_sys_addr, - .err_addr_to_imc_addr = adl_err_addr_to_imc_addr, -}; - static struct res_config nvl_h_cfg = { .machine_check = true, .num_imc = 2, @@ -861,27 +971,27 @@ static struct pci_device_id igen6_pci_tbl[] = { { PCI_VDEVICE(INTEL, DID_ADL_SKU2), .driver_data = (kernel_ulong_t)&adl_cfg }, { PCI_VDEVICE(INTEL, DID_ADL_SKU3), .driver_data = (kernel_ulong_t)&adl_cfg }, { PCI_VDEVICE(INTEL, DID_ADL_SKU4), .driver_data = (kernel_ulong_t)&adl_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU1), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU2), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU3), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU4), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU5), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU6), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU7), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU8), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU9), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU10), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU11), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU12), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_AZB_SKU1), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ASL_SKU1), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ASL_SKU2), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ASL_SKU3), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_RPL_P_SKU1), .driver_data = (kernel_ulong_t)&rpl_p_cfg }, - { PCI_VDEVICE(INTEL, DID_RPL_P_SKU2), .driver_data = (kernel_ulong_t)&rpl_p_cfg }, - { PCI_VDEVICE(INTEL, DID_RPL_P_SKU3), .driver_data = (kernel_ulong_t)&rpl_p_cfg }, - { PCI_VDEVICE(INTEL, DID_RPL_P_SKU4), .driver_data = (kernel_ulong_t)&rpl_p_cfg }, - { PCI_VDEVICE(INTEL, DID_RPL_P_SKU5), .driver_data = (kernel_ulong_t)&rpl_p_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU1), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU2), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU3), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU4), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU5), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU6), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU7), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU8), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU9), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU10), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU11), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU12), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_AZB_SKU1), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ASL_SKU1), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ASL_SKU2), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ASL_SKU3), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_RPL_P_SKU1), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_RPL_P_SKU2), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_RPL_P_SKU3), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_RPL_P_SKU4), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_RPL_P_SKU5), .driver_data = (kernel_ulong_t)&adl_cfg }, { PCI_VDEVICE(INTEL, DID_MTL_PS_SKU1), .driver_data = (kernel_ulong_t)&mtl_ps_cfg }, { PCI_VDEVICE(INTEL, DID_MTL_PS_SKU2), .driver_data = (kernel_ulong_t)&mtl_ps_cfg }, { PCI_VDEVICE(INTEL, DID_MTL_PS_SKU3), .driver_data = (kernel_ulong_t)&mtl_ps_cfg }, @@ -892,6 +1002,7 @@ static struct pci_device_id igen6_pci_tbl[] = { { PCI_VDEVICE(INTEL, DID_ARL_UH_SKU1), .driver_data = (kernel_ulong_t)&mtl_p_cfg }, { PCI_VDEVICE(INTEL, DID_ARL_UH_SKU2), .driver_data = (kernel_ulong_t)&mtl_p_cfg }, { PCI_VDEVICE(INTEL, DID_ARL_UH_SKU3), .driver_data = (kernel_ulong_t)&mtl_p_cfg }, + { PCI_VDEVICE(INTEL, DID_WCL_SKU1), .driver_data = (kernel_ulong_t)&mtl_p_cfg }, { PCI_VDEVICE(INTEL, DID_PTL_H_SKU1), .driver_data = (kernel_ulong_t)&ptl_h_cfg }, { PCI_VDEVICE(INTEL, DID_PTL_H_SKU2), .driver_data = (kernel_ulong_t)&ptl_h_cfg }, { PCI_VDEVICE(INTEL, DID_PTL_H_SKU3), .driver_data = (kernel_ulong_t)&ptl_h_cfg }, @@ -906,7 +1017,7 @@ static struct pci_device_id igen6_pci_tbl[] = { { PCI_VDEVICE(INTEL, DID_PTL_H_SKU12), .driver_data = (kernel_ulong_t)&ptl_h_cfg }, { PCI_VDEVICE(INTEL, DID_PTL_H_SKU13), .driver_data = (kernel_ulong_t)&ptl_h_cfg }, { PCI_VDEVICE(INTEL, DID_PTL_H_SKU14), .driver_data = (kernel_ulong_t)&ptl_h_cfg }, - { PCI_VDEVICE(INTEL, DID_WCL_SKU1), .driver_data = (kernel_ulong_t)&wcl_cfg }, + { PCI_VDEVICE(INTEL, DID_STF_SKU1), .driver_data = (kernel_ulong_t)&ptl_h_cfg }, { PCI_VDEVICE(INTEL, DID_NVL_H_SKU1), .driver_data = (kernel_ulong_t)&nvl_h_cfg }, { PCI_VDEVICE(INTEL, DID_NVL_H_SKU2), .driver_data = (kernel_ulong_t)&nvl_h_cfg }, { PCI_VDEVICE(INTEL, DID_NVL_H_SKU3), .driver_data = (kernel_ulong_t)&nvl_h_cfg }, @@ -1007,55 +1118,13 @@ static void set_dimm_params(struct igen6_imc *imc, int chan) imc->dimm_s_size[chan] = MAD_DIMM_CH_DIMM_S_SIZE(val); } -static int decode_chan_idx(u64 addr, u64 mask, int intlv_bit) -{ - u64 hash_addr = addr & mask, hash = 0; - u64 intlv = (addr >> intlv_bit) & 1; - int i; - - for (i = 6; i < 20; i++) - hash ^= (hash_addr >> i) & 1; - - return (int)hash ^ intlv; -} - -static u64 decode_channel_addr(u64 addr, int intlv_bit) -{ - u64 channel_addr; - - /* Remove the interleave bit and shift upper part down to fill gap */ - channel_addr = GET_BITFIELD(addr, intlv_bit + 1, 63) << intlv_bit; - channel_addr |= GET_BITFIELD(addr, 0, intlv_bit - 1); - - return channel_addr; -} - -static void decode_addr(u64 addr, u32 hash, u64 s_size, int l_map, - int *idx, u64 *sub_addr) -{ - int intlv_bit = CHANNEL_HASH_LSB_MASK_BIT(hash) + 6; - - if (addr > 2 * s_size) { - *sub_addr = addr - s_size; - *idx = l_map; - return; - } - - if (CHANNEL_HASH_MODE(hash)) { - *sub_addr = decode_channel_addr(addr, intlv_bit); - *idx = decode_chan_idx(addr, CHANNEL_HASH_MASK(hash), intlv_bit); - } else { - *sub_addr = decode_channel_addr(addr, 6); - *idx = GET_BITFIELD(addr, 6, 6); - } -} - static int igen6_decode(struct decoded_addr *res) { struct igen6_imc *imc = &igen6_pvt->imc[res->mc]; - u64 addr = res->imc_addr, sub_addr, s_size; - int idx, l_map; - u32 hash; + u64 addr = res->imc_addr, s_size; + int intlv_bit, l_map; + u32 hash, hash_mask; + struct slice slice; if (addr >= igen6_tom) { edac_dbg(0, "Address 0x%llx out of range\n", addr); @@ -1066,17 +1135,25 @@ static int igen6_decode(struct decoded_addr *res) hash = readl(imc->window + CHANNEL_HASH_OFFSET); s_size = imc->ch_s_size; l_map = imc->ch_l_map; - decode_addr(addr, hash, s_size, l_map, &idx, &sub_addr); - res->channel_idx = idx; - res->channel_addr = sub_addr; + hash_mask = CHANNEL_HASH_MODE(hash) ? CHANNEL_HASH_MASK(hash) : 0; + intlv_bit = CHANNEL_HASH_LSB_MASK_BIT(hash) + 6; + + translate_to_lower_level(addr, hash_mask, 0, intlv_bit, s_size, l_map, &slice); + + res->channel_idx = slice.id; + res->channel_addr = slice.addr; /* Decode sub-channel/DIMM */ hash = readl(imc->window + CHANNEL_EHASH_OFFSET); - s_size = imc->dimm_s_size[idx]; - l_map = imc->dimm_l_map[idx]; - decode_addr(res->channel_addr, hash, s_size, l_map, &idx, &sub_addr); - res->sub_channel_idx = idx; - res->sub_channel_addr = sub_addr; + s_size = imc->dimm_s_size[res->channel_idx]; + l_map = imc->dimm_l_map[res->channel_idx]; + hash_mask = CHANNEL_HASH_MODE(hash) ? CHANNEL_HASH_MASK(hash) : 0; + intlv_bit = CHANNEL_HASH_LSB_MASK_BIT(hash) + 6; + + translate_to_lower_level(res->channel_addr, hash_mask, 0, intlv_bit, s_size, l_map, &slice); + + res->sub_channel_idx = slice.id; + res->sub_channel_addr = slice.addr; return 0; } @@ -1230,11 +1307,7 @@ static void ecclog_work_cb(struct work_struct *work) llist_for_each_entry_safe(node, tmp, head, llnode) { memset(&res, 0, sizeof(res)); - if (res_cfg->err_addr) - eaddr = res_cfg->err_addr(node->ecclog); - else - eaddr = node->ecclog & res_cfg->reg_eccerrlog_addr_mask; - + eaddr = node->ecclog & res_cfg->reg_eccerrlog_addr_mask; res.mc = node->mc; res.sys_addr = res_cfg->err_addr_to_sys_addr(eaddr, res.mc); res.imc_addr = res_cfg->err_addr_to_imc_addr(eaddr, res.mc); @@ -1476,18 +1549,27 @@ static struct igen6_pvt *igen6_pvt_setup(struct pci_dev *pdev) { void __iomem *memss_pma_cr; struct igen6_pvt *pvt; + int imc_num, rc; u64 mchbar; - int rc; - pvt = kzalloc_obj(*igen6_pvt); - if (!pvt) + rc = get_mchbar(pdev, &mchbar); + if (rc) return NULL; - rc = get_mchbar(pdev, &mchbar); - if (rc) { - kfree(pvt); + imc_num = get_imc_num(mchbar); + if (!imc_num) { + igen6_printk(KERN_ERR, "No mc found.\n"); return NULL; } + edac_dbg(2, "%d mcs found.\n", imc_num); + + /* Use the runtime detected IMC count. */ + if (res_cfg->num_imc != imc_num) + res_cfg->num_imc = imc_num; + + pvt = kzalloc_flex(*pvt, imc, imc_num); + if (!pvt) + return NULL; memss_pma_cr = ioremap(mchbar, MCHBAR_SIZE * 2); if (!memss_pma_cr) { @@ -1572,12 +1654,6 @@ static void igen6_check(struct mem_ctl_info *mci) irq_work_queue(&ecclog_irq_work); } -/* Check whether the memory controller is absent. */ -static bool igen6_imc_absent(void __iomem *window) -{ - return readl(window + MAD_INTER_CHANNEL_OFFSET) == ~0; -} - static void imc_release(struct device *dev) { /* Nothing to do, the 'imc' owns the 'dev' and will also release it. */ @@ -1689,26 +1765,15 @@ static int igen6_register_mcis(struct pci_dev *pdev, u64 mchbar) { void __iomem *window; int lmc, pmc, rc; - u64 base; - - for (lmc = 0, pmc = 0; pmc < NUM_IMC; pmc++) { - base = mchbar + pmc * MCHBAR_SIZE; - window = ioremap(base, MCHBAR_SIZE); - if (!window) { - igen6_printk(KERN_ERR, "Failed to ioremap 0x%llx for mc%d\n", base, pmc); - rc = -ENOMEM; - goto out_unregister_mcis; - } - if (igen6_imc_absent(window)) { - iounmap(window); - edac_dbg(2, "Skip absent mc%d\n", pmc); + for (lmc = 0, pmc = 0; pmc < MAX_IMC_TO_PROBE; pmc++) { + window = map_imc_window(mchbar, pmc); + if (!window) continue; - } rc = igen6_register_mci(lmc, window, pdev); if (rc) - goto out_iounmap; + goto err_unregister; /* Done, if all present MCs are detected and registered. */ if (++lmc >= res_cfg->num_imc) @@ -1728,10 +1793,8 @@ static int igen6_register_mcis(struct pci_dev *pdev, u64 mchbar) return 0; -out_iounmap: +err_unregister: iounmap(window); - -out_unregister_mcis: igen6_unregister_mcis(); return rc; diff --git a/drivers/edac/thunderx_edac.c b/drivers/edac/thunderx_edac.c index 75c04dfc3962..9c0a1e48f96f 100644 --- a/drivers/edac/thunderx_edac.c +++ b/drivers/edac/thunderx_edac.c @@ -729,10 +729,8 @@ static int thunderx_lmc_probe(struct pci_dev *pdev, thunderx_lmc_err_isr, thunderx_lmc_threaded_isr, 0, "[EDAC] ThunderX LMC", mci); - if (ret) { - dev_err(&pdev->dev, "Cannot set ISR: %d\n", ret); + if (ret) goto err_free; - } lmc->node = FIELD_GET(THUNDERX_NODE, pci_resource_start(pdev, 0)); diff --git a/drivers/edac/xgene_edac.c b/drivers/edac/xgene_edac.c index 9955396c9a52..62b8166dc287 100644 --- a/drivers/edac/xgene_edac.c +++ b/drivers/edac/xgene_edac.c @@ -1924,11 +1924,8 @@ static int xgene_edac_probe(struct platform_device *pdev) rc = devm_request_irq(&pdev->dev, irq, xgene_edac_isr, IRQF_SHARED, dev_name(&pdev->dev), edac); - if (rc) { - dev_err(&pdev->dev, - "Could not request IRQ %d\n", irq); + if (rc) goto out_err; - } } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c index 87e15e39eb30..ec6e5bde7f80 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c @@ -299,10 +299,10 @@ amdgpu_devcoredump_print_ibs(struct drm_printer *p, amdgpu_res_first(abo->tbo.resource, offset, coredump->ibs[i].ib_size_dw * 4, &cursor); while (cursor.remaining) { - amdgpu_device_mm_access(adev, cursor.start / 4, - &ib_content[off], cursor.size / 4, + amdgpu_device_mm_access(adev, cursor.start, + &ib_content[off], cursor.size, false); - off += cursor.size; + off += cursor.size / 4; amdgpu_res_next(&cursor, cursor.size); } emit_content = true; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 44bed0ba64a3..104d1d2cbad9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -771,6 +771,9 @@ static int amdgpu_device_read_fb_via_bar0(struct amdgpu_device *adev, if (!buf || !size) return -EINVAL; + if (!amdgpu_sriov_vf(adev)) + return -EINVAL; + flags = pci_resource_flags(adev->pdev, 0); if ((flags & IORESOURCE_UNSET) || !(flags & IORESOURCE_MEM)) return -EINVAL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c index b96f94e5169f..1a86a47406b1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c @@ -879,7 +879,7 @@ bool amdgpu_mes_queue_reset_by_mes_supported(struct amdgpu_device *adev) return (ip_maj == 11 && mes_sched >= 0x8c) || ((ip_maj == 12 && ip_min == 0) && mes_sched >= 0x8d) || - ((ip_maj == 12 && ip_min == 1) && mes_sched >= 0x73); + ((ip_maj == 12 && ip_min == 1) && mes_sched >= 0x7b); } /* Fix me -- node_id is used to identify the correct MES instances in the future */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 04f6ebf31cca..42adc8e738d8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -396,6 +396,12 @@ static bool psp_get_runtime_db_entry(struct amdgpu_device *adev, bool ret = false; int i; + /* + * Runtime DB is for dGPUs only. + */ + if (adev->flags & AMD_IS_APU) + return false; + if (amdgpu_ip_version(adev, MP0_HWIP, 0) == IP_VERSION(13, 0, 6) || amdgpu_ip_version(adev, MP0_HWIP, 0) == IP_VERSION(13, 0, 12) || amdgpu_ip_version(adev, MP0_HWIP, 0) == IP_VERSION(13, 0, 14) || diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c index 0a816b3c5ff9..e43bda0cab3f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c @@ -1544,7 +1544,7 @@ int amdgpu_userq_post_reset(struct amdgpu_device *adev, bool vram_lost) struct amdgpu_usermode_queue *queue; const struct amdgpu_userq_funcs *userq_funcs; unsigned long queue_id; - int r = 0; + int ret = 0, r; xa_for_each(&adev->userq_doorbell_xa, queue_id, queue) { if (queue->state == AMDGPU_USERQ_STATE_HUNG && !vram_lost) { @@ -1555,6 +1555,7 @@ int amdgpu_userq_post_reset(struct amdgpu_device *adev, bool vram_lost) r = userq_funcs->map(queue); if (r) { dev_err(adev->dev, "Failed to remap queue %ld\n", queue_id); + ret = r; continue; } trace_amdgpu_userq_state_changed(queue, AMDGPU_USERQ_STATE_MAPPED); @@ -1562,5 +1563,5 @@ int amdgpu_userq_post_reset(struct amdgpu_device *adev, bool vram_lost) } } - return r; + return ret; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index aedf72c2333e..bb04101b0fb5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -2090,7 +2090,7 @@ int amdgpu_vm_bo_clear_mappings(struct amdgpu_device *adev, after->start = eaddr + 1; after->last = tmp->last; after->offset = tmp->offset; - after->offset += (after->start - tmp->start) << PAGE_SHIFT; + after->offset += (after->start - tmp->start) << AMDGPU_GPU_PAGE_SHIFT; after->flags = tmp->flags; after->bo_va = tmp->bo_va; list_add(&after->list, &tmp->bo_va->invalids); @@ -3122,7 +3122,7 @@ static void amdgpu_debugfs_vm_bo_status_info(struct seq_file *m, id = 0; seq_puts(m, "\tIdle BOs:\n"); - list_for_each_entry(base, &lists->needs_update, vm_status) { + list_for_each_entry(base, &lists->idle, vm_status) { if (!base->bo) continue; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index 69776dbe188d..0ff5a80aa918 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -1651,10 +1651,10 @@ static int gfx_v11_0_sw_init(struct amdgpu_ip_block *ip_block) case IP_VERSION(11, 0, 2): case IP_VERSION(11, 0, 3): if (!adev->gfx.disable_uq && - adev->gfx.me_fw_version >= 2420 && - adev->gfx.pfp_fw_version >= 2580 && - adev->gfx.mec_fw_version >= 2650 && - adev->mes.fw_version[0] >= 120) { + adev->gfx.me_fw_version >= 3090 && + adev->gfx.pfp_fw_version >= 3190 && + adev->gfx.mec_fw_version >= 3450 && + adev->mes.fw_version[0] >= 147) { adev->userq_funcs[AMDGPU_HW_IP_GFX] = &userq_mes_funcs; adev->userq_funcs[AMDGPU_HW_IP_COMPUTE] = &userq_mes_funcs; } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c index 1e5fd1ef8f1d..e2a81a55c63b 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c @@ -1436,10 +1436,10 @@ static int gfx_v12_0_sw_init(struct amdgpu_ip_block *ip_block) case IP_VERSION(12, 0, 0): case IP_VERSION(12, 0, 1): if (!adev->gfx.disable_uq && - adev->gfx.me_fw_version >= 2780 && - adev->gfx.pfp_fw_version >= 2840 && - adev->gfx.mec_fw_version >= 3050 && - adev->mes.fw_version[0] >= 123) { + adev->gfx.me_fw_version >= 3090 && + adev->gfx.pfp_fw_version >= 3190 && + adev->gfx.mec_fw_version >= 3450 && + adev->mes.fw_version[0] >= 147) { adev->userq_funcs[AMDGPU_HW_IP_GFX] = &userq_mes_funcs; adev->userq_funcs[AMDGPU_HW_IP_COMPUTE] = &userq_mes_funcs; } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 6cf427995078..7f91186ef1d1 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -4546,9 +4546,11 @@ static int gfx_v8_0_mqd_init(struct amdgpu_ring *ring) /* set static priority for a queue/ring */ gfx_v8_0_mqd_set_priority(ring, mqd); tmp = RREG32(mmCP_HQD_QUANTUM); - tmp = REG_SET_FIELD(tmp, CP_HQD_QUANTUM, QUANTUM_EN, 1); - tmp = REG_SET_FIELD(tmp, CP_HQD_QUANTUM, QUANTUM_SCALE, 1); - tmp = REG_SET_FIELD(tmp, CP_HQD_QUANTUM, QUANTUM_DURATION, 10); + if (ring != &adev->gfx.kiq[0].ring) { + tmp = REG_SET_FIELD(tmp, CP_HQD_QUANTUM, QUANTUM_EN, 1); + tmp = REG_SET_FIELD(tmp, CP_HQD_QUANTUM, QUANTUM_SCALE, 1); + tmp = REG_SET_FIELD(tmp, CP_HQD_QUANTUM, QUANTUM_DURATION, 10); + } mqd->cp_hqd_quantum = tmp; /* map_queues packet doesn't need activate the queue, 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 4bc947c3bd0d..9811e4e10291 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -1455,6 +1455,14 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm, dqm_evict_mqd_bo(dqm, q); } + /* + * Heavy-weight TLB flush after MES removes queues to ensure + * in-flight memory accesses complete before memory is freed/migrated. + * HWS does this automatically, MES does not. + */ + if (dqm->dev->kfd->shared_resources.enable_mes) + kfd_flush_tlb(pdd); + if (!dqm->dev->kfd->shared_resources.enable_mes) { pdd->last_evict_timestamp = get_jiffies_64(); retval = execute_queues_cpsch(dqm, @@ -3746,8 +3754,11 @@ int suspend_queues(struct kfd_process *p, if (!per_device_suspended) { dqm_unlock(dqm); mutex_unlock(&p->event_mutex); - if (total_suspended) + if (total_suspended) { amdgpu_amdkfd_debug_mem_fence(dqm->dev->adev); + /* Heavy-weight TLB flush after MES suspends queues */ + kfd_flush_tlb(pdd); + } continue; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index ef1d1cb46152..4fe40e9fcfc8 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -1169,13 +1169,13 @@ int pqm_debugfs_mqds(struct seq_file *m, void *data) mqd_mgr = q->device->dqm->mqd_mgrs[mqd_type]; size = mqd_mgr->mqd_stride(mqd_mgr, &q->properties); - } - for (xcc = 0; xcc < num_xccs; xcc++) { - mqd = q->mqd + size * xcc; - r = mqd_mgr->debugfs_show_mqd(m, mqd); - if (r != 0) - break; + for (xcc = 0; xcc < num_xccs; xcc++) { + mqd = q->mqd + size * xcc; + r = mqd_mgr->debugfs_show_mqd(m, mqd); + if (r != 0) + break; + } } } 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 ec483276d753..2fe934036e36 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -3879,7 +3879,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_commit *state, continue; bundle->surface_updates[planes_count].surface = dc_plane; - if (new_pcrtc_state->color_mgmt_changed) { + if (new_pcrtc_state->color_mgmt_changed || new_plane_state->color_mgmt_changed) { bundle->surface_updates[planes_count].gamma = &dc_plane->gamma_correction; bundle->surface_updates[planes_count].in_transfer_func = &dc_plane->in_transfer_func; bundle->surface_updates[planes_count].gamut_remap_matrix = &dc_plane->gamut_remap_matrix; @@ -5698,6 +5698,10 @@ static bool should_reset_plane(struct drm_atomic_commit *state, if (new_crtc_state->color_mgmt_changed) return true; + /* Plane color pipeline or its colorop changes. */ + if (new_plane_state->color_mgmt_changed) + return true; + /* * On zpos change, planes need to be reordered by removing and re-adding * them one by one to the dc state, in order of descending zpos. diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_backlight.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_backlight.c index e61bbc310f33..b9e90ea449ca 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_backlight.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_backlight.c @@ -534,8 +534,12 @@ void amdgpu_dm_update_connector_ext_caps(struct amdgpu_dm_connector *aconnector) else if (!IS_ERR_OR_NULL(panel_backlight_quirk) && panel_backlight_quirk->force_pwm) caps->aux_support = false; - if (caps->aux_support) - aconnector->dc_link->backlight_control_type = BACKLIGHT_CONTROL_AMD_AUX; + if (caps->aux_support) { + if (aconnector->dc_link->dpcd_caps.panel_luminance_control) + aconnector->dc_link->backlight_control_type = BACKLIGHT_CONTROL_VESA_AUX; + else + aconnector->dc_link->backlight_control_type = BACKLIGHT_CONTROL_AMD_AUX; + } luminance_range = &conn_base->display_info.luminance_range; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c index 824ef3ce5de0..e13b96358208 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c @@ -2208,16 +2208,41 @@ int amdgpu_dm_plane_init(struct amdgpu_display_manager *dm, if (res) return res; - if (plane->type == DRM_PLANE_TYPE_OVERLAY && - plane_cap && plane_cap->per_pixel_alpha) { + /* Blend mode support varies on DCE generations according to HW caps + * and number of planes per CRTC. However, as current driver + * implementation only creates one primary and one cursor plane per + * CRTC for DCE (overlay is only created if + * DC_PLANE_TYPE_DCN_UNIVERSAL), the primary plane blend mode is + * ignored across DCE versions. Keep PREMULTI to avoid uAPI + * regressions: it was the default/mandatory mode for many years and, + * with no overlay plane, primary composes on top of a black + * background, where PREMULTI and PIXEL_NONE are equivalent. + */ + if (plane_cap && plane_cap->type != DC_PLANE_TYPE_DCN_UNIVERSAL) { + unsigned int blend_caps = BIT(DRM_MODE_BLEND_PIXEL_NONE) | + BIT(DRM_MODE_BLEND_PREMULTI); + + drm_plane_create_blend_mode_property(plane, blend_caps); + } else if ((plane->type == DRM_PLANE_TYPE_OVERLAY || + plane->type == DRM_PLANE_TYPE_PRIMARY) && + plane_cap && plane_cap->per_pixel_alpha) { unsigned int blend_caps = BIT(DRM_MODE_BLEND_PIXEL_NONE) | BIT(DRM_MODE_BLEND_PREMULTI) | BIT(DRM_MODE_BLEND_COVERAGE); - drm_plane_create_alpha_property(plane); drm_plane_create_blend_mode_property(plane, blend_caps); + + if (plane->type == DRM_PLANE_TYPE_OVERLAY) + drm_plane_create_alpha_property(plane); } + /* Cursor color format is set to CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA + * by default, so only advertise DRM_MODE_BLEND_PREMULTI blend mode for + * this type of plane. + */ + if (plane->type == DRM_PLANE_TYPE_CURSOR) + drm_plane_create_blend_mode_property(plane, BIT(DRM_MODE_BLEND_PREMULTI)); + if (plane->type == DRM_PLANE_TYPE_PRIMARY) { /* * Allow OVERLAY planes to be used as underlays by assigning an diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 7eaaf38cd9ab..fc9080f0c093 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -1797,7 +1797,11 @@ bool resource_can_pipe_disable_cursor(struct pipe_ctx *pipe_ctx) * pipe-split, merge together per same height. */ for (split_pipe = pipe_ctx->top_pipe; split_pipe; - split_pipe = split_pipe->top_pipe) + split_pipe = split_pipe->top_pipe) { + + if (split_pipe == test_pipe) + continue; + if (split_pipe->plane_state->layer_index == test_pipe->plane_state->layer_index) { struct rect r2_half; @@ -1809,6 +1813,7 @@ bool resource_can_pipe_disable_cursor(struct pipe_ctx *pipe_ctx) r2_bottom = min(r2_bottom, r2_half.y + r2_half.height); break; } + } if (r1.x >= r2.x && r1.y >= r2.y && r1_right <= r2_right && r1_bottom <= r2_bottom) return true; diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c index 66fe7f313ea3..62ca235cd649 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c @@ -320,6 +320,8 @@ static struct fixed31_32 interp_tf_pts(const struct fixed31_32 *output_tf_channe return value; } +#define NUM_DEGAMMA_REGIONS 9 + bool cm3_helper_translate_curve_to_degamma_hw_format( const struct dc_transfer_func *output_tf, struct pwl_params *lut_params) @@ -343,31 +345,15 @@ bool cm3_helper_translate_curve_to_degamma_hw_format( memset(lut_params, 0, sizeof(struct pwl_params)); memset(seg_distr, 0, sizeof(seg_distr)); - if (output_tf->tf == TRANSFER_FUNCTION_PQ || - output_tf->tf == TRANSFER_FUNCTION_SRGB) { - /* 9 segments - * segments are from 2^-9 to 0 - */ - const uint8_t SEG_COUNT = 9; - seg_distr[0] = 0; // Since we only have one point in darkest region - for (k = 1; k < SEG_COUNT; k++) - seg_distr[k] = k - 1; // 2^(k-1) points per region; halves as k decreases - - region_start = -SEG_COUNT; - region_end = 0; - } else { - /* 12 segments - * segments are from 2^-12 to 2^0 - * There are less than 256 points, for optimization - */ - const uint8_t SEG_COUNT = 12; - - for (i = 0; i < SEG_COUNT; i++) - seg_distr[i] = 4; + /* 9 segments + * segments are from 2^-9 to 2^0 + */ + seg_distr[0] = 0; // Since we only have one point in darkest region + for (k = 1; k < NUM_DEGAMMA_REGIONS; k++) + seg_distr[k] = k - 1; // 2^(k-1) points per region; halves as k decreases - region_start = -SEG_COUNT; - region_end = 0; - } + region_start = -NUM_DEGAMMA_REGIONS; + region_end = 0; for (i = region_end - region_start; i < MAX_REGIONS_NUMBER ; i++) seg_distr[i] = -1; diff --git a/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_core/dml2_core_dcn5_funcs_mode_programming.c b/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_core/dml2_core_dcn5_funcs_mode_programming.c index 8497eaea012e..297e21e7c68d 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_core/dml2_core_dcn5_funcs_mode_programming.c +++ b/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_core/dml2_core_dcn5_funcs_mode_programming.c @@ -1128,8 +1128,8 @@ static bool dcn5_mode_programming(struct dml2_core_calcs_mode_programming_ex *in CalculateWatermarks_params->USRRetrainingSupport = &mode_lib->mp.USRRetrainingSupport; CalculateWatermarks_params->temp_read_or_ppt_support = mode_lib->mp.temp_read_or_ppt_support; CalculateWatermarks_params->global_temp_read_or_ppt_supported = &mode_lib->mp.global_temp_read_or_ppt_supported; - CalculateWatermarks_params->VActiveLatencyHidingMargin = 0; - CalculateWatermarks_params->VActiveLatencyHidingUs = 0; + CalculateWatermarks_params->VActiveLatencyHidingMargin = NULL; + CalculateWatermarks_params->VActiveLatencyHidingUs = NULL; dcn5_calculate_watermarks_and_dram_speed_change_support(&mode_lib->scratch, CalculateWatermarks_params); diff --git a/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_core/dml2_core_shared_types.h b/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_core/dml2_core_shared_types.h index 8a371bd1a7a5..28f4a53d0617 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_core/dml2_core_shared_types.h +++ b/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_core/dml2_core_shared_types.h @@ -1819,8 +1819,8 @@ struct dml2_core_calcs_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport_param bool UnboundedRequestEnabled; unsigned int CompressedBufferSizeInkByte; bool max_outstanding_when_urgent_expected; - const unsigned int max_outstanding_requests; - const unsigned int max_request_size_bytes; + unsigned int max_outstanding_requests; + unsigned int max_request_size_bytes; const unsigned int *meta_row_height_l; const unsigned int *meta_row_height_c; const enum dml2_pstate_method *uclk_pstate_switch_modes; diff --git a/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_pmo/dml2_pmo_dcn6_stage_optimizers.c b/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_pmo/dml2_pmo_dcn6_stage_optimizers.c index 0b884a8661c8..6d6611a6b5a6 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_pmo/dml2_pmo_dcn6_stage_optimizers.c +++ b/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_pmo/dml2_pmo_dcn6_stage_optimizers.c @@ -1414,7 +1414,7 @@ static bool find_shift_for_valid_cache_id_assignment(const int *mcache_boundarie success = true; for (pipe_index = 0; pipe_index < pipe_count; pipe_index++) { if (!calculate_first_second_splitting(mcache_boundaries, num_boundaries, *shift, - pipe_vp_startx[pipe_index], pipe_vp_endx[pipe_index], 0, 0)) { + pipe_vp_startx[pipe_index], pipe_vp_endx[pipe_index], NULL, NULL)) { success = false; break; } diff --git a/drivers/gpu/drm/amd/display/dc/dml2_0/dml2_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2_0/dml2_translation_helper.c index 166f10b8862f..c82886323a51 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2_0/dml2_translation_helper.c +++ b/drivers/gpu/drm/amd/display/dc/dml2_0/dml2_translation_helper.c @@ -301,6 +301,7 @@ void dml2_init_socbb_params(struct dml2_context *dml2, const struct dc *in_dc, s out->smn_latency_us = 2; out->dispclk_dppclk_vco_speed_mhz = 3600; out->pct_ideal_dram_bw_after_urgent_pixel_only = 65.0; + out->gpuvm_min_page_size_kbytes = 4; break; diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c index dd854d992692..f43fc4b78a8d 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c @@ -103,6 +103,11 @@ static int get_estimated_bw(struct dc_link *link) { uint8_t bw_estimated_bw = 0; + if (link->dpia_bw_alloc_config.bw_granularity == 0) { + DC_LOG_ERROR("%s: BW granularity is zero!\n", __func__); + return 0; + } + core_link_read_dpcd( link, ESTIMATED_BW, diff --git a/drivers/gpu/drm/drm_atomic_state_helper.c b/drivers/gpu/drm/drm_atomic_state_helper.c index d90d1d7c9cf9..a2ef272e9f27 100644 --- a/drivers/gpu/drm/drm_atomic_state_helper.c +++ b/drivers/gpu/drm/drm_atomic_state_helper.c @@ -278,7 +278,14 @@ void __drm_atomic_helper_plane_state_init(struct drm_plane_state *plane_state, plane_state->rotation = DRM_MODE_ROTATE_0; plane_state->alpha = DRM_BLEND_ALPHA_OPAQUE; + plane_state->pixel_blend_mode = DRM_MODE_BLEND_PREMULTI; + if (plane->blend_mode_property) { + if (!drm_object_property_get_default_value(&plane->base, + plane->blend_mode_property, + &val)) + plane_state->pixel_blend_mode = val; + } if (plane->color_encoding_property) { if (!drm_object_property_get_default_value(&plane->base, diff --git a/drivers/gpu/drm/drm_atomic_uapi.c b/drivers/gpu/drm/drm_atomic_uapi.c index 1050dddadb17..5ea593b3a98e 100644 --- a/drivers/gpu/drm/drm_atomic_uapi.c +++ b/drivers/gpu/drm/drm_atomic_uapi.c @@ -1449,9 +1449,6 @@ static int prepare_signaling(struct drm_device *dev, if (arg->flags & DRM_MODE_PAGE_FLIP_EVENT) { struct drm_pending_vblank_event *e = crtc_state->event; - if (!file_priv) - continue; - ret = drm_event_reserve_init(dev, file_priv, &e->base, &e->event.base); if (ret) { @@ -1567,6 +1564,8 @@ static void complete_signaling(struct drm_device *dev, * to prevent a double free in drm_atomic_commit_clear. */ if (event && (event->base.fence || event->base.file_priv)) { + if (crtc_state->commit && crtc_state->commit->abort_completion) + drm_crtc_commit_put(crtc_state->commit); drm_event_cancel_free(dev, &event->base); crtc_state->event = NULL; } diff --git a/drivers/gpu/drm/drm_pagemap.c b/drivers/gpu/drm/drm_pagemap.c index 892b325fa99b..a0546955d0b9 100644 --- a/drivers/gpu/drm/drm_pagemap.c +++ b/drivers/gpu/drm/drm_pagemap.c @@ -384,6 +384,58 @@ next: } /** + * drm_pagemap_migrate_populate_src_pages() - Populate the source page array + * @pages: Array of source pages to populate + * @src_mpfn: Source array of migrate PFNs + * @dst_mpfn: Destination array of migrate PFNs + * @npages: Number of pages in the arrays + * + * Populate @pages with the device pages the copy callback is to read from. + * + * Entries are normally only populated at the head of each source folio, with + * the copy callback deriving the rest of the folio from the order recorded in + * the corresponding drm_pagemap_addr. That does not work where + * drm_pagemap_migrate_populate_ram_pfn() had to demote a higher-order source + * folio to order-0 destination folios: the drm_pagemap_addr entries are then + * per-page, and the copy callback needs a source page for each of them. + * Populate every entry for those ranges. + * + * Note that the source folio itself is only split later, by + * migrate_vma_pages() / migrate_device_pages(), so its order cannot be used to + * detect the demotion - the destination has to be inspected instead. + */ +static void drm_pagemap_migrate_populate_src_pages(struct page **pages, + unsigned long *src_mpfn, + unsigned long *dst_mpfn, + unsigned long npages) +{ + unsigned long i; + + for (i = 0; i < npages;) { + struct page *page = migrate_pfn_to_page(src_mpfn[i]); + unsigned int order = 0; + unsigned long j, nr; + + if (!page) { + i++; + continue; + } + + order = folio_order(page_folio(page)); + nr = NR_PAGES(order); + + if (order && !(dst_mpfn[i] & MIGRATE_PFN_COMPOUND)) { + for (j = 0; j < nr && i + j < npages; j++) + pages[i + j] = folio_page(page_folio(page), j); + } else { + pages[i] = page; + } + + i += nr; + } +} + +/** * drm_pagemap_migrate_unmap_pages() - Unmap pages previously mapped for GPU SVM migration * @dev: The device for which the pages were mapped * @migrate_pfn: Array of migrate pfns set up for the mapped pages. Used to @@ -875,6 +927,7 @@ static int drm_pagemap_migrate_populate_ram_pfn(struct vm_area_struct *vas, struct page *page = NULL, *src_page; struct folio *folio; unsigned int order = 0; + gfp_t gfp = GFP_HIGHUSER; if (!(src_mpfn[i] & MIGRATE_PFN_MIGRATE)) goto next; @@ -891,11 +944,51 @@ static int drm_pagemap_migrate_populate_ram_pfn(struct vm_area_struct *vas, order = folio_order(page_folio(src_page)); - /* TODO: Support fallback to single pages if THP allocation fails */ + /* + * A large source folio is always collected whole, at its head + * page, PMD aligned and flagged MIGRATE_PFN_COMPOUND: anything + * else is split before it reaches us, either by + * migrate_vma_collect_pmd() or, for the eviction path, by + * migrate_device_pfns(). Both the order-0 fallback below and + * drm_pagemap_migrate_populate_src_pages() rely on that, as + * they index the folio from @i. + */ + WARN_ON_ONCE(order && + (src_page != folio_page(page_folio(src_page), 0) || + !(src_mpfn[i] & MIGRATE_PFN_COMPOUND))); + + if (order) + gfp |= __GFP_NOWARN; + if (vas) - folio = vma_alloc_folio(GFP_HIGHUSER, order, vas, addr); + folio = vma_alloc_folio(gfp, order, vas, addr); else - folio = folio_alloc(GFP_HIGHUSER, order); + folio = folio_alloc(gfp, order); + + if (!folio && order) { + /* + * Higher-order allocation failed, fall back to + * order-0 allocations for the entire range covered + * by the original higher-order allocation, without + * setting MIGRATE_PFN_COMPOUND, until we move past + * that range. + */ + unsigned long nr = NR_PAGES(order); + unsigned long j; + + gfp &= ~__GFP_NOWARN; + for (j = 0; j < nr && i < npages; j++, i++, addr += PAGE_SIZE) { + folio = vas ? + vma_alloc_folio(gfp, 0, vas, addr) : + folio_alloc(gfp, 0); + if (!folio) + goto free_pages; + + page = folio_page(folio, 0); + mpfn[i] = migrate_pfn(page_to_pfn(page)); + } + continue; + } if (!folio) goto free_pages; @@ -940,11 +1033,11 @@ free_pages: if (!page) goto next_put; + order = folio_order(page_folio(page)); + put_page(page); mpfn[i] = 0; - order = folio_order(page_folio(page)); - next_put: i += NR_PAGES(order); } @@ -1103,11 +1196,116 @@ void drm_pagemap_put(struct drm_pagemap *dpagemap) EXPORT_SYMBOL(drm_pagemap_put); /** + * drm_pagemap_page_get_flags() - Read flags from a device-private folio + * @page: Pointer to a page of the device-private folio + * + * Return: The DRM_PAGEMAP_ZDD_FLAG_* bits encoded in zone_device_data. + */ +static unsigned long drm_pagemap_page_get_flags(struct page *page) +{ + struct folio *folio = page_folio(page); + + return (unsigned long)folio_zone_device_data(folio) & + DRM_PAGEMAP_ZDD_FLAG_MASK; +} + +/** + * drm_pagemap_page_set_flags() - Set flags on a device-private folio + * @page: Pointer to a page of the device-private folio + * @flags: DRM_PAGEMAP_ZDD_FLAG_* bits to set + * + * Preserve any flags already encoded alongside the ZDD pointer. + */ +static void drm_pagemap_page_set_flags(struct page *page, + unsigned long flags) +{ + struct folio *folio = page_folio(page); + unsigned long old; + + if (WARN_ON_ONCE(flags & ~DRM_PAGEMAP_ZDD_FLAG_MASK)) + return; + + old = (unsigned long)folio_zone_device_data(folio); + folio_set_zone_device_data(folio, (void *)(old | flags)); +} + +/** + * drm_pagemap_retire_migrated_pages() - Record migrated device-private folios + * @src_pfns: source array after migrate_vma_pages() or migrate_device_pages() + * @npages: number of entries in @src_pfns + * + * Flag device-private folios successfully migrated to RAM before finalize + * unlocks the sources. The migrated state is stored in the physical folio, so + * it survives later folio splits and subsequent migrations can skip it. + */ +static void drm_pagemap_retire_migrated_pages(unsigned long *src_pfns, + unsigned long npages) +{ + unsigned long i = 0; + + while (i < npages) { + struct page *page = migrate_pfn_to_page(src_pfns[i]); + unsigned long nr = 1; + + if (!page) { + i++; + continue; + } + + if (src_pfns[i] & MIGRATE_PFN_COMPOUND) + nr = folio_nr_pages(page_folio(page)); + + if ((src_pfns[i] & MIGRATE_PFN_MIGRATE) && + is_device_private_page(page)) + drm_pagemap_page_set_flags(page, + DRM_PAGEMAP_ZDD_FLAG_MIGRATED); + + i += nr; + } +} + +/** + * drm_pagemap_skip_retired_pages() - Skip retired device-private folios + * @src_pfns: MIGRATE_PFN-encoded source array + * @npages: number of entries in @src_pfns + * + * Skip source folios already migrated to RAM, identified by the migrated flag + * stored in the physical folio's zone_device_data. + */ +static void drm_pagemap_skip_retired_pages(unsigned long *src_pfns, + unsigned long npages) +{ + unsigned long i = 0; + + while (i < npages) { + struct page *page = migrate_pfn_to_page(src_pfns[i]); + unsigned long nr = 1; + + if (!page) { + i++; + continue; + } + + if (src_pfns[i] & MIGRATE_PFN_COMPOUND) + nr = folio_nr_pages(page_folio(page)); + + if ((src_pfns[i] & MIGRATE_PFN_MIGRATE) && + is_device_private_page(page) && + (drm_pagemap_page_get_flags(page) & + DRM_PAGEMAP_ZDD_FLAG_MIGRATED)) + src_pfns[i] &= ~MIGRATE_PFN_MIGRATE; + + i += nr; + } +} + +/** * drm_pagemap_evict_to_ram() - Evict GPU SVM range to RAM * @devmem_allocation: Pointer to the device memory allocation * - * Similar to __drm_pagemap_migrate_to_ram but does not require mmap lock and - * migration done via migrate_device_* functions. + * Similar to __drm_pagemap_migrate_to_ram(), but uses the + * migrate_device_* helpers and does not require the mmap lock. + * Device-private PFNs already migrated to RAM by either path are skipped. * * Return: 0 on success, negative error code on failure. */ @@ -1115,17 +1313,18 @@ int drm_pagemap_evict_to_ram(struct drm_pagemap_devmem *devmem_allocation) { const struct drm_pagemap_devmem_ops *ops = devmem_allocation->ops; struct drm_pagemap_iova_state state = {}; - unsigned long npages, mpages = 0; + unsigned long npages, mpages; struct page **pages; unsigned long *src, *dst; struct drm_pagemap_addr *pagemap_addr; void *buf; - int i, err = 0; + int err = 0; unsigned int retry_count = 2; npages = devmem_allocation->size >> PAGE_SHIFT; retry: + mpages = 0; if (!mmget_not_zero(devmem_allocation->mm)) return -EFAULT; @@ -1148,6 +1347,8 @@ retry: if (err) goto err_free; + drm_pagemap_skip_retired_pages(src, npages); + err = drm_pagemap_migrate_populate_ram_pfn(NULL, NULL, npages, &mpages, src, dst, 0); if (err || !mpages) @@ -1160,27 +1361,20 @@ retry: if (err) goto err_finalize; - for (i = 0; i < npages;) { - unsigned int order = 0; - - pages[i] = migrate_pfn_to_page(src[i]); - if (pages[i]) - order = folio_order(page_folio(pages[i])); - - i += NR_PAGES(order); - } + drm_pagemap_migrate_populate_src_pages(pages, src, dst, npages); err = ops->copy_to_ram(pages, pagemap_addr, npages, NULL); if (err) goto err_finalize; err_finalize: + drm_pagemap_migrate_unmap_pages(devmem_allocation->dev, pagemap_addr, dst, npages, + DMA_FROM_DEVICE, &state); if (err) drm_pagemap_migration_unlock_put_pages(npages, dst); migrate_device_pages(src, dst, npages); + drm_pagemap_retire_migrated_pages(src, npages); migrate_device_finalize(src, dst, npages); - drm_pagemap_migrate_unmap_pages(devmem_allocation->dev, pagemap_addr, dst, npages, - DMA_FROM_DEVICE, &state); err_free: kvfree(buf); @@ -1235,7 +1429,7 @@ static int __drm_pagemap_migrate_to_ram(struct vm_area_struct *vas, struct drm_pagemap_addr *pagemap_addr; unsigned long start, end; void *buf; - int i, err = 0; + int err = 0; zdd = drm_pagemap_page_zone_device_data(page); if (time_before64(get_jiffies_64(), zdd->devmem_allocation->timeslice_expiration)) @@ -1275,13 +1469,15 @@ static int __drm_pagemap_migrate_to_ram(struct vm_area_struct *vas, if (!migrate.cpages) goto err_free; + drm_pagemap_skip_retired_pages(migrate.src, npages); + ops = zdd->devmem_allocation->ops; dev = zdd->devmem_allocation->dev; err = drm_pagemap_migrate_populate_ram_pfn(vas, page, npages, &mpages, migrate.src, migrate.dst, start); - if (err) + if (err || !mpages) goto err_finalize; err = drm_pagemap_migrate_map_system_pages(dev, pagemap_addr, @@ -1290,29 +1486,23 @@ static int __drm_pagemap_migrate_to_ram(struct vm_area_struct *vas, if (err) goto err_finalize; - for (i = 0; i < npages;) { - unsigned int order = 0; - - pages[i] = migrate_pfn_to_page(migrate.src[i]); - if (pages[i]) - order = folio_order(page_folio(pages[i])); - - i += NR_PAGES(order); - } + drm_pagemap_migrate_populate_src_pages(pages, migrate.src, migrate.dst, + npages); err = ops->copy_to_ram(pages, pagemap_addr, npages, NULL); if (err) goto err_finalize; err_finalize: - if (err) - drm_pagemap_migration_unlock_put_pages(npages, migrate.dst); - migrate_vma_pages(&migrate); - migrate_vma_finalize(&migrate); if (dev) drm_pagemap_migrate_unmap_pages(dev, pagemap_addr, migrate.dst, npages, DMA_FROM_DEVICE, &state); + if (err) + drm_pagemap_migration_unlock_put_pages(npages, migrate.dst); + migrate_vma_pages(&migrate); + drm_pagemap_retire_migrated_pages(migrate.src, npages); + migrate_vma_finalize(&migrate); err_free: kvfree(buf); err_out: @@ -1360,13 +1550,19 @@ static vm_fault_t drm_pagemap_migrate_to_ram(struct vm_fault *vmf) static void drm_pagemap_folio_split(struct folio *orig_folio, struct folio *new_folio) { struct drm_pagemap_zdd *zdd; + unsigned long orig_data, new_data; if (!new_folio) return; new_folio->pgmap = orig_folio->pgmap; - zdd = folio_zone_device_data(orig_folio); - folio_set_zone_device_data(new_folio, drm_pagemap_zdd_get(zdd)); + + orig_data = (unsigned long)folio_zone_device_data(orig_folio); + zdd = (struct drm_pagemap_zdd *)(orig_data & ~DRM_PAGEMAP_ZDD_FLAG_MASK); + + new_data = (unsigned long)drm_pagemap_zdd_get(zdd); + new_data |= orig_data & DRM_PAGEMAP_ZDD_FLAG_MASK; + folio_set_zone_device_data(new_folio, (void *)new_data); } static const struct dev_pagemap_ops drm_pagemap_pagemap_ops = { diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index 9b44c78cd77f..fe3436d1235d 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -524,7 +524,7 @@ int drm_gem_prime_handle_to_fd(struct drm_device *dev, return PTR_ERR(dmabuf); } - fd_install(fd, dmabuf->file); + dma_buf_fd_install(dmabuf, fd); *prime_fd = fd; return 0; } diff --git a/drivers/gpu/drm/gud/gud_connector.c b/drivers/gpu/drm/gud/gud_connector.c index ea0cca58b7c8..8141c3a1e30a 100644 --- a/drivers/gpu/drm/gud/gud_connector.c +++ b/drivers/gpu/drm/gud/gud_connector.c @@ -396,8 +396,16 @@ static int gud_connector_add_tv_mode(struct gud_device *gdrm, struct drm_connect } num_modes = ret / GUD_CONNECTOR_TV_MODE_NAME_LEN; - for (i = 0; i < num_modes; i++) - modes[i] = &buf[i * GUD_CONNECTOR_TV_MODE_NAME_LEN]; + for (i = 0; i < num_modes; i++) { + char *mode = &buf[i * GUD_CONNECTOR_TV_MODE_NAME_LEN]; + + if (!memchr(mode, '\0', GUD_CONNECTOR_TV_MODE_NAME_LEN)) { + ret = -EIO; + goto free; + } + + modes[i] = mode; + } ret = drm_mode_create_tv_properties_legacy(connector->dev, num_modes, modes); free: diff --git a/drivers/gpu/drm/gud/gud_drv.c b/drivers/gpu/drm/gud/gud_drv.c index 89bd6ca36003..3a1b9e2a2eaa 100644 --- a/drivers/gpu/drm/gud/gud_drv.c +++ b/drivers/gpu/drm/gud/gud_drv.c @@ -289,6 +289,8 @@ static int gud_plane_add_properties(struct gud_device *gdrm) * but mask out any additions on future devices. */ val &= GUD_ROTATION_MASK; + if (!(val & GUD_ROTATION_0)) + continue; ret = drm_plane_create_rotation_property(&gdrm->plane, DRM_MODE_ROTATE_0, val); break; diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c index a53d88727177..a1a5720996b7 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.c +++ b/drivers/gpu/drm/i915/display/intel_cdclk.c @@ -2381,8 +2381,10 @@ static void bxt_sanitize_cdclk(struct intel_display *display) * dividers both syncing to an active pipe, or asynchronously * (PIPE_NONE). */ - cdctl &= ~bxt_cdclk_cd2x_pipe_mask(display); - cdctl |= bxt_cdclk_cd2x_pipe(display, INVALID_PIPE); + if (DISPLAY_VER(display) < 30) { + cdctl &= ~bxt_cdclk_cd2x_pipe_mask(display); + cdctl |= bxt_cdclk_cd2x_pipe(display, INVALID_PIPE); + } if (cdctl != expected) { if (DISPLAY_VER(display) < 20) { @@ -2713,8 +2715,8 @@ static void intel_set_cdclk(struct intel_display *display, } } -static bool dg2_power_well_count(struct intel_display *display, - const struct intel_cdclk_state *cdclk_state) +static int dg2_power_well_count(struct intel_display *display, + const struct intel_cdclk_state *cdclk_state) { return display->platform.dg2 ? hweight8(cdclk_state->active_pipes) : 0; } diff --git a/drivers/gpu/drm/i915/display/intel_cursor.c b/drivers/gpu/drm/i915/display/intel_cursor.c index 0673f16f6fd0..86bb96ac449b 100644 --- a/drivers/gpu/drm/i915/display/intel_cursor.c +++ b/drivers/gpu/drm/i915/display/intel_cursor.c @@ -530,13 +530,18 @@ static int i9xx_check_cursor(struct intel_crtc_state *crtc_state, } static void i9xx_cursor_disable_sel_fetch_arm(struct intel_dsb *dsb, - struct intel_plane *plane, - const struct intel_crtc_state *crtc_state) + struct intel_plane *plane) { struct intel_display *display = to_intel_display(plane); enum pipe pipe = plane->pipe; - if (!crtc_state->enable_psr2_sel_fetch) + /* + * Clear this whenever the hardware has selective fetch, not just when + * the current state uses it. The cursor may have been enabled with + * selective fetch earlier and had its enable bit orphaned when the + * feature was switched off. + */ + if (!HAS_PSR2_SEL_FETCH(display)) return; intel_de_write_dsb(display, dsb, SEL_FETCH_CUR_CTL(pipe), 0); @@ -586,7 +591,7 @@ static void i9xx_cursor_update_sel_fetch_arm(struct intel_dsb *dsb, if (crtc_state->enable_psr2_su_region_et) wa_16021440873(dsb, plane, crtc_state, plane_state); else - i9xx_cursor_disable_sel_fetch_arm(dsb, plane, crtc_state); + i9xx_cursor_disable_sel_fetch_arm(dsb, plane); } } @@ -695,7 +700,7 @@ static void i9xx_cursor_update_arm(struct intel_dsb *dsb, if (plane_state) i9xx_cursor_update_sel_fetch_arm(dsb, plane, crtc_state, plane_state); else - i9xx_cursor_disable_sel_fetch_arm(dsb, plane, crtc_state); + i9xx_cursor_disable_sel_fetch_arm(dsb, plane); if (plane->cursor.base != base || plane->cursor.size != fbc_ctl || diff --git a/drivers/gpu/drm/i915/display/intel_cx0_phy.c b/drivers/gpu/drm/i915/display/intel_cx0_phy.c index 452062417ce9..dbebd7210848 100644 --- a/drivers/gpu/drm/i915/display/intel_cx0_phy.c +++ b/drivers/gpu/drm/i915/display/intel_cx0_phy.c @@ -3233,7 +3233,8 @@ static void intel_cx0pll_enable(struct intel_encoder *encoder, * 8. Program DDI_CLK_VALFREQ to match intended DDI * clock frequency. */ - intel_de_write(display, DDI_CLK_VALFREQ(encoder->port), port_clock); + intel_de_write(display, DDI_CLK_VALFREQ(encoder->port), + intel_ddi_link_symbol_clock(encoder, port_clock)); /* * 9. Set PORT_CLOCK_CTL register PCLK PLL Request @@ -3406,7 +3407,7 @@ void intel_mtl_tbt_pll_enable_clock(struct intel_encoder *encoder, int port_cloc * clock frequency. */ intel_de_write(display, DDI_CLK_VALFREQ(encoder->port), - port_clock); + intel_ddi_link_symbol_clock(encoder, port_clock)); } void intel_mtl_pll_enable(struct intel_encoder *encoder, diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index b8985e1e0a81..02a53c9848e1 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -1529,6 +1529,17 @@ int intel_ddi_level(struct intel_encoder *encoder, return level; } +int intel_ddi_link_symbol_clock(struct intel_encoder *encoder, int clock) +{ + if (intel_encoder_is_dp(encoder)) + return intel_dp_link_symbol_clock(clock); + + if (intel_hdmi_is_frl(clock)) + return DIV_ROUND_CLOSEST(clock * 10, 18); + + return clock; +} + static void hsw_set_signal_levels(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state) diff --git a/drivers/gpu/drm/i915/display/intel_ddi.h b/drivers/gpu/drm/i915/display/intel_ddi.h index 580ecb09b8b6..239d5a403f91 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.h +++ b/drivers/gpu/drm/i915/display/intel_ddi.h @@ -81,6 +81,7 @@ void intel_ddi_sanitize_encoder_pll_mapping(struct intel_encoder *encoder); int intel_ddi_level(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, int lane); +int intel_ddi_link_symbol_clock(struct intel_encoder *encoder, int clock); void intel_ddi_update_active_dpll(struct intel_atomic_state *state, struct intel_encoder *encoder, struct intel_crtc *crtc); diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c index 3be1643f8d03..57daed0b0b36 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c @@ -765,10 +765,6 @@ static int mst_stream_compute_config(struct intel_atomic_state *state, if (ret) return ret; - ret = intel_pfit_compute_config(pipe_config, conn_state); - if (ret) - return ret; - for_each_joiner_candidate(connector, adjusted_mode, num_joined_pipes) { if (num_joined_pipes > 1) pipe_config->joiner_pipes = GENMASK(crtc->pipe + num_joined_pipes - 1, diff --git a/drivers/gpu/drm/i915/display/intel_lt_phy.c b/drivers/gpu/drm/i915/display/intel_lt_phy.c index 8fc6d230493f..86492651b01d 100644 --- a/drivers/gpu/drm/i915/display/intel_lt_phy.c +++ b/drivers/gpu/drm/i915/display/intel_lt_phy.c @@ -1976,7 +1976,8 @@ void intel_lt_phy_pll_enable(struct intel_encoder *encoder, * Change. We handle this step in bxt_set_cdclk(). */ /* 10. Program DDI_CLK_VALFREQ to match intended DDI clock frequency. */ - intel_de_write(display, DDI_CLK_VALFREQ(encoder->port), port_clock); + intel_de_write(display, DDI_CLK_VALFREQ(encoder->port), + intel_ddi_link_symbol_clock(encoder, port_clock)); /* 11. Program PORT_CLOCK_CTL[PCLK PLL Request LN0] = 1. */ intel_de_rmw(display, XELPDP_PORT_CLOCK_CTL(display, port), @@ -2023,7 +2024,8 @@ void intel_lt_phy_pll_enable(struct intel_encoder *encoder, lane_phy_pulse_status, lane_phy_pulse_status); } else { - intel_de_write(display, DDI_CLK_VALFREQ(encoder->port), port_clock); + intel_de_write(display, DDI_CLK_VALFREQ(encoder->port), + intel_ddi_link_symbol_clock(encoder, port_clock)); } /* diff --git a/drivers/gpu/drm/i915/display/skl_universal_plane.c b/drivers/gpu/drm/i915/display/skl_universal_plane.c index 07a683293352..5cda1ab90e40 100644 --- a/drivers/gpu/drm/i915/display/skl_universal_plane.c +++ b/drivers/gpu/drm/i915/display/skl_universal_plane.c @@ -879,13 +879,18 @@ skl_plane_disable_arm(struct intel_dsb *dsb, } static void icl_plane_disable_sel_fetch_arm(struct intel_dsb *dsb, - struct intel_plane *plane, - const struct intel_crtc_state *crtc_state) + struct intel_plane *plane) { struct intel_display *display = to_intel_display(plane); enum pipe pipe = plane->pipe; - if (!crtc_state->enable_psr2_sel_fetch) + /* + * Clear this whenever the hardware has selective fetch, not just when + * the current state uses it. The plane may have been enabled with + * selective fetch earlier and had its enable bit orphaned when the + * feature was switched off. + */ + if (!HAS_PSR2_SEL_FETCH(display)) return; intel_de_write_dsb(display, dsb, SEL_FETCH_PLANE_CTL(pipe, plane->id), 0); @@ -921,7 +926,7 @@ icl_plane_disable_arm(struct intel_dsb *dsb, skl_write_plane_wm(dsb, plane, crtc_state); - icl_plane_disable_sel_fetch_arm(dsb, plane, crtc_state); + icl_plane_disable_sel_fetch_arm(dsb, plane); if (plane_has_normalizer(plane)) intel_de_write_dsb(display, dsb, @@ -1641,7 +1646,7 @@ static void icl_plane_update_sel_fetch_arm(struct intel_dsb *dsb, intel_de_write_dsb(display, dsb, SEL_FETCH_PLANE_CTL(pipe, plane->id), SEL_FETCH_PLANE_CTL_ENABLE); else - icl_plane_disable_sel_fetch_arm(dsb, plane, crtc_state); + icl_plane_disable_sel_fetch_arm(dsb, plane); } static void diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index 82415af47d54..2f03f95945f1 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -958,6 +958,9 @@ static int i915_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) (struct intel_device_info *) ent->driver_data; int err; + if (!intel_info) + return -ENODEV; + if (intel_info->require_force_probe && !id_forced(pdev->device)) { dev_info(&pdev->dev, "Your graphics device %04x is not properly supported by i915 in this\n" diff --git a/drivers/gpu/drm/nouveau/include/nvkm/engine/disp.h b/drivers/gpu/drm/nouveau/include/nvkm/engine/disp.h index 7903d7470d19..01145db32c53 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/engine/disp.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/engine/disp.h @@ -87,4 +87,5 @@ int gp102_disp_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct int gv100_disp_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_disp **); int tu102_disp_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_disp **); int ga102_disp_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_disp **); +int gb202_disp_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_disp **); #endif diff --git a/drivers/gpu/drm/nouveau/nouveau_chan.c b/drivers/gpu/drm/nouveau/nouveau_chan.c index 598513f60449..f142f6310596 100644 --- a/drivers/gpu/drm/nouveau/nouveau_chan.c +++ b/drivers/gpu/drm/nouveau/nouveau_chan.c @@ -90,6 +90,14 @@ nouveau_channel_del(struct nouveau_channel **pchan) { struct nouveau_channel *chan = *pchan; if (chan) { + /* + * Drop the kill-event subscription first. Its handler + * dereferences chan->fence, which the fence context teardown + * below frees, so leaving it armed across the teardown leaves + * a window for a use-after-free. + */ + nvif_event_dtor(&chan->kill); + if (chan->fence) nouveau_fence(chan->cli->drm)->context_del(chan); @@ -100,7 +108,6 @@ nouveau_channel_del(struct nouveau_channel **pchan) nvif_object_dtor(&chan->nvsw); nvif_object_dtor(&chan->gart); nvif_object_dtor(&chan->vram); - nvif_event_dtor(&chan->kill); nvif_object_dtor(&chan->user); nvif_mem_dtor(&chan->mem_userd); nouveau_vma_del(&chan->sema.vma); diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index 9442ec6e1f6c..ad4570c50be7 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -267,7 +267,7 @@ static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf) nouveau_fence_new(&fence, dmem->migrate.chan); migrate_vma_pages(&args); nouveau_dmem_fence_done(&fence); - dma_unmap_page(drm->dev->dev, dma_info.dma_addr, PAGE_SIZE, + dma_unmap_page(drm->dev->dev, dma_info.dma_addr, dma_info.size, DMA_BIDIRECTIONAL); done: migrate_vma_finalize(&args); @@ -279,11 +279,25 @@ err: static void nouveau_dmem_folio_split(struct folio *head, struct folio *tail) { + struct nouveau_dmem_chunk *chunk; + struct nouveau_dmem *dmem; + if (tail == NULL) return; tail->pgmap = head->pgmap; tail->mapping = head->mapping; folio_set_zone_device_data(tail, folio_zone_device_data(head)); + + /* + * The split hands out a new independently-freeable folio that will + * later be released via nouveau_dmem_folio_free(); account for it so + * chunk->callocated stays balanced. + */ + chunk = nouveau_page_to_chunk(&head->page); + dmem = chunk->drm->dmem; + spin_lock(&dmem->lock); + chunk->callocated++; + spin_unlock(&dmem->lock); } static const struct dev_pagemap_ops nouveau_dmem_pagemap_ops = { @@ -772,7 +786,7 @@ static unsigned long nouveau_dmem_migrate_copy_one(struct nouveau_drm *drm, return mpfn; out_dma_unmap: - dma_unmap_page(dev, dma_info->dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL); + dma_unmap_page(dev, dma_info->dma_addr, dma_info->size, DMA_BIDIRECTIONAL); out_free_page: nouveau_dmem_page_free_locked(drm, dpage); out: diff --git a/drivers/gpu/drm/nouveau/nouveau_sgdma.c b/drivers/gpu/drm/nouveau/nouveau_sgdma.c index fa3b4ebf38a8..2bd0376193ae 100644 --- a/drivers/gpu/drm/nouveau/nouveau_sgdma.c +++ b/drivers/gpu/drm/nouveau/nouveau_sgdma.c @@ -72,9 +72,7 @@ nouveau_sgdma_create_ttm(struct ttm_buffer_object *bo, uint32_t page_flags) struct nouveau_sgdma_be *nvbe; enum ttm_caching caching; - if (nvbo->force_coherent) - caching = ttm_uncached; - else if (drm->agp.bridge) + if (nvbo->force_coherent || drm->agp.bridge) caching = ttm_write_combined; else caching = ttm_cached; diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c b/drivers/gpu/drm/nouveau/nouveau_uvmm.c index f5e4756b4de4..fc125fd44a9b 100644 --- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c +++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c @@ -1319,6 +1319,7 @@ nouveau_uvmm_bind_job_submit(struct nouveau_job *job, op->va.range); if (!op->reg || op->reg->dirty) { ret = -ENOENT; + op->reg = NULL; goto unwind_continue; } @@ -1327,6 +1328,7 @@ nouveau_uvmm_bind_job_submit(struct nouveau_job *job, op->va.range); if (IS_ERR(op->ops)) { ret = PTR_ERR(op->ops); + op->reg = NULL; goto unwind_continue; } @@ -1473,6 +1475,7 @@ unwind: op->va.range); break; case OP_UNMAP_SPARSE: + op->reg->dirty = false; __nouveau_uvma_region_insert(uvmm, op->reg); nouveau_uvmm_sm_unmap_prepare_unwind(uvmm, &op->new, op->ops); @@ -1489,7 +1492,8 @@ unwind: break; } - drm_gpuva_ops_free(&uvmm->base, op->ops); + if (!IS_ERR_OR_NULL(op->ops)) + drm_gpuva_ops_free(&uvmm->base, op->ops); op->ops = NULL; op->reg = NULL; } diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c index ea62dc97f118..96c8a5b29999 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c @@ -2846,7 +2846,7 @@ nv1b2_chipset = { .pci = { 0x00000001, gh100_pci_new }, .timer = { 0x00000001, gk20a_timer_new }, .vfn = { 0x00000001, ga100_vfn_new }, - .disp = { 0x00000001, ga102_disp_new }, + .disp = { 0x00000001, gb202_disp_new }, .fifo = { 0x00000001, ga102_fifo_new }, }; @@ -2862,7 +2862,7 @@ nv1b3_chipset = { .pci = { 0x00000001, gh100_pci_new }, .timer = { 0x00000001, gk20a_timer_new }, .vfn = { 0x00000001, ga100_vfn_new }, - .disp = { 0x00000001, ga102_disp_new }, + .disp = { 0x00000001, gb202_disp_new }, .fifo = { 0x00000001, ga102_fifo_new }, }; @@ -2878,7 +2878,7 @@ nv1b5_chipset = { .pci = { 0x00000001, gh100_pci_new }, .timer = { 0x00000001, gk20a_timer_new }, .vfn = { 0x00000001, ga100_vfn_new }, - .disp = { 0x00000001, ga102_disp_new }, + .disp = { 0x00000001, gb202_disp_new }, .fifo = { 0x00000001, ga102_fifo_new }, }; @@ -2894,7 +2894,7 @@ nv1b6_chipset = { .pci = { 0x00000001, gh100_pci_new }, .timer = { 0x00000001, gk20a_timer_new }, .vfn = { 0x00000001, ga100_vfn_new }, - .disp = { 0x00000001, ga102_disp_new }, + .disp = { 0x00000001, gb202_disp_new }, .fifo = { 0x00000001, ga102_fifo_new }, }; @@ -2910,7 +2910,7 @@ nv1b7_chipset = { .pci = { 0x00000001, gh100_pci_new }, .timer = { 0x00000001, gk20a_timer_new }, .vfn = { 0x00000001, ga100_vfn_new }, - .disp = { 0x00000001, ga102_disp_new }, + .disp = { 0x00000001, gb202_disp_new }, .fifo = { 0x00000001, ga102_fifo_new }, }; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild index e1aecd3fe96c..98d6ca5ac311 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild @@ -27,6 +27,7 @@ nvkm-y += nvkm/engine/disp/gp102.o nvkm-y += nvkm/engine/disp/gv100.o nvkm-y += nvkm/engine/disp/tu102.o nvkm-y += nvkm/engine/disp/ga102.o +nvkm-y += nvkm/engine/disp/gb202.o nvkm-y += nvkm/engine/disp/udisp.o nvkm-y += nvkm/engine/disp/uconn.o diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ga102.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ga102.c index ab0a85c92430..820834b5ee9b 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ga102.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ga102.c @@ -144,12 +144,23 @@ ga102_disp = { }, }; +static const struct nvkm_disp_func +ga102_gsp_disp = { + .uevent = &gv100_disp_chan_uevent, + .ramht_size = 0x2000, + .gsp.intr = tu102_disp_intr, + .gsp.head = &tu102_gsp_head, + .gsp.hdmi_gcp = tu102_sor_hdmi_gcp, + .gsp.hdmi_infoframe_avi = gv100_sor_hdmi_infoframe_avi, + .gsp.hdmi_infoframe_vsi = gv100_sor_hdmi_infoframe_vsi, +}; + int ga102_disp_new(struct nvkm_device *device, enum nvkm_subdev_type type, int inst, struct nvkm_disp **pdisp) { if (nvkm_gsp_rm(device->gsp)) - return r535_disp_new(&ga102_disp, device, type, inst, pdisp); + return r535_disp_new(&ga102_gsp_disp, device, type, inst, pdisp); return nvkm_disp_new_(&ga102_disp, device, type, inst, pdisp); } diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gb202.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gb202.c new file mode 100644 index 000000000000..d0360610f9fa --- /dev/null +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gb202.c @@ -0,0 +1,191 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright 2026 Valve Corp. + */ +#include "priv.h" +#include "head.h" +#include "ior.h" + +#include <subdev/timer.h> + +/* GB20x (NVD5.0) reorganised the SF HDMI packet units. The AVI unit is + * unchanged from GV100, but the legacy VSI unit is gone. Vendor infoframes + * are sent through the shared generic infoframe units instead. Register + * layout per NVIDIA's clc971.h/clca71.h, programming sequence per + * nvhdmipkt_C971.c:programAdvancedInfoframeC971(). + */ +static void +gb202_sor_hdmi_infoframe_vsi(struct nvkm_ior *ior, int head, void *data, u32 size) +{ + struct nvkm_device *device = ior->disp->engine.subdev.device; + const u32 hoff = head * 0x400; + /* Generic infoframe unit 1, the slot NVIDIA's driver uses for the VSI. */ + const u32 ctrl = 0x6f0138 + hoff; + u8 buf[36] = {}; + int i; + + /* Disable the unit and wait for it to go idle. */ + nvkm_mask(device, ctrl, 0x00000001, 0x00000000); + if (nvkm_msec(device, 2000, + if (!(nvkm_rd32(device, ctrl) & 0x00400000)) + break; + ) < 0) + return; + + if (!size) + return; + + /* Clear SENT status, and point the data port at unit 1's slot. */ + nvkm_mask(device, ctrl, 0x00800000, 0x00800000); + nvkm_wr32(device, 0x6f03f0 + hoff, 0x00000001); + + /* The data port takes the raw packet, except that a zero is inserted + * in HB3 after the three header bytes. A slot is 9 dwords (HB0-3 plus + * up to 32 payload bytes). An HDMI infoframe carries at most PB0-27, + * so the tail stays zero, and we always write the whole slot. + */ + size = min_t(u32, size, 31); + memcpy(buf, data, min_t(u32, size, 3)); + if (size > 3) + memcpy(&buf[4], (u8 *)data + 3, size - 3); + + for (i = 0; i < 36; i += 4) { + nvkm_wr32(device, 0x6f03f4 + hoff, buf[i + 0] | buf[i + 1] << 8 | + buf[i + 2] << 16 | + (u32)buf[i + 3] << 24); + } + + /* No flip ID or scanline matching. */ + nvkm_wr32(device, 0x6f013c + hoff, 0x00000000); + + /* ENABLE | RUN_MODE=ALWAYS | LOC=VBLANK | OFFSET=1 | SIZE=0. */ + nvkm_wr32(device, ctrl, 0x00000041); + + /* Audio priority low (the init value). */ + nvkm_wr32(device, 0x6f03f8 + hoff, 0x00000002); +} + +/* General Control Packet AVMute bracket. The GCP unit moved to slot 1 on + * NVD5.0. Only SB0 (the AVMute bit) is ours to write so we must not do a + * full write here: SB1 carries the deep-color CD/PP fields, and SB1_CTRL + * (bit 24, new with clc871.h) controls where their generation happens (HW + * or driver) on these chips, with the default being HW. + */ +static void +gb202_sor_hdmi_gcp(struct nvkm_ior *sor, int head, bool enable) +{ + struct nvkm_device *device = sor->disp->engine.subdev.device; + const u32 hdmi = head * 0x400; + + nvkm_mask(device, 0x6f0040 + hdmi, 0x00000001, 0x00000000); + nvkm_mask(device, 0x6f004c + hdmi, 0x000000ff, !enable ? 0x00000001 : + 0x00000010); + nvkm_mask(device, 0x6f0040 + hdmi, 0x00000001, 0x00000001); +} + +/* Same core-channel state mirror as gv100_head_state() (assembly at 0x680000, + * armed at +0x8000, per-head method offsets unchanged), but NVD5.0 spaces + * heads 0x800 apart (see NVCA7D_HEAD_SET_*(a) in clca7d.h). + */ +static void +gb202_head_state(struct nvkm_head *head, struct nvkm_head_state *state) +{ + struct nvkm_device *device = head->disp->engine.subdev.device; + const u32 hoff = (state == &head->arm) * 0x8000 + head->id * 0x800; + u32 data; + + data = nvkm_rd32(device, 0x682064 + hoff); + state->vtotal = (data & 0xffff0000) >> 16; + state->htotal = (data & 0x0000ffff); + data = nvkm_rd32(device, 0x682068 + hoff); + state->vsynce = (data & 0xffff0000) >> 16; + state->hsynce = (data & 0x0000ffff); + data = nvkm_rd32(device, 0x68206c + hoff); + state->vblanke = (data & 0xffff0000) >> 16; + state->hblanke = (data & 0x0000ffff); + data = nvkm_rd32(device, 0x682070 + hoff); + state->vblanks = (data & 0xffff0000) >> 16; + state->hblanks = (data & 0x0000ffff); + /* Bit 31 is ADJ1000DIV1001, not a HERTZ bit. We don't have enough bits + * to add the full clock in hz on Blackwell (35 bits), but state->hz + * is unused and obsolete under GSP so this is fine. + */ + state->hz = nvkm_rd32(device, 0x68200c + hoff) & 0x7fffffff; + + data = nvkm_rd32(device, 0x682004 + hoff); + switch ((data & 0x000000f0) >> 4) { + case 5: state->or.depth = 30; break; + case 4: state->or.depth = 24; break; + case 1: state->or.depth = 18; break; + default: + state->or.depth = 18; + WARN_ON(1); + break; + } +} + +/* NVD5.0 (GB20x and later) moved the RM head-timing interrupt enable to + * the low-latency vector's EN1 block. The event latch is unchanged. + */ +static void +gb202_head_vblank_put(struct nvkm_head *head) +{ + struct nvkm_device *device = head->disp->engine.subdev.device; + + nvkm_mask(device, 0x611ef0 + (head->id * 4), 0x00000002, 0x00000000); +} + +static void +gb202_head_vblank_get(struct nvkm_head *head) +{ + struct nvkm_device *device = head->disp->engine.subdev.device; + + nvkm_wr32(device, 0x611800 + (head->id * 4), 0x00000002); + nvkm_mask(device, 0x611ef0 + (head->id * 4), 0x00000002, 0x00000002); +} + +static irqreturn_t +gb202_disp_intr(struct nvkm_inth *inth) +{ + struct nvkm_disp *disp = container_of(inth, typeof(*disp), engine.subdev.inth); + irqreturn_t ret = tu102_disp_intr(inth); + + /* The FE interrupt vectors are message-based on NVD5.0. Re-arm the + * low-latency vector so it fires again for any event that latched + * while we were servicing. + */ + nvkm_wr32(disp->engine.subdev.device, 0x611f34, 0x00000001); + return ret; +} + +static const struct nvkm_head_func +gb202_gsp_head = { + .state = gb202_head_state, + .rgpos = gv100_head_rgpos, + .vblank_get = gb202_head_vblank_get, + .vblank_put = gb202_head_vblank_put, +}; + +/* GB20x is GSP-only. This table supplies the register programming the + * GSP-RM display path needs from the chip. + */ +static const struct nvkm_disp_func +gb202_gsp_disp = { + .uevent = &gv100_disp_chan_uevent, + .ramht_size = 0x2000, + /* Head timing arrives on the dedicated low-latency vector. */ + .gsp.intr = gb202_disp_intr, + .gsp.intr_low_latency = true, + .gsp.head = &gb202_gsp_head, + .gsp.hdmi_gcp = gb202_sor_hdmi_gcp, + /* The legacy AVI unit is unchanged on GB20x. */ + .gsp.hdmi_infoframe_avi = gv100_sor_hdmi_infoframe_avi, + .gsp.hdmi_infoframe_vsi = gb202_sor_hdmi_infoframe_vsi, +}; + +int +gb202_disp_new(struct nvkm_device *device, enum nvkm_subdev_type type, int inst, + struct nvkm_disp **pdisp) +{ + return r535_disp_new(&gb202_gsp_disp, device, type, inst, pdisp); +} diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/head.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/head.h index b642729c254f..5976498da909 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/head.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/head.h @@ -56,6 +56,8 @@ int gv100_head_new(struct nvkm_disp *, int id); void gv100_head_state(struct nvkm_head *head, struct nvkm_head_state *state); void gv100_head_rgpos(struct nvkm_head *head, u16 *hline, u16 *vline); +extern const struct nvkm_head_func tu102_gsp_head; + #define HEAD_MSG(h,l,f,a...) do { \ struct nvkm_head *_h = (h); \ nvkm_##l(&_h->disp->engine.subdev, "head-%d: "f"\n", _h->id, ##a); \ diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h index 3ba04bead2f9..5d682a774f2d 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h @@ -194,6 +194,7 @@ void gv100_sor_dp_audio_sym(struct nvkm_ior *, int, u16, u32); void gv100_sor_dp_watermark(struct nvkm_ior *, int, u8); extern const struct nvkm_ior_func_hda gv100_sor_hda; +void tu102_sor_hdmi_gcp(struct nvkm_ior *, int, bool); void tu102_sor_dp_vcpi(struct nvkm_ior *, int, u8, u8, u16, u16); int nv50_pior_cnt(struct nvkm_disp *, unsigned long *); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/priv.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/priv.h index a3fd7cb7c488..fde321dbd7c8 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/priv.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/priv.h @@ -5,6 +5,8 @@ #include <engine/disp.h> #include <core/enum.h> struct nvkm_head; +struct nvkm_head_func; +struct nvkm_ior; struct nvkm_outp; struct dcb_output; @@ -34,6 +36,20 @@ struct nvkm_disp_func { int (*new)(struct nvkm_disp *, int id); } wndw, head, dac, sor, pior; + /* Register programming that the GSP-RM display path (rm/r535) needs from + * the chip, everything else on that path goes through RM. The hooks are + * called unconditionally and the head table is handed to nvkm_head_new_(). + */ + struct { + irqreturn_t (*intr)(struct nvkm_inth *); + /* Head-timing interrupts arrive on a second DISP vector. */ + bool intr_low_latency; + const struct nvkm_head_func *head; + void (*hdmi_gcp)(struct nvkm_ior *, int head, bool enable); + void (*hdmi_infoframe_avi)(struct nvkm_ior *, int head, void *data, u32 size); + void (*hdmi_infoframe_vsi)(struct nvkm_ior *, int head, void *data, u32 size); + } gsp; + u16 ramht_size; struct nvkm_sclass root; @@ -72,6 +88,7 @@ int gv100_disp_wndw_cnt(struct nvkm_disp *, unsigned long *); int gv100_disp_caps_new(const struct nvkm_oclass *, void *, u32, struct nvkm_object **); int tu102_disp_init(struct nvkm_disp *); +irqreturn_t tu102_disp_intr(struct nvkm_inth *); void nv50_disp_dptmds_war_2(struct nvkm_disp *, struct dcb_output *); void nv50_disp_dptmds_war_3(struct nvkm_disp *, struct dcb_output *); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c index dcb9f8ba374c..f6c163072ff6 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c @@ -30,6 +30,21 @@ #include <nvif/class.h> +/* General Control Packet: bracket an audio enable/disable with AVMute + * through the legacy GCP SF unit. Used by the GSP-RM path, which sends the + * equivalent packet via RM as well but keeps the direct write in sync. + */ +void +tu102_sor_hdmi_gcp(struct nvkm_ior *sor, int head, bool enable) +{ + struct nvkm_device *device = sor->disp->engine.subdev.device; + const u32 hdmi = head * 0x400; + + nvkm_mask(device, 0x6f00c0 + hdmi, 0x00000001, 0x00000000); + nvkm_wr32(device, 0x6f00cc + hdmi, !enable ? 0x00000001 : 0x00000010); + nvkm_mask(device, 0x6f00c0 + hdmi, 0x00000001, 0x00000001); +} + void tu102_sor_dp_vcpi(struct nvkm_ior *sor, int head, u8 slot, u8 slot_nr, u16 pbn, u16 aligned) { @@ -104,6 +119,64 @@ tu102_sor_new(struct nvkm_disp *disp, int id) return nvkm_ior_new_(&tu102_sor, disp, SOR, id, hda & BIT(id)); } +/* The GSP-RM display path leaves head-timing (vblank) interrupts and their + * enables to us. These program the RM head-timing line (bit 1 of the + * per-head enable, not the bit nvkm's own gv100 path uses). + */ +static void +tu102_head_vblank_put(struct nvkm_head *head) +{ + struct nvkm_device *device = head->disp->engine.subdev.device; + + nvkm_mask(device, 0x611d80 + (head->id * 4), 0x00000002, 0x00000000); +} + +static void +tu102_head_vblank_get(struct nvkm_head *head) +{ + struct nvkm_device *device = head->disp->engine.subdev.device; + + nvkm_wr32(device, 0x611800 + (head->id * 4), 0x00000002); + nvkm_mask(device, 0x611d80 + (head->id * 4), 0x00000002, 0x00000002); +} + +const struct nvkm_head_func +tu102_gsp_head = { + .state = gv100_head_state, + .rgpos = gv100_head_rgpos, + .vblank_get = tu102_head_vblank_get, + .vblank_put = tu102_head_vblank_put, +}; + +static void +tu102_disp_intr_head_timing(struct nvkm_disp *disp, int head) +{ + struct nvkm_subdev *subdev = &disp->engine.subdev; + struct nvkm_device *device = subdev->device; + u32 stat = nvkm_rd32(device, 0x611c00 + (head * 0x04)); + + if (stat & 0x00000002) { + nvkm_disp_vblank(disp, head); + + nvkm_wr32(device, 0x611800 + (head * 0x04), 0x00000002); + } +} + +irqreturn_t +tu102_disp_intr(struct nvkm_inth *inth) +{ + struct nvkm_disp *disp = container_of(inth, typeof(*disp), engine.subdev.inth); + struct nvkm_subdev *subdev = &disp->engine.subdev; + struct nvkm_device *device = subdev->device; + unsigned long mask = nvkm_rd32(device, 0x611ec0) & 0x000000ff; + int head; + + for_each_set_bit(head, &mask, 8) + tu102_disp_intr_head_timing(disp, head); + + return IRQ_HANDLED; +} + int tu102_disp_init(struct nvkm_disp *disp) { @@ -230,12 +303,23 @@ tu102_disp = { }, }; +static const struct nvkm_disp_func +tu102_gsp_disp = { + .uevent = &gv100_disp_chan_uevent, + .ramht_size = 0x2000, + .gsp.intr = tu102_disp_intr, + .gsp.head = &tu102_gsp_head, + .gsp.hdmi_gcp = tu102_sor_hdmi_gcp, + .gsp.hdmi_infoframe_avi = gv100_sor_hdmi_infoframe_avi, + .gsp.hdmi_infoframe_vsi = gv100_sor_hdmi_infoframe_vsi, +}; + int tu102_disp_new(struct nvkm_device *device, enum nvkm_subdev_type type, int inst, struct nvkm_disp **pdisp) { if (nvkm_gsp_rm(device->gsp)) - return r535_disp_new(&tu102_disp, device, type, inst, pdisp); + return r535_disp_new(&tu102_gsp_disp, device, type, inst, pdisp); return nvkm_disp_new_(&tu102_disp, device, type, inst, pdisp); } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/disp.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/disp.c index e77733a5d9c3..f5f22173fc2c 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/disp.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/disp.c @@ -400,16 +400,16 @@ r535_sor_dp_audio(struct nvkm_ior *sor, int head, bool enable) r535_sor_dp_audio_mute(sor, false); } -static void -r535_sor_dp_vcpi(struct nvkm_ior *sor, int head, u8 slot, u8 slot_nr, u16 pbn, u16 aligned_pbn) +static int +r535_dp_vcpi(struct nvkm_ior *sor, int head, u8 slot, u8 slot_nr, u16 pbn, u16 aligned_pbn) { struct nvkm_disp *disp = sor->disp; struct NV0073_CTRL_CMD_DP_CONFIG_STREAM_PARAMS *ctrl; ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom, NV0073_CTRL_CMD_DP_CONFIG_STREAM, sizeof(*ctrl)); - if (WARN_ON(IS_ERR(ctrl))) - return; + if (IS_ERR(ctrl)) + return PTR_ERR(ctrl); ctrl->subDeviceInstance = 0; ctrl->head = head; @@ -429,12 +429,20 @@ r535_sor_dp_vcpi(struct nvkm_ior *sor, int head, u8 slot, u8 slot_nr, u16 pbn, u ctrl->MST.sendACT = 0; ctrl->MST.singleHeadMSTPipeline = 0; ctrl->MST.bEnableAudioOverRightPanel = 0; - WARN_ON(nvkm_gsp_rm_ctrl_wr(&disp->rm.objcom, ctrl)); + return nvkm_gsp_rm_ctrl_wr(&disp->rm.objcom, ctrl); +} + +static void +r535_sor_dp_vcpi(struct nvkm_ior *sor, int head, u8 slot, u8 slot_nr, u16 pbn, u16 aligned_pbn) +{ + const struct nvkm_rm_api *rmapi = sor->disp->engine.subdev.device->gsp->rm->api; + + WARN_ON(rmapi->disp->dp.vcpi(sor, head, slot, slot_nr, pbn, aligned_pbn)); } static int -r535_sor_dp_sst(struct nvkm_ior *sor, int head, bool ef, - u32 watermark, u32 hblanksym, u32 vblanksym) +r535_dp_sst(struct nvkm_ior *sor, int head, bool ef, + u32 watermark, u32 hblanksym, u32 vblanksym) { struct nvkm_disp *disp = sor->disp; struct NV0073_CTRL_CMD_DP_CONFIG_STREAM_PARAMS *ctrl; @@ -461,6 +469,15 @@ r535_sor_dp_sst(struct nvkm_ior *sor, int head, bool ef, return nvkm_gsp_rm_ctrl_wr(&disp->rm.objcom, ctrl); } +static int +r535_sor_dp_sst(struct nvkm_ior *sor, int head, bool ef, + u32 watermark, u32 hblanksym, u32 vblanksym) +{ + const struct nvkm_rm_api *rmapi = sor->disp->engine.subdev.device->gsp->rm->api; + + return rmapi->disp->dp.sst(sor, head, ef, watermark, hblanksym, vblanksym); +} + static const struct nvkm_ior_func_dp r535_sor_dp = { .sst = r535_sor_dp_sst, @@ -545,16 +562,21 @@ r535_sor_hdmi_ctrl_audio(struct nvkm_outp *outp, bool enable) static void r535_sor_hdmi_audio(struct nvkm_ior *sor, int head, bool enable) { - struct nvkm_device *device = sor->disp->engine.subdev.device; - const u32 hdmi = head * 0x400; - r535_sor_hdmi_ctrl_audio(sor->asy.outp, enable); r535_sor_hdmi_ctrl_audio_mute(sor->asy.outp, !enable); + sor->disp->func->gsp.hdmi_gcp(sor, head, enable); +} + +static void +r535_sor_hdmi_infoframe_avi(struct nvkm_ior *sor, int head, void *data, u32 size) +{ + sor->disp->func->gsp.hdmi_infoframe_avi(sor, head, data, size); +} - /* General Control (GCP). */ - nvkm_mask(device, 0x6f00c0 + hdmi, 0x00000001, 0x00000000); - nvkm_wr32(device, 0x6f00cc + hdmi, !enable ? 0x00000001 : 0x00000010); - nvkm_mask(device, 0x6f00c0 + hdmi, 0x00000001, 0x00000001); +static void +r535_sor_hdmi_infoframe_vsi(struct nvkm_ior *sor, int head, void *data, u32 size) +{ + sor->disp->func->gsp.hdmi_infoframe_vsi(sor, head, data, size); } static void @@ -582,8 +604,8 @@ r535_sor_hdmi = { .ctrl = r535_sor_hdmi_ctrl, .scdc = r535_sor_hdmi_scdc, /*TODO: SF_USER -> KMS. */ - .infoframe_avi = gv100_sor_hdmi_infoframe_avi, - .infoframe_vsi = gv100_sor_hdmi_infoframe_vsi, + .infoframe_avi = r535_sor_hdmi_infoframe_avi, + .infoframe_vsi = r535_sor_hdmi_infoframe_vsi, .audio = r535_sor_hdmi_audio, }; @@ -608,31 +630,6 @@ r535_sor_cnt(struct nvkm_disp *disp, unsigned long *pmask) return 4; } -static void -r535_head_vblank_put(struct nvkm_head *head) -{ - struct nvkm_device *device = head->disp->engine.subdev.device; - - nvkm_mask(device, 0x611d80 + (head->id * 4), 0x00000002, 0x00000000); -} - -static void -r535_head_vblank_get(struct nvkm_head *head) -{ - struct nvkm_device *device = head->disp->engine.subdev.device; - - nvkm_wr32(device, 0x611800 + (head->id * 4), 0x00000002); - nvkm_mask(device, 0x611d80 + (head->id * 4), 0x00000002, 0x00000002); -} - -static const struct nvkm_head_func -r535_head = { - .state = gv100_head_state, - .rgpos = gv100_head_rgpos, - .vblank_get = r535_head_vblank_get, - .vblank_put = r535_head_vblank_put, -}; - static struct nvkm_conn * r535_conn_new(struct nvkm_disp *disp, u32 id) { @@ -1405,35 +1402,6 @@ r535_disp_event = { }; static void -r535_disp_intr_head_timing(struct nvkm_disp *disp, int head) -{ - struct nvkm_subdev *subdev = &disp->engine.subdev; - struct nvkm_device *device = subdev->device; - u32 stat = nvkm_rd32(device, 0x611c00 + (head * 0x04)); - - if (stat & 0x00000002) { - nvkm_disp_vblank(disp, head); - - nvkm_wr32(device, 0x611800 + (head * 0x04), 0x00000002); - } -} - -static irqreturn_t -r535_disp_intr(struct nvkm_inth *inth) -{ - struct nvkm_disp *disp = container_of(inth, typeof(*disp), engine.subdev.inth); - struct nvkm_subdev *subdev = &disp->engine.subdev; - struct nvkm_device *device = subdev->device; - unsigned long mask = nvkm_rd32(device, 0x611ec0) & 0x000000ff; - int head; - - for_each_set_bit(head, &mask, 8) - r535_disp_intr_head_timing(disp, head); - - return IRQ_HANDLED; -} - -static void r535_disp_fini(struct nvkm_disp *disp, bool suspend) { if (!disp->engine.subdev.use.enabled) @@ -1659,7 +1627,7 @@ r535_disp_oneinit(struct nvkm_disp *disp) nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); for_each_set_bit(i, &disp->head.mask, disp->head.nr) { - ret = nvkm_head_new_(&r535_head, disp, i); + ret = nvkm_head_new_(disp->func->gsp.head, disp, i); if (ret) return ret; } @@ -1703,12 +1671,20 @@ r535_disp_oneinit(struct nvkm_disp *disp) if (ret) return ret; - ret = nvkm_gsp_intr_stall(gsp, disp->engine.subdev.type, disp->engine.subdev.inst); + /* Chips that raise head-timing interrupts on a separate low-latency + * vector report it as a second DISP interrupt table entry, exposed + * as instance 1 by the RM engine-index translation (see + * r570_gsp_xlat_mc_engine_idx()). Their high-latency vector + * (instance 0) is left unhandled as no event nouveau enables is + * routed to it, and without a handler it stays masked. + */ + ret = nvkm_gsp_intr_stall(gsp, disp->engine.subdev.type, + disp->func->gsp.intr_low_latency ? 1 : disp->engine.subdev.inst); if (ret < 0) return ret; ret = nvkm_inth_add(&device->vfn->intr, ret, NVKM_INTR_PRIO_NORMAL, &disp->engine.subdev, - r535_disp_intr, &disp->engine.subdev.inth); + disp->func->gsp.intr, &disp->engine.subdev.inth); if (ret) return ret; @@ -1741,6 +1717,7 @@ r535_disp_new(const struct nvkm_disp_func *hw, struct nvkm_device *device, rm->uevent = hw->uevent; rm->sor.cnt = r535_sor_cnt; rm->sor.new = r535_sor_new; + rm->gsp = hw->gsp; rm->ramht_size = hw->ramht_size; rm->root.oclass = gpu->disp.class.root; @@ -1782,6 +1759,8 @@ r535_disp = { .dp = { .get_caps = r535_dp_get_caps, .set_indexed_link_rates = r535_dp_set_indexed_link_rates, + .sst = r535_dp_sst, + .vcpi = r535_dp_vcpi, }, .chan = { .set_pushbuf = r535_disp_chan_set_pushbuf, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/disp.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/disp.c index a96e31c2d80b..8a23837f356e 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/disp.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/disp.c @@ -5,6 +5,7 @@ #include <rm/rm.h> #include <engine/disp.h> +#include <engine/disp/ior.h> #include <engine/disp/outp.h> #include "nvhw/drf.h" @@ -75,6 +76,67 @@ r570_disp_chan_set_pushbuf(struct nvkm_disp *disp, s32 oclass, int inst, struct } static int +r570_dp_vcpi(struct nvkm_ior *sor, int head, u8 slot, u8 slot_nr, u16 pbn, u16 aligned_pbn) +{ + struct nvkm_disp *disp = sor->disp; + NV0073_CTRL_CMD_DP_CONFIG_STREAM_PARAMS *ctrl; + + ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom, + NV0073_CTRL_CMD_DP_CONFIG_STREAM, sizeof(*ctrl)); + if (IS_ERR(ctrl)) + return PTR_ERR(ctrl); + + ctrl->subDeviceInstance = 0; + ctrl->head = head; + ctrl->sorIndex = sor->id; + ctrl->dpLink = sor->asy.link == 2; + ctrl->bEnableOverride = 1; + ctrl->bMST = 1; + ctrl->hBlankSym = 0; + ctrl->vBlankSym = 0; + ctrl->colorFormat = 0; + ctrl->bEnableTwoHeadOneOr = 0; + ctrl->singleHeadMultistreamMode = 0; + ctrl->MST.slotStart = slot; + ctrl->MST.slotEnd = slot + slot_nr - 1; + ctrl->MST.PBN = pbn; + ctrl->MST.Timeslice = aligned_pbn; + ctrl->MST.sendACT = 0; + ctrl->MST.singleHeadMSTPipeline = 0; + ctrl->MST.bEnableAudioOverRightPanel = 0; + return nvkm_gsp_rm_ctrl_wr(&disp->rm.objcom, ctrl); +} + +static int +r570_dp_sst(struct nvkm_ior *sor, int head, bool ef, + u32 watermark, u32 hblanksym, u32 vblanksym) +{ + struct nvkm_disp *disp = sor->disp; + NV0073_CTRL_CMD_DP_CONFIG_STREAM_PARAMS *ctrl; + + ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom, + NV0073_CTRL_CMD_DP_CONFIG_STREAM, sizeof(*ctrl)); + if (IS_ERR(ctrl)) + return PTR_ERR(ctrl); + + ctrl->subDeviceInstance = 0; + ctrl->head = head; + ctrl->sorIndex = sor->id; + ctrl->dpLink = sor->asy.link == 2; + ctrl->bEnableOverride = 1; + ctrl->bMST = 0; + ctrl->hBlankSym = hblanksym; + ctrl->vBlankSym = vblanksym; + ctrl->colorFormat = 0; + ctrl->bEnableTwoHeadOneOr = 0; + ctrl->SST.bEnhancedFraming = ef; + ctrl->SST.tuSize = 64; + ctrl->SST.waterMark = watermark; + ctrl->SST.bEnableAudioOverRightPanel = 0; + return nvkm_gsp_rm_ctrl_wr(&disp->rm.objcom, ctrl); +} + +static int r570_dp_set_indexed_link_rates(struct nvkm_outp *outp) { NV0073_CTRL_CMD_DP_CONFIG_INDEXED_LINK_RATES_PARAMS *ctrl; @@ -255,6 +317,8 @@ r570_disp = { .dp = { .get_caps = r570_dp_get_caps, .set_indexed_link_rates = r570_dp_set_indexed_link_rates, + .sst = r570_dp_sst, + .vcpi = r570_dp_vcpi, }, .chan = { .set_pushbuf = r570_disp_chan_set_pushbuf, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/gsp.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/gsp.c index 996941c668ba..1488771c63fc 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/gsp.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/gsp.c @@ -44,6 +44,15 @@ r570_gsp_xlat_mc_engine_idx(u32 mc_engine_idx, enum nvkm_subdev_type *ptype, int *ptype = NVKM_ENGINE_DISP; *pinst = 0; return true; + case MC_ENGINE_IDX_DISP_LOW: + /* GB20x+ report a separate low-latency display vector, used + * for head-timing interrupts. Expose it as a second DISP + * interrupt instance. r535_disp_oneinit() attaches the + * handler to it when the chip's gsp.intr_low_latency is set. + */ + *ptype = NVKM_ENGINE_DISP; + *pinst = 1; + return true; case MC_ENGINE_IDX_CE0 ... MC_ENGINE_IDX_CE19: *ptype = NVKM_ENGINE_CE; *pinst = mc_engine_idx - MC_ENGINE_IDX_CE0; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/nvrm/disp.h b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/nvrm/disp.h index 06e972835d77..742b25a2a12d 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/nvrm/disp.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/nvrm/disp.h @@ -256,6 +256,8 @@ typedef struct NV0073_CTRL_DP_CTRL_PARAMS { NvU32 eightLaneDpcdBaseAddr; } NV0073_CTRL_DP_CTRL_PARAMS; +#define NV0073_CTRL_CMD_DP_CONFIG_STREAM (0x731362U) /* finn: Evaluated from "(FINN_NV04_DISPLAY_COMMON_DP_INTERFACE_ID << 8) | NV0073_CTRL_CMD_DP_CONFIG_STREAM_PARAMS_MESSAGE_ID" */ + typedef struct NV0073_CTRL_CMD_DP_CONFIG_STREAM_PARAMS { NvU32 subDeviceInstance; NvU32 head; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/rm.h b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/rm.h index a9af94adf9ef..fcd0221dcea1 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/rm.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/rm.h @@ -6,6 +6,7 @@ #ifndef __NVKM_RM_H__ #define __NVKM_RM_H__ #include "handles.h" +struct nvkm_ior; struct nvkm_outp; struct r535_gr; @@ -93,6 +94,10 @@ struct nvkm_rm_api { struct { int (*get_caps)(struct nvkm_disp *, int *link_bw, bool *mst, bool *wm); int (*set_indexed_link_rates)(struct nvkm_outp *); + int (*sst)(struct nvkm_ior *, int head, bool ef, + u32 watermark, u32 hblanksym, u32 vblanksym); + int (*vcpi)(struct nvkm_ior *, int head, + u8 slot, u8 slot_nr, u16 pbn, u16 aligned_pbn); } dp; struct { diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c index f4489efc94a7..22b0fde6ba34 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c @@ -195,6 +195,9 @@ check_io_mapping(struct nv50_instmem *imem) { struct nvkm_device *device = imem->base.subdev.device; + if (imem->iomap.size) + return true; + return io_mapping_init_wc(&imem->iomap, device->func->resource_addr(device, NVKM_BAR2_INST), device->func->resource_size(device, NVKM_BAR2_INST)) != NULL; diff --git a/drivers/gpu/drm/sysfb/ofdrm.c b/drivers/gpu/drm/sysfb/ofdrm.c index 819aed466727..9d60db45139c 100644 --- a/drivers/gpu/drm/sysfb/ofdrm.c +++ b/drivers/gpu/drm/sysfb/ofdrm.c @@ -2,6 +2,7 @@ #include <linux/aperture.h> #include <linux/of_address.h> +#include <linux/overflow.h> #include <linux/pci.h> #include <linux/platform_device.h> #include <linux/pm.h> @@ -238,7 +239,7 @@ static bool is_avivo(u32 vendor, u32 device) /* This will match most R5xx */ return (vendor == PCI_VENDOR_ID_ATI) && ((device >= PCI_VENDOR_ID_ATI_R520 && device < 0x7800) || - (PCI_VENDOR_ID_ATI_R600 >= 0x9400)); + (device >= PCI_VENDOR_ID_ATI_R600)); } static enum ofdrm_model display_get_model_of(struct drm_device *dev, struct device_node *of_node) @@ -913,7 +914,10 @@ static struct ofdrm_device *ofdrm_device_create(struct drm_driver *drv, return ERR_PTR(-EINVAL); } - fb_size = linebytes * height; + if (check_mul_overflow(linebytes, height, &fb_size)) { + drm_err(dev, "framebuffer size exceeds maximum\n"); + return ERR_PTR(-EINVAL); + } /* * Try to figure out the address of the framebuffer. Unfortunately, Open diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c index 0b3fcc7011b3..fefc3761a4bc 100644 --- a/drivers/gpu/drm/tegra/dc.c +++ b/drivers/gpu/drm/tegra/dc.c @@ -904,6 +904,7 @@ static struct drm_plane *tegra_primary_plane_create(struct drm_device *drm, struct tegra_dc *dc) { unsigned long possible_crtcs = tegra_plane_get_possible_crtcs(drm); + unsigned int blend_caps = BIT(DRM_MODE_BLEND_COVERAGE); enum drm_plane_type type = DRM_PLANE_TYPE_PRIMARY; struct tegra_plane *plane; unsigned int num_formats; @@ -939,6 +940,7 @@ static struct drm_plane *tegra_primary_plane_create(struct drm_device *drm, } drm_plane_helper_add(&plane->base, &tegra_plane_helper_funcs); + drm_plane_create_blend_mode_property(&plane->base, blend_caps); drm_plane_create_zpos_property(&plane->base, plane->index, 0, 255); err = drm_plane_create_rotation_property(&plane->base, @@ -1209,6 +1211,7 @@ static struct drm_plane *tegra_dc_cursor_plane_create(struct drm_device *drm, struct tegra_dc *dc) { unsigned long possible_crtcs = tegra_plane_get_possible_crtcs(drm); + unsigned int blend_caps = BIT(DRM_MODE_BLEND_COVERAGE); struct tegra_plane *plane; unsigned int num_formats; const u32 *formats; @@ -1252,6 +1255,7 @@ static struct drm_plane *tegra_dc_cursor_plane_create(struct drm_device *drm, } drm_plane_helper_add(&plane->base, &tegra_cursor_plane_helper_funcs); + drm_plane_create_blend_mode_property(&plane->base, blend_caps); drm_plane_create_zpos_immutable_property(&plane->base, 255); return &plane->base; @@ -1356,6 +1360,7 @@ static struct drm_plane *tegra_dc_overlay_plane_create(struct drm_device *drm, bool cursor) { unsigned long possible_crtcs = tegra_plane_get_possible_crtcs(drm); + unsigned int blend_caps = BIT(DRM_MODE_BLEND_COVERAGE); struct tegra_plane *plane; unsigned int num_formats; enum drm_plane_type type; @@ -1394,6 +1399,7 @@ static struct drm_plane *tegra_dc_overlay_plane_create(struct drm_device *drm, } drm_plane_helper_add(&plane->base, &tegra_plane_helper_funcs); + drm_plane_create_blend_mode_property(&plane->base, blend_caps); drm_plane_create_zpos_property(&plane->base, plane->index, 0, 255); err = drm_plane_create_rotation_property(&plane->base, diff --git a/drivers/gpu/drm/tegra/hub.c b/drivers/gpu/drm/tegra/hub.c index bd442bfd4540..448f49f3a7d7 100644 --- a/drivers/gpu/drm/tegra/hub.c +++ b/drivers/gpu/drm/tegra/hub.c @@ -759,6 +759,7 @@ struct drm_plane *tegra_shared_plane_create(struct drm_device *drm, unsigned int index, enum drm_plane_type type) { + unsigned int blend_caps = BIT(DRM_MODE_BLEND_COVERAGE); struct tegra_drm *tegra = drm->dev_private; struct tegra_display_hub *hub = tegra->hub; struct tegra_shared_plane *plane; @@ -797,6 +798,7 @@ struct drm_plane *tegra_shared_plane_create(struct drm_device *drm, } drm_plane_helper_add(p, &tegra_shared_plane_helper_funcs); + drm_plane_create_blend_mode_property(p, blend_caps); drm_plane_create_zpos_property(p, 0, 0, 255); return p; diff --git a/drivers/gpu/drm/tiny/cirrus-qemu.c b/drivers/gpu/drm/tiny/cirrus-qemu.c index 075221b431d3..3bf23fcf6574 100644 --- a/drivers/gpu/drm/tiny/cirrus-qemu.c +++ b/drivers/gpu/drm/tiny/cirrus-qemu.c @@ -582,6 +582,9 @@ static int cirrus_pci_probe(struct pci_dev *pdev, struct cirrus_device *cirrus; int ret; + if (pci_resource_len(pdev, 0) < CIRRUS_VRAM_SIZE) + return -ENODEV; + ret = aperture_remove_conflicting_pci_devices(pdev, cirrus_driver.name); if (ret) return ret; diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c b/drivers/gpu/drm/virtio/virtgpu_display.c index 44ffffec550f..a1a875a0c706 100644 --- a/drivers/gpu/drm/virtio/virtgpu_display.c +++ b/drivers/gpu/drm/virtio/virtgpu_display.c @@ -344,7 +344,7 @@ virtio_gpu_user_framebuffer_create(struct drm_device *dev, if (ret) { kfree(virtio_gpu_fb); drm_gem_object_put(obj); - return NULL; + return ERR_PTR(ret); } return &virtio_gpu_fb->base; @@ -378,8 +378,11 @@ int virtio_gpu_modeset_init(struct virtio_gpu_device *vgdev) vgdev->ddev->mode_config.fb_modifiers_not_supported = true; - for (i = 0 ; i < vgdev->num_scanouts; ++i) - vgdev_output_init(vgdev, i); + for (i = 0; i < vgdev->num_scanouts; ++i) { + ret = vgdev_output_init(vgdev, i); + if (ret) + return ret; + } ret = drm_vblank_init(vgdev->ddev, vgdev->num_scanouts); if (ret) diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h index 17a6a4d26516..9df4c7117341 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.h +++ b/drivers/gpu/drm/virtio/virtgpu_drv.h @@ -43,6 +43,8 @@ #include <drm/drm_probe_helper.h> #include <drm/virtgpu_drm.h> +#include <xen/xen.h> + #define DRIVER_NAME "virtio_gpu" #define DRIVER_DESC "virtio GPU" @@ -60,6 +62,24 @@ /* See virtio_gpu_ctx_create. One additional character for NULL terminator. */ #define DEBUG_NAME_MAX_LEN 65 +/* + * Whether the host must be told about resource backing pages by DMA address + * rather than guest-physical address. + * + * This mirrors vring_use_map_api() in drivers/virtio/virtio_ring.c, including + * its xen_domain() case. + */ +static inline bool virtio_gpu_use_dma_api(const struct virtio_device *vdev) +{ + if (!virtio_has_dma_quirk(vdev)) + return true; + + if (xen_domain()) + return true; + + return false; +} + struct virtio_gpu_object_params { unsigned long size; bool dumb; @@ -343,6 +363,7 @@ void virtio_gpu_array_put_free_work(struct work_struct *work); /* virtgpu_vq.c */ int virtio_gpu_alloc_vbufs(struct virtio_gpu_device *vgdev); void virtio_gpu_free_vbufs(struct virtio_gpu_device *vgdev); +void virtio_gpu_reclaim_vbufs(struct virtio_gpu_device *vgdev); void virtio_gpu_cmd_create_resource(struct virtio_gpu_device *vgdev, struct virtio_gpu_object *bo, struct virtio_gpu_object_params *params, diff --git a/drivers/gpu/drm/virtio/virtgpu_kms.c b/drivers/gpu/drm/virtio/virtgpu_kms.c index 1ffe1e431f65..1d4d3bf46a20 100644 --- a/drivers/gpu/drm/virtio/virtgpu_kms.c +++ b/drivers/gpu/drm/virtio/virtgpu_kms.c @@ -352,6 +352,7 @@ void virtio_gpu_deinit(struct drm_device *dev) flush_work(&vgdev->cursorq.dequeue_work); flush_work(&vgdev->config_changed_work); virtio_reset_device(vgdev->vdev); + virtio_gpu_reclaim_vbufs(vgdev); vgdev->vdev->config->del_vqs(vgdev->vdev); mutex_destroy(&vgdev->obj_restore_lock); } diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c index 9bc0bd68c314..49899485be6f 100644 --- a/drivers/gpu/drm/virtio/virtgpu_object.c +++ b/drivers/gpu/drm/virtio/virtgpu_object.c @@ -173,7 +173,7 @@ static int virtio_gpu_object_shmem_init(struct virtio_gpu_device *vgdev, struct virtio_gpu_mem_entry **ents, unsigned int *nents) { - bool use_dma_api = !virtio_has_dma_quirk(vgdev->vdev); + bool use_dma_api = virtio_gpu_use_dma_api(vgdev->vdev); struct scatterlist *sg; struct sg_table *pages; int si; diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c index f2b0ab0f610e..c02c03c10d92 100644 --- a/drivers/gpu/drm/virtio/virtgpu_vq.c +++ b/drivers/gpu/drm/virtio/virtgpu_vq.c @@ -208,6 +208,21 @@ static void free_vbuf(struct virtio_gpu_device *vgdev, kmem_cache_free(vgdev->vbufs, vbuf); } +void virtio_gpu_reclaim_vbufs(struct virtio_gpu_device *vgdev) +{ + struct virtio_gpu_vbuffer *vbuf; + + while ((vbuf = virtqueue_detach_unused_buf(vgdev->ctrlq.vq))) { + if (vbuf->objs) + virtio_gpu_array_put_free(vbuf->objs); + if (vbuf->resp_cb_data) + virtio_gpu_cleanup_object(vbuf->resp_cb_data); + free_vbuf(vgdev, vbuf); + } + while ((vbuf = virtqueue_detach_unused_buf(vgdev->cursorq.vq))) + free_vbuf(vgdev, vbuf); +} + static void reclaim_vbufs(struct virtqueue *vq, struct list_head *reclaim_list) { struct virtio_gpu_vbuffer *vbuf; @@ -764,7 +779,7 @@ int virtio_gpu_panic_cmd_transfer_to_host_2d(struct virtio_gpu_device *vgdev, struct virtio_gpu_object *bo = gem_to_virtio_gpu_obj(objs->objs[0]); struct virtio_gpu_transfer_to_host_2d *cmd_p; struct virtio_gpu_vbuffer *vbuf; - bool use_dma_api = !virtio_has_dma_quirk(vgdev->vdev); + bool use_dma_api = virtio_gpu_use_dma_api(vgdev->vdev); if (virtio_gpu_is_shmem(bo) && use_dma_api) dma_sync_sgtable_for_device(vgdev->vdev->dev.parent, @@ -795,7 +810,7 @@ void virtio_gpu_cmd_transfer_to_host_2d(struct virtio_gpu_device *vgdev, struct virtio_gpu_object *bo = gem_to_virtio_gpu_obj(objs->objs[0]); struct virtio_gpu_transfer_to_host_2d *cmd_p; struct virtio_gpu_vbuffer *vbuf; - bool use_dma_api = !virtio_has_dma_quirk(vgdev->vdev); + bool use_dma_api = virtio_gpu_use_dma_api(vgdev->vdev); if (virtio_gpu_is_shmem(bo) && use_dma_api) dma_sync_sgtable_for_device(vgdev->vdev->dev.parent, @@ -1228,7 +1243,7 @@ void virtio_gpu_cmd_transfer_to_host_3d(struct virtio_gpu_device *vgdev, struct virtio_gpu_object *bo = gem_to_virtio_gpu_obj(objs->objs[0]); struct virtio_gpu_transfer_host_3d *cmd_p; struct virtio_gpu_vbuffer *vbuf; - bool use_dma_api = !virtio_has_dma_quirk(vgdev->vdev); + bool use_dma_api = virtio_gpu_use_dma_api(vgdev->vdev); if (virtio_gpu_is_shmem(bo) && use_dma_api) dma_sync_sgtable_for_device(vgdev->vdev->dev.parent, diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c index 9c5384b95c63..ab09dcff5860 100644 --- a/drivers/gpu/drm/xe/xe_oa.c +++ b/drivers/gpu/drm/xe/xe_oa.c @@ -2435,9 +2435,9 @@ int xe_oa_add_config_ioctl(struct drm_device *dev, u64 data, struct drm_file *fi oa_config->id = idr_alloc(&oa->metrics_idr, oa_config, 1, 0, GFP_KERNEL); if (oa_config->id < 0) { - drm_dbg(&oa->xe->drm, "Failed to create sysfs entry for OA config\n"); + drm_dbg(&oa->xe->drm, "Failed to allocate id for OA config\n"); err = oa_config->id; - goto sysfs_err; + goto id_alloc_err; } id = oa_config->id; @@ -2448,6 +2448,8 @@ int xe_oa_add_config_ioctl(struct drm_device *dev, u64 data, struct drm_file *fi return id; +id_alloc_err: + sysfs_remove_group(oa->metrics_kobj, &oa_config->sysfs_metric); sysfs_err: mutex_unlock(&oa->metrics_lock); reg_err: diff --git a/drivers/gpu/drm/xe/xe_vram.c b/drivers/gpu/drm/xe/xe_vram.c index 7b4478fb1697..56cff1e44530 100644 --- a/drivers/gpu/drm/xe/xe_vram.c +++ b/drivers/gpu/drm/xe/xe_vram.c @@ -90,6 +90,9 @@ static int get_flat_ccs_offset(struct xe_gt *gt, u64 tile_size, u64 *poffset) offset |= offset_lo << 6; /* HW view bits 31:6 */ offset *= num_enabled; /* convert to SW view */ + drm_info(&xe->drm, "FLAT_CCS base:%llx, aligned:%s\n", offset, + str_yes_no(IS_ALIGNED(offset, SZ_128K))); + /* * Everything below this offset is handed to the VRAM * allocator, so it has to be the *first* address the diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig index aa7fa11a0197..a81bf51cbcf1 100644 --- a/drivers/hid/Kconfig +++ b/drivers/hid/Kconfig @@ -1253,7 +1253,7 @@ config HID_HYPERV_MOUSE config HID_HYPERV_MOUSE_KUNIT_TEST bool "KUnit tests for Hyper-V mouse driver" if !KUNIT_ALL_TESTS - depends on KUNIT && HID_HYPERV_MOUSE + depends on KUNIT && (HID_HYPERV_MOUSE = KUNIT || KUNIT = y) default KUNIT_ALL_TESTS help Builds unit tests for the Hyper-V synthetic HID driver. diff --git a/drivers/hid/bpf/hid_bpf_struct_ops.c b/drivers/hid/bpf/hid_bpf_struct_ops.c index 702c22fae136..c90b68956cb3 100644 --- a/drivers/hid/bpf/hid_bpf_struct_ops.c +++ b/drivers/hid/bpf/hid_bpf_struct_ops.c @@ -62,6 +62,10 @@ struct hid_bpf_offset_write_range { u32 end; }; +struct hid_bpf_ctx__safe_trusted { + struct hid_device *hid; +}; + static int hid_bpf_ops_btf_struct_access(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size) @@ -86,6 +90,8 @@ static int hid_bpf_ops_btf_struct_access(struct bpf_verifier_log *log, const char *cur = NULL; int i; + BTF_TYPE_EMIT(struct hid_bpf_ctx__safe_trusted); + t = btf_type_by_id(reg->btf, reg->btf_id); for (i = 0; i < ARRAY_SIZE(write_ranges); i++) { @@ -250,6 +256,11 @@ static void hid_bpf_unreg(void *kdata, struct bpf_link *link) mutex_lock(&hdev->bpf.prog_list_lock); + if (!ops->hdev) { + mutex_unlock(&hdev->bpf.prog_list_lock); + return; + } + list_del_rcu(&ops->list); synchronize_srcu(&hdev->bpf.srcu); ops->hdev = NULL; @@ -310,13 +321,17 @@ static struct bpf_struct_ops bpf_hid_bpf_ops = { void __hid_bpf_ops_destroy_device(struct hid_device *hdev) { struct hid_bpf_ops *e; + int count = 0; - rcu_read_lock(); - list_for_each_entry_rcu(e, &hdev->bpf.prog_list, list) { - hid_put_device(hdev); + mutex_lock(&hdev->bpf.prog_list_lock); + list_for_each_entry(e, &hdev->bpf.prog_list, list) { e->hdev = NULL; + count++; } - rcu_read_unlock(); + mutex_unlock(&hdev->bpf.prog_list_lock); + + while (count--) + hid_put_device(hdev); } static int __init hid_bpf_struct_ops_init(void) diff --git a/drivers/hid/hid-hyperv.c b/drivers/hid/hid-hyperv.c index 6579bd19da13..cfc061dbdd24 100644 --- a/drivers/hid/hid-hyperv.c +++ b/drivers/hid/hid-hyperv.c @@ -687,7 +687,7 @@ static void mousevsc_device_info_valid_descriptor(struct kunit *test) info->hid_descriptor.bLength = sizeof(struct hid_descriptor); info->hid_descriptor.rpt_desc.wDescriptorLength = cpu_to_le16(4); - report = ((u8 *)&info->hid_descriptor) + info->hid_descriptor.bLength; + report = (u8 *)(info + 1); memset(report, 0x42, 4); mousevsc_on_receive_device_info(input_dev, info, sizeof(*info) + 4); @@ -713,7 +713,7 @@ static void mousevsc_device_info_report_desc_oob(struct kunit *test) info->hid_descriptor.bLength = sizeof(struct hid_descriptor); info->hid_descriptor.rpt_desc.wDescriptorLength = cpu_to_le16(64); - report = ((u8 *)&info->hid_descriptor) + info->hid_descriptor.bLength; + report = (u8 *)(info + 1); memset(report, 0x42, 8); mousevsc_on_receive_device_info(input_dev, info, sizeof(*info) + 8); diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 341bf587863b..b3aca5aa9176 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -338,6 +338,7 @@ #define I2C_VENDOR_ID_CIRQUE 0x0488 #define I2C_PRODUCT_ID_CIRQUE_1063 0x1063 +#define I2C_PRODUCT_ID_CIRQUE_D0C1 0xD0C1 #define USB_VENDOR_ID_CJTOUCH 0x24b8 #define USB_DEVICE_ID_CJTOUCH_MULTI_TOUCH_0020 0x0020 diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 2c41bacab1ca..451c7324e6a0 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -1321,21 +1321,18 @@ static void mt_touch_report(struct hid_device *hid, * Includes multi-packet support where subsequent * packets are sent with zero contactcount. */ - if (contact_count >= 0) { + if (contact_count > 0) + app->num_expected = contact_count; + else if (app->num_received == 0 && app->prev_scantime != scantime) { /* + * New multi-report frame: + * * For Win8 PTPs the first packet (td->num_received == 0) may * have a contactcount of 0 if there only is a button event. - * We double check that this is not a continuation packet - * of a possible multi-packet frame be checking that the - * timestamp has changed. + * + * Some other devices use a sentinel frame with 0 to release all contacts */ - if ((app->quirks & MT_QUIRK_WIN8_PTP_BUTTONS) && - app->num_received == 0 && - app->prev_scantime != scantime) - app->num_expected = contact_count; - /* A non 0 contact count always indicates a first packet */ - else if (contact_count) - app->num_expected = contact_count; + app->num_expected = 0; } app->prev_scantime = scantime; diff --git a/drivers/hid/hid-rmi.c b/drivers/hid/hid-rmi.c index 2bd781f1e0f5..ecc19387f6b0 100644 --- a/drivers/hid/hid-rmi.c +++ b/drivers/hid/hid-rmi.c @@ -235,7 +235,23 @@ static int rmi_hid_read_block(struct rmi_transport_dev *xport, u16 addr, break; } - read_input_count = data->readReport[1]; + read_input_count = min_t(int, data->readReport[1], + data->input_report_size - 2); + if (!read_input_count) { + /* + * A zero length reply advances neither + * bytes_read nor bytes_needed, and because a + * reply did arrive the wait above does not + * time out either, so a device answering 0 + * forever would spin here indefinitely with + * page_mutex held. + */ + hid_warn(hdev, "%s: zero-length read reply\n", + __func__); + clear_bit(RMI_READ_DATA_PENDING, &data->flags); + ret = -EIO; + break; + } memcpy(buf + bytes_read, &data->readReport[2], min(read_input_count, bytes_needed)); @@ -271,6 +287,11 @@ static int rmi_hid_write_block(struct rmi_transport_dev *xport, u16 addr, goto exit; } + if (len + 4 > data->output_report_size) { + ret = -EINVAL; + goto exit; + } + data->writeReport[0] = RMI_WRITE_REPORT_ID; data->writeReport[1] = len; data->writeReport[2] = addr & 0xFF; @@ -666,8 +687,16 @@ static int rmi_probe(struct hid_device *hdev, const struct hid_device_id *id) return ret; } - if (id->driver_data) - data->device_flags = id->driver_data; + /* + * RMI_DEVICE can only mean "this probe validated the RMI reports and + * allocated writeReport": every bail-out to start below skips that + * allocation, and device_flags left carrying RMI_DEVICE from + * driver_data would send rmi_input_configured() into rmi_set_page() + * with writeReport still NULL. A bind through the new_id sysfs + * attribute can supply driver_data with the bit set, so do not let + * driver_data grant it. + */ + data->device_flags = id->driver_data & ~RMI_DEVICE; /* * Check for the RMI specific report ids. If they are misisng @@ -696,6 +725,17 @@ static int rmi_probe(struct hid_device *hdev, const struct hid_device_id *id) data->output_report_size = hid_report_len(output_report); + /* + * The write reports built by this driver occupy 6 bytes and the read + * handshake looks at the first 3 bytes of an input report, so refuse + * to drive a device whose reports cannot hold them. + */ + if (data->output_report_size < 6 || data->input_report_size < 3) { + hid_err(hdev, "rmi reports too small (out=%u in=%u)\n", + data->output_report_size, data->input_report_size); + goto start; + } + data->device_flags |= RMI_DEVICE; alloc_size = data->output_report_size + data->input_report_size; diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c index 0e725a0f0abe..0ff07fdab442 100644 --- a/drivers/hid/i2c-hid/i2c-hid-core.c +++ b/drivers/hid/i2c-hid/i2c-hid-core.c @@ -136,6 +136,8 @@ static const struct i2c_hid_quirks { I2C_HID_QUIRK_BAD_INPUT_SIZE }, { I2C_VENDOR_ID_CIRQUE, I2C_PRODUCT_ID_CIRQUE_1063, I2C_HID_QUIRK_NO_SLEEP_ON_SUSPEND }, + { I2C_VENDOR_ID_CIRQUE, I2C_PRODUCT_ID_CIRQUE_D0C1, + I2C_HID_QUIRK_NO_IRQ_AFTER_RESET }, /* * Without additional power on command, at least some QTEC devices send garbage */ diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index a29bf051ada7..8feb8027be95 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -1550,6 +1550,19 @@ static int wacom_intuos_pro2_bt_irq(struct wacom_wac *wacom, size_t len) return 0; } + if (wacom->features.type == INTUOSP2_BT || + wacom->features.type == INTUOSP2S_BT) { + if (len < 286) { + dev_warn(wacom->pen_input->dev.parent, + "Pro2 BT report too short: %zu bytes\n", len); + return 0; + } + } else if (len < 46) { + dev_warn(wacom->pen_input->dev.parent, + "Pro2 BT report too short: %zu bytes\n", len); + return 0; + } + wacom_intuos_pro2_bt_pen(wacom); if (wacom->features.type == INTUOSP2_BT || wacom->features.type == INTUOSP2S_BT) { diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 33dbc71b730f..1a5072425c4a 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -340,8 +340,6 @@ struct cache { struct list_head invalidation_requests; sector_t migration_threshold; - wait_queue_head_t migration_wait; - atomic_t nr_allocated_migrations; /* * The number of in flight migrations that are performing @@ -397,7 +395,11 @@ struct cache { bool loaded_mappings:1; bool loaded_discards:1; - struct rw_semaphore background_work_lock; + /* background work management */ + bool background_work_allowed; + unsigned background_work_nr; + spinlock_t background_work_lock; + wait_queue_head_t background_work_wait; struct batcher committer; struct work_struct commit_ws; @@ -488,19 +490,13 @@ static struct dm_cache_migration *alloc_migration(struct cache *cache) memset(mg, 0, sizeof(*mg)); mg->cache = cache; - atomic_inc(&cache->nr_allocated_migrations); return mg; } static void free_migration(struct dm_cache_migration *mg) { - struct cache *cache = mg->cache; - - if (atomic_dec_and_test(&cache->nr_allocated_migrations)) - wake_up(&cache->migration_wait); - - mempool_free(mg, &cache->migration_pool); + mempool_free(mg, &mg->cache->migration_pool); } /*----------------------------------------------------------------*/ @@ -1030,34 +1026,39 @@ static void calc_discard_block_range(struct cache *cache, struct bio *bio, static void prevent_background_work(struct cache *cache) { - lockdep_off(); - down_write(&cache->background_work_lock); - lockdep_on(); + spin_lock_irq(&cache->background_work_lock); + cache->background_work_allowed = false; + wait_event_lock_irq(cache->background_work_wait, + cache->background_work_nr == 0, + cache->background_work_lock); + spin_unlock_irq(&cache->background_work_lock); } static void allow_background_work(struct cache *cache) { - lockdep_off(); - up_write(&cache->background_work_lock); - lockdep_on(); + spin_lock_irq(&cache->background_work_lock); + cache->background_work_allowed = true; + spin_unlock_irq(&cache->background_work_lock); } static bool background_work_begin(struct cache *cache) { bool r; - lockdep_off(); - r = down_read_trylock(&cache->background_work_lock); - lockdep_on(); - + spin_lock_irq(&cache->background_work_lock); + r = cache->background_work_allowed; + if (r) + cache->background_work_nr++; + spin_unlock_irq(&cache->background_work_lock); return r; } static void background_work_end(struct cache *cache) { - lockdep_off(); - up_read(&cache->background_work_lock); - lockdep_on(); + spin_lock_irq(&cache->background_work_lock); + if (--cache->background_work_nr == 0) + wake_up(&cache->background_work_wait); + spin_unlock_irq(&cache->background_work_lock); } /*----------------------------------------------------------------*/ @@ -1462,6 +1463,9 @@ static void invalidate_complete(struct dm_cache_migration *mg, bool success) struct bio_list bios; struct cache *cache = mg->cache; + if (success) + atomic_inc(&cache->stats.demotion); + bio_list_init(&bios); if (mg->cell) { if (dm_cell_unlock_v2(cache->prison, mg->cell, &bios)) @@ -1733,7 +1737,6 @@ static int map_bio(struct cache *cache, struct bio *bio, dm_oblock_t block, if (passthrough_mode(cache)) { if (bio_data_dir(bio) == WRITE) { bio_drop_shared_lock(cache, bio); - atomic_inc(&cache->stats.demotion); invalidate_start(cache, cblock, block, bio); return DM_MAPIO_SUBMITTED; } else @@ -2507,9 +2510,7 @@ static int cache_create(struct cache_args *ca, struct cache **result) spin_lock_init(&cache->lock); bio_list_init(&cache->deferred_bios); - atomic_set(&cache->nr_allocated_migrations, 0); atomic_set(&cache->nr_io_migrations, 0); - init_waitqueue_head(&cache->migration_wait); r = -ENOMEM; atomic_set(&cache->nr_dirty, 0); @@ -2592,8 +2593,10 @@ static int cache_create(struct cache_args *ca, struct cache **result) issue_op, cache, cache->wq); dm_iot_init(&cache->tracker); - init_rwsem(&cache->background_work_lock); - prevent_background_work(cache); + init_waitqueue_head(&cache->background_work_wait); + spin_lock_init(&cache->background_work_lock); + cache->background_work_allowed = false; + cache->background_work_nr = 0; *result = cache; return 0; diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 608b617fb817..9e170de50ad3 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1745,7 +1745,6 @@ static void crypt_dec_pending(struct dm_crypt_io *io) { struct crypt_config *cc = io->cc; struct bio *base_bio = io->base_bio; - blk_status_t error = io->error; if (!atomic_dec_and_test(&io->io_pending)) return; @@ -1767,7 +1766,7 @@ static void crypt_dec_pending(struct dm_crypt_io *io) else kfree(io->integrity_metadata); - base_bio->bi_status = error; + base_bio->bi_status = io->error; bio_endio(base_bio); } diff --git a/drivers/md/dm-ebs-target.c b/drivers/md/dm-ebs-target.c index 1e52bde48b91..5d67c6c19d4b 100644 --- a/drivers/md/dm-ebs-target.c +++ b/drivers/md/dm-ebs-target.c @@ -265,8 +265,7 @@ static int ebs_ctr(struct dm_target *ti, unsigned int argc, char **argv) r = -EINVAL; if (sscanf(argv[1], "%llu%c", &tmp, &dummy) != 1 || - tmp != (sector_t)tmp || - (sector_t)tmp >= ti->len) { + tmp != (sector_t)tmp) { ti->error = "Invalid device offset sector"; goto bad; } diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index c50feaa98bf9..92970e12267a 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -1979,8 +1979,8 @@ static void integrity_metadata(struct work_struct *w) if (unlikely(dio->op == REQ_OP_DISCARD)) { unsigned int bi_size = dio->bio_details.bi_iter.bi_size; - unsigned int max_size = likely(checksums != checksums_onstack) ? PAGE_SIZE : HASH_MAX_DIGESTSIZE; - unsigned int max_blocks = max_size / ic->tag_size; + unsigned int max_size = likely(checksums != checksums_onstack) ? PAGE_SIZE : sizeof(checksums_onstack); + unsigned int max_blocks = (max_size - extra_space) / ic->tag_size; sector_t sector = dio->range.logical_sector; if (!ic->discard_keyed) @@ -3875,6 +3875,10 @@ static void dm_integrity_resume(struct dm_target *ti) r = sync_rw_sb(ic, REQ_OP_READ); if (r) dm_integrity_io_error(ic, "reading superblock", r); + + if (ic->mode == 'R') + goto skip_writes; + if ((ic->sb->flags & flags) != flags) { ic->sb->flags |= flags; r = sync_rw_sb(ic, REQ_OP_WRITE | REQ_FUA); @@ -3984,6 +3988,7 @@ static void dm_integrity_resume(struct dm_target *ti) } } +skip_writes: ic->reboot_notifier.notifier_call = dm_integrity_reboot; ic->reboot_notifier.next = NULL; ic->reboot_notifier.priority = INT_MAX - 1; /* be notified after md and before hardware drivers */ @@ -4130,6 +4135,10 @@ static void dm_integrity_io_hints(struct dm_target *ti, struct queue_limits *lim limits->dma_alignment = limits->logical_block_size - 1; limits->discard_granularity = ic->sectors_per_block << SECTOR_SHIFT; + if (ic->internal_hash && + (ic->mode == 'D' || ic->mode == 'B' || ic->mode == 'I')) + limits->features |= BLK_FEAT_STABLE_WRITES; + if (!ic->internal_hash) { struct blk_integrity *bi = &limits->integrity; diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index 90fd669636ec..d4fac2caca86 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -1822,24 +1822,20 @@ static int fastrpc_dmabuf_alloc(struct fastrpc_user *fl, char __user *argp) return err; } - bp.fd = dma_buf_fd(buf->dmabuf, O_ACCMODE); + bp.fd = get_unused_fd_flags(O_ACCMODE); if (bp.fd < 0) { dma_buf_put(buf->dmabuf); - return -EINVAL; + return bp.fd; } if (copy_to_user(argp, &bp, sizeof(bp))) { - /* - * The usercopy failed, but we can't do much about it, as - * dma_buf_fd() already called fd_install() and made the - * file descriptor accessible for the current process. It - * might already be closed and dmabuf no longer valid when - * we reach this point. Therefore "leak" the fd and rely on - * the process exit path to do any required cleanup. - */ + put_unused_fd(bp.fd); + dma_buf_put(buf->dmabuf); return -EFAULT; } + dma_buf_fd_install(buf->dmabuf, bp.fd); + return 0; } diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 839f7482dc18..654f051d0023 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -875,7 +875,7 @@ static int rlb_initialize(struct bonding *bond) spin_unlock_bh(&bond->mode_lock); /* register to receive ARPs */ - bond->recv_probe = rlb_arp_recv; + WRITE_ONCE(bond->recv_probe, rlb_arp_recv); return 0; } @@ -1281,10 +1281,10 @@ unwind: } /* determine if the packet is NA or NS */ -static bool alb_determine_nd(struct sk_buff *skb, struct bonding *bond) +static bool alb_determine_nd(struct sk_buff *skb) { - struct ipv6hdr *ip6hdr; - struct icmp6hdr *hdr; + const struct ipv6hdr *ip6hdr; + const struct icmp6hdr *hdr; if (!pskb_network_may_pull(skb, sizeof(*ip6hdr))) return true; @@ -1296,7 +1296,8 @@ static bool alb_determine_nd(struct sk_buff *skb, struct bonding *bond) if (!pskb_network_may_pull(skb, sizeof(*ip6hdr) + sizeof(*hdr))) return true; - hdr = icmp6_hdr(skb); + ip6hdr = ipv6_hdr(skb); + hdr = (const struct icmp6hdr *)(ip6hdr + 1); return hdr->icmp6_type == NDISC_NEIGHBOUR_ADVERTISEMENT || hdr->icmp6_type == NDISC_NEIGHBOUR_SOLICITATION; } @@ -1381,7 +1382,7 @@ struct slave *bond_xmit_tlb_slave_get(struct bonding *bond, if (!is_multicast_ether_addr(eth_data->h_dest)) { switch (skb->protocol) { case htons(ETH_P_IPV6): - if (alb_determine_nd(skb, bond)) + if (alb_determine_nd(skb)) break; fallthrough; case htons(ETH_P_IP): @@ -1467,7 +1468,7 @@ struct slave *bond_xmit_alb_slave_get(struct bonding *bond, break; } - if (alb_determine_nd(skb, bond)) { + if (alb_determine_nd(skb)) { do_tx_balance = false; break; } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index ef9eb0c53c66..a9bff7663eec 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1245,7 +1245,7 @@ static void bond_peer_notify_may_events(struct bonding *bond, bool force) } if (notified || force) - bond->send_peer_notif--; + WRITE_ONCE(bond->send_peer_notif, bond->send_peer_notif - 1); } /** @@ -2284,7 +2284,7 @@ skip_mac_set: } } - bond->slave_cnt++; + WRITE_ONCE(bond->slave_cnt, bond->slave_cnt + 1); netdev_compute_master_upper_features(bond->dev, true); bond_set_carrier(bond); @@ -2517,9 +2517,7 @@ static int __bond_release_one(struct net_device *bond_dev, bond_alb_deinit_slave(bond, slave); } - if (all) { - RCU_INIT_POINTER(bond->curr_active_slave, NULL); - } else if (oldcurrent == slave) { + if (!all && oldcurrent == slave) { /* Note that we hold RTNL over this sequence, so there * is no concern that another slave add/remove event * will interfere. @@ -2533,7 +2531,7 @@ static int __bond_release_one(struct net_device *bond_dev, unblock_netpoll_tx(); synchronize_rcu(); - bond->slave_cnt--; + WRITE_ONCE(bond->slave_cnt, bond->slave_cnt - 1); if (!bond_has_slaves(bond)) { call_netdevice_notifiers(NETDEV_CHANGEADDR, bond->dev); @@ -4385,13 +4383,13 @@ static int bond_open(struct net_device *bond_dev) if (bond->params.arp_interval) { /* arp interval, in milliseconds. */ queue_delayed_work(bond->wq, &bond->arp_work, 0); - bond->recv_probe = bond_rcv_validate; + WRITE_ONCE(bond->recv_probe, bond_rcv_validate); } if (BOND_MODE(bond) == BOND_MODE_8023AD) { queue_delayed_work(bond->wq, &bond->ad_work, 0); /* register to receive LACPDUs */ - bond->recv_probe = bond_3ad_lacpdu_recv; + WRITE_ONCE(bond->recv_probe, bond_3ad_lacpdu_recv); bond_3ad_initiate_agg_selection(bond, 1); bond_for_each_slave(bond, slave, iter) @@ -4413,7 +4411,7 @@ static int bond_close(struct net_device *bond_dev) struct slave *slave; bond_work_cancel_all(bond); - bond->send_peer_notif = 0; + WRITE_ONCE(bond->send_peer_notif, 0); WRITE_ONCE(bond->recv_probe, NULL); /* Wait for any in-flight RX handlers */ @@ -5118,7 +5116,7 @@ static void bond_skip_slave(struct bond_up_slave *slaves, if (skipslave == slaves->arr[idx]) { slaves->arr[idx] = slaves->arr[slaves->count - 1]; - slaves->count--; + WRITE_ONCE(slaves->count, slaves->count - 1); break; } } diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 36b8d89387ee..9efadeff6a22 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -1147,11 +1147,11 @@ static int bond_option_arp_interval_set(struct bonding *bond, */ if (!newval->value) { if (bond->params.arp_validate) - bond->recv_probe = NULL; + WRITE_ONCE(bond->recv_probe, NULL); cancel_delayed_work_sync(&bond->arp_work); } else { /* arp_validate can be set only in active-backup mode */ - bond->recv_probe = bond_rcv_validate; + WRITE_ONCE(bond->recv_probe, bond_rcv_validate); cancel_delayed_work_sync(&bond->mii_work); queue_delayed_work(bond->wq, &bond->arp_work, 0); } diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h index fa9a8edce22f..8277c1c87bb3 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.h +++ b/drivers/net/ethernet/airoha/airoha_eth.h @@ -538,7 +538,7 @@ struct airoha_wdma_info { /* RX queue to IRQ mapping: BIT(q) in IRQ(n) */ #define RX_IRQ0_BANK_PIN_MASK 0x839f -#define RX_IRQ1_BANK_PIN_MASK 0x7fe00000 +#define RX_IRQ1_BANK_PIN_MASK 0xffe00000 #define RX_IRQ2_BANK_PIN_MASK 0x20 #define RX_IRQ3_BANK_PIN_MASK 0x40 #define RX_IRQ_BANK_PIN_MASK(_n) \ diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c index 2de974213090..e2e850c1b90b 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c @@ -3400,7 +3400,7 @@ static void xgbe_enable_rx(struct xgbe_prv_data *pdata) XGMAC_IOWRITE(pdata, MAC_RQC0R, reg_val); /* Enable MAC Rx */ - XGMAC_IOWRITE_BITS(pdata, MAC_RCR, DCRCC, 1); + XGMAC_IOWRITE_BITS(pdata, MAC_RCR, DCRCC, 0); XGMAC_IOWRITE_BITS(pdata, MAC_RCR, CST, 1); XGMAC_IOWRITE_BITS(pdata, MAC_RCR, ACS, 1); XGMAC_IOWRITE_BITS(pdata, MAC_RCR, RE, 1); @@ -3411,7 +3411,6 @@ static void xgbe_disable_rx(struct xgbe_prv_data *pdata) unsigned int i; /* Disable MAC Rx */ - XGMAC_IOWRITE_BITS(pdata, MAC_RCR, DCRCC, 0); XGMAC_IOWRITE_BITS(pdata, MAC_RCR, CST, 0); XGMAC_IOWRITE_BITS(pdata, MAC_RCR, ACS, 0); XGMAC_IOWRITE_BITS(pdata, MAC_RCR, RE, 0); diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index 1e1f52285a39..d6931c41f39d 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -968,6 +968,8 @@ struct macb_dma_desc_ptp { * of the frame * @mapping: DMA address of the skb's fragment buffer * @size: size of the DMA mapped buffer + * @fcs_len: FCS bytes appended in software, 0 or ETH_FCS_LEN, only + * set for the last buffer of the frame * @mapped_as_page: true when buffer was mapped with skb_frag_dma_map(), * false when buffer was mapped with dma_map_single() */ @@ -975,6 +977,7 @@ struct macb_tx_skb { struct sk_buff *skb; dma_addr_t mapping; size_t size; + u8 fcs_len; bool mapped_as_page; }; diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 76ee4f506033..b1939da4c95a 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1322,8 +1322,8 @@ static void macb_tx_error_task(struct work_struct *work) bp->netdev->stats.tx_packets++; queue->stats.tx_packets++; packets++; - bp->netdev->stats.tx_bytes += skb->len; - queue->stats.tx_bytes += skb->len; + bp->netdev->stats.tx_bytes += skb->len - tx_skb->fcs_len; + queue->stats.tx_bytes += skb->len - tx_skb->fcs_len; bytes += skb->len; } } else { @@ -1450,8 +1450,8 @@ static int macb_tx_complete(struct macb_queue *queue, int budget) skb->data); bp->netdev->stats.tx_packets++; queue->stats.tx_packets++; - bp->netdev->stats.tx_bytes += skb->len; - queue->stats.tx_bytes += skb->len; + bp->netdev->stats.tx_bytes += skb->len - tx_skb->fcs_len; + queue->stats.tx_bytes += skb->len - tx_skb->fcs_len; packets++; bytes += skb->len; } @@ -2199,7 +2199,8 @@ static void macb_poll_controller(struct net_device *netdev) static unsigned int macb_tx_map(struct macb *bp, struct macb_queue *queue, struct sk_buff *skb, - unsigned int hdrlen) + unsigned int hdrlen, + u8 fcs_len) { unsigned int f, nr_frags = skb_shinfo(skb)->nr_frags; unsigned int len, i, tx_head = queue->tx_head; @@ -2284,6 +2285,7 @@ static unsigned int macb_tx_map(struct macb *bp, /* This is the last buffer of the frame: save socket buffer */ tx_skb->skb = skb; + tx_skb->fcs_len = fcs_len; /* Update TX ring: update buffer descriptors in reverse order * to avoid race condition @@ -2417,6 +2419,7 @@ static inline int macb_clear_csum(struct sk_buff *skb) return 0; } +/* Returns a negative errno, or the FCS bytes appended (0 or ETH_FCS_LEN). */ static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *netdev) { bool cloned = skb_cloned(*skb) || skb_header_cloned(*skb) || @@ -2465,7 +2468,7 @@ add_fcs: skb_put_u8(*skb, (fcs >> 16) & 0xff); skb_put_u8(*skb, (fcs >> 24) & 0xff); - return 0; + return ETH_FCS_LEN; } static netdev_tx_t macb_start_xmit(struct sk_buff *skb, @@ -2478,6 +2481,7 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, netdev_tx_t ret = NETDEV_TX_OK; unsigned int hdrlen; unsigned long flags; + int fcs_len; bool is_lso; if (macb_clear_csum(skb)) { @@ -2485,7 +2489,8 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, return ret; } - if (macb_pad_and_fcs(&skb, netdev)) { + fcs_len = macb_pad_and_fcs(&skb, netdev); + if (fcs_len < 0) { dev_kfree_skb_any(skb); return ret; } @@ -2548,7 +2553,7 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, } /* Map socket buffer for DMA transfer */ - if (macb_tx_map(bp, queue, skb, hdrlen)) { + if (macb_tx_map(bp, queue, skb, hdrlen, fcs_len)) { dev_kfree_skb_any(skb); goto unlock; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index 74c041ab5280..937b085582b5 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -3468,6 +3468,8 @@ err: return ret; } +#define PCI_DEVID_OCTEONTX2_RVU_AFVF 0xA0F8 + static int rvu_enable_sriov(struct rvu *rvu) { struct pci_dev *pdev = rvu->pdev; @@ -3486,24 +3488,27 @@ static int rvu_enable_sriov(struct rvu *rvu) return 0; pci_read_config_word(pdev, pos + PCI_SRIOV_VF_DID, &rvu->vf_devid); - chans = rvu_get_num_lbk_chans(); - if (chans < 0) - return chans; - vfs = pci_sriov_get_totalvfs(pdev); - - /* Limit VFs in case we have more VFs than LBK channels available. */ - if (vfs > chans) - vfs = chans; - if (!vfs) return 0; - /* LBK channel number 63 is used for switching packets between - * CGX mapped VFs. Hence limit LBK pairs till 62 only. - */ - if (vfs > 62) - vfs = 62; + if (rvu->vf_devid == PCI_DEVID_OCTEONTX2_RVU_AFVF) { + chans = rvu_get_num_lbk_chans(); + if (chans < 0) + return chans; + + /* The last LBK channel is reserved for switching packets between + * CGX mapped VFs. Also, since LBK VFs work in pairs, limit VF + * count to available LBK channels minus 2. + */ + vfs = min(vfs, chans - 2); + + if (vfs <= 0) { + dev_warn(&pdev->dev, + "Skipping SRIOV enablement, not enough LBK channels available\n"); + return 0; + } + } /* Save VFs number for reference in VF interrupts handlers. * Since interrupts might start arriving during SRIOV enablement diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index 60922944675b..c34f8d86cc8a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -2957,10 +2957,9 @@ static void npc_mcam_free_all_entries(struct rvu *rvu, struct npc_mcam *mcam, } } - /* Disable the entry */ - npc_enable_mcam_entry(rvu, mcam, blkaddr, index, false); - if (!cn20k_dft_rl) { + /* Disable the entry */ + npc_enable_mcam_entry(rvu, mcam, blkaddr, index, false); mcam->entry2pfvf_map[index] = NPC_MCAM_INVALID_MAP; /* Free the entry in bitmap */ npc_mcam_clear_bit(mcam, index); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c index 4f984f6a2cb9..55ec6387ab28 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c @@ -3,6 +3,7 @@ #include "rx.h" #include "en/xdp.h" +#include <linux/bitmap.h> #include <net/xdp_sock_drv.h> #include <linux/filter.h> @@ -156,6 +157,7 @@ err_reuse_batch: xsk_buff_free(xsk_buffs[batch]); err: + bitmap_fill(wi->skip_release_bitmap, rq->mpwqe.pages_per_wqe); rq->stats->buff_alloc_err++; return -ENOMEM; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 206cf9db3466..7bd0606a5253 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -410,8 +410,11 @@ static inline void mlx5e_free_rx_wqe(struct mlx5e_rq *rq, static void mlx5e_xsk_free_rx_wqe(struct mlx5e_wqe_frag_info *wi) { - if (!(wi->flags & BIT(MLX5E_WQE_FRAG_SKIP_RELEASE))) - xsk_buff_free(*wi->xskp); + if (wi->flags & BIT(MLX5E_WQE_FRAG_SKIP_RELEASE)) + return; + + xsk_buff_free(*wi->xskp); + wi->flags |= BIT(MLX5E_WQE_FRAG_SKIP_RELEASE); } static void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix) diff --git a/drivers/net/ethernet/oa_tc6.c b/drivers/net/ethernet/oa_tc6.c index 417c15d1ff42..6fcc5f561d56 100644 --- a/drivers/net/ethernet/oa_tc6.c +++ b/drivers/net/ethernet/oa_tc6.c @@ -83,7 +83,7 @@ struct oa_tc6 { u16 spi_data_tx_buf_offset; u16 tx_credits; u8 rx_chunks_available; - bool rx_buf_overflow; + bool wait_until_start_valid; bool int_flag; bool disable_traffic; bool prot_ctrl; @@ -455,7 +455,7 @@ static int oa_tc6_mdiobus_read(struct mii_bus *bus, int addr, int regnum) { struct oa_tc6 *tc6 = bus->priv; u32 regval; - bool ret; + int ret; ret = oa_tc6_read_register(tc6, OA_TC6_PHY_STD_REG_ADDR_BASE | (regnum & OA_TC6_PHY_STD_REG_ADDR_MASK), @@ -693,6 +693,26 @@ static int oa_tc6_enable_data_transfer(struct oa_tc6 *tc6) return oa_tc6_write_register(tc6, OA_TC6_REG_CONFIG0, value); } +/* Called when a frame that is meant to be transmitted, is dropped. */ +static void oa_tc6_drop_tx_skb(struct oa_tc6 *tc6, struct sk_buff *skb) +{ + if (skb) { + tc6->netdev->stats.tx_dropped++; + dev_kfree_skb_any(skb); + } +} + +static struct sk_buff *oa_tc6_detach_waiting_tx_skb(struct oa_tc6 *tc6) +{ + struct sk_buff *skb; + + lockdep_assert_held(&tc6->tx_skb_lock); + skb = tc6->waiting_tx_skb; + tc6->waiting_tx_skb = NULL; + + return skb; +} + static void oa_tc6_cleanup_ongoing_rx_skb(struct oa_tc6 *tc6) { if (tc6->rx_skb) { @@ -704,29 +724,39 @@ static void oa_tc6_cleanup_ongoing_rx_skb(struct oa_tc6 *tc6) static void oa_tc6_cleanup_ongoing_tx_skb(struct oa_tc6 *tc6) { - if (tc6->ongoing_tx_skb) { - tc6->netdev->stats.tx_dropped++; - kfree_skb(tc6->ongoing_tx_skb); - tc6->ongoing_tx_skb = NULL; - } + oa_tc6_drop_tx_skb(tc6, tc6->ongoing_tx_skb); + tc6->ongoing_tx_skb = NULL; } static void oa_tc6_cleanup_waiting_tx_skb(struct oa_tc6 *tc6) { - if (tc6->waiting_tx_skb) { - tc6->netdev->stats.tx_dropped++; - kfree_skb(tc6->waiting_tx_skb); - tc6->waiting_tx_skb = NULL; - } + struct sk_buff *skb; + + spin_lock_bh(&tc6->tx_skb_lock); + skb = oa_tc6_detach_waiting_tx_skb(tc6); + spin_unlock_bh(&tc6->tx_skb_lock); + + oa_tc6_drop_tx_skb(tc6, skb); } -static void oa_tc6_free_pending_skbs(struct oa_tc6 *tc6) +static void oa_tc6_free_ongoing_skbs(struct oa_tc6 *tc6) { oa_tc6_cleanup_ongoing_tx_skb(tc6); oa_tc6_cleanup_ongoing_rx_skb(tc6); +} + +static void oa_tc6_free_pending_skbs(struct oa_tc6 *tc6) +{ + oa_tc6_free_ongoing_skbs(tc6); oa_tc6_cleanup_waiting_tx_skb(tc6); } +static void oa_tc6_look_for_new_frame(struct oa_tc6 *tc6) +{ + tc6->wait_until_start_valid = true; + oa_tc6_cleanup_ongoing_rx_skb(tc6); +} + /* If the failure is at SPI interface level, masking and clearing * the interrupt of the device won't work. Since SPI interrupt is * disabled, it should stop the repeated interrupts. @@ -734,9 +764,19 @@ static void oa_tc6_free_pending_skbs(struct oa_tc6 *tc6) static void oa_tc6_disable_traffic(struct oa_tc6 *tc6) { u32 regval = OA_TC6_INT_MASK0_ALL_INTERRUPTS; + struct sk_buff *skb; + spin_lock_bh(&tc6->tx_skb_lock); tc6->disable_traffic = true; - oa_tc6_free_pending_skbs(tc6); + skb = oa_tc6_detach_waiting_tx_skb(tc6); + spin_unlock_bh(&tc6->tx_skb_lock); + + /* disable_traffic, when set, is a point of no return to + * working state. Keeping the TX queues disabled. + */ + netif_tx_disable(tc6->netdev); + oa_tc6_drop_tx_skb(tc6, skb); + oa_tc6_free_ongoing_skbs(tc6); oa_tc6_write_register(tc6, OA_TC6_REG_INT_MASK0, regval); oa_tc6_read_register(tc6, OA_TC6_REG_STATUS0, ®val); oa_tc6_write_register(tc6, OA_TC6_REG_STATUS0, regval); @@ -755,6 +795,13 @@ static int oa_tc6_process_extended_status(struct oa_tc6 *tc6) return ret; } + /* This function is called for each chunk received in a given SPI + * transaction. In case, extended status bit is set in more than + * one chunk, skip the write, if status0 is already cleared. + */ + if (!value) + return 0; + /* Clear the error interrupts status */ ret = oa_tc6_write_register(tc6, OA_TC6_REG_STATUS0, value); if (ret) { @@ -764,8 +811,7 @@ static int oa_tc6_process_extended_status(struct oa_tc6 *tc6) } if (FIELD_GET(OA_TC6_STATUS0_RX_BUFFER_OVERFLOW_ERROR, value)) { - tc6->rx_buf_overflow = true; - oa_tc6_cleanup_ongoing_rx_skb(tc6); + oa_tc6_look_for_new_frame(tc6); net_err_ratelimited("%s: Receive buffer overflow error\n", tc6->netdev->name); return -EAGAIN; @@ -791,6 +837,8 @@ static int oa_tc6_process_extended_status(struct oa_tc6 *tc6) static int oa_tc6_process_rx_chunk_footer(struct oa_tc6 *tc6, u32 footer) { + int ret = 0; + /* Process rx chunk footer for the following, * 1. tx credits * 2. errors if any from MAC-PHY @@ -801,9 +849,11 @@ static int oa_tc6_process_rx_chunk_footer(struct oa_tc6 *tc6, u32 footer) footer); if (FIELD_GET(OA_TC6_DATA_FOOTER_EXTENDED_STS, footer)) { - int ret = oa_tc6_process_extended_status(tc6); - - if (ret) + ret = oa_tc6_process_extended_status(tc6); + /* EAGAIN error is recoverable. Move on to check + * HEADER and SYNC errors before returning. + */ + if (ret && ret != -EAGAIN) return ret; } @@ -821,7 +871,7 @@ static int oa_tc6_process_rx_chunk_footer(struct oa_tc6 *tc6, u32 footer) return -ENODEV; } - return 0; + return ret; } static void oa_tc6_submit_rx_skb(struct oa_tc6 *tc6) @@ -846,13 +896,35 @@ static void oa_tc6_submit_rx_skb(struct oa_tc6 *tc6) tc6->rx_skb = NULL; } -static void oa_tc6_update_rx_skb(struct oa_tc6 *tc6, u8 *payload, u8 length) +/* On oversubscribed traffic condition, particularly with overwhelming rx + * buffer overflow errors, there could be data chunk loss. If tail + length + * goes beyond end pointer, that is an indication that the data chunk with + * end_valid bit is lost. Time to look for a data chunk with start_valid bit. + * + * If rx_skb is NULL, it is time to start looking for data chunk with + * start_bit. + */ +static int oa_tc6_update_rx_skb(struct oa_tc6 *tc6, u8 *payload, u8 length) { + if (!tc6->rx_skb || + skb_tailroom(tc6->rx_skb) < length) { + oa_tc6_look_for_new_frame(tc6); + return -EAGAIN; + } + memcpy(skb_put(tc6->rx_skb, length), payload, length); + return 0; } +/* On overwhelming rx buffer overflow errors, due to data chunk loss, it is + * possible that we get two data chunks with start_valid bit set, without + * end_valid bit set in between. In this case, rx_skb would have a valid + * buffer pointer. We should release, if a valid pointer is found before + * allocating a new one. + */ static int oa_tc6_allocate_rx_skb(struct oa_tc6 *tc6) { + oa_tc6_cleanup_ongoing_rx_skb(tc6); tc6->rx_skb = netdev_alloc_skb_ip_align(tc6->netdev, tc6->netdev->mtu + ETH_HLEN + ETH_FCS_LEN); if (!tc6->rx_skb) { @@ -872,7 +944,9 @@ static int oa_tc6_prcs_complete_rx_frame(struct oa_tc6 *tc6, u8 *payload, if (ret) return ret; - oa_tc6_update_rx_skb(tc6, payload, size); + ret = oa_tc6_update_rx_skb(tc6, payload, size); + if (ret) + return ret; oa_tc6_submit_rx_skb(tc6); @@ -887,22 +961,24 @@ static int oa_tc6_prcs_rx_frame_start(struct oa_tc6 *tc6, u8 *payload, u16 size) if (ret) return ret; - oa_tc6_update_rx_skb(tc6, payload, size); - - return 0; + return oa_tc6_update_rx_skb(tc6, payload, size); } -static void oa_tc6_prcs_rx_frame_end(struct oa_tc6 *tc6, u8 *payload, u16 size) +static int oa_tc6_prcs_rx_frame_end(struct oa_tc6 *tc6, u8 *payload, u16 size) { - oa_tc6_update_rx_skb(tc6, payload, size); + int ret; - oa_tc6_submit_rx_skb(tc6); + ret = oa_tc6_update_rx_skb(tc6, payload, size); + if (!ret) + oa_tc6_submit_rx_skb(tc6); + return ret; } -static void oa_tc6_prcs_ongoing_rx_frame(struct oa_tc6 *tc6, u8 *payload, - u32 footer) +static int oa_tc6_prcs_ongoing_rx_frame(struct oa_tc6 *tc6, u8 *payload, + u32 footer) { - oa_tc6_update_rx_skb(tc6, payload, OA_TC6_CHUNK_PAYLOAD_SIZE); + return oa_tc6_update_rx_skb(tc6, payload, + OA_TC6_CHUNK_PAYLOAD_SIZE); } static int oa_tc6_prcs_rx_chunk_payload(struct oa_tc6 *tc6, u8 *data, @@ -917,10 +993,10 @@ static int oa_tc6_prcs_rx_chunk_payload(struct oa_tc6 *tc6, u8 *data, u16 size; /* Restart the new rx frame after receiving rx buffer overflow error */ - if (start_valid && tc6->rx_buf_overflow) - tc6->rx_buf_overflow = false; + if (start_valid && tc6->wait_until_start_valid) + tc6->wait_until_start_valid = false; - if (tc6->rx_buf_overflow) + if (tc6->wait_until_start_valid) return 0; /* Process the chunk with complete rx frame */ @@ -942,8 +1018,7 @@ static int oa_tc6_prcs_rx_chunk_payload(struct oa_tc6 *tc6, u8 *data, /* Process the chunk with only rx frame end */ if (end_valid && !start_valid) { size = end_byte_offset + 1; - oa_tc6_prcs_rx_frame_end(tc6, data, size); - return 0; + return oa_tc6_prcs_rx_frame_end(tc6, data, size); } /* Process the chunk with previous rx frame end and next rx frame @@ -957,6 +1032,15 @@ static int oa_tc6_prcs_rx_chunk_payload(struct oa_tc6 *tc6, u8 *data, if (tc6->rx_skb) { size = end_byte_offset + 1; oa_tc6_prcs_rx_frame_end(tc6, data, size); + + /* Return value from oa_tc6_prcs_rx_frame_end is not + * checked. If it returned an error, it is to make + * the code to look for new frame. At this stage, + * code below is going to process a new frame. So, + * error condition is set to false, in case it is + * set before proceeding. + */ + tc6->wait_until_start_valid = false; } size = OA_TC6_CHUNK_PAYLOAD_SIZE - start_byte_offset; return oa_tc6_prcs_rx_frame_start(tc6, @@ -965,9 +1049,7 @@ static int oa_tc6_prcs_rx_chunk_payload(struct oa_tc6 *tc6, u8 *data, } /* Process the chunk with ongoing rx frame data */ - oa_tc6_prcs_ongoing_rx_frame(tc6, data, footer); - - return 0; + return oa_tc6_prcs_ongoing_rx_frame(tc6, data, footer); } static u32 oa_tc6_get_rx_chunk_footer(struct oa_tc6 *tc6, u16 footer_offset) @@ -983,8 +1065,9 @@ static u32 oa_tc6_get_rx_chunk_footer(struct oa_tc6 *tc6, u16 footer_offset) static int oa_tc6_process_spi_data_rx_buf(struct oa_tc6 *tc6, u16 length) { u16 no_of_rx_chunks = length / OA_TC6_CHUNK_SIZE; + bool retry = false; + int ret = 0; u32 footer; - int ret; /* All the rx chunks in the receive SPI data buffer are examined here */ for (int i = 0; i < no_of_rx_chunks; i++) { @@ -993,8 +1076,11 @@ static int oa_tc6_process_spi_data_rx_buf(struct oa_tc6 *tc6, u16 length) OA_TC6_CHUNK_PAYLOAD_SIZE); ret = oa_tc6_process_rx_chunk_footer(tc6, footer); - if (ret) - return ret; + if (ret) { + if (ret != -EAGAIN) + return ret; + retry = true; + } /* If there is a data valid chunks then process it for the * information needed to determine the validity and the location @@ -1006,12 +1092,35 @@ static int oa_tc6_process_spi_data_rx_buf(struct oa_tc6 *tc6, u16 length) ret = oa_tc6_prcs_rx_chunk_payload(tc6, payload, footer); - if (ret) - return ret; + if (ret) { + if (ret != -ENOMEM && ret != -EAGAIN) + return ret; + retry = true; + } } } - return 0; + /* Not bailing out on recoverable error codes, -EAGAIN and + * -ENOMEM. If subsequent loop iterations, if any, succeeds, + * error code would be overwritten. retry flag helps to + * make the caller to continue and retry. Since recovery + * action for -ENOMEM and -EAGAIN are same, we are returning + * one of the error codes, that is -EAGAIN. + * + * Successful recovery depends on how small the frames are, + * how many chunks, among the received chunks triggered the + * error, whether data is intact even with error conditions. + * As a result, there is no single, best method to recover + * most data when error conditions hit. We do our best by + * processing all the chunks with good "footer header" and + * "data valid" bit set. + */ + if (retry) { + ret = -EAGAIN; + oa_tc6_look_for_new_frame(tc6); + } + + return ret; } static __be32 oa_tc6_prepare_data_header(bool data_valid, bool start_valid, @@ -1173,12 +1282,9 @@ static int oa_tc6_try_spi_transfer(struct oa_tc6 *tc6) } ret = oa_tc6_process_spi_data_rx_buf(tc6, spi_len); - if (ret) { - if (ret == -EAGAIN) - continue; - oa_tc6_cleanup_ongoing_tx_skb(tc6); - oa_tc6_cleanup_ongoing_rx_skb(tc6); + if (ret && ret != -EAGAIN) { + oa_tc6_free_ongoing_skbs(tc6); netdev_err(tc6->netdev, "Device error: %d\n", ret); return ret; } @@ -1200,15 +1306,20 @@ static irqreturn_t oa_tc6_macphy_threaded_irq(int irq, void *data) * no need to attempt spi transfer, once it fails. Pending skbs * are already freed. */ - if (!tc6->disable_traffic) { - while (tc6->int_flag || - (tc6->waiting_tx_skb && tc6->tx_credits)) { - ret = oa_tc6_try_spi_transfer(tc6); - if (ret) { - disable_irq_nosync(tc6->spi->irq); - oa_tc6_disable_traffic(tc6); - break; - } + spin_lock_bh(&tc6->tx_skb_lock); + if (tc6->disable_traffic) { + spin_unlock_bh(&tc6->tx_skb_lock); + return IRQ_HANDLED; + } + spin_unlock_bh(&tc6->tx_skb_lock); + + while (tc6->int_flag || + (tc6->waiting_tx_skb && tc6->tx_credits)) { + ret = oa_tc6_try_spi_transfer(tc6); + if (ret) { + disable_irq_nosync(tc6->spi->irq); + oa_tc6_disable_traffic(tc6); + break; } } @@ -1287,23 +1398,30 @@ EXPORT_SYMBOL_GPL(oa_tc6_zero_align_receive_frame_enable); * @tc6: oa_tc6 struct. * @skb: socket buffer in which the ethernet frame is stored. * - * Return: NETDEV_TX_OK if the transmit ethernet frame skb added in the tx_skb_q - * otherwise returns NETDEV_TX_BUSY. + * Return: NETDEV_TX_OK either on successful queueing of the packet for + * transmission, or on packet getting dropped. Packet can be dropped due to + * failure in linearizing the buffer or disable_traffic is set due to + * earlier fatal error. Returns NETDEV_TX_BUSY when there is no room + * to queue the packet. */ netdev_tx_t oa_tc6_start_xmit(struct oa_tc6 *tc6, struct sk_buff *skb) { - if (tc6->disable_traffic || tc6->waiting_tx_skb) { - netif_stop_queue(tc6->netdev); - return NETDEV_TX_BUSY; - } - if (skb_linearize(skb)) { - dev_kfree_skb_any(skb); - tc6->netdev->stats.tx_dropped++; + oa_tc6_drop_tx_skb(tc6, skb); return NETDEV_TX_OK; } spin_lock_bh(&tc6->tx_skb_lock); + if (tc6->waiting_tx_skb) { + netif_stop_queue(tc6->netdev); + spin_unlock_bh(&tc6->tx_skb_lock); + return NETDEV_TX_BUSY; + } + if (tc6->disable_traffic) { + spin_unlock_bh(&tc6->tx_skb_lock); + oa_tc6_drop_tx_skb(tc6, skb); + return NETDEV_TX_OK; + } tc6->waiting_tx_skb = skb; spin_unlock_bh(&tc6->tx_skb_lock); @@ -1462,8 +1580,10 @@ EXPORT_SYMBOL_GPL(oa_tc6_init); */ void oa_tc6_exit(struct oa_tc6 *tc6) { - tc6->disable_traffic = true; disable_irq(tc6->spi->irq); + spin_lock_bh(&tc6->tx_skb_lock); + tc6->disable_traffic = true; + spin_unlock_bh(&tc6->tx_skb_lock); oa_tc6_phy_exit(tc6); oa_tc6_free_pending_skbs(tc6); } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index f2fc89176654..24656b35350b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3676,6 +3676,14 @@ static int stmmac_hw_setup(struct net_device *dev) /* Initialize MTL*/ stmmac_mtl_configuration(priv); + /* Apply the RX packet parser table */ + if (priv->tc_entries) { + ret = stmmac_rxp_config(priv, priv->hw->pcsr, priv->tc_entries, + priv->tc_entries_max); + if (ret) + return ret; + } + /* Initialize Safety Features */ stmmac_safety_feat_configuration(priv); @@ -4319,6 +4327,7 @@ static bool stmmac_vlan_insert(struct stmmac_priv *priv, struct sk_buff *skb, /** * stmmac_tso_allocator - close entry point of the driver * @priv: driver private structure + * @entry: TX queue buffer index * @des: buffer start address * @total_len: total length to fill in descriptors * @last_segment: condition for the last descriptor @@ -4327,8 +4336,9 @@ static bool stmmac_vlan_insert(struct stmmac_priv *priv, struct sk_buff *skb, * This function fills descriptor and request new descriptors according to * buffer length to fill */ -static void stmmac_tso_allocator(struct stmmac_priv *priv, dma_addr_t des, - int total_len, bool last_segment, u32 queue) +static void stmmac_tso_allocator(struct stmmac_priv *priv, u32 *entry, + dma_addr_t des, int total_len, + bool last_segment, u32 queue) { struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[queue]; struct dma_desc *desc; @@ -4340,14 +4350,13 @@ static void stmmac_tso_allocator(struct stmmac_priv *priv, dma_addr_t des, while (tmp_len > 0) { dma_addr_t curr_addr; - tx_q->cur_tx = STMMAC_NEXT_ENTRY(tx_q->cur_tx, - priv->dma_conf.dma_tx_size); - WARN_ON(tx_q->tx_skbuff[tx_q->cur_tx]); + *entry = STMMAC_NEXT_ENTRY(*entry, priv->dma_conf.dma_tx_size); + WARN_ON(tx_q->tx_skbuff[*entry]); if (tx_q->tbs & STMMAC_TBS_AVAIL) - desc = &tx_q->dma_entx[tx_q->cur_tx].basic; + desc = &tx_q->dma_entx[*entry].basic; else - desc = &tx_q->dma_tx[tx_q->cur_tx]; + desc = &tx_q->dma_tx[*entry]; curr_addr = des + (total_len - tmp_len); stmmac_set_desc_addr(priv, desc, curr_addr); @@ -4486,7 +4495,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) { struct dma_desc *desc, *first, *mss_desc = NULL; struct stmmac_priv *priv = netdev_priv(dev); - unsigned int first_entry, tx_packets; + unsigned int first_entry, entry, tx_packets; struct stmmac_txq_stats *txq_stats; struct stmmac_tx_queue *tx_q; bool set_ic, is_last_segment; @@ -4549,22 +4558,24 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) } first_entry = tx_q->cur_tx; - WARN_ON(tx_q->tx_skbuff[first_entry]); + entry = first_entry; + + WARN_ON(tx_q->tx_skbuff[entry]); if (tx_q->tbs & STMMAC_TBS_AVAIL) - desc = &tx_q->dma_entx[first_entry].basic; + desc = &tx_q->dma_entx[entry].basic; else - desc = &tx_q->dma_tx[first_entry]; + desc = &tx_q->dma_tx[entry]; first = desc; /* first descriptor: fill Headers on Buf1 */ des = dma_map_single(priv->device, skb->data, skb_headlen(skb), DMA_TO_DEVICE); if (dma_mapping_error(priv->device, des)) - goto dma_map_err; + goto error; stmmac_set_desc_addr(priv, first, des); - stmmac_tso_allocator(priv, des + proto_hdr_len, pay_len, + stmmac_tso_allocator(priv, &entry, des + proto_hdr_len, pay_len, (nfrags == 0), queue); /* In case two or more DMA transmit descriptors are allocated for this @@ -4579,8 +4590,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) * this DMA buffer right after the DMA engine completely finishes the * full buffer transmission. */ - stmmac_set_tx_skb_dma_entry(tx_q, tx_q->cur_tx, des, skb_headlen(skb), - false); + stmmac_set_tx_skb_dma_entry(tx_q, entry, des, skb_headlen(skb), false); /* Prepare fragments */ for (i = 0; i < nfrags; i++) { @@ -4590,14 +4600,15 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) skb_frag_size(frag), DMA_TO_DEVICE); if (dma_mapping_error(priv->device, des)) - goto dma_map_err; + goto error_dma_unmap; - stmmac_tso_allocator(priv, des, skb_frag_size(frag), + stmmac_tso_allocator(priv, &entry, des, skb_frag_size(frag), (i == nfrags - 1), queue); - stmmac_set_tx_skb_dma_entry(tx_q, tx_q->cur_tx, des, + stmmac_set_tx_skb_dma_entry(tx_q, entry, des, skb_frag_size(frag), true); } + tx_q->cur_tx = entry; stmmac_set_tx_dma_last_segment(tx_q, tx_q->cur_tx); @@ -4702,7 +4713,19 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; -dma_map_err: +error_dma_unmap: + for (;;) { + desc = stmmac_get_tx_desc(priv, tx_q, first_entry); + stmmac_release_tx_desc(priv, desc, priv->descriptor_mode); + stmmac_free_tx_buffer(priv, &priv->dma_conf, queue, + first_entry); + if (first_entry == entry) + break; + + first_entry = STMMAC_NEXT_ENTRY(first_entry, + priv->dma_conf.dma_tx_size); + } +error: dev_err(priv->device, "Tx dma map failed\n"); dev_kfree_skb(skb); priv->xstats.tx_dropped++; diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 298efc76a56b..69fe5717846b 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -318,6 +318,11 @@ static int gtp_inner_proto(struct sk_buff *skb, unsigned int hdrlen, static int gtp_rx(struct pdp_ctx *pctx, struct sk_buff *skb, unsigned int hdrlen, unsigned int role, __u16 inner_proto) { + if (skb_is_gso(skb)) { + netdev_dbg(pctx->dev, "GSO is not supported in GTP\n"); + goto err; + } + if (!gtp_check_ms(skb, pctx, hdrlen, role, inner_proto)) { netdev_dbg(pctx->dev, "No PDP ctx for this MS\n"); return 1; diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 4939cf67b336..f29864db662a 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -848,7 +848,6 @@ static int ipvlan_device_event(struct notifier_block *unused, __ipvlan_link_delete(net, ipvlan->dev, &lst_kill); } - unregister_netdevice_many(&lst_kill); break; } case NETDEV_FEAT_CHANGE: @@ -899,6 +898,9 @@ static int ipvlan_device_event(struct notifier_block *unused, mutex_unlock(&port->pnodes_lock); + /* Avoid invoking nested netdevice notifiers under pnodes_lock. */ + unregister_netdevice_many(&lst_kill); + ipvlan_port_put(port); return ret; diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c index 9c171697e762..2c04be6d61a8 100644 --- a/drivers/net/ntb_netdev.c +++ b/drivers/net/ntb_netdev.c @@ -127,8 +127,10 @@ static void ntb_netdev_rx_handler(struct ntb_transport_qp *qp, void *qp_data, { struct ntb_netdev_queue *q = qp_data; struct ntb_netdev *dev = q->ntdev; + struct pcpu_sw_netstats *tstats; struct sk_buff *skb, *new_skb; struct net_device *ndev; + unsigned long flags; int rc; ndev = dev->ndev; @@ -139,17 +141,20 @@ static void ntb_netdev_rx_handler(struct ntb_transport_qp *qp, void *qp_data, netdev_dbg(ndev, "%s: %d byte payload received\n", __func__, len); if (len < 0) { - ndev->stats.rx_errors++; - ndev->stats.rx_length_errors++; + DEV_STATS_INC(ndev, rx_errors); + DEV_STATS_INC(ndev, rx_length_errors); goto enqueue_again; } - ndev->stats.rx_packets++; - ndev->stats.rx_bytes += len; + tstats = this_cpu_ptr(ndev->tstats); + flags = u64_stats_update_begin_irqsave(&tstats->syncp); + u64_stats_inc(&tstats->rx_packets); + u64_stats_add(&tstats->rx_bytes, len); + u64_stats_update_end_irqrestore(&tstats->syncp, flags); new_skb = netdev_alloc_skb(ndev, ndev->mtu + ETH_HLEN); if (!new_skb) { - ndev->stats.rx_dropped++; + DEV_STATS_INC(ndev, rx_dropped); goto enqueue_again; } @@ -166,8 +171,8 @@ enqueue_again: rc = ntb_transport_rx_enqueue(qp, skb, skb->data, ndev->mtu + ETH_HLEN); if (rc) { dev_kfree_skb_any(skb); - ndev->stats.rx_errors++; - ndev->stats.rx_fifo_errors++; + DEV_STATS_INC(ndev, rx_errors); + DEV_STATS_INC(ndev, rx_fifo_errors); } } @@ -210,25 +215,39 @@ static void ntb_netdev_tx_handler(struct ntb_transport_qp *qp, void *qp_data, { struct ntb_netdev_queue *q = qp_data; struct ntb_netdev *dev = q->ntdev; + struct pcpu_sw_netstats *tstats; struct net_device *ndev; struct sk_buff *skb; + unsigned long flags; + bool registered; ndev = dev->ndev; skb = data; if (!skb || !ndev) return; + rcu_read_lock(); + registered = READ_ONCE(ndev->reg_state) == NETREG_REGISTERED; + if (!registered) + goto free_skb; + if (len > 0) { - ndev->stats.tx_packets++; - ndev->stats.tx_bytes += skb->len; + /* The memcpy kthread can migrate, so pin the per-CPU update. */ + tstats = get_cpu_ptr(ndev->tstats); + flags = u64_stats_update_begin_irqsave(&tstats->syncp); + u64_stats_inc(&tstats->tx_packets); + u64_stats_add(&tstats->tx_bytes, skb->len); + u64_stats_update_end_irqrestore(&tstats->syncp, flags); + put_cpu_ptr(ndev->tstats); } else { - ndev->stats.tx_errors++; - ndev->stats.tx_aborted_errors++; + DEV_STATS_INC(ndev, tx_errors); + DEV_STATS_INC(ndev, tx_aborted_errors); } +free_skb: dev_kfree_skb_any(skb); - if (ntb_transport_tx_free_entry(qp) >= tx_start) { + if (registered && ntb_transport_tx_free_entry(qp) >= tx_start) { /* Make sure anybody stopping the queue after this sees the new * value of ntb_transport_tx_free_entry() */ @@ -237,6 +256,7 @@ static void ntb_netdev_tx_handler(struct ntb_transport_qp *qp, void *qp_data, ntb_transport_link_query(q->qp)) netif_wake_subqueue(ndev, q->qid); } + rcu_read_unlock(); } static const struct ntb_queue_handlers ntb_netdev_handlers = { @@ -277,7 +297,7 @@ static netdev_tx_t ntb_netdev_start_xmit(struct sk_buff *skb, drop: dev_kfree_skb_any(skb); - ndev->stats.tx_dropped++; + DEV_STATS_INC(ndev, tx_dropped); return NETDEV_TX_OK; } @@ -647,6 +667,7 @@ static int ntb_netdev_probe(struct device *client_dev) } ndev->features = NETIF_F_HIGHDMA; + ndev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE; diff --git a/drivers/net/ppp/ppp_async.c b/drivers/net/ppp/ppp_async.c index 583426d06381..ea7fe9608ffd 100644 --- a/drivers/net/ppp/ppp_async.c +++ b/drivers/net/ppp/ppp_async.c @@ -63,8 +63,6 @@ struct asyncppp { struct tasklet_struct tsk; - refcount_t refcnt; - struct completion dead; struct ppp_channel chan; /* interface to generic ppp layer */ unsigned char obuf[OBUFSIZE]; }; @@ -115,38 +113,6 @@ static const struct ppp_channel_ops async_ops = { */ /* - * We have a potential race on dereferencing tty->disc_data, - * because the tty layer provides no locking at all - thus one - * cpu could be running ppp_asynctty_receive while another - * calls ppp_asynctty_close, which zeroes tty->disc_data and - * frees the memory that ppp_asynctty_receive is using. The best - * way to fix this is to use a rwlock in the tty struct, but for now - * we use a single global rwlock for all ttys in ppp line discipline. - * - * FIXME: this is no longer true. The _close path for the ldisc is - * now guaranteed to be sane. - */ -static DEFINE_RWLOCK(disc_data_lock); - -static struct asyncppp *ap_get(struct tty_struct *tty) -{ - struct asyncppp *ap; - - read_lock(&disc_data_lock); - ap = tty->disc_data; - if (ap != NULL) - refcount_inc(&ap->refcnt); - read_unlock(&disc_data_lock); - return ap; -} - -static void ap_put(struct asyncppp *ap) -{ - if (refcount_dec_and_test(&ap->refcnt)) - complete(&ap->dead); -} - -/* * Called when a tty is put into PPP line discipline. Called in process * context. */ @@ -180,9 +146,6 @@ ppp_asynctty_open(struct tty_struct *tty) skb_queue_head_init(&ap->rqueue); tasklet_setup(&ap->tsk, ppp_async_process); - refcount_set(&ap->refcnt, 1); - init_completion(&ap->dead); - ap->chan.private = ap; ap->chan.ops = &async_ops; ap->chan.mtu = PPP_MRU; @@ -203,34 +166,18 @@ ppp_asynctty_open(struct tty_struct *tty) } /* - * Called when the tty is put into another line discipline - * or it hangs up. We have to wait for any cpu currently - * executing in any of the other ppp_asynctty_* routines to - * finish before we can call ppp_unregister_channel and free - * the asyncppp struct. This routine must be called from - * process context, not interrupt or softirq context. + * Called when the tty is put into another line discipline or it hangs up. + * This call is serialized against other ldisc functions. */ static void ppp_asynctty_close(struct tty_struct *tty) { - struct asyncppp *ap; + struct asyncppp *ap = tty->disc_data; - write_lock_irq(&disc_data_lock); - ap = tty->disc_data; - tty->disc_data = NULL; - write_unlock_irq(&disc_data_lock); if (!ap) return; - /* - * We have now ensured that nobody can start using ap from now - * on, but we have to wait for all existing users to finish. - * Note that ppp_unregister_channel ensures that no calls to - * our channel ops (i.e. ppp_async_send/ioctl) are in progress - * by the time it returns. - */ - if (!refcount_dec_and_test(&ap->refcnt)) - wait_for_completion(&ap->dead); + tty->disc_data = NULL; tasklet_kill(&ap->tsk); ppp_unregister_channel(&ap->chan); @@ -241,17 +188,6 @@ ppp_asynctty_close(struct tty_struct *tty) } /* - * Called on tty hangup in process context. - * - * Wait for I/O to driver to complete and unregister PPP channel. - * This is already done by the close routine, so just call that. - */ -static void ppp_asynctty_hangup(struct tty_struct *tty) -{ - ppp_asynctty_close(tty); -} - -/* * Read does nothing - no data is ever available this way. * Pppd reads and writes packets via /dev/ppp instead. */ @@ -281,7 +217,7 @@ ppp_asynctty_write(struct tty_struct *tty, struct file *file, const u8 *buf, static int ppp_asynctty_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { - struct asyncppp *ap = ap_get(tty); + struct asyncppp *ap = tty->disc_data; int err, val; int __user *p = (int __user *)arg; @@ -322,7 +258,6 @@ ppp_asynctty_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) err = tty_mode_ioctl(tty, cmd, arg); } - ap_put(ap); return err; } @@ -331,7 +266,7 @@ static void ppp_asynctty_receive(struct tty_struct *tty, const u8 *buf, const u8 *cflags, size_t count) { - struct asyncppp *ap = ap_get(tty); + struct asyncppp *ap = tty->disc_data; unsigned long flags; if (!ap) @@ -341,21 +276,19 @@ ppp_asynctty_receive(struct tty_struct *tty, const u8 *buf, const u8 *cflags, spin_unlock_irqrestore(&ap->recv_lock, flags); if (!skb_queue_empty(&ap->rqueue)) tasklet_schedule(&ap->tsk); - ap_put(ap); tty_unthrottle(tty); } static void ppp_asynctty_wakeup(struct tty_struct *tty) { - struct asyncppp *ap = ap_get(tty); + struct asyncppp *ap = tty->disc_data; clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags); if (!ap) return; set_bit(XMIT_WAKEUP, &ap->xmit_flags); tasklet_schedule(&ap->tsk); - ap_put(ap); } @@ -365,7 +298,6 @@ static struct tty_ldisc_ops ppp_ldisc = { .name = "ppp", .open = ppp_asynctty_open, .close = ppp_asynctty_close, - .hangup = ppp_asynctty_hangup, .read = ppp_asynctty_read, .write = ppp_asynctty_write, .ioctl = ppp_asynctty_ioctl, diff --git a/drivers/net/ppp/ppp_synctty.c b/drivers/net/ppp/ppp_synctty.c index 0b1bd1635c39..f87d43faeeab 100644 --- a/drivers/net/ppp/ppp_synctty.c +++ b/drivers/net/ppp/ppp_synctty.c @@ -38,11 +38,9 @@ #include <linux/ppp-ioctl.h> #include <linux/ppp_channel.h> #include <linux/spinlock.h> -#include <linux/completion.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/slab.h> -#include <linux/refcount.h> #include <linux/unaligned.h> #include <linux/uaccess.h> @@ -67,8 +65,6 @@ struct syncppp { struct tasklet_struct tsk; - refcount_t refcnt; - struct completion dead_cmp; struct ppp_channel chan; /* interface to generic ppp layer */ }; @@ -117,37 +113,6 @@ ppp_print_buffer (const char *name, const __u8 *buf, int count) */ /* - * We have a potential race on dereferencing tty->disc_data, - * because the tty layer provides no locking at all - thus one - * cpu could be running ppp_synctty_receive while another - * calls ppp_synctty_close, which zeroes tty->disc_data and - * frees the memory that ppp_synctty_receive is using. The best - * way to fix this is to use a rwlock in the tty struct, but for now - * we use a single global rwlock for all ttys in ppp line discipline. - * - * FIXME: Fixed in tty_io nowadays. - */ -static DEFINE_RWLOCK(disc_data_lock); - -static struct syncppp *sp_get(struct tty_struct *tty) -{ - struct syncppp *ap; - - read_lock(&disc_data_lock); - ap = tty->disc_data; - if (ap != NULL) - refcount_inc(&ap->refcnt); - read_unlock(&disc_data_lock); - return ap; -} - -static void sp_put(struct syncppp *ap) -{ - if (refcount_dec_and_test(&ap->refcnt)) - complete(&ap->dead_cmp); -} - -/* * Called when a tty is put into sync-PPP line discipline. */ static int @@ -177,9 +142,6 @@ ppp_sync_open(struct tty_struct *tty) skb_queue_head_init(&ap->rqueue); tasklet_setup(&ap->tsk, ppp_sync_process); - refcount_set(&ap->refcnt, 1); - init_completion(&ap->dead_cmp); - ap->chan.private = ap; ap->chan.ops = &sync_ops; ap->chan.mtu = PPP_MRU; @@ -201,34 +163,18 @@ ppp_sync_open(struct tty_struct *tty) } /* - * Called when the tty is put into another line discipline - * or it hangs up. We have to wait for any cpu currently - * executing in any of the other ppp_synctty_* routines to - * finish before we can call ppp_unregister_channel and free - * the syncppp struct. This routine must be called from - * process context, not interrupt or softirq context. + * Called when the tty is put into another line discipline or it hangs up. + * This call is serialized against other ldisc functions. */ static void ppp_sync_close(struct tty_struct *tty) { - struct syncppp *ap; + struct syncppp *ap = tty->disc_data; - write_lock_irq(&disc_data_lock); - ap = tty->disc_data; - tty->disc_data = NULL; - write_unlock_irq(&disc_data_lock); if (!ap) return; - /* - * We have now ensured that nobody can start using ap from now - * on, but we have to wait for all existing users to finish. - * Note that ppp_unregister_channel ensures that no calls to - * our channel ops (i.e. ppp_sync_send/ioctl) are in progress - * by the time it returns. - */ - if (!refcount_dec_and_test(&ap->refcnt)) - wait_for_completion(&ap->dead_cmp); + tty->disc_data = NULL; tasklet_kill(&ap->tsk); ppp_unregister_channel(&ap->chan); @@ -238,17 +184,6 @@ ppp_sync_close(struct tty_struct *tty) } /* - * Called on tty hangup in process context. - * - * Wait for I/O to driver to complete and unregister PPP channel. - * This is already done by the close routine, so just call that. - */ -static void ppp_sync_hangup(struct tty_struct *tty) -{ - ppp_sync_close(tty); -} - -/* * Read does nothing - no data is ever available this way. * Pppd reads and writes packets via /dev/ppp instead. */ @@ -273,7 +208,7 @@ ppp_sync_write(struct tty_struct *tty, struct file *file, const u8 *buf, static int ppp_synctty_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { - struct syncppp *ap = sp_get(tty); + struct syncppp *ap = tty->disc_data; int __user *p = (int __user *)arg; int err, val; @@ -314,7 +249,6 @@ ppp_synctty_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) break; } - sp_put(ap); return err; } @@ -323,7 +257,7 @@ static void ppp_sync_receive(struct tty_struct *tty, const u8 *buf, const u8 *cflags, size_t count) { - struct syncppp *ap = sp_get(tty); + struct syncppp *ap = tty->disc_data; unsigned long flags; if (!ap) @@ -333,21 +267,19 @@ ppp_sync_receive(struct tty_struct *tty, const u8 *buf, const u8 *cflags, spin_unlock_irqrestore(&ap->recv_lock, flags); if (!skb_queue_empty(&ap->rqueue)) tasklet_schedule(&ap->tsk); - sp_put(ap); tty_unthrottle(tty); } static void ppp_sync_wakeup(struct tty_struct *tty) { - struct syncppp *ap = sp_get(tty); + struct syncppp *ap = tty->disc_data; clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags); if (!ap) return; set_bit(XMIT_WAKEUP, &ap->xmit_flags); tasklet_schedule(&ap->tsk); - sp_put(ap); } @@ -357,7 +289,6 @@ static struct tty_ldisc_ops ppp_sync_ldisc = { .name = "pppsync", .open = ppp_sync_open, .close = ppp_sync_close, - .hangup = ppp_sync_hangup, .read = ppp_sync_read, .write = ppp_sync_write, .ioctl = ppp_synctty_ioctl, diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 8178a8758cd3..fdfdcf24ddcf 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1446,6 +1446,7 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x2c7c, 0x0316, 3)}, /* Quectel RG255C */ {QMI_QUIRK_SET_DTR(0x2cb7, 0x0104, 4)}, /* Fibocom NL678 series */ {QMI_QUIRK_SET_DTR(0x2cb7, 0x0112, 0)}, /* Fibocom FG132 */ + {QMI_QUIRK_SET_DTR(0x04b7, 0x8217, 8)}, /* Compal EXM-G1x */ {QMI_FIXED_INTF(0x0489, 0xe0b4, 0)}, /* Foxconn T77W968 LTE */ {QMI_FIXED_INTF(0x0489, 0xe0b5, 0)}, /* Foxconn T77W968 LTE with eSIM support*/ {QMI_FIXED_INTF(0x2692, 0x9025, 4)}, /* Cellient MPL200 (rebranded Qualcomm 05c6:9025) */ diff --git a/drivers/net/vxlan/vxlan_mdb.c b/drivers/net/vxlan/vxlan_mdb.c index d71e1925ecfd..841f42ffecb9 100644 --- a/drivers/net/vxlan/vxlan_mdb.c +++ b/drivers/net/vxlan/vxlan_mdb.c @@ -354,6 +354,10 @@ static bool vxlan_mdb_is_valid_source(const struct nlattr *attr, __be16 proto, NL_SET_ERR_MSG_MOD(extack, "IPv4 multicast source address is not allowed"); return false; } + if (ipv4_is_zeronet(nla_get_in_addr(attr))) { + NL_SET_ERR_MSG_MOD(extack, "IPv4 all-zeros source address is not allowed"); + return false; + } break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): { @@ -368,6 +372,10 @@ static bool vxlan_mdb_is_valid_source(const struct nlattr *attr, __be16 proto, NL_SET_ERR_MSG_MOD(extack, "IPv6 multicast source address is not allowed"); return false; } + if (ipv6_addr_any(&src)) { + NL_SET_ERR_MSG_MOD(extack, "IPv6 all-zeros source address is not allowed"); + return false; + } break; } #endif diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 1322c678f4eb..758245c799a1 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -155,8 +155,6 @@ static const struct class nvme_ns_chr_class = { }; static void nvme_put_subsystem(struct nvme_subsystem *subsys); -static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl, - unsigned nsid); static void nvme_update_keep_alive(struct nvme_ctrl *ctrl, struct nvme_command *cmd); static int nvme_get_log_lsi(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, @@ -1612,7 +1610,7 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, } if (nvme_multi_css(ctrl) && !csi_seen) { - dev_warn(ctrl->device, "Command set not reported for nsid:%d\n", + dev_warn(ctrl->device, "Command set not reported for nsid:%u\n", info->nsid); status = -EINVAL; } @@ -2341,14 +2339,6 @@ static int nvme_query_fdp_info(struct nvme_ns *ns, struct nvme_ns_info *info) size_t size; int i, ret; - /* - * The FDP configuration is static for the lifetime of the namespace, - * so return immediately if we've already registered this namespace's - * streams. - */ - if (head->nr_plids) - return 0; - ret = nvme_get_features(ctrl, NVME_FEAT_FDP, info->endgid, NULL, 0, &fdp); if (ret) { @@ -2395,6 +2385,7 @@ static int nvme_query_fdp_info(struct nvme_ns *ns, struct nvme_ns_info *info) for (i = 0; i < head->nr_plids; i++) head->plids[i] = le16_to_cpu(ruhs->ruhsd[i].pid); + head->write_stream_granularity = min(info->runs, U32_MAX); free: kfree(ruhs); return ret; @@ -2442,12 +2433,6 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, goto out; } - if (ns->ctrl->ctratt & NVME_CTRL_ATTR_FDPS) { - ret = nvme_query_fdp_info(ns, info); - if (ret < 0) - goto out; - } - if (nvme_invalid_lba_sz(le64_to_cpu(id->nsze), id->lbaf[lbaf].ds - SECTOR_SHIFT, &capacity)) { dev_warn_once(ns->ctrl->device, @@ -2468,9 +2453,26 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, if (!nvme_update_disk_info(ns, id, nvm, &lim)) capacity = 0; + /* + * A failed zone info query leaves zi zero-initialized, so skip the + * zoned limits update instead of configuring the queue from it. + * During a revalidation that keeps the zone geometry the queue was + * last validated with; on a first scan the namespace is registered + * without zoned limits, so that it is still available as a handle + * for admin commands. + */ if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && - ns->head->ids.csi == NVME_CSI_ZNS) - nvme_update_zone_info(ns, &lim, &zi); + ns->head->ids.csi == NVME_CSI_ZNS) { + if (zi.zone_size) + nvme_update_zone_info(ns, &lim, &zi); + else + dev_warn(ns->ctrl->device, + "zone info query failed for nsid %u, %s\n", + ns->head->ns_id, + blk_queue_is_zoned(ns->disk->queue) ? + "keeping the previous zone limits" : + "not enabling zoned mode"); + } if ((ns->ctrl->vwc & NVME_CTRL_VWC_PRESENT) && !info->no_vwc) lim.features |= BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA; @@ -2490,10 +2492,7 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, capacity = 0; lim.max_write_streams = ns->head->nr_plids; - if (lim.max_write_streams) - lim.write_stream_granularity = min(info->runs, U32_MAX); - else - lim.write_stream_granularity = 0; + lim.write_stream_granularity = ns->head->write_stream_granularity; /* * Only set the DEAC bit if the device guarantees that reads from @@ -4001,10 +4000,11 @@ static void nvme_add_ns_cdev(struct nvme_ns *ns) set_bit(NVME_NS_CDEV_LIVE, &ns->flags); } -static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl, +static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info) - __must_hold(&ctrl->subsys->lock) + __must_hold(&ns->ctrl->subsys->lock) { + struct nvme_ctrl *ctrl = ns->ctrl; struct nvme_ns_head *head; size_t size = sizeof(*head); int ret = -ENOMEM; @@ -4032,6 +4032,7 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl, ratelimit_state_init(&head->rs_nuse, 5 * HZ, 1); ratelimit_set_flags(&head->rs_nuse, RATELIMIT_MSG_ON_RELEASE); kref_init(&head->ref); + ns->head = head; if (head->ids.csi) { ret = nvme_get_effects_log(ctrl, head->ids.csi, &head->effects); @@ -4040,21 +4041,30 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl, } else head->effects = ctrl->effects; + if (ctrl->ctratt & NVME_CTRL_ATTR_FDPS) { + ret = nvme_query_fdp_info(ns, info); + if (ret < 0) + goto out_cleanup_srcu; + } + ret = nvme_mpath_alloc_disk(ctrl, head); if (ret) - goto out_cleanup_srcu; + goto out_cleanup_fdp; list_add_tail(&head->entry, &ctrl->subsys->nsheads); kref_get(&ctrl->subsys->ref); return head; +out_cleanup_fdp: + kfree(head->plids); out_cleanup_srcu: cleanup_srcu_struct(&head->srcu); out_ida_remove: ida_free(&ctrl->subsys->ns_ida, head->instance); out_free_head: kfree(head); + ns->head = NULL; out: if (ret > 0) ret = blk_status_to_errno(nvme_error_status(ret)); @@ -4116,13 +4126,13 @@ static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info) ((ns->ctrl->subsys->cmic & NVME_CTRL_CMIC_MULTI_CTRL) && info->is_shared)) { dev_err(ctrl->device, - "ignoring nsid %d because of duplicate IDs\n", + "ignoring nsid %u because of duplicate IDs\n", info->nsid); return ret; } dev_err(ctrl->device, - "clearing duplicate IDs for nsid %d\n", info->nsid); + "clearing duplicate IDs for nsid %u\n", info->nsid); dev_err(ctrl->device, "use of /dev/disk/by-id/ may cause data corruption\n"); memset(&info->ids.nguid, 0, sizeof(info->ids.nguid)); @@ -4137,11 +4147,11 @@ static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info) ret = nvme_subsys_check_duplicate_ids(ctrl->subsys, &info->ids); if (ret) { dev_err(ctrl->device, - "duplicate IDs in subsystem for nsid %d\n", + "duplicate IDs in subsystem for nsid %u\n", info->nsid); goto out_unlock; } - head = nvme_alloc_ns_head(ctrl, info); + head = nvme_alloc_ns_head(ns, info); if (IS_ERR(head)) { ret = PTR_ERR(head); goto out_unlock; @@ -4151,20 +4161,20 @@ static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info) if ((!info->is_shared || !head->shared) && !list_empty(&head->list)) { dev_err(ctrl->device, - "Duplicate unshared namespace %d\n", + "Duplicate unshared namespace %u\n", info->nsid); goto out_put_ns_head; } if (!nvme_ns_ids_equal(&head->ids, &info->ids)) { dev_err(ctrl->device, - "IDs don't match for shared namespace %d\n", + "IDs don't match for shared namespace %u\n", info->nsid); goto out_put_ns_head; } if (!multipath) { dev_warn(ctrl->device, - "Found shared namespace %d, but multipathing not supported.\n", + "Found shared namespace %u, but multipathing not supported.\n", info->nsid); dev_warn_once(ctrl->device, "Shared namespace support requires core_nvme.multipath=Y.\n"); @@ -4333,6 +4343,9 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info) last_path = true; } mutex_unlock(&ctrl->subsys->lock); + + /* guarantee not available in head->list */ + synchronize_srcu(&ns->head->srcu); if (last_path) nvme_put_ns_head(ns->head); nvme_put_ns_head(ns->head); @@ -4410,7 +4423,7 @@ static void nvme_validate_ns(struct nvme_ns *ns, struct nvme_ns_info *info) if (!nvme_ns_ids_equal(&ns->head->ids, &info->ids)) { dev_err(ns->ctrl->device, - "identifiers changed for nsid %d\n", ns->head->ns_id); + "identifiers changed for nsid %u\n", ns->head->ns_id); goto out; } @@ -4437,7 +4450,7 @@ static void nvme_scan_ns(struct nvme_ctrl *ctrl, unsigned nsid) if (info.ids.csi != NVME_CSI_NVM && !nvme_multi_css(ctrl)) { dev_warn(ctrl->device, - "command set not reported for nsid: %d\n", nsid); + "command set not reported for nsid: %u\n", nsid); return; } @@ -4501,15 +4514,16 @@ static void nvme_scan_ns_async(void *data, async_cookie_t cookie) nvme_scan_ns(scan_info->ctrl, nsid); } -static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl, - unsigned nsid) +static void nvme_remove_nsid_range(struct nvme_ctrl *ctrl, u32 start, u32 end) { struct nvme_ns *ns, *next; LIST_HEAD(rm_list); mutex_lock(&ctrl->namespaces_lock); list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) { - if (ns->head->ns_id > nsid) { + if (ns->head->ns_id >= end) + break; + if (ns->head->ns_id > start) { list_del_rcu(&ns->list); synchronize_srcu(&ctrl->srcu); list_add_tail_rcu(&ns->list, &rm_list); @@ -4559,13 +4573,14 @@ static int nvme_scan_ns_list(struct nvme_ctrl *ctrl) goto out; async_schedule_domain(nvme_scan_ns_async, &scan_info, &domain); - while (++prev < nsid) - nvme_ns_remove_by_nsid(ctrl, prev); + if (prev + 1 < nsid) + nvme_remove_nsid_range(ctrl, prev, nsid); + prev = max(prev + 1, nsid); } async_synchronize_full_domain(&domain); } out: - nvme_remove_invalid_namespaces(ctrl, prev); + nvme_remove_nsid_range(ctrl, prev, UINT_MAX); free: async_synchronize_full_domain(&domain); kfree(ns_list); @@ -4585,7 +4600,7 @@ static void nvme_scan_ns_sequential(struct nvme_ctrl *ctrl) for (i = 1; i <= nn; i++) nvme_scan_ns(ctrl, i); - nvme_remove_invalid_namespaces(ctrl, nn); + nvme_remove_nsid_range(ctrl, nn, UINT_MAX); } static void nvme_clear_changed_ns_log(struct nvme_ctrl *ctrl) diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index fd5abd04e080..59f823dfbbcc 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -1028,6 +1028,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, } if (strlen(p) < 11 || strncmp(p, "DHHC-1:", 7)) { pr_err("Invalid DH-CHAP secret %s\n", p); + kfree_sensitive(p); ret = -EINVAL; goto out; } @@ -1042,6 +1043,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, } if (strlen(p) < 11 || strncmp(p, "DHHC-1:", 7)) { pr_err("Invalid DH-CHAP secret %s\n", p); + kfree_sensitive(p); ret = -EINVAL; goto out; } diff --git a/drivers/nvme/host/fault_inject.c b/drivers/nvme/host/fault_inject.c index 105d6cb41c72..783e1999fef4 100644 --- a/drivers/nvme/host/fault_inject.c +++ b/drivers/nvme/host/fault_inject.c @@ -42,9 +42,11 @@ void nvme_fault_inject_init(struct nvme_fault_inject *fault_inj, } fault_inj->parent = parent; - /* create debugfs for status code and dont_retry */ + /* create debugfs for opcode, status code, and dont_retry */ + fault_inj->opcode = 0xffff; fault_inj->status = NVME_SC_INVALID_OPCODE; fault_inj->dont_retry = true; + debugfs_create_x16("opcode", 0600, dir, &fault_inj->opcode); debugfs_create_x16("status", 0600, dir, &fault_inj->status); debugfs_create_bool("dont_retry", 0600, dir, &fault_inj->dont_retry); } @@ -59,6 +61,7 @@ void nvme_should_fail(struct request *req) { struct gendisk *disk = req->q->disk; struct nvme_fault_inject *fault_inject = NULL; + struct nvme_command *cmd = nvme_req(req)->cmd; u16 status; if (disk) { @@ -72,7 +75,14 @@ void nvme_should_fail(struct request *req) fault_inject = &nvme_req(req)->ctrl->fault_inject; } - if (fault_inject && should_fail(&fault_inject->attr, 1)) { + if (!fault_inject) + return; + + if (fault_inject->opcode <= 0xff && + fault_inject->opcode != cmd->common.opcode) + return; + + if (should_fail(&fault_inject->attr, 1)) { /* inject status code and DNR bit */ status = fault_inject->status; if (fault_inject->dont_retry) diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 023710e08e0d..48454cb7a0fc 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2364,9 +2364,15 @@ nvme_fc_ctrl_free(struct kref *ref) struct nvme_fc_ctrl *ctrl = container_of(ref, struct nvme_fc_ctrl, ref); unsigned long flags; + bool owns_opts; - /* remove from rport list */ + /* + * Presence on the rport list means nvme_fc_init_ctrl() completed, + * and with it ownership of the fabrics options passed to it. If it + * failed instead, the options still belong to nvmf_create_ctrl(). + */ spin_lock_irqsave(&ctrl->rport->lock, flags); + owns_opts = !list_empty(&ctrl->ctrl_list); list_del(&ctrl->ctrl_list); spin_unlock_irqrestore(&ctrl->rport->lock, flags); @@ -2376,7 +2382,7 @@ nvme_fc_ctrl_free(struct kref *ref) nvme_fc_rport_put(ctrl->rport); ida_free(&nvme_fc_ctrl_cnt, ctrl->cnum); - if (ctrl->ctrl.opts) + if (owns_opts) nvmf_free_options(ctrl->ctrl.opts); kfree(ctrl); } @@ -3575,14 +3581,14 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) { dev_err(ctrl->ctrl.device, "NVME-FC{%d}: failed to init ctrl state\n", ctrl->cnum); - goto fail_ctrl; + goto fail_unlist; } if (!queue_delayed_work(nvme_wq, &ctrl->connect_work, 0)) { dev_err(ctrl->ctrl.device, "NVME-FC{%d}: failed to schedule initial connect\n", ctrl->cnum); - goto fail_ctrl; + goto fail_unlist; } flush_delayed_work(&ctrl->connect_work); @@ -3593,14 +3599,22 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, return &ctrl->ctrl; +fail_unlist: + /* + * Leaving the list hands the options back to nvmf_create_ctrl(); + * see nvme_fc_ctrl_free(). Re-init so that list_empty() there + * reports the controller as unlisted. + */ + spin_lock_irqsave(&rport->lock, flags); + list_del_init(&ctrl->ctrl_list); + spin_unlock_irqrestore(&rport->lock, flags); + fail_ctrl: nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING); cancel_work_sync(&ctrl->ioerr_work); cancel_work_sync(&ctrl->ctrl.reset_work); cancel_delayed_work_sync(&ctrl->connect_work); - ctrl->ctrl.opts = NULL; - if (ctrl->ctrl.admin_tagset) nvme_remove_admin_tag_set(&ctrl->ctrl); /* initiate nvme ctrl ref counting teardown */ diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 75e5d5a8a77c..2cff9fcbf740 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -323,6 +323,7 @@ struct nvme_fault_inject { #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS struct fault_attr attr; struct dentry *parent; + u16 opcode; bool dont_retry; /* DNR, do not retry */ u16 status; /* status code */ #endif @@ -571,6 +572,7 @@ struct nvme_ns_head { u16 nr_plids; u16 *plids; + u32 write_stream_granularity; #ifdef CONFIG_NVME_MULTIPATH struct bio_list requeue_list __guarded_by(&requeue_lock); diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 538385138e45..9cb811a2ce1f 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -2036,7 +2036,7 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx, struct ib_device *dev; bool queue_ready = test_bit(NVME_RDMA_Q_LIVE, &queue->flags); blk_status_t ret; - int err; + int err = 0; WARN_ON_ONCE(rq->tag < 0); @@ -2092,16 +2092,18 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx, err_unmap: nvme_rdma_unmap_data(queue, rq); err: - if (err == -EIO) - ret = nvme_host_path_error(rq); - else if (err == -ENOMEM || err == -EAGAIN) - ret = BLK_STS_RESOURCE; - else - ret = BLK_STS_IOERR; - nvme_cleanup_cmd(rq); + if (err != -EIO) { + nvme_cleanup_cmd(rq); + if (err == -ENOMEM || err == -EAGAIN) + ret = BLK_STS_RESOURCE; + else + ret = BLK_STS_IOERR; + } unmap_qe: ib_dma_unmap_single(dev, req->sqe.dma, sizeof(struct nvme_command), DMA_TO_DEVICE); + if (err == -EIO) + return nvme_host_path_error(rq); return ret; } diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c index abf8edaae371..02a2490a9ed7 100644 --- a/drivers/nvme/host/sysfs.c +++ b/drivers/nvme/host/sysfs.c @@ -166,7 +166,7 @@ static DEVICE_ATTR_RO(eui); static ssize_t nsid_show(struct device *dev, struct device_attribute *attr, char *buf) { - return sysfs_emit(buf, "%d\n", dev_to_ns_head(dev)->ns_id); + return sysfs_emit(buf, "%u\n", dev_to_ns_head(dev)->ns_id); } static DEVICE_ATTR_RO(nsid); diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 5fda9661bdb7..921934028e0b 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -413,8 +413,13 @@ static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req, * if we're the first on the send_list and we can try to send * directly, otherwise queue io_work. Also, only do that if we * are on the same cpu, so we don't introduce contention. + * + * TLS kTLS send takes ctx->tx_lock while blk_mq holds set->srcu. + * lockdep reports circular locking via elevator_lock. Defer TLS + * sends to the io workqueue instead of inline from this path. */ if (queue->io_cpu == raw_smp_processor_id() && + !nvme_tcp_queue_tls(queue) && empty && mutex_trylock(&queue->send_mutex)) { nvme_tcp_send_all(queue); mutex_unlock(&queue->send_mutex); @@ -684,6 +689,13 @@ static int nvme_tcp_handle_c2h_data(struct nvme_tcp_queue *queue, return -ENOENT; } + if (rq_data_dir(rq) != READ) { + dev_err(queue->ctrl->ctrl.device, + "queue %d tag %#x unexpected data for a write\n", + nvme_tcp_queue_id(queue), rq->tag); + return -EPROTO; + } + req = blk_mq_rq_to_pdu(rq); if (!blk_rq_payload_bytes(rq) || !req->curr_bio || !req->data_len) { dev_err(queue->ctrl->ctrl.device, diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c index 2a152e87bd76..e31ec6f4f94f 100644 --- a/drivers/nvme/host/zns.c +++ b/drivers/nvme/host/zns.c @@ -48,12 +48,12 @@ int nvme_query_zone_info(struct nvme_ns *ns, unsigned lbaf, NVME_CMD_EFFECTS_CSUPP)) { if (test_and_clear_bit(NVME_NS_FORCE_RO, &ns->flags)) dev_warn(ns->ctrl->device, - "Zone Append supported for zoned namespace:%d. Remove read-only mode\n", + "Zone Append supported for zoned namespace:%u. Remove read-only mode\n", ns->head->ns_id); } else { set_bit(NVME_NS_FORCE_RO, &ns->flags); dev_warn(ns->ctrl->device, - "Zone Append not supported for zoned namespace:%d. Forcing to read-only mode\n", + "Zone Append not supported for zoned namespace:%u. Forcing to read-only mode\n", ns->head->ns_id); } diff --git a/drivers/nvme/target/auth.c b/drivers/nvme/target/auth.c index edb9627d97b0..a55319bcdbd1 100644 --- a/drivers/nvme/target/auth.c +++ b/drivers/nvme/target/auth.c @@ -238,6 +238,12 @@ void nvmet_auth_sq_free(struct nvmet_sq *sq) sq->dhchap_skey = NULL; } +void nvmet_auth_sq_destroy(struct nvmet_sq *sq) +{ + cancel_delayed_work_sync(&sq->auth_expired_work); + nvmet_auth_sq_free(sq); +} + void nvmet_destroy_auth(struct nvmet_ctrl *ctrl) { ctrl->shash_id = 0; diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index 413ee2d16d29..6286e38436dd 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -814,7 +814,7 @@ static ssize_t nvmet_ns_resv_enable_store(struct config_item *item, mutex_lock(&ns->subsys->lock); if (ns->enabled) { - pr_err("the ns:%d is already enabled.\n", ns->nsid); + pr_err("the ns:%u is already enabled.\n", ns->nsid); mutex_unlock(&ns->subsys->lock); return -EINVAL; } @@ -880,7 +880,7 @@ static struct config_group *nvmet_ns_make(struct config_group *group, goto out; config_group_init_type_name(&ns->group, name, &nvmet_ns_type); - pr_info("adding nsid %d to subsystem %s\n", nsid, subsys->subsysnqn); + pr_info("adding nsid %u to subsystem %s\n", nsid, subsys->subsysnqn); return &ns->group; out: diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index d74c01c98f19..43871a8f56ca 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -558,7 +558,7 @@ static void nvmet_p2pmem_ns_add_p2p(struct nvmet_ctrl *ctrl, if (ret < 0) pci_dev_put(p2p_dev); - pr_info("using p2pmem on %s for nsid %d\n", pci_name(p2p_dev), + pr_info("using p2pmem on %s for nsid %u\n", pci_name(p2p_dev), ns->nsid); } @@ -591,6 +591,11 @@ int nvmet_ns_enable(struct nvmet_ns *ns) if (ns->enabled) goto out_unlock; + if (!ns->device_path) { + ret = -EINVAL; + goto out_unlock; + } + ret = nvmet_bdev_ns_enable(ns); if (ret == -ENOTBLK) ret = nvmet_file_ns_enable(ns); @@ -980,7 +985,7 @@ void nvmet_sq_destroy(struct nvmet_sq *sq) wait_for_completion(&sq->confirm_done); wait_for_completion(&sq->free_done); percpu_ref_exit(&sq->ref); - nvmet_auth_sq_free(sq); + nvmet_auth_sq_destroy(sq); nvmet_cq_put(sq->cq); /* diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index e362d7913a38..dbda55895f4f 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -924,6 +924,7 @@ u8 nvmet_setup_auth(struct nvmet_ctrl *ctrl, struct nvmet_sq *sq, bool reset); void nvmet_auth_sq_init(struct nvmet_sq *sq); void nvmet_destroy_auth(struct nvmet_ctrl *ctrl); void nvmet_auth_sq_free(struct nvmet_sq *sq); +void nvmet_auth_sq_destroy(struct nvmet_sq *sq); int nvmet_setup_dhgroup(struct nvmet_ctrl *ctrl, u8 dhgroup_id); bool nvmet_check_auth_status(struct nvmet_req *req); int nvmet_auth_host_hash(struct nvmet_req *req, u8 *response, @@ -950,6 +951,7 @@ static inline void nvmet_auth_sq_init(struct nvmet_sq *sq) } static inline void nvmet_destroy_auth(struct nvmet_ctrl *ctrl) {}; static inline void nvmet_auth_sq_free(struct nvmet_sq *sq) {}; +static inline void nvmet_auth_sq_destroy(struct nvmet_sq *sq) {}; static inline bool nvmet_check_auth_status(struct nvmet_req *req) { return true; diff --git a/drivers/nvme/target/pr.c b/drivers/nvme/target/pr.c index 0948a690a1c0..09d8c63f5680 100644 --- a/drivers/nvme/target/pr.c +++ b/drivers/nvme/target/pr.c @@ -145,7 +145,7 @@ static void nvmet_pr_add_resv_log(struct nvmet_ctrl *ctrl, u8 log_type, log.nsid = cpu_to_le32(nsid); if (!kfifo_put(&log_mgr->log_queue, log)) { - pr_info("a reservation log lost, cntlid:%d, log_type:%d, nsid:%d\n", + pr_info("a reservation log lost, cntlid:%d, log_type:%d, nsid:%u\n", ctrl->cntlid, log_type, nsid); log_mgr->lost_count++; } diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 49cba690914a..ffa1e172c259 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -1631,19 +1631,13 @@ static int nvmet_rdma_queue_connect(struct rdma_cm_id *cm_id, mutex_unlock(&nvmet_rdma_queue_mutex); if (pending > NVMET_RDMA_BACKLOG) { ret = NVME_SC_CONNECT_CTRL_BUSY; - goto put_device; + goto free_queue; } } ret = nvmet_rdma_cm_accept(cm_id, queue, &event->param.conn); - if (ret) { - /* - * Don't destroy the cm_id in free path, as we implicitly - * destroy the cm_id here with non-zero ret code. - */ - queue->cm_id = NULL; + if (ret) goto free_queue; - } mutex_lock(&nvmet_rdma_queue_mutex); list_add_tail(&queue->queue_list, &nvmet_rdma_queue_list); @@ -1652,6 +1646,11 @@ static int nvmet_rdma_queue_connect(struct rdma_cm_id *cm_id, return 0; free_queue: + /* + * Don't destroy the cm_id in free path, as we implicitly + * destroy the cm_id here with non-zero ret code. + */ + queue->cm_id = NULL; nvmet_rdma_free_queue(queue); put_device: kref_put(&ndev->ref, nvmet_rdma_free_dev); diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index e4f603b2ace7..e59810175262 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -103,6 +103,7 @@ enum nvmet_tcp_recv_state { enum { NVMET_TCP_F_INIT_FAILED = (1 << 0), + NVMET_TCP_F_R2T_SENT = (1 << 1), }; struct nvmet_tcp_cmd { @@ -776,6 +777,7 @@ static int nvmet_try_send_r2t(struct nvmet_tcp_cmd *cmd, bool last_in_batch) return -EAGAIN; cmd->queue->snd_cmd = NULL; + cmd->flags |= NVMET_TCP_F_R2T_SENT; return 1; } @@ -1009,6 +1011,12 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue) cmd = &queue->connect; } + if (unlikely(!(cmd->flags & NVMET_TCP_F_R2T_SENT))) { + pr_err("queue %d: unsolicited H2CData (ttag %u)\n", + queue->idx, data->ttag); + goto err_proto; + } + if (le32_to_cpu(data->data_offset) != cmd->rbytes_done) { pr_err("ttag %u unexpected data offset %u (expected %u)\n", data->ttag, le32_to_cpu(data->data_offset), @@ -1244,6 +1252,8 @@ recv: } queue->left = hdr->hlen - queue->offset + hdgst; + if (queue->left > sizeof(queue->pdu) - queue->offset) + return -EPROTO; goto recv; } diff --git a/drivers/pmdomain/mediatek/Kconfig b/drivers/pmdomain/mediatek/Kconfig index 8923e6516441..a2eb704a773c 100644 --- a/drivers/pmdomain/mediatek/Kconfig +++ b/drivers/pmdomain/mediatek/Kconfig @@ -43,9 +43,12 @@ config MTK_MFG_PM_DOMAIN This driver is required for the Mali GPU to work at all on MT8196 and MT6991. +endmenu + config AIROHA_CPU_PM_DOMAIN tristate "Airoha CPU power domain" default ARCH_AIROHA + depends on ARCH_AIROHA || COMPILE_TEST depends on HAVE_ARM_SMCCC depends on PM select PM_GENERIC_DOMAINS @@ -54,5 +57,3 @@ config AIROHA_CPU_PM_DOMAIN CPU frequency and power is controlled by ATF with SMC command to set performance states. - -endmenu diff --git a/drivers/pmdomain/qcom/rpmhpd.c b/drivers/pmdomain/qcom/rpmhpd.c index 96e4bd2f5a14..90743275942d 100644 --- a/drivers/pmdomain/qcom/rpmhpd.c +++ b/drivers/pmdomain/qcom/rpmhpd.c @@ -241,13 +241,9 @@ static struct rpmhpd *eliza_rpmhpds[] = { [RPMHPD_GFX] = &gfx, [RPMHPD_LCX] = &lcx, [RPMHPD_LMX] = &lmx, - [RPMHPD_MMCX] = &mmcx, - [RPMHPD_MMCX_AO] = &mmcx_ao, [RPMHPD_MSS] = &mss, [RPMHPD_MX] = &mx, [RPMHPD_MX_AO] = &mx_ao, - [RPMHPD_MXC] = &mxc, - [RPMHPD_MXC_AO] = &mxc_ao, [RPMHPD_NSP] = &nsp, }; diff --git a/drivers/ras/amd/atl/core.c b/drivers/ras/amd/atl/core.c index 0f7cd6dab0b0..d77dacdd4f56 100644 --- a/drivers/ras/amd/atl/core.c +++ b/drivers/ras/amd/atl/core.c @@ -190,7 +190,6 @@ static const struct x86_cpu_id amd_atl_cpuids[] = { X86_MATCH_FEATURE(X86_FEATURE_ZEN, NULL), { } }; -MODULE_DEVICE_TABLE(x86cpu, amd_atl_cpuids); static int __init amd_atl_init(void) { diff --git a/drivers/ras/amd/atl/map.c b/drivers/ras/amd/atl/map.c index 24a05af747d5..4ec9333ef745 100644 --- a/drivers/ras/amd/atl/map.c +++ b/drivers/ras/amd/atl/map.c @@ -771,9 +771,5 @@ int get_address_map(struct addr_ctx *ctx) dump_address_map(&ctx->map); - ret = validate_address_map(ctx); - if (ret) - return ret; - - return ret; + return validate_address_map(ctx); } diff --git a/drivers/s390/crypto/zcrypt_cca_key.h b/drivers/s390/crypto/zcrypt_cca_key.h index f5907b67db29..8a69eed75040 100644 --- a/drivers/s390/crypto/zcrypt_cca_key.h +++ b/drivers/s390/crypto/zcrypt_cca_key.h @@ -219,6 +219,7 @@ static inline int zcrypt_type6_crt_key(struct ica_rsa_modexpo_crt *crt, void *p) copy_from_user(key->key_parts + 2 * long_len + 2 * short_len, crt->u_mult_inv, long_len)) return -EFAULT; + memset(key->key_parts + 3 * long_len + 2 * short_len, 0, pad_len); memset(key->key_parts + 3 * long_len + 2 * short_len + pad_len, 0xff, crt->inputdatalength); pub = (struct cca_public_sec *)(key->key_parts + key_len); diff --git a/drivers/s390/crypto/zcrypt_ccamisc.c b/drivers/s390/crypto/zcrypt_ccamisc.c index d4ce6352b5b2..19909bf43dc9 100644 --- a/drivers/s390/crypto/zcrypt_ccamisc.c +++ b/drivers/s390/crypto/zcrypt_ccamisc.c @@ -1158,8 +1158,21 @@ static int _ip_cprb_helper(u16 cardnr, u16 domain, /* do not check the key here, it may be incomplete */ - /* copy the vlsc key token back */ + /* + * Copy the vlsc key token back. + * The available space in the destination (key_token) and the source + * (t) buffer is always larger as the valid range of prepparm->kb.len. + * Validate t->len by comparing it with the length information in the + * param block of the request (prepparm->kb.len) + * The value range of prepparm->kb.len has been checked above. + */ t = (struct cipherkeytoken *)prepparm->kb.tlv1.key_token; + if (t->len != prepparm->kb.len - 3 * sizeof(uint16_t)) { + ZCRYPT_DBF_ERR("%s reply with invalid key_token length %u\n", + __func__, t->len); + rc = -EIO; + goto out; + } memcpy(key_token, t, t->len); *key_token_size = t->len; diff --git a/drivers/s390/net/ctcm_mpc.c b/drivers/s390/net/ctcm_mpc.c index 08e36685e578..61c88fe853c5 100644 --- a/drivers/s390/net/ctcm_mpc.c +++ b/drivers/s390/net/ctcm_mpc.c @@ -826,7 +826,7 @@ static void mpc_action_go_ready(fsm_instance *fsm, int event, void *arg) fsm_deltimer(&grp->timer); - if (grp->saved_xid2->xid2_flag2 == 0x40) { + if (priv->xid->xid2_flag2 == 0x40) { priv->xid->xid2_flag2 = 0x00; if (grp->estconnfunc) { grp->estconnfunc(grp->port_num, 1, @@ -1636,7 +1636,6 @@ done: "The XID used in the MPC protocol is not valid, " "rc = %d\n", rc); priv->xid->xid2_flag2 = 0x40; - grp->saved_xid2->xid2_flag2 = 0x40; } return rc; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index a091f77cedaf..c4a35547dcc6 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -6600,11 +6600,13 @@ int ceph_mds_check_access(struct ceph_mds_client *mdsc, char *tpath, int mask) doutc(cl, "tpath '%s', mask %d, caller_uid %d, caller_gid %d\n", tpath, mask, caller_uid, caller_gid); + mutex_lock(&mdsc->mutex); for (i = 0; i < mdsc->s_cap_auths_num; i++) { struct ceph_mds_cap_auth *s = &mdsc->s_cap_auths[i]; err = ceph_mds_auth_match(mdsc, s, cred, tpath); if (err < 0) { + mutex_unlock(&mdsc->mutex); put_cred(cred); return err; } else if (err > 0) { @@ -6626,6 +6628,7 @@ int ceph_mds_check_access(struct ceph_mds_client *mdsc, char *tpath, int mask) doutc(cl, "root_squash_perms %d, rw_perms_s %p\n", root_squash_perms, rw_perms_s); if (root_squash_perms && rw_perms_s == NULL) { + mutex_unlock(&mdsc->mutex); doutc(cl, "access allowed\n"); return 0; } @@ -6640,6 +6643,7 @@ int ceph_mds_check_access(struct ceph_mds_client *mdsc, char *tpath, int mask) !!(mask & MAY_READ), !!(mask & MAY_WRITE)); } doutc(cl, "access denied\n"); + mutex_unlock(&mdsc->mutex); return -EACCES; } diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 3c62e3c3530b..e7a262c9c2ab 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -604,6 +604,7 @@ struct ceph_mds_client { struct rw_semaphore pool_perm_rwsem; struct rb_root pool_perm_tree; + /* protected by mutex */ u32 s_cap_auths_num; struct ceph_mds_cap_auth *s_cap_auths; diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 15edea30dc8b..72935f665f11 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -1420,6 +1420,11 @@ static int ceph_reconfigure_fc(struct fs_context *fc) else ceph_clear_mount_opt(fsc, SPARSEREAD); + if (fsopt->flags & CEPH_MOUNT_OPT_NEARFULL_SYNC) + ceph_set_mount_opt(fsc, NEARFULL_SYNC); + else + ceph_clear_mount_opt(fsc, NEARFULL_SYNC); + if (strcmp_null(fsc->mount_options->mon_addr, fsopt->mon_addr)) { kfree(fsc->mount_options->mon_addr); fsc->mount_options->mon_addr = fsopt->mon_addr; diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c index 4929f3431189..d8cac1cbf3bd 100644 --- a/fs/configfs/mount.c +++ b/fs/configfs/mount.c @@ -9,6 +9,7 @@ */ #include <linux/fs.h> +#include <linux/magic.h> #include <linux/module.h> #include <linux/mount.h> #include <linux/fs_context.h> @@ -19,9 +20,6 @@ #include <linux/configfs.h> #include "configfs_internal.h" -/* Random magic number */ -#define CONFIGFS_MAGIC 0x62656570 - static struct vfsmount *configfs_mount = NULL; struct kmem_cache *configfs_dir_cachep; static int configfs_mnt_count = 0; diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c index 60264833bb63..848a0d338b89 100644 --- a/fs/ntfs/attrib.c +++ b/fs/ntfs/attrib.c @@ -1737,8 +1737,8 @@ static struct attr_def *ntfs_attr_find_in_attrdef(const struct ntfs_volume *vol, struct attr_def *ad; WARN_ON(!type); - for (ad = vol->attrdef; (u8 *)ad - (u8 *)vol->attrdef < - vol->attrdef_size && ad->type; ++ad) { + for (ad = vol->attrdef; (u8 *)ad - (u8 *)vol->attrdef <= + vol->attrdef_size - (s32)sizeof(*ad) && ad->type; ++ad) { /* We have not found it yet, carry on searching. */ if (likely(le32_to_cpu(ad->type) < le32_to_cpu(type))) continue; @@ -2500,7 +2500,7 @@ int ntfs_resident_attr_record_add(struct ntfs_inode *ni, __le32 type, return offset; put_err_out: ntfs_attr_put_search_ctx(ctx); - return -EIO; + return err; } /* @@ -2639,7 +2639,7 @@ static int ntfs_non_resident_attr_record_add(struct ntfs_inode *ni, __le32 type, return offset; put_err_out: ntfs_attr_put_search_ctx(ctx); - return -1; + return err; } /* @@ -5704,12 +5704,12 @@ int ntfs_attr_fallocate(struct ntfs_inode *ni, loff_t start, loff_t byte_len, bo lcn << vol->cluster_size_bits, alloc_cnt << vol->cluster_size_bits); - if (err > 0) + if (err) goto out; } if (signal_pending(current)) - goto out; + goto signal_out; vcn += alloc_cnt; try_alloc_cnt -= alloc_cnt; @@ -5730,7 +5730,7 @@ int ntfs_attr_fallocate(struct ntfs_inode *ni, loff_t start, loff_t byte_len, bo up_write(&ni->runlist.lock); mutex_unlock(&ni->mrec_lock); if (err || signal_pending(current)) - goto out; + goto signal_out; vcn += alloc_cnt; try_alloc_cnt -= alloc_cnt; @@ -5756,4 +5756,8 @@ out_unmap: mutex_unlock(&ni->mrec_lock); out: return err >= 0 ? 0 : err; +signal_out: + if (!err) + err = -EINTR; + goto out; } diff --git a/fs/ntfs/bdev-io.c b/fs/ntfs/bdev-io.c index 86db4d9298ed..4f27eed3b072 100644 --- a/fs/ntfs/bdev-io.c +++ b/fs/ntfs/bdev-io.c @@ -34,7 +34,7 @@ int ntfs_bdev_read(struct block_device *bdev, char *data, loff_t start, size_t s int error; struct bio *bio; blk_opf_t op; - sector_t sector = start >> SECTOR_SHIFT; + sector_t sector = ntfs_bytes_to_bio_sector(start); if (start & (SECTOR_SIZE - 1)) return -EINVAL; diff --git a/fs/ntfs/bitmap.c b/fs/ntfs/bitmap.c index b1436b3151b9..1840b7d84c62 100644 --- a/fs/ntfs/bitmap.c +++ b/fs/ntfs/bitmap.c @@ -64,7 +64,7 @@ int ntfs_trim_fs(struct ntfs_volume *vol, struct fstrim_range *range) end = start_buf; while (end < end_buf) { - u64 aligned_start, aligned_count; + u64 aligned_start, aligned_end, aligned_count; u64 start = find_next_zero_bit(bitmap, end_buf - start_buf, end - start_buf) + start_buf; if (start >= end_buf) @@ -74,8 +74,10 @@ int ntfs_trim_fs(struct ntfs_volume *vol, struct fstrim_range *range) start - start_buf) + start_buf; aligned_start = ALIGN(ntfs_cluster_to_bytes(vol, start), dq); - aligned_count = - ALIGN_DOWN(ntfs_cluster_to_bytes(vol, end - start), dq); + aligned_end = ALIGN_DOWN(ntfs_cluster_to_bytes(vol, end), dq); + if (aligned_start >= aligned_end) + continue; + aligned_count = aligned_end - aligned_start; if (aligned_count >= range->minlen) { ret = blkdev_issue_discard(vol->sb->s_bdev, aligned_start >> 9, aligned_count >> 9, GFP_NOFS); diff --git a/fs/ntfs/compress.c b/fs/ntfs/compress.c index 2225630b19d7..197d8607fc63 100644 --- a/fs/ntfs/compress.c +++ b/fs/ntfs/compress.c @@ -1414,7 +1414,7 @@ static int ntfs_write_cb(struct ntfs_inode *ni, loff_t pos, struct page **pages, bio_pos = ntfs_cluster_to_bytes(vol, bio_lcn); bio = bio_alloc(vol->sb->s_bdev, DIV_ROUND_UP(bio_size, PAGE_SIZE), REQ_OP_WRITE, GFP_NOIO); - bio->bi_iter.bi_sector = ntfs_bytes_to_sector(vol, bio_pos); + bio->bi_iter.bi_sector = ntfs_bytes_to_bio_sector(bio_pos); for (i = 0; bio_size; i++) { unsigned int len = min_t(unsigned int, bio_size, PAGE_SIZE); diff --git a/fs/ntfs/ea.c b/fs/ntfs/ea.c index cdd306933d73..3f4ba7667522 100644 --- a/fs/ntfs/ea.c +++ b/fs/ntfs/ea.c @@ -404,10 +404,12 @@ alloc_new_ea: *packed_ea_size = p_ea_info->ea_length; mark_mft_record_dirty(ni); out: - if (ea_info_qsize > 0) - NInoSetHasEA(ni); - else - NInoClearHasEA(ni); + if (!err) { + if (ea_info_qsize > 0) + NInoSetHasEA(ni); + else + NInoClearHasEA(ni); + } kvfree(ea_buf); kvfree(old_ea_buf); @@ -615,7 +617,7 @@ static int ntfs_getxattr(const struct xattr_handler *handler, if (!buffer) { err = sizeof(u8); } else if (size < sizeof(u8)) { - err = -ENODATA; + err = -ERANGE; } else { err = sizeof(u8); *(u8 *)buffer = (u8)(le32_to_cpu(ni->flags) & 0x3F); @@ -628,7 +630,7 @@ static int ntfs_getxattr(const struct xattr_handler *handler, if (!buffer) { err = sizeof(u32); } else if (size < sizeof(u32)) { - err = -ENODATA; + err = -ERANGE; } else { err = sizeof(u32); *(u32 *)buffer = le32_to_cpu(ni->flags); @@ -753,18 +755,39 @@ static int ntfs_new_attr_flags(struct ntfs_inode *ni, __le32 fattr) old_arec_size = le32_to_cpu(a->length); /* - * Move payloads before shrinking the record. Otherwise resizing moves + * Move payloads before shrinking the record. Otherwise resizing moves * the following attribute over the old payload before it can be copied. + * + * When offsets increase, move mapping_pairs first to avoid name + * overwriting the start of mapping_pairs. */ if (arec_size < old_arec_size) { - if (a->name_length && name_ofs != old_name_ofs) - memmove((u8 *)a + name_ofs, (u8 *)a + old_name_ofs, - a->name_length * sizeof(__le16)); - if (mp_ofs != old_mp_ofs) - memmove((u8 *)a + mp_ofs, (u8 *)a + old_mp_ofs, mp_size); + if (name_ofs > old_name_ofs) { + /* Payload offsets increased: move mapping pairs first. */ + if (mp_ofs != old_mp_ofs) + memmove((u8 *)a + mp_ofs, + (u8 *)a + old_mp_ofs, + mp_size); + if (a->name_length && name_ofs != old_name_ofs) + memmove((u8 *)a + name_ofs, + (u8 *)a + old_name_ofs, + a->name_length * + sizeof(__le16)); + } else { + /* Payload offsets decreased or unchanged: move name first. */ + if (a->name_length && name_ofs != old_name_ofs) + memmove((u8 *)a + name_ofs, + (u8 *)a + old_name_ofs, + a->name_length * + sizeof(__le16)); + if (mp_ofs != old_mp_ofs) + memmove((u8 *)a + mp_ofs, + (u8 *)a + old_mp_ofs, + mp_size); + } } - err = ntfs_attr_record_resize(m, a, arec_size); + err = ntfs_attr_record_resize(ctx->mrec, a, arec_size); if (unlikely(err)) goto err_out; diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 88747217ba61..8164326b7812 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -270,18 +270,25 @@ static int ntfs_setattr_size(struct inode *vi, struct iattr *attr) return err; inode_dio_wait(vi); + + /* + * Serialize with page faults and pagecache instantiation so that + * readers cannot observe the size change until the attribute + * updates below have completed. + */ + filemap_invalidate_lock(vi->i_mapping); if (attr->ia_size > old_size) { truncate_pagecache(vi, old_size); i_size_write(vi, attr->ia_size); pagecache_isize_extended(vi, old_size, attr->ia_size); - } else + } else { truncate_setsize(vi, attr->ia_size); + } err = ntfs_truncate_vfs(vi, attr->ia_size, old_size); - if (err) { + if (err) i_size_write(vi, old_size); - return err; - } + filemap_invalidate_unlock(vi->i_mapping); return err; } @@ -669,6 +676,7 @@ out_lock: static vm_fault_t ntfs_filemap_page_mkwrite(struct vm_fault *vmf) { struct inode *inode = file_inode(vmf->vma->vm_file); + struct address_space *mapping = inode->i_mapping; vm_fault_t ret; if (NInoWofCompressed(NTFS_I(inode))) @@ -677,7 +685,14 @@ static vm_fault_t ntfs_filemap_page_mkwrite(struct vm_fault *vmf) sb_start_pagefault(inode->i_sb); file_update_time(vmf->vma->vm_file); + /* + * Serialize against truncate/fallocate which hold the lock + * exclusively while invalidating pagecache and changing extents. + */ + filemap_invalidate_lock_shared(mapping); ret = iomap_page_mkwrite(vmf, &ntfs_page_mkwrite_iomap_ops, NULL); + filemap_invalidate_unlock_shared(mapping); + sb_end_pagefault(inode->i_sb); return ret; } @@ -1116,7 +1131,6 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t offset, loff_t le struct ntfs_volume *vol = ni->vol; int err = 0; loff_t old_size; - bool map_locked = false; if (mode & ~(NTFS_FALLOC_FL_SUPPORTED)) return -EOPNOTSUPP; @@ -1148,16 +1162,13 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t offset, loff_t le inode_lock(vi); if (NInoCompressed(ni) || NInoEncrypted(ni) || NInoWofCompressed(ni)) { - err = -EOPNOTSUPP; - goto out; + inode_unlock(vi); + return -EOPNOTSUPP; } inode_dio_wait(vi); - if (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE | - FALLOC_FL_INSERT_RANGE)) { - filemap_invalidate_lock(vi->i_mapping); - map_locked = true; - } + /* Take invalidate_lock for all fallocate operations to prevent races */ + filemap_invalidate_lock(vi->i_mapping); switch (mode & FALLOC_FL_MODE_MASK) { case FALLOC_FL_ALLOCATE_RANGE: @@ -1182,14 +1193,15 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t offset, loff_t le err = file_modified(file); out: - if (map_locked) - filemap_invalidate_unlock(vi->i_mapping); + if (!err && mode == 0 && NInoNonResident(ni) && + offset > old_size) { + truncate_pagecache(vi, old_size); + pagecache_isize_extended(vi, old_size, offset); + } + + filemap_invalidate_unlock(vi->i_mapping); + if (!err) { - if (mode == 0 && NInoNonResident(ni) && - offset > old_size) { - truncate_pagecache(vi, old_size); - pagecache_isize_extended(vi, old_size, offset); - } NInoSetFileNameDirty(ni); inode_set_mtime_to_ts(vi, inode_set_ctime_current(vi)); mark_inode_dirty(vi); diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index 32edb4045178..5aedc045f65a 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -1852,7 +1852,7 @@ int ntfs_read_inode_mount(struct inode *vi) struct mft_record *m = NULL; struct attr_record *a; struct ntfs_attr_search_ctx *ctx; - unsigned int i, nr_blocks; + unsigned int i; int err; size_t new_rl_count; @@ -1896,11 +1896,6 @@ int ntfs_read_inode_mount(struct inode *vi) goto err_out; } - /* Determine the first block of the $MFT/$DATA attribute. */ - nr_blocks = ntfs_bytes_to_sector(vol, vol->mft_record_size); - if (!nr_blocks) - nr_blocks = 1; - /* Load $MFT/$DATA's first mft record. */ err = ntfs_bdev_read(sb->s_bdev, (char *)m, ntfs_cluster_to_bytes(vol, vol->mft_lcn), i); @@ -3780,8 +3775,7 @@ static s64 __ntfs_inode_non_resident_attr_pwrite(struct inode *vi, bio = bio_alloc(vol->sb->s_bdev, 1, REQ_OP_WRITE, GFP_NOIO); bio->bi_iter.bi_sector = - ntfs_bytes_to_sector(vol, - ntfs_cluster_to_bytes(vol, lcn) + + ntfs_bytes_to_bio_sector(ntfs_cluster_to_bytes(vol, lcn) + lcn_folio_off); length = min_t(unsigned long, diff --git a/fs/ntfs/lcnalloc.c b/fs/ntfs/lcnalloc.c index aa2e017a4384..0d6cd08ee2e7 100644 --- a/fs/ntfs/lcnalloc.c +++ b/fs/ntfs/lcnalloc.c @@ -53,10 +53,10 @@ int ntfs_cluster_free_from_rl_nolock(struct ntfs_volume *vol, if (rl->lcn < 0) continue; err = ntfs_bitmap_clear_run(lcnbmp_vi, rl->lcn, rl->length); - if (unlikely(err && (!ret || ret == -ENOMEM) && ret != err)) - ret = err; - else + if (likely(!err)) nr_freed += rl->length; + else if (!ret || ret == -ENOMEM) + ret = err; } ntfs_inc_free_clusters(vol, nr_freed); ntfs_debug("Done."); @@ -1045,8 +1045,9 @@ err_out: "Failed to rollback (error %i). Leaving inconsistent metadata! Unmount and run chkdsk.", (int)delta); NVolSetErrors(vol); + } else { + ntfs_dec_free_clusters(vol, delta); } - ntfs_dec_free_clusters(vol, delta); up_write(&vol->lcnbmp_lock); memalloc_nofs_restore(memalloc_flags); ntfs_error(vol->sb, "Aborting (error %i).", err); diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c index 984a0827f9ac..7e58c99f1728 100644 --- a/fs/ntfs/mft.c +++ b/fs/ntfs/mft.c @@ -499,8 +499,8 @@ int ntfs_sync_mft_mirror(struct ntfs_volume *vol, const u64 mft_no, bio = bio_alloc(vol->sb->s_bdev, 1, REQ_OP_WRITE, GFP_NOIO); bio->bi_iter.bi_sector = - NTFS_B_TO_SECTOR(vol, NTFS_CLU_TO_B(vol, vol->mftmirr_lcn) + - lcn_folio_off + folio_ofs); + ntfs_bytes_to_bio_sector(NTFS_CLU_TO_B(vol, vol->mftmirr_lcn) + + lcn_folio_off + folio_ofs); if (bio_add_folio(bio, folio, vol->mft_record_size, folio_ofs)) err = submit_bio_wait(bio); @@ -580,7 +580,7 @@ int write_mft_record_nolock(struct ntfs_inode *ni, struct mft_record *m, int syn err = pre_write_mst_fixup((struct ntfs_record *)fixup_m, vol->mft_record_size); if (err) { ntfs_error(vol->sb, "Failed to apply mst fixups!"); - goto err_out; + goto unmap_err_out; } folio_size = vol->mft_record_size / ni->mft_lcn_count; @@ -592,8 +592,8 @@ int write_mft_record_nolock(struct ntfs_inode *ni, struct mft_record *m, int syn bio = bio_alloc(vol->sb->s_bdev, 1, REQ_OP_WRITE, GFP_NOIO); bio->bi_iter.bi_sector = - NTFS_B_TO_SECTOR(vol, NTFS_CLU_TO_B(vol, ni->mft_lcn[i]) + - clu_off); + ntfs_bytes_to_bio_sector(NTFS_CLU_TO_B(vol, ni->mft_lcn[i]) + + clu_off); if (!bio_add_folio(bio, folio, folio_size, ni->folio_ofs + offset)) { @@ -645,6 +645,8 @@ done: return 0; put_bio_out: bio_put(bio); +unmap_err_out: + kunmap_local(kaddr); err_out: /* * The caller should mark the base inode as bad so no more I/O @@ -2740,8 +2742,8 @@ flush_bio: bio = bio_alloc(vol->sb->s_bdev, 1, REQ_OP_WRITE, GFP_NOIO); bio->bi_iter.bi_sector = - ntfs_bytes_to_sector(vol, - ntfs_cluster_to_bytes(vol, lcn) + off); + ntfs_bytes_to_bio_sector( + ntfs_cluster_to_bytes(vol, lcn) + off); } if (vol->cluster_size == NTFS_BLOCK_SIZE && diff --git a/fs/ntfs/ntfs.h b/fs/ntfs/ntfs.h index df5a75d506f6..45f77848a9cf 100644 --- a/fs/ntfs/ntfs.h +++ b/fs/ntfs/ntfs.h @@ -19,6 +19,7 @@ #include <linux/nls.h> #include <linux/smp.h> #include <linux/pagemap.h> +#include <linux/blk_types.h> #include <linux/uidgid.h> #include "volume.h" @@ -71,8 +72,6 @@ #define NTFS_CLU_TO_POFS(vol, clu) (((u64)(clu) << (vol)->cluster_size_bits) & \ ~PAGE_MASK) -#define NTFS_B_TO_SECTOR(vol, b) ((b) >> ((vol)->sb)->s_blocksize_bits) - enum { NTFS_BLOCK_SIZE = 512, NTFS_BLOCK_SIZE_BITS = 9, @@ -154,11 +153,10 @@ static inline u64 ntfs_cluster_to_poff(const struct ntfs_volume *vol, return (clu << vol->cluster_size_bits) & ~PAGE_MASK; } -/* Convert byte offset to sector (block) number. */ -static inline sector_t ntfs_bytes_to_sector(const struct ntfs_volume *vol, - u64 bytes) +/* Convert a byte offset on the volume to a bio sector number. */ +static inline sector_t ntfs_bytes_to_bio_sector(u64 bytes) { - return bytes >> vol->sb->s_blocksize_bits; + return bytes >> SECTOR_SHIFT; } /* Global variables. */ diff --git a/fs/ntfs/reparse.c b/fs/ntfs/reparse.c index 5e483a2f9060..1a6073e22677 100644 --- a/fs/ntfs/reparse.c +++ b/fs/ntfs/reparse.c @@ -405,7 +405,7 @@ unsigned int ntfs_reparse_tag_dt_types(struct ntfs_volume *vol, unsigned long mr vi = ntfs_iget(vol->sb, mref); if (IS_ERR(vi)) - return PTR_ERR(vi); + return DT_UNKNOWN; reparse_attr = (struct reparse_point *)ntfs_attr_readall(NTFS_I(vi), AT_REPARSE_POINT, NULL, 0, &attr_size); @@ -694,8 +694,9 @@ static int update_reparse_data(struct ntfs_inode *ni, struct ntfs_index_context goto put_rp_inode; } - if (set_reparse_index(ni, xr, ((const struct reparse_point *)value)->reparse_tag) && - oldsize > 0) { + err = set_reparse_index(ni, xr, + ((const struct reparse_point *)value)->reparse_tag); + if (err && oldsize > 0) { /* * If cannot index, try to remove the reparse * data and log the error. There will be an diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index 30481e5d5dd4..60d43339c590 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -557,8 +557,8 @@ static bool is_boot_sector_ntfs(const struct super_block *sb, * Check sectors per cluster value is valid and the cluster size * is not above the maximum (2MB). */ - if (b->bpb.sectors_per_cluster > 0x80 && - b->bpb.sectors_per_cluster < 0xf4) + if (b->bpb.sectors_per_cluster < 0xf4 && + !is_power_of_2(b->bpb.sectors_per_cluster)) goto not_ntfs; /* Check reserved/unused fields are really zero. */ @@ -695,7 +695,7 @@ static bool parse_ntfs_boot_sector(struct ntfs_volume *vol, * = -log2(mft_record_size) bytes. mft_record_size normaly is * 1024 bytes, which is encoded as 0xF6 (-10 in decimal). */ - vol->mft_record_size = 1 << -clusters_per_mft_record; + vol->mft_record_size = 1U << -clusters_per_mft_record; vol->mft_record_size_mask = vol->mft_record_size - 1; vol->mft_record_size_bits = ffs(vol->mft_record_size) - 1; ntfs_debug("vol->mft_record_size = %i (0x%x)", vol->mft_record_size, @@ -732,7 +732,7 @@ static bool parse_ntfs_boot_sector(struct ntfs_volume *vol, * index_record_size normaly equals 4096 bytes, which is * encoded as 0xF4 (-12 in decimal). */ - vol->index_record_size = 1 << -clusters_per_index_record; + vol->index_record_size = 1U << -clusters_per_index_record; vol->index_record_size_mask = vol->index_record_size - 1; vol->index_record_size_bits = ffs(vol->index_record_size) - 1; ntfs_debug("vol->index_record_size = %i (0x%x)", @@ -1241,9 +1241,9 @@ static bool load_and_init_attrdef(struct ntfs_volume *vol) goto failed; } NInoSetSparseDisabled(NTFS_I(ino)); - /* The size of FILE_AttrDef must be above 0 and fit inside 31 bits. */ + /* FILE_AttrDef must hold at least one entry and fit inside 31 bits. */ i_size = i_size_read(ino); - if (i_size <= 0 || i_size > 0x7fffffff) + if (i_size < (s64)sizeof(struct attr_def) || i_size > 0x7fffffff) goto iput_failed; vol->attrdef = kvzalloc(i_size, GFP_NOFS); if (!vol->attrdef) @@ -1862,7 +1862,8 @@ static int ntfs_sync_fs(struct super_block *sb, int wait) return 0; /* If there are some dirty buffers in the bdev inode */ - if (ntfs_clear_volume_flags(vol, VOLUME_IS_DIRTY)) { + if (!NVolErrors(vol) && + ntfs_clear_volume_flags(vol, VOLUME_IS_DIRTY)) { ntfs_warning(sb, "Failed to clear dirty bit in volume information flags. Run chkdsk."); err = -EIO; } diff --git a/fs/ntfs/wof.c b/fs/ntfs/wof.c index 8f84c2212eee..9847259e5b1a 100644 --- a/fs/ntfs/wof.c +++ b/fs/ntfs/wof.c @@ -39,8 +39,6 @@ struct ntfs_wof_workspace { struct mutex *lock; const struct ntfs_codec_ops *codec; u32 comp_unit; - void *input; - size_t input_size; void *output; void *scratch; }; @@ -97,30 +95,36 @@ static struct ntfs_wof_workspace *ntfs_wof_workspace(u8 block_size_bits) } } +/* + * Size of the buffer a chunk is read into. A chunk is read straight off the + * device, so the buffer has to hold @comp_unit bytes plus the leading partial + * sector. + */ +static size_t ntfs_wof_input_size(const struct ntfs_wof_workspace *ws) +{ + return round_up((size_t)ws->comp_unit + 511, 512); +} + static int ntfs_wof_workspace_prepare(struct ntfs_wof_workspace *ws) { - void *input, *output, *scratch; + void *output, *scratch; size_t scratch_size; - if (ws->input) + if (ws->output) return 0; - ws->input_size = round_up((size_t)ws->comp_unit + 511, 512); scratch_size = ws->codec->scratch_size(ws->comp_unit); if (!scratch_size) return -EINVAL; - input = kvmalloc(ws->input_size, GFP_NOFS); output = kvmalloc(ws->comp_unit, GFP_NOFS); scratch = kvzalloc(scratch_size, GFP_NOFS); - if (!input || !output || !scratch) { - kvfree(input); + if (!output || !scratch) { kvfree(output); kvfree(scratch); return -ENOMEM; } - ws->input = input; ws->output = output; ws->scratch = scratch; return 0; @@ -134,10 +138,8 @@ void ntfs_wof_free_workspaces(void) struct ntfs_wof_workspace *ws = ntfs_wof_workspaces[i]; mutex_lock(ws->lock); - kvfree(ws->input); kvfree(ws->output); kvfree(ws->scratch); - ws->input = NULL; ws->output = NULL; ws->scratch = NULL; mutex_unlock(ws->lock); @@ -602,6 +604,51 @@ static int ntfs_wof_try_direct(struct ntfs_wof_workspace *ws, chunk_end, src, src_len, dst_len); } +/* + * Decompress one chunk into @folio. Only this step needs the workspace, so it + * is the only step that takes the workspace lock. + */ +static int ntfs_wof_decompress_chunk(struct ntfs_wof_workspace *ws, + struct ntfs_volume *vol, + struct address_space *mapping, + struct folio *folio, loff_t folio_start, + loff_t folio_end, u64 chunk_file_offset, + char *chunk_mem, u32 chunk_size, + u32 decomp_size) +{ + loff_t chunk_end = chunk_file_offset + decomp_size; + loff_t copy_start, copy_end; + int err; + + mutex_lock(ws->lock); + err = ntfs_wof_workspace_prepare(ws); + if (err) + goto out_unlock; + + err = ntfs_wof_try_direct(ws, mapping, folio, chunk_file_offset, + chunk_end, chunk_mem, chunk_size, + decomp_size); + if (err != -EAGAIN) + goto out_unlock; + + err = ntfs_wof_decode(ws, chunk_mem, chunk_size, ws->output, + decomp_size); + if (err) { + ntfs_error(vol->sb, "Decompression failed: %d", err); + err = -EINVAL; + goto out_unlock; + } + + copy_start = max_t(loff_t, folio_start, chunk_file_offset); + copy_end = min_t(loff_t, folio_end, chunk_file_offset + decomp_size); + memcpy_to_folio(folio, copy_start - folio_start, + ws->output + copy_start - chunk_file_offset, + copy_end - copy_start); +out_unlock: + mutex_unlock(ws->lock); + return err; +} + int ntfs_read_wof_compressed_block(struct folio *folio) { struct address_space *mapping = folio->mapping; @@ -613,6 +660,8 @@ int ntfs_read_wof_compressed_block(struct folio *folio) loff_t folio_start = folio_pos(folio); loff_t folio_end = folio_next_pos(folio); char *chunk_mem; + void *input; + size_t input_size; u32 decomp_size; u64 chunk_count, chunk_idx, last_chunk, chunk_offset; int err = 0; @@ -652,10 +701,12 @@ int ntfs_read_wof_compressed_block(struct folio *folio) goto out_iput; } - mutex_lock(ws->lock); - err = ntfs_wof_workspace_prepare(ws); - if (err) - goto out_unlock_ws; + input_size = ntfs_wof_input_size(ws); + input = kvmalloc(input_size, GFP_NOFS); + if (!input) { + err = -ENOMEM; + goto out_iput; + } chunk_idx = div_u64(folio_start, ws->comp_unit); last_chunk = @@ -663,55 +714,35 @@ int ntfs_read_wof_compressed_block(struct folio *folio) chunk_count = DIV_ROUND_UP_ULL(i_size, ws->comp_unit); for (; chunk_idx <= last_chunk; chunk_idx++) { u32 chunk_size; - u64 chunk_file_offset; - loff_t chunk_end, copy_start, copy_end; decomp_size = chunk_idx + 1 == chunk_count ? i_size - chunk_idx * ws->comp_unit : ws->comp_unit; err = parse_wof_chunk_table(ni, wof_ni, chunk_idx, chunk_count, decomp_size, &chunk_offset, - &chunk_size, ws->input, - ws->input_size); + &chunk_size, input, input_size); if (err) - goto out_unlock_ws; + goto out_free_input; err = ntfs_read_wof_chunk(vol, wof_ni, chunk_offset, chunk_size, - ws->input, ws->input_size, - &chunk_mem); + input, input_size, &chunk_mem); if (err) - goto out_unlock_ws; - - chunk_file_offset = chunk_idx * ws->comp_unit; - chunk_end = chunk_file_offset + decomp_size; - err = ntfs_wof_try_direct(ws, mapping, folio, chunk_file_offset, - chunk_end, chunk_mem, chunk_size, - decomp_size); - if (!err) - continue; - if (err != -EAGAIN) - goto out_unlock_ws; + goto out_free_input; - err = ntfs_wof_decode(ws, chunk_mem, chunk_size, ws->output, - decomp_size); - if (err) { - ntfs_error(vol->sb, "Decompression failed: %d", err); - err = -EINVAL; - goto out_unlock_ws; - } - copy_start = max_t(loff_t, folio_start, chunk_file_offset); - copy_end = min_t(loff_t, folio_end, - chunk_file_offset + decomp_size); - memcpy_to_folio(folio, copy_start - folio_start, - ws->output + copy_start - chunk_file_offset, - copy_end - copy_start); + err = ntfs_wof_decompress_chunk(ws, vol, mapping, folio, + folio_start, folio_end, + chunk_idx * ws->comp_unit, + chunk_mem, chunk_size, + decomp_size); + if (err) + goto out_free_input; } if (folio_end > i_size) folio_zero_segment(folio, i_size - folio_start, folio_size(folio)); -out_unlock_ws: - mutex_unlock(ws->lock); +out_free_input: + kvfree(input); out_iput: iput(wof_inode); out: diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 204afc5e984b..1c78c695d0dd 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -1240,7 +1240,7 @@ static int ignore_hardlimit(struct dquot *dquot) { struct mem_dqinfo *info = &sb_dqopt(dquot->dq_sb)->info[dquot->dq_id.type]; - return capable(CAP_SYS_RESOURCE) && + return capable_noaudit(CAP_SYS_RESOURCE) && (info->dqi_format->qf_fmt_id != QFMT_VFS_OLD || !(info->dqi_flags & DQF_ROOT_SQUASH)); } diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index f5aad5f61dce..f8aa9e7b4bc6 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -3555,6 +3555,7 @@ int cifs_do_set_acl(const unsigned int xid, struct cifs_tcon *tcon, int rc = 0; int bytes_returned = 0; __u16 params, byte_count, data_count, param_offset, offset; + size_t cifs_acl_size, bytes_available; cifs_dbg(FYI, "In SetPosixACL (Unix) for path %s\n", fileName); setAclRetry: @@ -3574,8 +3575,7 @@ setAclRetry: } params = 6 + name_len; pSMB->MaxParameterCount = cpu_to_le16(2); - /* BB find max SMB size from sess */ - pSMB->MaxDataCount = cpu_to_le16(1000); + pSMB->MaxDataCount = cpu_to_le16(min_t(unsigned int, CIFSMaxBufSize, USHRT_MAX)); pSMB->MaxSetupCount = 0; pSMB->Reserved = 0; pSMB->Flags = 0; @@ -3587,6 +3587,15 @@ setAclRetry: parm_data = ((char *)pSMB) + offset; pSMB->ParameterOffset = cpu_to_le16(param_offset); + /* make sure we can fit the larger cifs_posix_aces in the buffer */ + cifs_acl_size = sizeof(struct cifs_posix_acl) + + (acl->a_count * sizeof(struct cifs_posix_ace)); + bytes_available = (CIFSMaxBufSize + MAX_HEADER_SIZE(tcon->ses->server)) - offset; + if (cifs_acl_size > bytes_available || cifs_acl_size > USHRT_MAX) { + rc = -E2BIG; + goto setACLerrorExit; + } + /* convert to on the wire format for POSIX ACL */ data_count = posix_acl_to_cifs(parm_data, acl, acl_type); @@ -6325,8 +6334,10 @@ CIFSSMBSetEA(const unsigned int xid, struct cifs_tcon *tcon, int name_len; int rc = 0; int bytes_returned = 0; - __u16 params, param_offset, byte_count, offset, count; + __u16 params, param_offset; + unsigned int byte_count, offset, count; int remap = cifs_remap(cifs_sb); + unsigned int total_len; cifs_dbg(FYI, "In SetEA\n"); SetEARetry: @@ -6378,6 +6389,13 @@ SetEARetry: pSMB->Reserved3 = 0; pSMB->SubCommand = cpu_to_le16(TRANS2_SET_PATH_INFORMATION); byte_count = 3 /* pad */ + params + count; + if (check_add_overflow(in_len, byte_count, &total_len) || + byte_count > U16_MAX || + total_len > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE) { + cifs_dbg(VFS, "EA request too large: %u bytes\n", total_len); + cifs_buf_release(pSMB); + return -E2BIG; + } pSMB->DataCount = cpu_to_le16(count); parm_data->list_len = cpu_to_le32(count); parm_data->list.EA_flags = 0; diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index bcd7f1ae99ba..b6e98eb31673 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -4189,14 +4189,25 @@ cifs_setup_session(const unsigned int xid, struct cifs_ses *ses, return rc; } -static int -cifs_set_vol_auth(struct smb3_fs_context *ctx, struct cifs_ses *ses) +static int set_fs_context_auth(struct smb3_fs_context *ctx, + struct cifs_ses *ses) { ctx->sectype = ses->sectype; - /* krb5 is special, since we don't need username or pw */ - if (ctx->sectype == Kerberos) + /* + * krb5 is special as we might need to pass username (passwordless) down + * to cifs.upcall(8) for keytab. + */ + if (ctx->sectype == Kerberos) { + if (ses->user_name && ses->user_name[0]) { + ctx->username = kstrndup(ses->user_name, + CIFS_MAX_USERNAME_LEN, + GFP_KERNEL); + if (!ctx->username) + return -ENOMEM; + } return 0; + } return cifs_set_cifscreds(ctx, ses); } @@ -4236,7 +4247,7 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) ctx->dfs_root_ses = master_tcon->ses->dfs_root_ses; ctx->unicode = master_tcon->ses->unicode; - rc = cifs_set_vol_auth(ctx, master_tcon->ses); + rc = set_fs_context_auth(ctx, master_tcon->ses); if (rc) { tcon = ERR_PTR(rc); goto out; diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index bdcd54157e6c..d7b0a9512dfa 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -999,26 +999,50 @@ static int cifs_do_truncate(const unsigned int xid, struct dentry *dentry) struct cifs_tcon *tcon; int rc; - rc = filemap_write_and_wait(inode->i_mapping); - if (is_interrupt_error(rc)) + rc = inode_lock_killable(inode); + if (rc) return -ERESTARTSYS; + + filemap_invalidate_lock(inode->i_mapping); + + rc = filemap_write_and_wait(inode->i_mapping); + if (is_interrupt_error(rc)) { + rc = -ERESTARTSYS; + goto out; + } mapping_set_error(inode->i_mapping, rc); cfile = find_writable_file(cinode, FIND_FSUID_ONLY); rc = cifs_file_flush(xid, inode, cfile); if (!rc) { if (cfile) { + struct netfs_inode *ictx = netfs_inode(inode); + tcon = tlink_tcon(cfile->tlink); server = tcon->ses->server; + netfs_wb_begin(ictx, false); rc = server->ops->set_file_size(xid, tcon, cfile, 0, false); - } - if (!rc) { - netfs_resize_file(&cinode->netfs, 0, true); - cifs_setsize(inode, 0); + if (!rc) { + netfs_resize_file(&cinode->netfs, 0, true); + cifs_setsize(inode, 0); + cifs_invalidate_cache(inode, 0); + } + netfs_wb_end(ictx); + } else { + /* + * No cached handle; evict stale pages so they can't + * be served after the file is later extended; let + * the server's O_TRUNC open response set the i_size + */ + truncate_inode_pages(inode->i_mapping, 0); cifs_invalidate_cache(inode, 0); } } + +out: + filemap_invalidate_unlock(inode->i_mapping); + inode_unlock(inode); if (cfile) cifsFileInfo_put(cfile); return rc; diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 7d6738ffcb80..cb4fd09f996e 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -1839,31 +1839,31 @@ free_vars: * * @tcon: destination file tcon * @bytes_left: how many bytes are left to copy + * @chunk_size: maximum size of a single chunk * * Return: maximum number of chunks with which Chunks[] can be filled. */ static inline u32 -calc_chunk_count(struct cifs_tcon *tcon, u64 bytes_left) +calc_chunk_count(struct cifs_tcon *tcon, u64 bytes_left, u32 chunk_size) { u32 max_chunks = READ_ONCE(tcon->max_chunks); u32 max_bytes_copy = READ_ONCE(tcon->max_bytes_copy); - u32 max_bytes_chunk = READ_ONCE(tcon->max_bytes_chunk); u64 need; u32 allowed; - if (!max_bytes_chunk || !max_bytes_copy || !max_chunks) + if (!chunk_size || !max_bytes_copy || !max_chunks) return 0; /* chunks needed for the remaining bytes */ - need = DIV_ROUND_UP_ULL(bytes_left, max_bytes_chunk); + need = DIV_ROUND_UP_ULL(bytes_left, chunk_size); /* chunks allowed per cc request */ - allowed = DIV_ROUND_UP(max_bytes_copy, max_bytes_chunk); + allowed = DIV_ROUND_UP(max_bytes_copy, chunk_size); return (u32)umin(need, umin(max_chunks, allowed)); } /** - * smb2_copychunk_range - server-side copy of data range + * __smb2_copychunk_range - server-side copy of data range * * @xid: transaction id * @src_file: source file @@ -1875,15 +1875,15 @@ calc_chunk_count(struct cifs_tcon *tcon, u64 bytes_left) * Obtains a resume key for @src_file and issues FSCTL_SRV_COPYCHUNK_WRITE * IOCTLs, splitting the request into chunks limited by tcon->max_*. * - * Return: @len on success; negative errno on failure. + * Return: 0 on success; negative errno on failure. */ -static ssize_t -smb2_copychunk_range(const unsigned int xid, - struct cifsFileInfo *src_file, - struct cifsFileInfo *dst_file, - u64 src_off, - u64 len, - u64 dst_off) +static int +__smb2_copychunk_range(const unsigned int xid, + struct cifsFileInfo *src_file, + struct cifsFileInfo *dst_file, + u64 src_off, + u64 len, + u64 dst_off) { int rc = 0; unsigned int ret_data_len = 0; @@ -1891,12 +1891,14 @@ smb2_copychunk_range(const unsigned int xid, struct copychunk_ioctl_rsp *cc_rsp = NULL; struct cifs_tcon *tcon; struct srv_copychunk *chunk; - u32 chunks, chunk_count, chunk_bytes; + u32 chunks, chunk_count, chunk_bytes, chunk_size; u32 copy_bytes, copy_bytes_left; u32 chunks_written, bytes_written; u64 total_bytes_left = len; u64 src_off_prev, dst_off_prev; + u64 max_chunk = 0; u32 retries = 0; + bool reverse = false; tcon = tlink_tcon(dst_file->tlink); @@ -1904,8 +1906,50 @@ smb2_copychunk_range(const unsigned int xid, dst_file->fid.volatile_fid, tcon->tid, tcon->ses->Suid, src_off, dst_off, len); + /* + * Same-file left shifts are safe in forward order. For a right shift, + * let L be the copy length, delta the distance between the source and + * destination, and C the normal chunk size: + * + * delta >= L: copy forwards using C + * delta < L: + * delta >= C: copy backwards using C + * delta < C: copy backwards with chunks limited to delta + * + * Copying backwards prevents one chunk from overwriting data needed by + * a later chunk. Limiting the chunk size to delta prevents an individual + * chunk from overlapping itself. + * This limit can be removed once all supported servers handle overlapping + * descriptors safely. + * + * A small right shift over a large range may therefore require many + * chunks. + */ + if (src_file == dst_file && dst_off > src_off) { + u64 delta = dst_off - src_off; + + if (delta < len) { + reverse = true; + max_chunk = delta; + } + } + + /* + * A backward copy walks the offsets down from the end of the range. + * Do this once, outside the retry loop, so a retry does not move the + * offsets again. + */ + if (reverse) { + src_off += len; + dst_off += len; + } + retry: - chunk_count = calc_chunk_count(tcon, total_bytes_left); + chunk_size = READ_ONCE(tcon->max_bytes_chunk); + if (max_chunk && max_chunk < chunk_size) + chunk_size = (u32)max_chunk; + + chunk_count = calc_chunk_count(tcon, total_bytes_left, chunk_size); if (!chunk_count) { rc = -EOPNOTSUPP; goto out; @@ -1946,16 +1990,21 @@ retry: while (copy_bytes_left > 0 && chunks < chunk_count) { chunk = &cc_req->Chunks[chunks++]; + chunk_bytes = umin(copy_bytes_left, chunk_size); + if (reverse) { + src_off -= chunk_bytes; + dst_off -= chunk_bytes; + } + chunk->SourceOffset = cpu_to_le64(src_off); chunk->TargetOffset = cpu_to_le64(dst_off); - - chunk_bytes = umin(copy_bytes_left, tcon->max_bytes_chunk); - chunk->Length = cpu_to_le32(chunk_bytes); /* Buffer is zeroed, no need to set chunk->Reserved = 0 */ - src_off += chunk_bytes; - dst_off += chunk_bytes; + if (!reverse) { + src_off += chunk_bytes; + dst_off += chunk_bytes; + } copy_bytes_left -= chunk_bytes; copy_bytes += chunk_bytes; @@ -2003,6 +2052,18 @@ retry: goto out; } + /* + * A successful COPYCHUNK should copy every descriptor (MS-SMB2 + * 3.3.5.15.6). Reject a short backward copy because the rewind + * below only supports forward copying. + */ + if (unlikely(reverse && bytes_written < copy_bytes)) { + cifs_tcon_dbg(VFS, "Copychunk short write %u/%u (reverse)\n", + bytes_written, copy_bytes); + rc = -EIO; + goto out; + } + /* Partial write: rewind */ if (bytes_written < copy_bytes) { u32 delta = copy_bytes - bytes_written; @@ -2064,10 +2125,27 @@ out: trace_smb3_copychunk_done(xid, src_file->fid.volatile_fid, dst_file->fid.volatile_fid, tcon->tid, tcon->ses->Suid, src_off, dst_off, len); - return len; + return 0; } } +static ssize_t +smb2_copychunk_range(const unsigned int xid, + struct cifsFileInfo *src_file, + struct cifsFileInfo *dst_file, + u64 src_off, + u64 len, + u64 dst_off) +{ + int rc; + + rc = __smb2_copychunk_range(xid, src_file, dst_file, src_off, len, + dst_off); + if (rc) + return rc; + return len; +} + static int smb2_flush_file(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *fid) @@ -2218,7 +2296,7 @@ smb2_duplicate_extents(const unsigned int xid, trgtfile->fid.volatile_fid, tcon->tid, tcon->ses->Suid, src_off, dest_off, len); inode = d_inode(trgtfile->dentry); - if (inode->i_size < dest_off + len) { + if (i_size_read(inode) < dest_off + len) { rc = smb2_set_file_size(xid, tcon, trgtfile, dest_off + len, false); if (rc) goto duplicate_extents_out; @@ -2235,7 +2313,10 @@ smb2_duplicate_extents(const unsigned int xid, if (ret_data_len > 0) cifs_dbg(FYI, "Non-zero response length in duplicate extents\n"); - if (rc == 0) { + if (rc) { + CIFS_I(inode)->time = 0; /* force reval */ + cifs_invalidate_cache(inode, 0); + } else { qrc = SMB2_query_info(xid, tcon, trgtfile->fid.persistent_fid, trgtfile->fid.volatile_fid, &file_inf); spin_lock(&inode->i_lock); @@ -3441,6 +3522,13 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, trace_smb3_zero_enter(xid, cfile->fid.persistent_fid, tcon->tid, ses->Suid, offset, len); + new_size = offset + len; + if (!keep_size && i_size_read(inode) < new_size) { + rc = inode_newsize_ok(inode, new_size); + if (rc) + goto out; + } + filemap_invalidate_lock(inode->i_mapping); netfs_read_sizes(inode, &i_size, &remote_i_size, &zero_point); @@ -3464,6 +3552,9 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, if (keep_size == false && !CIFS_CACHE_READ(cifsi)) goto zero_range_exit; + fscache_invalidate(cifs_inode_cookie(inode), NULL, + i_size_read(inode), 0); + rc = smb3_zero_data(file, tcon, offset, len, xid); if (rc < 0) goto zero_range_exit; @@ -3471,7 +3562,6 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, /* * do we also need to change the size of the file? */ - new_size = offset + len; if (keep_size == false && (unsigned long long)i_size_read(inode) < new_size) { rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, cfile->pid, new_size); @@ -3488,6 +3578,7 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, zero_range_exit: filemap_invalidate_unlock(inode->i_mapping); + out: free_xid(xid); if (rc) trace_smb3_zero_err(xid, cfile->fid.persistent_fid, tcon->tid, @@ -3533,6 +3624,8 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, */ truncate_pagecache_range(inode, offset, offset + len - 1); netfs_wait_for_outstanding_io(inode); + fscache_invalidate(cifs_inode_cookie(inode), NULL, + i_size_read(inode), 0); cifs_dbg(FYI, "Offset %lld len %lld\n", offset, len); @@ -3938,18 +4031,26 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon, } filemap_invalidate_lock(inode->i_mapping); - rc = filemap_write_and_wait_range(inode->i_mapping, off, old_eof - 1); + rc = filemap_write_and_wait_range(inode->i_mapping, + round_down(off, PAGE_SIZE), + old_eof - 1); if (rc < 0) goto out_2; - truncate_pagecache_range(inode, off, old_eof); + netfs_wait_for_outstanding_io(inode); + /* + * Invalidate cached folios from the page containing off to EOF before + * moving data on the server, so subsequent reads do not see stale data. + */ + truncate_pagecache_range(inode, round_down(off, PAGE_SIZE), -1); + fscache_invalidate(cifs_inode_cookie(inode), NULL, old_eof, 0); + spin_lock(&inode->i_lock); netfs_write_zero_point(inode, old_eof); spin_unlock(&inode->i_lock); - netfs_wait_for_outstanding_io(inode); - rc = smb2_copychunk_range(xid, cfile, cfile, off + len, - old_eof - off - len, off); + rc = __smb2_copychunk_range(xid, cfile, cfile, off + len, + old_eof - off - len, off); if (rc < 0) goto out_2; @@ -3982,7 +4083,7 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon, struct cifsFileInfo *cfile = file->private_data; struct inode *inode = file_inode(file); struct cifsInodeInfo *cifsi = CIFS_I(inode); - __u64 count, old_eof, new_eof; + loff_t old_eof, new_eof; xid = get_xid(); @@ -3992,15 +4093,32 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon, goto out; } - count = old_eof - off; - new_eof = old_eof + len; + if (check_add_overflow(old_eof, len, &new_eof)) { + rc = -EFBIG; + goto out; + } + rc = inode_newsize_ok(inode, new_eof); + if (rc) + goto out; + + /* SET_ZERO_DATA creates a hole only in a sparse file. */ + rc = smb2_set_sparse(xid, tcon, cfile, inode, true); + if (rc) + goto out; filemap_invalidate_lock(inode->i_mapping); - rc = filemap_write_and_wait_range(inode->i_mapping, off, new_eof - 1); + rc = filemap_write_and_wait_range(inode->i_mapping, + round_down(off, PAGE_SIZE), + old_eof - 1); if (rc < 0) goto out_2; - truncate_pagecache_range(inode, off, old_eof); netfs_wait_for_outstanding_io(inode); + /* + * Invalidate cached folios from the page containing off to EOF before + * moving data on the server, so subsequent reads do not see stale data. + */ + truncate_pagecache_range(inode, round_down(off, PAGE_SIZE), -1); + fscache_invalidate(cifs_inode_cookie(inode), NULL, old_eof, 0); rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, cfile->pid, new_eof); @@ -4013,7 +4131,12 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon, spin_unlock(&inode->i_lock); fscache_resize_cookie(cifs_inode_cookie(inode), i_size_read(inode)); - rc = smb2_copychunk_range(xid, cfile, cfile, off, count, off + len); + /* + * Move [off, old_eof) right by len. The helper copies backwards if the + * source and destination ranges overlap. + */ + rc = __smb2_copychunk_range(xid, cfile, cfile, off, old_eof - off, + off + len); if (rc < 0) goto out_2; spin_lock(&inode->i_lock); diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c index fdf4e50c27ce..e266859818a4 100644 --- a/fs/smb/client/transport.c +++ b/fs/smb/client/transport.c @@ -101,12 +101,11 @@ void __release_mid(struct TCP_Server_Info *server, struct mid_q_entry *midEntry) trace_smb3_slow_rsp(smb_cmd, midEntry->mid, midEntry->pid, midEntry->when_sent, midEntry->when_received); if (cifsFYI & CIFS_TIMER) { - pr_debug("slow rsp: cmd %d mid %llu", - midEntry->command, midEntry->mid); - cifs_info("A: 0x%lx S: 0x%lx R: 0x%lx\n", - now - midEntry->when_alloc, - now - midEntry->when_sent, - now - midEntry->when_received); + pr_debug("slow rsp: cmd %d mid %llu A: 0x%lx S: 0x%lx R: 0x%lx\n", + midEntry->command, midEntry->mid, + now - midEntry->when_alloc, + now - midEntry->when_sent, + now - midEntry->when_received); } } #endif diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c index 91fdd1ddc61f..4cb92d6599ee 100644 --- a/fs/smb/server/connection.c +++ b/fs/smb/server/connection.c @@ -13,6 +13,7 @@ #include "mgmt/ksmbd_ida.h" #include "mgmt/user_session.h" #include "connection.h" +#include "vfs_cache.h" #include "compress.h" #include "transport_tcp.h" #include "transport_rdma.h" @@ -384,12 +385,12 @@ static void ksmbd_conn_cancel_async_requests(struct ksmbd_conn *conn) spin_lock(&conn->request_lock); list_for_each_entry_safe(work, tmp, &conn->async_requests, async_request_entry) { - if (work->state != KSMBD_WORK_ACTIVE) + if (cmpxchg(&work->state, KSMBD_WORK_ACTIVE, + KSMBD_WORK_CANCELLED) != KSMBD_WORK_ACTIVE) continue; ksmbd_debug(CONN, "Cancel async request id %d\n", work->async_id); - work->state = KSMBD_WORK_CANCELLED; if (work->cancel_fn) work->cancel_fn(work->cancel_argv); } @@ -473,6 +474,9 @@ retry_idle: if (retry_count >= max_timeout) return -EIO; + /* A blocked byte-range lock cannot drain until teardown wakes it. */ + ksmbd_wake_session_blocked_works(sess); + down_read(&conn_list_lock); hash_for_each(conn_list, bkt, conn, hlist) { if (ksmbd_session_is_bound_to_conn(sess, conn)) { diff --git a/fs/smb/server/ksmbd_work.h b/fs/smb/server/ksmbd_work.h index 5f1d3ebab4fb..0844aa929f55 100644 --- a/fs/smb/server/ksmbd_work.h +++ b/fs/smb/server/ksmbd_work.h @@ -82,7 +82,7 @@ struct ksmbd_work { /* Contiguous SMB2 compression transform owned by this work item. */ void *compress_buf; - unsigned char state; + unsigned int state; /* No response for cancelled request */ bool send_no_response:1; /* Request is encrypted */ diff --git a/fs/smb/server/mgmt/share_config.c b/fs/smb/server/mgmt/share_config.c index b2d9580bddc6..cc9f18ede80d 100644 --- a/fs/smb/server/mgmt/share_config.c +++ b/fs/smb/server/mgmt/share_config.c @@ -146,9 +146,9 @@ static struct ksmbd_share_config *__share_lookup(const char *name) static int parse_veto_list(struct ksmbd_share_config *share, char *veto_list, - int veto_list_sz) + size_t veto_list_sz) { - int sz = 0; + size_t sz; if (!veto_list_sz) return 0; @@ -156,7 +156,7 @@ static int parse_veto_list(struct ksmbd_share_config *share, while (veto_list_sz > 0) { struct ksmbd_veto_pattern *p; - sz = strlen(veto_list); + sz = strnlen(veto_list, veto_list_sz); if (!sz) break; @@ -164,7 +164,7 @@ static int parse_veto_list(struct ksmbd_share_config *share, if (!p) return -ENOMEM; - p->pattern = kstrdup(veto_list, KSMBD_DEFAULT_GFP); + p->pattern = kstrndup(veto_list, sz, KSMBD_DEFAULT_GFP); if (!p->pattern) { kfree(p); return -ENOMEM; @@ -172,6 +172,9 @@ static int parse_veto_list(struct ksmbd_share_config *share, list_add(&p->list, &share->veto_list); + if (sz == veto_list_sz) + break; + veto_list += sz + 1; veto_list_sz -= (sz + 1); } @@ -224,17 +227,28 @@ static struct ksmbd_share_config *share_config_request(struct ksmbd_work *work, } if (!test_share_config_flag(share, KSMBD_SHARE_FLAG_PIPE)) { - int path_len = PATH_MAX; - - if (resp->payload_sz) - path_len = resp->payload_sz - resp->veto_list_sz; + size_t path_len; - share->path = kstrndup(ksmbd_share_config_path(resp), path_len, - KSMBD_DEFAULT_GFP); - if (!share->path) { - ret = -ENOMEM; + if (resp->payload_sz <= resp->veto_list_sz) { + ret = -EINVAL; } else { - ret = 0; + path_len = resp->payload_sz - resp->veto_list_sz; + if (resp->veto_list_sz) + path_len--; + + if (!path_len) { + ret = -EINVAL; + } else { + share->path = kstrndup( + ksmbd_share_config_path(resp), + path_len, KSMBD_DEFAULT_GFP); + if (!share->path) + ret = -ENOMEM; + else + ret = 0; + } + } + if (share->path) { share->path_sz = strlen(share->path); while (share->path_sz > 1 && share->path[share->path_sz - 1] == '/') diff --git a/fs/smb/server/mgmt/tree_connect.c b/fs/smb/server/mgmt/tree_connect.c index 5f63e236267a..dd1db3554cae 100644 --- a/fs/smb/server/mgmt/tree_connect.c +++ b/fs/smb/server/mgmt/tree_connect.c @@ -82,6 +82,8 @@ ksmbd_tree_conn_connect(struct ksmbd_work *work, const char *share_name) down_write(&sess->tree_conns_lock); ret = xa_err(xa_store(&sess->tree_conns, tree_conn->id, tree_conn, KSMBD_DEFAULT_GFP)); + if (!ret) + atomic_inc(&tree_conn->refcount); up_write(&sess->tree_conns_lock); if (ret) { status.ret = -ENOMEM; @@ -129,6 +131,12 @@ int ksmbd_tree_conn_disconnect(struct ksmbd_session *sess, struct ksmbd_tree_connect *tree_conn) { down_write(&sess->tree_conns_lock); + if (tree_conn->t_state == TREE_DISCONNECTED || + xa_load(&sess->tree_conns, tree_conn->id) != tree_conn) { + up_write(&sess->tree_conns_lock); + return -ENOENT; + } + tree_conn->t_state = TREE_DISCONNECTED; xa_erase(&sess->tree_conns, tree_conn->id); up_write(&sess->tree_conns_lock); diff --git a/fs/smb/server/mgmt/user_session.c b/fs/smb/server/mgmt/user_session.c index 7022d5d656b4..2eb8f730e99e 100644 --- a/fs/smb/server/mgmt/user_session.c +++ b/fs/smb/server/mgmt/user_session.c @@ -666,10 +666,21 @@ void destroy_previous_session(struct ksmbd_conn *conn, memcmp(user->passkey, prev_user->passkey, user->passkey_sz)) goto out; + down_write(&prev_sess->chann_lock); + if (prev_sess->tearing_down) { + up_write(&prev_sess->chann_lock); + goto out; + } + prev_sess->tearing_down = true; + up_write(&prev_sess->chann_lock); + ksmbd_all_conn_set_status(prev_sess, KSMBD_SESS_NEED_RECONNECT); err = ksmbd_conn_wait_idle_sess(conn, prev_sess); if (err) { - ksmbd_all_conn_set_status(prev_sess, KSMBD_SESS_NEED_SETUP); + down_write(&prev_sess->chann_lock); + prev_sess->tearing_down = false; + up_write(&prev_sess->chann_lock); + ksmbd_all_conn_set_status(prev_sess, KSMBD_SESS_GOOD); goto out; } diff --git a/fs/smb/server/mgmt/user_session.h b/fs/smb/server/mgmt/user_session.h index f8a24c33f7fe..3e52d4cc1324 100644 --- a/fs/smb/server/mgmt/user_session.h +++ b/fs/smb/server/mgmt/user_session.h @@ -42,6 +42,7 @@ struct ksmbd_session { bool sign; bool enc; + bool tearing_down; int state; __u8 *Preauth_HashValue; diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 58af0fddf39f..1b8c3482d1e4 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -924,31 +924,69 @@ out: ksmbd_conn_put(conn); } +/* + * Select and pin the connection used for an oplock break before doing any + * allocations which may sleep. The caller of oplock_break() holds a live + * reference on ci (a file being opened, a file being operated on, or an + * explicit ksmbd_inode_lookup_lock() reference in the parent lease break + * paths), so the inode cannot be freed during the call and its lock is + * reachable without dereferencing opinfo->o_fp, which is not pinned by + * the oplock reference and may be freed by a concurrent close. + * + * opinfo->conn is cleared under ci->m_lock by session_fd_check() when the + * durable handle owning the oplock is disconnected, reassigned by + * ksmbd_reopen_durable_fd() under the same lock, and the last + * ksmbd_conn_put() of the old connection frees it. Holding the read lock + * excludes both writers, so the connection cannot be freed while it is + * selected. + */ +static struct ksmbd_conn *smb2_oplock_break_conn_get(struct oplock_info *opinfo, + struct ksmbd_inode *ci) +{ + struct ksmbd_conn *conn; + + down_read(&ci->m_lock); + conn = READ_ONCE(opinfo->conn); + if (conn && !ksmbd_conn_releasing(conn)) + conn = ksmbd_conn_get(conn); + else + conn = NULL; + up_read(&ci->m_lock); + + return conn; +} + /** * smb2_oplock_break_noti() - send smb2 exclusive/batch to level2 oplock * break command from server to client * @opinfo: oplock info object + * @ci: inode owning the break target's oplock list, pinned by + * the caller * * Return: 0 on success, otherwise error */ -static int smb2_oplock_break_noti(struct oplock_info *opinfo) +static int smb2_oplock_break_noti(struct oplock_info *opinfo, + struct ksmbd_inode *ci) { struct ksmbd_conn *conn; struct oplock_break_info *br_info; int ret = 0; struct ksmbd_work *work; - conn = READ_ONCE(opinfo->conn); + conn = smb2_oplock_break_conn_get(opinfo, ci); if (!conn) return ksmbd_invalidate_durable_fd(opinfo->fid); work = ksmbd_alloc_work_struct(); - if (!work) + if (!work) { + ksmbd_conn_put(conn); return -ENOMEM; + } br_info = kmalloc_obj(struct oplock_break_info, KSMBD_DEFAULT_GFP); if (!br_info) { ksmbd_free_work_struct(work); + ksmbd_conn_put(conn); return -ENOMEM; } @@ -957,7 +995,8 @@ static int smb2_oplock_break_noti(struct oplock_info *opinfo) br_info->open_trunc = opinfo->open_trunc; work->request_buf = (char *)br_info; - work->conn = ksmbd_conn_get(conn); + /* Transfer the reference acquired by smb2_oplock_break_conn_get(). */ + work->conn = conn; work->sess = opinfo->sess; ksmbd_conn_r_count_inc(conn); @@ -1154,9 +1193,9 @@ static void wait_lease_breaking(struct oplock_info *opinfo) } } -static int oplock_break(struct oplock_info *brk_opinfo, int req_op_level, - struct ksmbd_work *in_work, bool share_break, - bool sync_lease_break) +static int oplock_break(struct oplock_info *brk_opinfo, struct ksmbd_inode *ci, + int req_op_level, struct ksmbd_work *in_work, + bool share_break, bool sync_lease_break) { int err = 0; bool sent_interim = false; @@ -1298,7 +1337,7 @@ again: } } - err = smb2_oplock_break_noti(brk_opinfo); + err = smb2_oplock_break_noti(brk_opinfo, ci); ksmbd_debug(OPLOCK, "oplock granted = %d\n", brk_opinfo->level); if (brk_opinfo->op_state == OPLOCK_CLOSING) @@ -1326,13 +1365,14 @@ static int oplock_break_add(struct list_head *head, struct oplock_info *opinfo) return 0; } -static void oplock_break_drain_none(struct list_head *head) +static void oplock_break_drain_none(struct list_head *head, + struct ksmbd_inode *ci) { struct oplock_break_entry *ent, *tmp; list_for_each_entry_safe(ent, tmp, head, list) { - oplock_break(ent->opinfo, SMB2_OPLOCK_LEVEL_NONE, NULL, false, - false); + oplock_break(ent->opinfo, ci, SMB2_OPLOCK_LEVEL_NONE, NULL, + false, false); list_del(&ent->list); opinfo_put(ent->opinfo); kfree(ent); @@ -1481,7 +1521,7 @@ void smb_send_parent_lease_break_noti(struct ksmbd_file *fp, } up_read(&p_ci->m_lock); - oplock_break_drain_none(&brk_list); + oplock_break_drain_none(&brk_list, p_ci); ksmbd_inode_put(p_ci); } @@ -1525,7 +1565,7 @@ void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp) } up_read(&p_ci->m_lock); - oplock_break_drain_none(&brk_list); + oplock_break_drain_none(&brk_list, p_ci); ksmbd_inode_put(p_ci); } @@ -1665,7 +1705,7 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, prev_durable_detached = prev_op_snapshot.durable_detached; prev_fid = prev_op_snapshot.fid; - err = oplock_break(prev_opinfo, break_level, work, + err = oplock_break(prev_opinfo, ci, break_level, work, share_ret < 0 && prev_opinfo->is_lease, false); if (prev_durable_detached || (prev_durable_open && err == -ENOENT)) ksmbd_invalidate_durable_fd(prev_fid); @@ -1771,7 +1811,8 @@ static bool smb_break_all_write_oplock(struct ksmbd_work *work, } brk_opinfo->open_trunc = is_trunc; - oplock_break(brk_opinfo, SMB2_OPLOCK_LEVEL_II, work, false, false); + oplock_break(brk_opinfo, fp->f_ci, SMB2_OPLOCK_LEVEL_II, work, false, + false); sent_break = true; opinfo_put(brk_opinfo); @@ -1863,7 +1904,7 @@ next: brk_op->op_state = OPLOCK_STATE_NONE; spin_unlock(&brk_op->state_lock); } else { - oplock_break(brk_op, + oplock_break(brk_op, ci, brk_op->is_lease && !is_trunc ? SMB2_OPLOCK_LEVEL_II : SMB2_OPLOCK_LEVEL_NONE, send_interim && !sent_interim ? work : NULL, diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index a8046f477d54..0ecc52fde69c 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -97,6 +97,11 @@ static int register_session_channel(struct ksmbd_session *sess, int rc = 0; down_write(&sess->chann_lock); + if (sess->tearing_down) { + rc = -ESHUTDOWN; + goto out; + } + if (xa_load(&sess->ksmbd_chann_list, (long)conn)) goto out; @@ -873,7 +878,8 @@ int smb2_allocate_rsp_buf(struct ksmbd_work *work) req = smb_get_msg(work->request_buf); if ((req->InfoType == SMB2_O_INFO_FILE && (req->FileInfoClass == FILE_FULL_EA_INFORMATION || - req->FileInfoClass == FILE_ALL_INFORMATION)) || + req->FileInfoClass == FILE_ALL_INFORMATION || + req->FileInfoClass == FILE_NORMALIZED_NAME_INFORMATION)) || req->InfoType == SMB2_O_INFO_SECURITY) sz = large_sz; } @@ -2784,6 +2790,7 @@ int smb2_tree_connect(struct ksmbd_work *work) struct ksmbd_session *sess = work->sess; char *treename = NULL, *name = NULL; struct ksmbd_tree_conn_status status; + struct ksmbd_tree_connect *tree_conn = NULL; struct ksmbd_share_config *share = NULL; int rc = -EINVAL; @@ -2811,6 +2818,7 @@ int smb2_tree_connect(struct ksmbd_work *work) status = ksmbd_tree_conn_connect(work, name); if (status.ret == KSMBD_TREE_CONN_STATUS_OK) { + tree_conn = status.tree_conn; rsp->hdr.Id.SyncId.TreeId = cpu_to_le32(status.tree_conn->id); share = status.tree_conn->share_conf; @@ -2854,8 +2862,15 @@ int smb2_tree_connect(struct ksmbd_work *work) status.tree_conn->posix_extensions = true; down_write(&sess->tree_conns_lock); - status.tree_conn->t_state = TREE_CONNECTED; + if (status.tree_conn->t_state == TREE_DISCONNECTED) { + status.ret = KSMBD_TREE_CONN_STATUS_ERROR; + share = NULL; + } else { + status.tree_conn->t_state = TREE_CONNECTED; + } up_write(&sess->tree_conns_lock); + if (status.ret != KSMBD_TREE_CONN_STATUS_OK) + goto out_err1; rsp->StructureSize = cpu_to_le16(16); out_err1: /* @@ -2882,9 +2897,6 @@ out_err1: rc = ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_tree_connect_rsp)); if (rc) { if (status.ret == KSMBD_TREE_CONN_STATUS_OK) { - down_write(&sess->tree_conns_lock); - status.tree_conn->t_state = TREE_DISCONNECTED; - up_write(&sess->tree_conns_lock); ksmbd_tree_conn_disconnect(sess, status.tree_conn); status.tree_conn = NULL; } @@ -2925,6 +2937,9 @@ out_err1: if (status.ret != KSMBD_TREE_CONN_STATUS_OK) smb2_set_err_rsp(work); + if (tree_conn) + ksmbd_tree_connect_put(tree_conn); + return rc; } @@ -3028,17 +3043,6 @@ int smb2_tree_disconnect(struct ksmbd_work *work) ksmbd_close_tree_conn_fds(work); - down_write(&sess->tree_conns_lock); - if (tcon->t_state == TREE_DISCONNECTED) { - up_write(&sess->tree_conns_lock); - rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; - err = -ENOENT; - goto err_out; - } - - tcon->t_state = TREE_DISCONNECTED; - up_write(&sess->tree_conns_lock); - err = ksmbd_tree_conn_disconnect(sess, tcon); if (err) { rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; @@ -3086,17 +3090,41 @@ int smb2_session_logoff(struct ksmbd_work *work) smb2_set_err_rsp(work); return -ENOENT; } + + down_write(&sess->chann_lock); + if (sess->tearing_down) { + up_write(&sess->chann_lock); + ksmbd_conn_unlock(conn); + rsp->hdr.Status = STATUS_USER_SESSION_DELETED; + smb2_set_err_rsp(work); + return -ENOENT; + } + sess->tearing_down = true; + up_write(&sess->chann_lock); + ksmbd_all_conn_set_status(sess, KSMBD_SESS_NEED_RECONNECT); ksmbd_conn_unlock(conn); + err = ksmbd_conn_wait_idle_sess(conn, sess); + if (err) { + down_write(&sess->chann_lock); + sess->tearing_down = false; + up_write(&sess->chann_lock); + ksmbd_all_conn_set_status(sess, KSMBD_SESS_GOOD); + rsp->hdr.Status = STATUS_UNEXPECTED_IO_ERROR; + smb2_set_err_rsp(work); + return err; + } + ksmbd_close_session_fds(work); - ksmbd_conn_wait_idle(conn); if (ksmbd_tree_conn_session_logoff(sess)) { ksmbd_debug(SMB, "Invalid tid %d\n", req->hdr.Id.SyncId.TreeId); rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; smb2_set_err_rsp(work); - return -ENOENT; + err = -ENOENT; + } else { + err = 0; } down_write(&conn->session_lock); @@ -3106,6 +3134,9 @@ int smb2_session_logoff(struct ksmbd_work *work) ksmbd_all_conn_set_status(sess, KSMBD_SESS_NEED_SETUP); + if (err) + return err; + rsp->StructureSize = cpu_to_le16(4); err = ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_logoff_rsp)); if (err) { @@ -6757,7 +6788,7 @@ static int get_file_normalized_name_info(struct ksmbd_work *work, { struct smb2_file_alt_name_info *file_info; char *filename, *normalized, *stream_name; - int conv_len, filename_len; + int buf_free_len, conv_len, filename_len; if (work->conn->dialect < SMB311_PROT_ID) { rsp->hdr.Status = STATUS_NOT_SUPPORTED; @@ -6781,6 +6812,14 @@ static int get_file_normalized_name_info(struct ksmbd_work *work, return -ENOMEM; filename_len = strlen(normalized); + buf_free_len = smb2_resp_buf_len(work, sizeof(*rsp) + + sizeof(*file_info)); + if (buf_free_len < 0 || + (size_t)buf_free_len < (filename_len + 1) * sizeof(__le16)) { + kfree(normalized); + return -EINVAL; + } + file_info = (struct smb2_file_alt_name_info *)rsp->Buffer; conv_len = smbConvertToUTF16((__le16 *)file_info->FileName, normalized, filename_len, @@ -7444,6 +7483,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, struct object_id_info *info; info = (struct object_id_info *)(rsp->Buffer); + memset(info, 0, sizeof(*info)); if (path.mnt->mnt_sb->s_uuid_len == 16) memcpy(info->objid, path.mnt->mnt_sb->s_uuid.b, @@ -7499,6 +7539,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->FreeSpaceStopFiltering = 0; info->DefaultQuotaThreshold = cpu_to_le64(SMB2_NO_FID); info->DefaultQuotaLimit = cpu_to_le64(SMB2_NO_FID); + info->FileSystemControlFlags = 0; info->Padding = 0; rsp->OutputBufferLength = cpu_to_le32(48); fixed_len = 48; @@ -7521,6 +7562,9 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->UserBlocksAvail = cpu_to_le64(stfs.f_bavail); info->TotalFileNodes = cpu_to_le64(stfs.f_files); info->FreeFileNodes = cpu_to_le64(stfs.f_ffree); + info->FileSysIdentifier = + cpu_to_le64((u64)(u32)stfs.f_fsid.val[1] << 32 | + (u32)stfs.f_fsid.val[0]); rsp->OutputBufferLength = cpu_to_le32(56); fixed_len = 56; } @@ -8620,13 +8664,18 @@ static noinline int smb2_read_pipe(struct ksmbd_work *work) } aux_payload_buf = - kvmalloc(rpc_resp->payload_sz, KSMBD_DEFAULT_GFP); + kvmalloc(ALIGN(rpc_resp->payload_sz, 8), + KSMBD_DEFAULT_GFP); if (!aux_payload_buf) { err = -ENOMEM; goto out; } memcpy(aux_payload_buf, rpc_resp->payload, rpc_resp->payload_sz); + if (rpc_resp->payload_sz & 7) + memset(aux_payload_buf + rpc_resp->payload_sz, 0, + ALIGN(rpc_resp->payload_sz, 8) - + rpc_resp->payload_sz); nbytes = rpc_resp->payload_sz; err = ksmbd_iov_pin_rsp_read(work, (void *)rsp, @@ -9680,14 +9729,14 @@ int smb2_cancel(struct ksmbd_work *work) * still on conn->async_requests with a live cancel_fn * pointing at the freed file_lock. */ - if (iter->state != KSMBD_WORK_ACTIVE) + if (cmpxchg(&iter->state, KSMBD_WORK_ACTIVE, + KSMBD_WORK_CANCELLED) != KSMBD_WORK_ACTIVE) break; ksmbd_debug(SMB, "smb2 with AsyncId %llu cancelled command = 0x%x\n", le64_to_cpu(hdr->Id.AsyncId), le16_to_cpu(chdr->Command)); - iter->state = KSMBD_WORK_CANCELLED; if (iter->cancel_fn == smb2_notify_cancel_fn) cancelled_notify = smb2_notify_cancel_claim(iter->cancel_argv); @@ -9716,11 +9765,16 @@ int smb2_cancel(struct ksmbd_work *work) iter == work) continue; + if (cmpxchg(&iter->state, KSMBD_WORK_ACTIVE, + KSMBD_WORK_CANCELLED) != KSMBD_WORK_ACTIVE) + break; + ksmbd_debug(SMB, "smb2 with mid %llu cancelled command = 0x%x\n", le64_to_cpu(hdr->MessageId), le16_to_cpu(chdr->Command)); - iter->state = KSMBD_WORK_CANCELLED; + if (iter->cancel_fn) + iter->cancel_fn(iter->cancel_argv); break; } spin_unlock(&conn->request_lock); diff --git a/fs/smb/server/smbacl.c b/fs/smb/server/smbacl.c index 8ad2e5a5cca8..1fad6ccf3a72 100644 --- a/fs/smb/server/smbacl.c +++ b/fs/smb/server/smbacl.c @@ -383,10 +383,10 @@ void free_acl_state(struct posix_acl_state *state) kfree(state->groups); } -static void parse_dacl(struct mnt_idmap *idmap, - struct smb_acl *pdacl, char *end_of_acl, - struct smb_sid *pownersid, struct smb_sid *pgrpsid, - struct smb_fattr *fattr) +static int parse_dacl(struct mnt_idmap *idmap, + struct smb_acl *pdacl, char *end_of_acl, + struct smb_sid *pownersid, struct smb_sid *pgrpsid, + struct smb_fattr *fattr) { int i, ret; u16 num_aces = 0; @@ -400,13 +400,13 @@ static void parse_dacl(struct mnt_idmap *idmap, bool owner_found = false, group_found = false, others_found = false; if (!pdacl) - return; + return 0; /* validate that we do not go past end of acl */ if (end_of_acl < (char *)pdacl + sizeof(struct smb_acl) || end_of_acl < (char *)pdacl + le16_to_cpu(pdacl->size)) { pr_err("ACL too small to parse DACL\n"); - return; + return -EINVAL; } ksmbd_debug(SMB, "DACL revision %d size %d num aces %d\n", @@ -418,31 +418,31 @@ static void parse_dacl(struct mnt_idmap *idmap, num_aces = le16_to_cpu(pdacl->num_aces); if (num_aces <= 0) - return; + return 0; dacl_size = le16_to_cpu(pdacl->size); if (dacl_size < sizeof(struct smb_acl)) - return; + return -EINVAL; if (num_aces > (dacl_size - sizeof(struct smb_acl)) / (offsetof(struct smb_ace, sid) + offsetof(struct smb_sid, sub_auth) + sizeof(__le16))) - return; + return -EINVAL; ret = init_acl_state(&acl_state, num_aces); if (ret) - return; + return ret; ret = init_acl_state(&default_acl_state, num_aces); if (ret) { free_acl_state(&acl_state); - return; + return ret; } ppace = kmalloc_objs(struct smb_ace *, num_aces, KSMBD_DEFAULT_GFP); if (!ppace) { free_acl_state(&default_acl_state); free_acl_state(&acl_state); - return; + return -ENOMEM; } /* @@ -451,8 +451,10 @@ static void parse_dacl(struct mnt_idmap *idmap, * user/group/other have no permissions */ for (i = 0; i < num_aces; ++i) { - if (end_of_acl - acl_base < acl_size) - break; + if (end_of_acl - acl_base < acl_size) { + ret = -EINVAL; + goto out; + } ppace[i] = (struct smb_ace *)(acl_base + acl_size); acl_base = (char *)ppace[i]; @@ -465,8 +467,10 @@ static void parse_dacl(struct mnt_idmap *idmap, (end_of_acl - acl_base < acl_size + sizeof(__le32) * ppace[i]->sid.num_subauth) || (le16_to_cpu(ppace[i]->size) < - acl_size + sizeof(__le32) * ppace[i]->sid.num_subauth)) - break; + acl_size + sizeof(__le32) * ppace[i]->sid.num_subauth)) { + ret = -EINVAL; + goto out; + } acl_size = le16_to_cpu(ppace[i]->size); ppace[i]->access_req = @@ -524,8 +528,8 @@ static void parse_dacl(struct mnt_idmap *idmap, temp_fattr.cf_uid = INVALID_UID; ret = sid_to_id(idmap, &ppace[i]->sid, SIDOWNER, &temp_fattr); if (ret || uid_eq(temp_fattr.cf_uid, INVALID_UID)) { - pr_err("%s: Error %d mapping Owner SID to uid\n", - __func__, ret); + pr_err_ratelimited("%s: Error %d mapping Owner SID to uid\n", + __func__, ret); continue; } @@ -541,7 +545,6 @@ static void parse_dacl(struct mnt_idmap *idmap, ((acl_mode & 0700) >> 6) | 0004; } } - kfree(ppace); if (owner_found) { /* The owner must be set to at least read-only. */ @@ -584,10 +587,12 @@ static void parse_dacl(struct mnt_idmap *idmap, fattr->cf_acls = posix_acl_alloc(acl_state.users->n + acl_state.groups->n + 4, KSMBD_DEFAULT_GFP); - if (fattr->cf_acls) { - cf_pace = fattr->cf_acls->a_entries; - posix_state_to_acl(&acl_state, cf_pace); + if (!fattr->cf_acls) { + ret = -ENOMEM; + goto out; } + cf_pace = fattr->cf_acls->a_entries; + posix_state_to_acl(&acl_state, cf_pace); } } @@ -598,14 +603,20 @@ static void parse_dacl(struct mnt_idmap *idmap, fattr->cf_dacls = posix_acl_alloc(default_acl_state.users->n + default_acl_state.groups->n + 4, KSMBD_DEFAULT_GFP); - if (fattr->cf_dacls) { - cf_pdace = fattr->cf_dacls->a_entries; - posix_state_to_acl(&default_acl_state, cf_pdace); + if (!fattr->cf_dacls) { + ret = -ENOMEM; + goto out; } + cf_pdace = fattr->cf_dacls->a_entries; + posix_state_to_acl(&default_acl_state, cf_pdace); } } + ret = 0; +out: + kfree(ppace); free_acl_state(&acl_state); free_acl_state(&default_acl_state); + return ret; } static void set_posix_acl_entries_dacl(struct mnt_idmap *idmap, @@ -966,8 +977,10 @@ int parse_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd, if (dacloffset < sizeof(struct smb_ntsd)) return -EINVAL; - parse_dacl(idmap, dacl_ptr, end_of_acl, - owner_sid_ptr, group_sid_ptr, fattr); + rc = parse_dacl(idmap, dacl_ptr, end_of_acl, + owner_sid_ptr, group_sid_ptr, fattr); + if (rc) + return rc; } return 0; diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c index 4b0b572a3e1b..e550aa41ad2c 100644 --- a/fs/smb/server/transport_ipc.c +++ b/fs/smb/server/transport_ipc.c @@ -532,14 +532,21 @@ static int ipc_validate_msg(struct ipc_msg_table_entry *entry) if (entry->msg_sz < sizeof(struct ksmbd_share_config_response)) return -EINVAL; - if (resp->payload_sz) { - if (resp->payload_sz < resp->veto_list_sz) - return -EINVAL; + if (strnlen(resp->share_name, sizeof(resp->share_name)) == + sizeof(resp->share_name)) + return -EINVAL; - if (check_add_overflow(sizeof(struct ksmbd_share_config_response), - resp->payload_sz, &msg_sz)) - return -EINVAL; - } + if (resp->veto_list_sz > resp->payload_sz) + return -EINVAL; + + if (resp->flags != KSMBD_SHARE_FLAG_INVALID && + !(resp->flags & KSMBD_SHARE_FLAG_PIPE) && + resp->payload_sz <= resp->veto_list_sz) + return -EINVAL; + + if (check_add_overflow(sizeof(struct ksmbd_share_config_response), + resp->payload_sz, &msg_sz)) + return -EINVAL; break; } case KSMBD_EVENT_LOGIN_REQUEST_EXT: diff --git a/fs/smb/server/transport_tcp.c b/fs/smb/server/transport_tcp.c index 832e93084605..4968cfc1a572 100644 --- a/fs/smb/server/transport_tcp.c +++ b/fs/smb/server/transport_tcp.c @@ -39,6 +39,7 @@ struct tcp_transport { static const struct ksmbd_transport_ops ksmbd_tcp_transport_ops; static void tcp_stop_kthread(struct task_struct *kthread); +static void ksmbd_tcp_stop_listener(struct interface *iface); static struct interface *alloc_iface(char *ifname); static void ksmbd_tcp_disconnect(struct ksmbd_transport *t); @@ -321,13 +322,20 @@ static int ksmbd_tcp_run_kthread(struct interface *iface) int rc; struct task_struct *kthread; - kthread = kthread_run(ksmbd_kthread_fn, (void *)iface, "ksmbd-%s", - iface->name); + kthread = kthread_create(ksmbd_kthread_fn, (void *)iface, "ksmbd-%s", + iface->name); if (IS_ERR(kthread)) { rc = PTR_ERR(kthread); return rc; } + + /* + * The listener can exit after its socket is shutdown, so keep the + * task_struct alive until the caller has stopped it. + */ + get_task_struct(kthread); iface->ksmbd_kthread = kthread; + wake_up_process(kthread); return 0; } @@ -598,12 +606,7 @@ static int ksmbd_netdev_event(struct notifier_block *nb, unsigned long event, if (iface && iface->state == IFACE_STATE_CONFIGURED) { ksmbd_debug(CONN, "netdev-down event: netdev(%s) is going down\n", iface->name); - kernel_sock_shutdown(iface->ksmbd_socket, SHUT_RDWR); - tcp_stop_kthread(iface->ksmbd_kthread); - iface->ksmbd_kthread = NULL; - sock_release(iface->ksmbd_socket); - iface->ksmbd_socket = NULL; - + ksmbd_tcp_stop_listener(iface); iface->state = IFACE_STATE_DOWN; break; } @@ -631,11 +634,25 @@ static void tcp_stop_kthread(struct task_struct *kthread) if (!kthread) return; - ret = kthread_stop(kthread); + ret = kthread_stop_put(kthread); if (ret) pr_err("failed to stop forker thread\n"); } +static void ksmbd_tcp_stop_listener(struct interface *iface) +{ + if (iface->ksmbd_socket) + kernel_sock_shutdown(iface->ksmbd_socket, SHUT_RDWR); + + tcp_stop_kthread(iface->ksmbd_kthread); + iface->ksmbd_kthread = NULL; + + if (iface->ksmbd_socket) { + sock_release(iface->ksmbd_socket); + iface->ksmbd_socket = NULL; + } +} + void ksmbd_tcp_destroy(void) { struct interface *iface, *tmp; @@ -643,6 +660,7 @@ void ksmbd_tcp_destroy(void) unregister_netdevice_notifier(&ksmbd_netdev_notifier); list_for_each_entry_safe(iface, tmp, &iface_list, entry) { + ksmbd_tcp_stop_listener(iface); list_del(&iface->entry); kfree(iface->name); kfree(iface); diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index d2b524f79cbe..c2c9aaa5de1b 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -2007,6 +2007,11 @@ out: return ret; } +static bool ksmbd_vfs_copy_range_valid(loff_t offset, size_t len) +{ + return offset >= 0 && (loff_t)len <= MAX_LFS_FILESIZE - offset; +} + int ksmbd_vfs_copy_file_ranges(struct ksmbd_work *work, struct ksmbd_file *src_fp, struct ksmbd_file *dst_fp, @@ -2042,6 +2047,10 @@ int ksmbd_vfs_copy_file_ranges(struct ksmbd_work *work, dst_off = le64_to_cpu(chunks[i].TargetOffset); len = le32_to_cpu(chunks[i].Length); + if (!ksmbd_vfs_copy_range_valid(src_off, len) || + !ksmbd_vfs_copy_range_valid(dst_off, len)) + return -E2BIG; + if (check_lock_range(src_fp->filp, src_off, src_off + len - 1, READ)) return -EAGAIN; @@ -2134,7 +2143,8 @@ int ksmbd_vfs_copy_file_ranges(struct ksmbd_work *work, len = le32_to_cpu(chunks[i].Length); copy_len = len; - if (src_off < 0) + if (!ksmbd_vfs_copy_range_valid(src_off, len) || + !ksmbd_vfs_copy_range_valid(dst_off, len)) return -E2BIG; if (src_off > src_file_size || len > src_file_size - src_off) { diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index 81626d204249..fd2c595f0486 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -846,12 +846,25 @@ static void set_close_state_blocked_works(struct ksmbd_file *fp) spin_lock(&fp->f_lock); list_for_each_entry(cancel_work, &fp->blocked_works, fp_entry) { - cancel_work->state = KSMBD_WORK_CLOSED; - cancel_work->cancel_fn(cancel_work->cancel_argv); + if (xchg(&cancel_work->state, KSMBD_WORK_CLOSED) == + KSMBD_WORK_ACTIVE) + cancel_work->cancel_fn(cancel_work->cancel_argv); } spin_unlock(&fp->f_lock); } +void ksmbd_wake_session_blocked_works(struct ksmbd_session *sess) +{ + struct ksmbd_file_table *ft = &sess->file_table; + struct ksmbd_file *fp; + unsigned int id; + + read_lock(&ft->lock); + idr_for_each_entry(ft->idr, fp, id) + set_close_state_blocked_works(fp); + read_unlock(&ft->lock); +} + int ksmbd_close_fd(struct ksmbd_work *work, u64 id) { struct ksmbd_file *fp; diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h index 502efb16f05f..1884f6deb9d0 100644 --- a/fs/smb/server/vfs_cache.h +++ b/fs/smb/server/vfs_cache.h @@ -226,6 +226,7 @@ void ksmbd_stop_durable_scavenger(void); bool ksmbd_durable_scavenger_active(void); void ksmbd_close_tree_conn_fds(struct ksmbd_work *work); void ksmbd_close_session_fds(struct ksmbd_work *work); +void ksmbd_wake_session_blocked_works(struct ksmbd_session *sess); 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); diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile index 9f7133e02576..399a207f2d0e 100644 --- a/fs/xfs/Makefile +++ b/fs/xfs/Makefile @@ -91,6 +91,7 @@ xfs-y += xfs_aops.o \ xfs_healthmon.o \ xfs_icache.o \ xfs_ioctl.o \ + xfs_ioend.o \ xfs_iomap.o \ xfs_iops.o \ xfs_inode.o \ diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h index c0b9f9f2c413..fca2eb74908c 100644 --- a/fs/xfs/libxfs/xfs_rtgroup.h +++ b/fs/xfs/libxfs/xfs_rtgroup.h @@ -359,7 +359,11 @@ static inline int xfs_initialize_rtgroups(struct xfs_mount *mp, # define xfs_rtgroup_unlock(rtg, gf) ((void)0) # define xfs_rtgroup_trans_join(tp, rtg, gf) ((void)0) # define xfs_update_rtsb(bp, sb_bp) ((void)0) -# define xfs_log_rtsb(tp, sb_bp) (NULL) +static inline struct xfs_buf *xfs_log_rtsb(struct xfs_trans *tp, + const struct xfs_buf *sb_bp) +{ + return NULL; +} # define xfs_rtgroup_get_geometry(rtg, rgeo) (-EOPNOTSUPP) #endif /* CONFIG_XFS_RT */ diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index 75f2a021ee6d..f0341adbb879 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -1470,36 +1470,33 @@ xfs_sync_sb_buf( bool update_rtsb) { struct xfs_trans *tp; - struct xfs_buf *bp; - struct xfs_buf *rtsb_bp = NULL; int error; error = xfs_trans_alloc(mp, &M_RES(mp)->tr_sb, 0, 0, 0, &tp); if (error) return error; - bp = xfs_trans_getsb(tp); xfs_log_sb(tp); - xfs_trans_bhold(tp, bp); - if (update_rtsb) { - rtsb_bp = xfs_log_rtsb(tp, bp); - if (rtsb_bp) - xfs_trans_bhold(tp, rtsb_bp); - } + if (update_rtsb) + xfs_log_rtsb(tp, xfs_trans_getsb(tp)); xfs_trans_set_sync(tp); error = xfs_trans_commit(tp); if (error) - goto out; - /* - * write out the sb buffer to get the changes to disk - */ - error = xfs_bwrite(bp); - if (!error && rtsb_bp) - error = xfs_bwrite(rtsb_bp); -out: - if (rtsb_bp) - xfs_buf_relse(rtsb_bp); - xfs_buf_relse(bp); + return error; + + /* Re-acquire and write the sb and rtsb to disk. */ + xfs_buf_lock(mp->m_sb_bp); + error = xfs_bwrite(mp->m_sb_bp); + xfs_buf_unlock(mp->m_sb_bp); + if (error) + return error; + + if (update_rtsb && mp->m_rtsb_bp) { + xfs_buf_lock(mp->m_rtsb_bp); + error = xfs_bwrite(mp->m_rtsb_bp); + xfs_buf_unlock(mp->m_rtsb_bp); + } + return error; } diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 74a6089abadf..8b6119776fb3 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -20,6 +20,7 @@ #include "xfs_errortag.h" #include "xfs_error.h" #include "xfs_icache.h" +#include "xfs_ioend.h" #include "xfs_zone_alloc.h" #include "xfs_rtgroup.h" #include <linux/bio-integrity.h> @@ -37,15 +38,6 @@ XFS_WPC(struct iomap_writepage_ctx *ctx) } /* - * Fast and loose check if this write could update the on-disk inode size. - */ -static inline bool xfs_ioend_is_append(struct iomap_ioend *ioend) -{ - return ioend->io_offset + ioend->io_size > - XFS_I(ioend->io_inode)->i_disk_size; -} - -/* * Update on-disk file size now that data has been written to disk. */ int @@ -80,175 +72,6 @@ xfs_setfilesize( return xfs_trans_commit(tp); } -static void -xfs_ioend_put_open_zones( - struct iomap_ioend *ioend) -{ - struct iomap_ioend *tmp; - - /* - * Put the open zone for all ioends merged into this one (if any). - */ - list_for_each_entry(tmp, &ioend->io_list, io_list) - xfs_open_zone_put(tmp->io_private); - - /* - * The main ioend might not have an open zone if the submission failed - * before xfs_zone_alloc_and_submit got called. - */ - if (ioend->io_private) - xfs_open_zone_put(ioend->io_private); -} - -/* - * IO write completion. - */ -STATIC void -xfs_end_ioend_write( - struct iomap_ioend *ioend) -{ - struct xfs_inode *ip = XFS_I(ioend->io_inode); - struct xfs_mount *mp = ip->i_mount; - bool is_zoned = xfs_is_zoned_inode(ip); - xfs_off_t offset = ioend->io_offset; - size_t size = ioend->io_size; - unsigned int nofs_flag; - int error; - - /* - * We can allocate memory here while doing writeback on behalf of - * memory reclaim. To avoid memory allocation deadlocks set the - * task-wide nofs context for the following operations. - */ - nofs_flag = memalloc_nofs_save(); - - /* - * Just clean up the in-memory structures if the fs has been shut down. - */ - if (xfs_is_shutdown(mp)) { - error = -EIO; - goto done; - } - - /* - * Clean up all COW blocks and underlying data fork delalloc blocks on - * I/O error. The delalloc punch is required because this ioend was - * mapped to blocks in the COW fork and the associated pages are no - * longer dirty. If we don't remove delalloc blocks here, they become - * stale and can corrupt free space accounting on unmount. - */ - error = blk_status_to_errno(ioend->io_bio.bi_status); - if (unlikely(error)) { - /* - * Zoned writes update the in-core open zone accounting before - * I/O submission. A failed write leaves that state - * inconsistent, so shut down the filesystem instead of letting - * later writers wait forever for open zone space to become - * available. - */ - if (is_zoned) { - xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR); - goto done; - } - if (ioend->io_flags & IOMAP_IOEND_SHARED) { - ASSERT(!is_zoned); - xfs_reflink_cancel_cow_range(ip, offset, size, true); - xfs_bmap_punch_delalloc_range(ip, XFS_DATA_FORK, offset, - offset + size, NULL); - } - goto done; - } - - /* - * Success: commit the COW or unwritten blocks if needed. - */ - if (is_zoned) - error = xfs_zoned_end_io(ip, offset, size, ioend->io_sector, - ioend->io_private, NULLFSBLOCK); - else if (ioend->io_flags & IOMAP_IOEND_SHARED) - error = xfs_reflink_end_cow(ip, offset, size); - else if (ioend->io_flags & IOMAP_IOEND_UNWRITTEN) - error = xfs_iomap_write_unwritten(ip, offset, size, false); - - if (!error && - !(ioend->io_flags & IOMAP_IOEND_DIRECT) && - xfs_ioend_is_append(ioend)) - error = xfs_setfilesize(ip, offset, size); -done: - if (is_zoned) - xfs_ioend_put_open_zones(ioend); - iomap_finish_ioends(ioend, error); - memalloc_nofs_restore(nofs_flag); -} - -/* - * Finish all pending IO completions that require transactional modifications. - * - * We try to merge physical and logically contiguous ioends before completion to - * minimise the number of transactions we need to perform during IO completion. - * Both unwritten extent conversion and COW remapping need to iterate and modify - * one physical extent at a time, so we gain nothing by merging physically - * discontiguous extents here. - * - * The ioend chain length that we can be processing here is largely unbound in - * length and we may have to perform significant amounts of work on each ioend - * to complete it. Hence we have to be careful about holding the CPU for too - * long in this loop. - */ -void -xfs_end_io( - struct work_struct *work) -{ - struct xfs_inode *ip = - container_of(work, struct xfs_inode, i_ioend_work); - struct iomap_ioend *ioend; - struct list_head tmp; - unsigned long flags; - - spin_lock_irqsave(&ip->i_ioend_lock, flags); - list_replace_init(&ip->i_ioend_list, &tmp); - spin_unlock_irqrestore(&ip->i_ioend_lock, flags); - - iomap_sort_ioends(&tmp); - while ((ioend = list_first_entry_or_null(&tmp, struct iomap_ioend, - io_list))) { - list_del_init(&ioend->io_list); - iomap_ioend_try_merge(ioend, &tmp); - if (bio_op(&ioend->io_bio) == REQ_OP_READ) - iomap_finish_ioends(ioend, - blk_status_to_errno(ioend->io_bio.bi_status)); - else - xfs_end_ioend_write(ioend); - cond_resched(); - } -} - -void -xfs_end_bio( - struct bio *bio) -{ - struct iomap_ioend *ioend = iomap_ioend_from_bio(bio); - struct xfs_inode *ip = XFS_I(ioend->io_inode); - struct xfs_mount *mp = ip->i_mount; - unsigned long flags; - - /* - * For Appends record the actually written block number and set the - * boundary flag if needed. - */ - if (IS_ENABLED(CONFIG_XFS_RT) && bio_is_zone_append(bio)) { - ioend->io_sector = bio->bi_iter.bi_sector; - xfs_mark_rtg_boundary(ioend); - } - - spin_lock_irqsave(&ip->i_ioend_lock, flags); - if (list_empty(&ip->i_ioend_list)) - WARN_ON_ONCE(!queue_work(mp->m_unwritten_workqueue, - &ip->i_ioend_work)); - list_add_tail(&ioend->io_list, &ip->i_ioend_list); - spin_unlock_irqrestore(&ip->i_ioend_lock, flags); -} - /* * We cannot cancel the ioend directly on error. We may have already set other * pages under writeback and hence we have to run I/O completion to mark the @@ -631,13 +454,8 @@ xfs_zoned_map_blocks( XFS_BMAPI_REMAP); xfs_iunlock(ip, XFS_ILOCK_EXCL); - wpc->iomap.type = IOMAP_MAPPED; - wpc->iomap.flags = IOMAP_F_DIRTY; - wpc->iomap.bdev = mp->m_rtdev_targp->bt_bdev; - wpc->iomap.offset = offset; - wpc->iomap.length = XFS_FSB_TO_B(mp, count_fsb); - wpc->iomap.flags = IOMAP_F_ANON_WRITE; - + xfs_iomap_set_anon_write(ip, &wpc->iomap, offset, + XFS_FSB_TO_B(mp, count_fsb)); trace_xfs_zoned_map_blocks(ip, offset, wpc->iomap.length); return 0; } diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h index 5a7a0f1a0b49..d5ae5c9d4c26 100644 --- a/fs/xfs/xfs_aops.h +++ b/fs/xfs/xfs_aops.h @@ -10,6 +10,5 @@ extern const struct address_space_operations xfs_address_space_operations; extern const struct address_space_operations xfs_dax_aops; int xfs_setfilesize(struct xfs_inode *ip, xfs_off_t offset, size_t size); -void xfs_end_bio(struct bio *bio); #endif /* __XFS_AOPS_H__ */ diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 7bff07e31cbd..426a67b813a7 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -25,7 +25,7 @@ #include "xfs_iomap.h" #include "xfs_reflink.h" #include "xfs_file.h" -#include "xfs_aops.h" +#include "xfs_ioend.h" #include "xfs_zone_alloc.h" #include "xfs_error.h" #include "xfs_errortag.h" diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c index b6a3bc9f143c..041bb2105ec6 100644 --- a/fs/xfs/xfs_fsmap.c +++ b/fs/xfs/xfs_fsmap.c @@ -1174,8 +1174,7 @@ xfs_getfsmap( if (!xfs_getfsmap_check_keys(&head->fmh_keys[0], &head->fmh_keys[1])) return -EINVAL; - use_rmap = xfs_has_rmapbt(mp) && - has_capability_noaudit(current, CAP_SYS_ADMIN); + use_rmap = xfs_has_rmapbt(mp) && capable_noaudit(CAP_SYS_ADMIN); head->fmh_entries = 0; /* Set up our device handlers. */ diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 9d8dd30bd927..a857b8aa255c 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -82,24 +82,20 @@ static inline xa_mark_t ici_tag_to_mark(unsigned int tag) /* * Allocate and initialise an xfs_inode. + * + * This can happen in context of already dirtied transactions, so the memory + * allocations must not fail. */ struct xfs_inode * xfs_inode_alloc( struct xfs_mount *mp, xfs_ino_t ino) { + gfp_t gfp = GFP_KERNEL | __GFP_NOFAIL; struct xfs_inode *ip; - /* - * XXX: If this didn't occur in transactions, we could drop GFP_NOFAIL - * and return NULL here on ENOMEM. - */ - ip = alloc_inode_sb(mp->m_super, xfs_inode_cache, GFP_KERNEL | __GFP_NOFAIL); - - if (inode_init_always(mp->m_super, VFS_I(ip))) { - kmem_cache_free(xfs_inode_cache, ip); - return NULL; - } + ip = alloc_inode_sb(mp->m_super, xfs_inode_cache, gfp); + inode_init_always_gfp(mp->m_super, VFS_I(ip), gfp); VFS_I(ip)->i_ino = ino; /* VFS doesn't initialise i_mode! */ diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 1b53701bebea..96ca3e480cb9 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -647,7 +647,7 @@ xfs_ioctl_setattr_get_trans( goto out_error; error = xfs_trans_alloc_ichange(ip, NULL, NULL, pdqp, - has_capability_noaudit(current, CAP_FOWNER), &tp); + capable_noaudit(CAP_FOWNER), &tp); if (error) goto out_error; diff --git a/fs/xfs/xfs_ioend.c b/fs/xfs/xfs_ioend.c new file mode 100644 index 000000000000..40695d18dac0 --- /dev/null +++ b/fs/xfs/xfs_ioend.c @@ -0,0 +1,184 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2016-2025 Christoph Hellwig. + * All Rights Reserved. + */ +#include "xfs_platform.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_inode.h" +#include "xfs_iomap.h" +#include "xfs_trace.h" +#include "xfs_bmap_util.h" +#include "xfs_reflink.h" +#include "xfs_zone_alloc.h" +#include "xfs_ioend.h" + +static void +xfs_ioend_put_open_zones( + struct iomap_ioend *ioend) +{ + struct iomap_ioend *tmp; + + /* + * Put the open zone for all ioends merged into this one (if any). + */ + list_for_each_entry(tmp, &ioend->io_list, io_list) + xfs_open_zone_put(tmp->io_private); + + /* + * The main ioend might not have an open zone if the submission failed + * before xfs_zone_alloc_and_submit got called. + */ + if (ioend->io_private) + xfs_open_zone_put(ioend->io_private); +} + +static void +xfs_end_ioend_write( + struct iomap_ioend *ioend) +{ + struct xfs_inode *ip = XFS_I(ioend->io_inode); + struct xfs_mount *mp = ip->i_mount; + bool is_zoned = xfs_is_zoned_inode(ip); + xfs_off_t offset = ioend->io_offset; + size_t size = ioend->io_size; + unsigned int nofs_flag; + int error; + + /* + * We can allocate memory here while doing writeback on behalf of + * memory reclaim. To avoid memory allocation deadlocks set the + * task-wide nofs context for the following operations. + */ + nofs_flag = memalloc_nofs_save(); + + /* + * Just clean up the in-memory structures if the fs has been shut down. + */ + if (xfs_is_shutdown(mp)) { + error = -EIO; + goto done; + } + + /* + * Clean up all COW blocks and underlying data fork delalloc blocks on + * I/O error. The delalloc punch is required because this ioend was + * mapped to blocks in the COW fork and the associated pages are no + * longer dirty. If we don't remove delalloc blocks here, they become + * stale and can corrupt free space accounting on unmount. + */ + error = blk_status_to_errno(ioend->io_bio.bi_status); + if (unlikely(error)) { + /* + * Zoned writes update the in-core open zone accounting before + * I/O submission. A failed write leaves that state + * inconsistent, so shut down the filesystem instead of letting + * later writers wait forever for open zone space to become + * available. + */ + if (is_zoned) { + xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR); + goto done; + } + if (ioend->io_flags & IOMAP_IOEND_SHARED) { + ASSERT(!is_zoned); + xfs_reflink_cancel_cow_range(ip, offset, size, true); + xfs_bmap_punch_delalloc_range(ip, XFS_DATA_FORK, offset, + offset + size, NULL); + } + goto done; + } + + /* + * Success: commit the COW or unwritten blocks if needed. + */ + if (is_zoned) + error = xfs_zoned_end_io(ip, offset, size, ioend->io_sector, + ioend->io_private, NULLFSBLOCK); + else if (ioend->io_flags & IOMAP_IOEND_SHARED) + error = xfs_reflink_end_cow(ip, offset, size); + else if (ioend->io_flags & IOMAP_IOEND_UNWRITTEN) + error = xfs_iomap_write_unwritten(ip, offset, size, false); + + if (!error && + !(ioend->io_flags & IOMAP_IOEND_DIRECT) && + xfs_ioend_is_append(ioend)) + error = xfs_setfilesize(ip, offset, size); +done: + if (is_zoned) + xfs_ioend_put_open_zones(ioend); + iomap_finish_ioends(ioend, error); + memalloc_nofs_restore(nofs_flag); +} + +/* + * Finish all pending IO completions that require transactional modifications. + * + * We try to merge physical and logically contiguous ioends before completion to + * minimise the number of transactions we need to perform during IO completion. + * Both unwritten extent conversion and COW remapping need to iterate and modify + * one physical extent at a time, so we gain nothing by merging physically + * discontiguous extents here. + * + * The ioend chain length that we can be processing here is largely unbound in + * length and we may have to perform significant amounts of work on each ioend + * to complete it. Hence we have to be careful about holding the CPU for too + * long in this loop. + */ +void +xfs_end_io( + struct work_struct *work) +{ + struct xfs_inode *ip = + container_of(work, struct xfs_inode, i_ioend_work); + struct iomap_ioend *ioend; + struct list_head tmp; + unsigned long flags; + + spin_lock_irqsave(&ip->i_ioend_lock, flags); + list_replace_init(&ip->i_ioend_list, &tmp); + spin_unlock_irqrestore(&ip->i_ioend_lock, flags); + + iomap_sort_ioends(&tmp); + while ((ioend = list_first_entry_or_null(&tmp, struct iomap_ioend, + io_list))) { + list_del_init(&ioend->io_list); + iomap_ioend_try_merge(ioend, &tmp); + if (bio_op(&ioend->io_bio) == REQ_OP_READ) + iomap_finish_ioends(ioend, + blk_status_to_errno(ioend->io_bio.bi_status)); + else + xfs_end_ioend_write(ioend); + cond_resched(); + } +} + +void +xfs_end_bio( + struct bio *bio) +{ + struct iomap_ioend *ioend = iomap_ioend_from_bio(bio); + struct xfs_inode *ip = XFS_I(ioend->io_inode); + struct xfs_mount *mp = ip->i_mount; + unsigned long flags; + + /* + * For Appends record the actually written block number and set the + * boundary flag if needed. + */ + if (IS_ENABLED(CONFIG_XFS_RT) && bio_is_zone_append(bio)) { + ioend->io_sector = bio->bi_iter.bi_sector; + xfs_mark_rtg_boundary(ioend); + } + + spin_lock_irqsave(&ip->i_ioend_lock, flags); + if (list_empty(&ip->i_ioend_list)) + WARN_ON_ONCE(!queue_work(mp->m_unwritten_workqueue, + &ip->i_ioend_work)); + list_add_tail(&ioend->io_list, &ip->i_ioend_list); + spin_unlock_irqrestore(&ip->i_ioend_lock, flags); +} diff --git a/fs/xfs/xfs_ioend.h b/fs/xfs/xfs_ioend.h new file mode 100644 index 000000000000..525865767fca --- /dev/null +++ b/fs/xfs/xfs_ioend.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __XFS_IOEND_H +#define __XFS_IOEND_H + +/* + * Fast and loose check if this write could update the on-disk inode size. + */ +static inline bool xfs_ioend_is_append(struct iomap_ioend *ioend) +{ + return ioend->io_offset + ioend->io_size > + XFS_I(ioend->io_inode)->i_disk_size; +} + +void xfs_end_bio(struct bio *bio); + +#endif /* __XFS_IOEND_H */ diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 71c45be8c652..7c6238fed61e 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1083,12 +1083,7 @@ xfs_zoned_direct_write_iomap_begin( return error; } - iomap->type = IOMAP_MAPPED; - iomap->flags = IOMAP_F_DIRTY; - iomap->bdev = ip->i_mount->m_rtdev_targp->bt_bdev; - iomap->offset = offset; - iomap->length = length; - iomap->flags = IOMAP_F_ANON_WRITE; + xfs_iomap_set_anon_write(ip, iomap, offset, length); return 0; } diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h index cffcec532ea6..c906c62d46f3 100644 --- a/fs/xfs/xfs_iomap.h +++ b/fs/xfs/xfs_iomap.h @@ -29,6 +29,20 @@ int xfs_zero_range(struct xfs_inode *ip, loff_t pos, loff_t len, int xfs_truncate_page(struct xfs_inode *ip, loff_t pos, struct xfs_zone_alloc_ctx *ac, bool *did_zero); +static inline void +xfs_iomap_set_anon_write( + struct xfs_inode *ip, + struct iomap *iomap, + loff_t offset, + loff_t length) +{ + iomap->type = IOMAP_MAPPED; + iomap->bdev = ip->i_mount->m_rtdev_targp->bt_bdev; + iomap->offset = offset; + iomap->length = length; + iomap->flags = IOMAP_F_ANON_WRITE | IOMAP_F_DIRTY; +} + static inline xfs_filblks_t xfs_aligned_fsb_count( xfs_fileoff_t offset_fsb, diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 4a3299abf774..d1306e723899 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -834,7 +834,7 @@ xfs_setattr_nonsize( } error = xfs_trans_alloc_ichange(ip, udqp, gdqp, NULL, - has_capability_noaudit(current, CAP_FOWNER), &tp); + capable_noaudit(CAP_FOWNER), &tp); if (error) goto out_dqrele; diff --git a/fs/xfs/xfs_platform.h b/fs/xfs/xfs_platform.h index 59a33c60e0ca..5d542e95fe44 100644 --- a/fs/xfs/xfs_platform.h +++ b/fs/xfs/xfs_platform.h @@ -289,15 +289,4 @@ int xfs_rw_bdev(struct block_device *bdev, sector_t sector, unsigned int count, # define PTR_FMT "%p" #endif -/* - * Helper for IO routines to grab backing pages from allocated kernel memory. - */ -static inline struct page * -kmem_to_page(void *addr) -{ - if (is_vmalloc_addr(addr)) - return vmalloc_to_page(addr); - return virt_to_page(addr); -} - #endif /* _XFS_PLATFORM_H */ diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 4b2eeb7783f7..b24db75eaedc 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -445,7 +445,7 @@ xfs_shutdown_devices( blkdev_issue_flush(mp->m_logdev_targp->bt_bdev); invalidate_bdev(mp->m_logdev_targp->bt_bdev); } - if (mp->m_rtdev_targp) { + if (mp->m_rtdev_targp && mp->m_rtdev_targp != mp->m_ddev_targp) { blkdev_issue_flush(mp->m_rtdev_targp->bt_bdev); invalidate_bdev(mp->m_rtdev_targp->bt_bdev); } diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c index 1e025848811a..a5d25b703dfc 100644 --- a/fs/xfs/xfs_trans_buf.c +++ b/fs/xfs/xfs_trans_buf.c @@ -521,7 +521,8 @@ xfs_trans_log_buf( { struct xfs_buf_log_item *bip = bp->b_log_item; - ASSERT(first <= last && last < BBTOB(bp->b_length)); + ASSERT(first <= last); + ASSERT(last < BBTOB(bp->b_length)); ASSERT(!(bip->bli_flags & XFS_BLI_ORDERED)); xfs_trans_dirty_buf(tp, bp); diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c index 7d13fa7ab30a..bdbb60cc5d5b 100644 --- a/fs/xfs/xfs_zone_alloc.c +++ b/fs/xfs/xfs_zone_alloc.c @@ -793,17 +793,35 @@ xfs_get_cached_zone( rcu_read_lock(); oz = VFS_I(ip)->i_private; - if (oz) { - /* - * GC only steals open zones at mount time, so no GC zones - * should end up in the cache. - */ - ASSERT(!oz->oz_is_gc); - if (!atomic_inc_not_zero(&oz->oz_ref)) + if (!oz) + goto out_unlock; + + /* + * GC only steals open zones at mount time, so no GC zones should end up + * in the cache. + */ + ASSERT(!oz->oz_is_gc); + + /* + * Drop the old cached open zone if it is full. + */ + if (oz->oz_allocated == rtg_blocks(oz->oz_rtg)) { + spin_lock(&ip->i_flags_lock); + oz = VFS_I(ip)->i_private; + if (oz && oz->oz_allocated == rtg_blocks(oz->oz_rtg)) { + VFS_I(ip)->i_private = NULL; + spin_unlock(&ip->i_flags_lock); + xfs_open_zone_put(oz); oz = NULL; + goto out_unlock; + } + spin_unlock(&ip->i_flags_lock); } - rcu_read_unlock(); + if (!atomic_inc_not_zero(&oz->oz_ref)) + oz = NULL; +out_unlock: + rcu_read_unlock(); return oz; } @@ -818,18 +836,41 @@ xfs_get_cached_zone( * that were every written to, but significantly simplifies the cached zone * lookup. Because the open_zone is clearly marked as full when all data * in the underlying RTG was written, the caching is always safe. + * + * Called with a reference on @oz held. And returns two references on the + * returned zone: one for the caller and one for pinning the zone in + * inode->i_private. */ -static void +static struct xfs_open_zone * xfs_set_cached_zone( struct xfs_inode *ip, struct xfs_open_zone *oz) { struct xfs_open_zone *old_oz; + /* + * If the open zone cached in the inode still has free space, use that + * instead of the new open zone just selected. This can happen when + * multiple threads race to perform zone selection for an inode. + * io_uring worker threads seem to be good way to trigger this. + * + * We need to grab an extra reference to this open zone as the caller + * owns a reference in addition to the i_private pointer. + */ + spin_lock(&ip->i_flags_lock); + old_oz = VFS_I(ip)->i_private; + if (old_oz && old_oz->oz_allocated < rtg_blocks(old_oz->oz_rtg) && + atomic_inc_not_zero(&old_oz->oz_ref)) { + spin_unlock(&ip->i_flags_lock); + xfs_open_zone_put(oz); + return old_oz; + } + VFS_I(ip)->i_private = oz; atomic_inc(&oz->oz_ref); - old_oz = xchg(&VFS_I(ip)->i_private, oz); + spin_unlock(&ip->i_flags_lock); if (old_oz) xfs_open_zone_put(old_oz); + return oz; } static void @@ -873,14 +914,13 @@ xfs_zone_alloc_and_submit( * the inode is still associated with a zone and use that if so. */ if (!*oz) +select_zone: *oz = xfs_get_cached_zone(ip); - if (!*oz) { -select_zone: *oz = xfs_select_zone(mp, write_hint, pack_tight); if (!*oz) goto out_error; - xfs_set_cached_zone(ip, *oz); + *oz = xfs_set_cached_zone(ip, *oz); } alloc_len = xfs_zone_alloc_blocks(*oz, XFS_B_TO_FSB(mp, ioend->io_size), diff --git a/fs/xfs/xfs_zone_gc.c b/fs/xfs/xfs_zone_gc.c index d0b85179a3d2..5fdcf98a2133 100644 --- a/fs/xfs/xfs_zone_gc.c +++ b/fs/xfs/xfs_zone_gc.c @@ -869,6 +869,11 @@ xfs_zone_gc_write_chunk( WRITE_ONCE(chunk->state, XFS_GC_BIO_NEW); list_move_tail(&chunk->entry, &data->writing); + /* + * If we run on top of stacked block device, the read I/O might have + * reset bi_bdev, restore it to the one we want. + */ + bio_set_dev(&chunk->bio, mp->m_rtdev_targp->bt_bdev); bio_reuse(&chunk->bio, REQ_OP_WRITE); while ((split_chunk = xfs_zone_gc_split_write(data, chunk))) xfs_zone_gc_submit_write(data, split_chunk); diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 1a45e0d521d8..a10a591c18b2 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -202,12 +202,8 @@ struct acpi_device_dir { /* Plug and Play */ -#define MAX_ACPI_DEVICE_NAME_LEN 40 -#define MAX_ACPI_CLASS_NAME_LEN 20 typedef char acpi_bus_id[8]; typedef u64 acpi_bus_address; -typedef char acpi_device_name[MAX_ACPI_DEVICE_NAME_LEN]; -typedef char acpi_device_class[MAX_ACPI_CLASS_NAME_LEN]; struct acpi_hardware_id { struct list_head list; @@ -229,16 +225,12 @@ struct acpi_device_pnp { acpi_bus_address bus_address; /* _ADR */ char *unique_id; /* _UID */ struct list_head ids; /* _HID and _CIDs */ - acpi_device_name device_name; /* Driver-determined */ - acpi_device_class device_class; /* " */ }; #define acpi_device_bid(d) ((d)->pnp.bus_id) #define acpi_device_adr(d) ((d)->pnp.bus_address) const char *acpi_device_hid(struct acpi_device *device); #define acpi_device_uid(d) ((d)->pnp.unique_id) -#define acpi_device_name(d) ((d)->pnp.device_name) -#define acpi_device_class(d) ((d)->pnp.device_class) /* Power Management */ @@ -578,6 +570,9 @@ int acpi_dev_for_each_child_reverse(struct acpi_device *adev, * ------ */ +#define MAX_ACPI_CLASS_NAME_LEN 20 +typedef char acpi_device_class[MAX_ACPI_CLASS_NAME_LEN]; + struct acpi_bus_event { struct list_head node; acpi_device_class device_class; diff --git a/include/drm/drm_pagemap.h b/include/drm/drm_pagemap.h index 95eb4b66b057..ebbd3b0ddf36 100644 --- a/include/drm/drm_pagemap.h +++ b/include/drm/drm_pagemap.h @@ -2,6 +2,7 @@ #ifndef _DRM_PAGEMAP_H_ #define _DRM_PAGEMAP_H_ +#include <linux/bits.h> #include <linux/dma-direction.h> #include <linux/hmm.h> #include <linux/memremap.h> @@ -339,6 +340,9 @@ struct drm_pagemap_migrate_details { #if IS_ENABLED(CONFIG_ZONE_DEVICE) +#define DRM_PAGEMAP_ZDD_FLAG_MIGRATED BIT(0) +#define DRM_PAGEMAP_ZDD_FLAG_MASK DRM_PAGEMAP_ZDD_FLAG_MIGRATED + int drm_pagemap_migrate_to_devmem(struct drm_pagemap_devmem *devmem_allocation, struct mm_struct *mm, unsigned long start, unsigned long end, @@ -373,7 +377,9 @@ static inline struct drm_pagemap_zdd *drm_pagemap_page_zone_device_data(struct p { struct folio *folio = page_folio(page); - return folio_zone_device_data(folio); + return (struct drm_pagemap_zdd *) + ((unsigned long)folio_zone_device_data(folio) & + ~DRM_PAGEMAP_ZDD_FLAG_MASK); } #else diff --git a/include/linux/capability.h b/include/linux/capability.h index 37db92b3d6f8..f8532d92fcad 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -145,6 +145,7 @@ extern bool has_capability_noaudit(struct task_struct *t, int cap); extern bool has_ns_capability_noaudit(struct task_struct *t, struct user_namespace *ns, int cap); extern bool capable(int cap); +bool capable_noaudit(int cap); extern bool ns_capable(struct user_namespace *ns, int cap); extern bool ns_capable_noaudit(struct user_namespace *ns, int cap); extern bool ns_capable_setid(struct user_namespace *ns, int cap); @@ -167,6 +168,10 @@ static inline bool capable(int cap) { return true; } +static inline bool capable_noaudit(int cap) +{ + return true; +} static inline bool ns_capable(struct user_namespace *ns, int cap) { return true; diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 7a631a257613..3754d697854b 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -527,7 +527,10 @@ struct cgroup { int nr_threaded_children; /* # of live threaded child cgroups */ - /* sequence number for cgroup.kill, serialized by css_set_lock. */ + /* + * Sequence number for cgroup.kill. Incremented with both cgroup_mutex + * and css_set_lock held. Readers hold either one. + */ unsigned int kill_seq; struct kernfs_node *kn; /* cgroup kernfs entry */ diff --git a/include/linux/device-id/ap.h b/include/linux/device-id/ap.h index 0992333a34db..e050abebbf3d 100644 --- a/include/linux/device-id/ap.h +++ b/include/linux/device-id/ap.h @@ -4,7 +4,6 @@ #ifdef __KERNEL__ #include <linux/types.h> -typedef unsigned long kernel_ulong_t; #endif #define AP_DEVICE_ID_MATCH_CARD_TYPE 0x01 @@ -14,7 +13,6 @@ typedef unsigned long kernel_ulong_t; struct ap_device_id { __u16 match_flags; /* which fields to match against */ __u8 dev_type; /* device type */ - kernel_ulong_t driver_info; }; #endif /* ifndef LINUX_DEVICE_ID_AP_H */ diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index d1203da56fc5..d15b2b31d3c9 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -567,6 +567,7 @@ void dma_buf_unpin(struct dma_buf_attachment *attach); struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info); int dma_buf_fd(struct dma_buf *dmabuf, int flags); +void dma_buf_fd_install(struct dma_buf *dmabuf, int fd); struct dma_buf *dma_buf_get(int fd); void dma_buf_put(struct dma_buf *dmabuf); diff --git a/include/linux/dma-fence-array.h b/include/linux/dma-fence-array.h index 1b1d87579c38..0c49d7ccefb6 100644 --- a/include/linux/dma-fence-array.h +++ b/include/linux/dma-fence-array.h @@ -28,7 +28,6 @@ struct dma_fence_array_cb { /** * struct dma_fence_array - fence to represent an array of fences * @base: fence base class - * @lock: spinlock for fence handling * @num_fences: number of fences in the array * @num_pending: fences in the array still pending * @fences: array of the fences diff --git a/include/linux/dma-fence-chain.h b/include/linux/dma-fence-chain.h index df3beadf1515..705c4394ac0d 100644 --- a/include/linux/dma-fence-chain.h +++ b/include/linux/dma-fence-chain.h @@ -20,7 +20,6 @@ * @prev: previous fence of the chain * @prev_seqno: original previous seqno before garbage collection * @fence: encapsulated fence - * @lock: spinlock for fence handling */ struct dma_fence_chain { struct dma_fence base; @@ -81,9 +80,8 @@ dma_fence_chain_contained(struct dma_fence *fence) } /** - * dma_fence_chain_alloc - * - * Returns a new struct dma_fence_chain object or NULL on failure. + * dma_fence_chain_alloc - Returns a new &struct dma_fence_chain object or + * %NULL on failure. * * This specialized allocator has to be a macro for its allocations to be * accounted separately (to have a separate alloc_tag). The typecast is @@ -93,7 +91,8 @@ dma_fence_chain_contained(struct dma_fence *fence) kmalloc_obj(struct dma_fence_chain) /** - * dma_fence_chain_free + * dma_fence_chain_free - Frees an allocated but not used + * &struct dma_fence_chain object. * @chain: chain node to free * * Frees up an allocated but not used struct dma_fence_chain object. This diff --git a/include/linux/edac.h b/include/linux/edac.h index e6b4e51130e5..f7a8218f9cc0 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -598,9 +598,6 @@ struct mem_ctl_info { int op_state; struct dentry *debugfs; - u8 fake_inject_layer[EDAC_MAX_LAYERS]; - bool fake_inject_ue; - u16 fake_inject_count; /* * Memory Controller hierarchy diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 3a2d35a9f307..a0cf0398519f 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -57,20 +57,21 @@ struct ip_mc_socklist { }; struct ip_sf_list { - struct ip_sf_list *sf_next; + struct ip_sf_list __rcu *sf_next; unsigned long sf_count[2]; /* include/exclude counts */ __be32 sf_inaddr; unsigned char sf_gsresp; /* include in g & s response? */ unsigned char sf_oldin; /* change state */ unsigned char sf_crcount; /* retrans. left to send */ + struct rcu_head rcu; }; struct ip_mc_list { struct in_device *interface; __be32 multiaddr; unsigned int sfmode; - struct ip_sf_list *sources; - struct ip_sf_list *tomb; + struct ip_sf_list __rcu *sources; + struct ip_sf_list __rcu *tomb; unsigned long sfcount[2]; union { struct ip_mc_list *next; diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 8c4f3bb24429..e6de7ae55bda 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -181,6 +181,7 @@ struct kprobe_blacklist_entry { struct list_head list; unsigned long start_addr; unsigned long end_addr; + struct rcu_head rcu; }; #ifdef CONFIG_KPROBES diff --git a/include/linux/nvme-tcp.h b/include/linux/nvme-tcp.h index e435250fcb4d..859338da8573 100644 --- a/include/linux/nvme-tcp.h +++ b/include/linux/nvme-tcp.h @@ -77,7 +77,7 @@ struct nvme_tcp_hdr { __le32 plen; }; -/** +/* * struct nvme_tcp_icreq_pdu - nvme tcp initialize connection request pdu * * @hdr: pdu generic header @@ -95,7 +95,7 @@ struct nvme_tcp_icreq_pdu { __u8 rsvd2[112]; }; -/** +/* * struct nvme_tcp_icresp_pdu - nvme tcp initialize connection response pdu * * @hdr: pdu common header @@ -113,12 +113,13 @@ struct nvme_tcp_icresp_pdu { __u8 rsvd[112]; }; -/** +/* * struct nvme_tcp_term_pdu - nvme tcp terminate connection pdu * * @hdr: pdu common header * @fes: fatal error status - * @fei: fatal error information + * @feil: fatal error information (low 16 bits) + * @feih: fatal error information (high 16 bits) */ struct nvme_tcp_term_pdu { struct nvme_tcp_hdr hdr; @@ -128,7 +129,7 @@ struct nvme_tcp_term_pdu { __u8 rsvd[10]; }; -/** +/* * struct nvme_tcp_cmd_pdu - nvme tcp command capsule pdu * * @hdr: pdu common header @@ -139,10 +140,9 @@ struct nvme_tcp_cmd_pdu { struct nvme_command cmd; }; -/** +/* * struct nvme_tcp_rsp_pdu - nvme tcp response capsule pdu * - * @hdr: pdu common header * @hdr: nvme-tcp generic header * @cqe: nvme completion queue entry */ @@ -151,7 +151,7 @@ struct nvme_tcp_rsp_pdu { struct nvme_completion cqe; }; -/** +/* * struct nvme_tcp_r2t_pdu - nvme tcp ready-to-transfer pdu * * @hdr: pdu common header @@ -169,7 +169,7 @@ struct nvme_tcp_r2t_pdu { __u8 rsvd[4]; }; -/** +/* * struct nvme_tcp_data_pdu - nvme tcp data pdu * * @hdr: pdu common header diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h index 4cc52698e214..8d7e5521f7cd 100644 --- a/include/linux/sched/user.h +++ b/include/linux/sched/user.h @@ -25,7 +25,8 @@ struct user_struct { #if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) || \ defined(CONFIG_NET) || defined(CONFIG_IO_URING) || \ - defined(CONFIG_VFIO_PCI_ZDEV_KVM) || IS_ENABLED(CONFIG_IOMMUFD) + defined(CONFIG_VFIO_PCI_ZDEV_KVM) || IS_ENABLED(CONFIG_IOMMUFD) || \ + defined(CONFIG_SECRETMEM) atomic_long_t locked_vm; #endif #ifdef CONFIG_WATCH_QUEUE diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 671c13494566..421f6fc45451 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3082,6 +3082,11 @@ static inline bool skb_transport_header_was_set(const struct sk_buff *skb) return skb->transport_header != (typeof(skb->transport_header))~0U; } +static inline void skb_unset_transport_header(struct sk_buff *skb) +{ + skb->transport_header = (typeof(skb->transport_header))~0U; +} + static inline unsigned char *skb_transport_header(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb)); diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 3357ee62d10b..5549298c1ec6 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -229,6 +229,9 @@ struct sock *vsock_find_bound_socket_net(struct sockaddr_vm *addr, struct sock *vsock_find_connected_socket_net(struct sockaddr_vm *src, struct sockaddr_vm *dst, struct net *net); +bool vsock_check_source(const struct vsock_sock *vsk, + const struct vsock_transport *transport, + const struct sockaddr_vm *src); void vsock_remove_sock(struct vsock_sock *vsk); void vsock_for_each_connected_socket(struct vsock_transport *transport, void (*fn)(struct sock *sk)); diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index 238ad3349456..795fb41b45f5 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -88,8 +88,6 @@ struct ip6_sf_socklist { struct in6_addr sl_addr[] __counted_by(sl_max); }; -#define IP6_SFBLOCK 10 /* allocate this many at once */ - struct ipv6_mc_socklist { struct in6_addr addr; int ifindex; diff --git a/include/net/ip.h b/include/net/ip.h index a8f57b4f4aa2..6f602df72ee6 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -704,7 +704,8 @@ static inline void ip_ipgre_mc_map(__be32 naddr, const unsigned char *broadcast, static __inline__ void inet_reset_saddr(struct sock *sk) { - inet_sk(sk)->inet_rcv_saddr = inet_sk(sk)->inet_saddr = 0; + inet_sk(sk)->inet_saddr = 0; + WRITE_ONCE(inet_sk(sk)->inet_rcv_saddr, 0); #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == PF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); diff --git a/include/net/tcp.h b/include/net/tcp.h index 670c20876f26..436495ff2271 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -765,8 +765,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, void tcp_send_probe0(struct sock *); int tcp_write_wakeup(struct sock *, int mib); void tcp_send_fin(struct sock *sk); -void tcp_send_active_reset(struct sock *sk, gfp_t priority, - enum sk_rst_reason reason); +void tcp_send_active_reset(struct sock *sk, enum sk_rst_reason reason); int tcp_send_synack(struct sock *); void tcp_push_one(struct sock *, unsigned int mss_now); void __tcp_send_ack(struct sock *sk, u32 rcv_nxt, u16 flags); diff --git a/include/trace/events/icmp.h b/include/trace/events/icmp.h index 09ae115099df..6937b778ae54 100644 --- a/include/trace/events/icmp.h +++ b/include/trace/events/icmp.h @@ -27,17 +27,20 @@ TRACE_EVENT(icmp_send, TP_fast_assign( struct iphdr *iph = ip_hdr(skb); - struct udphdr *uh = udp_hdr(skb); - int proto_4 = iph->protocol; + struct udphdr _uh, *uh = NULL; __be32 *p32; __entry->skbaddr = skb; __entry->type = type; __entry->code = code; - if (proto_4 != IPPROTO_UDP || (u8 *)uh < skb->head || - (u8 *)uh + sizeof(struct udphdr) - > skb_tail_pointer(skb)) { + if (iph->protocol == IPPROTO_UDP) + uh = skb_header_pointer(skb, + skb_network_offset(skb) + + (iph->ihl << 2), + sizeof(_uh), &_uh); + + if (!uh) { __entry->sport = 0; __entry->dport = 0; __entry->ulen = 0; diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index b32c72a662b6..42a5fa8ad6b0 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -1512,6 +1512,7 @@ struct drm_amdgpu_info_device { __u64 high_va_max; /* gfx10 pa_sc_tile_steering_override */ __u32 pa_sc_tile_steering_override; + __u32 pad; /* disabled TCCs */ __u64 tcc_disabled_mask; __u64 min_engine_clock; @@ -1536,7 +1537,6 @@ struct drm_amdgpu_info_device { __u32 csa_alignment; /* Userq IP mask (1 << AMDGPU_HW_IP_*) */ __u32 userq_ip_mask; - __u32 pad; }; struct drm_amdgpu_info_hw_ip { diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index fd5f0e95648e..66a91c8b1cb9 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -8,6 +8,7 @@ #define AUTOFS_SUPER_MAGIC 0x0187 #define CEPH_SUPER_MAGIC 0x00c36400 #define CODA_SUPER_MAGIC 0x73757245 +#define CONFIGFS_MAGIC 0x62656570 /* some random number */ #define CRAMFS_MAGIC 0x28cd3d45 /* some random number */ #define CRAMFS_MAGIC_WEND 0x453dcd28 /* magic number with the wrong endianess */ #define DEBUGFS_MAGIC 0x64626720 diff --git a/kernel/capability.c b/kernel/capability.c index 829f49ae07b9..90e6ab62f6db 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -326,7 +326,6 @@ bool has_capability_noaudit(struct task_struct *t, int cap) { return has_ns_capability_noaudit(t, &init_user_ns, cap); } -EXPORT_SYMBOL(has_capability_noaudit); static bool ns_capable_common(struct user_namespace *ns, int cap, @@ -416,6 +415,24 @@ bool capable(int cap) return ns_capable(&init_user_ns, cap); } EXPORT_SYMBOL(capable); + +/** + * capable_noaudit - Determine if the current task has a superior + * capability in effect by checking the process's effective + * capabilities (unaudited). + * @cap: The capability to be tested for + * + * This is the same as capable(), except it uses CAP_OPT_NOAUDIT as to prevent + * issuing spurious audit messages. + * + * This sets PF_SUPERPRIV on the task if the capability is available on the + * assumption that it's about to be used. + */ +bool capable_noaudit(int cap) +{ + return ns_capable_noaudit(&init_user_ns, cap); +} +EXPORT_SYMBOL(capable_noaudit); #endif /* CONFIG_MULTIUSER */ /** diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index c3a12fee7528..2d532bf2c0c7 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -6873,10 +6873,7 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs) spin_lock_irq(&css_set_lock); cset = task_css_set(current); get_css_set(cset); - if (kargs->cgrp) - kargs->kill_seq = kargs->cgrp->kill_seq; - else - kargs->kill_seq = cset->dfl_cgrp->kill_seq; + kargs->kill_seq = cset->dfl_cgrp->kill_seq; spin_unlock_irq(&css_set_lock); if (!(kargs->flags & CLONE_INTO_CGROUP)) { @@ -6940,6 +6937,7 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs) put_css_set(cset); kargs->cgrp = dst_cgrp; + kargs->kill_seq = dst_cgrp->kill_seq; return ret; err: diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index d100634fa12b..2538faac9aba 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1259,6 +1259,28 @@ static void reset_partition_data(struct cpuset *cs) cpumask_copy(cs->effective_cpus, parent->effective_cpus); } +/* Return true if isolated_cpus changes. */ +static bool isolated_cpu_update(int new_prs, int cpu) +{ + lockdep_assert_held(&callback_lock); + lockdep_assert_held(&cpuset_mutex); + + if (new_prs == PRS_ISOLATED) { + if (cpumask_test_cpu(cpu, isolated_cpus)) + return false; + cpumask_set_cpu(cpu, isolated_cpus); + return true; + } + + /* CPUs isolated at boot must remain isolated. */ + if (!cpumask_test_cpu(cpu, + housekeeping_cpumask(HK_TYPE_DOMAIN_BOOT)) || + !cpumask_test_cpu(cpu, isolated_cpus)) + return false; + cpumask_clear_cpu(cpu, isolated_cpus); + return true; +} + /* * isolated_cpus_update - Update the isolated_cpus mask * @old_prs: old partition_root_state @@ -1267,19 +1289,16 @@ static void reset_partition_data(struct cpuset *cs) */ static void isolated_cpus_update(int old_prs, int new_prs, struct cpumask *xcpus) { + bool updated = false; + int cpu; + WARN_ON_ONCE(old_prs == new_prs); lockdep_assert_held(&callback_lock); lockdep_assert_held(&cpuset_mutex); - if (new_prs == PRS_ISOLATED) { - if (cpumask_subset(xcpus, isolated_cpus)) - return; - cpumask_or(isolated_cpus, isolated_cpus, xcpus); - } else { - if (!cpumask_intersects(xcpus, isolated_cpus)) - return; - cpumask_andnot(isolated_cpus, isolated_cpus, xcpus); - } - update_housekeeping = true; + for_each_cpu(cpu, xcpus) + updated |= isolated_cpu_update(new_prs, cpu); + if (updated) + update_housekeeping = true; } /* diff --git a/kernel/kprobes.c b/kernel/kprobes.c index bfc89083daa9..6337da5cab9e 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1447,8 +1447,14 @@ static bool __within_kprobe_blacklist(unsigned long addr) /* * If 'kprobe_blacklist' is defined, check the address and * reject any probe registration in the prohibited area. + * Note: this can return true during transition period where + * (start_addr, end_addr) in the black list is shrinking + * but old entry has not been removed yet. This is acceptable + * because the worst case is that we reject more probes than + * we should. */ - list_for_each_entry(ent, &kprobe_blacklist, list) { + guard(rcu)(); + list_for_each_entry_rcu(ent, &kprobe_blacklist, list) { if (addr >= ent->start_addr && addr < ent->end_addr) return true; } @@ -2509,7 +2515,7 @@ int kprobe_add_ksym_blacklist(unsigned long entry) ent->start_addr = entry; ent->end_addr = entry + size; INIT_LIST_HEAD(&ent->list); - list_add_tail(&ent->list, &kprobe_blacklist); + list_add_tail_rcu(&ent->list, &kprobe_blacklist); return (int)size; } @@ -2603,8 +2609,8 @@ static void kprobe_remove_area_blacklist(unsigned long start, unsigned long end) list_for_each_entry_safe(ent, n, &kprobe_blacklist, list) { if (ent->start_addr < start || ent->start_addr >= end) continue; - list_del(&ent->list); - kfree(ent); + list_del_rcu(&ent->list); + kfree_rcu(ent, rcu); } } diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c index 10af28a9f2c0..713aa26b2828 100644 --- a/kernel/sched/ext/ext.c +++ b/kernel/sched/ext/ext.c @@ -876,9 +876,9 @@ struct task_struct *scx_task_iter_next_locked(struct scx_task_iter *iter) * unloading. The init_tasks ("swappers") should be excluded * from the iteration because: * - * - It's unsafe to use __setschduler_prio() on an init_task to - * determine the sched_class to use as it won't preserve its - * idle_sched_class. + * - It's unsafe to use __setscheduler_class() on an init_task + * to determine the sched_class to use as it won't preserve + * its idle_sched_class. * * - ops.init/exit_task() can easily be confused if called with * init_tasks as they, e.g., share PID 0. @@ -2806,6 +2806,8 @@ static void dispatch_to_local_dsq(struct scx_sched *sch, struct rq *rq, * @p: task to finish dispatching * @qseq_at_dispatch: qseq when @p started getting dispatched * @dsq_id: destination DSQ ID + * @slice: slice carried by the insert verdict, 0 keeps the current value + * @vtime: vtime carried by the insert verdict, committed on PRIQ inserts * @enq_flags: %SCX_ENQ_* * * Dispatching to local DSQs may need to wait for queueing to complete or @@ -5514,7 +5516,7 @@ static const struct kset_uevent_ops scx_uevent_ops = { }; /* - * Used by sched_fork() and __setscheduler_prio() to pick the matching + * Used by sched_fork() and __setscheduler_class() to pick the matching * sched_class. dl/rt are already handled. */ bool task_should_scx(int policy) @@ -7694,7 +7696,7 @@ static void scx_root_enable_workfn(struct kthread_work *work) /* * Enable ops for every task. Fork is excluded by scx_fork_rwsem * preventing new tasks from being added. No need to exclude tasks - * leaving as sched_ext_free() can handle both prepped and enabled + * leaving as sched_ext_dead() can handle both prepped and enabled * tasks. Prep all tasks first and then enable them with preemption * disabled. * @@ -7786,7 +7788,7 @@ static void scx_root_enable_workfn(struct kthread_work *work) /* * We're fully committed and can't fail. The task READY -> ENABLED - * transitions here are synchronized against sched_ext_free() through + * transitions here are synchronized against sched_ext_dead() through * scx_tasks_lock. */ percpu_down_write(&scx_fork_rwsem); @@ -8079,6 +8081,7 @@ static int bpf_scx_check_member(const struct btf_type *t, case offsetof(struct sched_ext_ops, cgroup_init): case offsetof(struct sched_ext_ops, cgroup_exit): case offsetof(struct sched_ext_ops, cgroup_prep_move): + case offsetof(struct sched_ext_ops, cgroup_set_bandwidth): #endif case offsetof(struct sched_ext_ops, cpu_online): case offsetof(struct sched_ext_ops, cpu_offline): @@ -9003,12 +9006,6 @@ static bool scx_dsq_move(struct bpf_iter_scx_dsq_kern *kit, if (unlikely(READ_ONCE(sch->aborting))) return false; - if (unlikely(!scx_task_on_sched(sch, p))) { - scx_error(sch, "scx_bpf_dsq_move[_vtime]() on %s[%d] but the task belongs to a different scheduler", - p->comm, p->pid); - return false; - } - /* * Can be called from either ops.dispatch() holding the dispatched rq's * lock or any context where no rq lock is held. If latter, lock @p's @@ -9040,6 +9037,17 @@ static bool scx_dsq_move(struct bpf_iter_scx_dsq_kern *kit, goto out; } + /* + * @p has been on $src_dsq and can't move anymore. If @p is not on @sch, + * the caller didn't have authority over @p at the time of the call. + */ + if (unlikely(!scx_task_on_sched(sch, p))) { + scx_error(sch, "scx_bpf_dsq_move[_vtime]() on %s[%d] but the task belongs to a different scheduler", + p->comm, p->pid); + raw_spin_unlock(&src_dsq->lock); + goto out; + } + /* @p is still on $src_dsq and stable, determine the destination */ dst_dsq = find_dsq_for_dispatch(sch, locked_rq ?: this_rq(), dsq_id, task_cpu(p)); @@ -9765,7 +9773,7 @@ __bpf_kfunc struct task_struct *bpf_iter_scx_dsq_next(struct bpf_iter_scx_dsq *i * bpf_iter_scx_dsq_destroy - Destroy a DSQ iterator * @it: iterator to destroy * - * Undo scx_iter_scx_dsq_new(). + * Undo bpf_iter_scx_dsq_new(). */ __bpf_kfunc void bpf_iter_scx_dsq_destroy(struct bpf_iter_scx_dsq *it) { @@ -11041,3 +11049,16 @@ static int __init scx_init(void) return 0; } __initcall(scx_init); + +/* + * Compatibility markers for userspace. Existence of a marker function + * represents that the kernel supports that sched-ext feature. + */ + +/* + * scx_compat_marker_cgroup_set_bandwidth_may_sleep: advertises that + * ops.cgroup_set_bandwidth() may be implemented as a sleepable callback. + */ +#ifdef CONFIG_EXT_GROUP_SCHED +DEFINE_SCX_COMPAT_MARKER(cgroup_set_bandwidth_may_sleep); +#endif /* CONFIG_EXT_GROUP_SCHED */ diff --git a/kernel/sched/ext/internal.h b/kernel/sched/ext/internal.h index 27bbf5e04d90..0967b99a4948 100644 --- a/kernel/sched/ext/internal.h +++ b/kernel/sched/ext/internal.h @@ -442,7 +442,7 @@ struct sched_ext_ops { * * Note that this callback may be called from a CPU other than the * one the task is going to run on. This can happen when a task - * property is changed (i.e., affinity), since scx_next_task_scx(), + * property is changed (i.e., affinity), since set_next_task_scx(), * which triggers this callback, may run on a CPU different from * the task's assigned CPU. * @@ -753,7 +753,7 @@ struct sched_ext_ops { * @burst_us: bandwidth control burst * * Update @cgrp's bandwidth control parameters. This is from the cpu.max - * cgroup interface. + * cgroup interface. This operation may block. * * @quota_us / @period_us determines the CPU bandwidth @cgrp is entitled * to. For example, if @period_us is 1_000_000 and @quota_us is @@ -2001,6 +2001,27 @@ struct scx_bstr_buf { char line[SCX_EXIT_MSG_LEN]; }; +/* Internal helper for DEFINE_SCX_COMPAT_MARKER(). */ +#define DECLARE_SCX_COMPAT_MARKER(func) \ + extern void scx_compat_marker_##func(void) + +/** + * DEFINE_SCX_COMPAT_MARKER() - define a userspace capability marker + * @func: marker suffix; the defined symbol is scx_compat_marker_@func + * + * Emit an empty, callerless function that is retained in the kernel's BTF. + * Its presence is part of the kernel<->userspace contract: userspace probes + * scx_compat_marker_@func (e.g. via BTF) to detect that this kernel supports + * the corresponding feature. + * + * The leading declaration suppresses the missing-prototype warning; the + * trailing declaration consumes the semicolon at the use site. + */ +#define DEFINE_SCX_COMPAT_MARKER(func) \ + DECLARE_SCX_COMPAT_MARKER(func); \ + __used __retain void scx_compat_marker_##func(void) {} \ + DECLARE_SCX_COMPAT_MARKER(func) + extern struct scx_sched __rcu *scx_root; DECLARE_PER_CPU(struct rq *, scx_locked_rq_state); diff --git a/kernel/trace/trace_btf.c b/kernel/trace/trace_btf.c index 00172f301f25..ee7a04886bf6 100644 --- a/kernel/trace/trace_btf.c +++ b/kernel/trace/trace_btf.c @@ -61,47 +61,50 @@ struct btf_anon_stack { /* * Find a member of data structure/union by name and return it. - * Return NULL if not found, or -EINVAL if parameter is invalid. - * If the member is an member of anonymous union/structure, the offset - * of that anonymous union/structure is stored into @anon_offset. Caller - * can calculate the correct offset from the root data structure by - * adding anon_offset to the member's offset. + * Return NULL if not found, or ERR_PTR(-EINVAL) if parameter is invalid. + * If the member is a member of an anonymous union/structure, the bit offset + * of that anonymous union/structure is stored into @anon_offset. + * If @member_type is non-NULL, the actual containing structure/union type + * of the found member is stored into @member_type. */ const struct btf_member *btf_find_struct_member(struct btf *btf, const struct btf_type *type, const char *member_name, - u32 *anon_offset) + u32 *anon_offset, + const struct btf_type **member_type) { struct btf_anon_stack *anon_stack; const struct btf_member *member; + const struct btf_type *mtype; u32 tid, cur_offset = 0; const char *name; int i, top = 0; + if (!btf_type_is_struct(type)) + return ERR_PTR(-EINVAL); + anon_stack = kzalloc_objs(*anon_stack, BTF_ANON_STACK_MAX); if (!anon_stack) return ERR_PTR(-ENOMEM); retry: - if (!btf_type_is_struct(type)) { - member = ERR_PTR(-EINVAL); - goto out; - } - for_each_member(i, type, member) { if (!member->name_off) { /* Anonymous union/struct: push it for later use */ - if (btf_type_skip_modifiers(btf, member->type, &tid) && + mtype = btf_type_skip_modifiers(btf, member->type, &tid); + if (mtype && btf_type_is_struct(mtype) && top < BTF_ANON_STACK_MAX) { anon_stack[top].tid = tid; - anon_stack[top++].offset = - cur_offset + member->offset; + anon_stack[top++].offset = cur_offset + + __btf_member_bit_offset(type, member); } } else { name = btf_name_by_offset(btf, member->name_off); if (name && !strcmp(member_name, name)) { if (anon_offset) *anon_offset = cur_offset; + if (member_type) + *member_type = type; goto out; } } diff --git a/kernel/trace/trace_btf.h b/kernel/trace/trace_btf.h index 4bc44bc261e6..4bd26bceae23 100644 --- a/kernel/trace/trace_btf.h +++ b/kernel/trace/trace_btf.h @@ -8,4 +8,5 @@ const struct btf_param *btf_get_func_param(const struct btf_type *func_proto, const struct btf_member *btf_find_struct_member(struct btf *btf, const struct btf_type *type, const char *member_name, - u32 *anon_offset); + u32 *anon_offset, + const struct btf_type **member_type); diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index c4163904ba74..804442b2f7d2 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -625,6 +625,7 @@ static int get_bitoffset_of_field(char **pfieldname, const struct btf_type **pty { const struct btf_type *type = *ptype; const struct btf_member *field; + const struct btf_type *mtype; struct btf *btf = ctx_btf(ctx); char *fieldname = *pfieldname; int bitoffs = 0; @@ -640,7 +641,7 @@ static int get_bitoffset_of_field(char **pfieldname, const struct btf_type **pty anon_offs = 0; field = btf_find_struct_member(btf, type, fieldname, - &anon_offs); + &anon_offs, &mtype); if (IS_ERR(field)) { trace_probe_log_err(ctx->offset, BAD_BTF_TID); return PTR_ERR(field); @@ -653,7 +654,7 @@ static int get_bitoffset_of_field(char **pfieldname, const struct btf_type **pty bitoffs += anon_offs; /* Accumulate the bit-offsets of the dot-connected fields */ - if (btf_type_kflag(type)) { + if (btf_type_kflag(mtype)) { bitoffs += BTF_MEMBER_BIT_OFFSET(field->offset); ctx->last_bitsize = BTF_MEMBER_BITFIELD_SIZE(field->offset); } else { @@ -661,11 +662,11 @@ static int get_bitoffset_of_field(char **pfieldname, const struct btf_type **pty ctx->last_bitsize = 0; } - type = btf_type_skip_modifiers(btf, field->type, NULL); - if (!type) { - trace_probe_log_err(ctx->offset, BAD_BTF_TID); - return -EINVAL; - } + type = btf_type_skip_modifiers(btf, field->type, NULL); + if (!type) { + trace_probe_log_err(ctx->offset, BAD_BTF_TID); + return -EINVAL; + } if (next) ctx->offset += next - fieldname; @@ -2552,19 +2553,60 @@ int traceprobe_set_print_fmt(struct trace_probe *tp, enum probe_print_type ptype int traceprobe_define_arg_fields(struct trace_event_call *event_call, size_t offset, struct trace_probe *tp) { + struct trace_probe_event *tpe = trace_probe_event_from_call(event_call); int ret, i; + /* + * A field created by trace_define_field() only stores the name and + * type pointers, it does not copy the strings. Here they point into + * the probe_arg of @tp, which is freed when @tp is removed. For an + * event with multiple probes attached, the field list is defined + * once by the first probe but kept alive by the surviving siblings, + * so removing that first probe would leave the fields referencing + * freed memory. Duplicate the strings and anchor the copies on the + * trace_probe_event, which lives as long as the field list itself. + * + * event_define_fields() ignores the return value of this hook, so + * if a previous attempt failed before creating any field, it may + * call here again. Release duplicates left behind by such an + * attempt before starting over. + */ + for (i = 0; i < tpe->nr_field_strings; i++) + kfree(tpe->field_strings[i]); + kfree(tpe->field_strings); + tpe->field_strings = NULL; + tpe->nr_field_strings = 0; + + if (tp->nr_args) { + tpe->field_strings = kcalloc(tp->nr_args * 2, sizeof(char *), + GFP_KERNEL); + if (!tpe->field_strings) + return -ENOMEM; + } + /* Set argument names as fields */ for (i = 0; i < tp->nr_args; i++) { struct probe_arg *parg = &tp->args[i]; const char *fmt = parg->type->fmttype; int size = parg->type->size; + char *name, *type; if (parg->fmt) fmt = parg->fmt; if (parg->count) size *= parg->count; - ret = trace_define_field(event_call, fmt, parg->name, + + name = kstrdup(parg->name, GFP_KERNEL); + type = kstrdup(fmt, GFP_KERNEL); + if (!name || !type) { + kfree(name); + kfree(type); + return -ENOMEM; + } + tpe->field_strings[tpe->nr_field_strings++] = name; + tpe->field_strings[tpe->nr_field_strings++] = type; + + ret = trace_define_field(event_call, type, name, offset + parg->offset, size, parg->type->is_signed, FILTER_OTHER); @@ -2576,6 +2618,11 @@ int traceprobe_define_arg_fields(struct trace_event_call *event_call, static void trace_probe_event_free(struct trace_probe_event *tpe) { + int i; + + for (i = 0; i < tpe->nr_field_strings; i++) + kfree(tpe->field_strings[i]); + kfree(tpe->field_strings); kfree(tpe->class.system); kfree(tpe->call.name); kfree(tpe->call.print_fmt); diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index fba1af092a9b..d1fb3520700f 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -264,6 +264,8 @@ struct trace_probe_event { struct trace_event_call call; struct list_head files; struct list_head probes; + char **field_strings; + int nr_field_strings; struct trace_uprobe_filter filter[]; }; diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 861d857adadb..22cc3c8181b8 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -368,7 +368,7 @@ error: static void free_trace_uprobe(struct trace_uprobe *tu) { - if (!tu) + if (IS_ERR_OR_NULL(tu)) return; path_put(&tu->path); @@ -533,7 +533,7 @@ static int register_trace_uprobe(struct trace_uprobe *tu) return ret; } -DEFINE_FREE(free_trace_uprobe, struct trace_uprobe *, if (_T) free_trace_uprobe(_T)) +DEFINE_FREE(free_trace_uprobe, struct trace_uprobe *, free_trace_uprobe(_T)) /* * Argument syntax: diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 3c034cbc5bb3..1ae3732a2c51 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3197,7 +3197,16 @@ restart: #ifdef CONFIG_PREEMPT_RT static void worker_lock_callback(struct worker_pool *pool) { - spin_lock(&pool->cb_lock); + /* + * SINGLE_DEPTH_NESTING is for a dead pool's bh_worker() running from + * drain_dead_softirq_workfn() inside a live pool's bh_worker(). The + * unlocked read is stable: the flag is only set while @pool's CPU is + * dead, inside a serialized hotplug operation. data_race() as the value + * only affects the lockdep annotation and the read can be elided when + * lockdep is disabled. + */ + spin_lock_nested(&pool->cb_lock, + data_race(pool->flags) & POOL_BH_DRAINING ? SINGLE_DEPTH_NESTING : 0); } static void worker_unlock_callback(struct worker_pool *pool) @@ -5285,12 +5294,6 @@ static void pwq_release_workfn(struct kthread_work *work) mutex_unlock(&wq->mutex); } - if (!is_percpu_pool(pool)) { - mutex_lock(&wq_pool_mutex); - put_unbound_pool(pool); - mutex_unlock(&wq_pool_mutex); - } - if (!list_empty(&pwq->pending_node)) { struct wq_node_nr_active *nna = wq_node_nr_active(pwq->wq, pwq->pool->node); @@ -5300,6 +5303,12 @@ static void pwq_release_workfn(struct kthread_work *work) raw_spin_unlock_irq(&nna->lock); } + if (!is_percpu_pool(pool)) { + mutex_lock(&wq_pool_mutex); + put_unbound_pool(pool); + mutex_unlock(&wq_pool_mutex); + } + kfree_rcu(pwq, rcu); /* @@ -8050,6 +8059,9 @@ static int wq_watchdog_param_set_thresh(const char *val, if (ret) return ret; + if (thresh > MAX_JIFFY_OFFSET / HZ) + return -ERANGE; + if (system_percpu_wq) wq_watchdog_set_thresh(thresh); else @@ -8080,12 +8092,12 @@ static inline void wq_watchdog_init(void) { } static void bh_pool_kick_normal(struct irq_work *irq_work) { - raise_softirq_irqoff(TASKLET_SOFTIRQ); + raise_softirq(TASKLET_SOFTIRQ); } static void bh_pool_kick_highpri(struct irq_work *irq_work) { - raise_softirq_irqoff(HI_SOFTIRQ); + raise_softirq(HI_SOFTIRQ); } static void __init restrict_unbound_cpumask(const char *name, const struct cpumask *mask) diff --git a/lib/once.c b/lib/once.c index d801bfa945e6..0a0a919156e0 100644 --- a/lib/once.c +++ b/lib/once.c @@ -93,6 +93,6 @@ void __do_once_sleepable_done(bool *done, struct static_key_true *once_key, { *done = true; mutex_unlock(&once_mutex); - static_branch_disable(once_key); + once_disable_jump(once_key, mod); } EXPORT_SYMBOL(__do_once_sleepable_done); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index ced400f72d43..afbb5974bd22 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2449,6 +2449,8 @@ static void zap_huge_pmd_folio(struct mm_struct *mm, struct vm_area_struct *vma, add_mm_counter(mm, mm_counter_file(folio), -HPAGE_PMD_NR); + if (is_present && pmd_dirty(pmdval)) + folio_mark_dirty(folio); if (is_present && pmd_young(pmdval) && likely(vma_has_recency(vma))) folio_mark_accessed(folio); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 785772845795..4f6f58bf3db6 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1992,7 +1992,8 @@ retry: if (h->surplus_huge_pages_node[folio_nid(folio)]) adjust_surplus = true; remove_hugetlb_folio(h, folio, adjust_surplus); - h->max_huge_pages--; + if (!adjust_surplus) + h->max_huge_pages--; spin_unlock_irq(&hugetlb_lock); /* @@ -2012,7 +2013,8 @@ retry: if (rc) { spin_lock_irq(&hugetlb_lock); add_hugetlb_folio(h, folio, adjust_surplus); - h->max_huge_pages++; + if (!adjust_surplus) + h->max_huge_pages++; goto out; } } else { @@ -7330,14 +7332,14 @@ void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, * There is no need to transfer the per-node surplus state * when we do not cross the node. */ - if (new_nid == old_nid) - return; - spin_lock_irq(&hugetlb_lock); - if (h->surplus_huge_pages_node[old_nid]) { - h->surplus_huge_pages_node[old_nid]--; - h->surplus_huge_pages_node[new_nid]++; + if (new_nid != old_nid) { + spin_lock_irq(&hugetlb_lock); + if (h->surplus_huge_pages_node[old_nid]) { + h->surplus_huge_pages_node[old_nid]--; + h->surplus_huge_pages_node[new_nid]++; + } + spin_unlock_irq(&hugetlb_lock); } - spin_unlock_irq(&hugetlb_lock); } /* diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index e0083de1ca82..ecb6e0b7819a 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -97,6 +97,7 @@ static void hugetlb_cgroup_init(struct hugetlb_cgroup *h_cgroup, struct page_counter *fault, *fault_parent = NULL; struct page_counter *rsvd, *rsvd_parent = NULL; unsigned long limit; + int ret; if (parent_h_cgroup) { fault_parent = hugetlb_cgroup_counter_from_cgroup( @@ -118,8 +119,10 @@ static void hugetlb_cgroup_init(struct hugetlb_cgroup *h_cgroup, limit = round_down(PAGE_COUNTER_MAX, pages_per_huge_page(&hstates[idx])); - VM_BUG_ON(page_counter_set_max(fault, limit)); - VM_BUG_ON(page_counter_set_max(rsvd, limit)); + ret = page_counter_set_max(fault, limit); + VM_WARN_ON_ONCE(ret); + ret = page_counter_set_max(rsvd, limit); + VM_WARN_ON_ONCE(ret); } } diff --git a/mm/hugetlb_cma.c b/mm/hugetlb_cma.c index db0680e82847..95fd2d190f0d 100644 --- a/mm/hugetlb_cma.c +++ b/mm/hugetlb_cma.c @@ -3,6 +3,7 @@ #include <linux/mm.h> #include <linux/cma.h> #include <linux/compiler.h> +#include <linux/cpuset.h> #include <linux/mm_inline.h> #include <asm/page.h> @@ -55,15 +56,25 @@ struct folio *hugetlb_cma_alloc_frozen_folio(int order, gfp_t gfp_mask, int node; struct folio *folio; struct page *page = NULL; + const nodemask_t *nmask; + unsigned int cpuset_mems_cookie; if (!hugetlb_cma_size) return NULL; - if (hugetlb_cma[nid]) +retry_cpuset: + if (!nodemask) { + cpuset_mems_cookie = read_mems_allowed_begin(); + nmask = &cpuset_current_mems_allowed; + } else { + nmask = nodemask; + } + + if (hugetlb_cma[nid] && node_isset(nid, *nmask)) page = cma_alloc_frozen_compound(hugetlb_cma[nid], order); if (!page && !(gfp_mask & __GFP_THISNODE)) { - for_each_node_mask(node, *nodemask) { + for_each_node_mask(node, *nmask) { if (node == nid || !hugetlb_cma[node]) continue; @@ -73,8 +84,12 @@ struct folio *hugetlb_cma_alloc_frozen_folio(int order, gfp_t gfp_mask, } } - if (!page) + if (!page) { + if (!nodemask && + unlikely(read_mems_allowed_retry(cpuset_mems_cookie))) + goto retry_cpuset; return NULL; + } folio = page_folio(page); folio_set_hugetlb_cma(folio); diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 11ff98d55c76..75639298efc2 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -454,12 +454,6 @@ int hugepage_madvise(struct vm_area_struct *vma, case MADV_HUGEPAGE: *vm_flags &= ~VM_NOHUGEPAGE; *vm_flags |= VM_HUGEPAGE; - /* - * If the vma become good for khugepaged to scan, - * register it here without waiting a page fault that - * may not happen any time soon. - */ - khugepaged_enter_vma(vma, *vm_flags); break; case MADV_NOHUGEPAGE: *vm_flags &= ~VM_HUGEPAGE; diff --git a/mm/madvise.c b/mm/madvise.c index 96f2387b2f46..eeee82cf2b3f 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -178,6 +178,14 @@ static int madvise_update_vma(vm_flags_t new_flags, /* vm_flags is protected by the mmap_lock held in write mode. */ vma_start_write(vma); vma->flags = new_vma_flags; + /* + * If the vma become good for khugepaged to scan, + * register it here without waiting a page fault that + * may not happen any time soon. + */ + if (vma_flags_test(&new_vma_flags, VMA_HUGEPAGE_BIT)) + khugepaged_enter_vma(vma, vma_flags_to_legacy(new_vma_flags)); + if (set_new_anon_name) return replace_anon_vma_name(vma, anon_name); diff --git a/mm/memcontrol-v1.c b/mm/memcontrol-v1.c index 835fc8e51184..05ef55cae4dc 100644 --- a/mm/memcontrol-v1.c +++ b/mm/memcontrol-v1.c @@ -96,7 +96,6 @@ enum { RES_LIMIT, RES_MAX_USAGE, RES_FAILCNT, - RES_SOFT_LIMIT, }; #ifdef CONFIG_LOCKDEP @@ -1888,6 +1887,30 @@ static int mem_cgroup_hierarchy_write(struct cgroup_subsys_state *css, return -EINVAL; } +static u64 mem_cgroup_soft_limit_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + return (u64)PAGE_COUNTER_MAX * PAGE_SIZE; +} + +static ssize_t mem_cgroup_soft_limit_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + unsigned long nr_pages; + int ret; + + ret = page_counter_memparse(strstrip(buf), "-1", &nr_pages); + if (ret) + return ret; + + pr_warn_once("soft_limit_in_bytes is deprecated and will be removed. " + "Writing any value to this file has no effect. " + "Please report your usecase to linux-mm@kvack.org if you " + "depend on this functionality.\n"); + + return nbytes; +} + static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css, struct cftype *cft) { @@ -1924,8 +1947,6 @@ static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css, return (u64)counter->watermark * PAGE_SIZE; case RES_FAILCNT: return counter->failcnt; - case RES_SOFT_LIMIT: - return (u64)READ_ONCE(memcg->soft_limit) * PAGE_SIZE; default: BUG(); } @@ -2020,17 +2041,6 @@ static ssize_t mem_cgroup_write(struct kernfs_open_file *of, break; } break; - case RES_SOFT_LIMIT: - if (IS_ENABLED(CONFIG_PREEMPT_RT)) { - ret = -EOPNOTSUPP; - } else { - pr_warn_once("soft_limit_in_bytes is deprecated and will be removed. " - "Please report your usecase to linux-mm@kvack.org if you " - "depend on this functionality.\n"); - WRITE_ONCE(memcg->soft_limit, nr_pages); - ret = 0; - } - break; } return ret ?: nbytes; } @@ -2384,9 +2394,8 @@ struct cftype mem_cgroup_legacy_files[] = { }, { .name = "soft_limit_in_bytes", - .private = MEMFILE_PRIVATE(_MEM, RES_SOFT_LIMIT), - .write = mem_cgroup_write, - .read_u64 = mem_cgroup_read_u64, + .write = mem_cgroup_soft_limit_write, + .read_u64 = mem_cgroup_soft_limit_read, }, { .name = "failcnt", diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 3498a5651d50..79053ece02cd 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2679,7 +2679,7 @@ static unsigned long alloc_pages_bulk_weighted_interleave(gfp_t gfp, prev_node = node; /* create a local copy of node weights to operate on outside rcu */ - weights = kzalloc(nr_node_ids, GFP_KERNEL); + weights = kmalloc(nr_node_ids, gfp & GFP_RECLAIM_MASK); if (!weights) return total_allocated; diff --git a/mm/migrate_device.c b/mm/migrate_device.c index 762c5cee8fec..009bfa8b212d 100644 --- a/mm/migrate_device.c +++ b/mm/migrate_device.c @@ -1423,6 +1423,15 @@ int migrate_device_range(unsigned long *src_pfns, unsigned long start, src_pfns[i] = migrate_device_pfn_lock(pfn); nr = folio_nr_pages(folio); + if (nr > npages - i) { + if (src_pfns[i] & MIGRATE_PFN_MIGRATE) { + folio_unlock(folio); + folio_put(folio); + } + memset(&src_pfns[i], 0, + (npages - i) * sizeof(*src_pfns)); + break; + } if (nr > 1) { src_pfns[i] |= MIGRATE_PFN_COMPOUND; for (j = 1; j < nr; j++) @@ -1457,6 +1466,15 @@ int migrate_device_pfns(unsigned long *src_pfns, unsigned long npages) src_pfns[i] = migrate_device_pfn_lock(src_pfns[i]); nr = folio_nr_pages(folio); + if (nr > npages - i) { + if (src_pfns[i] & MIGRATE_PFN_MIGRATE) { + folio_unlock(folio); + folio_put(folio); + } + memset(&src_pfns[i], 0, + (npages - i) * sizeof(*src_pfns)); + break; + } if (nr > 1) { src_pfns[i] |= MIGRATE_PFN_COMPOUND; for (j = 1; j < nr; j++) diff --git a/mm/mremap.c b/mm/mremap.c index e8df5cdb0ac9..2b4b523a86b8 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -1331,18 +1331,30 @@ static void dontunmap_complete(struct vma_remap_struct *vrm, { unsigned long start = vrm->addr; unsigned long end = vrm->addr + vrm->old_len; - unsigned long old_start = vrm->vma->vm_start; - unsigned long old_end = vrm->vma->vm_end; + struct vm_area_struct *vma = vrm->vma; + unsigned long old_start = vma->vm_start; + unsigned long old_end = vma->vm_end; /* We always clear VMA_LOCKED[ONFAULT]_BIT on the old VMA. */ - vma_clear_flags_mask(vrm->vma, VMA_LOCKED_MASK); + vma_clear_flags_mask(vma, VMA_LOCKED_MASK); /* * anon_vma links of the old vma is no longer needed after its page * table has been moved. */ - if (new_vma != vrm->vma && start == old_start && end == old_end) - unlink_anon_vmas(vrm->vma); + if (new_vma != vma && start == old_start && end == old_end) { + const pgoff_t pgoff_unfaulted = vma->vm_start >> PAGE_SHIFT; + + unlink_anon_vmas(vma); + /* + * The VMA is now unfaulted and it is an invariant that + * unfaulted anonymous VMAs have page offset equal to + * vma->vm_start >> PAGE_SHIFT. + */ + vma_set_anon_pgoff(vma, pgoff_unfaulted); + if (vma_is_anonymous(vma) && !vma->vm_file) + vma_set_pgoff(vma, pgoff_unfaulted); + } /* Because we won't unmap we don't need to touch locked_vm. */ } diff --git a/mm/secretmem.c b/mm/secretmem.c index d29865075b6e..384f5cfc457f 100644 --- a/mm/secretmem.c +++ b/mm/secretmem.c @@ -18,6 +18,8 @@ #include <linux/secretmem.h> #include <linux/set_memory.h> #include <linux/sched/signal.h> +#include <linux/sched/user.h> +#include <linux/cred.h> #include <uapi/linux/magic.h> @@ -47,10 +49,69 @@ bool secretmem_active(void) return !!atomic_read(&secretmem_users); } +struct secretmem_inode_state { + struct user_struct *user; + atomic_long_t nr_pages_accounted; +}; + +static bool __secretmem_account_pages(struct user_struct *user, + unsigned long nr_pages) +{ + unsigned long page_limit, cur_pages, new_pages; + + if (!nr_pages) + return true; + + page_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + + cur_pages = atomic_long_read(&user->locked_vm); + do { + new_pages = cur_pages + nr_pages; + if (new_pages > page_limit) + return false; + } while (!atomic_long_try_cmpxchg(&user->locked_vm, + &cur_pages, new_pages)); + return true; +} + +static bool secretmem_account_folio(struct secretmem_inode_state *state, + const struct folio *folio) +{ + const unsigned long nr_pages = folio_nr_pages(folio); + + if (!__secretmem_account_pages(state->user, nr_pages)) + return false; + + atomic_long_add(nr_pages, &state->nr_pages_accounted); + return true; +} + +static void __secretmem_unaccount_pages(struct secretmem_inode_state *state, + unsigned long nr_pages) +{ + atomic_long_sub(nr_pages, &state->user->locked_vm); + atomic_long_sub(nr_pages, &state->nr_pages_accounted); +} + +static void secretmem_unaccount_folio(struct secretmem_inode_state *state, + struct folio *folio) +{ + __secretmem_unaccount_pages(state, folio_nr_pages(folio)); +} + +static void secretmem_unaccount_all_folios(struct secretmem_inode_state *state) +{ + const unsigned long nr_pages_accounted = + atomic_long_read(&state->nr_pages_accounted); + + __secretmem_unaccount_pages(state, nr_pages_accounted); +} + static vm_fault_t secretmem_fault(struct vm_fault *vmf) { struct address_space *mapping = vmf->vma->vm_file->f_mapping; struct inode *inode = file_inode(vmf->vma->vm_file); + struct secretmem_inode_state *state = inode->i_private; pgoff_t offset = vmf->pgoff; gfp_t gfp = vmf->gfp_mask; unsigned long addr; @@ -72,8 +133,15 @@ retry: goto out; } + if (!secretmem_account_folio(state, folio)) { + folio_put(folio); + ret = VM_FAULT_SIGBUS; + goto out; + } + err = set_direct_map_invalid_noflush(folio_page(folio, 0)); if (err) { + secretmem_unaccount_folio(state, folio); folio_put(folio); ret = vmf_error(err); goto out; @@ -82,6 +150,7 @@ retry: __folio_mark_uptodate(folio); err = filemap_add_folio(mapping, folio, offset, gfp); if (unlikely(err)) { + secretmem_unaccount_folio(state, folio); /* * If a split of large page was required, it * already happened when we marked the page invalid @@ -112,22 +181,30 @@ static const struct vm_operations_struct secretmem_vm_ops = { .fault = secretmem_fault, }; +static void secretmem_destroy_inode_priv(struct inode *inode) +{ + struct secretmem_inode_state *state = inode->i_private; + + secretmem_unaccount_all_folios(state); + free_uid(state->user); + kfree(state); + inode->i_private = NULL; +} + static int secretmem_release(struct inode *inode, struct file *file) { atomic_dec(&secretmem_users); + secretmem_destroy_inode_priv(inode); + return 0; } static int secretmem_mmap_prepare(struct vm_area_desc *desc) { - const unsigned long len = vma_desc_size(desc); - if (!vma_desc_test_any(desc, VMA_SHARED_BIT, VMA_MAYSHARE_BIT)) return -EINVAL; - vma_desc_set_flags(desc, VMA_LOCKED_BIT, VMA_DONTDUMP_BIT); - if (!mlock_future_ok(desc->mm, /*is_vma_locked=*/ true, len)) - return -EAGAIN; + vma_desc_set_flags(desc, VMA_DONTDUMP_BIT); desc->vm_ops = &secretmem_vm_ops; return 0; @@ -187,20 +264,40 @@ static const struct inode_operations secretmem_iops = { static struct vfsmount *secretmem_mnt; +static int secretmem_init_inode_priv(struct inode *inode) +{ + struct secretmem_inode_state *state; + + state = kzalloc_obj(*state); + if (!state) + return -ENOMEM; + + state->user = get_uid(current_user()); + inode->i_private = state; + return 0; +} + static struct file *secretmem_file_create(unsigned long flags) { struct file *file; struct inode *inode; const char *anon_name = "[secretmem]"; + int err; inode = anon_inode_make_secure_inode(secretmem_mnt->mnt_sb, anon_name, NULL); if (IS_ERR(inode)) return ERR_CAST(inode); + err = secretmem_init_inode_priv(inode); + if (err) + goto err_free_inode; + file = alloc_file_pseudo(inode, secretmem_mnt, "secretmem", O_RDWR | O_LARGEFILE, &secretmem_fops); - if (IS_ERR(file)) - goto err_free_inode; + if (IS_ERR(file)) { + err = PTR_ERR(file); + goto err_free_priv; + } mapping_set_gfp_mask(inode->i_mapping, GFP_USER); mapping_set_unevictable(inode->i_mapping); @@ -215,10 +312,11 @@ static struct file *secretmem_file_create(unsigned long flags) atomic_inc(&secretmem_users); return file; - +err_free_priv: + secretmem_destroy_inode_priv(inode); err_free_inode: iput(inode); - return file; + return ERR_PTR(err); } SYSCALL_DEFINE1(memfd_secret, unsigned int, flags) diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 23fb68fce000..74f04c323c50 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -2171,8 +2171,10 @@ static ssize_t move_pages(struct userfaultfd_ctx *ctx, unsigned long dst_start, } if (err) { - if (err == -EAGAIN) + if (err == -EAGAIN) { + err = 0; continue; + } break; } diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 35a1be57e386..d7355c73f93e 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2632,11 +2632,11 @@ int hci_register_dev(struct hci_dev *hdev) if (error) BT_WARN("register suspend notifier failed error:%d\n", error); - queue_work(hdev->req_workqueue, &hdev->power_on); - idr_init(&hdev->adv_monitors_idr); msft_register(hdev); + queue_work(hdev->req_workqueue, &hdev->power_on); + return id; err_wqueue: diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index ee459dd411f5..644e31160d55 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -1337,7 +1337,7 @@ static void l2cap_le_connect(struct l2cap_chan *chan) struct l2cap_ecred_conn_data { struct { struct l2cap_ecred_conn_req_hdr req; - __le16 scid[5]; + __le16 scid[L2CAP_ECRED_CONN_SCID_MAX]; } __packed pdu; struct l2cap_chan *chan; struct pid *pid; @@ -1352,7 +1352,7 @@ static void l2cap_ecred_defer_connect(struct l2cap_chan *chan, void *data) if (chan == conn->chan) return; - if (!test_and_clear_bit(FLAG_DEFER_SETUP, &chan->flags)) + if (!test_bit(FLAG_DEFER_SETUP, &chan->flags)) return; pid = chan->ops->get_peer_pid(chan); @@ -1362,9 +1362,16 @@ static void l2cap_ecred_defer_connect(struct l2cap_chan *chan, void *data) chan->mode != L2CAP_MODE_EXT_FLOWCTL || chan->state != BT_CONNECT) return; + if (!test_and_clear_bit(FLAG_DEFER_SETUP, &chan->flags)) + return; + if (test_and_set_bit(FLAG_ECRED_CONN_REQ_SENT, &chan->flags)) return; + /* Unreachable, checked in l2cap_connect (+timer drops it if reached) */ + if (WARN_ON_ONCE(conn->count >= ARRAY_SIZE(conn->pdu.scid))) + return; + l2cap_ecred_init(chan, 0); /* Set the same ident so we can match on the rsp */ @@ -3894,6 +3901,9 @@ static void l2cap_ecred_rsp_defer(struct l2cap_chan *chan, void *data) struct l2cap_ecred_conn_rsp *rsp_flex = container_of(&rsp->pdu.rsp, struct l2cap_ecred_conn_rsp, hdr); + if (chan->mode != L2CAP_MODE_EXT_FLOWCTL) + return; + /* Check if channel for outgoing connection or if it wasn't deferred * since in those cases it must be skipped. */ @@ -3904,6 +3914,10 @@ static void l2cap_ecred_rsp_defer(struct l2cap_chan *chan, void *data) /* Reset ident so only one response is sent */ chan->ident = 0; + /* Unreachable, check in l2cap_ecred_conn_req. If reached, drop rest */ + if (WARN_ON_ONCE(rsp->count >= ARRAY_SIZE(rsp->pdu.scid))) + rsp->pdu.rsp.result = cpu_to_le16(L2CAP_CR_LE_NO_MEM); + /* Include all channels pending with the same ident */ if (!rsp->pdu.rsp.result) rsp_flex->dcid[rsp->count++] = cpu_to_le16(chan->scid); @@ -5063,6 +5077,7 @@ static int l2cap_le_connect_req(struct l2cap_conn *conn, __set_chan_timer(chan, chan->ops->get_sndtimeo(chan)); chan->ident = cmd->ident; + chan->mode = L2CAP_MODE_LE_FLOWCTL; if (test_bit(FLAG_DEFER_SETUP, &chan->flags)) { l2cap_state_change(chan, BT_CONNECT2); @@ -7369,6 +7384,9 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, goto done; } + mutex_lock(&conn->lock); + l2cap_chan_lock(chan); + if (chan->mode == L2CAP_MODE_EXT_FLOWCTL) { struct l2cap_chan_data data; @@ -7376,19 +7394,20 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, data.pid = chan->ops->get_peer_pid(chan); data.count = 1; - l2cap_chan_list(conn, l2cap_chan_by_pid, &data); + __l2cap_chan_list(conn, l2cap_chan_by_pid, &data); + + /* Leave room for non-deferred channel that ends the group. */ + if (test_bit(FLAG_DEFER_SETUP, &chan->flags)) + data.count += 1; /* Check if there isn't too many channels being connected */ if (data.count > L2CAP_ECRED_CONN_SCID_MAX) { hci_conn_drop(hcon); err = -EPROTO; - goto done; + goto chan_unlock; } } - mutex_lock(&conn->lock); - l2cap_chan_lock(chan); - if (cid && __l2cap_get_chan_by_dcid(conn, cid)) { hci_conn_drop(hcon); err = -EBUSY; diff --git a/net/bluetooth/msft.c b/net/bluetooth/msft.c index ded68568e6c9..d9dd722db3eb 100644 --- a/net/bluetooth/msft.c +++ b/net/bluetooth/msft.c @@ -769,8 +769,8 @@ void msft_register(struct hci_dev *hdev) INIT_LIST_HEAD(&msft->handle_map); INIT_LIST_HEAD(&msft->address_filters); - hdev->msft_data = msft; mutex_init(&msft->filter_lock); + hdev->msft_data = msft; } void msft_release(struct hci_dev *hdev) diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 3ef5d8bbf552..3e9b10f8abf1 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -808,7 +808,11 @@ void br_multicast_del_pg(struct net_bridge_mdb_entry *mp, struct hlist_node *tmp; rcu_assign_pointer(*pp, pg->next); - hlist_del_init(&pg->mglist); + /* Keep ->next (held under multicast_lock, freed later by the GC work): + * a port->mglist teardown walk may have latched this node as its next, + * and deleting other groups of the same port must not truncate it. + */ + hlist_del_init_rcu(&pg->mglist); br_multicast_eht_clean_sets(pg); hlist_for_each_entry_safe(ent, tmp, &pg->src_list, node) br_multicast_del_group_src(ent, false); @@ -835,6 +839,13 @@ static void br_multicast_find_del_pg(struct net_bridge *br, struct net_bridge_mdb_entry *mp; struct net_bridge_port_group *p; + /* A teardown walk over port->mglist can reach a group that an earlier + * iteration already deleted as a side effect. It is off mp->ports by + * now, so skip it instead of falling through to the WARN_ON() below. + */ + if (hlist_unhashed(&pg->mglist)) + return; + mp = br_mdb_ip_get(br, &pg->key.addr); if (WARN_ON(!mp)) return; diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 9c1b6cf8c36f..212e7797f9e4 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -1003,7 +1003,6 @@ static struct page *ceph_msg_data_iter_next(struct ceph_msg_data_cursor *cursor, * we'll get an iov_iter_get_pages2 variant that doesn't take * page refs. Until then, just put the page ref. */ - VM_BUG_ON_PAGE(!PageWriteback(page) && page_count(page) < 2, page); put_page(page); *length = min_t(size_t, len, cursor->resid); diff --git a/net/core/dev.c b/net/core/dev.c index 38336858c168..290e0f099e6b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -12703,7 +12703,7 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat, int new_ifindex, struct netlink_ext_ack *extack) { - struct netdev_name_node *name_node; + struct netdev_name_node *name_node, *tmp; struct net *net_old = dev_net(dev); char new_name[IFNAMSIZ] = {}; int err, new_nsid; @@ -12749,13 +12749,19 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, } /* Check that none of the altnames conflicts. */ err = -EEXIST; - netdev_for_each_altname(dev, name_node) { - if (netdev_name_in_use(net, name_node->name)) { - NL_SET_ERR_MSG_FMT(extack, - "An interface with the altname %s exists in the target netns", - name_node->name); - goto out; + netdev_for_each_altname_safe(dev, name_node, tmp) { + if (!netdev_name_in_use(net, name_node->name)) + continue; + + if (!check_net(net_old)) { + __netdev_name_node_alt_destroy(name_node); + continue; } + + NL_SET_ERR_MSG_FMT(extack, + "An interface with the altname %s exists in the target netns", + name_node->name); + goto out; } /* Check that new_ifindex isn't used yet. */ @@ -13210,7 +13216,6 @@ static struct pernet_operations __net_initdata netdev_net_ops = { static void __net_exit default_device_exit_net(struct net *net) { - struct netdev_name_node *name_node, *tmp; struct net_device *dev, *aux; /* * Push all migratable network devices back to the @@ -13234,10 +13239,6 @@ static void __net_exit default_device_exit_net(struct net *net) if (netdev_name_in_use(&init_net, fb_name)) snprintf(fb_name, IFNAMSIZ, "dev%%d"); - netdev_for_each_altname_safe(dev, name_node, tmp) - if (netdev_name_in_use(&init_net, name_node->name)) - __netdev_name_node_alt_destroy(name_node); - err = dev_change_net_namespace(dev, &init_net, fb_name); if (err) { pr_emerg("%s: failed to move %s to init_net: %d\n", diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c index 1b84385c04bd..d8c0a2867120 100644 --- a/net/core/gro_cells.c +++ b/net/core/gro_cells.c @@ -22,6 +22,8 @@ int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb) if (unlikely(!(dev->flags & IFF_UP))) goto drop; + skb_unset_transport_header(skb); + if (!gcells->cells || skb_cloned(skb) || netif_elide_gro(dev)) { res = netif_rx(skb); goto unlock; diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 8f8956fb061b..08d7f35cf608 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -1073,7 +1073,8 @@ netmem_ref page_pool_alloc_frag_netmem(struct page_pool *pool, if (WARN_ON(size > max_size)) return 0; - size = ALIGN(size, dma_get_cache_alignment()); + size = ALIGN(size, max_t(unsigned int, dma_get_cache_alignment(), + __alignof__(struct skb_shared_info))); *offset = pool->frag_offset; if (netmem && *offset + size > max_size) { diff --git a/net/core/sock.c b/net/core/sock.c index 1ad41904db25..fa60b7494c58 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2494,6 +2494,9 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority, #ifdef CONFIG_BPF_SYSCALL RCU_INIT_POINTER(newsk->sk_bpf_storage, NULL); #endif +#if IS_ENABLED(CONFIG_INET_PSP) + RCU_INIT_POINTER(newsk->psp_assoc, NULL); +#endif /* SANITY */ if (likely(newsk->sk_net_refcnt)) { diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 0483519b7fb0..7a362f2e2c2b 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -874,7 +874,7 @@ static void fib_rebalance(struct fib_info *fi) change_nexthops(fi) { int upper_bound; - if (nexthop_nh->fib_nh_flags & RTNH_F_DEAD) { + if (!total || nexthop_nh->fib_nh_flags & RTNH_F_DEAD) { upper_bound = -1; } else if (ip_ignore_linkdown(nexthop_nh->fib_nh_dev) && nexthop_nh->fib_nh_flags & RTNH_F_LINKDOWN) { diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index b80b8a92f46e..d56355aca797 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -188,6 +188,10 @@ static void ip_ma_put(struct ip_mc_list *im) } } +#define pmc_dereference(e, pmc) \ + rcu_dereference_protected(e, lockdep_is_held(&(pmc)->lock) || \ + lockdep_is_held(&(pmc)->interface->mc_tomb_lock)) + #define for_each_pmc_rcu(in_dev, pmc) \ for (pmc = rcu_dereference(in_dev->mc_list); \ pmc != NULL; \ @@ -198,13 +202,28 @@ static void ip_ma_put(struct ip_mc_list *im) pmc != NULL; \ pmc = rtnl_dereference(pmc->next_rcu)) +#define for_each_psf_mclock(pmc, psf) \ + for (psf = pmc_dereference((pmc)->sources, pmc); \ + psf; \ + psf = pmc_dereference(psf->sf_next, pmc)) + +#define for_each_psf_rcu(im, psf) \ + for (psf = rcu_dereference((im)->sources); \ + psf; \ + psf = rcu_dereference(psf->sf_next)) + +#define for_each_psf_tomb(pmc, psf) \ + for (psf = pmc_dereference((pmc)->tomb, pmc); \ + psf; \ + psf = pmc_dereference(psf->sf_next, pmc)) + static void ip_sf_list_clear_all(struct ip_sf_list *psf) { struct ip_sf_list *next; while (psf) { - next = psf->sf_next; - kfree(psf); + next = rcu_dereference_protected(psf->sf_next, 1); + kfree_rcu(psf, rcu); psf = next; } } @@ -349,7 +368,7 @@ igmp_scount(struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted) struct ip_sf_list *psf; int scount = 0; - for (psf = pmc->sources; psf; psf = psf->sf_next) { + for_each_psf_mclock(pmc, psf) { if (!is_in(pmc, psf, type, gdeleted, sdeleted)) continue; scount++; @@ -494,7 +513,8 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, struct net *net = dev_net(dev); struct igmpv3_report *pih; struct igmpv3_grec *pgr = NULL; - struct ip_sf_list *psf, *psf_next, *psf_prev, **psf_list; + struct ip_sf_list *psf, *psf_next, *psf_prev; + struct ip_sf_list __rcu **psf_list; int scount, stotal, first, isquery, truncate; unsigned int mtu; @@ -517,7 +537,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, psf_list = sdeleted ? &pmc->tomb : &pmc->sources; - if (!*psf_list) + if (!rcu_access_pointer(*psf_list)) goto empty_source; pih = skb ? igmpv3_report_hdr(skb) : NULL; @@ -533,10 +553,12 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, } first = 1; psf_prev = NULL; - for (psf = *psf_list; psf; psf = psf_next) { + for (psf = pmc_dereference(*psf_list, pmc); + psf; + psf = psf_next) { __be32 *psrc; - psf_next = psf->sf_next; + psf_next = pmc_dereference(psf->sf_next, pmc); if (!is_in(pmc, psf, type, gdeleted, sdeleted)) { psf_prev = psf; @@ -583,10 +605,12 @@ decrease_sf_crcount: psf->sf_crcount--; if ((sdeleted || gdeleted) && psf->sf_crcount == 0) { if (psf_prev) - psf_prev->sf_next = psf->sf_next; + rcu_assign_pointer(psf_prev->sf_next, + psf_next); else - *psf_list = psf->sf_next; - kfree(psf); + rcu_assign_pointer(*psf_list, + psf_next); + kfree_rcu(psf, rcu); continue; } } @@ -655,28 +679,29 @@ static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc) /* * remove zero-count source records from a source filter list */ -static void igmpv3_clear_zeros(struct ip_sf_list **ppsf) +static void igmpv3_clear_zeros(struct ip_sf_list __rcu **ppsf) { struct ip_sf_list *psf_prev, *psf_next, *psf; psf_prev = NULL; - for (psf = *ppsf; psf; psf = psf_next) { - psf_next = psf->sf_next; + for (psf = rcu_dereference_protected(*ppsf, 1); psf; psf = psf_next) { + psf_next = rcu_dereference_protected(psf->sf_next, 1); if (psf->sf_crcount == 0) { if (psf_prev) - psf_prev->sf_next = psf->sf_next; + rcu_assign_pointer(psf_prev->sf_next, psf_next); else - *ppsf = psf->sf_next; - kfree(psf); - } else + rcu_assign_pointer(*ppsf, psf_next); + kfree_rcu(psf, rcu); + } else { psf_prev = psf; + } } } static void kfree_pmc(struct ip_mc_list *pmc) { - ip_sf_list_clear_all(pmc->sources); - ip_sf_list_clear_all(pmc->tomb); + ip_sf_list_clear_all(rcu_dereference_protected(pmc->sources, 1)); + ip_sf_list_clear_all(rcu_dereference_protected(pmc->tomb, 1)); kfree(pmc); } @@ -710,7 +735,8 @@ static void igmpv3_send_cr(struct in_device *in_dev) igmpv3_clear_zeros(&pmc->sources); } } - if (pmc->crcount == 0 && !pmc->tomb && !pmc->sources) { + if (pmc->crcount == 0 && !rcu_access_pointer(pmc->tomb) && + !rcu_access_pointer(pmc->sources)) { if (pmc_prev) pmc_prev->next = pmc_next; else @@ -896,7 +922,7 @@ static int igmp_xmarksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) int i, scount; scount = 0; - for (psf = pmc->sources; psf; psf = psf->sf_next) { + for_each_psf_mclock(pmc, psf) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) { @@ -927,7 +953,7 @@ static int igmp_marksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) /* mark INCLUDE-mode sources */ scount = 0; - for (psf = pmc->sources; psf; psf = psf->sf_next) { + for_each_psf_mclock(pmc, psf) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) @@ -1228,11 +1254,12 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im, if (pmc->sfmode == MCAST_INCLUDE) { struct ip_sf_list *psf; + for_each_psf_mclock(im, psf) + psf->sf_crcount = pmc->crcount; pmc->tomb = im->tomb; pmc->sources = im->sources; - im->tomb = im->sources = NULL; - for (psf = pmc->sources; psf; psf = psf->sf_next) - psf->sf_crcount = pmc->crcount; + RCU_INIT_POINTER(im->tomb, NULL); + RCU_INIT_POINTER(im->sources, NULL); } spin_unlock_bh(&im->lock); @@ -1271,9 +1298,18 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im) if (pmc) { im->interface = pmc->interface; if (im->sfmode == MCAST_INCLUDE) { - swap(im->tomb, pmc->tomb); - swap(im->sources, pmc->sources); - for (psf = im->sources; psf; psf = psf->sf_next) + struct ip_sf_list *sources, *tomb; + + tomb = rcu_replace_pointer(im->tomb, + rcu_dereference_protected(pmc->tomb, 1), + lockdep_is_held(&im->lock)); + rcu_assign_pointer(pmc->tomb, tomb); + + sources = rcu_replace_pointer(im->sources, + rcu_dereference_protected(pmc->sources, 1), + lockdep_is_held(&im->lock)); + rcu_assign_pointer(pmc->sources, sources); + for_each_psf_mclock(im, psf) psf->sf_crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); } else { @@ -1310,8 +1346,8 @@ static void igmpv3_clear_delrec(struct in_device *in_dev) struct ip_sf_list *psf; spin_lock_bh(&pmc->lock); - psf = pmc->tomb; - pmc->tomb = NULL; + psf = pmc_dereference(pmc->tomb, pmc); + RCU_INIT_POINTER(pmc->tomb, NULL); spin_unlock_bh(&pmc->lock); ip_sf_list_clear_all(psf); } @@ -1990,7 +2026,7 @@ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, int rv = 0; psf_prev = NULL; - for (psf = pmc->sources; psf; psf = psf->sf_next) { + for_each_psf_mclock(pmc, psf) { if (psf->sf_inaddr == *psfsrc) break; psf_prev = psf; @@ -1999,7 +2035,7 @@ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, /* source filter not found, or count wrong => bug */ return -ESRCH; } - psf->sf_count[sfmode]--; + WRITE_ONCE(psf->sf_count[sfmode], psf->sf_count[sfmode] - 1); if (psf->sf_count[sfmode] == 0) { ip_rt_multicast_event(pmc->interface); } @@ -2011,19 +2047,28 @@ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, /* no more filters for this source */ if (psf_prev) - psf_prev->sf_next = psf->sf_next; + rcu_assign_pointer(psf_prev->sf_next, + pmc_dereference(psf->sf_next, pmc)); else - pmc->sources = psf->sf_next; + rcu_assign_pointer(pmc->sources, + pmc_dereference(psf->sf_next, pmc)); #ifdef CONFIG_IP_MULTICAST if (psf->sf_oldin && !IGMP_V1_SEEN(in_dev) && !IGMP_V2_SEEN(in_dev)) { - psf->sf_crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); - psf->sf_next = pmc->tomb; - pmc->tomb = psf; - rv = 1; - } else + struct ip_sf_list *dpsf = kmalloc_obj(*dpsf, GFP_ATOMIC); + + if (dpsf) { + *dpsf = *psf; + dpsf->sf_crcount = in_dev->mr_qrv ?: + READ_ONCE(net->ipv4.sysctl_igmp_qrv); + rcu_assign_pointer(dpsf->sf_next, + pmc_dereference(pmc->tomb, pmc)); + rcu_assign_pointer(pmc->tomb, dpsf); + rv = 1; + } + } #endif - kfree(psf); + kfree_rcu(psf, rcu); } return rv; } @@ -2060,7 +2105,7 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, err = -EINVAL; if (!pmc->sfcount[sfmode]) goto out_unlock; - pmc->sfcount[sfmode]--; + WRITE_ONCE(pmc->sfcount[sfmode], pmc->sfcount[sfmode] - 1); } err = 0; for (i = 0; i < sfcount; i++) { @@ -2083,7 +2128,7 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, #ifdef CONFIG_IP_MULTICAST pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); - for (psf = pmc->sources; psf; psf = psf->sf_next) + for_each_psf_mclock(pmc, psf) psf->sf_crcount = 0; igmp_ifc_event(pmc->interface); } else if (sf_setstate(pmc) || changerec) { @@ -2104,7 +2149,7 @@ static int ip_mc_add1_src(struct ip_mc_list *pmc, int sfmode, struct ip_sf_list *psf, *psf_prev; psf_prev = NULL; - for (psf = pmc->sources; psf; psf = psf->sf_next) { + for_each_psf_mclock(pmc, psf) { if (psf->sf_inaddr == *psfsrc) break; psf_prev = psf; @@ -2114,12 +2159,12 @@ static int ip_mc_add1_src(struct ip_mc_list *pmc, int sfmode, if (!psf) return -ENOBUFS; psf->sf_inaddr = *psfsrc; - if (psf_prev) { - psf_prev->sf_next = psf; - } else - pmc->sources = psf; + if (psf_prev) + rcu_assign_pointer(psf_prev->sf_next, psf); + else + rcu_assign_pointer(pmc->sources, psf); } - psf->sf_count[sfmode]++; + WRITE_ONCE(psf->sf_count[sfmode], psf->sf_count[sfmode] + 1); if (psf->sf_count[sfmode] == 1) { ip_rt_multicast_event(pmc->interface); } @@ -2132,13 +2177,15 @@ static void sf_markstate(struct ip_mc_list *pmc) struct ip_sf_list *psf; int mca_xcount = pmc->sfcount[MCAST_EXCLUDE]; - for (psf = pmc->sources; psf; psf = psf->sf_next) + for_each_psf_mclock(pmc, psf) { if (pmc->sfcount[MCAST_EXCLUDE]) { psf->sf_oldin = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; - } else + } else { psf->sf_oldin = psf->sf_count[MCAST_INCLUDE] != 0; + } + } } static int sf_setstate(struct ip_mc_list *pmc) @@ -2149,27 +2196,31 @@ static int sf_setstate(struct ip_mc_list *pmc) int new_in, rv; rv = 0; - for (psf = pmc->sources; psf; psf = psf->sf_next) { + for_each_psf_mclock(pmc, psf) { if (pmc->sfcount[MCAST_EXCLUDE]) { new_in = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; - } else + } else { new_in = psf->sf_count[MCAST_INCLUDE] != 0; + } if (new_in) { if (!psf->sf_oldin) { struct ip_sf_list *prev = NULL; - for (dpsf = pmc->tomb; dpsf; dpsf = dpsf->sf_next) { + for_each_psf_tomb(pmc, dpsf) { if (dpsf->sf_inaddr == psf->sf_inaddr) break; prev = dpsf; } if (dpsf) { + struct ip_sf_list *dpsf_next; + + dpsf_next = pmc_dereference(dpsf->sf_next, pmc); if (prev) - prev->sf_next = dpsf->sf_next; + rcu_assign_pointer(prev->sf_next, dpsf_next); else - pmc->tomb = dpsf->sf_next; - kfree(dpsf); + rcu_assign_pointer(pmc->tomb, dpsf_next); + kfree_rcu(dpsf, rcu); } psf->sf_crcount = qrv; rv++; @@ -2181,17 +2232,19 @@ static int sf_setstate(struct ip_mc_list *pmc) * add or update "delete" records if an active filter * is now inactive */ - for (dpsf = pmc->tomb; dpsf; dpsf = dpsf->sf_next) + for_each_psf_tomb(pmc, dpsf) { if (dpsf->sf_inaddr == psf->sf_inaddr) break; + } if (!dpsf) { dpsf = kmalloc_obj(*dpsf, GFP_ATOMIC); if (!dpsf) continue; *dpsf = *psf; /* pmc->lock held by callers */ - dpsf->sf_next = pmc->tomb; - pmc->tomb = dpsf; + rcu_assign_pointer(dpsf->sf_next, + pmc_dereference(pmc->tomb, pmc)); + rcu_assign_pointer(pmc->tomb, dpsf); } dpsf->sf_crcount = qrv; rv++; @@ -2231,7 +2284,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, #endif isexclude = pmc->sfmode == MCAST_EXCLUDE; if (!delta) - pmc->sfcount[sfmode]++; + WRITE_ONCE(pmc->sfcount[sfmode], pmc->sfcount[sfmode] + 1); err = 0; for (i = 0; i < sfcount; i++) { err = ip_mc_add1_src(pmc, sfmode, &psfsrc[i]); @@ -2242,7 +2295,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, int j; if (!delta) - pmc->sfcount[sfmode]--; + WRITE_ONCE(pmc->sfcount[sfmode], pmc->sfcount[sfmode] - 1); for (j = 0; j < i; j++) (void) ip_mc_del1_src(pmc, sfmode, &psfsrc[j]); } else if (isexclude != (pmc->sfcount[MCAST_EXCLUDE] != 0)) { @@ -2262,7 +2315,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); - for (psf = pmc->sources; psf; psf = psf->sf_next) + for_each_psf_mclock(pmc, psf) psf->sf_crcount = 0; igmp_ifc_event(in_dev); } else if (sf_setstate(pmc)) { @@ -2278,13 +2331,13 @@ static void ip_mc_clear_src(struct ip_mc_list *pmc) struct ip_sf_list *tomb, *sources; spin_lock_bh(&pmc->lock); - tomb = pmc->tomb; - pmc->tomb = NULL; - sources = pmc->sources; - pmc->sources = NULL; + tomb = pmc_dereference(pmc->tomb, pmc); + RCU_INIT_POINTER(pmc->tomb, NULL); + sources = pmc_dereference(pmc->sources, pmc); + RCU_INIT_POINTER(pmc->sources, NULL); pmc->sfmode = MCAST_EXCLUDE; - pmc->sfcount[MCAST_INCLUDE] = 0; - pmc->sfcount[MCAST_EXCLUDE] = 1; + WRITE_ONCE(pmc->sfcount[MCAST_INCLUDE], 0); + WRITE_ONCE(pmc->sfcount[MCAST_EXCLUDE], 1); spin_unlock_bh(&pmc->lock); ip_sf_list_clear_all(tomb); @@ -2866,20 +2919,19 @@ int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u rv = 1; } else if (im) { if (src_addr) { - spin_lock_bh(&im->lock); - for (psf = im->sources; psf; psf = psf->sf_next) { + for_each_psf_rcu(im, psf) { if (psf->sf_inaddr == src_addr) break; } if (psf) - rv = psf->sf_count[MCAST_INCLUDE] || - psf->sf_count[MCAST_EXCLUDE] != - im->sfcount[MCAST_EXCLUDE]; + rv = READ_ONCE(psf->sf_count[MCAST_INCLUDE]) || + READ_ONCE(psf->sf_count[MCAST_EXCLUDE]) != + READ_ONCE(im->sfcount[MCAST_EXCLUDE]); else - rv = im->sfcount[MCAST_EXCLUDE] != 0; - spin_unlock_bh(&im->lock); - } else + rv = READ_ONCE(im->sfcount[MCAST_EXCLUDE]) != 0; + } else { rv = 1; /* unspecified source; tentatively allow */ + } } return rv; } @@ -3043,7 +3095,7 @@ static inline struct ip_sf_list *igmp_mcf_get_first(struct seq_file *seq) im = rcu_dereference(idev->mc_list); if (likely(im)) { spin_lock_bh(&im->lock); - psf = im->sources; + psf = pmc_dereference(im->sources, im); if (likely(psf)) { state->im = im; state->idev = idev; @@ -3059,7 +3111,7 @@ static struct ip_sf_list *igmp_mcf_get_next(struct seq_file *seq, struct ip_sf_l { struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); - psf = psf->sf_next; + psf = pmc_dereference(psf->sf_next, state->im); while (!psf) { spin_unlock_bh(&state->im->lock); state->im = state->im->next; @@ -3075,7 +3127,7 @@ static struct ip_sf_list *igmp_mcf_get_next(struct seq_file *seq, struct ip_sf_l state->im = rcu_dereference(state->idev->mc_list); } spin_lock_bh(&state->im->lock); - psf = state->im->sources; + psf = pmc_dereference(state->im->sources, state->im); } out: return psf; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b4237d0e994d..1c867a302444 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3182,8 +3182,7 @@ void __tcp_close(struct sock *sk, long timeout) /* Unread data was tossed, zap the connection. */ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONCLOSE); tcp_set_state(sk, TCP_CLOSE); - tcp_send_active_reset(sk, sk->sk_allocation, - SK_RST_REASON_TCP_ABORT_ON_CLOSE); + tcp_send_active_reset(sk, SK_RST_REASON_TCP_ABORT_ON_CLOSE); } else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) { /* Check zero linger _after_ checking for unread data. */ sk->sk_prot->disconnect(sk, 0); @@ -3257,7 +3256,7 @@ adjudge_to_death: struct tcp_sock *tp = tcp_sk(sk); if (READ_ONCE(tp->linger2) < 0) { tcp_set_state(sk, TCP_CLOSE); - tcp_send_active_reset(sk, GFP_ATOMIC, + tcp_send_active_reset(sk, SK_RST_REASON_TCP_ABORT_ON_LINGER); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONLINGER); @@ -3276,7 +3275,7 @@ adjudge_to_death: if (sk->sk_state != TCP_CLOSE) { if (tcp_check_oom(sk, 0)) { tcp_set_state(sk, TCP_CLOSE); - tcp_send_active_reset(sk, GFP_ATOMIC, + tcp_send_active_reset(sk, SK_RST_REASON_TCP_ABORT_ON_MEMORY); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); @@ -3377,14 +3376,14 @@ int tcp_disconnect(struct sock *sk, int flags) } else if (unlikely(tp->repair)) { WRITE_ONCE(sk->sk_err, ECONNABORTED); } else if (tcp_need_reset(old_state)) { - tcp_send_active_reset(sk, gfp_any(), SK_RST_REASON_TCP_STATE); + tcp_send_active_reset(sk, SK_RST_REASON_TCP_STATE); WRITE_ONCE(sk->sk_err, ECONNRESET); } else if (tp->snd_nxt != tp->write_seq && (1 << old_state) & (TCPF_CLOSING | TCPF_LAST_ACK)) { /* The last check adjusts for discrepancy of Linux wrt. RFC * states */ - tcp_send_active_reset(sk, gfp_any(), + tcp_send_active_reset(sk, SK_RST_REASON_TCP_DISCONNECT_WITH_DATA); WRITE_ONCE(sk->sk_err, ECONNRESET); } else if (old_state == TCP_SYN_SENT) @@ -4562,9 +4561,11 @@ int do_tcp_getsockopt(struct sock *sk, int level, if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; - ca_ops = icsk->icsk_ca_ops; + rcu_read_lock(); + ca_ops = READ_ONCE(icsk->icsk_ca_ops); if (ca_ops && ca_ops->get_info) sz = ca_ops->get_info(sk, ~0U, &attr, &info); + rcu_read_unlock(); len = min_t(unsigned int, len, sz); if (copy_to_sockptr(optlen, &len, sizeof(int))) @@ -4577,16 +4578,24 @@ int do_tcp_getsockopt(struct sock *sk, int level, val = !inet_csk_in_pingpong_mode(sk); break; - case TCP_CONGESTION: + case TCP_CONGESTION: { + char ca_name[TCP_CA_NAME_MAX] = {}; + if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; len = min_t(unsigned int, len, TCP_CA_NAME_MAX); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; - if (copy_to_sockptr(optval, icsk->icsk_ca_ops->name, len)) + + rcu_read_lock(); + memcpy(ca_name, READ_ONCE(icsk->icsk_ca_ops)->name, + sizeof(ca_name)); + rcu_read_unlock(); + + if (copy_to_sockptr(optval, ca_name, len)) return -EFAULT; return 0; - + } case TCP_ULP: if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; @@ -5147,8 +5156,7 @@ int tcp_abort(struct sock *sk, int err) bh_lock_sock(sk); if (tcp_need_reset(sk->sk_state)) - tcp_send_active_reset(sk, GFP_ATOMIC, - SK_RST_REASON_TCP_STATE); + tcp_send_active_reset(sk, SK_RST_REASON_TCP_STATE); tcp_done_with_error(sk, err); bh_unlock_sock(sk); diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index e9f6c77e0631..8e83ef81fc18 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -223,7 +223,7 @@ void tcp_assign_congestion_control(struct sock *sk) ca = rcu_dereference(net->ipv4.tcp_congestion_control); if (unlikely(!bpf_try_module_get(ca, ca->owner))) ca = &tcp_reno; - icsk->icsk_ca_ops = ca; + WRITE_ONCE(icsk->icsk_ca_ops, ca); rcu_read_unlock(); memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); @@ -253,7 +253,7 @@ static void tcp_reinit_congestion_control(struct sock *sk, struct inet_connection_sock *icsk = inet_csk(sk); tcp_cleanup_congestion_control(sk); - icsk->icsk_ca_ops = ca; + WRITE_ONCE(icsk->icsk_ca_ops, ca); icsk->icsk_ca_setsockopt = 1; memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index 274e628e7cf8..5b457f68a581 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -111,7 +111,7 @@ __bpf_kfunc static void dctcp_init(struct sock *sk) /* No ECN support? Fall back to Reno. Also need to clear * ECT from sk since it is set during 3WHS for DCTCP. */ - inet_csk(sk)->icsk_ca_ops = &dctcp_reno; + WRITE_ONCE(inet_csk(sk)->icsk_ca_ops, &dctcp_reno); INET_ECN_dontxmit(sk); } @@ -228,7 +228,7 @@ static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr, if (ext & (1 << (INET_DIAG_DCTCPINFO - 1)) || ext & (1 << (INET_DIAG_VEGASINFO - 1))) { memset(&info->dctcp, 0, sizeof(info->dctcp)); - if (inet_csk(sk)->icsk_ca_ops != &dctcp_reno) { + if (READ_ONCE(inet_csk(sk)->icsk_ca_ops) != &dctcp_reno) { info->dctcp.dctcp_enabled = 1; info->dctcp.dctcp_ce_state = (u16) ca->ce_state; info->dctcp.dctcp_alpha = ca->dctcp_alpha; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index f3fa0b18eda0..0ddfd5af6e58 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -507,7 +507,7 @@ void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst) ca = tcp_ca_find_key(ca_key); if (likely(ca && bpf_try_module_get(ca, ca->owner))) { icsk->icsk_ca_dst_locked = tcp_ca_dst_locked(dst); - icsk->icsk_ca_ops = ca; + WRITE_ONCE(icsk->icsk_ca_ops, ca); ca_got_dst = true; } rcu_read_unlock(); diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 3b1fdcd3cb29..e74d99ca9fac 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -332,6 +332,7 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb, flush |= skb->ip_summed != p->ip_summed; flush |= skb->csum_level != p->csum_level; flush |= NAPI_GRO_CB(p)->count >= 64; + flush |= NAPI_GRO_CB(p)->is_flist != NAPI_GRO_CB(skb)->is_flist; skb_set_network_header(skb, skb_gro_receive_network_offset(skb)); if (flush || skb_gro_receive_list(p, skb)) @@ -395,12 +396,20 @@ static void tcp4_check_fraglist_gro(struct list_head *head, struct sk_buff *skb, struct net *net; int iif, sdif; - if (likely(!(skb->dev->features & NETIF_F_GRO_FRAGLIST))) - return; - p = tcp_gro_lookup(head, th); if (p) { - NAPI_GRO_CB(skb)->is_flist = NAPI_GRO_CB(p)->is_flist; + /* flist GRO applies to consecutive non-GSO skbs */ + if (!skb_is_gso(skb) || !NAPI_GRO_CB(p)->is_flist) { + NAPI_GRO_CB(skb)->is_flist = NAPI_GRO_CB(p)->is_flist; + return; + } + + /* Fall back to the regular GRO path */ + if (NAPI_GRO_CB(p)->count == 1) + NAPI_GRO_CB(p)->is_flist = 0; + + NAPI_GRO_CB(skb)->is_flist = 0; + return; } @@ -410,7 +419,7 @@ static void tcp4_check_fraglist_gro(struct list_head *head, struct sk_buff *skb, sk = __inet_lookup_established(net, iph->saddr, th->source, iph->daddr, ntohs(th->dest), iif, sdif); - NAPI_GRO_CB(skb)->is_flist = !sk; + NAPI_GRO_CB(skb)->is_flist = !sk && !skb_is_gso(skb); if (sk) sock_gen_put(sk); } @@ -430,7 +439,8 @@ struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb) if (!th) goto flush; - tcp4_check_fraglist_gro(head, skb, th); + if (unlikely(skb->dev->features & NETIF_F_GRO_FRAGLIST)) + tcp4_check_fraglist_gro(head, skb, th); return tcp_gro_receive(head, skb, th); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 6f4dca4a4de9..d960e3de7d50 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3849,9 +3849,9 @@ void tcp_send_fin(struct sock *sk) * was unread data in the receive queue. This behavior is recommended * by RFC 2525, section 2.17. -DaveM */ -void tcp_send_active_reset(struct sock *sk, gfp_t priority, - enum sk_rst_reason reason) +void tcp_send_active_reset(struct sock *sk, enum sk_rst_reason reason) { + gfp_t priority = sk_gfp_mask(sk, GFP_ATOMIC | __GFP_NOWARN); struct sk_buff *skb; TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTRSTS); @@ -4092,7 +4092,7 @@ static void tcp_ca_dst_init(struct sock *sk, const struct dst_entry *dst) if (likely(ca && bpf_try_module_get(ca, ca->owner))) { bpf_module_put(icsk->icsk_ca_ops, icsk->icsk_ca_ops->owner); icsk->icsk_ca_dst_locked = tcp_ca_dst_locked(dst); - icsk->icsk_ca_ops = ca; + WRITE_ONCE(icsk->icsk_ca_ops, ca); } rcu_read_unlock(); } diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 1038e7ba9c2e..e56eae4bc341 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -126,7 +126,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset) (!tp->snd_wnd && !tp->packets_out)) do_reset = true; if (do_reset) - tcp_send_active_reset(sk, GFP_ATOMIC, + tcp_send_active_reset(sk, SK_RST_REASON_TCP_ABORT_ON_MEMORY); tcp_done(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); @@ -809,7 +809,7 @@ static void tcp_keepalive_timer(struct timer_list *t) goto out; } } - tcp_send_active_reset(sk, GFP_ATOMIC, SK_RST_REASON_TCP_STATE); + tcp_send_active_reset(sk, SK_RST_REASON_TCP_STATE); goto death; } @@ -836,7 +836,7 @@ static void tcp_keepalive_timer(struct timer_list *t) icsk->icsk_probes_out > 0) || (user_timeout == 0 && icsk->icsk_probes_out >= keepalive_probes(tp))) { - tcp_send_active_reset(sk, GFP_ATOMIC, + tcp_send_active_reset(sk, SK_RST_REASON_TCP_KEEPALIVE_TIMEOUT); tcp_write_err(sk); goto out; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index af9603217444..bb8cfc62cb00 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -900,6 +900,15 @@ out: return sk; } +static void udp_err_update_exception(struct net *net, struct sk_buff *skb, + int type, int code, u32 info) +{ + if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) + ipv4_update_pmtu(skb, net, info, 0, IPPROTO_UDP); + else if (type == ICMP_REDIRECT) + ipv4_redirect(skb, net, 0, IPPROTO_UDP); +} + /* * This routine is called by the ICMP module when it gets some * sort of error condition. If err < 0 then the socket should @@ -923,6 +932,8 @@ int udp_err(struct sk_buff *skb, u32 info) int harderr; int err; + udp_err_update_exception(net, skb, type, code, info); + uh = (struct udphdr *)(skb->data + (iph->ihl << 2)); sk = __udp4_lib_lookup(net, iph->daddr, uh->dest, iph->saddr, uh->source, skb->dev->ifindex, @@ -2166,10 +2177,10 @@ int __udp_disconnect(struct sock *sk, int flags) */ sk->sk_state = TCP_CLOSE; - inet->inet_daddr = 0; + WRITE_ONCE(inet->inet_daddr, 0); inet->inet_dport = 0; sock_rps_reset_rxhash(sk); - sk->sk_bound_dev_if = 0; + WRITE_ONCE(sk->sk_bound_dev_if, 0); if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) { inet_reset_saddr(sk); if (sk->sk_prot->rehash && diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 51941ad656a3..09a4552f7f08 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -445,7 +445,7 @@ looped_back: hdr->segments_left--; addr = hdr->segments + hdr->segments_left; - skb_push(skb, sizeof(struct ipv6hdr)); + skb_push(skb, -skb_network_offset(skb)); if (skb->ip_summed == CHECKSUM_COMPLETE) seg6_update_csum(skb); @@ -469,7 +469,7 @@ looped_back: } ipv6_hdr(skb)->hop_limit--; - skb_pull(skb, sizeof(struct ipv6hdr)); + skb_pull(skb, skb_transport_offset(skb)); goto looped_back; } diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 69c51f1a5bf0..8ebda0b6a78b 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -878,6 +878,7 @@ static int ip6gre_xmit_other(struct sk_buff *skb, struct net_device *dev) static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { + struct ip_tunnel_info *tun_info = NULL; struct ip6_tnl *t = netdev_priv(dev); __be16 payload_protocol; int ret; @@ -888,6 +889,9 @@ static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb, if (!ip6_tnl_xmit_ctl(t, &t->parms.laddr, &t->parms.raddr)) goto tx_err; + if (t->parms.collect_md) + tun_info = skb_tunnel_info_txcheck(skb); + payload_protocol = skb_protocol(skb, true); switch (payload_protocol) { case htons(ETH_P_IP): @@ -907,7 +911,7 @@ static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb, return NETDEV_TX_OK; tx_err: - if (!t->parms.collect_md || !IS_ERR(skb_tunnel_info_txcheck(skb))) + if (!IS_ERR(tun_info)) DEV_STATS_INC(dev, tx_errors); DEV_STATS_INC(dev, tx_dropped); kfree_skb(skb); diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index aaba4c2aae23..ecef55f26189 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -240,7 +240,8 @@ static int __ipv6_sock_mc_join(struct sock *sk, int ifindex, return err; } - mc_lst->next = np->ipv6_mc_list; + rcu_assign_pointer(mc_lst->next, + sock_dereference(np->ipv6_mc_list, sk)); rcu_assign_pointer(np->ipv6_mc_list, mc_lst); return 0; @@ -300,7 +301,8 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) lnk = &mc_lst->next) { if ((ifindex == 0 || mc_lst->ifindex == ifindex) && ipv6_addr_equal(&mc_lst->addr, addr)) { - *lnk = mc_lst->next; + rcu_assign_pointer(*lnk, + sock_dereference(mc_lst->next, sk)); __ipv6_sock_mc_drop(sk, mc_lst); return 0; } @@ -333,7 +335,8 @@ void __ipv6_sock_mc_close(struct sock *sk) struct ipv6_mc_socklist *mc_lst; while ((mc_lst = sock_dereference(np->ipv6_mc_list, sk)) != NULL) { - np->ipv6_mc_list = mc_lst->next; + rcu_assign_pointer(np->ipv6_mc_list, + sock_dereference(mc_lst->next, sk)); __ipv6_sock_mc_drop(sk, mc_lst); } } @@ -355,12 +358,12 @@ int ip6_mc_source(int add, int omode, struct sock *sk, { struct ipv6_pinfo *inet6 = inet6_sk(sk); struct in6_addr *source, *group; + struct ip6_sf_socklist *newpsl, *psl; struct net *net = sock_net(sk); struct ipv6_mc_socklist *pmc; - struct ip6_sf_socklist *psl; struct inet6_dev *idev; int leavegroup = 0; - int i, j, rv; + int i, j; int err; source = &((struct sockaddr_in6 *)&pgsr->gsr_source)->sin6_addr; @@ -409,13 +412,11 @@ int ip6_mc_source(int add, int omode, struct sock *sk, if (!add) { if (!psl) goto done; /* err = -EADDRNOTAVAIL */ - rv = !0; for (i = 0; i < psl->sl_count; i++) { - rv = !ipv6_addr_equal(&psl->sl_addr[i], source); - if (rv == 0) + if (ipv6_addr_equal(&psl->sl_addr[i], source)) break; } - if (rv) /* source not found */ + if (i == psl->sl_count) /* source not found */ goto done; /* err = -EADDRNOTAVAIL */ /* special case - (INCLUDE, empty) == LEAVE_GROUP */ @@ -424,58 +425,74 @@ int ip6_mc_source(int add, int omode, struct sock *sk, goto done; } + atomic_sub(struct_size(psl, sl_addr, psl->sl_max), + &sk->sk_omem_alloc); + + if (psl->sl_count == 1) { + newpsl = NULL; + } else { + newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, + psl->sl_count - 1), + GFP_KERNEL); + if (!newpsl) { + atomic_add(struct_size(psl, sl_addr, psl->sl_max), + &sk->sk_omem_alloc); + err = -ENOBUFS; + goto done; + } + newpsl->sl_max = psl->sl_count - 1; + newpsl->sl_count = psl->sl_count - 1; + for (j = 0; j < i; j++) + newpsl->sl_addr[j] = psl->sl_addr[j]; + for (j = i + 1; j < psl->sl_count; j++) + newpsl->sl_addr[j - 1] = psl->sl_addr[j]; + } + /* update the interface filter */ ip6_mc_del_src(idev, group, omode, 1, source, 1); - for (j = i+1; j < psl->sl_count; j++) - psl->sl_addr[j-1] = psl->sl_addr[j]; - psl->sl_count--; + rcu_assign_pointer(pmc->sflist, newpsl); + kfree_rcu(psl, rcu); err = 0; goto done; } /* else, add a new source to the filter */ - if (psl && psl->sl_count >= sysctl_mld_max_msf) { + if (psl && psl->sl_count >= READ_ONCE(sysctl_mld_max_msf)) { err = -ENOBUFS; goto done; } - if (!psl || psl->sl_count == psl->sl_max) { - struct ip6_sf_socklist *newpsl; - int count = IP6_SFBLOCK; - - if (psl) - count += psl->sl_max; - newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, count), - GFP_KERNEL); - if (!newpsl) { - err = -ENOBUFS; - goto done; - } - newpsl->sl_max = count; - newpsl->sl_count = count - IP6_SFBLOCK; - if (psl) { - for (i = 0; i < psl->sl_count; i++) - newpsl->sl_addr[i] = psl->sl_addr[i]; - atomic_sub(struct_size(psl, sl_addr, psl->sl_max), - &sk->sk_omem_alloc); + if (psl) { + for (i = 0; i < psl->sl_count; i++) { + if (ipv6_addr_equal(&psl->sl_addr[i], source)) + goto done; /* err = -EADDRNOTAVAIL */ } - rcu_assign_pointer(pmc->sflist, newpsl); - kfree_rcu(psl, rcu); - psl = newpsl; } - rv = 1; /* > 0 for insert logic below if sl_count is 0 */ - for (i = 0; i < psl->sl_count; i++) { - rv = !ipv6_addr_equal(&psl->sl_addr[i], source); - if (rv == 0) /* There is an error in the address. */ - goto done; + + i = psl ? psl->sl_count + 1 : 1; + newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, i), + GFP_KERNEL); + if (!newpsl) { + err = -ENOBUFS; + goto done; } - for (j = psl->sl_count-1; j >= i; j--) - psl->sl_addr[j+1] = psl->sl_addr[j]; - psl->sl_addr[i] = *source; - psl->sl_count++; - err = 0; + newpsl->sl_max = i; + newpsl->sl_count = i; + if (psl) { + for (j = 0; j < psl->sl_count; j++) + newpsl->sl_addr[j] = psl->sl_addr[j]; + } + newpsl->sl_addr[i - 1] = *source; + /* update the interface list */ ip6_mc_add_src(idev, group, omode, 1, source, 1); + + if (psl) + atomic_sub(struct_size(psl, sl_addr, psl->sl_max), + &sk->sk_omem_alloc); + rcu_assign_pointer(pmc->sflist, newpsl); + kfree_rcu(psl, rcu); + err = 0; done: mutex_unlock(&idev->mc_lock); in6_dev_put(idev); @@ -784,9 +801,11 @@ static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) if (!pmc) return; if (pmc_prev) - rcu_assign_pointer(pmc_prev->next, pmc->next); + rcu_assign_pointer(pmc_prev->next, + mc_dereference(pmc->next, idev)); else - rcu_assign_pointer(idev->mc_tomb, pmc->next); + rcu_assign_pointer(idev->mc_tomb, + mc_dereference(pmc->next, idev)); im->idev = pmc->idev; if (im->mca_sfmode == MCAST_INCLUDE) { @@ -966,7 +985,7 @@ static int __ipv6_dev_mc_inc(struct net_device *dev, return -ENOMEM; } - rcu_assign_pointer(mc->next, idev->mc_list); + rcu_assign_pointer(mc->next, mc_dereference(idev->mc_list, idev)); rcu_assign_pointer(idev->mc_list, mc); mld_del_delrec(idev, mc); @@ -1000,7 +1019,8 @@ int __ipv6_dev_mc_dec(struct inet6_dev *idev, const struct in6_addr *addr) WRITE_ONCE(ma->mca_users, new_users); if (new_users == 0) { - *map = ma->next; + rcu_assign_pointer(*map, + mc_dereference(ma->next, idev)); igmp6_group_dropped(ma); inet6_ifmcaddr_notify(idev->dev, ma, @@ -2351,14 +2371,18 @@ static int ip6_mc_del1_src(struct ifmcaddr6 *pmc, int sfmode, if (psf->sf_oldin && !(pmc->mca_flags & MAF_NOREPORT) && !mld_in_v1_mode(idev)) { - psf->sf_crcount = idev->mc_qrv; - rcu_assign_pointer(psf->sf_next, - mc_dereference(pmc->mca_tomb, idev)); - rcu_assign_pointer(pmc->mca_tomb, psf); - rv = 1; - } else { - kfree_rcu(psf, rcu); + struct ip6_sf_list *dpsf = kmalloc_obj(*dpsf); + + if (dpsf) { + *dpsf = *psf; + dpsf->sf_crcount = idev->mc_qrv; + rcu_assign_pointer(dpsf->sf_next, + mc_dereference(pmc->mca_tomb, idev)); + rcu_assign_pointer(pmc->mca_tomb, dpsf); + rv = 1; + } } + kfree_rcu(psf, rcu); } return rv; } @@ -2621,7 +2645,7 @@ static void ip6_mc_clear_src(struct ifmcaddr6 *pmc) static void igmp6_join_group(struct ifmcaddr6 *ma) { - unsigned long delay; + unsigned long delay, interval; mc_assert_locked(ma->idev); @@ -2630,13 +2654,17 @@ static void igmp6_join_group(struct ifmcaddr6 *ma) igmp6_send(&ma->mca_addr, ma->idev->dev, ICMPV6_MGM_REPORT); - delay = get_random_u32_below(unsolicited_report_interval(ma->idev)); + interval = unsolicited_report_interval(ma->idev); + delay = interval; if (cancel_delayed_work(&ma->mca_work)) { refcount_dec(&ma->mca_refcnt); delay = ma->mca_work.timer.expires - jiffies; } + if (delay >= interval) + delay = get_random_u32_below(interval); + if (!mod_delayed_work(mld_wq, &ma->mca_work, delay)) refcount_inc(&ma->mca_refcnt); WRITE_ONCE(ma->mca_flags, ma->mca_flags | @@ -3001,7 +3029,7 @@ static int igmp6_mc_seq_show(struct seq_file *seq, void *v) struct ifmcaddr6 *im = (struct ifmcaddr6 *)v; struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq); unsigned int mca_flags = READ_ONCE(im->mca_flags); - unsigned long expires = READ_ONCE(im->mca_work.timer.expires); + long delta = READ_ONCE(im->mca_work.timer.expires) - jiffies; seq_printf(seq, "%-4d %-15s %pi6 %5d %08X %ld\n", @@ -3009,7 +3037,7 @@ static int igmp6_mc_seq_show(struct seq_file *seq, void *v) &im->mca_addr, READ_ONCE(im->mca_users), mca_flags, (mca_flags & MAF_TIMER_RUNNING) ? - jiffies_to_clock_t(expires - jiffies) : 0); + jiffies_delta_to_clock_t(delta) : 0); return 0; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 6a40c5074543..9658939511e0 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3255,7 +3255,7 @@ void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif) void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk) { - ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, + ip6_redirect(skb, sock_net(sk), skb->dev->ifindex, READ_ONCE(sk->sk_mark), sk_uid(sk)); } diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index f2a659cd6183..eec3778855eb 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -26,7 +26,18 @@ static void tcp6_check_fraglist_gro(struct list_head *head, struct sk_buff *skb, p = tcp_gro_lookup(head, th); if (p) { - NAPI_GRO_CB(skb)->is_flist = NAPI_GRO_CB(p)->is_flist; + /* flist GRO applies to consecutive non-GSO skbs */ + if (!skb_is_gso(skb) || !NAPI_GRO_CB(p)->is_flist) { + NAPI_GRO_CB(skb)->is_flist = NAPI_GRO_CB(p)->is_flist; + return; + } + + /* Fall back to the regular GRO path */ + if (NAPI_GRO_CB(p)->count == 1) + NAPI_GRO_CB(p)->is_flist = 0; + + NAPI_GRO_CB(skb)->is_flist = 0; + return; } @@ -36,7 +47,7 @@ static void tcp6_check_fraglist_gro(struct list_head *head, struct sk_buff *skb, sk = __inet6_lookup_established(net, &hdr->saddr, th->source, &hdr->daddr, ntohs(th->dest), iif, sdif); - NAPI_GRO_CB(skb)->is_flist = !sk; + NAPI_GRO_CB(skb)->is_flist = !sk && !skb_is_gso(skb); if (sk) sock_gen_put(sk); #endif /* IS_ENABLED(CONFIG_IPV6) */ diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index fd875908ac0c..93478d1ad576 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -690,6 +690,17 @@ out: return sk; } +static void udpv6_err_update_exception(struct net *net, struct sk_buff *skb, + u8 type, __be32 info) +{ + if (type == ICMPV6_PKT_TOOBIG) + ip6_update_pmtu(skb, net, info, skb->dev->ifindex, 0, + sock_net_uid(net, NULL)); + else if (type == NDISC_REDIRECT) + ip6_redirect(skb, net, skb->dev->ifindex, 0, + sock_net_uid(net, NULL)); +} + static int udpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { @@ -703,6 +714,8 @@ static int udpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, int harderr; int err; + udpv6_err_update_exception(net, skb, type, info); + daddr = seg6_get_daddr(skb, opt) ? : &hdr->daddr; saddr = &hdr->saddr; sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source, diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 4e5cc9da6e06..db261ecd19af 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -210,12 +210,6 @@ static int afiucv_hs_send(struct iucv_message *imsg, struct sock *sock, phs_hdr->flags = flags; if (flags == AF_IUCV_FLAG_SYN) phs_hdr->window = iucv->msglimit; - else if ((flags == AF_IUCV_FLAG_WIN) || !flags) { - confirm_recv = atomic_read(&iucv->msg_recv); - phs_hdr->window = confirm_recv; - if (confirm_recv) - phs_hdr->flags = phs_hdr->flags | AF_IUCV_FLAG_WIN; - } memcpy(phs_hdr->destUserID, iucv->dst_user_id, 8); memcpy(phs_hdr->destAppName, iucv->dst_name, 8); memcpy(phs_hdr->srcUserID, iucv->src_user_id, 8); @@ -250,13 +244,22 @@ static int afiucv_hs_send(struct iucv_message *imsg, struct sock *sock, } skb->protocol = cpu_to_be16(ETH_P_AF_IUCV); + /* Claim the receive credit here, not while building the header: every + * way this frame can be dropped has now been ruled out, so the window + * is zeroed only for as long as the transmit itself takes. + */ + if (flags == AF_IUCV_FLAG_WIN || !flags) { + confirm_recv = atomic_xchg(&iucv->msg_recv, 0); + phs_hdr->window = confirm_recv; + if (confirm_recv) + phs_hdr->flags = phs_hdr->flags | AF_IUCV_FLAG_WIN; + } + atomic_inc(&iucv->skbs_in_xmit); err = dev_queue_xmit(skb); if (net_xmit_eval(err)) { atomic_dec(&iucv->skbs_in_xmit); - } else { - atomic_sub(confirm_recv, &iucv->msg_recv); - WARN_ON(atomic_read(&iucv->msg_recv) < 0); + atomic_add(confirm_recv, &iucv->msg_recv); } return net_xmit_eval(err); @@ -1241,6 +1244,7 @@ static int iucv_sock_recvmsg(struct socket *sock, struct msghdr *msg, struct iucv_sock *iucv = iucv_sk(sk); unsigned int copied, rlen; struct sk_buff *skb, *rskb, *cskb; + bool send_win = false; int err = 0; u32 offset; @@ -1331,16 +1335,20 @@ static int iucv_sock_recvmsg(struct socket *sock, struct msghdr *msg, if (skb_queue_empty(&iucv->backlog_skb_q)) { if (!list_empty(&iucv->message_q.list)) iucv_process_message_q(sk); - if (atomic_read(&iucv->msg_recv) >= - iucv->msglimit / 2) { - err = iucv_send_ctrl(sk, AF_IUCV_FLAG_WIN); - if (err) { - sk->sk_state = IUCV_DISCONN; - sk->sk_state_change(sk); - } - } + if (iucv->transport == AF_IUCV_TRANS_HIPER && + atomic_read(&iucv->msg_recv) >= + iucv->msglimit / 2) + send_win = true; } spin_unlock_bh(&iucv->message_q.lock); + + if (send_win) { + err = iucv_send_ctrl(sk, AF_IUCV_FLAG_WIN); + if (err) { + sk->sk_state = IUCV_DISCONN; + sk->sk_state_change(sk); + } + } } done: diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h index 8f2bff268392..c53aa293a222 100644 --- a/net/mac802154/ieee802154_i.h +++ b/net/mac802154/ieee802154_i.h @@ -76,7 +76,12 @@ struct ieee802154_local { struct work_struct rx_mac_cmd_work; /* Association */ - struct ieee802154_pan_device *assoc_dev; + /* assoc_lock protects assoc_dev_extended_addr, assoc_addr, + * assoc_status, the assoc_done reinit/complete pairing and the + * IEEE802154_IS_ASSOCIATING bit in @ongoing. + */ + spinlock_t assoc_lock; + __le64 assoc_dev_extended_addr; struct completion assoc_done; __le16 assoc_addr; u8 assoc_status; diff --git a/net/mac802154/main.c b/net/mac802154/main.c index ea1efef3572a..63e89bd586e3 100644 --- a/net/mac802154/main.c +++ b/net/mac802154/main.c @@ -104,6 +104,7 @@ ieee802154_alloc_hw(size_t priv_data_len, const struct ieee802154_ops *ops) INIT_WORK(&local->rx_mac_cmd_work, mac802154_rx_mac_cmd_worker); init_completion(&local->assoc_done); + spin_lock_init(&local->assoc_lock); /* init supported flags with 802.15.4 default ranges */ phy->supported.max_minbe = 8; diff --git a/net/mac802154/scan.c b/net/mac802154/scan.c index 005338f89b75..dd156c01ac49 100644 --- a/net/mac802154/scan.c +++ b/net/mac802154/scan.c @@ -536,7 +536,9 @@ int mac802154_perform_association(struct ieee802154_sub_if_data *sdata, struct ieee802154_association_req_frame frame = {}; struct ieee802154_local *local = sdata->local; struct wpan_dev *wpan_dev = &sdata->wpan_dev; + __le16 resp_short_addr; struct sk_buff *skb; + u8 resp_status; int ret; frame.mhr.fc.type = IEEE802154_FC_TYPE_MAC_CMD; @@ -578,9 +580,11 @@ int mac802154_perform_association(struct ieee802154_sub_if_data *sdata, return ret; } - local->assoc_dev = coord; + spin_lock(&local->assoc_lock); reinit_completion(&local->assoc_done); + local->assoc_dev_extended_addr = coord->extended_addr; set_bit(IEEE802154_IS_ASSOCIATING, &local->ongoing); + spin_unlock(&local->assoc_lock); ret = ieee802154_mlme_tx_one_locked(local, sdata, skb); if (ret) { @@ -599,25 +603,37 @@ int mac802154_perform_association(struct ieee802154_sub_if_data *sdata, goto clear_assoc; } - if (local->assoc_status != IEEE802154_ASSOCIATION_SUCCESSFUL) { - if (local->assoc_status == IEEE802154_PAN_AT_CAPACITY) + /* The association is complete: mac802154_process_association_resp() + * cleared the associating bit before waking us, so a second (e.g. + * malicious) ASSOC RESP can no longer pass the recheck and overwrite + * the result. Snapshot assoc_status/assoc_addr under the lock. + */ + spin_lock(&local->assoc_lock); + resp_status = local->assoc_status; + resp_short_addr = local->assoc_addr; + spin_unlock(&local->assoc_lock); + + if (resp_status != IEEE802154_ASSOCIATION_SUCCESSFUL) { + if (resp_status == IEEE802154_PAN_AT_CAPACITY) ret = -ERANGE; else ret = -EPERM; dev_warn(&sdata->dev->dev, "Negative ASSOC RESP received from %8phC: %s\n", &ceaddr, - local->assoc_status == IEEE802154_PAN_AT_CAPACITY ? + resp_status == IEEE802154_PAN_AT_CAPACITY ? "PAN at capacity" : "access denied"); - goto clear_assoc; + return ret; } - ret = 0; - *short_addr = local->assoc_addr; + *short_addr = resp_short_addr; + + return 0; clear_assoc: + spin_lock(&local->assoc_lock); clear_bit(IEEE802154_IS_ASSOCIATING, &local->ongoing); - local->assoc_dev = NULL; + spin_unlock(&local->assoc_lock); return ret; } @@ -639,19 +655,28 @@ int mac802154_process_association_resp(struct ieee802154_sub_if_data *sdata, dest->mode != IEEE802154_EXTENDED_ADDRESSING)) return -EINVAL; - if (unlikely(dest->extended_addr != wpan_dev->extended_addr || - src->extended_addr != local->assoc_dev->extended_addr)) + spin_lock(&local->assoc_lock); + if (unlikely(!test_bit(IEEE802154_IS_ASSOCIATING, &local->ongoing) || + dest->extended_addr != wpan_dev->extended_addr || + src->extended_addr != local->assoc_dev_extended_addr)) { + spin_unlock(&local->assoc_lock); return -ENODEV; + } memcpy(&resp_pl, skb->data, sizeof(resp_pl)); local->assoc_addr = resp_pl.short_addr; local->assoc_status = resp_pl.status; + /* Clear the associating bit before waking the waiter: once the result + * is saved, any subsequent (e.g. malicious) ASSOC RESP must fail the + * test_bit() recheck above and can no longer overwrite the result. + */ + clear_bit(IEEE802154_IS_ASSOCIATING, &local->ongoing); + complete(&local->assoc_done); + spin_unlock(&local->assoc_lock); dev_dbg(&skb->dev->dev, "ASSOC RESP 0x%x received from %8phC, getting short address %04x\n", - local->assoc_status, &deaddr, local->assoc_addr); - - complete(&local->assoc_done); + resp_pl.status, &deaddr, resp_pl.short_addr); return 0; } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index b474d03620a7..e1f08f71cdb1 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3109,8 +3109,7 @@ static void mptcp_do_fastclose(struct sock *sk) */ inet_csk(ssk)->icsk_ack.rcv_mss = TCP_MIN_MSS; - tcp_send_active_reset(ssk, ssk->sk_allocation, - SK_RST_REASON_TCP_ABORT_ON_CLOSE); + tcp_send_active_reset(ssk, SK_RST_REASON_TCP_ABORT_ON_CLOSE); unlock: release_sock(ssk); } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 06a107d4e839..87ccb84e9927 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -690,7 +690,7 @@ mptcp_send_active_reset_reason(struct sock *sk) enum sk_rst_reason reason; reason = sk_rst_convert_mptcp_reason(subflow->reset_reason); - tcp_send_active_reset(sk, GFP_ATOMIC, reason); + tcp_send_active_reset(sk, reason); } /* Made the fwd mem carried by the given skb available to the msk, diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index b22cda322136..76bde7906d49 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2675,7 +2675,8 @@ static int tpacket_parse_header(struct packet_sock *po, void *frame, int size_max, void **data) { union tpacket_uhdr ph; - int tp_len, off; + u32 tp_len; + int off; ph.raw = frame; @@ -2695,7 +2696,7 @@ static int tpacket_parse_header(struct packet_sock *po, void *frame, break; } if (unlikely(tp_len > size_max)) { - pr_err("packet size is too long (%d > %d)\n", tp_len, size_max); + pr_err("packet size is too long (%u > %d)\n", tp_len, size_max); return -EMSGSIZE; } diff --git a/net/qrtr/af_qrtr.c b/net/qrtr/af_qrtr.c index a30fa56e6aa3..78347c937af7 100644 --- a/net/qrtr/af_qrtr.c +++ b/net/qrtr/af_qrtr.c @@ -9,6 +9,7 @@ #include <linux/termios.h> /* For TIOCINQ/OUTQ */ #include <linux/spinlock.h> #include <linux/wait.h> +#include <linux/workqueue.h> #include <net/sock.h> @@ -120,8 +121,10 @@ static DEFINE_XARRAY_ALLOC(qrtr_ports); * @nid: node id * @qrtr_tx_flow: xarray of qrtr_tx_flow, keyed by node << 32 | port * @qrtr_tx_lock: lock for qrtr_tx_flow inserts + * @hello_sent: hello packet send successful * @rx_queue: receive queue * @item: list item for broadcast list + * @say_hello: delayed work for sending hello packet */ struct qrtr_node { struct mutex ep_lock; @@ -132,8 +135,11 @@ struct qrtr_node { struct xarray qrtr_tx_flow; struct mutex qrtr_tx_lock; /* for qrtr_tx_flow */ + bool hello_sent; + struct sk_buff_head rx_queue; struct list_head item; + struct delayed_work say_hello; }; /** @@ -187,6 +193,8 @@ static void __qrtr_node_release(struct kref *kref) list_del(&node->item); mutex_unlock(&qrtr_node_lock); + cancel_delayed_work_sync(&node->say_hello); + skb_queue_purge(&node->rx_queue); /* Free tx flow counters */ @@ -341,6 +349,14 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, size_t len = skb->len; int rc, confirm_rx; + mutex_lock(&node->ep_lock); + if (!node->hello_sent && type != QRTR_TYPE_HELLO) { + mutex_unlock(&node->ep_lock); + kfree_skb(skb); + return -EAGAIN; + } + mutex_unlock(&node->ep_lock); + confirm_rx = qrtr_tx_wait(node, to->sq_node, to->sq_port, type); if (confirm_rx < 0) { kfree_skb(skb); @@ -353,7 +369,7 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, hdr->src_node_id = cpu_to_le32(from->sq_node); hdr->src_port_id = cpu_to_le32(from->sq_port); if (to->sq_port == QRTR_PORT_CTRL) { - hdr->dst_node_id = cpu_to_le32(node->nid); + hdr->dst_node_id = cpu_to_le32(READ_ONCE(node->nid)); hdr->dst_port_id = cpu_to_le32(QRTR_PORT_CTRL); } else { hdr->dst_node_id = cpu_to_le32(to->sq_node); @@ -372,6 +388,8 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, rc = node->ep->xmit(node->ep, skb); else kfree_skb(skb); + if (!rc && type == QRTR_TYPE_HELLO) + node->hello_sent = true; mutex_unlock(&node->ep_lock); } /* Need to ensure that a subsequent message carries the otherwise lost @@ -379,6 +397,9 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, if (rc && confirm_rx) qrtr_tx_flow_failed(node, to->sq_node, to->sq_port); + if (rc == -EAGAIN && type == QRTR_TYPE_HELLO) + schedule_delayed_work(&node->say_hello, msecs_to_jiffies(100)); + return rc; } @@ -416,7 +437,7 @@ static void qrtr_node_assign(struct qrtr_node *node, unsigned int nid) spin_lock_irqsave(&qrtr_nodes_lock, flags); radix_tree_insert(&qrtr_nodes, nid, node); if (node->nid == QRTR_EP_NID_AUTO) - node->nid = nid; + WRITE_ONCE(node->nid, nid); spin_unlock_irqrestore(&qrtr_nodes_lock, flags); } @@ -570,6 +591,38 @@ static struct sk_buff *qrtr_alloc_ctrl_packet(struct qrtr_ctrl_pkt **pkt, return skb; } +static void qrtr_hello_work(struct work_struct *work) +{ + struct sockaddr_qrtr from = {AF_QIPCRTR, 0, QRTR_PORT_CTRL}; + struct sockaddr_qrtr to = {AF_QIPCRTR, 0, QRTR_PORT_CTRL}; + struct qrtr_ctrl_pkt *pkt; + struct qrtr_node *node; + struct qrtr_sock *ctrl; + struct sk_buff *skb; + + node = container_of(to_delayed_work(work), struct qrtr_node, say_hello); + + /* NS must be bound before we can send; retry with backoff if not ready */ + ctrl = qrtr_port_lookup(QRTR_PORT_CTRL); + if (!ctrl) { + schedule_delayed_work(&node->say_hello, msecs_to_jiffies(100)); + return; + } + + skb = qrtr_alloc_ctrl_packet(&pkt, GFP_KERNEL); + if (!skb) { + qrtr_port_put(ctrl); + schedule_delayed_work(&node->say_hello, msecs_to_jiffies(100)); + return; + } + + pkt->cmd = cpu_to_le32(QRTR_TYPE_HELLO); + from.sq_node = qrtr_local_nid; + to.sq_node = node->nid; + qrtr_node_enqueue(node, skb, QRTR_TYPE_HELLO, &from, &to); + qrtr_port_put(ctrl); +} + /** * qrtr_endpoint_register() - register a new endpoint * @ep: endpoint to register @@ -595,6 +648,9 @@ int qrtr_endpoint_register(struct qrtr_endpoint *ep, unsigned int nid) node->nid = QRTR_EP_NID_AUTO; node->ep = ep; + node->hello_sent = false; + INIT_DELAYED_WORK(&node->say_hello, qrtr_hello_work); + xa_init(&node->qrtr_tx_flow); mutex_init(&node->qrtr_tx_lock); @@ -605,6 +661,9 @@ int qrtr_endpoint_register(struct qrtr_endpoint *ep, unsigned int nid) mutex_unlock(&qrtr_node_lock); ep->node = node; + /* Initiate HELLO handshake from the core layer */ + schedule_delayed_work(&node->say_hello, 0); + return 0; } EXPORT_SYMBOL_GPL(qrtr_endpoint_register); @@ -879,6 +938,9 @@ static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb, mutex_lock(&qrtr_node_lock); list_for_each_entry(node, &qrtr_all_nodes, item) { + /* Skip nodes with no assigned node ID yet. */ + if (READ_ONCE(node->nid) == QRTR_EP_NID_AUTO) + continue; skbn = pskb_copy(skb, GFP_KERNEL); if (!skbn) break; diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c index c5e7e01db249..bcb090ee79d4 100644 --- a/net/qrtr/ns.c +++ b/net/qrtr/ns.c @@ -212,6 +212,7 @@ static void lookup_notify(struct sockaddr_qrtr *to, struct qrtr_server *srv, pr_err("failed to send lookup notification\n"); } +/* Announce the list of servers registered on the local node */ static int announce_servers(struct sockaddr_qrtr *sq) { struct qrtr_server *srv; @@ -326,38 +327,8 @@ static int server_del(struct qrtr_node *node, unsigned int port, bool bcast) return 0; } -static int say_hello(struct sockaddr_qrtr *dest) -{ - struct qrtr_ctrl_pkt pkt; - struct msghdr msg = { }; - struct kvec iv; - int ret; - - iv.iov_base = &pkt; - iv.iov_len = sizeof(pkt); - - memset(&pkt, 0, sizeof(pkt)); - pkt.cmd = cpu_to_le32(QRTR_TYPE_HELLO); - - msg.msg_name = (struct sockaddr *)dest; - msg.msg_namelen = sizeof(*dest); - - ret = kernel_sendmsg(qrtr_ns.sock, &msg, &iv, 1, sizeof(pkt)); - if (ret < 0) - pr_err("failed to send hello msg\n"); - - return ret; -} - -/* Announce the list of servers registered on the local node */ static int ctrl_cmd_hello(struct sockaddr_qrtr *sq) { - int ret; - - ret = say_hello(sq); - if (ret < 0) - return ret; - return announce_servers(sq); } @@ -774,10 +745,6 @@ int qrtr_ns_init(void) qrtr_ns.bcast_sq.sq_node = QRTR_NODE_BCAST; qrtr_ns.bcast_sq.sq_port = QRTR_PORT_CTRL; - ret = say_hello(&qrtr_ns.bcast_sq); - if (ret < 0) - goto err_wq; - /* As the qrtr ns socket owner and creator is the same module, we have * to decrease the qrtr module reference count to guarantee that it * remains zero after the ns socket is created, otherwise, executing diff --git a/net/rds/connection.c b/net/rds/connection.c index 7c8ab8e973e1..b6c4beb50eaf 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -106,10 +106,12 @@ static struct rds_connection *rds_conn_lookup(struct net *net, } /* - * This is called by transports as they're bringing down a connection. - * It clears partial message state so that the transport can start sending - * and receiving over this connection again in the future. It is up to - * the transport to have serialized this call with its send and recv. + * This is called by rds_conn_shutdown() once the transport has brought + * a path down. It clears partial message state so that the transport + * can start sending and receiving over this path again in the future. + * The caller owns RDS_IN_XMIT and RDS_RECV_REFILL across this call, + * which is what serializes it against the send and receive-refill + * paths. */ static void rds_conn_path_reset(struct rds_conn_path *cp) { @@ -120,7 +122,16 @@ static void rds_conn_path_reset(struct rds_conn_path *cp) rds_stats_inc(s_conn_reset); rds_send_path_reset(cp); - cp->cp_flags = 0; + + /* Clear the bits the reset is responsible for individually: a + * blanket cp_flags = 0 is a plain store that can clobber a + * concurrent atomic read-modify-write on the same word. + * RDS_IN_XMIT and RDS_RECV_REFILL are held as locks by the + * caller, rds_conn_shutdown(), which releases them once the + * teardown is complete. + */ + clear_bit(RDS_LL_SEND_FULL, &cp->cp_flags); + clear_bit(RDS_RECONNECT_PENDING, &cp->cp_flags); /* Do not clear next_rx_seq here, else we cannot distinguish * retransmitted packets from new packets, and will hand all @@ -406,28 +417,70 @@ void rds_conn_shutdown(struct rds_conn_path *cp) } mutex_unlock(&cp->cp_cm_lock); + /* Quiesce the transmit and receive-refill paths by + * acquiring their bit locks, not merely waiting for + * them to be released: with a plain wait, either path + * can re-take its lock the instant after we sample it + * clear and then run concurrently with the transport + * shutdown and the path reset below. Holding both + * locks across the teardown makes that structurally + * impossible. + */ wait_event(cp->cp_waitq, - !test_bit(RDS_IN_XMIT, &cp->cp_flags)); + !test_and_set_bit_lock(RDS_IN_XMIT, &cp->cp_flags)); wait_event(cp->cp_waitq, - !test_bit(RDS_RECV_REFILL, &cp->cp_flags)); + !test_and_set_bit(RDS_RECV_REFILL, &cp->cp_flags)); conn->c_trans->conn_path_shutdown(cp); rds_conn_path_reset(cp); + /* Release the two locks and wake any waiter (e.g. + * rds_tcp_reset_callbacks()) that blocked on them while + * we held them. The unlock orders the transport's ring + * re-initialization and the path reset above before + * either bit is seen clear. rds_conn_path_reset() leaves + * both bits alone: ownership ends here, not inside the + * reset. + */ + clear_bit_unlock(RDS_IN_XMIT, &cp->cp_flags); + clear_bit_unlock(RDS_RECV_REFILL, &cp->cp_flags); + wake_up_all(&cp->cp_waitq); + if (!rds_conn_path_transition(cp, RDS_CONN_DISCONNECTING, - RDS_CONN_DOWN) && - !rds_conn_path_transition(cp, RDS_CONN_ERROR, RDS_CONN_DOWN)) { - /* This can happen - eg when we're in the middle of tearing - * down the connection, and someone unloads the rds module. - * Quite reproducible with loopback connections. - * Mostly harmless. + /* The path was dropped again while we tore it + * down: by a socket state-change callback in + * irq context on receipt of a FIN, or by an + * accept that claimed the path just before a + * drop put it back to RDS_CONN_ERROR and then + * installed a fresh socket on it. Unless a + * pending destroy suppressed it, the drop also + * queued another shutdown pass, and that pass + * must run, because it is what tears down + * whatever attached to the path after the + * transport shutdown above sampled its state. + * Consuming the RDS_CONN_ERROR here would turn + * that pass into a no-op: leave the state + * alone, and let the pass finish the job. * - * Note that this also happens with rds-tcp because - * we could have triggered rds_conn_path_drop in irq - * mode from rds_tcp_state change on the receipt of - * a FIN, thus we need to recheck for RDS_CONN_ERROR - * here. + * Quiesce the reconnect timer before bailing + * out, though. When a pending destroy did + * suppress the queue, no later pass runs, and + * rds_conn_path_destroy() is about to flush + * cp_down_w and free the path: it must not + * find cp_conn_w still armed. A successor + * pass, when there is one, re-arms the + * reconnect from its own tail. + */ + cancel_delayed_work_sync(&cp->cp_conn_w); + clear_bit(RDS_RECONNECT_PENDING, &cp->cp_flags); + + if (rds_conn_path_state(cp) == RDS_CONN_ERROR) + return; + /* No current cp_state writer leaves a + * DISCONNECTING path in any state but + * RDS_CONN_ERROR; report loudly if one ever + * does. */ rds_conn_path_error(cp, "%s: failed to transition " "to state DOWN, current state " diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index 357128d34a54..bd6cb3ffaa57 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -363,15 +363,14 @@ static int acquire_refill(struct rds_connection *conn) static void release_refill(struct rds_connection *conn) { - clear_bit(RDS_RECV_REFILL, &conn->c_flags); - smp_mb__after_atomic(); + clear_bit_unlock(RDS_RECV_REFILL, &conn->c_flags); /* We don't use wait_on_bit()/wake_up_bit() because our waking is in a * hot path and finding waiters is very rare. We don't want to walk * the system-wide hashed waitqueue buckets in the fast path only to * almost never find waiters. */ - if (waitqueue_active(&conn->c_waitq)) + if (wq_has_sleeper(&conn->c_waitq)) wake_up_all(&conn->c_waitq); } @@ -392,7 +391,9 @@ void rds_ib_recv_refill(struct rds_connection *conn, int prefill, gfp_t gfp) /* the goal here is to just make sure that someone, somewhere * is posting buffers. If we can't get the refill lock, - * let them do their thing + * let them do their thing. The holder may also be + * rds_conn_shutdown() tearing the path down, in which case + * there is nothing to post. */ if (!acquire_refill(conn)) return; diff --git a/net/rds/send.c b/net/rds/send.c index 15a1b97f13e7..1afa981e5c06 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -114,8 +114,13 @@ static void release_in_xmit(struct rds_conn_path *cp) * hot path and finding waiters is very rare. We don't want to walk * the system-wide hashed waitqueue buckets in the fast path only to * almost never find waiters. + * + * wq_has_sleeper() supplies the full barrier that orders the wait + * queue read after the bit clear; clear_bit_unlock() alone is only + * a release and would let this check read a stale empty queue, + * losing the wake-up. */ - if (waitqueue_active(&cp->cp_waitq)) + if (wq_has_sleeper(&cp->cp_waitq)) wake_up_all(&cp->cp_waitq); } @@ -239,8 +244,11 @@ restart: WRITE_ONCE(cp->cp_send_gen, send_gen); /* - * rds_conn_shutdown() sets the conn state and then tests RDS_IN_XMIT, - * we do the opposite to avoid races. + * rds_conn_shutdown() sets the conn state and then acquires + * RDS_IN_XMIT; we take the lock first and then check the state. + * Ownership is decided by the atomic RMW on the cp_flags word: + * if the teardown won the bit we back off here, and if we won + * it the teardown waits until we release it. */ if (!rds_conn_path_up(cp)) { release_in_xmit(cp); diff --git a/net/rds/tcp.c b/net/rds/tcp.c index b263634ac750..774a71f88d37 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -115,46 +115,90 @@ void rds_tcp_restore_callbacks(struct socket *sock, } /* - * rds_tcp_reset_callbacks() switches the to the new sock and - * returns the existing tc->t_sock. + * rds_tcp_reset_callbacks() switches a path to a new socket and + * releases the old one it finds in tc->t_sock, resolving a duelling + * SYN. * - * The only functions that set tc->t_sock are rds_tcp_set_callbacks - * and rds_tcp_reset_callbacks. Send and receive trust that - * it is set. The absence of RDS_CONN_UP bit protects those paths - * from being called while it isn't set. + * tc->t_sock is set by rds_tcp_set_callbacks() and cleared by + * rds_tcp_restore_callbacks(). Four paths write it: the active + * connect in rds_tcp_conn_path_connect(), which sets it and clears it + * again on failure; the accept path in rds_tcp_accept_one(), which + * sets it for a path with no socket yet; the teardown in + * rds_tcp_conn_path_shutdown(), which clears it; and the swap done + * here, which does both. The connect and accept paths are serialized + * against each other by t_conn_path_lock. Send and receive trust + * that it is set: the absence of RDS_CONN_UP protects those paths + * from being called while it isn't, and the swap done here runs under + * RDS_IN_XMIT so that it cannot interleave with a sender already + * inside rds_send_xmit(). */ void rds_tcp_reset_callbacks(struct socket *sock, struct rds_conn_path *cp) { struct rds_tcp_connection *tc = cp->cp_transport_data; - struct socket *osock = tc->t_sock; - - if (!osock) - goto newsock; + struct socket *osock; /* Need to resolve a duelling SYN between peers. * We have an outstanding SYN to this peer, which may * potentially have transitioned to the RDS_CONN_UP state, * so we must quiesce any send threads before resetting - * cp_transport_data. We quiesce these threads by setting - * cp_state to something other than RDS_CONN_UP, and then - * waiting for any existing threads in rds_send_xmit to - * complete release_in_xmit(). (Subsequent threads entering - * rds_send_xmit() will bail on !rds_conn_up(). + * cp_transport_data. Setting cp_state to something other + * than RDS_CONN_UP stops new senders, and owning RDS_IN_XMIT + * excludes any thread already inside rds_send_xmit() - or a + * teardown in rds_conn_shutdown(), which holds the same lock + * for the duration of the transport shutdown - for the whole + * socket swap and the rds_send_path_reset() below. * - * However an incoming syn-ack at this point would end up - * marking the conn as RDS_CONN_UP, and would again permit - * rds_send_xmi() threads through, so ideally we would - * synchronize on RDS_CONN_UP after lock_sock(), but cannot - * do that: waiting on !RDS_IN_XMIT after lock_sock() may - * end up deadlocking with tcp_sendmsg(), and the RDS_IN_XMIT - * would not get set. As a result, we set c_state to - * RDS_CONN_RESETTTING, to ensure that rds_tcp_state_change - * cannot mark rds_conn_path_up() in the window before lock_sock() + * An incoming syn-ack at this point would end up marking the + * conn as RDS_CONN_UP, and would again permit rds_send_xmit() + * threads through, so ideally we would synchronize on + * RDS_CONN_UP after lock_sock(), but cannot do that: acquiring + * RDS_IN_XMIT after lock_sock() may end up deadlocking with + * tcp_sendmsg(), which takes the socket lock while holding + * RDS_IN_XMIT. As a result, we set c_state to + * RDS_CONN_RESETTING, to ensure that rds_tcp_state_change + * cannot mark rds_conn_path_up() in the window before + * lock_sock(). + * + * Only make that transition if the path is still connecting + * (or already resetting from an earlier duel). A path in any + * other state - typically RDS_CONN_DISCONNECTING or + * RDS_CONN_ERROR with a shutdown in flight - is dropped + * instead. That still replaces its state, with RDS_CONN_ERROR, + * and, unless a pending destroy is about to reap the whole + * connection anyway, queues one more shutdown pass. A shutdown + * already in flight leaves that RDS_CONN_ERROR alone when it + * finishes; the queued pass then completes the transition to + * RDS_CONN_DOWN and tears down anything that attached to the + * path in the meantime. + */ + if (!rds_conn_path_transition(cp, RDS_CONN_CONNECTING, + RDS_CONN_RESETTING) && + !rds_conn_path_transition(cp, RDS_CONN_RESETTING, + RDS_CONN_RESETTING)) + rds_conn_path_drop(cp, 0); + wait_event(cp->cp_waitq, + !test_and_set_bit_lock(RDS_IN_XMIT, &cp->cp_flags)); + + /* Read t_sock only while owning RDS_IN_XMIT, never before the + * wait: the teardown in rds_conn_shutdown() releases the old + * socket and clears t_sock, so a pointer sampled earlier can + * be stale by the time we wake up. The teardown holds the + * same lock while it does so, so what we read here cannot + * change under us until we release it. + */ + osock = tc->t_sock; + if (!osock) + goto newsock; + + /* reset receive side state for rds_tcp_data_recv() for osock. + * + * The sync cancels while owning RDS_IN_XMIT rely on cp_wq + * being ordered: a teardown blocked on the bit occupies + * cp_wq's only execution slot, so cp_send_w and cp_recv_w are + * pending at most and the cancels never flush. Nothing here + * may flush or wait on cp_wq itself. */ - atomic_set(&cp->cp_state, RDS_CONN_RESETTING); - wait_event(cp->cp_waitq, !test_bit(RDS_IN_XMIT, &cp->cp_flags)); - /* reset receive side state for rds_tcp_data_recv() for osock */ cancel_delayed_work_sync(&cp->cp_send_w); cancel_delayed_work_sync(&cp->cp_recv_w); lock_sock(osock->sk); @@ -172,6 +216,9 @@ newsock: lock_sock(sock->sk); rds_tcp_set_callbacks(sock, cp); release_sock(sock->sk); + + clear_bit_unlock(RDS_IN_XMIT, &cp->cp_flags); + wake_up_all(&cp->cp_waitq); } /* Add tc to rds_tcp_tc_list and set tc->t_sock. See comments diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index a3db9b057084..13fa60c1985b 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -295,7 +295,11 @@ int rds_tcp_accept_one(struct rds_tcp_net *rtn) if (rs_tcp->t_sock) { /* Duelling SYN has been handled in rds_tcp_accept_one() */ rds_tcp_reset_callbacks(new_sock, cp); - /* rds_connect_path_complete() marks RDS_CONN_UP */ + /* rds_connect_path_complete() marks RDS_CONN_UP, or, + * if a concurrent shutdown won the duel, drops the + * path again and the pass that drop queues reaps the + * socket installed above. + */ rds_connect_path_complete(cp, RDS_CONN_RESETTING); } else { rds_tcp_set_callbacks(new_sock, cp); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index b4415d358c91..37eced84dfa5 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -443,12 +443,21 @@ static size_t tcf_action_shared_attrs_size(const struct tc_action *act) + nla_total_size(IFNAMSIZ) /* TCA_ACT_KIND */ + cookie_len /* TCA_ACT_COOKIE */ + nla_total_size(sizeof(struct nla_bitfield32)) /* TCA_ACT_HW_STATS */ + /* TCA_ACT_USED_HW_STATS */ + + nla_total_size(sizeof(struct nla_bitfield32)) + + nla_total_size(sizeof(u32)) /* TCA_ACT_IN_HW_COUNT */ + nla_total_size(0) /* TCA_ACT_STATS nested */ + nla_total_size(sizeof(struct nla_bitfield32)) /* TCA_ACT_FLAGS */ /* TCA_STATS_BASIC */ + nla_total_size_64bit(sizeof(struct gnet_stats_basic)) - /* TCA_STATS_PKT64 */ - + nla_total_size_64bit(sizeof(u64)) + /* TCA_STATS_BASIC_HW */ + + nla_total_size_64bit(sizeof(struct gnet_stats_basic)) + /* TCA_STATS_PKT64, emitted by both of the basic copies above */ + + 2 * nla_total_size_64bit(sizeof(u64)) + /* TCA_STATS_RATE_EST */ + + nla_total_size_64bit(sizeof(struct gnet_stats_rate_est)) + /* TCA_STATS_RATE_EST64 */ + + nla_total_size_64bit(sizeof(struct gnet_stats_rate_est64)) /* TCA_STATS_QUEUE */ + nla_total_size_64bit(sizeof(struct gnet_stats_queue)) + nla_total_size(0) /* TCA_ACT_OPTIONS nested */ @@ -1688,12 +1697,12 @@ out_nlmsg_trim: static int tcf_get_notify(struct net *net, u32 portid, struct nlmsghdr *n, - struct tc_action *actions[], int event, + struct tc_action *actions[], size_t attr_size, int event, struct netlink_ext_ack *extack) { struct sk_buff *skb; - skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + skb = alloc_skb(max(attr_size, NLMSG_GOODSIZE), GFP_KERNEL); if (!skb) return -ENOBUFS; if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, event, @@ -1858,11 +1867,13 @@ static int tcf_action_delete(struct net *net, struct tc_action *actions[]) static struct sk_buff *tcf_reoffload_del_notify_msg(struct net *net, struct tc_action *action) { - size_t attr_size = tcf_action_fill_size(action); struct tc_action *actions[TCA_ACT_MAX_PRIO] = { [0] = action, }; struct sk_buff *skb; + size_t attr_size; + + attr_size = tcf_action_full_attrs_size(tcf_action_fill_size(action)); skb = alloc_skb(max(attr_size, NLMSG_GOODSIZE), GFP_KERNEL); if (!skb) @@ -1879,15 +1890,18 @@ static struct sk_buff *tcf_reoffload_del_notify_msg(struct net *net, static int tcf_reoffload_del_notify(struct net *net, struct tc_action *action) { const struct tc_action_ops *ops = action->ops; - struct sk_buff *skb; + struct sk_buff *skb = NULL; int ret; - if (!rtnl_notify_needed(net, 0, RTNLGRP_TC)) { - skb = NULL; - } else { + if (rtnl_notify_needed(net, 0, RTNLGRP_TC)) { skb = tcf_reoffload_del_notify_msg(net, action); + /* The action has already lost its hardware instance and is + * skip_sw, so it must be released whether or not the + * notification can be built. Drop the notification rather + * than leave an action behind that processes no packets. + */ if (IS_ERR(skb)) - return PTR_ERR(skb); + skb = NULL; } ret = tcf_idr_release_unsafe(action); @@ -2044,7 +2058,8 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, attr_size = tcf_action_full_attrs_size(attr_size); if (event == RTM_GETACTION) - ret = tcf_get_notify(net, portid, n, actions, event, extack); + ret = tcf_get_notify(net, portid, n, actions, attr_size, event, + extack); else { /* delete */ ret = tcf_del_notify(net, n, actions, portid, attr_size, extack); if (ret) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 0e275b58151c..1cefea571efd 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1703,6 +1703,11 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, return -EINVAL; } nla_opt_msk = nla_next(nla_opt_msk, &msk_depth); + + if (msk_depth && !nla_ok(nla_opt_msk, msk_depth)) { + NL_SET_ERR_MSG(extack, "A mask attribute is invalid"); + return -EINVAL; + } } return 0; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index ac6d0fa5a40e..a3e65c8cf29e 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -370,6 +370,10 @@ static int u32_init(struct tcf_proto *tp) refcount_set(&root_ht->refcnt, 1); root_ht->handle = tp_c ? gen_new_htid(tp_c, root_ht) : id2handle(0); + if (root_ht->handle == 0) { + kfree(root_ht); + return -ENOMEM; + } root_ht->prio = tp->prio; root_ht->is_root = true; idr_init(&root_ht->handle_idr); @@ -695,21 +699,33 @@ out: return ret; } -static u32 gen_new_kid(struct tc_u_hnode *ht, u32 htid) +static u32 gen_new_kid(struct tc_u_hnode *ht, u32 htid, int *err) { u32 index = htid | 0x800; u32 max = htid | 0xFFF; + *err = 0; + if (idr_alloc_u32(&ht->handle_idr, NULL, &index, max, GFP_KERNEL)) { index = htid + 1; - if (idr_alloc_u32(&ht->handle_idr, NULL, &index, max, - GFP_KERNEL)) - index = max; + *err = idr_alloc_u32(&ht->handle_idr, NULL, &index, max, + GFP_KERNEL); + if (*err) + return 0; } return index; } +static int u32_kid_extack(int err, struct netlink_ext_ack *extack) +{ + if (err == -ENOSPC) + NL_SET_ERR_MSG_MOD(extack, "Hash table node ID pool exhausted"); + else + NL_SET_ERR_MSG_MOD(extack, "Failed to allocate node ID"); + return err; +} + static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = { [TCA_U32_CLASSID] = { .type = NLA_U32 }, [TCA_U32_HASH] = { .type = NLA_U32 }, @@ -1079,7 +1095,9 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, * handle which is used to uniquely identify the match entry. */ if (!TC_U32_NODE(handle)) { - handle = gen_new_kid(ht, htid); + handle = gen_new_kid(ht, htid, &err); + if (err) + return u32_kid_extack(err, extack); } else { handle = htid | TC_U32_NODE(handle); err = idr_alloc_u32(&ht->handle_idr, NULL, &handle, @@ -1091,7 +1109,9 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, /* The user did not give us a handle; lets just generate one * from the table's pool of nodeids. */ - handle = gen_new_kid(ht, htid); + handle = gen_new_kid(ht, htid, &err); + if (err) + return u32_kid_extack(err, extack); } if (tb[TCA_U32_SEL] == NULL) { diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index 5f988b3a8814..d666cec6b194 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -212,8 +212,10 @@ new_skb: chunk->chunk_end = ((__u8 *)ch) + SCTP_PAD4(ntohs(ch->length)); skb_pull(chunk->skb, sizeof(*ch)); chunk->subh.v = NULL; /* Subheader is no longer valid. */ - - if (chunk->chunk_end + sizeof(*ch) <= skb_tail_pointer(chunk->skb)) { + if (unlikely(ntohs(ch->length) < sizeof(*ch))) { + chunk->pdiscard = 1; + } else if (chunk->chunk_end + sizeof(*ch) <= + skb_tail_pointer(chunk->skb)) { /* This is not a singleton */ chunk->singleton = 0; } else if (chunk->chunk_end > skb_tail_pointer(chunk->skb)) { diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 236e25abc7a4..84a4c97d0f75 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -3215,6 +3215,9 @@ bool sctp_verify_asconf(const struct sctp_association *asoc, *errp = param.p; switch (param.p->type) { case SCTP_PARAM_ERR_CAUSE: + if (length < sizeof(struct sctp_addip_param) + + sizeof(struct sctp_errhdr)) + return false; break; case SCTP_PARAM_IPV4_ADDRESS: if (length != sizeof(struct sctp_ipv4addr_param)) @@ -3448,20 +3451,15 @@ static __be16 sctp_get_asconf_response(struct sctp_chunk *asconf_ack, case SCTP_PARAM_ERR_CAUSE: length = sizeof(*asconf_ack_param); err_param = (void *)asconf_ack_param + length; - asconf_ack_len -= length; - if (asconf_ack_len > 0) - return err_param->cause; - else - return SCTP_ERROR_INV_PARAM; - break; + return err_param->cause; default: return SCTP_ERROR_INV_PARAM; } } length = ntohs(asconf_ack_param->param_hdr.length); - asconf_ack_param = (void *)asconf_ack_param + length; - asconf_ack_len -= length; + asconf_ack_param = (void *)asconf_ack_param + SCTP_PAD4(length); + asconf_ack_len -= SCTP_PAD4(length); } return err_code; diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 94716406d602..0d99b7e8c082 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -1545,17 +1545,8 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type, timeout = asoc->timeouts[cmd->obj.to]; BUG_ON(!timeout); - /* - * SCTP has a hard time with timer starts. Because we process - * timer starts as side effects, it can be hard to tell if we - * have already started a timer or not, which leads to BUG - * halts when we call add_timer. So here, instead of just starting - * a timer, if the timer is already started, and just mod - * the timer with the shorter of the two expiration times - */ - if (!timer_pending(timer)) + if (!timer_reduce(timer, jiffies + timeout)) sctp_association_hold(asoc); - timer_reduce(timer, jiffies + timeout); break; case SCTP_CMD_TIMER_RESTART: diff --git a/net/tipc/link.c b/net/tipc/link.c index 49dfc098d89b..6427c69f8929 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -504,7 +504,7 @@ bool tipc_link_create(struct net *net, char *if_name, int bearer_id, snprintf(l->name, sizeof(l->name), "%s:%s-%s:unknown", self_str, if_name, peer_str); - strcpy(l->if_name, if_name); + strscpy(l->if_name, if_name); l->addr = peer; l->peer_caps = peer_caps; l->net = net; @@ -574,7 +574,7 @@ bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer, u8 *peer_id, snprintf(l->name, sizeof(l->name), "%s:%s", tipc_bclink_name, peer_str); } else { - strcpy(l->name, tipc_bclink_name); + strscpy(l->name, tipc_bclink_name); } trace_tipc_link_reset(l, TIPC_DUMP_ALL, "bclink created!"); tipc_link_reset(l); @@ -1898,7 +1898,7 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, msg_set_dest_session(hdr, l->peer_session); } msg_set_max_pkt(hdr, l->advertised_mtu); - strcpy(data, l->if_name); + memcpy(data, l->if_name, TIPC_MAX_IF_NAME); msg_set_size(hdr, INT_H_SIZE + TIPC_MAX_IF_NAME); skb_trim(skb, INT_H_SIZE + TIPC_MAX_IF_NAME); } diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 253c72d1366e..6fda36ab1766 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -763,21 +763,40 @@ struct publication *tipc_nametbl_publish(struct net *net, struct tipc_uaddr *ua, struct tipc_socket_addr *sk, u32 key) { struct name_table *nt = tipc_name_table(net); + u32 max_user_pub = TIPC_MAX_PUBL - 1; struct tipc_net *tn = tipc_net(net); struct publication *p = NULL; struct sk_buff *skb = NULL; + bool protocol_type = false; u32 rc_dests; + if (ua->sr.type == TIPC_NODE_STATE || ua->sr.type == TIPC_LINK_STATE || + ua->sr.type == TIPC_TOP_SRV) + protocol_type = true; + spin_lock_bh(&tn->nametbl_lock); + if (protocol_type) + goto insert; - if (nt->local_publ_count >= TIPC_MAX_PUBL) { - pr_warn("Bind failed, max limit %u reached\n", TIPC_MAX_PUBL); + /* Reserve one entry for node state service type because it has cluster + * scope and it is distributed in bulk. So, the maximum number of user's + * publications is (TIPC_MAX_PUBL - 1). + */ + if (nt->local_publ_count >= max_user_pub) { + pr_warn("Bind failed, max limit %u reached\n", max_user_pub); goto exit; } +insert: p = tipc_nametbl_insert_publ(net, ua, sk, key); if (p) { - nt->local_publ_count++; + /* Not count node state, link state and topology server types + * so that maximum nt->local_publ_count does not prevent + * protocol service types from being inserted into the name + * table. + */ + if (!protocol_type) + nt->local_publ_count++; skb = tipc_named_publish(net, p); } rc_dests = nt->rc_dests; @@ -810,7 +829,10 @@ void tipc_nametbl_withdraw(struct net *net, struct tipc_uaddr *ua, p = tipc_nametbl_remove_publ(net, ua, sk, key); if (p) { - nt->local_publ_count--; + if (p->sr.type != TIPC_NODE_STATE && + p->sr.type != TIPC_LINK_STATE && + p->sr.type != TIPC_TOP_SRV) + nt->local_publ_count--; skb = tipc_named_withdraw(net, p); list_del_init(&p->binding_sock); kfree_rcu(p, rcu); diff --git a/net/tipc/node.c b/net/tipc/node.c index 683a136e53ef..bd91378b7540 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1333,7 +1333,9 @@ static void tipc_node_reset_links(struct tipc_node *n) pr_warn("Resetting all links to %x\n", n->addr); + tipc_node_write_lock(n); trace_tipc_node_reset_links(n, true, " "); + tipc_node_write_unlock_fast(n); for (i = 0; i < MAX_BEARERS; i++) { tipc_node_link_down(n, i, false); } diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index a33b2a2d381d..f840498b58af 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -438,6 +438,38 @@ struct sock *vsock_find_connected_socket(struct sockaddr_vm *src, } EXPORT_SYMBOL_GPL(vsock_find_connected_socket); +/** + * vsock_check_source - validate a packet source against a socket peer + * @vsk: socket receiving the packet + * @transport: transport receiving the packet + * @src: source address from the packet + * + * Return: true if the packet arrived on the socket's assigned transport and + * its source matches the stored peer. Loopback packets are generated + * internally and always use the local CID as their source, including + * connections using a valid CID alias. + * + * The caller must hold the socket lock and must not call this for listening + * sockets, which accept packets from any source and have no assigned + * transport. + */ +bool vsock_check_source(const struct vsock_sock *vsk, + const struct vsock_transport *transport, + const struct sockaddr_vm *src) +{ + if (vsk->transport != transport) + return false; + + if (src->svm_port != vsk->remote_addr.svm_port) + return false; + + if (src->svm_cid == vsk->remote_addr.svm_cid) + return true; + + return transport->get_local_cid() == VMADDR_CID_LOCAL; +} +EXPORT_SYMBOL_GPL(vsock_check_source); + void vsock_remove_sock(struct vsock_sock *vsk) { /* Transport reassignment must not remove the binding. */ diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 88df82364f77..f225f53ed4ba 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -1836,7 +1836,8 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, * lock_sock (note: listener sockets are not assigned to any transport) */ if (sock_flag(sk, SOCK_DONE) || - (sk->sk_state != TCP_LISTEN && vsk->transport != &t->transport)) { + (sk->sk_state != TCP_LISTEN && + !vsock_check_source(vsk, &t->transport, &src))) { (void)virtio_transport_reset_no_sock(t, skb, net); release_sock(sk); sock_put(sk); diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 1c4ee039c166..1f186e8f8364 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -680,11 +680,13 @@ static int vmci_transport_recv_stream_cb(void *data, struct vmci_datagram *dg) struct vmci_transport_packet *pkt; struct vsock_sock *vsk; bool bh_process_pkt; + bool drop_pkt; int err; sk = NULL; err = VMCI_SUCCESS; bh_process_pkt = false; + drop_pkt = false; /* Ignore incoming packets from resources that aren't vsock * implementations. @@ -765,17 +767,29 @@ static int vmci_transport_recv_stream_cb(void *data, struct vmci_datagram *dg) bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { - /* The local context ID may be out of date, update it. */ - vsk->local_addr.svm_cid = dst.svm_cid; + if (sk->sk_state != TCP_LISTEN && + !vsock_check_source(vsk, &vmci_transport, &src)) { + drop_pkt = true; + err = VMCI_ERROR_NO_ACCESS; + } else { + /* The local context ID may be out of date, update it. */ + vsk->local_addr.svm_cid = dst.svm_cid; - if (sk->sk_state == TCP_ESTABLISHED) - vmci_trans(vsk)->notify_ops->handle_notify_pkt( - sk, pkt, true, &dst, &src, - &bh_process_pkt); + if (sk->sk_state == TCP_ESTABLISHED) + vmci_trans(vsk)->notify_ops->handle_notify_pkt(sk, pkt, true, + &dst, &src, + &bh_process_pkt); + } } bh_unlock_sock(sk); + if (drop_pkt) { + if (vmci_transport_send_reset_bh(&dst, &src, pkt) < 0) + pr_err("unable to send reset\n"); + goto out; + } + if (!bh_process_pkt) { struct vmci_transport_recv_pkt_info *recv_pkt_info; @@ -900,6 +914,7 @@ static void vmci_transport_recv_pkt_work(struct work_struct *work) { struct vmci_transport_recv_pkt_info *recv_pkt_info; struct vmci_transport_packet *pkt; + struct sockaddr_vm src; struct sock *sk; recv_pkt_info = @@ -908,6 +923,12 @@ static void vmci_transport_recv_pkt_work(struct work_struct *work) pkt = &recv_pkt_info->pkt; lock_sock(sk); + vsock_addr_init(&src, pkt->dg.src.context, pkt->src_port); + if (sk->sk_state != TCP_LISTEN && + !vsock_check_source(vsock_sk(sk), &vmci_transport, &src)) { + vmci_transport_reply_reset(pkt); + goto out; + } /* The local context ID may be out of date. */ vsock_sk(sk)->local_addr.svm_cid = pkt->dg.dst.context; @@ -937,6 +958,7 @@ static void vmci_transport_recv_pkt_work(struct work_struct *work) break; } +out: release_sock(sk); kfree(recv_pkt_info); /* Release reference obtained in the stream callback when we fetched diff --git a/security/Kconfig.hardening b/security/Kconfig.hardening index 6923036e1a2f..81c81ad983ad 100644 --- a/security/Kconfig.hardening +++ b/security/Kconfig.hardening @@ -278,7 +278,7 @@ config CC_HAS_RANDSTRUCT choice prompt "Randomize layout of sensitive kernel structures" - default RANDSTRUCT_FULL if COMPILE_TEST && (GCC_PLUGINS || CC_HAS_RANDSTRUCT) + default RANDSTRUCT_FULL if !(RUST_IS_AVAILABLE && HAVE_RUST) && COMPILE_TEST && (GCC_PLUGINS || CC_HAS_RANDSTRUCT) default RANDSTRUCT_NONE help If you enable this, the layouts of structures that are entirely diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig index b3a9f86809b0..72654cf797cd 100644 --- a/security/integrity/ima/Kconfig +++ b/security/integrity/ima/Kconfig @@ -46,12 +46,16 @@ config IMA_KEXEC config IMA_MEASURE_PCR_IDX int + prompt "PCR Index for Aggregate" if EXPERT range 8 14 default 10 help IMA_MEASURE_PCR_IDX determines the TPM PCR register index that IMA uses to maintain the integrity aggregate of the - measurement list. If unsure, use the default 10. + measurement list. Most attestation tooling expects PCR 10. + + The default is almost always what you want. Only change this + if you know what you are doing. config IMA_LSM_RULES bool diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c index ced2e131b061..b280488e15fc 100644 --- a/security/integrity/ima/ima_appraise.c +++ b/security/integrity/ima/ima_appraise.c @@ -748,6 +748,8 @@ static int validate_hash_algo(struct dentry *dentry, return -EACCES; path = dentry_path(dentry, pathbuf, PATH_MAX); + if (IS_ERR(path)) + path = NULL; integrity_audit_msg(AUDIT_INTEGRITY_DATA, d_inode(dentry), path, "set_data", errmsg, -EACCES, 0); diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index f79d07bb63c6..68d9a5e6c232 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -165,7 +165,10 @@ static struct ima_rule_entry dont_measure_rules[] __ro_after_init = { {.action = DONT_MEASURE, .fsmagic = CGROUP2_SUPER_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_MEASURE, .fsmagic = NSFS_MAGIC, .flags = IMA_FSMAGIC}, - {.action = DONT_MEASURE, .fsmagic = EFIVARFS_MAGIC, .flags = IMA_FSMAGIC} + {.action = DONT_MEASURE, .fsmagic = EFIVARFS_MAGIC, + .flags = IMA_FSMAGIC}, + {.action = DONT_MEASURE, .fsmagic = CONFIGFS_MAGIC, + .flags = IMA_FSMAGIC} }; static struct ima_rule_entry original_measurement_rules[] __ro_after_init = { @@ -211,6 +214,8 @@ static struct ima_rule_entry default_appraise_rules[] __ro_after_init = { {.action = DONT_APPRAISE, .fsmagic = EFIVARFS_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_APPRAISE, .fsmagic = CGROUP_SUPER_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_APPRAISE, .fsmagic = CGROUP2_SUPER_MAGIC, .flags = IMA_FSMAGIC}, + {.action = DONT_APPRAISE, .fsmagic = CONFIGFS_MAGIC, + .flags = IMA_FSMAGIC}, #ifdef CONFIG_IMA_WRITE_POLICY {.action = APPRAISE, .func = POLICY_CHECK, .flags = IMA_FUNC | IMA_DIGSIG_REQUIRED}, diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 035aaf113d1d..e5e17f100aae 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -7267,24 +7267,6 @@ static int selinux_bpf_prog(struct bpf_prog *prog) BPF__PROG_RUN, NULL); } -static u32 selinux_bpffs_creator_sid(u32 fd) -{ - struct path path; - struct super_block *sb; - struct superblock_security_struct *sbsec; - - CLASS(fd, f)(fd); - - if (fd_empty(f)) - return SECSID_NULL; - - path = fd_file(f)->f_path; - sb = path.dentry->d_sb; - sbsec = selinux_superblock(sb); - - return sbsec->creator_sid; -} - static int selinux_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, struct bpf_token *token, bool kernel) { @@ -7297,7 +7279,7 @@ static int selinux_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, if (!token) ssid = bpfsec->sid; else - ssid = selinux_bpffs_creator_sid(attr->map_token_fd); + ssid = selinux_bpf_token_security(token)->grantor_sid; return avc_has_perm(ssid, bpfsec->sid, SECCLASS_BPF, BPF__MAP_CREATE, NULL); @@ -7315,7 +7297,7 @@ static int selinux_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, if (!token) ssid = bpfsec->sid; else - ssid = selinux_bpffs_creator_sid(attr->prog_token_fd); + ssid = selinux_bpf_token_security(token)->grantor_sid; return avc_has_perm(ssid, bpfsec->sid, SECCLASS_BPF, BPF__PROG_LOAD, NULL); @@ -7329,12 +7311,14 @@ static int selinux_bpf_token_create(struct bpf_token *token, const struct path *path) { struct bpf_security_struct *bpfsec; - u32 sid = selinux_bpffs_creator_sid(attr->token_create.bpffs_fd); + struct superblock_security_struct *sbsec; int err; + sbsec = selinux_superblock(path->dentry->d_sb); + bpfsec = selinux_bpf_token_security(token); bpfsec->sid = current_sid(); - bpfsec->grantor_sid = sid; + bpfsec->grantor_sid = sbsec->creator_sid; bpfsec->perms = 0; /** @@ -7343,15 +7327,15 @@ static int selinux_bpf_token_create(struct bpf_token *token, * in the allowed_cmds bitmap. */ if (bpf_token_cmd(token, BPF_MAP_CREATE)) { - err = avc_has_perm(bpfsec->sid, sid, SECCLASS_BPF, - BPF__MAP_CREATE_AS, NULL); + err = avc_has_perm(bpfsec->sid, bpfsec->grantor_sid, + SECCLASS_BPF, BPF__MAP_CREATE_AS, NULL); if (err) return err; bpfsec->perms |= BPF__MAP_CREATE; } if (bpf_token_cmd(token, BPF_PROG_LOAD)) { - err = avc_has_perm(bpfsec->sid, sid, SECCLASS_BPF, - BPF__PROG_LOAD_AS, NULL); + err = avc_has_perm(bpfsec->sid, bpfsec->grantor_sid, + SECCLASS_BPF, BPF__PROG_LOAD_AS, NULL); if (err) return err; bpfsec->perms |= BPF__PROG_LOAD; diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 4a5057e7629d..62324282fcae 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -1468,6 +1468,8 @@ static int snd_pcm_pre_start(struct snd_pcm_substream *substream, struct snd_pcm_runtime *runtime = substream->runtime; if (runtime->state != SNDRV_PCM_STATE_PREPARED) return -EBADFD; + if (atomic_read(&runtime->buffer_accessing) < 0) + return -EBADFD; /* during hw_params, hw_free or prepare */ if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK && !snd_pcm_playback_data(substream)) return -EPIPE; @@ -4021,20 +4023,33 @@ int snd_pcm_mmap_data(struct snd_pcm_substream *substream, struct file *file, return -EINVAL; } runtime = substream->runtime; - if (runtime->state == SNDRV_PCM_STATE_OPEN) - return -EBADFD; - if (!(runtime->info & SNDRV_PCM_INFO_MMAP)) - return -ENXIO; + /* don't race with buffer reallocation in hw_params/hw_free */ + if (!atomic_inc_unless_negative(&runtime->buffer_accessing)) + return -EBUSY; + if (runtime->state == SNDRV_PCM_STATE_OPEN) { + err = -EBADFD; + goto out; + } + if (!(runtime->info & SNDRV_PCM_INFO_MMAP)) { + err = -ENXIO; + goto out; + } if (runtime->access == SNDRV_PCM_ACCESS_RW_INTERLEAVED || - runtime->access == SNDRV_PCM_ACCESS_RW_NONINTERLEAVED) - return -EINVAL; + runtime->access == SNDRV_PCM_ACCESS_RW_NONINTERLEAVED) { + err = -EINVAL; + goto out; + } size = area->vm_end - area->vm_start; offset = area->vm_pgoff << PAGE_SHIFT; dma_bytes = PAGE_ALIGN(runtime->dma_bytes); - if ((size_t)size > dma_bytes) - return -EINVAL; - if (offset > dma_bytes - size) - return -EINVAL; + if ((size_t)size > dma_bytes) { + err = -EINVAL; + goto out; + } + if (offset > dma_bytes - size) { + err = -EINVAL; + goto out; + } area->vm_ops = &snd_pcm_vm_ops_data; area->vm_private_data = substream; @@ -4044,6 +4059,8 @@ int snd_pcm_mmap_data(struct snd_pcm_substream *substream, struct file *file, err = snd_pcm_lib_default_mmap(substream, area); if (!err) atomic_inc(&substream->mmap_count); +out: + atomic_dec(&runtime->buffer_accessing); return err; } EXPORT_SYMBOL(snd_pcm_mmap_data); diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index 34b4c7d6dbe6..2617bb5b4faf 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -785,7 +785,7 @@ int snd_rawmidi_input_params(struct snd_rawmidi_substream *substream, substream->framing = framing; substream->clock_type = clock_type; } - return 0; + return err; } EXPORT_SYMBOL(snd_rawmidi_input_params); diff --git a/sound/core/ump.c b/sound/core/ump.c index d183c8a000bd..3d1a2ed3b476 100644 --- a/sound/core/ump.c +++ b/sound/core/ump.c @@ -1335,6 +1335,8 @@ static void update_legacy_names(struct snd_ump_endpoint *ump) { struct snd_rawmidi *rmidi = ump->legacy_rmidi; + if (!rmidi) + return; update_legacy_substreams(ump, rmidi, SNDRV_RAWMIDI_STREAM_INPUT); update_legacy_substreams(ump, rmidi, SNDRV_RAWMIDI_STREAM_OUTPUT); } @@ -1343,6 +1345,8 @@ static void ump_legacy_set_rawmidi_name(struct snd_ump_endpoint *ump) { struct snd_rawmidi *rmidi = ump->legacy_rmidi; + if (!rmidi) + return; snprintf(rmidi->name, sizeof(rmidi->name), "%.68s (MIDI 1.0)", ump->core.name); } diff --git a/sound/drivers/dummy.c b/sound/drivers/dummy.c index b908d2564aee..3f6bfee29986 100644 --- a/sound/drivers/dummy.c +++ b/sound/drivers/dummy.c @@ -808,7 +808,7 @@ static int snd_dummy_capsrc_put(struct snd_kcontrol *kcontrol, struct snd_ctl_el left = ucontrol->value.integer.value[0] & 1; right = ucontrol->value.integer.value[1] & 1; guard(spinlock_irq)(&dummy->mixer_lock); - change = dummy->capture_source[addr][0] != left && + change = dummy->capture_source[addr][0] != left || dummy->capture_source[addr][1] != right; dummy->capture_source[addr][0] = left; dummy->capture_source[addr][1] = right; diff --git a/sound/hda/codecs/cirrus/cs420x.c b/sound/hda/codecs/cirrus/cs420x.c index 85c2ecf46d38..6cba01228c27 100644 --- a/sound/hda/codecs/cirrus/cs420x.c +++ b/sound/hda/codecs/cirrus/cs420x.c @@ -571,6 +571,7 @@ static const struct hda_model_fixup cs4208_models[] = { static const struct hda_quirk cs4208_fixup_tbl[] = { SND_PCI_QUIRK_VENDOR(0x106b, "Apple", CS4208_MAC_AUTO), + SND_PCI_QUIRK(0x8086, 0x7270, "MacBookAir 7,2", CS4208_MAC_AUTO), {} /* terminator */ }; @@ -583,6 +584,7 @@ static const struct hda_quirk cs4208_mac_fixup_tbl[] = { SND_PCI_QUIRK(0x106b, 0x7800, "MacPro 6,1", CS4208_MACMINI), SND_PCI_QUIRK(0x106b, 0x7b00, "MacBookPro 12,1", CS4208_MBP11), SND_PCI_QUIRK(0x106b, 0x7f00, "iMac 16,1", CS4208_MBP11), + SND_PCI_QUIRK(0x8086, 0x7270, "MacBookAir 7,2", CS4208_MBA6), {} /* terminator */ }; diff --git a/sound/hda/codecs/conexant.c b/sound/hda/codecs/conexant.c index 7357dc91ac49..9bfdbf5c9032 100644 --- a/sound/hda/codecs/conexant.c +++ b/sound/hda/codecs/conexant.c @@ -249,6 +249,25 @@ static void cx_update_headset_mic_vref(struct hda_codec *codec, struct hda_jack_ } } +#define SN6140_S3_AFG_D0_DELAY_MS 1000 + +static void cx_set_power_state(struct hda_codec *codec, hda_nid_t fg, + unsigned int power_state) +{ + snd_hda_codec_write_sync(codec, fg, 0, AC_VERB_SET_POWER_STATE, power_state); + + /* + * SN6140 may not respond to AFG D0 immediately after S3. + * Wait before the D0 verb so the power-state command itself succeeds. + */ + if (codec->core.vendor_id == 0x14f11f87 && + power_state == AC_PWRST_D0 && + codec->core.dev.power.power_state.event == PM_EVENT_RESUME) + msleep(SN6140_S3_AFG_D0_DELAY_MS); + + snd_hda_codec_set_power_to_all(codec, fg, power_state); +} + static int cx_suspend(struct hda_codec *codec) { cx_auto_shutdown(codec); @@ -1308,6 +1327,7 @@ static const struct hda_codec_ops cx_codec_ops = { .init = cx_init, .unsol_event = snd_hda_jack_unsol_event, .suspend = cx_suspend, + .set_power_state = cx_set_power_state, .check_power_status = snd_hda_gen_check_power_status, .stream_pm = snd_hda_gen_stream_pm, }; diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index e4349743a251..95b40a177d2b 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -2379,6 +2379,33 @@ static void alc_fixup_headset_mode_alc255_no_hp_mic(struct hda_codec *codec, } } +/* + * On the Acer Aspire A515-57G (and possibly other models sharing this + * board), if headphones are already inserted into the combo jack before + * the codec powers up (cold boot), the impedance-based headset-type + * sensing races and misclassifies the jack, driving the wrong output + * configuration (audible as missing center-panned/vocal content). A + * genuine physical unplug/replug after boot fixes it by forcing a fresh + * sense transient. Mirror that here on cold boot only: give the sense + * hardware time to settle, then force a fresh classification. + */ +static void alc_fixup_headset_mode_acer_coldboot(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + struct alc_spec *spec = codec->spec; + + alc_fixup_headset_mode(codec, fix, action); + + if (action == HDA_FIXUP_ACT_INIT && + !is_s3_resume(codec) && !is_s4_resume(codec) && + spec->current_headset_mode != ALC_HEADSET_MODE_UNPLUGGED) { + msleep(500); + spec->current_headset_mode = ALC_HEADSET_MODE_UNKNOWN; + spec->current_headset_type = ALC_HEADSET_TYPE_UNKNOWN; + alc_fixup_headset_mode(codec, fix, action); + } +} + static void alc288_update_headset_jack_cb(struct hda_codec *codec, struct hda_jack_callback *jack) { @@ -4248,6 +4275,7 @@ enum { ALC282_FIXUP_ACER_DISABLE_LINEOUT, ALC255_FIXUP_ACER_LIMIT_INT_MIC_BOOST, ALC256_FIXUP_ACER_HEADSET_MIC, + ALC256_FIXUP_ACER_COLDBOOT, ALC285_FIXUP_IDEAPAD_S740_COEF, ALC285_FIXUP_HP_LIMIT_INT_MIC_BOOST, ALC295_FIXUP_ASUS_DACS, @@ -6311,6 +6339,12 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC }, + [ALC256_FIXUP_ACER_COLDBOOT] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_headset_mode_acer_coldboot, + .chained = true, + .chain_id = ALC256_FIXUP_ACER_SFG16_MICMUTE_LED, + }, [ALC285_FIXUP_IDEAPAD_S740_COEF] = { .type = HDA_FIXUP_FUNC, .v.func = alc285_fixup_ideapad_s740_coef, @@ -7148,13 +7182,14 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x1597, "Acer Nitro 5 AN517-55", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x159e, "Acer Nitro 5 AN515-46", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x160e, "Acer PT316-51S", ALC2XX_FIXUP_HEADSET_MIC), - SND_PCI_QUIRK(0x1025, 0x1616, "Acer Aspire A515-57", ALC256_FIXUP_ACER_SFG16_MICMUTE_LED), + SND_PCI_QUIRK(0x1025, 0x1616, "Acer Aspire A515-57", ALC256_FIXUP_ACER_COLDBOOT), SND_PCI_QUIRK(0x1025, 0x161f, "Acer S40-54", ALC256_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x1640, "Acer Aspire A315-44P", ALC256_FIXUP_ACER_SFG16_MICMUTE_LED), SND_PCI_QUIRK(0x1025, 0x166c, "Acer Predator PH16-71", ALC2XX_FIXUP_HEADSET_MIC), 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), + SND_PCI_QUIRK(0x1025, 0x1731, "Acer Predator PHN16-72", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x173a, "Acer Swift SFG14-73", ALC245_FIXUP_ACER_MICMUTE_LED), SND_PCI_QUIRK(0x1025, 0x1758, "Acer Nitro ANV15-41", ALC245_FIXUP_ACER_MICMUTE_LED), SND_PCI_QUIRK(0x1025, 0x1826, "Acer Helios ZPC", ALC287_FIXUP_PREDATOR_SPK_CS35L41_I2C_2), @@ -8100,6 +8135,7 @@ 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), + SND_PCI_QUIRK(0x17aa, 0x380b, "Lenovo Yoga Slim 9 14ILL10", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), /* Yoga Pro 9 16IMH9 and Legion 7 16ITHG6 share PCI SSID 17aa:3811 * with Legion S7 15IMH05; use codec SSID to distinguish them */ @@ -8287,6 +8323,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1d05, 0x3034, "TongFang X6KK45xU", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1d05, 0x30ba, "TongFang XxAF5xxx", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1d17, 0x3288, "Haier Boyue G42", ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS), + SND_PCI_QUIRK(0x1d19, 0x0006, "VAIO VJS131", ALC233_FIXUP_ASUS_MIC_NO_PRESENCE), 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), diff --git a/sound/hda/core/device.c b/sound/hda/core/device.c index 776d629ba252..a45f61e12c1a 100644 --- a/sound/hda/core/device.c +++ b/sound/hda/core/device.c @@ -404,6 +404,7 @@ static void setup_fg_nodes(struct hdac_device *codec) */ int snd_hdac_refresh_widgets(struct hdac_device *codec) { + hda_nid_t fg = codec->afg ? codec->afg : codec->mfg; hda_nid_t start_nid; int nums, err = 0; @@ -412,10 +413,10 @@ int snd_hdac_refresh_widgets(struct hdac_device *codec) * widgets array. */ guard(mutex)(&codec->widget_lock); - nums = snd_hdac_get_sub_nodes(codec, codec->afg, &start_nid); + nums = snd_hdac_get_sub_nodes(codec, fg, &start_nid); if (!start_nid || nums <= 0 || nums >= 0xff) { dev_err(&codec->dev, "cannot read sub nodes for FG 0x%02x\n", - codec->afg); + fg); return -EINVAL; } diff --git a/sound/parisc/harmony.c b/sound/parisc/harmony.c index fb40476c6c91..a9625aedf2a4 100644 --- a/sound/parisc/harmony.c +++ b/sound/parisc/harmony.c @@ -868,6 +868,9 @@ snd_harmony_create(struct snd_card *card, goto free_and_ret; } + spin_lock_init(&h->mixer_lock); + spin_lock_init(&h->lock); + err = request_irq(padev->irq, snd_harmony_interrupt, 0, "harmony", h); if (err) { @@ -877,9 +880,6 @@ snd_harmony_create(struct snd_card *card, } h->irq = padev->irq; - spin_lock_init(&h->mixer_lock); - spin_lock_init(&h->lock); - err = snd_device_new(card, SNDRV_DEV_LOWLEVEL, h, &ops); if (err < 0) goto free_and_ret; diff --git a/sound/usb/caiaq/audio.c b/sound/usb/caiaq/audio.c index ba3f73455ebe..bb6280aa3533 100644 --- a/sound/usb/caiaq/audio.c +++ b/sound/usb/caiaq/audio.c @@ -828,16 +828,13 @@ int snd_usb_caiaq_audio_init(struct snd_usb_caiaqdev *cdev) cdev->data_urbs_in = alloc_urbs(cdev, SNDRV_PCM_STREAM_CAPTURE, &ret); if (ret < 0) { - kfree(cdev->data_cb_info); - free_urbs(cdev->data_urbs_in); + snd_usb_caiaq_audio_free(cdev); return ret; } cdev->data_urbs_out = alloc_urbs(cdev, SNDRV_PCM_STREAM_PLAYBACK, &ret); if (ret < 0) { - kfree(cdev->data_cb_info); - free_urbs(cdev->data_urbs_in); - free_urbs(cdev->data_urbs_out); + snd_usb_caiaq_audio_free(cdev); return ret; } @@ -858,6 +855,9 @@ void snd_usb_caiaq_audio_free(struct snd_usb_caiaqdev *cdev) dev_dbg(dev, "%s(%p)\n", __func__, cdev); free_urbs(cdev->data_urbs_in); + cdev->data_urbs_in = NULL; free_urbs(cdev->data_urbs_out); + cdev->data_urbs_out = NULL; kfree(cdev->data_cb_info); + cdev->data_cb_info = NULL; } diff --git a/sound/usb/fcp.c b/sound/usb/fcp.c index 5fc2131b4561..68bb7eabf107 100644 --- a/sound/usb/fcp.c +++ b/sound/usb/fcp.c @@ -191,6 +191,10 @@ static int fcp_usb(struct usb_mixer_interface *mixer, u32 opcode, const int max_retries = 5; int err; + CLASS(snd_usb_lock, pm)(mixer->chip); + if (pm.err < 0) + return -EIO; + if (!private->urb) return -ENODEV; @@ -1026,6 +1030,10 @@ static int fcp_init(struct usb_mixer_interface *mixer, struct usb_device *dev = mixer->chip->dev; int err; + CLASS(snd_usb_lock, pm)(mixer->chip); + if (pm.err < 0) + return -EIO; + err = snd_usb_ctl_msg(dev, usb_rcvctrlpipe(dev, 0), FCP_USB_REQ_STEP0, USB_RECIP_INTERFACE | USB_TYPE_CLASS | USB_DIR_IN, diff --git a/sound/usb/midi.c b/sound/usb/midi.c index 8a9bc37f0b6e..7e5b1b13360f 100644 --- a/sound/usb/midi.c +++ b/sound/usb/midi.c @@ -971,6 +971,8 @@ static void snd_usbmidi_us122l_output(struct snd_usb_midi_out_endpoint *ep, default: count = 2; } + if (ep->max_transfer < count) + return; count = snd_rawmidi_transmit(ep->ports[0].substream, urb->transfer_buffer, count); diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c index ace4ccad8f51..69093c666282 100644 --- a/sound/usb/mixer_maps.c +++ b/sound/usb/mixer_maps.c @@ -519,6 +519,19 @@ static const struct usbmix_name_map audient_id14_map[] = { }; /* + * Audient iD24: feature unit 12 ("Speaker Playback Volume") sits in the + * monitor-mixer branch and does not apply volume to all of its channels; + * when userspace adopts it as the master playback volume, the left main + * output stays at 0 dB while the right one is attenuated, producing a + * stereo imbalance. Rename it so that it is not picked up as the + * stream's master volume control. + */ +static const struct usbmix_name_map audient_id24_map[] = { + { 12, "Monitor Mix Playback" }, /* FU, partial channel coverage */ + {} +}; + +/* * Control map entries */ @@ -612,6 +625,11 @@ static const struct usbmix_ctl_map usbmix_ctl_maps[] = { .map = audient_id14_map, }, { + /* Audient iD24 */ + .id = USB_ID(0x2708, 0x000d), + .map = audient_id24_map, + }, + { /* KEF X300A */ .id = USB_ID(0x27ac, 0x1000), .map = scms_usb3318_map, diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c index a1f5592cc5d5..fc622eb95dc5 100644 --- a/sound/usb/mixer_quirks.c +++ b/sound/usb/mixer_quirks.c @@ -3480,6 +3480,10 @@ static int snd_rme_digiface_write_reg(struct snd_kcontrol *kcontrol, int item, u struct usb_device *dev = chip->dev; int err; + CLASS(snd_usb_lock, pm)(chip); + if (pm.err < 0) + return -EIO; + err = snd_usb_ctl_msg(dev, usb_sndctrlpipe(dev, 0), item, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, @@ -3499,6 +3503,10 @@ static int snd_rme_digiface_read_status(struct snd_kcontrol *kcontrol, u32 statu __le32 buf[4] = {}; int err; + CLASS(snd_usb_lock, pm)(chip); + if (pm.err < 0) + return -EIO; + err = snd_usb_ctl_msg(dev, usb_rcvctrlpipe(dev, 0), RME_DIGIFACE_READ_STATUS, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE, diff --git a/sound/usb/mixer_s1810c.c b/sound/usb/mixer_s1810c.c index 2e5a8d37ec57..bdb5e3aaff3b 100644 --- a/sound/usb/mixer_s1810c.c +++ b/sound/usb/mixer_s1810c.c @@ -474,6 +474,10 @@ snd_s1810c_switch_get(struct snd_kcontrol *kctl, u32 state = 0; int ret; + CLASS(snd_usb_lock, pm)(mixer->chip); + if (pm.err < 0) + return -EIO; + guard(mutex)(&private->data_mutex); ret = snd_s1810c_get_switch_state(mixer, kctl, &state); if (ret < 0) @@ -504,6 +508,10 @@ snd_s1810c_switch_set(struct snd_kcontrol *kctl, u32 newval = 0; int ret = 0; + CLASS(snd_usb_lock, pm)(mixer->chip); + if (pm.err < 0) + return -EIO; + guard(mutex)(&private->data_mutex); ret = snd_s1810c_get_switch_state(mixer, kctl, &curval); if (ret < 0) diff --git a/sound/usb/mixer_scarlett.c b/sound/usb/mixer_scarlett.c index 673eb8d8724d..369968565c19 100644 --- a/sound/usb/mixer_scarlett.c +++ b/sound/usb/mixer_scarlett.c @@ -707,6 +707,10 @@ static int scarlett_ctl_meter_get(struct snd_kcontrol *kctl, int idx = snd_usb_ctrl_intf(elem->head.mixer->hostif) | (elem->head.id << 8); int err; + CLASS(snd_usb_lock, pm)(chip); + if (pm.err < 0) + return -EIO; + err = snd_usb_ctl_msg(chip->dev, usb_rcvctrlpipe(chip->dev, 0), UAC2_CS_MEM, diff --git a/sound/usb/mixer_scarlett2.c b/sound/usb/mixer_scarlett2.c index 502854cc9f9f..ed5fe746d438 100644 --- a/sound/usb/mixer_scarlett2.c +++ b/sound/usb/mixer_scarlett2.c @@ -2603,9 +2603,9 @@ static int scarlett2_usb_rx(struct usb_device *dev, int interface, } /* Send a proprietary format request to the Scarlett interface */ -static int scarlett2_usb( - struct usb_mixer_interface *mixer, u32 cmd, - void *req_data, u16 req_size, void *resp_data, u16 resp_size) +static int scarlett2_usb_nopm(struct usb_mixer_interface *mixer, u32 cmd, + void *req_data, u16 req_size, + void *resp_data, u16 resp_size) { struct scarlett2_data *private = mixer->private_data; struct usb_device *dev = mixer->chip->dev; @@ -2713,6 +2713,18 @@ retry: return err; } +static int scarlett2_usb(struct usb_mixer_interface *mixer, u32 cmd, + void *req_data, u16 req_size, + void *resp_data, u16 resp_size) +{ + CLASS(snd_usb_lock, pm)(mixer->chip); + if (pm.err < 0) + return -EIO; + + return scarlett2_usb_nopm(mixer, cmd, req_data, req_size, + resp_data, resp_size); +} + /* Send a USB message to get data; result placed in *buf */ static int scarlett2_usb_get( struct usb_mixer_interface *mixer, @@ -3020,9 +3032,21 @@ static int scarlett2_usb_set_config_buf( /* Send SCARLETT2_USB_DATA_CMD SCARLETT2_USB_CONFIG_SAVE */ static void scarlett2_config_save(struct usb_mixer_interface *mixer) { - int err; + __le32 req = cpu_to_le32(SCARLETT2_USB_CONFIG_SAVE); + int err = scarlett2_usb(mixer, SCARLETT2_USB_DATA_CMD, + &req, sizeof(req), NULL, 0); + + if (err < 0) + usb_audio_err(mixer->chip, "config save failed: %d\n", err); +} + +/* The USB suspend callback must not acquire another PM reference. */ +static void scarlett2_config_save_nopm(struct usb_mixer_interface *mixer) +{ + __le32 req = cpu_to_le32(SCARLETT2_USB_CONFIG_SAVE); + int err = scarlett2_usb_nopm(mixer, SCARLETT2_USB_DATA_CMD, + &req, sizeof(req), NULL, 0); - err = scarlett2_usb_activate_config(mixer, SCARLETT2_USB_CONFIG_SAVE); if (err < 0) usb_audio_err(mixer->chip, "config save failed: %d\n", err); } @@ -8639,7 +8663,7 @@ static void scarlett2_private_suspend(struct usb_mixer_interface *mixer) struct scarlett2_data *private = mixer->private_data; if (cancel_delayed_work_sync(&private->work)) - scarlett2_config_save(private->mixer); + scarlett2_config_save_nopm(private->mixer); scarlett2_cleanup_urb(mixer); } diff --git a/sound/usb/mixer_us16x08.c b/sound/usb/mixer_us16x08.c index ebff185cbd2c..14fb1ad764a7 100644 --- a/sound/usb/mixer_us16x08.c +++ b/sound/usb/mixer_us16x08.c @@ -151,6 +151,9 @@ static const char *const route_names[] = { static int snd_us16x08_recv_urb(struct snd_usb_audio *chip, unsigned char *buf, int size) { + CLASS(snd_usb_lock, pm)(chip); + if (pm.err < 0) + return -EIO; guard(mutex)(&chip->mutex); snd_usb_ctl_msg(chip->dev, @@ -165,6 +168,10 @@ static int snd_us16x08_recv_urb(struct snd_usb_audio *chip, */ static int snd_us16x08_send_urb(struct snd_usb_audio *chip, char *buf, int size) { + CLASS(snd_usb_lock, pm)(chip); + if (pm.err < 0) + return -EIO; + return snd_usb_ctl_msg(chip->dev, usb_sndctrlpipe(chip->dev, 0), SND_US16X08_URB_REQUEST, SND_US16X08_URB_REQUESTTYPE, 0, 0, buf, size); diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h index 979d4cabfaf9..76f5e025e107 100644 --- a/tools/sched_ext/include/scx/common.bpf.h +++ b/tools/sched_ext/include/scx/common.bpf.h @@ -48,6 +48,7 @@ extern int LINUX_KERNEL_VERSION __kconfig; extern const char CONFIG_CC_VERSION_TEXT[64] __kconfig __weak; extern const char CONFIG_LOCALVERSION[64] __kconfig __weak; +extern bool CONFIG_PREEMPT_RCU __kconfig __weak; /* * Earlier versions of clang/pahole lost upper 32bits in 64bit enums which can @@ -97,6 +98,7 @@ s32 scx_bpf_pick_any_cpu_node(const cpumask_t *cpus_allowed, int node, u64 flags s32 scx_bpf_pick_any_cpu(const cpumask_t *cpus_allowed, u64 flags) __ksym; bool scx_bpf_task_running(const struct task_struct *p) __ksym; s32 scx_bpf_task_cpu(const struct task_struct *p) __ksym; +struct rq *scx_bpf_cpu_rq(s32 cpu) __ksym __weak; struct rq *scx_bpf_locked_rq(void) __ksym; struct task_struct *scx_bpf_cpu_curr(s32 cpu) __ksym __weak; struct task_struct *scx_bpf_tid_to_task(u64 tid) __ksym __weak; @@ -528,31 +530,102 @@ static __always_inline const struct cpumask *cast_mask(struct bpf_cpumask *mask) } /* + * True if the non-sleepable BPF trampoline prolog (__bpf_prog_enter) calls + * migrate_disable() for the current task. Recorded once by + * scx_lib_init_probe, an fentry program on bpf_scx_reg() that fires during + * the natural scheduler-attach call chain (auto-attached by scx_ops_attach!). + * + * Defaults to true (conservative). Over-reporting in is_migration_disabled() + * causes local-only dispatch, which is safe. Under-reporting can crash the + * scheduler, so we err high if the probe somehow fails to run. + */ +bool __scx_prolog_disables_migration __weak = true; + +/* + * scx_lib_init_probe - non-sleepable prolog probe. + * + * Attached to bpf_scx_reg(), the .reg callback in bpf_sched_ext_ops + * (kernel/sched/ext.c). The kernel's struct_ops machinery invokes + * bpf_scx_reg when userspace creates the scheduler link, before + * ops.init() fires. Its address is taken in the vtable, so the symbol + * is non-inlinable and has been stable since introduction. + * + * Entering via fentry runs us through __bpf_prog_enter -- the + * non-sleepable prolog that consumers of is_migration_disabled() live + * under. + * + * Loud warning: the prolog adds at most 1 to migration_disabled. + * Reading > 1 means something upstream in the + * bpf_struct_ops_link_create -> bpf_scx_reg path disabled migration + * before the prolog ran, invalidating the probe; audit and adjust. + */ +SEC("fentry/bpf_scx_reg") __weak +int scx_lib_init_probe(void *ctx) +{ + if (bpf_core_field_exists(((struct task_struct *)0)->migration_disabled)) { + const struct task_struct *p = bpf_get_current_task_btf(); + unsigned int md = p->migration_disabled; + + if (md > 1) + bpf_printk("scx_lib_init_probe: unexpected migration_disabled=%u " + "upstream of BPF prolog; probe result unreliable", + md); + + __scx_prolog_disables_migration = md > 0; + } + return 0; +} + +/* * Return true if task @p cannot migrate to a different CPU, false * otherwise. + * + * IMPORTANT: designed for NON-SLEEPABLE BPF contexts only. Sleepable + * contexts (BPF_STRUCT_OPS_SLEEPABLE, SEC("syscall"), + * SEC("fentry.s/...")) enter via __bpf_prog_enter_sleepable() or + * __bpf_prog_enter_sleepable_recur(), both of which unconditionally + * call migrate_disable(); this helper can yield a false negative for + * p == current there, which can crash the scheduler. */ static inline bool is_migration_disabled(const struct task_struct *p) { /* - * Testing p->migration_disabled in a BPF code is tricky because the - * migration is _always_ disabled while running the BPF code. - * The prolog (__bpf_prog_enter) and epilog (__bpf_prog_exit) for BPF - * code execution disable and re-enable the migration of the current - * task, respectively. So, the _current_ task of the sched_ext ops is - * always migration-disabled. Moreover, p->migration_disabled could be - * two or greater when a sched_ext ops BPF code (e.g., ops.tick) is - * executed in the middle of the other BPF code execution. + * Testing p->migration_disabled in BPF is tricky because the BPF prolog + * (__bpf_prog_enter) may call migrate_disable() for the current task, + * making migration_disabled == 1 even for tasks that are not truly + * migration-disabled. + * + * Since commit 8e4f0b1ebcf2 ("bpf: use rcu_read_lock_dont_migrate() for + * trampoline.c"), the BPF prolog calls migrate_disable() only when + * CONFIG_PREEMPT_RCU is enabled. Two fast paths cover the common cases: + * + * 1) CONFIG_PREEMPT_RCU: prolog always calls migrate_disable(), so + * migration_disabled == 1 for the current task is ambiguous. + * Disambiguate by checking p == current. + * + * 2) v6.18+ without CONFIG_PREEMPT_RCU: prolog never calls + * migrate_disable(), so migration_disabled == 1 is unambiguously + * a real migrate_disable() call. * - * Therefore, we should decide that the _current_ task is - * migration-disabled only when its migration_disabled count is greater - * than one. In other words, when p->migration_disabled == 1, there is - * an ambiguity, so we should check if @p is the current task or not. + * A slow path handles pre-v6.18 kernels without CONFIG_PREEMPT_RCU, + * where the prolog historically called migrate_disable() unconditionally + * but a cherry-picked downstream kernel may not. The runtime-probed flag + * __scx_prolog_disables_migration (set by scx_lib_init_probe) distinguishes + * the two cases without relying on the kernel version alone. */ if (bpf_core_field_exists(p->migration_disabled)) { - if (p->migration_disabled == 1) - return bpf_get_current_task_btf() != p; - else - return p->migration_disabled; + if (p->migration_disabled == 1) { + /* Fast path: prolog always disables migration */ + if (CONFIG_PREEMPT_RCU) + return bpf_get_current_task_btf() != p; + /* Fast path: prolog never disables migration */ + if (LINUX_KERNEL_VERSION >= KERNEL_VERSION(6, 18, 0)) + return true; + /* Slow path: pre-v6.18, !PREEMPT_RCU - use runtime flag */ + return __scx_prolog_disables_migration ? + bpf_get_current_task_btf() != p : true; + } + return p->migration_disabled; } return false; } @@ -1021,7 +1094,20 @@ static inline u64 scx_clock_task(u32 cpu) { struct rq___local *rq = get_current_rq(cpu); - /* Equivalent to the kernel's rq_clock_task(). */ + /* + * Equivalent to the kernel's rq_clock_task(): wall-clock time minus + * cumulative IRQ time (CONFIG_IRQ_TIME_ACCOUNTING) and hypervisor + * steal time (CONFIG_PARAVIRT_TIME_ACCOUNTING). Without those configs, + * it equals rq->clock. + * + * Conceptually this clock advances during idle (the idle task counts + * as a running task), but rq->clock_task is only updated on scheduling + * events. With NO_HZ_IDLE (the default), the periodic tick is stopped + * on idle CPUs, so rq->clock_task is not refreshed while a CPU is + * idle. Reading this clock for a remote idle CPU from a BPF timer + * callback returns the value from when the CPU last went idle, making + * the delta over an idle interval effectively zero. + */ return rq ? rq->clock_task : 0; } @@ -1032,9 +1118,23 @@ static inline u64 scx_clock_pelt(u32 cpu) /* * Equivalent to the kernel's rq_clock_pelt(): subtracts * lost_idle_time from clock_pelt to absorb the jump that occurs - * when clock_pelt resyncs with clock_task at idle exit. The result - * is a continuous, capacity-invariant clock safe for both task - * execution time stamping and cross-idle measurements. + * when clock_pelt resyncs with clock_task at idle exit. The intent + * is a continuous, capacity- and frequency-invariant clock that is + * frozen during idle, IRQ, and hypervisor steal. + * + * However, like scx_clock_task(), this clock has a stale-read issue + * for remote idle CPUs with NO_HZ_IDLE (the default). clock_pelt + * itself advances at wall-clock rate (hardware-clock based), but + * lost_idle_time is only updated via update_rq_clock_pelt(), which + * requires update_rq_clock() to be called. With NO_HZ_IDLE, the + * periodic tick is stopped on idle CPUs, so lost_idle_time is not + * refreshed during idle. Reading this clock for a remote idle CPU + * from a BPF timer callback therefore returns a value that drifts + * at wall-clock rate -- the same stale behaviour as scx_clock_task(). + * + * Without NO_HZ_IDLE, periodic ticks keep lost_idle_time nearly in + * sync (stale by at most one tick period, ~1 ms), so the result is + * accurate. */ return rq ? (rq->clock_pelt - rq->lost_idle_time) : 0; } diff --git a/tools/sched_ext/include/scx/compat.bpf.h b/tools/sched_ext/include/scx/compat.bpf.h index 3ab642f92c8a..6944221f96cc 100644 --- a/tools/sched_ext/include/scx/compat.bpf.h +++ b/tools/sched_ext/include/scx/compat.bpf.h @@ -92,15 +92,20 @@ int bpf_cpumask_populate(struct bpf_cpumask *dst, void *src, size_t src__sz) __k /* * v6.19: Introduce lockless peek API for user DSQs. + * v7.1: Fix scx_bpf_dsq_peek() spuriously returning NULL on non-empty + * FIFO DSQs (2f2ea7709266). * - * Preserve the following macro until v6.21. + * The kfunc exists from v6.19 but can return NULL for a non-empty FIFO DSQ + * before the v7.1 fix. Require kernel version >= 7.1.0 before calling it; + * otherwise fall through to the bpf_iter_scx_dsq fallback below. */ static inline struct task_struct *__COMPAT_scx_bpf_dsq_peek(u64 dsq_id) { struct task_struct *p = NULL; struct bpf_iter_scx_dsq it; - if (bpf_ksym_exists(scx_bpf_dsq_peek)) + if (bpf_ksym_exists(scx_bpf_dsq_peek) && + LINUX_KERNEL_VERSION >= KERNEL_VERSION(7, 1, 0)) return scx_bpf_dsq_peek(dsq_id); if (!bpf_iter_scx_dsq_new(&it, dsq_id, 0)) p = bpf_iter_scx_dsq_next(&it); @@ -239,6 +244,26 @@ static inline bool __COMPAT_is_enq_cpu_selected(u64 enq_flags) scx_bpf_pick_any_cpu(cpus_allowed, flags)) /* + * v6.18: Add a helper to retrieve the current task running on a CPU. + * + * The kernel tree dropped this helper and scx_bpf_cpu_rq(), but schedulers in + * this tree still support pre-v6.18 kernels where scx_bpf_cpu_curr() doesn't + * resolve and the scx_bpf_cpu_rq() fallback still exists. Keep it until + * pre-v6.18 kernels fall out of the support window. + */ +static inline struct task_struct *__COMPAT_scx_bpf_cpu_curr(int cpu) +{ + struct rq *rq; + + if (bpf_ksym_exists(scx_bpf_cpu_curr)) + return scx_bpf_cpu_curr(cpu); + + rq = scx_bpf_cpu_rq(cpu); + + return rq ? rq->curr : NULL; +} + +/* * v6.19: To work around BPF maximum parameter limit, the following kfuncs are * replaced with variants that pack scalar arguments in a struct. Wrappers are * provided to maintain source compatibility. @@ -379,6 +404,17 @@ static inline void scx_bpf_task_set_dsq_vtime(struct task_struct *p, u64 vtime) } /* + * v7.1: New scx_bpf_dsq_reenq() that allows re-enqueues on more DSQs. This + * will eventually deprecate scx_bpf_reenqueue_local(). + */ +void scx_bpf_dsq_reenq___compat(u64 dsq_id, u64 reenq_flags) __ksym __weak; + +static inline bool __COMPAT_has_generic_reenq(void) +{ + return bpf_ksym_exists(scx_bpf_dsq_reenq___compat); +} + +/* * v6.19: The new void variant can be called from anywhere while the older v1 * variant can only be called from ops.cpu_release(). The double ___ prefixes on * the v2 variant need to be removed once libbpf is updated to ignore ___ prefix @@ -395,21 +431,31 @@ static inline bool __COMPAT_scx_bpf_reenqueue_local_from_anywhere(void) static inline void scx_bpf_reenqueue_local(void) { - if (__COMPAT_scx_bpf_reenqueue_local_from_anywhere()) + if (__COMPAT_has_generic_reenq()) + scx_bpf_dsq_reenq___compat(SCX_DSQ_LOCAL, 0); + else if (__COMPAT_scx_bpf_reenqueue_local_from_anywhere()) scx_bpf_reenqueue_local___v2___compat(); else scx_bpf_reenqueue_local___v1(); } -/* - * v7.1: New scx_bpf_dsq_reenq() that allows re-enqueues on more DSQs. This - * will eventually deprecate scx_bpf_reenqueue_local(). - */ -void scx_bpf_dsq_reenq___compat(u64 dsq_id, u64 reenq_flags) __ksym __weak; - -static inline bool __COMPAT_has_generic_reenq(void) +static inline int scx_bpf_reenqueue_local_from_anywhere(void) { - return bpf_ksym_exists(scx_bpf_dsq_reenq___compat); + /* + * The generic reenq kfunc and the v2 reenqueue-local variant can both be + * called from anywhere; v1 cannot. Test each ksym in its own branch with a + * distinct call: combining them with || would fold into a bitwise OR of the + * two ksym addresses, which the verifier rejects. + */ + if (__COMPAT_has_generic_reenq()) { + scx_bpf_dsq_reenq___compat(SCX_DSQ_LOCAL, 0); + return 0; + } + if (__COMPAT_scx_bpf_reenqueue_local_from_anywhere()) { + scx_bpf_reenqueue_local___v2___compat(); + return 0; + } + return -EOPNOTSUPP; } static inline void scx_bpf_dsq_reenq(u64 dsq_id, u64 reenq_flags) diff --git a/tools/sched_ext/include/scx/compat.h b/tools/sched_ext/include/scx/compat.h index d2e4384df5af..7c12df45fdba 100644 --- a/tools/sched_ext/include/scx/compat.h +++ b/tools/sched_ext/include/scx/compat.h @@ -10,9 +10,14 @@ #include <bpf/btf.h> #include <bpf/libbpf.h> #include <fcntl.h> +#include <stdint.h> +#include <stdio.h> #include <stdlib.h> +#include <string.h> #include <unistd.h> +#include "enums_abi.autogen.h" + struct btf *__COMPAT_vmlinux_btf __attribute__((weak)); static inline void __COMPAT_load_vmlinux_btf(void) @@ -23,6 +28,85 @@ static inline void __COMPAT_load_vmlinux_btf(void) } } +/* + * Recover the true value of a 64-bit enum enumerator whose kernel BTF entry + * was truncated to its low 32 bits. + * + * Kernels whose BTF was generated without BTF_KIND_ENUM64 support encode + * 64-bit enums as 8-byte BTF_KIND_ENUM entries whose enumerator values only + * carry the low 32 bits. This happens with pahole < 1.24, which predates + * ENUM64, and with pahole passing --skip_encoding_btf_enum64 (e.g. Google's + * Container-Optimized OS / GKE kernels deliberately pass it for backward + * compatibility with older BTF consumers). The high bits + * can't be recovered from kernel BTF, so substitute the value from the + * vmlinux.h this tree was built against, cross-checked against the low 32 + * bits the kernel did provide. + * + * Note that this is a best-effort recovery, not a ground truth. The + * substitution assumes the running kernel agrees with this tree's vmlinux.h + * on the high 32 bits, but only the low 32 bits can actually be verified. + * The cross-check is vacuous for enumerators whose value has no low bits + * set (e.g. SCX_DSQ_FLAG_BUILTIN, __SCX_ENQ_INTERNAL_MASK, + * SCX_ENQ_CLEAR_OPSS, SCX_ECODE_*): their lo32 is 0 and matches anything, + * so those substitutions rest entirely on the high bits never moving. An + * enumerator missing from the table (a kernel newer than this tree's + * vmlinux.h, or a stale autogen table) can't be recovered at all. If a + * substitution is ever wrong, the scheduler operates on bogus values (e.g. + * dispatching to nonexistent DSQ ids or silently dropping flags) and can + * wildly malfunction, which is why the mismatch and table-miss paths refuse + * instead of guessing. + */ +static inline bool __COMPAT_recover_truncated_enum64(const char *type, + const char *name, + u32 lo32, u64 *v) +{ + static bool warned; + size_t i; + + for (i = 0; i < sizeof(__scx_enum_abi_vals) / sizeof(__scx_enum_abi_vals[0]); i++) { + const struct __scx_enum_abi_val *e = &__scx_enum_abi_vals[i]; + + if (strcmp(e->type, type) || strcmp(e->name, name)) + continue; + + if (e->val <= (u64)UINT32_MAX) { + *v = lo32; + return true; + } + + if ((u32)e->val != lo32) { + fprintf(stderr, "ERROR: kernel BTF value of %s::%s (0x%x) doesn't match the low 32 bits of the vmlinux.h value (0x%llx); refusing to substitute\n", + type, name, lo32, (unsigned long long)e->val); + return false; + } + + if (!warned) { + fprintf(stderr, + "WARNING: kernel BTF lacks BTF_KIND_ENUM64 encoding (generated by\n" + "WARNING: pahole < 1.24 or with --skip_encoding_btf_enum64), so 64-bit\n" + "WARNING: scx enum values are truncated to their low 32 bits in kernel\n" + "WARNING: BTF. Substituting the full 64-bit values from the vmlinux.h\n" + "WARNING: this binary was built against, cross-checked against the low\n" + "WARNING: 32 bits the kernel does provide. The high 32 bits cannot be\n" + "WARNING: verified: if the running kernel's actual values differ from\n" + "WARNING: the build-time vmlinux.h (e.g. an enum that moved in a newer\n" + "WARNING: kernel), the scheduler will operate on bogus values, such as\n" + "WARNING: dispatching to nonexistent DSQ ids, and can wildly malfunction.\n"); + warned = true; + } + *v = e->val; + return true; + } + + /* + * Unknown enumerator (likely a stale autogen table). Fail + * pessimistically to avoid returning an invalid value. + */ + fprintf(stderr, "ERROR: kernel BTF truncates 64-bit enum %s::%s to 0x%x; 64-bit variant not found in vmlinux.h\n", + type, name, lo32); + return false; +} + static inline bool __COMPAT_read_enum(const char *type, const char *name, u64 *v) { const struct btf_type *t; @@ -46,6 +130,19 @@ static inline bool __COMPAT_read_enum(const char *type, const char *name, u64 *v n = btf__name_by_offset(__COMPAT_vmlinux_btf, e[i].name_off); SCX_BUG_ON(!n, "btf__name_by_offset()"); if (!strcmp(n, name)) { + /* + * Try to recover a 64-bit enum from an 8-byte + * BTF_KIND_ENUM that was encoded without ENUM64 + * support (old pahole or + * --skip_encoding_btf_enum64). Only scx_* + * types are covered by the substitution table; + * non-scx types fall through to the raw value + * so this generic utility keeps working for + * them. + */ + if (t->size == 8 && !strncmp(type, "scx_", 4)) + return __COMPAT_recover_truncated_enum64(type, name, + (u32)e[i].val, v); *v = e[i].val; return true; } diff --git a/tools/sched_ext/include/scx/enum_defs.autogen.h b/tools/sched_ext/include/scx/enum_defs.autogen.h index 19aa1de3e700..63b6b14b19bd 100644 --- a/tools/sched_ext/include/scx/enum_defs.autogen.h +++ b/tools/sched_ext/include/scx/enum_defs.autogen.h @@ -56,6 +56,10 @@ #define HAVE_SCX_DEQ_SLEEP #define HAVE_SCX_DEQ_CORE_SCHED_EXEC #define HAVE_SCX_DEQ_SCHED_CHANGE +#define HAVE_SCX_DSP_NONE +#define HAVE_SCX_DSP_LOCAL +#define HAVE_SCX_DSP_PREV +#define HAVE_SCX_DSP_RETRY #define HAVE_SCX_DSQ_FLAG_BUILTIN #define HAVE_SCX_DSQ_FLAG_LOCAL_ON #define HAVE_SCX_DSQ_INVALID @@ -188,7 +192,6 @@ #define HAVE_SCX_RQ_SUB_IDLE_RENOTIFY #define HAVE_SCX_RQ_ROOT_IDLE_RENOTIFY #define HAVE_SCX_RQ_IN_WAKEUP -#define HAVE_SCX_RQ_IN_BALANCE #define HAVE_SCX_RQ_IN_DISPATCH #define HAVE_SCX_SCHED_PCPU_BYPASSING #define HAVE_SCX_SLICE_OOB_DUR_BITS diff --git a/tools/sched_ext/include/scx/enums_abi.autogen.h b/tools/sched_ext/include/scx/enums_abi.autogen.h new file mode 100644 index 000000000000..d53899764f5a --- /dev/null +++ b/tools/sched_ext/include/scx/enums_abi.autogen.h @@ -0,0 +1,223 @@ +/* + * WARNING: This file is autogenerated from gen_enum_defs.py [1]. + * + * scx enumerator values from the vmlinux.h this tree is built against. + * Used as the substitution source when the running kernel's BTF lacks + * BTF_KIND_ENUM64 encoding and 64-bit enum values are truncated. + * + * [1] https://github.com/sched-ext/scx/blob/main/scripts/gen_enum_defs.py + */ + +#ifndef __ENUMS_ABI_AUTOGEN_H__ +#define __ENUMS_ABI_AUTOGEN_H__ + +struct __scx_enum_abi_val { + const char *type; + const char *name; + u64 val; +}; + +static const struct __scx_enum_abi_val __scx_enum_abi_vals[] + __attribute__((unused)) = { + { "scx_arena_consts", "SCX_ARENA_MIN_ORDER", 0x3LLU }, + { "scx_arena_consts", "SCX_ARENA_GROW_PAGES", 0x4LLU }, + { "scx_cap_flags", "__SCX_CAP_ENQ_IMMED", 0x0LLU }, + { "scx_cap_flags", "__SCX_CAP_ENQ", 0x1LLU }, + { "scx_cap_flags", "__SCX_CAP_PREEMPT", 0x2LLU }, + { "scx_cap_flags", "__SCX_CAP_PERF", 0x3LLU }, + { "scx_cap_flags", "__SCX_NR_CAPS", 0x4LLU }, + { "scx_cap_flags", "__SCX_CAP_ALL", 0xfLLU }, + { "scx_cap_flags", "SCX_CAP_ENQ_IMMED", 0x1LLU }, + { "scx_cap_flags", "SCX_CAP_ENQ", 0x2LLU }, + { "scx_cap_flags", "SCX_CAP_PREEMPT", 0x4LLU }, + { "scx_cap_flags", "SCX_CAP_PERF", 0x8LLU }, + { "scx_cap_flags", "SCX_CAP_BASE", 0x1LLU }, + { "scx_cap_flags", "SCX_CAPS_REENQ_ON_LOSS", 0x3LLU }, + { "scx_cid_consts", "SCX_CID_SHARD_SIZE_DFL", 0x18LLU }, + { "scx_cid_consts", "SCX_CID_SHARD_MAX_CPUS", 0x200LLU }, + { "scx_consts", "SCX_DSP_DFL_MAX_BATCH", 0x20LLU }, + { "scx_consts", "SCX_DSP_MAX_LOOPS", 0x20LLU }, + { "scx_consts", "SCX_WATCHDOG_MAX_TIMEOUT", 0x7530LLU }, + { "scx_consts", "SCX_RESCUE_DFL_BW_PPT", 0x14LLU }, + { "scx_consts", "SCX_RESCUE_MAX_BW_PPT", 0xfaLLU }, + { "scx_consts", "SCX_RESCUE_DISABLE", 0xffffffffLLU }, + { "scx_consts", "SCX_RESCUE_DFL_QUANTUM_US", 0x1388LLU }, + { "scx_consts", "SCX_RESCUE_MIN_QUANTUM_US", 0x3e8LLU }, + { "scx_consts", "SCX_RESCUE_MAX_QUANTUM_US", 0x186a0LLU }, + { "scx_consts", "SCX_RESCUE_MIN_SLICE_US", 0x3e8LLU }, + { "scx_consts", "SCX_RESCUE_OVERLOAD_MULT", 0x10LLU }, + { "scx_consts", "SCX_RESCUE_MIN_OVERLOAD_MS", 0x3e8LLU }, + { "scx_consts", "SCX_RESCUE_MAX_OVERLOAD_MS", 0x3a98LLU }, + { "scx_consts", "SCX_TID_CHUNK", 0x400LLU }, + { "scx_consts", "SCX_EXIT_BT_LEN", 0x40LLU }, + { "scx_consts", "SCX_EXIT_MSG_LEN", 0x400LLU }, + { "scx_consts", "SCX_EXIT_DUMP_DFL_LEN", 0x8000LLU }, + { "scx_consts", "SCX_CPUPERF_ONE", 0x400LLU }, + { "scx_consts", "SCX_TASK_ITER_BATCH", 0x20LLU }, + { "scx_consts", "SCX_BYPASS_HOST_NTH", 0x2LLU }, + { "scx_consts", "SCX_BYPASS_LB_DFL_INTV_US", 0x7a120LLU }, + { "scx_consts", "SCX_BYPASS_LB_DONOR_PCT", 0x7dLLU }, + { "scx_consts", "SCX_BYPASS_LB_MIN_DELTA_DIV", 0x4LLU }, + { "scx_consts", "SCX_BYPASS_LB_BATCH", 0x100LLU }, + { "scx_consts", "SCX_REENQ_MAX_REPEAT", 0x100LLU }, + { "scx_consts", "SCX_SUB_MAX_DEPTH", 0x4LLU }, + { "scx_cpu_preempt_reason", "SCX_CPU_PREEMPT_RT", 0x0LLU }, + { "scx_cpu_preempt_reason", "SCX_CPU_PREEMPT_DL", 0x1LLU }, + { "scx_cpu_preempt_reason", "SCX_CPU_PREEMPT_STOP", 0x2LLU }, + { "scx_cpu_preempt_reason", "SCX_CPU_PREEMPT_UNKNOWN", 0x3LLU }, + { "scx_deq_flags", "SCX_DEQ_SLEEP", 0x1LLU }, + { "scx_deq_flags", "SCX_DEQ_CORE_SCHED_EXEC", 0x100000000LLU }, + { "scx_deq_flags", "SCX_DEQ_SCHED_CHANGE", 0x200000000LLU }, + { "scx_dsp_verdict", "SCX_DSP_NONE", 0x0LLU }, + { "scx_dsp_verdict", "SCX_DSP_LOCAL", 0x1LLU }, + { "scx_dsp_verdict", "SCX_DSP_PREV", 0x2LLU }, + { "scx_dsp_verdict", "SCX_DSP_RETRY", 0x3LLU }, + { "scx_dsq_id_flags", "SCX_DSQ_FLAG_BUILTIN", 0x8000000000000000LLU }, + { "scx_dsq_id_flags", "SCX_DSQ_FLAG_LOCAL_ON", 0x4000000000000000LLU }, + { "scx_dsq_id_flags", "SCX_DSQ_INVALID", 0x8000000000000000LLU }, + { "scx_dsq_id_flags", "SCX_DSQ_GLOBAL", 0x8000000000000001LLU }, + { "scx_dsq_id_flags", "SCX_DSQ_LOCAL", 0x8000000000000002LLU }, + { "scx_dsq_id_flags", "SCX_DSQ_BYPASS", 0x8000000000000003LLU }, + { "scx_dsq_id_flags", "SCX_DSQ_REJECT", 0x8000000000000004LLU }, + { "scx_dsq_id_flags", "SCX_DSQ_RESCUE", 0x8000000000000005LLU }, + { "scx_dsq_id_flags", "SCX_DSQ_LOCAL_ON", 0xc000000000000000LLU }, + { "scx_dsq_id_flags", "SCX_DSQ_LOCAL_CPU_MASK", 0xffffffffLLU }, + { "scx_dsq_iter_flags", "SCX_DSQ_ITER_REV", 0x10000LLU }, + { "scx_dsq_iter_flags", "__SCX_DSQ_ITER_HAS_SLICE", 0x40000000LLU }, + { "scx_dsq_iter_flags", "__SCX_DSQ_ITER_HAS_VTIME", 0x80000000LLU }, + { "scx_dsq_iter_flags", "__SCX_DSQ_ITER_USER_FLAGS", 0x10000LLU }, + { "scx_dsq_iter_flags", "__SCX_DSQ_ITER_ALL_FLAGS", 0xc0010000LLU }, + { "scx_dsq_lnode_flags", "SCX_DSQ_LNODE_ITER_CURSOR", 0x1LLU }, + { "scx_dsq_lnode_flags", "__SCX_DSQ_LNODE_PRIV_SHIFT", 0x10LLU }, + { "scx_enable_state", "SCX_ENABLING", 0x0LLU }, + { "scx_enable_state", "SCX_ENABLED", 0x1LLU }, + { "scx_enable_state", "SCX_DISABLING", 0x2LLU }, + { "scx_enable_state", "SCX_DISABLED", 0x3LLU }, + { "scx_enq_flags", "SCX_ENQ_WAKEUP", 0x1LLU }, + { "scx_enq_flags", "SCX_ENQ_HEAD", 0x10000LLU }, + { "scx_enq_flags", "SCX_ENQ_CPU_SELECTED", 0x100000LLU }, + { "scx_enq_flags", "SCX_ENQ_PREEMPT", 0x100000000LLU }, + { "scx_enq_flags", "SCX_ENQ_IMMED", 0x200000000LLU }, + { "scx_enq_flags", "SCX_ENQ_RESCUE", 0x400000000LLU }, + { "scx_enq_flags", "SCX_ENQ_REENQ", 0x10000000000LLU }, + { "scx_enq_flags", "SCX_ENQ_LAST", 0x20000000000LLU }, + { "scx_enq_flags", "__SCX_ENQ_INTERNAL_MASK", 0xff00000000000000LLU }, + { "scx_enq_flags", "SCX_ENQ_CLEAR_OPSS", 0x100000000000000LLU }, + { "scx_enq_flags", "SCX_ENQ_DSQ_PRIQ", 0x200000000000000LLU }, + { "scx_enq_flags", "SCX_ENQ_NESTED", 0x400000000000000LLU }, + { "scx_enq_flags", "SCX_ENQ_GDSQ_FALLBACK", 0x800000000000000LLU }, + { "scx_enq_flags", "SCX_ENQ_IGNORE_CAPS", 0x1000000000000000LLU }, + { "scx_enq_flags", "SCX_ENQ_APPLY_SLICE", 0x2000000000000000LLU }, + { "scx_enq_flags", "SCX_ENQ_SLICE_DFL", 0x4000000000000000LLU }, + { "scx_ent_dsq_flags", "SCX_TASK_DSQ_ON_PRIQ", 0x1LLU }, + { "scx_ent_flags", "SCX_TASK_QUEUED", 0x1LLU }, + { "scx_ent_flags", "SCX_TASK_IN_CUSTODY", 0x2LLU }, + { "scx_ent_flags", "SCX_TASK_RESET_RUNNABLE_AT", 0x4LLU }, + { "scx_ent_flags", "SCX_TASK_DEQD_FOR_SLEEP", 0x8LLU }, + { "scx_ent_flags", "SCX_TASK_SUB_INIT", 0x10LLU }, + { "scx_ent_flags", "SCX_TASK_IMMED", 0x20LLU }, + { "scx_ent_flags", "SCX_TASK_PROTECTED", 0x40LLU }, + { "scx_ent_flags", "SCX_TASK_STATE_SHIFT", 0x8LLU }, + { "scx_ent_flags", "SCX_TASK_STATE_BITS", 0x3LLU }, + { "scx_ent_flags", "SCX_TASK_STATE_MASK", 0x700LLU }, + { "scx_ent_flags", "SCX_TASK_NONE", 0x0LLU }, + { "scx_ent_flags", "SCX_TASK_INIT_BEGIN", 0x100LLU }, + { "scx_ent_flags", "SCX_TASK_INIT", 0x200LLU }, + { "scx_ent_flags", "SCX_TASK_READY", 0x300LLU }, + { "scx_ent_flags", "SCX_TASK_ENABLED", 0x400LLU }, + { "scx_ent_flags", "SCX_TASK_DEAD", 0x500LLU }, + { "scx_ent_flags", "SCX_TASK_REENQ_REASON_SHIFT", 0xcLLU }, + { "scx_ent_flags", "SCX_TASK_REENQ_REASON_BITS", 0x3LLU }, + { "scx_ent_flags", "SCX_TASK_REENQ_REASON_MASK", 0x7000LLU }, + { "scx_ent_flags", "SCX_TASK_REENQ_NONE", 0x0LLU }, + { "scx_ent_flags", "SCX_TASK_REENQ_KFUNC", 0x1000LLU }, + { "scx_ent_flags", "SCX_TASK_REENQ_IMMED", 0x2000LLU }, + { "scx_ent_flags", "SCX_TASK_REENQ_PREEMPTED", 0x3000LLU }, + { "scx_ent_flags", "SCX_TASK_REENQ_CAP", 0x4000LLU }, + { "scx_ent_flags", "SCX_TASK_CURSOR", 0xffffffff80000000LLU }, + { "scx_exit_code", "SCX_ECODE_RSN_HOTPLUG", 0x100000000LLU }, + { "scx_exit_code", "SCX_ECODE_RSN_CGROUP_OFFLINE", 0x200000000LLU }, + { "scx_exit_code", "SCX_ECODE_ACT_RESTART", 0x1000000000000LLU }, + { "scx_exit_flags", "SCX_EFLAG_INITIALIZED", 0x1LLU }, + { "scx_exit_kind", "SCX_EXIT_NONE", 0x0LLU }, + { "scx_exit_kind", "SCX_EXIT_DONE", 0x1LLU }, + { "scx_exit_kind", "SCX_EXIT_UNREG", 0x40LLU }, + { "scx_exit_kind", "SCX_EXIT_UNREG_BPF", 0x41LLU }, + { "scx_exit_kind", "SCX_EXIT_UNREG_KERN", 0x42LLU }, + { "scx_exit_kind", "SCX_EXIT_SYSRQ", 0x43LLU }, + { "scx_exit_kind", "SCX_EXIT_PARENT", 0x44LLU }, + { "scx_exit_kind", "SCX_EXIT_PARENT_KILL", 0x45LLU }, + { "scx_exit_kind", "SCX_EXIT_ERROR", 0x400LLU }, + { "scx_exit_kind", "SCX_EXIT_ERROR_BPF", 0x401LLU }, + { "scx_exit_kind", "SCX_EXIT_ERROR_STALL", 0x402LLU }, + { "scx_exit_kind", "SCX_EXIT_ERROR_REENQ", 0x403LLU }, + { "scx_exit_kind", "SCX_EXIT_ERROR_RESCUE", 0x404LLU }, + { "scx_kf_allow_flags", "SCX_KF_ALLOW_UNLOCKED", 0x1LLU }, + { "scx_kf_allow_flags", "SCX_KF_ALLOW_INIT_CIDS", 0x2LLU }, + { "scx_kf_allow_flags", "SCX_KF_ALLOW_CPU_RELEASE", 0x4LLU }, + { "scx_kf_allow_flags", "SCX_KF_ALLOW_DISPATCH", 0x8LLU }, + { "scx_kf_allow_flags", "SCX_KF_ALLOW_ENQUEUE", 0x10LLU }, + { "scx_kf_allow_flags", "SCX_KF_ALLOW_SELECT_CPU", 0x20LLU }, + { "scx_kick_flags", "SCX_KICK_IDLE", 0x1LLU }, + { "scx_kick_flags", "SCX_KICK_PREEMPT", 0x2LLU }, + { "scx_kick_flags", "SCX_KICK_WAIT", 0x4LLU }, + { "scx_opi", "SCX_OPI_BEGIN", 0x0LLU }, + { "scx_opi", "SCX_OPI_NORMAL_BEGIN", 0x0LLU }, + { "scx_opi", "SCX_OPI_NORMAL_END", 0x21LLU }, + { "scx_opi", "SCX_OPI_CPU_HOTPLUG_BEGIN", 0x21LLU }, + { "scx_opi", "SCX_OPI_CPU_HOTPLUG_END", 0x23LLU }, + { "scx_opi", "SCX_OPI_END", 0x23LLU }, + { "scx_ops_flags", "SCX_OPS_KEEP_BUILTIN_IDLE", 0x1LLU }, + { "scx_ops_flags", "SCX_OPS_ENQ_LAST", 0x2LLU }, + { "scx_ops_flags", "SCX_OPS_ENQ_EXITING", 0x4LLU }, + { "scx_ops_flags", "SCX_OPS_SWITCH_PARTIAL", 0x8LLU }, + { "scx_ops_flags", "SCX_OPS_ENQ_MIGRATION_DISABLED", 0x10LLU }, + { "scx_ops_flags", "SCX_OPS_ALLOW_QUEUED_WAKEUP", 0x20LLU }, + { "scx_ops_flags", "SCX_OPS_BUILTIN_IDLE_PER_NODE", 0x40LLU }, + { "scx_ops_flags", "SCX_OPS_ALWAYS_ENQ_IMMED", 0x80LLU }, + { "scx_ops_flags", "SCX_OPS_TID_TO_TASK", 0x100LLU }, + { "scx_ops_flags", "SCX_OPS_ALL_FLAGS", 0x1ffLLU }, + { "scx_ops_flags", "__SCX_OPS_INTERNAL_MASK", 0xff00000000000000LLU }, + { "scx_ops_flags", "SCX_OPS_HAS_CPU_PREEMPT", 0x100000000000000LLU }, + { "scx_ops_state", "SCX_OPSS_NONE", 0x0LLU }, + { "scx_ops_state", "SCX_OPSS_QUEUEING", 0x1LLU }, + { "scx_ops_state", "SCX_OPSS_QUEUED", 0x2LLU }, + { "scx_ops_state", "SCX_OPSS_DISPATCHING", 0x3LLU }, + { "scx_ops_state", "SCX_OPSS_QSEQ_SHIFT", 0x2LLU }, + { "scx_pick_idle_cpu_flags", "SCX_PICK_IDLE_CORE", 0x1LLU }, + { "scx_pick_idle_cpu_flags", "SCX_PICK_IDLE_IN_NODE", 0x2LLU }, + { "scx_public_consts", "SCX_OPS_NAME_LEN", 0x80LLU }, + { "scx_public_consts", "SCX_SLICE_DFL", 0x1312d00LLU }, + { "scx_public_consts", "SCX_SLICE_BYPASS", 0x4c4b40LLU }, + { "scx_public_consts", "SCX_SLICE_INF", 0xffffffffffffffffLLU }, + { "scx_reenq_flags", "SCX_REENQ_ANY", 0x1LLU }, + { "scx_reenq_flags", "SCX_REENQ_CAP_REVOKE", 0x2LLU }, + { "scx_reenq_flags", "__SCX_REENQ_FILTER_MASK", 0xffffLLU }, + { "scx_reenq_flags", "__SCX_REENQ_USER_MASK", 0x1LLU }, + { "scx_reenq_flags", "SCX_REENQ_TSR_RQ_OPEN", 0x100000000LLU }, + { "scx_reenq_flags", "SCX_REENQ_TSR_NOT_FIRST", 0x200000000LLU }, + { "scx_reenq_flags", "__SCX_REENQ_TSR_MASK", 0xf00000000LLU }, + { "scx_rq_flags", "SCX_RQ_ONLINE", 0x1LLU }, + { "scx_rq_flags", "SCX_RQ_CAN_STOP_TICK", 0x2LLU }, + { "scx_rq_flags", "SCX_RQ_CLK_VALID", 0x20LLU }, + { "scx_rq_flags", "SCX_RQ_BAL_CB_PENDING", 0x40LLU }, + { "scx_rq_flags", "SCX_RQ_SUB_IDLE_RENOTIFY", 0x80LLU }, + { "scx_rq_flags", "SCX_RQ_ROOT_IDLE_RENOTIFY", 0x100LLU }, + { "scx_rq_flags", "SCX_RQ_IN_WAKEUP", 0x10000LLU }, + { "scx_rq_flags", "SCX_RQ_IN_DISPATCH", 0x20000LLU }, + { "scx_sched_pcpu_flags", "SCX_SCHED_PCPU_BYPASSING", 0x1LLU }, + { "scx_slice_oob_consts", "SCX_SLICE_OOB_DUR_BITS", 0x2bLLU }, + { "scx_slice_oob_consts", "SCX_SLICE_OOB_ID_BITS", 0x14LLU }, + { "scx_slice_oob_consts", "SCX_SLICE_OOB_DUR_MASK", 0x7ffffffffffLLU }, + { "scx_slice_oob_consts", "SCX_SLICE_OOB_ID_SHIFT", 0x2bLLU }, + { "scx_slice_oob_consts", "SCX_SLICE_OOB_ID_MASK", 0xfffffLLU }, + { "scx_slice_oob_consts", "SCX_SLICE_OOB_PENDING", 0x8000000000000000LLU }, + { "scx_tg_flags", "SCX_TG_ONLINE", 0x1LLU }, + { "scx_tg_flags", "SCX_TG_INITED", 0x2LLU }, + { "scx_tg_flags", "SCX_TG_SUB_INIT", 0x4LLU }, + { "scx_wake_flags", "SCX_WAKE_FORK", 0x4LLU }, + { "scx_wake_flags", "SCX_WAKE_TTWU", 0x8LLU }, + { "scx_wake_flags", "SCX_WAKE_SYNC", 0x10LLU }, +}; + +#endif /* __ENUMS_ABI_AUTOGEN_H__ */ diff --git a/tools/sched_ext/scx_central.bpf.c b/tools/sched_ext/scx_central.bpf.c index 64dd60b3e922..65dae9e45400 100644 --- a/tools/sched_ext/scx_central.bpf.c +++ b/tools/sched_ext/scx_central.bpf.c @@ -299,6 +299,7 @@ static int central_timerfn(void *map, int *key, struct bpf_timer *timer) u64 now = scx_bpf_now(); u64 nr_to_kick = nr_queued; s32 i, curr_cpu; + int ret; curr_cpu = bpf_get_smp_processor_id(); if (timer_pinned && (curr_cpu != central_cpu)) { @@ -332,7 +333,10 @@ static int central_timerfn(void *map, int *key, struct bpf_timer *timer) scx_bpf_kick_cpu(cpu, SCX_KICK_PREEMPT); } - bpf_timer_start(timer, TIMER_INTERVAL_NS, BPF_F_TIMER_CPU_PIN); + ret = bpf_timer_start(timer, TIMER_INTERVAL_NS, + timer_pinned ? BPF_F_TIMER_CPU_PIN : 0); + if (ret) + scx_bpf_error("bpf_timer_start failed (%d)", ret); __sync_fetch_and_add(&nr_timers, 1); return 0; } diff --git a/tools/sched_ext/scx_flatcg.bpf.c b/tools/sched_ext/scx_flatcg.bpf.c index 64cf4dd964d6..454ebb820c5e 100644 --- a/tools/sched_ext/scx_flatcg.bpf.c +++ b/tools/sched_ext/scx_flatcg.bpf.c @@ -937,7 +937,7 @@ void BPF_STRUCT_OPS(fcg_cgroup_move, struct task_struct *p, if (!(from_cgc = find_cgrp_ctx(from)) || !(to_cgc = find_cgrp_ctx(to))) return; - delta = time_delta(p->scx.dsq_vtime, from_cgc->tvtime_now); + delta = (s64)(p->scx.dsq_vtime - from_cgc->tvtime_now); scx_bpf_task_set_dsq_vtime(p, to_cgc->tvtime_now + delta); } diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c index 5bb8b90a275a..9f6e61d7ca07 100644 --- a/tools/sched_ext/scx_qmap.bpf.c +++ b/tools/sched_ext/scx_qmap.bpf.c @@ -1246,7 +1246,8 @@ static int monitor_timerfn(void *map, int *key, struct bpf_timer *timer) scx_read_event(&events, SCX_EV_BYPASS_ACTIVATE)); } - bpf_timer_start(timer, ONE_SEC_IN_NS, 0); + if (bpf_timer_start(timer, ONE_SEC_IN_NS, 0)) + scx_bpf_error("failed to re-arm stats timer"); return 0; } @@ -1268,7 +1269,8 @@ struct { static int lowpri_timerfn(void *map, int *key, struct bpf_timer *timer) { scx_bpf_dsq_reenq(LOWPRI_DSQ, 0); - bpf_timer_start(timer, LOWPRI_INTV_NS, 0); + if (bpf_timer_start(timer, LOWPRI_INTV_NS, 0)) + scx_bpf_error("failed to re-arm lowpri timer"); return 0; } @@ -1747,7 +1749,8 @@ static void rr_advance(void) static int round_robin_timerfn(void *map, int *key, struct bpf_timer *timer) { rr_advance(); - bpf_timer_start(timer, round_robin_ns, 0); + if (bpf_timer_start(timer, round_robin_ns, 0)) + scx_bpf_error("failed to re-arm round-robin timer"); return 0; } diff --git a/tools/testing/selftests/alsa/mixer-test.c b/tools/testing/selftests/alsa/mixer-test.c index a329f901c5ed..0857d64c322a 100644 --- a/tools/testing/selftests/alsa/mixer-test.c +++ b/tools/testing/selftests/alsa/mixer-test.c @@ -319,8 +319,8 @@ static bool ctl_value_index_valid(struct ctl_data *ctl, /* Only check step size if there is one and we're in bounds */ if (snd_ctl_elem_info_get_step(ctl->info) && - (int_val - snd_ctl_elem_info_get_min(ctl->info) % - snd_ctl_elem_info_get_step(ctl->info))) { + (int_val - snd_ctl_elem_info_get_min(ctl->info)) % + snd_ctl_elem_info_get_step(ctl->info)) { ksft_print_msg("%s.%d value %ld invalid for step %ld minimum %ld\n", ctl->name, index, int_val, snd_ctl_elem_info_get_step(ctl->info), diff --git a/tools/testing/selftests/cgroup/test_core.c b/tools/testing/selftests/cgroup/test_core.c index e9bee164bb70..20d2b63774c3 100644 --- a/tools/testing/selftests/cgroup/test_core.c +++ b/tools/testing/selftests/cgroup/test_core.c @@ -919,7 +919,6 @@ int main(int argc, char *argv[]) int i; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), &nsdelegate)) { if (setup_named_v1_root(root, sizeof(root), CG_NAMED_NAME)) ksft_exit_skip("cgroup v2 isn't mounted and could not setup named v1 hierarchy\n"); @@ -932,6 +931,7 @@ int main(int argc, char *argv[]) ksft_exit_skip("Failed to set memory controller\n"); post_v2_setup: + ksft_set_plan(ARRAY_SIZE(tests)); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/cgroup/test_cpu.c b/tools/testing/selftests/cgroup/test_cpu.c index f9f7017d9299..735a53bb222b 100644 --- a/tools/testing/selftests/cgroup/test_cpu.c +++ b/tools/testing/selftests/cgroup/test_cpu.c @@ -832,7 +832,6 @@ int main(int argc, char *argv[]) int i; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); @@ -840,6 +839,7 @@ int main(int argc, char *argv[]) if (cg_write(root, "cgroup.subtree_control", "+cpu")) ksft_exit_skip("Failed to set cpu controller\n"); + ksft_set_plan(ARRAY_SIZE(tests)); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/cgroup/test_cpuset.c b/tools/testing/selftests/cgroup/test_cpuset.c index 8c2d4d4ef1fc..3dfadd280c1c 100644 --- a/tools/testing/selftests/cgroup/test_cpuset.c +++ b/tools/testing/selftests/cgroup/test_cpuset.c @@ -497,7 +497,6 @@ int main(int argc, char *argv[]) int i; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); @@ -505,6 +504,7 @@ int main(int argc, char *argv[]) if (cg_write(root, "cgroup.subtree_control", "+cpuset")) ksft_exit_skip("Failed to set cpuset controller\n"); + ksft_set_plan(ARRAY_SIZE(tests)); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh index da8f7b920178..131d8b4551ef 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh @@ -797,7 +797,6 @@ check_isolcpus() EXPECTED_ISOLCPUS=$1 ISCPUS=${CGROUP2}/cpuset.cpus.isolated ISOLCPUS=$(cat $ISCPUS) - HKICPUS=$(cat /sys/devices/system/cpu/isolated) LASTISOLCPU= SCHED_DOMAINS=/sys/kernel/debug/sched/domains if [[ $EXPECTED_ISOLCPUS = . ]] @@ -836,11 +835,6 @@ check_isolcpus() EXPECTED_ISOLCPUS=$EXPECTED_SDOMAIN # - # The inverse of HK_TYPE_DOMAIN cpumask in $HKICPUS should match $ISOLCPUS - # - [[ "$ISOLCPUS" != "$HKICPUS" ]] && return 1 - - # # Use the sched domain in debugfs to check isolated CPUs, if available # [[ -d $SCHED_DOMAINS ]] || return 0 @@ -1162,6 +1156,63 @@ test_isolated() } # +# Select an online CPU isolated from scheduler domains at boot. +# $1: test name used in the skip message +# +get_boot_isolated_cpu() +{ + TEST_NAME=$1 + BOOT_ISOLATED_FILE=/sys/devices/system/cpu/isolated + + [[ -r $BOOT_ISOLATED_FILE ]] || { + echo "$TEST_NAME test SKIPPED: boot isolation state unavailable" + return 1 + } + BOOT_CPUS=$(cat $BOOT_ISOLATED_FILE) + [[ -n "$BOOT_CPUS" ]] || { + echo "$TEST_NAME test SKIPPED: no boot-isolated CPU" + return 1 + } + + BOOT_CPU=$(echo "$BOOT_CPUS" | sed -e 's/[,-].*//') + CPU_ONLINE=/sys/devices/system/cpu/cpu${BOOT_CPU}/online + [[ ! -e $CPU_ONLINE || $(cat $CPU_ONLINE) -eq 1 ]] || { + echo "$TEST_NAME test SKIPPED: CPU $BOOT_CPU is offline" + return 1 + } +} + +# +# A CPU isolated at boot must stay isolated after it is released by a dynamic +# isolated partition. +# +test_boot_isolated() +{ + TEST_NAME="Boot-isolated CPU partition release" + get_boot_isolated_cpu "$TEST_NAME" || return 0 + echo "Running $TEST_NAME test ..." + + cd $CGROUP2/test + echo member > cpuset.cpus.partition + echo $BOOT_CPU > cpuset.cpus + [[ $(cat cpuset.cpus.effective) = "$BOOT_CPU" ]] || { + echo "$TEST_NAME test SKIPPED: CPU $BOOT_CPU is unavailable" + echo "" > cpuset.cpus + cd $CGROUP2 + return 0 + } + test_partition isolated + test_partition member + check_isolcpus "." || { + echo "Boot-isolated CPU $BOOT_CPU was lost after partition release" + exit 1 + } + echo "" > cpuset.cpus + cd $CGROUP2 + echo "$TEST_NAME test PASSED." +} + +# # Wait for inotify event for the given file and read it # $1: cgroup file to wait for # $2: file to store the read result @@ -1232,5 +1283,6 @@ trap cleanup 0 2 3 6 run_state_test TEST_MATRIX run_remote_state_test REMOTE_TEST_MATRIX test_isolated +test_boot_isolated test_inotify echo "All tests PASSED." diff --git a/tools/testing/selftests/cgroup/test_freezer.c b/tools/testing/selftests/cgroup/test_freezer.c index 0569e93fa6b0..f28bb02e9783 100644 --- a/tools/testing/selftests/cgroup/test_freezer.c +++ b/tools/testing/selftests/cgroup/test_freezer.c @@ -1491,9 +1491,9 @@ int main(int argc, char *argv[]) int i; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); + ksft_set_plan(ARRAY_SIZE(tests)); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/cgroup/test_kill.c b/tools/testing/selftests/cgroup/test_kill.c index f6cd23a8ecc7..bac1ddd8cb94 100644 --- a/tools/testing/selftests/cgroup/test_kill.c +++ b/tools/testing/selftests/cgroup/test_kill.c @@ -7,6 +7,7 @@ #include <stdlib.h> #include <string.h> #include <sys/types.h> +#include <sys/wait.h> #include <unistd.h> #include "kselftest.h" @@ -261,6 +262,59 @@ cleanup: return ret; } +/* + * Test that a cgroup that was killed in the past can still be the target + * of clone3(CLONE_INTO_CGROUP): writing cgroup.kill must only kill the + * tasks in the cgroup at the time of the write, not tasks cloned into + * it afterwards. + */ +static int test_cgkill_clone_into_killed(const char *root) +{ + pid_t pid; + int cgroup_fd = -EBADF; + int ret = KSFT_FAIL; + char *cgroup = NULL; + + cgroup = cg_name(root, "cg_test_clone_into_killed"); + if (!cgroup) + goto cleanup; + + if (cg_create(cgroup)) + goto cleanup; + + /* Kill the cgroup while it is still empty. */ + if (cg_write(cgroup, "cgroup.kill", "1")) + goto cleanup; + + cgroup_fd = dirfd_open_opath(cgroup); + if (cgroup_fd < 0) + goto cleanup; + + pid = clone_into_cgroup(cgroup_fd); + if (pid < 0) { + if (errno == ENOSYS) + ret = KSFT_SKIP; + goto cleanup; + } + + if (pid == 0) + exit(EXIT_SUCCESS); + + /* The child must not be SIGKILLed; it has to exit cleanly. */ + if (clone_reap(pid, WEXITED) != EXIT_SUCCESS) + goto cleanup; + + ret = KSFT_PASS; + +cleanup: + if (cgroup_fd >= 0) + close(cgroup_fd); + if (cgroup) + cg_destroy(cgroup); + free(cgroup); + return ret; +} + #define T(x) { x, #x } struct cgkill_test { int (*fn)(const char *root); @@ -269,6 +323,7 @@ struct cgkill_test { T(test_cgkill_simple), T(test_cgkill_tree), T(test_cgkill_forkbomb), + T(test_cgkill_clone_into_killed), }; #undef T @@ -278,9 +333,9 @@ int main(int argc, char *argv[]) int i; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); + ksft_set_plan(ARRAY_SIZE(tests)); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c index 1db0ba1226b9..437f2d35f205 100644 --- a/tools/testing/selftests/cgroup/test_kmem.c +++ b/tools/testing/selftests/cgroup/test_kmem.c @@ -145,7 +145,7 @@ static int cg_run_in_subcgroups(const char *parent, return -1; } - if (cg_run(child, fn, NULL)) { + if (cg_run(child, fn, arg)) { cg_destroy(child); free(child); return -1; @@ -426,7 +426,6 @@ int main(int argc, char **argv) int i; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); @@ -441,6 +440,7 @@ int main(int argc, char **argv) if (cg_write(root, "cgroup.subtree_control", "+memory")) ksft_exit_skip("Failed to set memory controller\n"); + ksft_set_plan(ARRAY_SIZE(tests)); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c index 0ebf796f3cff..3a84d068fbf3 100644 --- a/tools/testing/selftests/cgroup/test_memcontrol.c +++ b/tools/testing/selftests/cgroup/test_memcontrol.c @@ -1798,7 +1798,6 @@ int main(int argc, char **argv) page_size = BUF_SIZE; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); @@ -1823,6 +1822,7 @@ int main(int argc, char **argv) ksft_exit_skip("Failed to query cgroup mount option\n"); has_localevents = proc_status; + ksft_set_plan(ARRAY_SIZE(tests)); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/cgroup/test_pids.c b/tools/testing/selftests/cgroup/test_pids.c index 9a387c815d2c..710109b53dfe 100644 --- a/tools/testing/selftests/cgroup/test_pids.c +++ b/tools/testing/selftests/cgroup/test_pids.c @@ -148,7 +148,6 @@ int main(int argc, char **argv) char root[PATH_MAX]; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); @@ -163,6 +162,7 @@ int main(int argc, char **argv) if (cg_write(root, "cgroup.subtree_control", "+pids")) ksft_exit_skip("Failed to set pids controller\n"); + ksft_set_plan(ARRAY_SIZE(tests)); for (int i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/cgroup/test_zswap.c b/tools/testing/selftests/cgroup/test_zswap.c index f7b4c4370db6..609c48f38524 100644 --- a/tools/testing/selftests/cgroup/test_zswap.c +++ b/tools/testing/selftests/cgroup/test_zswap.c @@ -819,7 +819,6 @@ int main(int argc, char **argv) page_size = BUF_SIZE; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); @@ -836,6 +835,7 @@ int main(int argc, char **argv) if (cg_write(root, "cgroup.subtree_control", "+memory")) ksft_exit_skip("Failed to set memory controller\n"); + ksft_set_plan(ARRAY_SIZE(tests)); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c index fc9694fc4e89..1d49df671919 100644 --- a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c +++ b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c @@ -390,6 +390,116 @@ static void test_alloc_errors(char *heap_name) close(heap_fd); } +/* + * count_open_fds - return the number of open file descriptors. + * + * The fd opened by opendir() itself is counted, but since it is opened + * and closed within each call, it cancels out when comparing two counts. + * Returns -1 on error. + */ +static int count_open_fds(void) +{ + DIR *d = opendir("/proc/self/fd"); + struct dirent *de; + int count = 0; + + if (!d) + return -1; + + while ((de = readdir(d))) + if (de->d_name[0] != '.') + count++; + closedir(d); + return count; +} + +/* + * test_alloc_no_fd_leak_on_efault - verify no fd is leaked when + * copy_to_user() fails during DMA_HEAP_IOCTL_ALLOC. + * + * The bug: dma_buf_fd() called fd_install() before copy_to_user(). + * If copy_to_user() then failed (e.g. via mprotect), the fd was + * silently installed in the fd table but never returned to userspace. + * + * The fix: reserve the fd with get_unused_fd_flags() first, attempt + * copy_to_user(), and only call fd_install() on success. + * + * We trigger the failure by placing the ioctl argument in a private + * anonymous page and flipping it to PROT_READ before the ioctl. + * Inside the kernel, copy_from_user() reads from the page (reads are + * allowed under PROT_READ, so it succeeds), but copy_to_user() that + * writes the fd number back faults, returning -EFAULT. We then + * count open file descriptors before and after; with the bug an extra + * fd is left in the table. + */ +static void test_alloc_no_fd_leak_on_efault(char *heap_name) +{ + int heap_fd = -1; + int fd_before, fd_after; + int ret; + long page_size; + struct dma_heap_allocation_data *req; + + ksft_print_msg("Testing fd leak when copy_to_user() fails:\n"); + + heap_fd = dmabuf_heap_open(heap_name); + + page_size = sysconf(_SC_PAGESIZE); + + /* + * Place the ioctl argument in its own private anonymous page so + * we can flip its protection independently. + */ + req = mmap(NULL, page_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (req == MAP_FAILED) { + ksft_test_result_fail("mmap failed: %s\n", strerror(errno)); + goto out; + } + + memset(req, 0, sizeof(*req)); + req->len = page_size; + req->fd_flags = O_RDWR | O_CLOEXEC; + + fd_before = count_open_fds(); + if (fd_before < 0) { + ksft_test_result_fail("count_open_fds: %s\n", strerror(errno)); + munmap(req, page_size); + goto out; + } + + /* + * Make the page read-only so copy_to_user() will fault. The + * ioctl must fail with -1; if it returns success the test setup + * is broken (mprotect is synchronous, so there is no race). + */ + mprotect(req, page_size, PROT_READ); + + ret = ioctl(heap_fd, DMA_HEAP_IOCTL_ALLOC, req); + + /* Re-allow writes so munmap can clean up */ + mprotect(req, page_size, PROT_READ | PROT_WRITE); + munmap(req, page_size); + + if (ret != -1) { + ksft_test_result_fail("ioctl returned %d, expected -1 EFAULT\n", + ret); + goto out; + } + + fd_after = count_open_fds(); + if (fd_after < 0) { + ksft_test_result_fail("count_open_fds: %s\n", strerror(errno)); + goto out; + } + + ksft_test_result(fd_before == fd_after, + "fd leak on EFAULT: before=%d after=%d\n", + fd_before, fd_after); +out: + close(heap_fd); +} + static int numer_of_heaps(void) { DIR *d = opendir(DEVPATH); @@ -420,7 +530,7 @@ int main(void) return KSFT_SKIP; } - ksft_set_plan(11 * numer_of_heaps()); + ksft_set_plan(12 * numer_of_heaps()); while ((dir = readdir(d))) { if (!strncmp(dir->d_name, ".", 2)) @@ -435,6 +545,7 @@ int main(void) test_alloc_zeroed(dir->d_name, ONE_MEG); test_alloc_compat(dir->d_name); test_alloc_errors(dir->d_name); + test_alloc_no_fd_leak_on_efault(dir->d_name); } closedir(d); diff --git a/tools/testing/selftests/hid/hid_bpf.c b/tools/testing/selftests/hid/hid_bpf.c index b851339308c2..7ab86296ff23 100644 --- a/tools/testing/selftests/hid/hid_bpf.c +++ b/tools/testing/selftests/hid/hid_bpf.c @@ -67,14 +67,17 @@ struct test_program { int insert_head; }; #define LOAD_PROGRAMS(progs) \ - load_programs(progs, ARRAY_SIZE(progs), _metadata, self, variant) + load_programs(progs, ARRAY_SIZE(progs), false, _metadata, self, variant) +#define LOAD_PROGRAMS_MAY_FAIL(progs) \ + load_programs(progs, ARRAY_SIZE(progs), true, _metadata, self, variant) #define LOAD_BPF \ - load_programs(NULL, 0, _metadata, self, variant) -static void load_programs(const struct test_program programs[], - const size_t progs_count, - struct __test_metadata *_metadata, - FIXTURE_DATA(hid_bpf) * self, - const FIXTURE_VARIANT(hid_bpf) * variant) + load_programs(NULL, 0, false, _metadata, self, variant) +static int load_programs(const struct test_program programs[], + const size_t progs_count, + bool load_may_fail, + struct __test_metadata *_metadata, + FIXTURE_DATA(hid_bpf) * self, + const FIXTURE_VARIANT(hid_bpf) * variant) { struct bpf_map *iter_map; int err = -EINVAL; @@ -128,6 +131,9 @@ static void load_programs(const struct test_program programs[], } err = hid__load(self->skel); + if (err && load_may_fail) + return err; + ASSERT_OK(err) TH_LOG("hid_skel_load failed: %d", err); for (int i = 0; i < progs_count; i++) { @@ -147,6 +153,7 @@ static void load_programs(const struct test_program programs[], self->hidraw_fd = open_hidraw(&self->hid); ASSERT_GE(self->hidraw_fd, 0) TH_LOG("open_hidraw"); + return 0; } /* @@ -904,11 +911,39 @@ TEST_F(hid_bpf, test_rdesc_fixup_get_data_overflow) { .name = "hid_rdesc_fixup_get_data_overflow" }, }; - LOAD_PROGRAMS(progs); + /* newer verifier can detect the overflow at load time */ + if (LOAD_PROGRAMS_MAY_FAIL(progs)) + return; ASSERT_EQ(self->skel->bss->get_data_overflow_check, 1); } +TEST_F(hid_bpf, test_rdesc_fixup_change_uniq_name_phys) +{ + const struct test_program progs[] = { + { .name = "hid_rdesc_fixup_change_uniq_name_phys" }, + }; + char expected[256], buf[256] = {}; + int err; + + LOAD_PROGRAMS(progs); + + err = ioctl(self->hidraw_fd, HIDIOCGRAWNAME(sizeof(buf)), buf); + ASSERT_GE(err, 0) TH_LOG("HIDIOCGRAWNAME"); + ASSERT_STREQ("name coming from bpf", buf); + + snprintf(expected, sizeof(expected), "%d phys:coming:from:bpf", self->hid.dev_id); + + err = ioctl(self->hidraw_fd, HIDIOCGRAWPHYS(sizeof(buf)), buf); + ASSERT_GE(err, 0) TH_LOG("HIDIOCGRAWPHYS"); + ASSERT_STREQ(expected, buf); + + err = ioctl(self->hidraw_fd, HIDIOCGRAWUNIQ(sizeof(buf)), buf); + ASSERT_GE(err, 0) TH_LOG("HIDIOCGRAWUNIQ"); + ASSERT_STREQ("uniq:coming:from:bpf", buf); + +} + static int libbpf_print_fn(enum libbpf_print_level level, const char *format, va_list args) { diff --git a/tools/testing/selftests/hid/progs/hid.c b/tools/testing/selftests/hid/progs/hid.c index b21fbb13c926..361dc7eaad22 100644 --- a/tools/testing/selftests/hid/progs/hid.c +++ b/tools/testing/selftests/hid/progs/hid.c @@ -255,6 +255,32 @@ struct hid_bpf_ops rdesc_fixup_get_data_overflow = { .hid_rdesc_fixup = (void *)hid_rdesc_fixup_get_data_overflow, }; +SEC("?struct_ops.s/hid_rdesc_fixup") +int BPF_PROG(hid_rdesc_fixup_change_uniq_name_phys, struct hid_bpf_ctx *hid_ctx) +{ +#define HID_BPF_MEMCPY(target, str) \ + __builtin_memcpy(target, str, sizeof(str)) + + HID_BPF_MEMCPY(hid_ctx->hid->name, "name coming from bpf"); + HID_BPF_MEMCPY(hid_ctx->hid->uniq, "uniq:coming:from:bpf"); + /* hid_bpf relies on a phys being a rand % 1024 */ + for (int i = 0; i < 5; i++) { + if (!hid_ctx->hid->phys[i]) { + HID_BPF_MEMCPY(hid_ctx->hid->phys + i, " phys:coming:from:bpf"); + break; + } + } + +#undef HID_BPF_MEMCPY + + return 0; +} + +SEC(".struct_ops.link") +struct hid_bpf_ops rdesc_fixup_change_uniq_name_phys = { + .hid_rdesc_fixup = (void *)hid_rdesc_fixup_change_uniq_name_phys, +}; + SEC("?struct_ops/hid_device_event") int BPF_PROG(hid_test_insert1, struct hid_bpf_ctx *hid_ctx, enum hid_report_type type) { diff --git a/tools/testing/selftests/hid/progs/hid_bpf_helpers.h b/tools/testing/selftests/hid/progs/hid_bpf_helpers.h index cdca912f3afd..05698793762a 100644 --- a/tools/testing/selftests/hid/progs/hid_bpf_helpers.h +++ b/tools/testing/selftests/hid/progs/hid_bpf_helpers.h @@ -61,6 +61,9 @@ enum hid_report_type { struct hid_device { unsigned int id; + char name[128]; + char phys[64]; + char uniq[64]; } __attribute__((preserve_access_index)); struct bpf_wq { diff --git a/tools/testing/selftests/mm/memfd_secret.c b/tools/testing/selftests/mm/memfd_secret.c index aac4f795c327..c55d84c5e613 100644 --- a/tools/testing/selftests/mm/memfd_secret.c +++ b/tools/testing/selftests/mm/memfd_secret.c @@ -57,33 +57,6 @@ static void test_file_apis(int fd) pass("file IO is blocked as expected\n"); } -static void test_mlock_limit(int fd) -{ - size_t len; - char *mem; - - len = mlock_limit_cur; - if (len % page_size != 0) - len = (len/page_size) * page_size; - - mem = mmap(NULL, len, prot, mode, fd, 0); - if (mem == MAP_FAILED) { - fail("unable to mmap secret memory\n"); - return; - } - munmap(mem, len); - - len = mlock_limit_max * 2; - mem = mmap(NULL, len, prot, mode, fd, 0); - if (mem != MAP_FAILED) { - fail("unexpected mlock limit violation\n"); - munmap(mem, len); - return; - } - - pass("mlock limit is respected\n"); -} - static void test_vmsplice(int fd, const char *desc) { ssize_t transferred; @@ -297,7 +270,7 @@ static void prepare(void) strerror(errno)); } -#define NUM_TESTS 6 +#define NUM_TESTS 5 int main(int argc, char *argv[]) { @@ -319,7 +292,6 @@ int main(int argc, char *argv[]) if (ftruncate(fd, page_size)) ksft_exit_fail_msg("ftruncate failed: %s\n", strerror(errno)); - test_mlock_limit(fd); test_file_apis(fd); /* * We have to run the first vmsplice test before any secretmem page was diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 0f5c178bc224..517c09d60bef 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -28,6 +28,7 @@ TEST_PROGS := \ double_udp_encap.sh \ drop_monitor_tests.sh \ ecmp_rehash.sh \ + exception_cache.sh \ fcnal-ipv4.sh \ fcnal-ipv6.sh \ fcnal-other.sh \ diff --git a/tools/testing/selftests/net/exception_cache.sh b/tools/testing/selftests/net/exception_cache.sh new file mode 100755 index 000000000000..8d3eed5c532a --- /dev/null +++ b/tools/testing/selftests/net/exception_cache.sh @@ -0,0 +1,521 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test that the state of the route exception cache after an ICMP error is +# processed does not depend on whether the quoted packet was matched to a +# socket. Otherwise, an off-path attacker can probe the cache to discover the +# ephemeral port used by a connected UDP socket. +# +# When the quoted packet is not matched to a socket, the same exception is +# created as when it is matched, so that neither its presence nor its contents +# reveal the result of socket matching. +# +# +----+ +# +---------| r1 | +# | +----+ +# +----+ +--------+ | .1 +# | h1 |---| bridge | | 198.51.100.0/30 +# +----+ +--------+ | 2001:db8:2::/64 +# .1 | | .2 +# | +----+ +----+ +# +---------| r2 |-----------| h2 | +# .2 .3 +----+ .1 .2 +----+ +# 203.0.113.0/24 +# 2001:db8:3::/64 +# 192.0.2.0/24 +# 2001:db8:1::/64 +# +# Traffic from h1 to h2 is routed via r1, which reaches h2's network via r2 +# over the point-to-point link. The MTU of the r2 - h2 link is lowered so that +# r2 emits ICMP errors towards h1. +# +# For the redirect tests r1's route to h2's network is replaced with one via r2 +# on the shared segment, so that r1 forwards the packet back to the segment it +# arrived from and emits a redirect towards h1. +# +# The packets that provoke the ICMP errors are injected with a packet socket so +# that no socket is ever associated with them. A socket is created separately, +# with socat, when a test needs the ICMP error to be matched. + +# shellcheck disable=SC1091,SC2034,SC2154,SC2329 +source lib.sh + +require_command jq +require_command mausezahn +require_command nstat +require_command socat + +ALL_TESTS=" + pmtu_no_socket_ipv4 + pmtu_no_socket_ipv6 + pmtu_socket_ipv4 + pmtu_socket_ipv6 + pmtu_omit_ipv4 + pmtu_omit_ipv6 + redirect_no_socket_ipv4 + redirect_no_socket_ipv6 + redirect_socket_ipv4 + redirect_socket_ipv6 +" + +# Shared segment. +H1_ADDR4=192.0.2.1 +R1_ADDR4=192.0.2.2 +R2_ADDR4=192.0.2.3 +H1_ADDR6=2001:db8:1::1 +R1_ADDR6=2001:db8:1::2 +R2_ADDR6=2001:db8:1::3 + +# r1 - r2 link. +R2_R1_ADDR4=198.51.100.2 +R2_R1_ADDR6=2001:db8:2::2 + +# r2 - h2 link. +H2_ADDR4=203.0.113.2 +H2_NET4=203.0.113.0/24 +H2_ADDR6=2001:db8:3::2 +H2_NET6=2001:db8:3::/64 + +SPORT=12345 +DPORT=54321 + +# The MTU of the shared segment and of the r1 - r2 link. Large enough for the +# injected packets to reach r2 intact. +SEGMENT_MTU=2000 +# Size of the injected packets. The PMTU tests need a size that exceeds every +# MTU used for the r2 - h2 link, so that r2 responds with an ICMP error. The +# redirect tests need a size that does not, otherwise r2 would respond with an +# ICMP error in addition to the redirect emitted by r1. +PMTU_PACKET_SIZE=1800 +REDIRECT_PACKET_SIZE=100 + +# The MTUs used for the r2 - h2 link. All of them must be at least +# IPV6_MIN_MTU, otherwise IPv6 silently ignores the error instead of creating +# an exception. +MTU_MID=1400 +MTU_LOW=1300 + +# Values for the IP{,V6}_MTU_DISCOVER socket option. +PMTUDISC_DONT=0 +PMTUDISC_OMIT=5 + +SOCAT_PID= + +linklocal_get() +{ + local ns=$1; shift + local dev=$1; shift + + ip -n "$ns" -j -6 addr show dev "$dev" | \ + jq -r '.[]["addr_info"][] | select(.scope == "link") | .local' +} + +linklocal_exists() +{ + local ns=$1; shift + local dev=$1; shift + + [ -n "$(linklocal_get "$ns" "$dev")" ] +} + +family_vars_set() +{ + local family=$1; shift + + FAMILY=$family + + if [ "$family" -eq 4 ]; then + H1_ADDR=$H1_ADDR4 + H2_ADDR=$H2_ADDR4 + MZ_FAMILY_OPT=() + # Without the Don't Fragment bit set r2 fragments the packet + # instead of reporting the MTU of the next hop. + MZ_IP_OPTS="df," + SOCAT_DST="UDP4-CONNECT:$H2_ADDR4:$DPORT" + SOCAT_BIND="bind=$H1_ADDR4:$SPORT" + SOCAT_PMTUDISC="ip-mtu-discover" + else + H1_ADDR=$H1_ADDR6 + H2_ADDR=$H2_ADDR6 + MZ_FAMILY_OPT=(-6) + MZ_IP_OPTS= + SOCAT_DST="UDP6-CONNECT:[$H2_ADDR6]:$DPORT" + SOCAT_BIND="bind=[$H1_ADDR6]:$SPORT" + SOCAT_PMTUDISC="ipv6-mtu-discover" + fi +} + +topology_setup() +{ + local ns + + setup_ns h1 r1 r2 h2 sw + defer cleanup_all_ns + + # Link-local addresses are generated from the MAC address and read + # back during setup, so request that generation mode explicitly and + # make the addresses available as soon as the devices are brought up. + for ns in "$h1" "$r1" "$r2" "$h2" "$sw"; do + ip netns exec "$ns" sysctl -qw \ + net.ipv6.conf.default.addr_gen_mode=0 \ + net.ipv6.conf.default.accept_dad=0 \ + net.ipv6.conf.all.accept_dad=0 + done + + ip -n "$sw" link add name br0 type bridge + ip -n "$sw" link set dev br0 mtu "$SEGMENT_MTU" up + + ip -n "$h1" link add name eth0 mtu "$SEGMENT_MTU" type veth \ + peer name swp1 mtu "$SEGMENT_MTU" netns "$sw" + ip -n "$r1" link add name eth0 mtu "$SEGMENT_MTU" type veth \ + peer name swp2 mtu "$SEGMENT_MTU" netns "$sw" + ip -n "$r2" link add name eth0 mtu "$SEGMENT_MTU" type veth \ + peer name swp3 mtu "$SEGMENT_MTU" netns "$sw" + ip -n "$r1" link add name eth1 mtu "$SEGMENT_MTU" type veth \ + peer name eth1 mtu "$SEGMENT_MTU" netns "$r2" + ip -n "$r2" link add name eth2 type veth peer name eth0 netns "$h2" + + ip -n "$sw" link set dev swp1 master br0 up + ip -n "$sw" link set dev swp2 master br0 up + ip -n "$sw" link set dev swp3 master br0 up + + ip -n "$h1" link set dev eth0 up + ip -n "$r1" link set dev eth0 up + ip -n "$r1" link set dev eth1 up + ip -n "$r2" link set dev eth0 up + ip -n "$r2" link set dev eth1 up + ip -n "$r2" link set dev eth2 up + ip -n "$h2" link set dev eth0 up + + ip -n "$h1" address add "$H1_ADDR4/24" dev eth0 + ip -n "$r1" address add "$R1_ADDR4/24" dev eth0 + ip -n "$r2" address add "$R2_ADDR4/24" dev eth0 + ip -n "$r1" address add 198.51.100.1/30 dev eth1 + ip -n "$r2" address add "$R2_R1_ADDR4/30" dev eth1 + ip -n "$r2" address add 203.0.113.1/24 dev eth2 + ip -n "$h2" address add "$H2_ADDR4/24" dev eth0 + + ip -n "$h1" -6 address add "$H1_ADDR6/64" dev eth0 nodad + ip -n "$r1" -6 address add "$R1_ADDR6/64" dev eth0 nodad + ip -n "$r2" -6 address add "$R2_ADDR6/64" dev eth0 nodad + ip -n "$r1" -6 address add 2001:db8:2::1/64 dev eth1 nodad + ip -n "$r2" -6 address add "$R2_R1_ADDR6/64" dev eth1 nodad + ip -n "$r2" -6 address add 2001:db8:3::1/64 dev eth2 nodad + ip -n "$h2" -6 address add "$H2_ADDR6/64" dev eth0 nodad + + ip netns exec "$r1" sysctl -qw net.ipv4.ip_forward=1 + ip netns exec "$r1" sysctl -qw net.ipv4.conf.all.send_redirects=1 + ip netns exec "$r1" sysctl -qw net.ipv6.conf.all.forwarding=1 + ip netns exec "$r2" sysctl -qw net.ipv4.ip_forward=1 + ip netns exec "$r2" sysctl -qw net.ipv6.conf.all.forwarding=1 + + ip netns exec "$h1" sysctl -qw net.ipv4.conf.all.accept_redirects=1 + ip netns exec "$h1" sysctl -qw net.ipv4.conf.eth0.accept_redirects=1 + ip netns exec "$h1" sysctl -qw net.ipv6.conf.all.accept_redirects=1 + ip netns exec "$h1" sysctl -qw net.ipv6.conf.eth0.accept_redirects=1 + + slowwait 5 linklocal_exists "$r1" eth0 + check_err $? "r1: link-local address was not generated" + slowwait 5 linklocal_exists "$r2" eth0 + check_err $? "r2: link-local address was not generated" + + R1_LLADDR=$(linklocal_get "$r1" eth0) + R2_LLADDR=$(linklocal_get "$r2" eth0) + R1_MAC=$(ip -n "$r1" -j link show dev eth0 | jq -r '.[]["address"]') + R2_MAC=$(ip -n "$r2" -j link show dev eth0 | jq -r '.[]["address"]') + + ip -n "$h1" route add "$H2_NET4" via "$R1_ADDR4" dev eth0 + ip -n "$h1" -6 route add "$H2_NET6" via "$R1_LLADDR" dev eth0 + ip -n "$r1" route add "$H2_NET4" via "$R2_R1_ADDR4" dev eth1 + ip -n "$r1" -6 route add "$H2_NET6" via "$R2_R1_ADDR6" dev eth1 + ip -n "$h2" route add default via 203.0.113.1 dev eth0 + ip -n "$h2" -6 route add default via 2001:db8:3::1 dev eth0 + + far_mtu_set "$MTU_MID" +} + +# Make r1 forward towards h2's network over the segment it receives the packet +# from, so that it emits a redirect towards h1. +redirect_route_set() +{ + ip -n "$r1" route replace "$H2_NET4" via "$R2_ADDR4" dev eth0 + ip -n "$r1" -6 route replace "$H2_NET6" via "$R2_LLADDR" dev eth0 + + # __ip_do_redirect() only creates an exception if the new gateway is + # already a valid neighbour. Otherwise it merely triggers address + # resolution. IPv6 resolves the target itself, in rt6_do_redirect(). + ip -n "$h1" neigh replace "$R2_ADDR4" lladdr "$R2_MAC" dev eth0 \ + nud permanent +} + +far_mtu_set() +{ + local mtu=$1; shift + + ip -n "$r2" link set dev eth2 mtu "$mtu" + ip -n "$h2" link set dev eth0 mtu "$mtu" +} + +socket_is_open() +{ + ip netns exec "$h1" ss -uHn "sport = :$SPORT" | grep -q . +} + +socket_start() +{ + # Disable PMTU discovery by default so that ICMP errors are not + # reported to the socket. Otherwise socat would exit when the first one + # arrives and later packets in the same test would not be matched to a + # socket. The exception is still created, as ip{,6}_sk_accept_pmtu() + # only rejects IP{,V6}_PMTUDISC_{INTERFACE,OMIT}. + local pmtudisc=${1:-$PMTUDISC_DONT} + + # Send socat's diagnostics to /dev/null. It reports the ICMP errors + # that reach the socket, which is exactly what the tests provoke. + ip netns exec "$h1" socat -u -lf/dev/null \ + "$SOCAT_DST,$SOCAT_BIND,$SOCAT_PMTUDISC=$pmtudisc" \ + OPEN:/dev/null,wronly=1 & + SOCAT_PID=$! + defer socket_stop + + slowwait 5 socket_is_open + check_err $? "socket did not open" +} + +socket_stop() +{ + [ -z "$SOCAT_PID" ] && return 0 + + kill "$SOCAT_PID" &> /dev/null + wait "$SOCAT_PID" 2> /dev/null + SOCAT_PID= +} + +# Inject a packet towards h2 with a packet socket. No socket is associated with +# it, so an ICMP error quoting it is matched to a socket only if one was +# created separately with the same source port. +packet_send() +{ + local size=$1; shift + + ip netns exec "$h1" mausezahn "${MZ_FAMILY_OPT[@]}" eth0 \ + -a own -b "$R1_MAC" -A "$H1_ADDR" -B "$H2_ADDR" \ + -t udp "${MZ_IP_OPTS}sp=$SPORT,dp=$DPORT" \ + -p "$size" -c 1 -q +} + +exception_show() +{ + if [ "$FAMILY" -eq 4 ]; then + # IPv4 exceptions without a bound route are not dumped, but + # "route get" reports the exception and binds a route to it. + ip -n "$h1" route get "$H2_ADDR" + else + # IPv6 does not report a cache indication in "route get" + # output, so dump the exceptions instead. + ip -n "$h1" -6 route show cache | grep -F "$H2_ADDR" || true + fi +} + +exception_mtu_get() +{ + exception_show | grep -o "mtu [0-9]*" | cut -d ' ' -f 2 +} + +exception_gw_get() +{ + exception_show | grep -o "via [0-9a-f.:]*" | cut -d ' ' -f 2 +} + +exception_mtu_check() +{ + local expected=$1; shift + + [ "$(exception_mtu_get)" = "$expected" ] +} + +icmp_errors_get() +{ + local ctr=IcmpInDestUnreachs + + [ "$FAMILY" -eq 6 ] && ctr=Icmp6InPktTooBigs + + ip netns exec "$h1" nstat -asz "$ctr" | \ + awk -v ctr="$ctr" '$1 == ctr { print $2 }' +} + +exception_pmtu_check() +{ + local mtu=$1; shift + local desc=$1; shift + + busywait "$BUSYWAIT_TIMEOUT" exception_mtu_check "$mtu" + check_err $? "$desc: exception does not carry an MTU of $mtu" +} + +pmtu_no_socket() +{ + local family=$1; shift + + RET=0 + family_vars_set "$family" + topology_setup + + packet_send "$PMTU_PACKET_SIZE" + exception_pmtu_check "$MTU_MID" "No socket" + + log_test "IPv$family: PMTU: exception without a matching socket" +} + +pmtu_no_socket_ipv4() +{ + pmtu_no_socket 4 +} + +pmtu_no_socket_ipv6() +{ + pmtu_no_socket 6 +} + +pmtu_socket() +{ + local family=$1; shift + local t0 + + RET=0 + family_vars_set "$family" + topology_setup + socket_start + + packet_send "$PMTU_PACKET_SIZE" + exception_pmtu_check "$MTU_MID" "Matching socket" + + # A lower PMTU replaces the one currently stored in the exception. + far_mtu_set "$MTU_LOW" + packet_send "$PMTU_PACKET_SIZE" + exception_pmtu_check "$MTU_LOW" "Lower PMTU" + + # A higher PMTU is ignored, so the exception is left as it is. Wait + # for the error to be received, as otherwise the check below would + # pass even if it never was. + far_mtu_set "$MTU_MID" + t0=$(icmp_errors_get) + packet_send "$PMTU_PACKET_SIZE" + busywait "$BUSYWAIT_TIMEOUT" until_counter_is ">= $((t0 + 1))" \ + icmp_errors_get > /dev/null + check_err $? "Higher PMTU: ICMP error was not received" + + exception_mtu_check "$MTU_LOW" + check_err $? "Higher PMTU: exception does not carry an MTU of $MTU_LOW" + + log_test "IPv$family: PMTU: exception with a matching socket" +} + +pmtu_socket_ipv4() +{ + pmtu_socket 4 +} + +pmtu_socket_ipv6() +{ + pmtu_socket 6 +} + +pmtu_omit() +{ + local family=$1; shift + + RET=0 + family_vars_set "$family" + topology_setup + socket_start "$PMTUDISC_OMIT" + + packet_send "$PMTU_PACKET_SIZE" + exception_pmtu_check "$MTU_MID" "PMTU discovery disabled" + + log_test "IPv$family: PMTU: exception with a socket ignoring it" +} + +pmtu_omit_ipv4() +{ + pmtu_omit 4 +} + +pmtu_omit_ipv6() +{ + pmtu_omit 6 +} + +exception_gw_check() +{ + local expected=$1; shift + + [ -n "$expected" ] && [ "$(exception_gw_get)" = "$expected" ] +} + +redirect_gw_new() +{ + if [ "$FAMILY" -eq 4 ]; then + echo "$R2_ADDR4" + else + echo "$R2_LLADDR" + fi +} + +redirect_no_socket() +{ + local family=$1; shift + + RET=0 + family_vars_set "$family" + topology_setup + redirect_route_set + + packet_send "$REDIRECT_PACKET_SIZE" + busywait "$BUSYWAIT_TIMEOUT" exception_gw_check "$(redirect_gw_new)" + check_err $? "No socket: exception does not carry the new gateway" + + log_test "IPv$family: Redirect: exception without a matching socket" +} + +redirect_no_socket_ipv4() +{ + redirect_no_socket 4 +} + +redirect_no_socket_ipv6() +{ + redirect_no_socket 6 +} + +redirect_socket() +{ + local family=$1; shift + + RET=0 + family_vars_set "$family" + topology_setup + redirect_route_set + socket_start + + packet_send "$REDIRECT_PACKET_SIZE" + busywait "$BUSYWAIT_TIMEOUT" exception_gw_check "$(redirect_gw_new)" + check_err $? "Matching socket: exception does not carry the new gateway" + + log_test "IPv$family: Redirect: exception with a matching socket" +} + +redirect_socket_ipv4() +{ + redirect_socket 4 +} + +redirect_socket_ipv6() +{ + redirect_socket 6 +} + +trap defer_scopes_cleanup EXIT +tests_run + +exit "$EXIT_STATUS" diff --git a/tools/testing/selftests/net/test_vxlan_mdb.sh b/tools/testing/selftests/net/test_vxlan_mdb.sh index 58da5de99ac4..f9600aabd4a2 100755 --- a/tools/testing/selftests/net/test_vxlan_mdb.sh +++ b/tools/testing/selftests/net/test_vxlan_mdb.sh @@ -685,6 +685,9 @@ star_g_common() run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $grp permanent filter_mode exclude source_list $grp dst $vtep_ip src_vni 10010" log_test $? 255 "Invalid source in source list" + run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $grp permanent filter_mode exclude source_list $all_zeros_grp dst $vtep_ip src_vni 10010" + log_test $? 255 "All-zeros source in source list" + run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $grp permanent source_list $src1 dst $vtep_ip src_vni 10010" log_test $? 255 "Source list without filter mode" } @@ -784,6 +787,9 @@ sg_common() run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $grp src $grp permanent dst $vtep_ip src_vni 10010" log_test $? 255 "(S, G) with an invalid source list" + run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $grp src $all_zeros_grp permanent dst $vtep_ip src_vni 10010" + log_test $? 255 "(S, G) with an all-zeros source" + run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $all_zeros_grp src $src permanent dst $vtep_ip src_vni 10010" log_test $? 255 "All-zeros group with source" } diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json b/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json index b2ca9d4e991b..e2b03f2b5e89 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json @@ -353,5 +353,28 @@ "teardown": [ "$TC qdisc del dev $DEV1 parent root drr" ] + }, + { + "id": "70fd", + "name": "Add u32 filter when node ID pool is exhausted (4096th filter rejected)", + "category": [ + "filter", + "u32" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DUMMY clsact", + "bash -c 'for i in {1..4095}; do echo filter add dev $DUMMY ingress prio 1 protocol ip u32 match u8 0 0 at 0; done | $TC -b -'" + ], + "cmdUnderTest": "$TC filter add dev $DUMMY ingress prio 1 protocol ip u32 match u8 0 0 at 0", + "expExitCode": "2", + "verifyCmd": "$TC -d filter show dev $DUMMY ingress", + "matchPattern": "fh 800::", + "matchCount": "4095", + "teardown": [ + "$TC qdisc del dev $DUMMY clsact" + ] } ] diff --git a/tools/workqueue/wq_dump.py b/tools/workqueue/wq_dump.py index 31afc24ef17b..9313ebe0c525 100644 --- a/tools/workqueue/wq_dump.py +++ b/tools/workqueue/wq_dump.py @@ -78,6 +78,12 @@ def cpumask_str(cpumask): wq_type_len = 9 +def wq_attrs(wq): + try: + return wq.attrs + except AttributeError: + return wq.unbound_attrs + def wq_type_str(wq): if wq.flags & WQ_BH: return f'{"bh":{wq_type_len}}' @@ -85,7 +91,7 @@ def wq_type_str(wq): if wq.flags & WQ_ORDERED: return f'{"ordered":{wq_type_len}}' else: - if wq.attrs.affn_strict: + if wq_attrs(wq).affn_strict: return f'{"unbound,S":{wq_type_len}}' else: return f'{"unbound":{wq_type_len}}' @@ -206,7 +212,7 @@ for wq in list_for_each_entry('struct workqueue_struct', workqueues.address_of_( print(f'{wq.name.string_().decode():{WQ_NAME_LEN}}', end='') if wq.flags & WQ_UNBOUND: - print(f' {cpumask_str(wq.attrs.cpumask):{ucpus_len}}', end='') + print(f' {cpumask_str(wq_attrs(wq).cpumask):{ucpus_len}}', end='') else: print(f' {"":{ucpus_len}}', end='') |