diff options
236 files changed, 2037 insertions, 1247 deletions
diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index 129f413ea349..3abc576ff797 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -61,22 +61,6 @@ attribute-sets: nested-attributes: bitset-bits - - name: u64-array - attributes: - - - name: u64 - type: nest - multi-attr: true - nested-attributes: u64 - - - name: s32-array - attributes: - - - name: s32 - type: nest - multi-attr: true - nested-attributes: s32 - - name: string attributes: - @@ -705,16 +689,16 @@ attribute-sets: type: u8 - name: corrected - type: nest - nested-attributes: u64-array + type: binary + sub-type: u64 - name: uncorr - type: nest - nested-attributes: u64-array + type: binary + sub-type: u64 - name: corr-bits - type: nest - nested-attributes: u64-array + type: binary + sub-type: u64 - name: fec attributes: @@ -827,8 +811,8 @@ attribute-sets: type: u32 - name: index - type: nest - nested-attributes: s32-array + type: binary + sub-type: s32 - name: module attributes: diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/devlink.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/devlink.rst index 3a7a714cc08f..3354ca3608ee 100644 --- a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/devlink.rst +++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/devlink.rst @@ -40,6 +40,7 @@ flow_steering_mode: Device flow steering mode --------------------------------------------- The flow steering mode parameter controls the flow steering mode of the driver. Two modes are supported: + 1. 'dmfs' - Device managed flow steering. 2. 'smfs' - Software/Driver managed flow steering. @@ -99,6 +100,7 @@ between representors and stacked devices. By default metadata is enabled on the supported devices in E-switch. Metadata is applicable only for E-switch in switchdev mode and users may disable it when NONE of the below use cases will be in use: + 1. HCA is in Dual/multi-port RoCE mode. 2. VF/SF representor bonding (Usually used for Live migration) 3. Stacked devices @@ -180,7 +182,8 @@ User commands examples: $ devlink health diagnose pci/0000:82:00.0 reporter tx -NOTE: This command has valid output only when interface is up, otherwise the command has empty output. +.. note:: + This command has valid output only when interface is up, otherwise the command has empty output. - Show number of tx errors indicated, number of recover flows ended successfully, is autorecover enabled and graceful period from last recover:: @@ -232,8 +235,9 @@ User commands examples: $ devlink health dump show pci/0000:82:00.0 reporter fw -NOTE: This command can run only on the PF which has fw tracer ownership, -running it on other PF or any VF will return "Operation not permitted". +.. note:: + This command can run only on the PF which has fw tracer ownership, + running it on other PF or any VF will return "Operation not permitted". fw fatal reporter ----------------- @@ -256,7 +260,8 @@ User commands examples: $ devlink health dump show pci/0000:82:00.1 reporter fw_fatal -NOTE: This command can run only on PF. +.. note:: + This command can run only on PF. vnic reporter ------------- @@ -265,28 +270,37 @@ It is responsible for querying the vnic diagnostic counters from fw and displayi them in realtime. Description of the vnic counters: -total_q_under_processor_handle: number of queues in an error state due to -an async error or errored command. -send_queue_priority_update_flow: number of QP/SQ priority/SL update -events. -cq_overrun: number of times CQ entered an error state due to an -overflow. -async_eq_overrun: number of times an EQ mapped to async events was -overrun. -comp_eq_overrun: number of times an EQ mapped to completion events was -overrun. -quota_exceeded_command: number of commands issued and failed due to quota -exceeded. -invalid_command: number of commands issued and failed dues to any reason -other than quota exceeded. -nic_receive_steering_discard: number of packets that completed RX flow -steering but were discarded due to a mismatch in flow table. + +- total_q_under_processor_handle + number of queues in an error state due to + an async error or errored command. +- send_queue_priority_update_flow + number of QP/SQ priority/SL update events. +- cq_overrun + number of times CQ entered an error state due to an overflow. +- async_eq_overrun + number of times an EQ mapped to async events was overrun. + comp_eq_overrun number of times an EQ mapped to completion events was + overrun. +- quota_exceeded_command + number of commands issued and failed due to quota exceeded. +- invalid_command + number of commands issued and failed dues to any reason other than quota + exceeded. +- nic_receive_steering_discard + number of packets that completed RX flow + steering but were discarded due to a mismatch in flow table. User commands examples: -- Diagnose PF/VF vnic counters + +- Diagnose PF/VF vnic counters:: + $ devlink health diagnose pci/0000:82:00.1 reporter vnic + - Diagnose representor vnic counters (performed by supplying devlink port of the - representor, which can be obtained via devlink port command) + representor, which can be obtained via devlink port command):: + $ devlink health diagnose pci/0000:82:00.1/65537 reporter vnic -NOTE: This command can run over all interfaces such as PF/VF and representor ports. +.. note:: + This command can run over all interfaces such as PF/VF and representor ports. diff --git a/Documentation/trace/histogram.rst b/Documentation/trace/histogram.rst index 479c9eac6335..3c9b263de9c2 100644 --- a/Documentation/trace/histogram.rst +++ b/Documentation/trace/histogram.rst @@ -35,7 +35,7 @@ Documentation written by Tom Zanussi in place of an explicit value field - this is simply a count of event hits. If 'values' isn't specified, an implicit 'hitcount' value will be automatically created and used as the only value. - Keys can be any field, or the special string 'stacktrace', which + Keys can be any field, or the special string 'common_stacktrace', which will use the event's kernel stacktrace as the key. The keywords 'keys' or 'key' can be used to specify keys, and the keywords 'values', 'vals', or 'val' can be used to specify values. Compound @@ -54,7 +54,7 @@ Documentation written by Tom Zanussi 'compatible' if the fields named in the trigger share the same number and type of fields and those fields also have the same names. Note that any two events always share the compatible 'hitcount' and - 'stacktrace' fields and can therefore be combined using those + 'common_stacktrace' fields and can therefore be combined using those fields, however pointless that may be. 'hist' triggers add a 'hist' file to each event's subdirectory. @@ -547,9 +547,9 @@ Extended error information the hist trigger display symbolic call_sites, we can have the hist trigger additionally display the complete set of kernel stack traces that led to each call_site. To do that, we simply use the special - value 'stacktrace' for the key parameter:: + value 'common_stacktrace' for the key parameter:: - # echo 'hist:keys=stacktrace:values=bytes_req,bytes_alloc:sort=bytes_alloc' > \ + # echo 'hist:keys=common_stacktrace:values=bytes_req,bytes_alloc:sort=bytes_alloc' > \ /sys/kernel/tracing/events/kmem/kmalloc/trigger The above trigger will use the kernel stack trace in effect when an @@ -561,9 +561,9 @@ Extended error information every callpath to a kmalloc for a kernel compile):: # cat /sys/kernel/tracing/events/kmem/kmalloc/hist - # trigger info: hist:keys=stacktrace:vals=bytes_req,bytes_alloc:sort=bytes_alloc:size=2048 [active] + # trigger info: hist:keys=common_stacktrace:vals=bytes_req,bytes_alloc:sort=bytes_alloc:size=2048 [active] - { stacktrace: + { common_stacktrace: __kmalloc_track_caller+0x10b/0x1a0 kmemdup+0x20/0x50 hidraw_report_event+0x8a/0x120 [hid] @@ -581,7 +581,7 @@ Extended error information cpu_startup_entry+0x315/0x3e0 rest_init+0x7c/0x80 } hitcount: 3 bytes_req: 21 bytes_alloc: 24 - { stacktrace: + { common_stacktrace: __kmalloc_track_caller+0x10b/0x1a0 kmemdup+0x20/0x50 hidraw_report_event+0x8a/0x120 [hid] @@ -596,7 +596,7 @@ Extended error information do_IRQ+0x5a/0xf0 ret_from_intr+0x0/0x30 } hitcount: 3 bytes_req: 21 bytes_alloc: 24 - { stacktrace: + { common_stacktrace: kmem_cache_alloc_trace+0xeb/0x150 aa_alloc_task_context+0x27/0x40 apparmor_cred_prepare+0x1f/0x50 @@ -608,7 +608,7 @@ Extended error information . . . - { stacktrace: + { common_stacktrace: __kmalloc+0x11b/0x1b0 i915_gem_execbuffer2+0x6c/0x2c0 [i915] drm_ioctl+0x349/0x670 [drm] @@ -616,7 +616,7 @@ Extended error information SyS_ioctl+0x81/0xa0 system_call_fastpath+0x12/0x6a } hitcount: 17726 bytes_req: 13944120 bytes_alloc: 19593808 - { stacktrace: + { common_stacktrace: __kmalloc+0x11b/0x1b0 load_elf_phdrs+0x76/0xa0 load_elf_binary+0x102/0x1650 @@ -625,7 +625,7 @@ Extended error information SyS_execve+0x3a/0x50 return_from_execve+0x0/0x23 } hitcount: 33348 bytes_req: 17152128 bytes_alloc: 20226048 - { stacktrace: + { common_stacktrace: kmem_cache_alloc_trace+0xeb/0x150 apparmor_file_alloc_security+0x27/0x40 security_file_alloc+0x16/0x20 @@ -636,7 +636,7 @@ Extended error information SyS_open+0x1e/0x20 system_call_fastpath+0x12/0x6a } hitcount: 4766422 bytes_req: 9532844 bytes_alloc: 38131376 - { stacktrace: + { common_stacktrace: __kmalloc+0x11b/0x1b0 seq_buf_alloc+0x1b/0x50 seq_read+0x2cc/0x370 @@ -1026,7 +1026,7 @@ Extended error information First we set up an initially paused stacktrace trigger on the netif_receive_skb event:: - # echo 'hist:key=stacktrace:vals=len:pause' > \ + # echo 'hist:key=common_stacktrace:vals=len:pause' > \ /sys/kernel/tracing/events/net/netif_receive_skb/trigger Next, we set up an 'enable_hist' trigger on the sched_process_exec @@ -1060,9 +1060,9 @@ Extended error information $ wget https://www.kernel.org/pub/linux/kernel/v3.x/patch-3.19.xz # cat /sys/kernel/tracing/events/net/netif_receive_skb/hist - # trigger info: hist:keys=stacktrace:vals=len:sort=hitcount:size=2048 [paused] + # trigger info: hist:keys=common_stacktrace:vals=len:sort=hitcount:size=2048 [paused] - { stacktrace: + { common_stacktrace: __netif_receive_skb_core+0x46d/0x990 __netif_receive_skb+0x18/0x60 netif_receive_skb_internal+0x23/0x90 @@ -1079,7 +1079,7 @@ Extended error information kthread+0xd2/0xf0 ret_from_fork+0x42/0x70 } hitcount: 85 len: 28884 - { stacktrace: + { common_stacktrace: __netif_receive_skb_core+0x46d/0x990 __netif_receive_skb+0x18/0x60 netif_receive_skb_internal+0x23/0x90 @@ -1097,7 +1097,7 @@ Extended error information irq_thread+0x11f/0x150 kthread+0xd2/0xf0 } hitcount: 98 len: 664329 - { stacktrace: + { common_stacktrace: __netif_receive_skb_core+0x46d/0x990 __netif_receive_skb+0x18/0x60 process_backlog+0xa8/0x150 @@ -1115,7 +1115,7 @@ Extended error information inet_sendmsg+0x64/0xa0 sock_sendmsg+0x3d/0x50 } hitcount: 115 len: 13030 - { stacktrace: + { common_stacktrace: __netif_receive_skb_core+0x46d/0x990 __netif_receive_skb+0x18/0x60 netif_receive_skb_internal+0x23/0x90 @@ -1142,14 +1142,14 @@ Extended error information into the histogram. In order to avoid having to set everything up again, we can just clear the histogram first:: - # echo 'hist:key=stacktrace:vals=len:clear' >> \ + # echo 'hist:key=common_stacktrace:vals=len:clear' >> \ /sys/kernel/tracing/events/net/netif_receive_skb/trigger Just to verify that it is in fact cleared, here's what we now see in the hist file:: # cat /sys/kernel/tracing/events/net/netif_receive_skb/hist - # trigger info: hist:keys=stacktrace:vals=len:sort=hitcount:size=2048 [paused] + # trigger info: hist:keys=common_stacktrace:vals=len:sort=hitcount:size=2048 [paused] Totals: Hits: 0 @@ -1485,12 +1485,12 @@ Extended error information And here's an example that shows how to combine histogram data from any two events even if they don't share any 'compatible' fields - other than 'hitcount' and 'stacktrace'. These commands create a + other than 'hitcount' and 'common_stacktrace'. These commands create a couple of triggers named 'bar' using those fields:: - # echo 'hist:name=bar:key=stacktrace:val=hitcount' > \ + # echo 'hist:name=bar:key=common_stacktrace:val=hitcount' > \ /sys/kernel/tracing/events/sched/sched_process_fork/trigger - # echo 'hist:name=bar:key=stacktrace:val=hitcount' > \ + # echo 'hist:name=bar:key=common_stacktrace:val=hitcount' > \ /sys/kernel/tracing/events/net/netif_rx/trigger And displaying the output of either shows some interesting if @@ -1501,16 +1501,16 @@ Extended error information # event histogram # - # trigger info: hist:name=bar:keys=stacktrace:vals=hitcount:sort=hitcount:size=2048 [active] + # trigger info: hist:name=bar:keys=common_stacktrace:vals=hitcount:sort=hitcount:size=2048 [active] # - { stacktrace: + { common_stacktrace: kernel_clone+0x18e/0x330 kernel_thread+0x29/0x30 kthreadd+0x154/0x1b0 ret_from_fork+0x3f/0x70 } hitcount: 1 - { stacktrace: + { common_stacktrace: netif_rx_internal+0xb2/0xd0 netif_rx_ni+0x20/0x70 dev_loopback_xmit+0xaa/0xd0 @@ -1528,7 +1528,7 @@ Extended error information call_cpuidle+0x3b/0x60 cpu_startup_entry+0x22d/0x310 } hitcount: 1 - { stacktrace: + { common_stacktrace: netif_rx_internal+0xb2/0xd0 netif_rx_ni+0x20/0x70 dev_loopback_xmit+0xaa/0xd0 @@ -1543,7 +1543,7 @@ Extended error information SyS_sendto+0xe/0x10 entry_SYSCALL_64_fastpath+0x12/0x6a } hitcount: 2 - { stacktrace: + { common_stacktrace: netif_rx_internal+0xb2/0xd0 netif_rx+0x1c/0x60 loopback_xmit+0x6c/0xb0 @@ -1561,7 +1561,7 @@ Extended error information sock_sendmsg+0x38/0x50 ___sys_sendmsg+0x14e/0x270 } hitcount: 76 - { stacktrace: + { common_stacktrace: netif_rx_internal+0xb2/0xd0 netif_rx+0x1c/0x60 loopback_xmit+0x6c/0xb0 @@ -1579,7 +1579,7 @@ Extended error information sock_sendmsg+0x38/0x50 ___sys_sendmsg+0x269/0x270 } hitcount: 77 - { stacktrace: + { common_stacktrace: netif_rx_internal+0xb2/0xd0 netif_rx+0x1c/0x60 loopback_xmit+0x6c/0xb0 @@ -1597,7 +1597,7 @@ Extended error information sock_sendmsg+0x38/0x50 SYSC_sendto+0xef/0x170 } hitcount: 88 - { stacktrace: + { common_stacktrace: kernel_clone+0x18e/0x330 SyS_clone+0x19/0x20 entry_SYSCALL_64_fastpath+0x12/0x6a @@ -1949,7 +1949,7 @@ uninterruptible state:: # cd /sys/kernel/tracing # echo 's:block_lat pid_t pid; u64 delta; unsigned long[] stack;' > dynamic_events - # echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=stacktrace if prev_state == 2' >> events/sched/sched_switch/trigger + # echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=common_stacktrace if prev_state == 2' >> events/sched/sched_switch/trigger # echo 'hist:keys=prev_pid:delta=common_timestamp.usecs-$ts,s=$st:onmax($delta).trace(block_lat,prev_pid,$delta,$s)' >> events/sched/sched_switch/trigger # echo 1 > events/synthetic/block_lat/enable # cat trace diff --git a/MAINTAINERS b/MAINTAINERS index 250518fc70ff..8fdb06662395 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -956,7 +956,8 @@ F: Documentation/networking/device_drivers/ethernet/amazon/ena.rst F: drivers/net/ethernet/amazon/ AMAZON RDMA EFA DRIVER -M: Gal Pressman <galpress@amazon.com> +M: Michael Margolin <mrgolin@amazon.com> +R: Gal Pressman <gal.pressman@linux.dev> R: Yossi Leybovich <sleybo@amazon.com> L: linux-rdma@vger.kernel.org S: Supported @@ -1600,7 +1601,7 @@ F: drivers/media/i2c/ar0521.c ARASAN NAND CONTROLLER DRIVER M: Miquel Raynal <miquel.raynal@bootlin.com> -M: Naga Sureshkumar Relli <nagasure@xilinx.com> +R: Michal Simek <michal.simek@amd.com> L: linux-mtd@lists.infradead.org S: Maintained F: Documentation/devicetree/bindings/mtd/arasan,nand-controller.yaml @@ -1763,7 +1764,7 @@ F: include/linux/amba/mmci.h ARM PRIMECELL PL35X NAND CONTROLLER DRIVER M: Miquel Raynal <miquel.raynal@bootlin.com> -M: Naga Sureshkumar Relli <nagasure@xilinx.com> +R: Michal Simek <michal.simek@amd.com> L: linux-mtd@lists.infradead.org S: Maintained F: Documentation/devicetree/bindings/mtd/arm,pl353-nand-r2p1.yaml @@ -1771,7 +1772,7 @@ F: drivers/mtd/nand/raw/pl35x-nand-controller.c ARM PRIMECELL PL35X SMC DRIVER M: Miquel Raynal <miquel.raynal@bootlin.com> -M: Naga Sureshkumar Relli <nagasure@xilinx.com> +R: Michal Simek <michal.simek@amd.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: Documentation/devicetree/bindings/memory-controllers/arm,pl35x-smc.yaml @@ -5138,7 +5139,7 @@ X: drivers/clk/clkdev.c COMMON INTERNET FILE SYSTEM CLIENT (CIFS and SMB3) M: Steve French <sfrench@samba.org> -R: Paulo Alcantara <pc@cjr.nz> (DFS, global name space) +R: Paulo Alcantara <pc@manguebit.com> (DFS, global name space) R: Ronnie Sahlberg <lsahlber@redhat.com> (directory leases, sparse files) R: Shyam Prasad N <sprasad@microsoft.com> (multichannel) R: Tom Talpey <tom@talpey.com> (RDMA, smbdirect) @@ -9343,7 +9344,7 @@ F: include/linux/hisi_acc_qm.h HISILICON ROCE DRIVER M: Haoyue Xu <xuhaoyue1@hisilicon.com> -M: Wenpeng Liang <liangwenpeng@huawei.com> +M: Junxian Huang <huangjunxian6@hisilicon.com> L: linux-rdma@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/infiniband/hisilicon-hns-roce.txt diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 348c0fa1fc8c..2bb0c38419ff 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -799,8 +799,11 @@ menu "Power management options" source "kernel/power/Kconfig" +# Hibernation is only possible on systems where the SBI implementation has +# marked its reserved memory as not accessible from, or does not run +# from the same memory as, Linux config ARCH_HIBERNATION_POSSIBLE - def_bool y + def_bool NONPORTABLE config ARCH_HIBERNATION_HEADER def_bool HIBERNATION diff --git a/arch/riscv/errata/Makefile b/arch/riscv/errata/Makefile index a1055965fbee..7b2637c8c332 100644 --- a/arch/riscv/errata/Makefile +++ b/arch/riscv/errata/Makefile @@ -1,2 +1,6 @@ +ifdef CONFIG_RELOCATABLE +KBUILD_CFLAGS += -fno-pie +endif + obj-$(CONFIG_ERRATA_SIFIVE) += sifive/ obj-$(CONFIG_ERRATA_THEAD) += thead/ diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h index fe6f23006641..ce1ebda1a49a 100644 --- a/arch/riscv/include/asm/hugetlb.h +++ b/arch/riscv/include/asm/hugetlb.h @@ -36,6 +36,9 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte, int dirty); +#define __HAVE_ARCH_HUGE_PTEP_GET +pte_t huge_ptep_get(pte_t *ptep); + pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags); #define arch_make_huge_pte arch_make_huge_pte diff --git a/arch/riscv/include/asm/perf_event.h b/arch/riscv/include/asm/perf_event.h index d42c901f9a97..665bbc9b2f84 100644 --- a/arch/riscv/include/asm/perf_event.h +++ b/arch/riscv/include/asm/perf_event.h @@ -10,4 +10,11 @@ #include <linux/perf_event.h> #define perf_arch_bpf_user_pt_regs(regs) (struct user_regs_struct *)regs + +#define perf_arch_fetch_caller_regs(regs, __ip) { \ + (regs)->epc = (__ip); \ + (regs)->s0 = (unsigned long) __builtin_frame_address(0); \ + (regs)->sp = current_stack_pointer; \ + (regs)->status = SR_PP; \ +} #endif /* _ASM_RISCV_PERF_EVENT_H */ diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index fbdccc21418a..153864e4f399 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -23,6 +23,10 @@ ifdef CONFIG_FTRACE CFLAGS_REMOVE_alternative.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_cpufeature.o = $(CC_FLAGS_FTRACE) endif +ifdef CONFIG_RELOCATABLE +CFLAGS_alternative.o += -fno-pie +CFLAGS_cpufeature.o += -fno-pie +endif ifdef CONFIG_KASAN KASAN_SANITIZE_alternative.o := n KASAN_SANITIZE_cpufeature.o := n diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c index a163a3e0f0d4..e0ef56dc57b9 100644 --- a/arch/riscv/mm/hugetlbpage.c +++ b/arch/riscv/mm/hugetlbpage.c @@ -3,6 +3,30 @@ #include <linux/err.h> #ifdef CONFIG_RISCV_ISA_SVNAPOT +pte_t huge_ptep_get(pte_t *ptep) +{ + unsigned long pte_num; + int i; + pte_t orig_pte = ptep_get(ptep); + + if (!pte_present(orig_pte) || !pte_napot(orig_pte)) + return orig_pte; + + pte_num = napot_pte_num(napot_cont_order(orig_pte)); + + for (i = 0; i < pte_num; i++, ptep++) { + pte_t pte = ptep_get(ptep); + + if (pte_dirty(pte)) + orig_pte = pte_mkdirty(orig_pte); + + if (pte_young(pte)) + orig_pte = pte_mkyoung(orig_pte); + } + + return orig_pte; +} + pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, @@ -218,6 +242,7 @@ void huge_ptep_set_wrprotect(struct mm_struct *mm, { pte_t pte = ptep_get(ptep); unsigned long order; + pte_t orig_pte; int i, pte_num; if (!pte_napot(pte)) { @@ -228,9 +253,12 @@ void huge_ptep_set_wrprotect(struct mm_struct *mm, order = napot_cont_order(pte); pte_num = napot_pte_num(order); ptep = huge_pte_offset(mm, addr, napot_cont_size(order)); + orig_pte = get_clear_contig_flush(mm, addr, ptep, pte_num); + + orig_pte = pte_wrprotect(orig_pte); for (i = 0; i < pte_num; i++, addr += PAGE_SIZE, ptep++) - ptep_set_wrprotect(mm, addr, ptep); + set_pte_at(mm, addr, ptep, orig_pte); } pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 747e5b1ef02d..c6bb966e4123 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -922,9 +922,9 @@ static void __init create_kernel_page_table(pgd_t *pgdir, bool early) static void __init create_fdt_early_page_table(uintptr_t fix_fdt_va, uintptr_t dtb_pa) { +#ifndef CONFIG_BUILTIN_DTB uintptr_t pa = dtb_pa & ~(PMD_SIZE - 1); -#ifndef CONFIG_BUILTIN_DTB /* Make sure the fdt fixmap address is always aligned on PMD size */ BUILD_BUG_ON(FIX_FDT % (PMD_SIZE / PAGE_SIZE)); diff --git a/arch/x86/crypto/aria-aesni-avx-asm_64.S b/arch/x86/crypto/aria-aesni-avx-asm_64.S index 7c1abc513f34..9556dacd9841 100644 --- a/arch/x86/crypto/aria-aesni-avx-asm_64.S +++ b/arch/x86/crypto/aria-aesni-avx-asm_64.S @@ -773,8 +773,6 @@ .octa 0x3F893781E95FE1576CDA64D2BA0CB204 #ifdef CONFIG_AS_GFNI -.section .rodata.cst8, "aM", @progbits, 8 -.align 8 /* AES affine: */ #define tf_aff_const BV8(1, 1, 0, 0, 0, 1, 1, 0) .Ltf_aff_bitmatrix: diff --git a/arch/x86/include/asm/fpu/sched.h b/arch/x86/include/asm/fpu/sched.h index c2d6cd78ed0c..78fcde7b1f07 100644 --- a/arch/x86/include/asm/fpu/sched.h +++ b/arch/x86/include/asm/fpu/sched.h @@ -39,7 +39,7 @@ extern void fpu_flush_thread(void); static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu) { if (cpu_feature_enabled(X86_FEATURE_FPU) && - !(current->flags & (PF_KTHREAD | PF_IO_WORKER))) { + !(current->flags & (PF_KTHREAD | PF_USER_WORKER))) { save_fpregs_to_fpstate(old_fpu); /* * The save operation preserved register state, so the diff --git a/arch/x86/kernel/fpu/context.h b/arch/x86/kernel/fpu/context.h index 9fcfa5c4dad7..af5cbdd9bd29 100644 --- a/arch/x86/kernel/fpu/context.h +++ b/arch/x86/kernel/fpu/context.h @@ -57,7 +57,7 @@ static inline void fpregs_restore_userregs(void) struct fpu *fpu = ¤t->thread.fpu; int cpu = smp_processor_id(); - if (WARN_ON_ONCE(current->flags & (PF_KTHREAD | PF_IO_WORKER))) + if (WARN_ON_ONCE(current->flags & (PF_KTHREAD | PF_USER_WORKER))) return; if (!fpregs_state_valid(fpu, cpu)) { diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index caf33486dc5e..1015af1ae562 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -426,7 +426,7 @@ void kernel_fpu_begin_mask(unsigned int kfpu_mask) this_cpu_write(in_kernel_fpu, true); - if (!(current->flags & (PF_KTHREAD | PF_IO_WORKER)) && + if (!(current->flags & (PF_KTHREAD | PF_USER_WORKER)) && !test_thread_flag(TIF_NEED_FPU_LOAD)) { set_thread_flag(TIF_NEED_FPU_LOAD); save_fpregs_to_fpstate(¤t->thread.fpu); diff --git a/block/blk-settings.c b/block/blk-settings.c index 896b4654ab00..4dd59059b788 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -915,6 +915,7 @@ static bool disk_has_partitions(struct gendisk *disk) void disk_set_zoned(struct gendisk *disk, enum blk_zoned_model model) { struct request_queue *q = disk->queue; + unsigned int old_model = q->limits.zoned; switch (model) { case BLK_ZONED_HM: @@ -952,7 +953,7 @@ void disk_set_zoned(struct gendisk *disk, enum blk_zoned_model model) */ blk_queue_zone_write_granularity(q, queue_logical_block_size(q)); - } else { + } else if (old_model != BLK_ZONED_NONE) { disk_clear_zone_settings(disk); } } diff --git a/drivers/acpi/apei/apei-internal.h b/drivers/acpi/apei/apei-internal.h index 1d6ef9654725..67c2c3b959e1 100644 --- a/drivers/acpi/apei/apei-internal.h +++ b/drivers/acpi/apei/apei-internal.h @@ -7,7 +7,6 @@ #ifndef APEI_INTERNAL_H #define APEI_INTERNAL_H -#include <linux/cper.h> #include <linux/acpi.h> struct apei_exec_context; @@ -130,10 +129,5 @@ static inline u32 cper_estatus_len(struct acpi_hest_generic_status *estatus) return sizeof(*estatus) + estatus->data_length; } -void cper_estatus_print(const char *pfx, - const struct acpi_hest_generic_status *estatus); -int cper_estatus_check_header(const struct acpi_hest_generic_status *estatus); -int cper_estatus_check(const struct acpi_hest_generic_status *estatus); - int apei_osc_setup(void); #endif diff --git a/drivers/acpi/apei/bert.c b/drivers/acpi/apei/bert.c index c23eb75866d0..7514e38d5640 100644 --- a/drivers/acpi/apei/bert.c +++ b/drivers/acpi/apei/bert.c @@ -23,6 +23,7 @@ #include <linux/module.h> #include <linux/init.h> #include <linux/acpi.h> +#include <linux/cper.h> #include <linux/io.h> #include "apei-internal.h" diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 7bb12deab70c..8ce90284eb34 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -2694,18 +2694,36 @@ static unsigned int atapi_xlat(struct ata_queued_cmd *qc) return 0; } -static struct ata_device *ata_find_dev(struct ata_port *ap, int devno) +static struct ata_device *ata_find_dev(struct ata_port *ap, unsigned int devno) { - if (!sata_pmp_attached(ap)) { - if (likely(devno >= 0 && - devno < ata_link_max_devices(&ap->link))) + /* + * For the non-PMP case, ata_link_max_devices() returns 1 (SATA case), + * or 2 (IDE master + slave case). However, the former case includes + * libsas hosted devices which are numbered per scsi host, leading + * to devno potentially being larger than 0 but with each struct + * ata_device having its own struct ata_port and struct ata_link. + * To accommodate these, ignore devno and always use device number 0. + */ + if (likely(!sata_pmp_attached(ap))) { + int link_max_devices = ata_link_max_devices(&ap->link); + + if (link_max_devices == 1) + return &ap->link.device[0]; + + if (devno < link_max_devices) return &ap->link.device[devno]; - } else { - if (likely(devno >= 0 && - devno < ap->nr_pmp_links)) - return &ap->pmp_link[devno].device[0]; + + return NULL; } + /* + * For PMP-attached devices, the device number corresponds to C + * (channel) of SCSI [H:C:I:L], indicating the port pmp link + * for the device. + */ + if (devno < ap->nr_pmp_links) + return &ap->pmp_link[devno].device[0]; + return NULL; } diff --git a/drivers/base/regmap/Kconfig b/drivers/base/regmap/Kconfig index 33a8366e22a5..0db2021f7477 100644 --- a/drivers/base/regmap/Kconfig +++ b/drivers/base/regmap/Kconfig @@ -4,16 +4,23 @@ # subsystems should select the appropriate symbols. config REGMAP + bool "Register Map support" if KUNIT_ALL_TESTS default y if (REGMAP_I2C || REGMAP_SPI || REGMAP_SPMI || REGMAP_W1 || REGMAP_AC97 || REGMAP_MMIO || REGMAP_IRQ || REGMAP_SOUNDWIRE || REGMAP_SOUNDWIRE_MBQ || REGMAP_SCCB || REGMAP_I3C || REGMAP_SPI_AVMM || REGMAP_MDIO || REGMAP_FSI) select IRQ_DOMAIN if REGMAP_IRQ select MDIO_BUS if REGMAP_MDIO - bool + help + Enable support for the Register Map (regmap) access API. + + Usually, this option is automatically selected when needed. + However, you may want to enable it manually for running the regmap + KUnit tests. + + If unsure, say N. config REGMAP_KUNIT tristate "KUnit tests for regmap" - depends on KUNIT + depends on KUNIT && REGMAP default KUNIT_ALL_TESTS - select REGMAP select REGMAP_RAM config REGMAP_AC97 diff --git a/drivers/base/regmap/regcache-maple.c b/drivers/base/regmap/regcache-maple.c index 9b1b559107ef..c2e3a0f6c218 100644 --- a/drivers/base/regmap/regcache-maple.c +++ b/drivers/base/regmap/regcache-maple.c @@ -203,15 +203,18 @@ static int regcache_maple_sync(struct regmap *map, unsigned int min, mas_for_each(&mas, entry, max) { for (r = max(mas.index, lmin); r <= min(mas.last, lmax); r++) { + mas_pause(&mas); + rcu_read_unlock(); ret = regcache_sync_val(map, r, entry[r - mas.index]); if (ret != 0) goto out; + rcu_read_lock(); } } -out: rcu_read_unlock(); +out: map->cache_bypass = false; return ret; diff --git a/drivers/base/regmap/regmap-sdw.c b/drivers/base/regmap/regmap-sdw.c index 09899ae99fc1..159c0b740b00 100644 --- a/drivers/base/regmap/regmap-sdw.c +++ b/drivers/base/regmap/regmap-sdw.c @@ -59,6 +59,10 @@ static int regmap_sdw_config_check(const struct regmap_config *config) if (config->pad_bits != 0) return -ENOTSUPP; + /* Only bulk writes are supported not multi-register writes */ + if (config->can_multi_write) + return -ENOTSUPP; + return 0; } diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index db7851f0e3b8..fa2d3fba6ac9 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -2082,6 +2082,8 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg, size_t val_count = val_len / val_bytes; size_t chunk_count, chunk_bytes; size_t chunk_regs = val_count; + size_t max_data = map->max_raw_write - map->format.reg_bytes - + map->format.pad_bytes; int ret, i; if (!val_count) @@ -2089,8 +2091,8 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg, if (map->use_single_write) chunk_regs = 1; - else if (map->max_raw_write && val_len > map->max_raw_write) - chunk_regs = map->max_raw_write / val_bytes; + else if (map->max_raw_write && val_len > max_data) + chunk_regs = max_data / val_bytes; chunk_count = val_count / chunk_regs; chunk_bytes = chunk_regs * val_bytes; diff --git a/drivers/char/tpm/tpm_tis_core.h b/drivers/char/tpm/tpm_tis_core.h index e978f457fd4d..610bfadb6acf 100644 --- a/drivers/char/tpm/tpm_tis_core.h +++ b/drivers/char/tpm/tpm_tis_core.h @@ -84,10 +84,10 @@ enum tis_defaults { #define ILB_REMAP_SIZE 0x100 enum tpm_tis_flags { - TPM_TIS_ITPM_WORKAROUND = BIT(0), - TPM_TIS_INVALID_STATUS = BIT(1), - TPM_TIS_DEFAULT_CANCELLATION = BIT(2), - TPM_TIS_IRQ_TESTED = BIT(3), + TPM_TIS_ITPM_WORKAROUND = 0, + TPM_TIS_INVALID_STATUS = 1, + TPM_TIS_DEFAULT_CANCELLATION = 2, + TPM_TIS_IRQ_TESTED = 3, }; struct tpm_tis_data { diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c index 8858470246e1..ee3a219e3a89 100644 --- a/drivers/dma/at_hdmac.c +++ b/drivers/dma/at_hdmac.c @@ -132,7 +132,7 @@ #define ATC_DST_PIP BIT(12) /* Destination Picture-in-Picture enabled */ #define ATC_SRC_DSCR_DIS BIT(16) /* Src Descriptor fetch disable */ #define ATC_DST_DSCR_DIS BIT(20) /* Dst Descriptor fetch disable */ -#define ATC_FC GENMASK(22, 21) /* Choose Flow Controller */ +#define ATC_FC GENMASK(23, 21) /* Choose Flow Controller */ #define ATC_FC_MEM2MEM 0x0 /* Mem-to-Mem (DMA) */ #define ATC_FC_MEM2PER 0x1 /* Mem-to-Periph (DMA) */ #define ATC_FC_PER2MEM 0x2 /* Periph-to-Mem (DMA) */ @@ -153,8 +153,6 @@ #define ATC_AUTO BIT(31) /* Auto multiple buffer tx enable */ /* Bitfields in CFG */ -#define ATC_PER_MSB(h) ((0x30U & (h)) >> 4) /* Extract most significant bits of a handshaking identifier */ - #define ATC_SRC_PER GENMASK(3, 0) /* Channel src rq associated with periph handshaking ifc h */ #define ATC_DST_PER GENMASK(7, 4) /* Channel dst rq associated with periph handshaking ifc h */ #define ATC_SRC_REP BIT(8) /* Source Replay Mod */ @@ -181,10 +179,15 @@ #define ATC_DPIP_HOLE GENMASK(15, 0) #define ATC_DPIP_BOUNDARY GENMASK(25, 16) -#define ATC_SRC_PER_ID(id) (FIELD_PREP(ATC_SRC_PER_MSB, (id)) | \ - FIELD_PREP(ATC_SRC_PER, (id))) -#define ATC_DST_PER_ID(id) (FIELD_PREP(ATC_DST_PER_MSB, (id)) | \ - FIELD_PREP(ATC_DST_PER, (id))) +#define ATC_PER_MSB GENMASK(5, 4) /* Extract MSBs of a handshaking identifier */ +#define ATC_SRC_PER_ID(id) \ + ({ typeof(id) _id = (id); \ + FIELD_PREP(ATC_SRC_PER_MSB, FIELD_GET(ATC_PER_MSB, _id)) | \ + FIELD_PREP(ATC_SRC_PER, _id); }) +#define ATC_DST_PER_ID(id) \ + ({ typeof(id) _id = (id); \ + FIELD_PREP(ATC_DST_PER_MSB, FIELD_GET(ATC_PER_MSB, _id)) | \ + FIELD_PREP(ATC_DST_PER, _id); }) diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 7da6d9b6098e..c3b37168b21f 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -1102,6 +1102,8 @@ at_xdmac_prep_interleaved(struct dma_chan *chan, NULL, src_addr, dst_addr, xt, xt->sgl); + if (!first) + return NULL; /* Length of the block is (BLEN+1) microblocks. */ for (i = 0; i < xt->numf - 1; i++) @@ -1132,8 +1134,9 @@ at_xdmac_prep_interleaved(struct dma_chan *chan, src_addr, dst_addr, xt, chunk); if (!desc) { - list_splice_tail_init(&first->descs_list, - &atchan->free_descs_list); + if (first) + list_splice_tail_init(&first->descs_list, + &atchan->free_descs_list); return NULL; } diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c index ecbf67c2ad2b..d32deb9b4e3d 100644 --- a/drivers/dma/idxd/cdev.c +++ b/drivers/dma/idxd/cdev.c @@ -277,7 +277,6 @@ static int idxd_cdev_open(struct inode *inode, struct file *filp) if (wq_dedicated(wq)) { rc = idxd_wq_set_pasid(wq, pasid); if (rc < 0) { - iommu_sva_unbind_device(sva); dev_err(dev, "wq set pasid failed: %d\n", rc); goto failed_set_pasid; } diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index 0d9257fbdfb0..b4731fe6bbc1 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -1050,7 +1050,7 @@ static bool _trigger(struct pl330_thread *thrd) return true; } -static bool _start(struct pl330_thread *thrd) +static bool pl330_start_thread(struct pl330_thread *thrd) { switch (_state(thrd)) { case PL330_STATE_FAULT_COMPLETING: @@ -1702,7 +1702,7 @@ static int pl330_update(struct pl330_dmac *pl330) thrd->req_running = -1; /* Get going again ASAP */ - _start(thrd); + pl330_start_thread(thrd); /* For now, just make a list of callbacks to be done */ list_add_tail(&descdone->rqd, &pl330->req_done); @@ -2089,7 +2089,7 @@ static void pl330_tasklet(struct tasklet_struct *t) } else { /* Make sure the PL330 Channel thread is active */ spin_lock(&pch->thread->dmac->lock); - _start(pch->thread); + pl330_start_thread(pch->thread); spin_unlock(&pch->thread->dmac->lock); } @@ -2107,7 +2107,7 @@ static void pl330_tasklet(struct tasklet_struct *t) if (power_down) { pch->active = true; spin_lock(&pch->thread->dmac->lock); - _start(pch->thread); + pl330_start_thread(pch->thread); spin_unlock(&pch->thread->dmac->lock); power_down = false; } diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c index fc3a2a05ab7b..b8329a23728d 100644 --- a/drivers/dma/ti/k3-udma.c +++ b/drivers/dma/ti/k3-udma.c @@ -5527,7 +5527,7 @@ static int udma_probe(struct platform_device *pdev) return ret; } -static int udma_pm_suspend(struct device *dev) +static int __maybe_unused udma_pm_suspend(struct device *dev) { struct udma_dev *ud = dev_get_drvdata(dev); struct dma_device *dma_dev = &ud->ddev; @@ -5549,7 +5549,7 @@ static int udma_pm_suspend(struct device *dev) return 0; } -static int udma_pm_resume(struct device *dev) +static int __maybe_unused udma_pm_resume(struct device *dev) { struct udma_dev *ud = dev_get_drvdata(dev); struct dma_device *dma_dev = &ud->ddev; diff --git a/drivers/firmware/efi/libstub/Makefile.zboot b/drivers/firmware/efi/libstub/Makefile.zboot index 89ef820f3b34..2c489627a807 100644 --- a/drivers/firmware/efi/libstub/Makefile.zboot +++ b/drivers/firmware/efi/libstub/Makefile.zboot @@ -32,7 +32,8 @@ zboot-size-len-$(CONFIG_KERNEL_GZIP) := 0 $(obj)/vmlinuz: $(obj)/vmlinux.bin FORCE $(call if_changed,$(zboot-method-y)) -OBJCOPYFLAGS_vmlinuz.o := -I binary -O $(EFI_ZBOOT_BFD_TARGET) $(EFI_ZBOOT_OBJCOPY_FLAGS) \ +# avoid eager evaluation to prevent references to non-existent build artifacts +OBJCOPYFLAGS_vmlinuz.o = -I binary -O $(EFI_ZBOOT_BFD_TARGET) $(EFI_ZBOOT_OBJCOPY_FLAGS) \ --rename-section .data=.gzdata,load,alloc,readonly,contents $(obj)/vmlinuz.o: $(obj)/vmlinuz FORCE $(call if_changed,objcopy) diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h index 67d5a20802e0..54a2822cae77 100644 --- a/drivers/firmware/efi/libstub/efistub.h +++ b/drivers/firmware/efi/libstub/efistub.h @@ -1133,4 +1133,7 @@ const u8 *__efi_get_smbios_string(const struct efi_smbios_record *record, void efi_remap_image(unsigned long image_base, unsigned alloc_size, unsigned long code_size); +asmlinkage efi_status_t __efiapi +efi_zboot_entry(efi_handle_t handle, efi_system_table_t *systab); + #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index 4e2531758866..95b0f984acbf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -593,6 +593,8 @@ void amdgpu_gmc_tmz_set(struct amdgpu_device *adev) case IP_VERSION(9, 3, 0): /* GC 10.3.7 */ case IP_VERSION(10, 3, 7): + /* GC 11.0.1 */ + case IP_VERSION(11, 0, 1): if (amdgpu_tmz == 0) { adev->gmc.tmz_enabled = false; dev_info(adev->dev, @@ -616,7 +618,6 @@ void amdgpu_gmc_tmz_set(struct amdgpu_device *adev) case IP_VERSION(10, 3, 1): /* YELLOW_CARP*/ case IP_VERSION(10, 3, 3): - case IP_VERSION(11, 0, 1): case IP_VERSION(11, 0, 4): /* Don't enable it by default yet. */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c index b07c000fc8ba..4fa019c8aefc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c @@ -241,6 +241,31 @@ int amdgpu_jpeg_process_poison_irq(struct amdgpu_device *adev, return 0; } +int amdgpu_jpeg_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *ras_block) +{ + int r, i; + + r = amdgpu_ras_block_late_init(adev, ras_block); + if (r) + return r; + + if (amdgpu_ras_is_supported(adev, ras_block->block)) { + for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) { + if (adev->jpeg.harvest_config & (1 << i)) + continue; + + r = amdgpu_irq_get(adev, &adev->jpeg.inst[i].ras_poison_irq, 0); + if (r) + goto late_fini; + } + } + return 0; + +late_fini: + amdgpu_ras_block_late_fini(adev, ras_block); + return r; +} + int amdgpu_jpeg_ras_sw_init(struct amdgpu_device *adev) { int err; @@ -262,7 +287,7 @@ int amdgpu_jpeg_ras_sw_init(struct amdgpu_device *adev) adev->jpeg.ras_if = &ras->ras_block.ras_comm; if (!ras->ras_block.ras_late_init) - ras->ras_block.ras_late_init = amdgpu_ras_block_late_init; + ras->ras_block.ras_late_init = amdgpu_jpeg_ras_late_init; return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.h index 0ca76f0f23e9..1471a1ebb034 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.h @@ -38,6 +38,7 @@ struct amdgpu_jpeg_reg{ struct amdgpu_jpeg_inst { struct amdgpu_ring ring_dec; struct amdgpu_irq_src irq; + struct amdgpu_irq_src ras_poison_irq; struct amdgpu_jpeg_reg external; }; @@ -72,6 +73,8 @@ int amdgpu_jpeg_dec_ring_test_ib(struct amdgpu_ring *ring, long timeout); int amdgpu_jpeg_process_poison_irq(struct amdgpu_device *adev, struct amdgpu_irq_src *source, struct amdgpu_iv_entry *entry); +int amdgpu_jpeg_ras_late_init(struct amdgpu_device *adev, + struct ras_common_if *ras_block); int amdgpu_jpeg_ras_sw_init(struct amdgpu_device *adev); #endif /*__AMDGPU_JPEG_H__*/ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index e63fcc58e8e0..2d94f1b63bd6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -1181,6 +1181,31 @@ int amdgpu_vcn_process_poison_irq(struct amdgpu_device *adev, return 0; } +int amdgpu_vcn_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *ras_block) +{ + int r, i; + + r = amdgpu_ras_block_late_init(adev, ras_block); + if (r) + return r; + + if (amdgpu_ras_is_supported(adev, ras_block->block)) { + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + if (adev->vcn.harvest_config & (1 << i)) + continue; + + r = amdgpu_irq_get(adev, &adev->vcn.inst[i].ras_poison_irq, 0); + if (r) + goto late_fini; + } + } + return 0; + +late_fini: + amdgpu_ras_block_late_fini(adev, ras_block); + return r; +} + int amdgpu_vcn_ras_sw_init(struct amdgpu_device *adev) { int err; @@ -1202,7 +1227,7 @@ int amdgpu_vcn_ras_sw_init(struct amdgpu_device *adev) adev->vcn.ras_if = &ras->ras_block.ras_comm; if (!ras->ras_block.ras_late_init) - ras->ras_block.ras_late_init = amdgpu_ras_block_late_init; + ras->ras_block.ras_late_init = amdgpu_vcn_ras_late_init; return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h index c730949ece7d..f1397ef66fd7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h @@ -234,6 +234,7 @@ struct amdgpu_vcn_inst { struct amdgpu_ring ring_enc[AMDGPU_VCN_MAX_ENC_RINGS]; atomic_t sched_score; struct amdgpu_irq_src irq; + struct amdgpu_irq_src ras_poison_irq; struct amdgpu_vcn_reg external; struct amdgpu_bo *dpg_sram_bo; struct dpg_pause_state pause_state; @@ -400,6 +401,8 @@ void amdgpu_debugfs_vcn_fwlog_init(struct amdgpu_device *adev, int amdgpu_vcn_process_poison_irq(struct amdgpu_device *adev, struct amdgpu_irq_src *source, struct amdgpu_iv_entry *entry); +int amdgpu_vcn_ras_late_init(struct amdgpu_device *adev, + struct ras_common_if *ras_block); int amdgpu_vcn_ras_sw_init(struct amdgpu_device *adev); #endif diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c index b040f51d9aa9..73e0dc5a10cd 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c @@ -102,13 +102,13 @@ static int jpeg_v2_5_sw_init(void *handle) /* JPEG DJPEG POISON EVENT */ r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_jpeg[i], - VCN_2_6__SRCID_DJPEG0_POISON, &adev->jpeg.inst[i].irq); + VCN_2_6__SRCID_DJPEG0_POISON, &adev->jpeg.inst[i].ras_poison_irq); if (r) return r; /* JPEG EJPEG POISON EVENT */ r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_jpeg[i], - VCN_2_6__SRCID_EJPEG0_POISON, &adev->jpeg.inst[i].irq); + VCN_2_6__SRCID_EJPEG0_POISON, &adev->jpeg.inst[i].ras_poison_irq); if (r) return r; } @@ -221,6 +221,9 @@ static int jpeg_v2_5_hw_fini(void *handle) if (adev->jpeg.cur_state != AMD_PG_STATE_GATE && RREG32_SOC15(JPEG, i, mmUVD_JRBC_STATUS)) jpeg_v2_5_set_powergating_state(adev, AMD_PG_STATE_GATE); + + if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__JPEG)) + amdgpu_irq_put(adev, &adev->jpeg.inst[i].ras_poison_irq, 0); } return 0; @@ -569,6 +572,14 @@ static int jpeg_v2_5_set_interrupt_state(struct amdgpu_device *adev, return 0; } +static int jpeg_v2_6_set_ras_interrupt_state(struct amdgpu_device *adev, + struct amdgpu_irq_src *source, + unsigned int type, + enum amdgpu_interrupt_state state) +{ + return 0; +} + static int jpeg_v2_5_process_interrupt(struct amdgpu_device *adev, struct amdgpu_irq_src *source, struct amdgpu_iv_entry *entry) @@ -593,10 +604,6 @@ static int jpeg_v2_5_process_interrupt(struct amdgpu_device *adev, case VCN_2_0__SRCID__JPEG_DECODE: amdgpu_fence_process(&adev->jpeg.inst[ip_instance].ring_dec); break; - case VCN_2_6__SRCID_DJPEG0_POISON: - case VCN_2_6__SRCID_EJPEG0_POISON: - amdgpu_jpeg_process_poison_irq(adev, source, entry); - break; default: DRM_ERROR("Unhandled interrupt: %d %d\n", entry->src_id, entry->src_data[0]); @@ -725,6 +732,11 @@ static const struct amdgpu_irq_src_funcs jpeg_v2_5_irq_funcs = { .process = jpeg_v2_5_process_interrupt, }; +static const struct amdgpu_irq_src_funcs jpeg_v2_6_ras_irq_funcs = { + .set = jpeg_v2_6_set_ras_interrupt_state, + .process = amdgpu_jpeg_process_poison_irq, +}; + static void jpeg_v2_5_set_irq_funcs(struct amdgpu_device *adev) { int i; @@ -735,6 +747,9 @@ static void jpeg_v2_5_set_irq_funcs(struct amdgpu_device *adev) adev->jpeg.inst[i].irq.num_types = 1; adev->jpeg.inst[i].irq.funcs = &jpeg_v2_5_irq_funcs; + + adev->jpeg.inst[i].ras_poison_irq.num_types = 1; + adev->jpeg.inst[i].ras_poison_irq.funcs = &jpeg_v2_6_ras_irq_funcs; } } @@ -800,6 +815,7 @@ const struct amdgpu_ras_block_hw_ops jpeg_v2_6_ras_hw_ops = { static struct amdgpu_jpeg_ras jpeg_v2_6_ras = { .ras_block = { .hw_ops = &jpeg_v2_6_ras_hw_ops, + .ras_late_init = amdgpu_jpeg_ras_late_init, }, }; diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c index 77e1e64aa1d1..a3d83c9f2c9a 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c @@ -87,13 +87,13 @@ static int jpeg_v4_0_sw_init(void *handle) /* JPEG DJPEG POISON EVENT */ r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, - VCN_4_0__SRCID_DJPEG0_POISON, &adev->jpeg.inst->irq); + VCN_4_0__SRCID_DJPEG0_POISON, &adev->jpeg.inst->ras_poison_irq); if (r) return r; /* JPEG EJPEG POISON EVENT */ r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, - VCN_4_0__SRCID_EJPEG0_POISON, &adev->jpeg.inst->irq); + VCN_4_0__SRCID_EJPEG0_POISON, &adev->jpeg.inst->ras_poison_irq); if (r) return r; @@ -202,7 +202,8 @@ static int jpeg_v4_0_hw_fini(void *handle) RREG32_SOC15(JPEG, 0, regUVD_JRBC_STATUS)) jpeg_v4_0_set_powergating_state(adev, AMD_PG_STATE_GATE); } - amdgpu_irq_put(adev, &adev->jpeg.inst->irq, 0); + if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__JPEG)) + amdgpu_irq_put(adev, &adev->jpeg.inst->ras_poison_irq, 0); return 0; } @@ -670,6 +671,14 @@ static int jpeg_v4_0_set_interrupt_state(struct amdgpu_device *adev, return 0; } +static int jpeg_v4_0_set_ras_interrupt_state(struct amdgpu_device *adev, + struct amdgpu_irq_src *source, + unsigned int type, + enum amdgpu_interrupt_state state) +{ + return 0; +} + static int jpeg_v4_0_process_interrupt(struct amdgpu_device *adev, struct amdgpu_irq_src *source, struct amdgpu_iv_entry *entry) @@ -680,10 +689,6 @@ static int jpeg_v4_0_process_interrupt(struct amdgpu_device *adev, case VCN_4_0__SRCID__JPEG_DECODE: amdgpu_fence_process(&adev->jpeg.inst->ring_dec); break; - case VCN_4_0__SRCID_DJPEG0_POISON: - case VCN_4_0__SRCID_EJPEG0_POISON: - amdgpu_jpeg_process_poison_irq(adev, source, entry); - break; default: DRM_DEV_ERROR(adev->dev, "Unhandled interrupt: %d %d\n", entry->src_id, entry->src_data[0]); @@ -753,10 +758,18 @@ static const struct amdgpu_irq_src_funcs jpeg_v4_0_irq_funcs = { .process = jpeg_v4_0_process_interrupt, }; +static const struct amdgpu_irq_src_funcs jpeg_v4_0_ras_irq_funcs = { + .set = jpeg_v4_0_set_ras_interrupt_state, + .process = amdgpu_jpeg_process_poison_irq, +}; + static void jpeg_v4_0_set_irq_funcs(struct amdgpu_device *adev) { adev->jpeg.inst->irq.num_types = 1; adev->jpeg.inst->irq.funcs = &jpeg_v4_0_irq_funcs; + + adev->jpeg.inst->ras_poison_irq.num_types = 1; + adev->jpeg.inst->ras_poison_irq.funcs = &jpeg_v4_0_ras_irq_funcs; } const struct amdgpu_ip_block_version jpeg_v4_0_ip_block = { @@ -811,6 +824,7 @@ const struct amdgpu_ras_block_hw_ops jpeg_v4_0_ras_hw_ops = { static struct amdgpu_jpeg_ras jpeg_v4_0_ras = { .ras_block = { .hw_ops = &jpeg_v4_0_ras_hw_ops, + .ras_late_init = amdgpu_jpeg_ras_late_init, }, }; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c index ab0b45d0ead1..515681c88dcb 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c @@ -143,7 +143,7 @@ static int vcn_v2_5_sw_init(void *handle) /* VCN POISON TRAP */ r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_vcns[j], - VCN_2_6__SRCID_UVD_POISON, &adev->vcn.inst[j].irq); + VCN_2_6__SRCID_UVD_POISON, &adev->vcn.inst[j].ras_poison_irq); if (r) return r; } @@ -354,6 +354,9 @@ static int vcn_v2_5_hw_fini(void *handle) (adev->vcn.cur_state != AMD_PG_STATE_GATE && RREG32_SOC15(VCN, i, mmUVD_STATUS))) vcn_v2_5_set_powergating_state(adev, AMD_PG_STATE_GATE); + + if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__VCN)) + amdgpu_irq_put(adev, &adev->vcn.inst[i].ras_poison_irq, 0); } return 0; @@ -1807,6 +1810,14 @@ static int vcn_v2_5_set_interrupt_state(struct amdgpu_device *adev, return 0; } +static int vcn_v2_6_set_ras_interrupt_state(struct amdgpu_device *adev, + struct amdgpu_irq_src *source, + unsigned int type, + enum amdgpu_interrupt_state state) +{ + return 0; +} + static int vcn_v2_5_process_interrupt(struct amdgpu_device *adev, struct amdgpu_irq_src *source, struct amdgpu_iv_entry *entry) @@ -1837,9 +1848,6 @@ static int vcn_v2_5_process_interrupt(struct amdgpu_device *adev, case VCN_2_0__SRCID__UVD_ENC_LOW_LATENCY: amdgpu_fence_process(&adev->vcn.inst[ip_instance].ring_enc[1]); break; - case VCN_2_6__SRCID_UVD_POISON: - amdgpu_vcn_process_poison_irq(adev, source, entry); - break; default: DRM_ERROR("Unhandled interrupt: %d %d\n", entry->src_id, entry->src_data[0]); @@ -1854,6 +1862,11 @@ static const struct amdgpu_irq_src_funcs vcn_v2_5_irq_funcs = { .process = vcn_v2_5_process_interrupt, }; +static const struct amdgpu_irq_src_funcs vcn_v2_6_ras_irq_funcs = { + .set = vcn_v2_6_set_ras_interrupt_state, + .process = amdgpu_vcn_process_poison_irq, +}; + static void vcn_v2_5_set_irq_funcs(struct amdgpu_device *adev) { int i; @@ -1863,6 +1876,9 @@ static void vcn_v2_5_set_irq_funcs(struct amdgpu_device *adev) continue; adev->vcn.inst[i].irq.num_types = adev->vcn.num_enc_rings + 1; adev->vcn.inst[i].irq.funcs = &vcn_v2_5_irq_funcs; + + adev->vcn.inst[i].ras_poison_irq.num_types = adev->vcn.num_enc_rings + 1; + adev->vcn.inst[i].ras_poison_irq.funcs = &vcn_v2_6_ras_irq_funcs; } } @@ -1965,6 +1981,7 @@ const struct amdgpu_ras_block_hw_ops vcn_v2_6_ras_hw_ops = { static struct amdgpu_vcn_ras vcn_v2_6_ras = { .ras_block = { .hw_ops = &vcn_v2_6_ras_hw_ops, + .ras_late_init = amdgpu_vcn_ras_late_init, }, }; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c index bf0674039598..e5fd1e00914d 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c @@ -139,7 +139,7 @@ static int vcn_v4_0_sw_init(void *handle) /* VCN POISON TRAP */ r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_vcns[i], - VCN_4_0__SRCID_UVD_POISON, &adev->vcn.inst[i].irq); + VCN_4_0__SRCID_UVD_POISON, &adev->vcn.inst[i].ras_poison_irq); if (r) return r; @@ -305,8 +305,8 @@ static int vcn_v4_0_hw_fini(void *handle) vcn_v4_0_set_powergating_state(adev, AMD_PG_STATE_GATE); } } - - amdgpu_irq_put(adev, &adev->vcn.inst[i].irq, 0); + if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__VCN)) + amdgpu_irq_put(adev, &adev->vcn.inst[i].ras_poison_irq, 0); } return 0; @@ -1976,6 +1976,24 @@ static int vcn_v4_0_set_interrupt_state(struct amdgpu_device *adev, struct amdgp } /** + * vcn_v4_0_set_ras_interrupt_state - set VCN block RAS interrupt state + * + * @adev: amdgpu_device pointer + * @source: interrupt sources + * @type: interrupt types + * @state: interrupt states + * + * Set VCN block RAS interrupt state + */ +static int vcn_v4_0_set_ras_interrupt_state(struct amdgpu_device *adev, + struct amdgpu_irq_src *source, + unsigned int type, + enum amdgpu_interrupt_state state) +{ + return 0; +} + +/** * vcn_v4_0_process_interrupt - process VCN block interrupt * * @adev: amdgpu_device pointer @@ -2007,9 +2025,6 @@ static int vcn_v4_0_process_interrupt(struct amdgpu_device *adev, struct amdgpu_ case VCN_4_0__SRCID__UVD_ENC_GENERAL_PURPOSE: amdgpu_fence_process(&adev->vcn.inst[ip_instance].ring_enc[0]); break; - case VCN_4_0__SRCID_UVD_POISON: - amdgpu_vcn_process_poison_irq(adev, source, entry); - break; default: DRM_ERROR("Unhandled interrupt: %d %d\n", entry->src_id, entry->src_data[0]); @@ -2024,6 +2039,11 @@ static const struct amdgpu_irq_src_funcs vcn_v4_0_irq_funcs = { .process = vcn_v4_0_process_interrupt, }; +static const struct amdgpu_irq_src_funcs vcn_v4_0_ras_irq_funcs = { + .set = vcn_v4_0_set_ras_interrupt_state, + .process = amdgpu_vcn_process_poison_irq, +}; + /** * vcn_v4_0_set_irq_funcs - set VCN block interrupt irq functions * @@ -2041,6 +2061,9 @@ static void vcn_v4_0_set_irq_funcs(struct amdgpu_device *adev) adev->vcn.inst[i].irq.num_types = adev->vcn.num_enc_rings + 1; adev->vcn.inst[i].irq.funcs = &vcn_v4_0_irq_funcs; + + adev->vcn.inst[i].ras_poison_irq.num_types = adev->vcn.num_enc_rings + 1; + adev->vcn.inst[i].ras_poison_irq.funcs = &vcn_v4_0_ras_irq_funcs; } } @@ -2114,6 +2137,7 @@ const struct amdgpu_ras_block_hw_ops vcn_v4_0_ras_hw_ops = { static struct amdgpu_vcn_ras vcn_v4_0_ras = { .ras_block = { .hw_ops = &vcn_v4_0_ras_hw_ops, + .ras_late_init = amdgpu_vcn_ras_late_init, }, }; diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index 422fbf79da64..5403e9399a46 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -2113,15 +2113,6 @@ void dcn20_optimize_bandwidth( if (hubbub->funcs->program_compbuf_size) hubbub->funcs->program_compbuf_size(hubbub, context->bw_ctx.bw.dcn.compbuf_size_kb, true); - if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching) { - dc_dmub_srv_p_state_delegate(dc, - true, context); - context->bw_ctx.bw.dcn.clk.p_state_change_support = true; - dc->clk_mgr->clks.fw_based_mclk_switching = true; - } else { - dc->clk_mgr->clks.fw_based_mclk_switching = false; - } - dc->clk_mgr->funcs->update_clocks( dc->clk_mgr, context, diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c index 8263a07f265f..32121db2851e 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c @@ -983,36 +983,13 @@ void dcn30_set_disp_pattern_generator(const struct dc *dc, } void dcn30_prepare_bandwidth(struct dc *dc, - struct dc_state *context) + struct dc_state *context) { - bool p_state_change_support = context->bw_ctx.bw.dcn.clk.p_state_change_support; - /* Any transition into an FPO config should disable MCLK switching first to avoid - * driver and FW P-State synchronization issues. - */ - if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching || dc->clk_mgr->clks.fw_based_mclk_switching) { - dc->optimized_required = true; - context->bw_ctx.bw.dcn.clk.p_state_change_support = false; - } - if (dc->clk_mgr->dc_mode_softmax_enabled) if (dc->clk_mgr->clks.dramclk_khz <= dc->clk_mgr->bw_params->dc_mode_softmax_memclk * 1000 && context->bw_ctx.bw.dcn.clk.dramclk_khz > dc->clk_mgr->bw_params->dc_mode_softmax_memclk * 1000) dc->clk_mgr->funcs->set_max_memclk(dc->clk_mgr, dc->clk_mgr->bw_params->clk_table.entries[dc->clk_mgr->bw_params->clk_table.num_entries - 1].memclk_mhz); dcn20_prepare_bandwidth(dc, context); - /* - * enabled -> enabled: do not disable - * enabled -> disabled: disable - * disabled -> enabled: don't care - * disabled -> disabled: don't care - */ - if (!context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching) - dc_dmub_srv_p_state_delegate(dc, false, context); - - if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching || dc->clk_mgr->clks.fw_based_mclk_switching) { - /* After disabling P-State, restore the original value to ensure we get the correct P-State - * on the next optimize. */ - context->bw_ctx.bw.dcn.clk.p_state_change_support = p_state_change_support; - } } diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c index d6d9e3b1b2c0..02e69ccff3ba 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c @@ -6925,23 +6925,6 @@ static int si_dpm_enable(struct amdgpu_device *adev) return 0; } -static int si_set_temperature_range(struct amdgpu_device *adev) -{ - int ret; - - ret = si_thermal_enable_alert(adev, false); - if (ret) - return ret; - ret = si_thermal_set_temperature_range(adev, R600_TEMP_RANGE_MIN, R600_TEMP_RANGE_MAX); - if (ret) - return ret; - ret = si_thermal_enable_alert(adev, true); - if (ret) - return ret; - - return ret; -} - static void si_dpm_disable(struct amdgpu_device *adev) { struct rv7xx_power_info *pi = rv770_get_pi(adev); @@ -7626,18 +7609,6 @@ static int si_dpm_process_interrupt(struct amdgpu_device *adev, static int si_dpm_late_init(void *handle) { - int ret; - struct amdgpu_device *adev = (struct amdgpu_device *)handle; - - if (!adev->pm.dpm_enabled) - return 0; - - ret = si_set_temperature_range(adev); - if (ret) - return ret; -#if 0 //TODO ? - si_dpm_powergate_uvd(adev, true); -#endif return 0; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c index 7433dcaa16e0..067b4e0b026c 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c @@ -582,7 +582,7 @@ static int vangogh_print_legacy_clk_levels(struct smu_context *smu, DpmClocks_t *clk_table = smu->smu_table.clocks_table; SmuMetrics_legacy_t metrics; struct smu_dpm_context *smu_dpm_ctx = &(smu->smu_dpm); - int i, size = 0, ret = 0; + int i, idx, size = 0, ret = 0; uint32_t cur_value = 0, value = 0, count = 0; bool cur_value_match_level = false; @@ -656,7 +656,8 @@ static int vangogh_print_legacy_clk_levels(struct smu_context *smu, case SMU_MCLK: case SMU_FCLK: for (i = 0; i < count; i++) { - ret = vangogh_get_dpm_clk_limited(smu, clk_type, i, &value); + idx = (clk_type == SMU_FCLK || clk_type == SMU_MCLK) ? (count - i - 1) : i; + ret = vangogh_get_dpm_clk_limited(smu, clk_type, idx, &value); if (ret) return ret; if (!value) @@ -683,7 +684,7 @@ static int vangogh_print_clk_levels(struct smu_context *smu, DpmClocks_t *clk_table = smu->smu_table.clocks_table; SmuMetrics_t metrics; struct smu_dpm_context *smu_dpm_ctx = &(smu->smu_dpm); - int i, size = 0, ret = 0; + int i, idx, size = 0, ret = 0; uint32_t cur_value = 0, value = 0, count = 0; bool cur_value_match_level = false; uint32_t min, max; @@ -765,7 +766,8 @@ static int vangogh_print_clk_levels(struct smu_context *smu, case SMU_MCLK: case SMU_FCLK: for (i = 0; i < count; i++) { - ret = vangogh_get_dpm_clk_limited(smu, clk_type, i, &value); + idx = (clk_type == SMU_FCLK || clk_type == SMU_MCLK) ? (count - i - 1) : i; + ret = vangogh_get_dpm_clk_limited(smu, clk_type, idx, &value); if (ret) return ret; if (!value) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c index 5cdc07165480..8a8ba25c9ad7 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c @@ -494,7 +494,7 @@ static int renoir_set_fine_grain_gfx_freq_parameters(struct smu_context *smu) static int renoir_print_clk_levels(struct smu_context *smu, enum smu_clk_type clk_type, char *buf) { - int i, size = 0, ret = 0; + int i, idx, size = 0, ret = 0; uint32_t cur_value = 0, value = 0, count = 0, min = 0, max = 0; SmuMetrics_t metrics; struct smu_dpm_context *smu_dpm_ctx = &(smu->smu_dpm); @@ -594,7 +594,8 @@ static int renoir_print_clk_levels(struct smu_context *smu, case SMU_VCLK: case SMU_DCLK: for (i = 0; i < count; i++) { - ret = renoir_get_dpm_clk_limited(smu, clk_type, i, &value); + idx = (clk_type == SMU_FCLK || clk_type == SMU_MCLK) ? (count - i - 1) : i; + ret = renoir_get_dpm_clk_limited(smu, clk_type, idx, &value); if (ret) return ret; if (!value) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c index 8fa9a36c38b6..6d9760eac16d 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c @@ -478,7 +478,7 @@ static int smu_v13_0_4_get_dpm_level_count(struct smu_context *smu, static int smu_v13_0_4_print_clk_levels(struct smu_context *smu, enum smu_clk_type clk_type, char *buf) { - int i, size = 0, ret = 0; + int i, idx, size = 0, ret = 0; uint32_t cur_value = 0, value = 0, count = 0; uint32_t min, max; @@ -512,7 +512,8 @@ static int smu_v13_0_4_print_clk_levels(struct smu_context *smu, break; for (i = 0; i < count; i++) { - ret = smu_v13_0_4_get_dpm_freq_by_index(smu, clk_type, i, &value); + idx = (clk_type == SMU_FCLK || clk_type == SMU_MCLK) ? (count - i - 1) : i; + ret = smu_v13_0_4_get_dpm_freq_by_index(smu, clk_type, idx, &value); if (ret) break; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c index 66445964efbd..0081fa607e02 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c @@ -866,7 +866,7 @@ out: static int smu_v13_0_5_print_clk_levels(struct smu_context *smu, enum smu_clk_type clk_type, char *buf) { - int i, size = 0, ret = 0; + int i, idx, size = 0, ret = 0; uint32_t cur_value = 0, value = 0, count = 0; uint32_t min = 0, max = 0; @@ -898,7 +898,8 @@ static int smu_v13_0_5_print_clk_levels(struct smu_context *smu, goto print_clk_out; for (i = 0; i < count; i++) { - ret = smu_v13_0_5_get_dpm_freq_by_index(smu, clk_type, i, &value); + idx = (clk_type == SMU_MCLK) ? (count - i - 1) : i; + ret = smu_v13_0_5_get_dpm_freq_by_index(smu, clk_type, idx, &value); if (ret) goto print_clk_out; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c index 04e56b0b3033..798f36cfcebd 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c @@ -1000,7 +1000,7 @@ out: static int yellow_carp_print_clk_levels(struct smu_context *smu, enum smu_clk_type clk_type, char *buf) { - int i, size = 0, ret = 0; + int i, idx, size = 0, ret = 0; uint32_t cur_value = 0, value = 0, count = 0; uint32_t min, max; @@ -1033,7 +1033,8 @@ static int yellow_carp_print_clk_levels(struct smu_context *smu, goto print_clk_out; for (i = 0; i < count; i++) { - ret = yellow_carp_get_dpm_freq_by_index(smu, clk_type, i, &value); + idx = (clk_type == SMU_FCLK || clk_type == SMU_MCLK) ? (count - i - 1) : i; + ret = yellow_carp_get_dpm_freq_by_index(smu, clk_type, idx, &value); if (ret) goto print_clk_out; diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 050b8ae7b8e7..3035cba2c6a2 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -877,12 +877,17 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream, stream->oa_buffer.last_ctx_id = ctx_id; } - /* - * Clear out the report id and timestamp as a means to detect unlanded - * reports. - */ - oa_report_id_clear(stream, report32); - oa_timestamp_clear(stream, report32); + if (is_power_of_2(report_size)) { + /* + * Clear out the report id and timestamp as a means + * to detect unlanded reports. + */ + oa_report_id_clear(stream, report32); + oa_timestamp_clear(stream, report32); + } else { + /* Zero out the entire report */ + memset(report32, 0, report_size); + } } if (start_offset != *offset) { diff --git a/drivers/hid/hid-google-hammer.c b/drivers/hid/hid-google-hammer.c index 7ae5f27df54d..c6bdb9c4ef3e 100644 --- a/drivers/hid/hid-google-hammer.c +++ b/drivers/hid/hid-google-hammer.c @@ -587,6 +587,8 @@ static const struct hid_device_id hammer_devices[] = { { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_HAMMER) }, { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, + USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_JEWEL) }, + { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_MAGNEMITE) }, { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_MASTERBALL) }, diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index d79e946acdcb..5d29abac2300 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -529,6 +529,7 @@ #define USB_DEVICE_ID_GOOGLE_MOONBALL 0x5044 #define USB_DEVICE_ID_GOOGLE_DON 0x5050 #define USB_DEVICE_ID_GOOGLE_EEL 0x5057 +#define USB_DEVICE_ID_GOOGLE_JEWEL 0x5061 #define USB_VENDOR_ID_GOTOP 0x08f2 #define USB_DEVICE_ID_SUPER_Q2 0x007f diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index 0fcfd85fea0f..2246044b1639 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -314,6 +314,7 @@ static int hidpp_send_message_sync(struct hidpp_device *hidpp, dbg_hid("%s:timeout waiting for response\n", __func__); memset(response, 0, sizeof(struct hidpp_report)); ret = -ETIMEDOUT; + goto exit; } if (response->report_id == REPORT_ID_HIDPP_SHORT && diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index 8214896adada..76e5353aca0c 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -2224,7 +2224,9 @@ static void wacom_update_name(struct wacom *wacom, const char *suffix) } else if (strstr(product_name, "Wacom") || strstr(product_name, "wacom") || strstr(product_name, "WACOM")) { - strscpy(name, product_name, sizeof(name)); + if (strscpy(name, product_name, sizeof(name)) < 0) { + hid_warn(wacom->hdev, "String overflow while assembling device name"); + } } else { snprintf(name, sizeof(name), "Wacom %s", product_name); } @@ -2242,7 +2244,9 @@ static void wacom_update_name(struct wacom *wacom, const char *suffix) if (name[strlen(name)-1] == ' ') name[strlen(name)-1] = '\0'; } else { - strscpy(name, features->name, sizeof(name)); + if (strscpy(name, features->name, sizeof(name)) < 0) { + hid_warn(wacom->hdev, "String overflow while assembling device name"); + } } snprintf(wacom_wac->name, sizeof(wacom_wac->name), "%s%s", @@ -2410,8 +2414,13 @@ static int wacom_parse_and_register(struct wacom *wacom, bool wireless) goto fail_quirks; } - if (features->device_type & WACOM_DEVICETYPE_WL_MONITOR) + if (features->device_type & WACOM_DEVICETYPE_WL_MONITOR) { error = hid_hw_open(hdev); + if (error) { + hid_err(hdev, "hw open failed\n"); + goto fail_quirks; + } + } wacom_set_shared_values(wacom_wac); devres_close_group(&hdev->dev, wacom); @@ -2500,8 +2509,10 @@ static void wacom_wireless_work(struct work_struct *work) goto fail; } - strscpy(wacom_wac->name, wacom_wac1->name, - sizeof(wacom_wac->name)); + if (strscpy(wacom_wac->name, wacom_wac1->name, + sizeof(wacom_wac->name)) < 0) { + hid_warn(wacom->hdev, "String overflow while assembling device name"); + } } return; diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index dc0f7d9a992c..2ccf83837134 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -831,7 +831,7 @@ static int wacom_intuos_inout(struct wacom_wac *wacom) /* Enter report */ if ((data[1] & 0xfc) == 0xc0) { /* serial number of the tool */ - wacom->serial[idx] = ((data[3] & 0x0f) << 28) + + wacom->serial[idx] = ((__u64)(data[3] & 0x0f) << 28) + (data[4] << 20) + (data[5] << 12) + (data[6] << 4) + (data[7] >> 4); diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index e86afecfbe46..b1c36412025f 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -3341,9 +3341,7 @@ static int bnxt_re_process_raw_qp_pkt_rx(struct bnxt_re_qp *gsi_qp, udwr.remote_qkey = gsi_sqp->qplib_qp.qkey; /* post data received in the send queue */ - rc = bnxt_re_post_send_shadow_qp(rdev, gsi_sqp, swr); - - return 0; + return bnxt_re_post_send_shadow_qp(rdev, gsi_sqp, swr); } static void bnxt_re_process_res_rawqp1_wc(struct ib_wc *wc, diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index b9e2f89337e8..e34eccd178d0 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -1336,6 +1336,10 @@ static void bnxt_re_setup_cc(struct bnxt_re_dev *rdev, bool enable) { struct bnxt_qplib_cc_param cc_param = {}; + /* Do not enable congestion control on VFs */ + if (rdev->is_virtfn) + return; + /* Currently enabling only for GenP5 adapters */ if (!bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx)) return; diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index f139d4cd1712..8974f6235cfa 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -2056,6 +2056,12 @@ int bnxt_qplib_create_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq) u32 pg_sz_lvl; int rc; + if (!cq->dpi) { + dev_err(&rcfw->pdev->dev, + "FP: CREATE_CQ failed due to NULL DPI\n"); + return -EINVAL; + } + hwq_attr.res = res; hwq_attr.depth = cq->max_wqe; hwq_attr.stride = sizeof(struct cq_base); @@ -2069,11 +2075,6 @@ int bnxt_qplib_create_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq) CMDQ_BASE_OPCODE_CREATE_CQ, sizeof(req)); - if (!cq->dpi) { - dev_err(&rcfw->pdev->dev, - "FP: CREATE_CQ failed due to NULL DPI\n"); - return -EINVAL; - } req.dpi = cpu_to_le32(cq->dpi->dpi); req.cq_handle = cpu_to_le64(cq->cq_handle); req.cq_size = cpu_to_le32(cq->hwq.max_elements); diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.c b/drivers/infiniband/hw/bnxt_re/qplib_res.c index 126d4f26f75a..81b0c5e879f9 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_res.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_res.c @@ -215,17 +215,9 @@ int bnxt_qplib_alloc_init_hwq(struct bnxt_qplib_hwq *hwq, return -EINVAL; hwq_attr->sginfo->npages = npages; } else { - unsigned long sginfo_num_pages = ib_umem_num_dma_blocks( - hwq_attr->sginfo->umem, hwq_attr->sginfo->pgsize); - + npages = ib_umem_num_dma_blocks(hwq_attr->sginfo->umem, + hwq_attr->sginfo->pgsize); hwq->is_user = true; - npages = sginfo_num_pages; - npages = (npages * PAGE_SIZE) / - BIT_ULL(hwq_attr->sginfo->pgshft); - if ((sginfo_num_pages * PAGE_SIZE) % - BIT_ULL(hwq_attr->sginfo->pgshft)) - if (!npages) - npages++; } if (npages == MAX_PBL_LVL_0_PGS && !hwq_attr->sginfo->nopte) { diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c index 1714a1e23113..b967a17a44be 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c @@ -617,16 +617,15 @@ int bnxt_qplib_reg_mr(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mr, /* Free the hwq if it already exist, must be a rereg */ if (mr->hwq.max_elements) bnxt_qplib_free_hwq(res, &mr->hwq); - /* Use system PAGE_SIZE */ hwq_attr.res = res; hwq_attr.depth = pages; - hwq_attr.stride = buf_pg_size; + hwq_attr.stride = sizeof(dma_addr_t); hwq_attr.type = HWQ_TYPE_MR; hwq_attr.sginfo = &sginfo; hwq_attr.sginfo->umem = umem; hwq_attr.sginfo->npages = pages; - hwq_attr.sginfo->pgsize = PAGE_SIZE; - hwq_attr.sginfo->pgshft = PAGE_SHIFT; + hwq_attr.sginfo->pgsize = buf_pg_size; + hwq_attr.sginfo->pgshft = ilog2(buf_pg_size); rc = bnxt_qplib_alloc_init_hwq(&mr->hwq, &hwq_attr); if (rc) { dev_err(&res->pdev->dev, diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c index 8eca6c14d0cf..2a195c4b0f17 100644 --- a/drivers/infiniband/hw/efa/efa_verbs.c +++ b/drivers/infiniband/hw/efa/efa_verbs.c @@ -1403,7 +1403,7 @@ static int pbl_continuous_initialize(struct efa_dev *dev, */ static int pbl_indirect_initialize(struct efa_dev *dev, struct pbl_context *pbl) { - u32 size_in_pages = DIV_ROUND_UP(pbl->pbl_buf_size_in_bytes, PAGE_SIZE); + u32 size_in_pages = DIV_ROUND_UP(pbl->pbl_buf_size_in_bytes, EFA_CHUNK_PAYLOAD_SIZE); struct scatterlist *sgl; int sg_dma_cnt, err; diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 84f1167de1d9..d4c6b9bc0a4e 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -4583,11 +4583,9 @@ static int modify_qp_init_to_rtr(struct ib_qp *ibqp, mtu = ib_mtu_enum_to_int(ib_mtu); if (WARN_ON(mtu <= 0)) return -EINVAL; -#define MAX_LP_MSG_LEN 16384 - /* MTU * (2 ^ LP_PKTN_INI) shouldn't be bigger than 16KB */ - lp_pktn_ini = ilog2(MAX_LP_MSG_LEN / mtu); - if (WARN_ON(lp_pktn_ini >= 0xF)) - return -EINVAL; +#define MIN_LP_MSG_LEN 1024 + /* mtu * (2 ^ lp_pktn_ini) should be in the range of 1024 to mtu */ + lp_pktn_ini = ilog2(max(mtu, MIN_LP_MSG_LEN) / mtu); if (attr_mask & IB_QP_PATH_MTU) { hr_reg_write(context, QPC_MTU, ib_mtu); @@ -5012,7 +5010,6 @@ static int hns_roce_v2_set_abs_fields(struct ib_qp *ibqp, static bool check_qp_timeout_cfg_range(struct hns_roce_dev *hr_dev, u8 *timeout) { #define QP_ACK_TIMEOUT_MAX_HIP08 20 -#define QP_ACK_TIMEOUT_OFFSET 10 #define QP_ACK_TIMEOUT_MAX 31 if (hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP08) { @@ -5021,7 +5018,7 @@ static bool check_qp_timeout_cfg_range(struct hns_roce_dev *hr_dev, u8 *timeout) "local ACK timeout shall be 0 to 20.\n"); return false; } - *timeout += QP_ACK_TIMEOUT_OFFSET; + *timeout += HNS_ROCE_V2_QP_ACK_TIMEOUT_OFS_HIP08; } else if (hr_dev->pci_dev->revision > PCI_REVISION_ID_HIP08) { if (*timeout > QP_ACK_TIMEOUT_MAX) { ibdev_warn(&hr_dev->ib_dev, @@ -5307,6 +5304,18 @@ out: return ret; } +static u8 get_qp_timeout_attr(struct hns_roce_dev *hr_dev, + struct hns_roce_v2_qp_context *context) +{ + u8 timeout; + + timeout = (u8)hr_reg_read(context, QPC_AT); + if (hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP08) + timeout -= HNS_ROCE_V2_QP_ACK_TIMEOUT_OFS_HIP08; + + return timeout; +} + static int hns_roce_v2_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr) @@ -5384,7 +5393,7 @@ static int hns_roce_v2_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, qp_attr->max_dest_rd_atomic = 1 << hr_reg_read(&context, QPC_RR_MAX); qp_attr->min_rnr_timer = (u8)hr_reg_read(&context, QPC_MIN_RNR_TIME); - qp_attr->timeout = (u8)hr_reg_read(&context, QPC_AT); + qp_attr->timeout = get_qp_timeout_attr(hr_dev, &context); qp_attr->retry_cnt = hr_reg_read(&context, QPC_RETRY_NUM_INIT); qp_attr->rnr_retry = hr_reg_read(&context, QPC_RNR_NUM_INIT); diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h index 1b44d2434ab4..7033eae2407c 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h @@ -44,6 +44,8 @@ #define HNS_ROCE_V2_MAX_XRCD_NUM 0x1000000 #define HNS_ROCE_V2_RSV_XRCD_NUM 0 +#define HNS_ROCE_V2_QP_ACK_TIMEOUT_OFS_HIP08 10 + #define HNS_ROCE_V3_SCCC_SZ 64 #define HNS_ROCE_V3_GMV_ENTRY_SZ 32 diff --git a/drivers/infiniband/hw/hns/hns_roce_mr.c b/drivers/infiniband/hw/hns/hns_roce_mr.c index 37a5cf62f88b..14376490ac22 100644 --- a/drivers/infiniband/hw/hns/hns_roce_mr.c +++ b/drivers/infiniband/hw/hns/hns_roce_mr.c @@ -33,6 +33,7 @@ #include <linux/vmalloc.h> #include <rdma/ib_umem.h> +#include <linux/math.h> #include "hns_roce_device.h" #include "hns_roce_cmd.h" #include "hns_roce_hem.h" @@ -909,6 +910,44 @@ static int mtr_init_buf_cfg(struct hns_roce_dev *hr_dev, return page_cnt; } +static u64 cal_pages_per_l1ba(unsigned int ba_per_bt, unsigned int hopnum) +{ + return int_pow(ba_per_bt, hopnum - 1); +} + +static unsigned int cal_best_bt_pg_sz(struct hns_roce_dev *hr_dev, + struct hns_roce_mtr *mtr, + unsigned int pg_shift) +{ + unsigned long cap = hr_dev->caps.page_size_cap; + struct hns_roce_buf_region *re; + unsigned int pgs_per_l1ba; + unsigned int ba_per_bt; + unsigned int ba_num; + int i; + + for_each_set_bit_from(pg_shift, &cap, sizeof(cap) * BITS_PER_BYTE) { + if (!(BIT(pg_shift) & cap)) + continue; + + ba_per_bt = BIT(pg_shift) / BA_BYTE_LEN; + ba_num = 0; + for (i = 0; i < mtr->hem_cfg.region_count; i++) { + re = &mtr->hem_cfg.region[i]; + if (re->hopnum == 0) + continue; + + pgs_per_l1ba = cal_pages_per_l1ba(ba_per_bt, re->hopnum); + ba_num += DIV_ROUND_UP(re->count, pgs_per_l1ba); + } + + if (ba_num <= ba_per_bt) + return pg_shift; + } + + return 0; +} + static int mtr_alloc_mtt(struct hns_roce_dev *hr_dev, struct hns_roce_mtr *mtr, unsigned int ba_page_shift) { @@ -917,6 +956,10 @@ static int mtr_alloc_mtt(struct hns_roce_dev *hr_dev, struct hns_roce_mtr *mtr, hns_roce_hem_list_init(&mtr->hem_list); if (!cfg->is_direct) { + ba_page_shift = cal_best_bt_pg_sz(hr_dev, mtr, ba_page_shift); + if (!ba_page_shift) + return -ERANGE; + ret = hns_roce_hem_list_request(hr_dev, &mtr->hem_list, cfg->region, cfg->region_count, ba_page_shift); diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index ab5cdf782785..eaa12c124598 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -522,11 +522,6 @@ static int irdma_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata) if (!iwqp->user_mode) cancel_delayed_work_sync(&iwqp->dwork_flush); - irdma_qp_rem_ref(&iwqp->ibqp); - wait_for_completion(&iwqp->free_qp); - irdma_free_lsmm_rsrc(iwqp); - irdma_cqp_qp_destroy_cmd(&iwdev->rf->sc_dev, &iwqp->sc_qp); - if (!iwqp->user_mode) { if (iwqp->iwscq) { irdma_clean_cqes(iwqp, iwqp->iwscq); @@ -534,6 +529,12 @@ static int irdma_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata) irdma_clean_cqes(iwqp, iwqp->iwrcq); } } + + irdma_qp_rem_ref(&iwqp->ibqp); + wait_for_completion(&iwqp->free_qp); + irdma_free_lsmm_rsrc(iwqp); + irdma_cqp_qp_destroy_cmd(&iwdev->rf->sc_dev, &iwqp->sc_qp); + irdma_remove_push_mmap_entries(iwqp); irdma_free_qp_rsrc(iwqp); @@ -3291,6 +3292,7 @@ static int irdma_post_send(struct ib_qp *ibqp, break; case IB_WR_LOCAL_INV: info.op_type = IRDMA_OP_TYPE_INV_STAG; + info.local_fence = info.read_fence; info.op.inv_local_stag.target_stag = ib_wr->ex.invalidate_rkey; err = irdma_uk_stag_local_invalidate(ukqp, &info, true); break; diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c index db18ace74d2b..f46c5a5fd0ae 100644 --- a/drivers/infiniband/sw/rxe/rxe_comp.c +++ b/drivers/infiniband/sw/rxe/rxe_comp.c @@ -115,15 +115,16 @@ static enum ib_wc_opcode wr_to_wc_opcode(enum ib_wr_opcode opcode) void retransmit_timer(struct timer_list *t) { struct rxe_qp *qp = from_timer(qp, t, retrans_timer); + unsigned long flags; rxe_dbg_qp(qp, "retransmit timer fired\n"); - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (qp->valid) { qp->comp.timeout = 1; rxe_sched_task(&qp->comp.task); } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); } void rxe_comp_queue_pkt(struct rxe_qp *qp, struct sk_buff *skb) @@ -481,11 +482,13 @@ static void do_complete(struct rxe_qp *qp, struct rxe_send_wqe *wqe) static void comp_check_sq_drain_done(struct rxe_qp *qp) { - spin_lock_bh(&qp->state_lock); + unsigned long flags; + + spin_lock_irqsave(&qp->state_lock, flags); if (unlikely(qp_state(qp) == IB_QPS_SQD)) { if (qp->attr.sq_draining && qp->comp.psn == qp->req.psn) { qp->attr.sq_draining = 0; - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); if (qp->ibqp.event_handler) { struct ib_event ev; @@ -499,7 +502,7 @@ static void comp_check_sq_drain_done(struct rxe_qp *qp) return; } } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); } static inline enum comp_state complete_ack(struct rxe_qp *qp, @@ -625,13 +628,15 @@ static void free_pkt(struct rxe_pkt_info *pkt) */ static void reset_retry_timer(struct rxe_qp *qp) { + unsigned long flags; + if (qp_type(qp) == IB_QPT_RC && qp->qp_timeout_jiffies) { - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (qp_state(qp) >= IB_QPS_RTS && psn_compare(qp->req.psn, qp->comp.psn) > 0) mod_timer(&qp->retrans_timer, jiffies + qp->qp_timeout_jiffies); - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); } } @@ -643,18 +648,19 @@ int rxe_completer(struct rxe_qp *qp) struct rxe_pkt_info *pkt = NULL; enum comp_state state; int ret; + unsigned long flags; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (!qp->valid || qp_state(qp) == IB_QPS_ERR || qp_state(qp) == IB_QPS_RESET) { bool notify = qp->valid && (qp_state(qp) == IB_QPS_ERR); drain_resp_pkts(qp); flush_send_queue(qp, notify); - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); goto exit; } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); if (qp->comp.timeout) { qp->comp.timeout_retry = 1; diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c index 2bc7361152ea..a38fab19bed1 100644 --- a/drivers/infiniband/sw/rxe/rxe_net.c +++ b/drivers/infiniband/sw/rxe/rxe_net.c @@ -412,15 +412,16 @@ int rxe_xmit_packet(struct rxe_qp *qp, struct rxe_pkt_info *pkt, int err; int is_request = pkt->mask & RXE_REQ_MASK; struct rxe_dev *rxe = to_rdev(qp->ibqp.device); + unsigned long flags; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if ((is_request && (qp_state(qp) < IB_QPS_RTS)) || (!is_request && (qp_state(qp) < IB_QPS_RTR))) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); rxe_dbg_qp(qp, "Packet dropped. QP is not in ready state\n"); goto drop; } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); rxe_icrc_generate(skb, pkt); diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index c5451a4488ca..61a2eb77d999 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -300,6 +300,7 @@ int rxe_qp_from_init(struct rxe_dev *rxe, struct rxe_qp *qp, struct rxe_pd *pd, struct rxe_cq *rcq = to_rcq(init->recv_cq); struct rxe_cq *scq = to_rcq(init->send_cq); struct rxe_srq *srq = init->srq ? to_rsrq(init->srq) : NULL; + unsigned long flags; rxe_get(pd); rxe_get(rcq); @@ -325,10 +326,10 @@ int rxe_qp_from_init(struct rxe_dev *rxe, struct rxe_qp *qp, struct rxe_pd *pd, if (err) goto err2; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); qp->attr.qp_state = IB_QPS_RESET; qp->valid = 1; - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); return 0; @@ -492,24 +493,28 @@ static void rxe_qp_reset(struct rxe_qp *qp) /* move the qp to the error state */ void rxe_qp_error(struct rxe_qp *qp) { - spin_lock_bh(&qp->state_lock); + unsigned long flags; + + spin_lock_irqsave(&qp->state_lock, flags); qp->attr.qp_state = IB_QPS_ERR; /* drain work and packet queues */ rxe_sched_task(&qp->resp.task); rxe_sched_task(&qp->comp.task); rxe_sched_task(&qp->req.task); - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); } static void rxe_qp_sqd(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask) { - spin_lock_bh(&qp->state_lock); + unsigned long flags; + + spin_lock_irqsave(&qp->state_lock, flags); qp->attr.sq_draining = 1; rxe_sched_task(&qp->comp.task); rxe_sched_task(&qp->req.task); - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); } /* caller should hold qp->state_lock */ @@ -555,14 +560,16 @@ int rxe_qp_from_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask, qp->attr.cur_qp_state = attr->qp_state; if (mask & IB_QP_STATE) { - spin_lock_bh(&qp->state_lock); + unsigned long flags; + + spin_lock_irqsave(&qp->state_lock, flags); err = __qp_chk_state(qp, attr, mask); if (!err) { qp->attr.qp_state = attr->qp_state; rxe_dbg_qp(qp, "state -> %s\n", qps2str[attr->qp_state]); } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); if (err) return err; @@ -688,6 +695,8 @@ int rxe_qp_from_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask, /* called by the query qp verb */ int rxe_qp_to_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask) { + unsigned long flags; + *attr = qp->attr; attr->rq_psn = qp->resp.psn; @@ -708,12 +717,13 @@ int rxe_qp_to_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask) /* Applications that get this state typically spin on it. * Yield the processor */ - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (qp->attr.sq_draining) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); cond_resched(); + } else { + spin_unlock_irqrestore(&qp->state_lock, flags); } - spin_unlock_bh(&qp->state_lock); return 0; } @@ -736,10 +746,11 @@ int rxe_qp_chk_destroy(struct rxe_qp *qp) static void rxe_qp_do_cleanup(struct work_struct *work) { struct rxe_qp *qp = container_of(work, typeof(*qp), cleanup_work.work); + unsigned long flags; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); qp->valid = 0; - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); qp->qp_timeout_jiffies = 0; if (qp_type(qp) == IB_QPT_RC) { diff --git a/drivers/infiniband/sw/rxe/rxe_recv.c b/drivers/infiniband/sw/rxe/rxe_recv.c index 2f953cc74256..5861e4244049 100644 --- a/drivers/infiniband/sw/rxe/rxe_recv.c +++ b/drivers/infiniband/sw/rxe/rxe_recv.c @@ -14,6 +14,7 @@ static int check_type_state(struct rxe_dev *rxe, struct rxe_pkt_info *pkt, struct rxe_qp *qp) { unsigned int pkt_type; + unsigned long flags; if (unlikely(!qp->valid)) return -EINVAL; @@ -38,19 +39,19 @@ static int check_type_state(struct rxe_dev *rxe, struct rxe_pkt_info *pkt, return -EINVAL; } - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (pkt->mask & RXE_REQ_MASK) { if (unlikely(qp_state(qp) < IB_QPS_RTR)) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); return -EINVAL; } } else { if (unlikely(qp_state(qp) < IB_QPS_RTS)) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); return -EINVAL; } } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); return 0; } diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c index 65134a9aefe7..5fe7cbae3031 100644 --- a/drivers/infiniband/sw/rxe/rxe_req.c +++ b/drivers/infiniband/sw/rxe/rxe_req.c @@ -99,17 +99,18 @@ static void req_retry(struct rxe_qp *qp) void rnr_nak_timer(struct timer_list *t) { struct rxe_qp *qp = from_timer(qp, t, rnr_nak_timer); + unsigned long flags; rxe_dbg_qp(qp, "nak timer fired\n"); - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (qp->valid) { /* request a send queue retry */ qp->req.need_retry = 1; qp->req.wait_for_rnr_timer = 0; rxe_sched_task(&qp->req.task); } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); } static void req_check_sq_drain_done(struct rxe_qp *qp) @@ -118,8 +119,9 @@ static void req_check_sq_drain_done(struct rxe_qp *qp) unsigned int index; unsigned int cons; struct rxe_send_wqe *wqe; + unsigned long flags; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (qp_state(qp) == IB_QPS_SQD) { q = qp->sq.queue; index = qp->req.wqe_index; @@ -140,7 +142,7 @@ static void req_check_sq_drain_done(struct rxe_qp *qp) break; qp->attr.sq_draining = 0; - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); if (qp->ibqp.event_handler) { struct ib_event ev; @@ -154,7 +156,7 @@ static void req_check_sq_drain_done(struct rxe_qp *qp) return; } while (0); } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); } static struct rxe_send_wqe *__req_next_wqe(struct rxe_qp *qp) @@ -173,6 +175,7 @@ static struct rxe_send_wqe *__req_next_wqe(struct rxe_qp *qp) static struct rxe_send_wqe *req_next_wqe(struct rxe_qp *qp) { struct rxe_send_wqe *wqe; + unsigned long flags; req_check_sq_drain_done(qp); @@ -180,13 +183,13 @@ static struct rxe_send_wqe *req_next_wqe(struct rxe_qp *qp) if (wqe == NULL) return NULL; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (unlikely((qp_state(qp) == IB_QPS_SQD) && (wqe->state != wqe_state_processing))) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); return NULL; } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); wqe->mask = wr_opcode_mask(wqe->wr.opcode, qp); return wqe; @@ -676,16 +679,17 @@ int rxe_requester(struct rxe_qp *qp) struct rxe_queue *q = qp->sq.queue; struct rxe_ah *ah; struct rxe_av *av; + unsigned long flags; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (unlikely(!qp->valid)) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); goto exit; } if (unlikely(qp_state(qp) == IB_QPS_ERR)) { wqe = __req_next_wqe(qp); - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); if (wqe) goto err; else @@ -700,10 +704,10 @@ int rxe_requester(struct rxe_qp *qp) qp->req.wait_psn = 0; qp->req.need_retry = 0; qp->req.wait_for_rnr_timer = 0; - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); goto exit; } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); /* we come here if the retransmit timer has fired * or if the rnr timer has fired. If the retransmit diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c index 68f6cd188d8e..1da044f6b7d4 100644 --- a/drivers/infiniband/sw/rxe/rxe_resp.c +++ b/drivers/infiniband/sw/rxe/rxe_resp.c @@ -1047,6 +1047,7 @@ static enum resp_states do_complete(struct rxe_qp *qp, struct ib_uverbs_wc *uwc = &cqe.uibwc; struct rxe_recv_wqe *wqe = qp->resp.wqe; struct rxe_dev *rxe = to_rdev(qp->ibqp.device); + unsigned long flags; if (!wqe) goto finish; @@ -1137,12 +1138,12 @@ static enum resp_states do_complete(struct rxe_qp *qp, return RESPST_ERR_CQ_OVERFLOW; finish: - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (unlikely(qp_state(qp) == IB_QPS_ERR)) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); return RESPST_CHK_RESOURCE; } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); if (unlikely(!pkt)) return RESPST_DONE; @@ -1468,18 +1469,19 @@ int rxe_responder(struct rxe_qp *qp) enum resp_states state; struct rxe_pkt_info *pkt = NULL; int ret; + unsigned long flags; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (!qp->valid || qp_state(qp) == IB_QPS_ERR || qp_state(qp) == IB_QPS_RESET) { bool notify = qp->valid && (qp_state(qp) == IB_QPS_ERR); drain_req_pkts(qp); flush_recv_queue(qp, notify); - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); goto exit; } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); qp->resp.aeth_syndrome = AETH_ACK_UNLIMITED; diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index dea605b7f683..4d8f6b8051ff 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -904,10 +904,10 @@ static int rxe_post_send_kernel(struct rxe_qp *qp, if (!err) rxe_sched_task(&qp->req.task); - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (qp_state(qp) == IB_QPS_ERR) rxe_sched_task(&qp->comp.task); - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); return err; } @@ -917,22 +917,23 @@ static int rxe_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr, { struct rxe_qp *qp = to_rqp(ibqp); int err; + unsigned long flags; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); /* caller has already called destroy_qp */ if (WARN_ON_ONCE(!qp->valid)) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); rxe_err_qp(qp, "qp has been destroyed"); return -EINVAL; } if (unlikely(qp_state(qp) < IB_QPS_RTS)) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); *bad_wr = wr; rxe_err_qp(qp, "qp not ready to send"); return -EINVAL; } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); if (qp->is_user) { /* Utilize process context to do protocol processing */ @@ -1008,22 +1009,22 @@ static int rxe_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr, struct rxe_rq *rq = &qp->rq; unsigned long flags; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); /* caller has already called destroy_qp */ if (WARN_ON_ONCE(!qp->valid)) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); rxe_err_qp(qp, "qp has been destroyed"); return -EINVAL; } /* see C10-97.2.1 */ if (unlikely((qp_state(qp) < IB_QPS_INIT))) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); *bad_wr = wr; rxe_dbg_qp(qp, "qp not ready to post recv"); return -EINVAL; } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); if (unlikely(qp->srq)) { *bad_wr = wr; @@ -1044,10 +1045,10 @@ static int rxe_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr, spin_unlock_irqrestore(&rq->producer_lock, flags); - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (qp_state(qp) == IB_QPS_ERR) rxe_sched_task(&qp->resp.task); - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); return err; } diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index 6de900776e24..4d800601e8ec 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -282,6 +282,7 @@ config EXYNOS_IOMMU_DEBUG config IPMMU_VMSA bool "Renesas VMSA-compatible IPMMU" depends on ARCH_RENESAS || COMPILE_TEST + depends on ARM || ARM64 || COMPILE_TEST depends on !GENERIC_ATOMIC64 # for IOMMU_IO_PGTABLE_LPAE select IOMMU_API select IOMMU_IO_PGTABLE_LPAE diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h index e98f20a9bdd8..9beeceb9d825 100644 --- a/drivers/iommu/amd/amd_iommu.h +++ b/drivers/iommu/amd/amd_iommu.h @@ -15,9 +15,7 @@ extern irqreturn_t amd_iommu_int_thread(int irq, void *data); extern irqreturn_t amd_iommu_int_handler(int irq, void *data); extern void amd_iommu_apply_erratum_63(struct amd_iommu *iommu, u16 devid); extern void amd_iommu_restart_event_logging(struct amd_iommu *iommu); -extern int amd_iommu_init_devices(void); -extern void amd_iommu_uninit_devices(void); -extern void amd_iommu_init_notifier(void); +extern void amd_iommu_restart_ga_log(struct amd_iommu *iommu); extern void amd_iommu_set_rlookup_table(struct amd_iommu *iommu, u16 devid); #ifdef CONFIG_AMD_IOMMU_DEBUGFS diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 329a406cc37d..c2d80a4e5fb0 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -759,6 +759,30 @@ void amd_iommu_restart_event_logging(struct amd_iommu *iommu) } /* + * This function restarts event logging in case the IOMMU experienced + * an GA log overflow. + */ +void amd_iommu_restart_ga_log(struct amd_iommu *iommu) +{ + u32 status; + + status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET); + if (status & MMIO_STATUS_GALOG_RUN_MASK) + return; + + pr_info_ratelimited("IOMMU GA Log restarting\n"); + + iommu_feature_disable(iommu, CONTROL_GALOG_EN); + iommu_feature_disable(iommu, CONTROL_GAINT_EN); + + writel(MMIO_STATUS_GALOG_OVERFLOW_MASK, + iommu->mmio_base + MMIO_STATUS_OFFSET); + + iommu_feature_enable(iommu, CONTROL_GAINT_EN); + iommu_feature_enable(iommu, CONTROL_GALOG_EN); +} + +/* * This function resets the command buffer if the IOMMU stopped fetching * commands from it. */ diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 4a314647d1f7..dc1ec6849775 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -845,6 +845,7 @@ amd_iommu_set_pci_msi_domain(struct device *dev, struct amd_iommu *iommu) { } (MMIO_STATUS_EVT_OVERFLOW_INT_MASK | \ MMIO_STATUS_EVT_INT_MASK | \ MMIO_STATUS_PPR_INT_MASK | \ + MMIO_STATUS_GALOG_OVERFLOW_MASK | \ MMIO_STATUS_GALOG_INT_MASK) irqreturn_t amd_iommu_int_thread(int irq, void *data) @@ -868,10 +869,16 @@ irqreturn_t amd_iommu_int_thread(int irq, void *data) } #ifdef CONFIG_IRQ_REMAP - if (status & MMIO_STATUS_GALOG_INT_MASK) { + if (status & (MMIO_STATUS_GALOG_INT_MASK | + MMIO_STATUS_GALOG_OVERFLOW_MASK)) { pr_devel("Processing IOMMU GA Log\n"); iommu_poll_ga_log(iommu); } + + if (status & MMIO_STATUS_GALOG_OVERFLOW_MASK) { + pr_info_ratelimited("IOMMU GA Log overflow\n"); + amd_iommu_restart_ga_log(iommu); + } #endif if (status & MMIO_STATUS_EVT_OVERFLOW_INT_MASK) { @@ -2067,7 +2074,7 @@ static struct protection_domain *protection_domain_alloc(unsigned int type) { struct io_pgtable_ops *pgtbl_ops; struct protection_domain *domain; - int pgtable = amd_iommu_pgtable; + int pgtable; int mode = DEFAULT_PGTABLE_LEVEL; int ret; @@ -2084,6 +2091,10 @@ static struct protection_domain *protection_domain_alloc(unsigned int type) mode = PAGE_MODE_NONE; } else if (type == IOMMU_DOMAIN_UNMANAGED) { pgtable = AMD_IOMMU_V1; + } else if (type == IOMMU_DOMAIN_DMA || type == IOMMU_DOMAIN_DMA_FQ) { + pgtable = amd_iommu_pgtable; + } else { + return NULL; } switch (pgtable) { @@ -2118,6 +2129,15 @@ out_err: return NULL; } +static inline u64 dma_max_address(void) +{ + if (amd_iommu_pgtable == AMD_IOMMU_V1) + return ~0ULL; + + /* V2 with 4/5 level page table */ + return ((1ULL << PM_LEVEL_SHIFT(amd_iommu_gpt_level)) - 1); +} + static struct iommu_domain *amd_iommu_domain_alloc(unsigned type) { struct protection_domain *domain; @@ -2134,7 +2154,7 @@ static struct iommu_domain *amd_iommu_domain_alloc(unsigned type) return NULL; domain->domain.geometry.aperture_start = 0; - domain->domain.geometry.aperture_end = ~0ULL; + domain->domain.geometry.aperture_end = dma_max_address(); domain->domain.geometry.force_aperture = true; return &domain->domain; @@ -2387,7 +2407,7 @@ static void amd_iommu_iotlb_sync(struct iommu_domain *domain, unsigned long flags; spin_lock_irqsave(&dom->lock, flags); - domain_flush_pages(dom, gather->start, gather->end - gather->start, 1); + domain_flush_pages(dom, gather->start, gather->end - gather->start + 1, 1); amd_iommu_domain_flush_complete(dom); spin_unlock_irqrestore(&dom->lock, flags); } @@ -3493,8 +3513,7 @@ int amd_iommu_activate_guest_mode(void *data) struct irte_ga *entry = (struct irte_ga *) ir_data->entry; u64 valid; - if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) || - !entry || entry->lo.fields_vapic.guest_mode) + if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) || !entry) return 0; valid = entry->lo.fields_vapic.valid; diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index aecc7d154f28..e93906d6e112 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -781,7 +781,8 @@ static void mtk_iommu_flush_iotlb_all(struct iommu_domain *domain) { struct mtk_iommu_domain *dom = to_mtk_domain(domain); - mtk_iommu_tlb_flush_all(dom->bank->parent_data); + if (dom->bank) + mtk_iommu_tlb_flush_all(dom->bank->parent_data); } static void mtk_iommu_iotlb_sync(struct iommu_domain *domain, diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c index ea5a3088bb7e..4054030c3237 100644 --- a/drivers/iommu/rockchip-iommu.c +++ b/drivers/iommu/rockchip-iommu.c @@ -1335,20 +1335,22 @@ static int rk_iommu_probe(struct platform_device *pdev) for (i = 0; i < iommu->num_irq; i++) { int irq = platform_get_irq(pdev, i); - if (irq < 0) - return irq; + if (irq < 0) { + err = irq; + goto err_pm_disable; + } err = devm_request_irq(iommu->dev, irq, rk_iommu_irq, IRQF_SHARED, dev_name(dev), iommu); - if (err) { - pm_runtime_disable(dev); - goto err_remove_sysfs; - } + if (err) + goto err_pm_disable; } dma_set_mask_and_coherent(dev, rk_ops->dma_bit_mask); return 0; +err_pm_disable: + pm_runtime_disable(dev); err_remove_sysfs: iommu_device_sysfs_remove(&iommu->iommu); err_put_group: diff --git a/drivers/mailbox/mailbox-test.c b/drivers/mailbox/mailbox-test.c index c4a705c30331..fc6a12a51b40 100644 --- a/drivers/mailbox/mailbox-test.c +++ b/drivers/mailbox/mailbox-test.c @@ -98,6 +98,7 @@ static ssize_t mbox_test_message_write(struct file *filp, size_t count, loff_t *ppos) { struct mbox_test_device *tdev = filp->private_data; + char *message; void *data; int ret; @@ -113,12 +114,13 @@ static ssize_t mbox_test_message_write(struct file *filp, return -EINVAL; } - mutex_lock(&tdev->mutex); - - tdev->message = kzalloc(MBOX_MAX_MSG_LEN, GFP_KERNEL); - if (!tdev->message) + message = kzalloc(MBOX_MAX_MSG_LEN, GFP_KERNEL); + if (!message) return -ENOMEM; + mutex_lock(&tdev->mutex); + + tdev->message = message; ret = copy_from_user(tdev->message, userbuf, count); if (ret) { ret = -EFAULT; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 4739ed891e75..9ea285fbc4a6 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -5516,7 +5516,7 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio) sector = raid5_compute_sector(conf, raid_bio->bi_iter.bi_sector, 0, &dd_idx, NULL); - end_sector = bio_end_sector(raid_bio); + end_sector = sector + bio_sectors(raid_bio); rcu_read_lock(); if (r5c_big_stripe_cached(conf, sector)) diff --git a/drivers/mmc/core/pwrseq_sd8787.c b/drivers/mmc/core/pwrseq_sd8787.c index 2e120ad83020..0c5f5e371e1f 100644 --- a/drivers/mmc/core/pwrseq_sd8787.c +++ b/drivers/mmc/core/pwrseq_sd8787.c @@ -28,7 +28,6 @@ struct mmc_pwrseq_sd8787 { struct mmc_pwrseq pwrseq; struct gpio_desc *reset_gpio; struct gpio_desc *pwrdn_gpio; - u32 reset_pwrdwn_delay_ms; }; #define to_pwrseq_sd8787(p) container_of(p, struct mmc_pwrseq_sd8787, pwrseq) @@ -39,7 +38,7 @@ static void mmc_pwrseq_sd8787_pre_power_on(struct mmc_host *host) gpiod_set_value_cansleep(pwrseq->reset_gpio, 1); - msleep(pwrseq->reset_pwrdwn_delay_ms); + msleep(300); gpiod_set_value_cansleep(pwrseq->pwrdn_gpio, 1); } @@ -51,17 +50,37 @@ static void mmc_pwrseq_sd8787_power_off(struct mmc_host *host) gpiod_set_value_cansleep(pwrseq->reset_gpio, 0); } +static void mmc_pwrseq_wilc1000_pre_power_on(struct mmc_host *host) +{ + struct mmc_pwrseq_sd8787 *pwrseq = to_pwrseq_sd8787(host->pwrseq); + + /* The pwrdn_gpio is really CHIP_EN, reset_gpio is RESETN */ + gpiod_set_value_cansleep(pwrseq->pwrdn_gpio, 1); + msleep(5); + gpiod_set_value_cansleep(pwrseq->reset_gpio, 1); +} + +static void mmc_pwrseq_wilc1000_power_off(struct mmc_host *host) +{ + struct mmc_pwrseq_sd8787 *pwrseq = to_pwrseq_sd8787(host->pwrseq); + + gpiod_set_value_cansleep(pwrseq->reset_gpio, 0); + gpiod_set_value_cansleep(pwrseq->pwrdn_gpio, 0); +} + static const struct mmc_pwrseq_ops mmc_pwrseq_sd8787_ops = { .pre_power_on = mmc_pwrseq_sd8787_pre_power_on, .power_off = mmc_pwrseq_sd8787_power_off, }; -static const u32 sd8787_delay_ms = 300; -static const u32 wilc1000_delay_ms = 5; +static const struct mmc_pwrseq_ops mmc_pwrseq_wilc1000_ops = { + .pre_power_on = mmc_pwrseq_wilc1000_pre_power_on, + .power_off = mmc_pwrseq_wilc1000_power_off, +}; static const struct of_device_id mmc_pwrseq_sd8787_of_match[] = { - { .compatible = "mmc-pwrseq-sd8787", .data = &sd8787_delay_ms }, - { .compatible = "mmc-pwrseq-wilc1000", .data = &wilc1000_delay_ms }, + { .compatible = "mmc-pwrseq-sd8787", .data = &mmc_pwrseq_sd8787_ops }, + { .compatible = "mmc-pwrseq-wilc1000", .data = &mmc_pwrseq_wilc1000_ops }, {/* sentinel */}, }; MODULE_DEVICE_TABLE(of, mmc_pwrseq_sd8787_of_match); @@ -77,7 +96,6 @@ static int mmc_pwrseq_sd8787_probe(struct platform_device *pdev) return -ENOMEM; match = of_match_node(mmc_pwrseq_sd8787_of_match, pdev->dev.of_node); - pwrseq->reset_pwrdwn_delay_ms = *(u32 *)match->data; pwrseq->pwrdn_gpio = devm_gpiod_get(dev, "powerdown", GPIOD_OUT_LOW); if (IS_ERR(pwrseq->pwrdn_gpio)) @@ -88,7 +106,7 @@ static int mmc_pwrseq_sd8787_probe(struct platform_device *pdev) return PTR_ERR(pwrseq->reset_gpio); pwrseq->pwrseq.dev = dev; - pwrseq->pwrseq.ops = &mmc_pwrseq_sd8787_ops; + pwrseq->pwrseq.ops = match->data; pwrseq->pwrseq.owner = THIS_MODULE; platform_set_drvdata(pdev, pwrseq); diff --git a/drivers/mmc/host/vub300.c b/drivers/mmc/host/vub300.c index e4c4bfac3763..9ec593d52f0f 100644 --- a/drivers/mmc/host/vub300.c +++ b/drivers/mmc/host/vub300.c @@ -1713,6 +1713,9 @@ static void construct_request_response(struct vub300_mmc_host *vub300, int bytes = 3 & less_cmd; int words = less_cmd >> 2; u8 *r = vub300->resp.response.command_response; + + if (!resp_len) + return; if (bytes == 3) { cmd->resp[words] = (r[1 + (words << 2)] << 24) | (r[2 + (words << 2)] << 16) diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c index 01f1c6792df9..8dc4f5c493fc 100644 --- a/drivers/mtd/mtdchar.c +++ b/drivers/mtd/mtdchar.c @@ -590,8 +590,8 @@ static void adjust_oob_length(struct mtd_info *mtd, uint64_t start, (end_page - start_page + 1) * oob_per_page); } -static int mtdchar_write_ioctl(struct mtd_info *mtd, - struct mtd_write_req __user *argp) +static noinline_for_stack int +mtdchar_write_ioctl(struct mtd_info *mtd, struct mtd_write_req __user *argp) { struct mtd_info *master = mtd_get_master(mtd); struct mtd_write_req req; @@ -688,8 +688,8 @@ static int mtdchar_write_ioctl(struct mtd_info *mtd, return ret; } -static int mtdchar_read_ioctl(struct mtd_info *mtd, - struct mtd_read_req __user *argp) +static noinline_for_stack int +mtdchar_read_ioctl(struct mtd_info *mtd, struct mtd_read_req __user *argp) { struct mtd_info *master = mtd_get_master(mtd); struct mtd_read_req req; diff --git a/drivers/mtd/nand/raw/ingenic/ingenic_ecc.h b/drivers/mtd/nand/raw/ingenic/ingenic_ecc.h index 2cda439b5e11..017868f59f22 100644 --- a/drivers/mtd/nand/raw/ingenic/ingenic_ecc.h +++ b/drivers/mtd/nand/raw/ingenic/ingenic_ecc.h @@ -36,25 +36,25 @@ int ingenic_ecc_correct(struct ingenic_ecc *ecc, void ingenic_ecc_release(struct ingenic_ecc *ecc); struct ingenic_ecc *of_ingenic_ecc_get(struct device_node *np); #else /* CONFIG_MTD_NAND_INGENIC_ECC */ -int ingenic_ecc_calculate(struct ingenic_ecc *ecc, +static inline int ingenic_ecc_calculate(struct ingenic_ecc *ecc, struct ingenic_ecc_params *params, const u8 *buf, u8 *ecc_code) { return -ENODEV; } -int ingenic_ecc_correct(struct ingenic_ecc *ecc, +static inline int ingenic_ecc_correct(struct ingenic_ecc *ecc, struct ingenic_ecc_params *params, u8 *buf, u8 *ecc_code) { return -ENODEV; } -void ingenic_ecc_release(struct ingenic_ecc *ecc) +static inline void ingenic_ecc_release(struct ingenic_ecc *ecc) { } -struct ingenic_ecc *of_ingenic_ecc_get(struct device_node *np) +static inline struct ingenic_ecc *of_ingenic_ecc_get(struct device_node *np) { return ERR_PTR(-ENODEV); } diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c index afb424579f0b..30c15e4e1cc0 100644 --- a/drivers/mtd/nand/raw/marvell_nand.c +++ b/drivers/mtd/nand/raw/marvell_nand.c @@ -2457,6 +2457,12 @@ static int marvell_nfc_setup_interface(struct nand_chip *chip, int chipnr, NDTR1_WAIT_MODE; } + /* + * Reset nfc->selected_chip so the next command will cause the timing + * registers to be updated in marvell_nfc_select_target(). + */ + nfc->selected_chip = NULL; + return 0; } @@ -2894,10 +2900,6 @@ static int marvell_nfc_init(struct marvell_nfc *nfc) regmap_update_bits(sysctrl_base, GENCONF_CLK_GATING_CTRL, GENCONF_CLK_GATING_CTRL_ND_GATE, GENCONF_CLK_GATING_CTRL_ND_GATE); - - regmap_update_bits(sysctrl_base, GENCONF_ND_CLK_CTRL, - GENCONF_ND_CLK_CTRL_EN, - GENCONF_ND_CLK_CTRL_EN); } /* Configure the DMA if appropriate */ diff --git a/drivers/mtd/spi-nor/core.c b/drivers/mtd/spi-nor/core.c index 0bb0ad14a2fc..5f29fac8669a 100644 --- a/drivers/mtd/spi-nor/core.c +++ b/drivers/mtd/spi-nor/core.c @@ -2018,6 +2018,7 @@ static const struct spi_nor_manufacturer *manufacturers[] = { static const struct flash_info spi_nor_generic_flash = { .name = "spi-nor-generic", + .n_banks = 1, /* * JESD216 rev A doesn't specify the page size, therefore we need a * sane default. @@ -2921,7 +2922,8 @@ static void spi_nor_late_init_params(struct spi_nor *nor) if (nor->flags & SNOR_F_HAS_LOCK && !nor->params->locking_ops) spi_nor_init_default_locking_ops(nor); - nor->params->bank_size = div64_u64(nor->params->size, nor->info->n_banks); + if (nor->info->n_banks > 1) + params->bank_size = div64_u64(params->size, nor->info->n_banks); } /** @@ -2987,6 +2989,7 @@ static void spi_nor_init_default_params(struct spi_nor *nor) /* Set SPI NOR sizes. */ params->writesize = 1; params->size = (u64)info->sector_size * info->n_sectors; + params->bank_size = params->size; params->page_size = info->page_size; if (!(info->flags & SPI_NOR_NO_FR)) { diff --git a/drivers/mtd/spi-nor/spansion.c b/drivers/mtd/spi-nor/spansion.c index 15f9a80c10b9..36876aa849ed 100644 --- a/drivers/mtd/spi-nor/spansion.c +++ b/drivers/mtd/spi-nor/spansion.c @@ -361,7 +361,7 @@ static int cypress_nor_determine_addr_mode_by_sr1(struct spi_nor *nor, */ static int cypress_nor_set_addr_mode_nbytes(struct spi_nor *nor) { - struct spi_mem_op op; + struct spi_mem_op op = {}; u8 addr_mode; int ret; @@ -492,7 +492,7 @@ s25fs256t_post_bfpt_fixup(struct spi_nor *nor, const struct sfdp_parameter_header *bfpt_header, const struct sfdp_bfpt *bfpt) { - struct spi_mem_op op; + struct spi_mem_op op = {}; int ret; ret = cypress_nor_set_addr_mode_nbytes(nor); diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 64a2f2f83735..08a46ffd53af 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -7170,7 +7170,7 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev) goto out; } if (chip->reset) - usleep_range(1000, 2000); + usleep_range(10000, 20000); /* Detect if the device is configured in single chip addressing mode, * otherwise continue with address specific smi init/detection. diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c index 33a9574e9e04..32d2c6fac652 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c @@ -1329,7 +1329,7 @@ static enum xgbe_mode xgbe_phy_status_aneg(struct xgbe_prv_data *pdata) return pdata->phy_if.phy_impl.an_outcome(pdata); } -static void xgbe_phy_status_result(struct xgbe_prv_data *pdata) +static bool xgbe_phy_status_result(struct xgbe_prv_data *pdata) { struct ethtool_link_ksettings *lks = &pdata->phy.lks; enum xgbe_mode mode; @@ -1367,8 +1367,13 @@ static void xgbe_phy_status_result(struct xgbe_prv_data *pdata) pdata->phy.duplex = DUPLEX_FULL; - if (xgbe_set_mode(pdata, mode) && pdata->an_again) + if (!xgbe_set_mode(pdata, mode)) + return false; + + if (pdata->an_again) xgbe_phy_reconfig_aneg(pdata); + + return true; } static void xgbe_phy_status(struct xgbe_prv_data *pdata) @@ -1398,7 +1403,8 @@ static void xgbe_phy_status(struct xgbe_prv_data *pdata) return; } - xgbe_phy_status_result(pdata); + if (xgbe_phy_status_result(pdata)) + return; if (test_bit(XGBE_LINK_INIT, &pdata->dev_state)) clear_bit(XGBE_LINK_INIT, &pdata->dev_state); diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 059bd911c51d..52d0a126eb61 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -1152,11 +1152,11 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) unsigned int total_rx_bytes = 0, total_rx_pkts = 0; unsigned int offset = rx_ring->rx_offset; struct xdp_buff *xdp = &rx_ring->xdp; + u32 cached_ntc = rx_ring->first_desc; struct ice_tx_ring *xdp_ring = NULL; struct bpf_prog *xdp_prog = NULL; u32 ntc = rx_ring->next_to_clean; u32 cnt = rx_ring->count; - u32 cached_ntc = ntc; u32 xdp_xmit = 0; u32 cached_ntu; bool failure; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index f40497823e65..7c0f2adbea00 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -490,7 +490,7 @@ static void poll_trace(struct mlx5_fw_tracer *tracer, (u64)timestamp_low; break; default: - if (tracer_event->event_id >= tracer->str_db.first_string_trace || + if (tracer_event->event_id >= tracer->str_db.first_string_trace && tracer_event->event_id <= tracer->str_db.first_string_trace + tracer->str_db.num_string_trace) { tracer_event->type = TRACER_EVENT_TYPE_STRING; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index b8987a404d75..8e999f238194 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -327,6 +327,7 @@ struct mlx5e_params { unsigned int sw_mtu; int hard_mtu; bool ptp_rx; + __be32 terminate_lkey_be; }; static inline u8 mlx5e_get_dcb_num_tc(struct mlx5e_params *params) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c index 7ac1ad9c46de..7e8e96cc5cd0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c @@ -51,7 +51,7 @@ int mlx5e_port_query_buffer(struct mlx5e_priv *priv, if (err) goto out; - for (i = 0; i < MLX5E_MAX_BUFFER; i++) { + for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) { buffer = MLX5_ADDR_OF(pbmc_reg, out, buffer[i]); port_buffer->buffer[i].lossy = MLX5_GET(bufferx_reg, buffer, lossy); @@ -73,14 +73,24 @@ int mlx5e_port_query_buffer(struct mlx5e_priv *priv, port_buffer->buffer[i].lossy); } - port_buffer->headroom_size = total_used; + port_buffer->internal_buffers_size = 0; + for (i = MLX5E_MAX_NETWORK_BUFFER; i < MLX5E_TOTAL_BUFFERS; i++) { + buffer = MLX5_ADDR_OF(pbmc_reg, out, buffer[i]); + port_buffer->internal_buffers_size += + MLX5_GET(bufferx_reg, buffer, size) * port_buff_cell_sz; + } + port_buffer->port_buffer_size = MLX5_GET(pbmc_reg, out, port_buffer_size) * port_buff_cell_sz; - port_buffer->spare_buffer_size = - port_buffer->port_buffer_size - total_used; - - mlx5e_dbg(HW, priv, "total buffer size=%d, spare buffer size=%d\n", - port_buffer->port_buffer_size, + port_buffer->headroom_size = total_used; + port_buffer->spare_buffer_size = port_buffer->port_buffer_size - + port_buffer->internal_buffers_size - + port_buffer->headroom_size; + + mlx5e_dbg(HW, priv, + "total buffer size=%u, headroom buffer size=%u, internal buffers size=%u, spare buffer size=%u\n", + port_buffer->port_buffer_size, port_buffer->headroom_size, + port_buffer->internal_buffers_size, port_buffer->spare_buffer_size); out: kfree(out); @@ -206,11 +216,11 @@ static int port_update_pool_cfg(struct mlx5_core_dev *mdev, if (!MLX5_CAP_GEN(mdev, sbcam_reg)) return 0; - for (i = 0; i < MLX5E_MAX_BUFFER; i++) + for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) lossless_buff_count += ((port_buffer->buffer[i].size) && (!(port_buffer->buffer[i].lossy))); - for (i = 0; i < MLX5E_MAX_BUFFER; i++) { + for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) { p = select_sbcm_params(&port_buffer->buffer[i], lossless_buff_count); err = mlx5e_port_set_sbcm(mdev, 0, i, MLX5_INGRESS_DIR, @@ -293,7 +303,7 @@ static int port_set_buffer(struct mlx5e_priv *priv, if (err) goto out; - for (i = 0; i < MLX5E_MAX_BUFFER; i++) { + for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) { void *buffer = MLX5_ADDR_OF(pbmc_reg, in, buffer[i]); u64 size = port_buffer->buffer[i].size; u64 xoff = port_buffer->buffer[i].xoff; @@ -351,7 +361,7 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer, { int i; - for (i = 0; i < MLX5E_MAX_BUFFER; i++) { + for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) { if (port_buffer->buffer[i].lossy) { port_buffer->buffer[i].xoff = 0; port_buffer->buffer[i].xon = 0; @@ -408,7 +418,7 @@ static int update_buffer_lossy(struct mlx5_core_dev *mdev, int err; int i; - for (i = 0; i < MLX5E_MAX_BUFFER; i++) { + for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) { prio_count = 0; lossy_count = 0; @@ -432,11 +442,11 @@ static int update_buffer_lossy(struct mlx5_core_dev *mdev, } if (changed) { - err = port_update_pool_cfg(mdev, port_buffer); + err = update_xoff_threshold(port_buffer, xoff, max_mtu, port_buff_cell_sz); if (err) return err; - err = update_xoff_threshold(port_buffer, xoff, max_mtu, port_buff_cell_sz); + err = port_update_pool_cfg(mdev, port_buffer); if (err) return err; @@ -515,7 +525,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, if (change & MLX5E_PORT_BUFFER_PRIO2BUFFER) { update_prio2buffer = true; - for (i = 0; i < MLX5E_MAX_BUFFER; i++) + for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) mlx5e_dbg(HW, priv, "%s: requested to map prio[%d] to buffer %d\n", __func__, i, prio2buffer[i]); @@ -530,7 +540,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, } if (change & MLX5E_PORT_BUFFER_SIZE) { - for (i = 0; i < MLX5E_MAX_BUFFER; i++) { + for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) { mlx5e_dbg(HW, priv, "%s: buffer[%d]=%d\n", __func__, i, buffer_size[i]); if (!port_buffer.buffer[i].lossy && !buffer_size[i]) { mlx5e_dbg(HW, priv, "%s: lossless buffer[%d] size cannot be zero\n", @@ -544,7 +554,9 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, mlx5e_dbg(HW, priv, "%s: total buffer requested=%d\n", __func__, total_used); - if (total_used > port_buffer.port_buffer_size) + if (total_used > port_buffer.headroom_size && + (total_used - port_buffer.headroom_size) > + port_buffer.spare_buffer_size) return -EINVAL; update_buffer = true; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h index a6ef118de758..f4a19ffbb641 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h @@ -35,7 +35,8 @@ #include "en.h" #include "port.h" -#define MLX5E_MAX_BUFFER 8 +#define MLX5E_MAX_NETWORK_BUFFER 8 +#define MLX5E_TOTAL_BUFFERS 10 #define MLX5E_DEFAULT_CABLE_LEN 7 /* 7 meters */ #define MLX5_BUFFER_SUPPORTED(mdev) (MLX5_CAP_GEN(mdev, pcam_reg) && \ @@ -60,8 +61,9 @@ struct mlx5e_bufferx_reg { struct mlx5e_port_buffer { u32 port_buffer_size; u32 spare_buffer_size; - u32 headroom_size; - struct mlx5e_bufferx_reg buffer[MLX5E_MAX_BUFFER]; + u32 headroom_size; /* Buffers 0-7 */ + u32 internal_buffers_size; /* Buffers 8-9 */ + struct mlx5e_bufferx_reg buffer[MLX5E_MAX_NETWORK_BUFFER]; }; int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c index fc923a99b6a4..0380a04c3691 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c @@ -84,7 +84,7 @@ mlx5e_tc_act_init_parse_state(struct mlx5e_tc_act_parse_state *parse_state, int mlx5e_tc_act_post_parse(struct mlx5e_tc_act_parse_state *parse_state, - struct flow_action *flow_action, + struct flow_action *flow_action, int from, int to, struct mlx5_flow_attr *attr, enum mlx5_flow_namespace_type ns_type) { @@ -96,6 +96,11 @@ mlx5e_tc_act_post_parse(struct mlx5e_tc_act_parse_state *parse_state, priv = parse_state->flow->priv; flow_action_for_each(i, act, flow_action) { + if (i < from) + continue; + else if (i > to) + break; + tc_act = mlx5e_tc_act_get(act->id, ns_type); if (!tc_act || !tc_act->post_parse) continue; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h index 0e6e1872ac62..d6c12d0ea55b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h @@ -112,7 +112,7 @@ mlx5e_tc_act_init_parse_state(struct mlx5e_tc_act_parse_state *parse_state, int mlx5e_tc_act_post_parse(struct mlx5e_tc_act_parse_state *parse_state, - struct flow_action *flow_action, + struct flow_action *flow_action, int from, int to, struct mlx5_flow_attr *attr, enum mlx5_flow_namespace_type ns_type); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index 6a052c6cfc15..f0c3464f037f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -492,6 +492,19 @@ void mlx5e_encap_put(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e) mlx5e_encap_dealloc(priv, e); } +static void mlx5e_encap_put_locked(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e) +{ + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + + lockdep_assert_held(&esw->offloads.encap_tbl_lock); + + if (!refcount_dec_and_test(&e->refcnt)) + return; + list_del(&e->route_list); + hash_del_rcu(&e->encap_hlist); + mlx5e_encap_dealloc(priv, e); +} + static void mlx5e_decap_put(struct mlx5e_priv *priv, struct mlx5e_decap_entry *d) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; @@ -816,6 +829,8 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv, uintptr_t hash_key; int err = 0; + lockdep_assert_held(&esw->offloads.encap_tbl_lock); + parse_attr = attr->parse_attr; tun_info = parse_attr->tun_info[out_index]; mpls_info = &parse_attr->mpls_info[out_index]; @@ -829,7 +844,6 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv, hash_key = hash_encap_info(&key); - mutex_lock(&esw->offloads.encap_tbl_lock); e = mlx5e_encap_get(priv, &key, hash_key); /* must verify if encap is valid or not */ @@ -840,15 +854,6 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv, goto out_err; } - mutex_unlock(&esw->offloads.encap_tbl_lock); - wait_for_completion(&e->res_ready); - - /* Protect against concurrent neigh update. */ - mutex_lock(&esw->offloads.encap_tbl_lock); - if (e->compl_result < 0) { - err = -EREMOTEIO; - goto out_err; - } goto attach_flow; } @@ -877,15 +882,12 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv, INIT_LIST_HEAD(&e->flows); hash_add_rcu(esw->offloads.encap_tbl, &e->encap_hlist, hash_key); tbl_time_before = mlx5e_route_tbl_get_last_update(priv); - mutex_unlock(&esw->offloads.encap_tbl_lock); if (family == AF_INET) err = mlx5e_tc_tun_create_header_ipv4(priv, mirred_dev, e); else if (family == AF_INET6) err = mlx5e_tc_tun_create_header_ipv6(priv, mirred_dev, e); - /* Protect against concurrent neigh update. */ - mutex_lock(&esw->offloads.encap_tbl_lock); complete_all(&e->res_ready); if (err) { e->compl_result = err; @@ -920,18 +922,15 @@ attach_flow: } else { flow_flag_set(flow, SLOW); } - mutex_unlock(&esw->offloads.encap_tbl_lock); return err; out_err: - mutex_unlock(&esw->offloads.encap_tbl_lock); if (e) - mlx5e_encap_put(priv, e); + mlx5e_encap_put_locked(priv, e); return err; out_err_init: - mutex_unlock(&esw->offloads.encap_tbl_lock); kfree(tun_info); kfree(e); return err; @@ -1016,6 +1015,93 @@ out_err: return err; } +int mlx5e_tc_tun_encap_dests_set(struct mlx5e_priv *priv, + struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr, + struct netlink_ext_ack *extack, + bool *vf_tun) +{ + struct mlx5e_tc_flow_parse_attr *parse_attr; + struct mlx5_esw_flow_attr *esw_attr; + struct net_device *encap_dev = NULL; + struct mlx5e_rep_priv *rpriv; + struct mlx5e_priv *out_priv; + struct mlx5_eswitch *esw; + int out_index; + int err = 0; + + if (!mlx5e_is_eswitch_flow(flow)) + return 0; + + parse_attr = attr->parse_attr; + esw_attr = attr->esw_attr; + *vf_tun = false; + + esw = priv->mdev->priv.eswitch; + mutex_lock(&esw->offloads.encap_tbl_lock); + for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) { + struct net_device *out_dev; + int mirred_ifindex; + + if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP)) + continue; + + mirred_ifindex = parse_attr->mirred_ifindex[out_index]; + out_dev = dev_get_by_index(dev_net(priv->netdev), mirred_ifindex); + if (!out_dev) { + NL_SET_ERR_MSG_MOD(extack, "Requested mirred device not found"); + err = -ENODEV; + goto out; + } + err = mlx5e_attach_encap(priv, flow, attr, out_dev, out_index, + extack, &encap_dev); + dev_put(out_dev); + if (err) + goto out; + + if (esw_attr->dests[out_index].flags & + MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE && + !esw_attr->dest_int_port) + *vf_tun = true; + + out_priv = netdev_priv(encap_dev); + rpriv = out_priv->ppriv; + esw_attr->dests[out_index].rep = rpriv->rep; + esw_attr->dests[out_index].mdev = out_priv->mdev; + } + + if (*vf_tun && esw_attr->out_count > 1) { + NL_SET_ERR_MSG_MOD(extack, "VF tunnel encap with mirroring is not supported"); + err = -EOPNOTSUPP; + goto out; + } + +out: + mutex_unlock(&esw->offloads.encap_tbl_lock); + return err; +} + +void mlx5e_tc_tun_encap_dests_unset(struct mlx5e_priv *priv, + struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr) +{ + struct mlx5_esw_flow_attr *esw_attr; + int out_index; + + if (!mlx5e_is_eswitch_flow(flow)) + return; + + esw_attr = attr->esw_attr; + + for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) { + if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP)) + continue; + + mlx5e_detach_encap(flow->priv, flow, attr, out_index); + kfree(attr->parse_attr->tun_info[out_index]); + } +} + static int cmp_route_info(struct mlx5e_route_key *a, struct mlx5e_route_key *b) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h index 8ad273dde40e..5d7d67687cbc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h @@ -30,6 +30,15 @@ int mlx5e_attach_decap_route(struct mlx5e_priv *priv, void mlx5e_detach_decap_route(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow); +int mlx5e_tc_tun_encap_dests_set(struct mlx5e_priv *priv, + struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr, + struct netlink_ext_ack *extack, + bool *vf_tun); +void mlx5e_tc_tun_encap_dests_unset(struct mlx5e_priv *priv, + struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr); + struct ip_tunnel_info *mlx5e_dup_tun_info(const struct ip_tunnel_info *tun_info); int mlx5e_tc_set_attr_rx_tun(struct mlx5e_tc_flow *flow, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c index 1f90594499c6..41c396e76457 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c @@ -150,10 +150,8 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb, inlen = MLX5_ST_SZ_BYTES(modify_tir_in); in = kvzalloc(inlen, GFP_KERNEL); - if (!in) { - err = -ENOMEM; - goto out; - } + if (!in) + return -ENOMEM; if (enable_uc_lb) lb_flags = MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST; @@ -171,14 +169,13 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb, tirn = tir->tirn; err = mlx5_core_modify_tir(mdev, tirn, in); if (err) - goto out; + break; } + mutex_unlock(&mdev->mlx5e_res.hw_objs.td.list_lock); -out: kvfree(in); if (err) netdev_err(priv->netdev, "refresh tir(0x%x) failed, %d\n", tirn, err); - mutex_unlock(&mdev->mlx5e_res.hw_objs.td.list_lock); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index 89de92d06483..ebee52a8361a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -926,9 +926,10 @@ static int mlx5e_dcbnl_getbuffer(struct net_device *dev, if (err) return err; - for (i = 0; i < MLX5E_MAX_BUFFER; i++) + for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) dcb_buffer->buffer_size[i] = port_buffer.buffer[i].size; - dcb_buffer->total_size = port_buffer.port_buffer_size; + dcb_buffer->total_size = port_buffer.port_buffer_size - + port_buffer.internal_buffers_size; return 0; } @@ -970,7 +971,7 @@ static int mlx5e_dcbnl_setbuffer(struct net_device *dev, if (err) return err; - for (i = 0; i < MLX5E_MAX_BUFFER; i++) { + for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) { if (port_buffer.buffer[i].size != dcb_buffer->buffer_size[i]) { changed |= MLX5E_PORT_BUFFER_SIZE; buffer_size = dcb_buffer->buffer_size; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 2944691f06ad..a7c526ee5024 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -727,26 +727,6 @@ static void mlx5e_rq_free_shampo(struct mlx5e_rq *rq) mlx5e_rq_shampo_hd_free(rq); } -static __be32 mlx5e_get_terminate_scatter_list_mkey(struct mlx5_core_dev *dev) -{ - u32 out[MLX5_ST_SZ_DW(query_special_contexts_out)] = {}; - u32 in[MLX5_ST_SZ_DW(query_special_contexts_in)] = {}; - int res; - - if (!MLX5_CAP_GEN(dev, terminate_scatter_list_mkey)) - return MLX5_TERMINATE_SCATTER_LIST_LKEY; - - MLX5_SET(query_special_contexts_in, in, opcode, - MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS); - res = mlx5_cmd_exec_inout(dev, query_special_contexts, in, out); - if (res) - return MLX5_TERMINATE_SCATTER_LIST_LKEY; - - res = MLX5_GET(query_special_contexts_out, out, - terminate_scatter_list_mkey); - return cpu_to_be32(res); -} - static int mlx5e_alloc_rq(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk, struct mlx5e_rq_param *rqp, @@ -908,7 +888,7 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params, /* check if num_frags is not a pow of two */ if (rq->wqe.info.num_frags < (1 << rq->wqe.info.log_num_frags)) { wqe->data[f].byte_count = 0; - wqe->data[f].lkey = mlx5e_get_terminate_scatter_list_mkey(mdev); + wqe->data[f].lkey = params->terminate_lkey_be; wqe->data[f].addr = 0; } } @@ -5007,6 +4987,8 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 /* RQ */ mlx5e_build_rq_params(mdev, params); + params->terminate_lkey_be = mlx5_core_get_terminate_scatter_list_mkey(mdev); + params->packet_merge.timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT); /* CQ moderation params */ @@ -5279,12 +5261,16 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev, mlx5e_timestamp_init(priv); + priv->dfs_root = debugfs_create_dir("nic", + mlx5_debugfs_get_dev_root(mdev)); + fs = mlx5e_fs_init(priv->profile, mdev, !test_bit(MLX5E_STATE_DESTROYING, &priv->state), priv->dfs_root); if (!fs) { err = -ENOMEM; mlx5_core_err(mdev, "FS initialization failed, %d\n", err); + debugfs_remove_recursive(priv->dfs_root); return err; } priv->fs = fs; @@ -5305,6 +5291,7 @@ static void mlx5e_nic_cleanup(struct mlx5e_priv *priv) mlx5e_health_destroy_reporters(priv); mlx5e_ktls_cleanup(priv); mlx5e_fs_cleanup(priv->fs); + debugfs_remove_recursive(priv->dfs_root); priv->fs = NULL; } @@ -5851,8 +5838,8 @@ void mlx5e_detach_netdev(struct mlx5e_priv *priv) } static int -mlx5e_netdev_attach_profile(struct net_device *netdev, struct mlx5_core_dev *mdev, - const struct mlx5e_profile *new_profile, void *new_ppriv) +mlx5e_netdev_init_profile(struct net_device *netdev, struct mlx5_core_dev *mdev, + const struct mlx5e_profile *new_profile, void *new_ppriv) { struct mlx5e_priv *priv = netdev_priv(netdev); int err; @@ -5868,6 +5855,25 @@ mlx5e_netdev_attach_profile(struct net_device *netdev, struct mlx5_core_dev *mde err = new_profile->init(priv->mdev, priv->netdev); if (err) goto priv_cleanup; + + return 0; + +priv_cleanup: + mlx5e_priv_cleanup(priv); + return err; +} + +static int +mlx5e_netdev_attach_profile(struct net_device *netdev, struct mlx5_core_dev *mdev, + const struct mlx5e_profile *new_profile, void *new_ppriv) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + int err; + + err = mlx5e_netdev_init_profile(netdev, mdev, new_profile, new_ppriv); + if (err) + return err; + err = mlx5e_attach_netdev(priv); if (err) goto profile_cleanup; @@ -5875,7 +5881,6 @@ mlx5e_netdev_attach_profile(struct net_device *netdev, struct mlx5_core_dev *mde profile_cleanup: new_profile->cleanup(priv); -priv_cleanup: mlx5e_priv_cleanup(priv); return err; } @@ -5894,6 +5899,12 @@ int mlx5e_netdev_change_profile(struct mlx5e_priv *priv, priv->profile->cleanup(priv); mlx5e_priv_cleanup(priv); + if (mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) { + mlx5e_netdev_init_profile(netdev, mdev, new_profile, new_ppriv); + set_bit(MLX5E_STATE_DESTROYING, &priv->state); + return -EIO; + } + err = mlx5e_netdev_attach_profile(netdev, mdev, new_profile, new_ppriv); if (err) { /* roll back to original profile */ netdev_warn(netdev, "%s: new profile init failed, %d\n", __func__, err); @@ -5955,8 +5966,11 @@ static int mlx5e_suspend(struct auxiliary_device *adev, pm_message_t state) struct net_device *netdev = priv->netdev; struct mlx5_core_dev *mdev = priv->mdev; - if (!netif_device_present(netdev)) + if (!netif_device_present(netdev)) { + if (test_bit(MLX5E_STATE_DESTROYING, &priv->state)) + mlx5e_destroy_mdev_resources(mdev); return -ENODEV; + } mlx5e_detach_netdev(priv); mlx5e_destroy_mdev_resources(mdev); @@ -6002,9 +6016,6 @@ static int mlx5e_probe(struct auxiliary_device *adev, priv->profile = profile; priv->ppriv = NULL; - priv->dfs_root = debugfs_create_dir("nic", - mlx5_debugfs_get_dev_root(priv->mdev)); - err = profile->init(mdev, netdev); if (err) { mlx5_core_err(mdev, "mlx5e_nic_profile init failed, %d\n", err); @@ -6033,7 +6044,6 @@ err_resume: err_profile_cleanup: profile->cleanup(priv); err_destroy_netdev: - debugfs_remove_recursive(priv->dfs_root); mlx5e_destroy_netdev(priv); err_devlink_port_unregister: mlx5e_devlink_port_unregister(mlx5e_dev); @@ -6053,7 +6063,6 @@ static void mlx5e_remove(struct auxiliary_device *adev) unregister_netdev(priv->netdev); mlx5e_suspend(adev, state); priv->profile->cleanup(priv); - debugfs_remove_recursive(priv->dfs_root); mlx5e_destroy_netdev(priv); mlx5e_devlink_port_unregister(mlx5e_dev); mlx5e_destroy_devlink(mlx5e_dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 1fc386eccaf8..3e7041bd5705 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -30,6 +30,7 @@ * SOFTWARE. */ +#include <linux/debugfs.h> #include <linux/mlx5/fs.h> #include <net/switchdev.h> #include <net/pkt_cls.h> @@ -812,11 +813,15 @@ static int mlx5e_init_ul_rep(struct mlx5_core_dev *mdev, { struct mlx5e_priv *priv = netdev_priv(netdev); + priv->dfs_root = debugfs_create_dir("nic", + mlx5_debugfs_get_dev_root(mdev)); + priv->fs = mlx5e_fs_init(priv->profile, mdev, !test_bit(MLX5E_STATE_DESTROYING, &priv->state), priv->dfs_root); if (!priv->fs) { netdev_err(priv->netdev, "FS allocation failed\n"); + debugfs_remove_recursive(priv->dfs_root); return -ENOMEM; } @@ -829,6 +834,7 @@ static int mlx5e_init_ul_rep(struct mlx5_core_dev *mdev, static void mlx5e_cleanup_rep(struct mlx5e_priv *priv) { mlx5e_fs_cleanup(priv->fs); + debugfs_remove_recursive(priv->dfs_root); priv->fs = NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index e95414ef1f04..8a5a8703f0a3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1700,91 +1700,6 @@ int mlx5e_tc_query_route_vport(struct net_device *out_dev, struct net_device *ro } static int -set_encap_dests(struct mlx5e_priv *priv, - struct mlx5e_tc_flow *flow, - struct mlx5_flow_attr *attr, - struct netlink_ext_ack *extack, - bool *vf_tun) -{ - struct mlx5e_tc_flow_parse_attr *parse_attr; - struct mlx5_esw_flow_attr *esw_attr; - struct net_device *encap_dev = NULL; - struct mlx5e_rep_priv *rpriv; - struct mlx5e_priv *out_priv; - int out_index; - int err = 0; - - if (!mlx5e_is_eswitch_flow(flow)) - return 0; - - parse_attr = attr->parse_attr; - esw_attr = attr->esw_attr; - *vf_tun = false; - - for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) { - struct net_device *out_dev; - int mirred_ifindex; - - if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP)) - continue; - - mirred_ifindex = parse_attr->mirred_ifindex[out_index]; - out_dev = dev_get_by_index(dev_net(priv->netdev), mirred_ifindex); - if (!out_dev) { - NL_SET_ERR_MSG_MOD(extack, "Requested mirred device not found"); - err = -ENODEV; - goto out; - } - err = mlx5e_attach_encap(priv, flow, attr, out_dev, out_index, - extack, &encap_dev); - dev_put(out_dev); - if (err) - goto out; - - if (esw_attr->dests[out_index].flags & - MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE && - !esw_attr->dest_int_port) - *vf_tun = true; - - out_priv = netdev_priv(encap_dev); - rpriv = out_priv->ppriv; - esw_attr->dests[out_index].rep = rpriv->rep; - esw_attr->dests[out_index].mdev = out_priv->mdev; - } - - if (*vf_tun && esw_attr->out_count > 1) { - NL_SET_ERR_MSG_MOD(extack, "VF tunnel encap with mirroring is not supported"); - err = -EOPNOTSUPP; - goto out; - } - -out: - return err; -} - -static void -clean_encap_dests(struct mlx5e_priv *priv, - struct mlx5e_tc_flow *flow, - struct mlx5_flow_attr *attr) -{ - struct mlx5_esw_flow_attr *esw_attr; - int out_index; - - if (!mlx5e_is_eswitch_flow(flow)) - return; - - esw_attr = attr->esw_attr; - - for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) { - if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP)) - continue; - - mlx5e_detach_encap(priv, flow, attr, out_index); - kfree(attr->parse_attr->tun_info[out_index]); - } -} - -static int verify_attr_actions(u32 actions, struct netlink_ext_ack *extack) { if (!(actions & @@ -1820,7 +1735,7 @@ post_process_attr(struct mlx5e_tc_flow *flow, if (err) goto err_out; - err = set_encap_dests(flow->priv, flow, attr, extack, &vf_tun); + err = mlx5e_tc_tun_encap_dests_set(flow->priv, flow, attr, extack, &vf_tun); if (err) goto err_out; @@ -3944,8 +3859,8 @@ parse_tc_actions(struct mlx5e_tc_act_parse_state *parse_state, struct mlx5_flow_attr *prev_attr; struct flow_action_entry *act; struct mlx5e_tc_act *tc_act; + int err, i, i_split = 0; bool is_missable; - int err, i; ns_type = mlx5e_get_flow_namespace(flow); list_add(&attr->list, &flow->attrs); @@ -3986,7 +3901,8 @@ parse_tc_actions(struct mlx5e_tc_act_parse_state *parse_state, i < flow_action->num_entries - 1)) { is_missable = tc_act->is_missable ? tc_act->is_missable(act) : false; - err = mlx5e_tc_act_post_parse(parse_state, flow_action, attr, ns_type); + err = mlx5e_tc_act_post_parse(parse_state, flow_action, i_split, i, attr, + ns_type); if (err) goto out_free_post_acts; @@ -3996,6 +3912,7 @@ parse_tc_actions(struct mlx5e_tc_act_parse_state *parse_state, goto out_free_post_acts; } + i_split = i + 1; list_add(&attr->list, &flow->attrs); } @@ -4010,7 +3927,7 @@ parse_tc_actions(struct mlx5e_tc_act_parse_state *parse_state, } } - err = mlx5e_tc_act_post_parse(parse_state, flow_action, attr, ns_type); + err = mlx5e_tc_act_post_parse(parse_state, flow_action, i_split, i, attr, ns_type); if (err) goto out_free_post_acts; @@ -4324,7 +4241,7 @@ mlx5_free_flow_attr_actions(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *a if (attr->post_act_handle) mlx5e_tc_post_act_del(get_post_action(flow->priv), attr->post_act_handle); - clean_encap_dests(flow->priv, flow, attr); + mlx5e_tc_tun_encap_dests_unset(flow->priv, flow, attr); if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) mlx5_fc_destroy(counter_dev, attr->counter); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index fe698c79616c..3db4866d7880 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -824,7 +824,7 @@ static int comp_irqs_request_pci(struct mlx5_core_dev *dev) ncomp_eqs = table->num_comp_eqs; cpus = kcalloc(ncomp_eqs, sizeof(*cpus), GFP_KERNEL); if (!cpus) - ret = -ENOMEM; + return -ENOMEM; i = 0; rcu_read_lock(); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index a7eb65cd0bdd..d6ee016deae1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -923,7 +923,6 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct pci_dev *pdev, } mlx5_pci_vsc_init(dev); - dev->caps.embedded_cpu = mlx5_read_embedded_cpu(dev); return 0; err_clr_master: @@ -1155,6 +1154,7 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot, u64 timeout goto err_cmd_cleanup; } + dev->caps.embedded_cpu = mlx5_read_embedded_cpu(dev); mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_UP); mlx5_start_health_poll(dev); @@ -1802,15 +1802,16 @@ static void remove_one(struct pci_dev *pdev) struct devlink *devlink = priv_to_devlink(dev); set_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state); - /* mlx5_drain_fw_reset() is using devlink APIs. Hence, we must drain - * fw_reset before unregistering the devlink. + /* mlx5_drain_fw_reset() and mlx5_drain_health_wq() are using + * devlink notify APIs. + * Hence, we must drain them before unregistering the devlink. */ mlx5_drain_fw_reset(dev); + mlx5_drain_health_wq(dev); devlink_unregister(devlink); mlx5_sriov_disable(pdev); mlx5_thermal_uninit(dev); mlx5_crdump_disable(dev); - mlx5_drain_health_wq(dev); mlx5_uninit_one(dev); mlx5_pci_close(dev); mlx5_mdev_uninit(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c index 9d735c343a3b..678f0be81375 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c @@ -32,6 +32,7 @@ #include <linux/kernel.h> #include <linux/mlx5/driver.h> +#include <linux/mlx5/qp.h> #include "mlx5_core.h" int mlx5_core_create_mkey(struct mlx5_core_dev *dev, u32 *mkey, u32 *in, @@ -122,3 +123,23 @@ int mlx5_core_destroy_psv(struct mlx5_core_dev *dev, int psv_num) return mlx5_cmd_exec_in(dev, destroy_psv, in); } EXPORT_SYMBOL(mlx5_core_destroy_psv); + +__be32 mlx5_core_get_terminate_scatter_list_mkey(struct mlx5_core_dev *dev) +{ + u32 out[MLX5_ST_SZ_DW(query_special_contexts_out)] = {}; + u32 in[MLX5_ST_SZ_DW(query_special_contexts_in)] = {}; + u32 mkey; + + if (!MLX5_CAP_GEN(dev, terminate_scatter_list_mkey)) + return MLX5_TERMINATE_SCATTER_LIST_LKEY; + + MLX5_SET(query_special_contexts_in, in, opcode, + MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS); + if (mlx5_cmd_exec_inout(dev, query_special_contexts, in, out)) + return MLX5_TERMINATE_SCATTER_LIST_LKEY; + + mkey = MLX5_GET(query_special_contexts_out, out, + terminate_scatter_list_mkey); + return cpu_to_be32(mkey); +} +EXPORT_SYMBOL(mlx5_core_get_terminate_scatter_list_mkey); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index db5687d9fec9..843da89a9035 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -141,7 +141,7 @@ static void irq_release(struct mlx5_irq *irq) irq_update_affinity_hint(irq->map.virq, NULL); #ifdef CONFIG_RFS_ACCEL rmap = mlx5_eq_table_get_rmap(pool->dev); - if (rmap && irq->map.index) + if (rmap) irq_cpu_rmap_remove(rmap, irq->map.virq); #endif @@ -232,12 +232,13 @@ struct mlx5_irq *mlx5_irq_alloc(struct mlx5_irq_pool *pool, int i, if (!irq) return ERR_PTR(-ENOMEM); if (!i || !pci_msix_can_alloc_dyn(dev->pdev)) { - /* The vector at index 0 was already allocated. - * Just get the irq number. If dynamic irq is not supported - * vectors have also been allocated. + /* The vector at index 0 is always statically allocated. If + * dynamic irq is not supported all vectors are statically + * allocated. In both cases just get the irq number and set + * the index. */ irq->map.virq = pci_irq_vector(dev->pdev, i); - irq->map.index = 0; + irq->map.index = i; } else { irq->map = pci_msix_alloc_irq_at(dev->pdev, MSI_ANY_INDEX, af_desc); if (!irq->map.virq) { @@ -570,11 +571,11 @@ int mlx5_irqs_request_vectors(struct mlx5_core_dev *dev, u16 *cpus, int nirqs, af_desc.is_managed = false; for (i = 0; i < nirqs; i++) { + cpumask_clear(&af_desc.mask); cpumask_set_cpu(cpus[i], &af_desc.mask); irq = mlx5_irq_request(dev, i + 1, &af_desc, rmap); if (IS_ERR(irq)) break; - cpumask_clear(&af_desc.mask); irqs[i] = irq; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c index e2f26d0bc615..0692363cf80e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c @@ -63,6 +63,7 @@ static void mlx5_sf_dev_remove(struct auxiliary_device *adev) struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev); struct devlink *devlink = priv_to_devlink(sf_dev->mdev); + mlx5_drain_health_wq(sf_dev->mdev); devlink_unregister(devlink); mlx5_uninit_one(sf_dev->mdev); iounmap(sf_dev->mdev->iseg); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c index 13e06a6a6b22..d6947fe13d56 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c @@ -213,6 +213,8 @@ struct mlx5dr_ptrn_mgr *mlx5dr_ptrn_mgr_create(struct mlx5dr_domain *dmn) } INIT_LIST_HEAD(&mgr->ptrn_list); + mutex_init(&mgr->modify_hdr_mutex); + return mgr; free_mgr: @@ -237,5 +239,6 @@ void mlx5dr_ptrn_mgr_destroy(struct mlx5dr_ptrn_mgr *mgr) } mlx5dr_icm_pool_destroy(mgr->ptrn_icm_pool); + mutex_destroy(&mgr->modify_hdr_mutex); kfree(mgr); } diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c index afa3b92a6905..0d5a41a2ae01 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c @@ -245,12 +245,6 @@ static bool mlxbf_gige_rx_packet(struct mlxbf_gige *priv, int *rx_pkts) skb = priv->rx_skb[rx_pi_rem]; - skb_put(skb, datalen); - - skb->ip_summed = CHECKSUM_NONE; /* device did not checksum packet */ - - skb->protocol = eth_type_trans(skb, netdev); - /* Alloc another RX SKB for this same index */ rx_skb = mlxbf_gige_alloc_skb(priv, MLXBF_GIGE_DEFAULT_BUF_SZ, &rx_buf_dma, DMA_FROM_DEVICE); @@ -259,6 +253,13 @@ static bool mlxbf_gige_rx_packet(struct mlxbf_gige *priv, int *rx_pkts) priv->rx_skb[rx_pi_rem] = rx_skb; dma_unmap_single(priv->dev, *rx_wqe_addr, MLXBF_GIGE_DEFAULT_BUF_SZ, DMA_FROM_DEVICE); + + skb_put(skb, datalen); + + skb->ip_summed = CHECKSUM_NONE; /* device did not checksum packet */ + + skb->protocol = eth_type_trans(skb, netdev); + *rx_wqe_addr = rx_buf_dma; } else if (rx_cqe & MLXBF_GIGE_RX_CQE_PKT_STATUS_MAC_ERR) { priv->stats.rx_mac_errors++; diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 06d6292e09b3..d907727c7b7a 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -1279,8 +1279,6 @@ static void mana_poll_tx_cq(struct mana_cq *cq) if (comp_read < 1) return; - apc->eth_stats.tx_cqes = comp_read; - for (i = 0; i < comp_read; i++) { struct mana_tx_comp_oob *cqe_oob; @@ -1363,8 +1361,6 @@ static void mana_poll_tx_cq(struct mana_cq *cq) WARN_ON_ONCE(1); cq->work_done = pkt_transmitted; - - apc->eth_stats.tx_cqes -= pkt_transmitted; } static void mana_post_pkt_rxq(struct mana_rxq *rxq) @@ -1626,15 +1622,11 @@ static void mana_poll_rx_cq(struct mana_cq *cq) { struct gdma_comp *comp = cq->gdma_comp_buf; struct mana_rxq *rxq = cq->rxq; - struct mana_port_context *apc; int comp_read, i; - apc = netdev_priv(rxq->ndev); - comp_read = mana_gd_poll_cq(cq->gdma_cq, comp, CQE_POLLING_BUFFER); WARN_ON_ONCE(comp_read > CQE_POLLING_BUFFER); - apc->eth_stats.rx_cqes = comp_read; rxq->xdp_flush = false; for (i = 0; i < comp_read; i++) { @@ -1646,8 +1638,6 @@ static void mana_poll_rx_cq(struct mana_cq *cq) return; mana_process_rx_cqe(rxq, cq, &comp[i]); - - apc->eth_stats.rx_cqes--; } if (rxq->xdp_flush) diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c index a64c81410dc1..0dc78679f620 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c +++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c @@ -13,11 +13,9 @@ static const struct { } mana_eth_stats[] = { {"stop_queue", offsetof(struct mana_ethtool_stats, stop_queue)}, {"wake_queue", offsetof(struct mana_ethtool_stats, wake_queue)}, - {"tx_cqes", offsetof(struct mana_ethtool_stats, tx_cqes)}, {"tx_cq_err", offsetof(struct mana_ethtool_stats, tx_cqe_err)}, {"tx_cqe_unknown_type", offsetof(struct mana_ethtool_stats, tx_cqe_unknown_type)}, - {"rx_cqes", offsetof(struct mana_ethtool_stats, rx_cqes)}, {"rx_coalesced_err", offsetof(struct mana_ethtool_stats, rx_coalesced_err)}, {"rx_cqe_unknown_type", offsetof(struct mana_ethtool_stats, diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c index 29afaddb598d..aace87139cea 100644 --- a/drivers/net/ethernet/renesas/rswitch.c +++ b/drivers/net/ethernet/renesas/rswitch.c @@ -1485,7 +1485,7 @@ static netdev_tx_t rswitch_start_xmit(struct sk_buff *skb, struct net_device *nd if (rswitch_get_num_cur_queues(gq) >= gq->ring_size - 1) { netif_stop_subqueue(ndev, 0); - return ret; + return NETDEV_TX_BUSY; } if (skb_put_padto(skb, ETH_ZLEN)) diff --git a/drivers/net/ethernet/sfc/tc.c b/drivers/net/ethernet/sfc/tc.c index 0327639a628a..c004443c1d58 100644 --- a/drivers/net/ethernet/sfc/tc.c +++ b/drivers/net/ethernet/sfc/tc.c @@ -624,13 +624,12 @@ static int efx_tc_flower_replace_foreign(struct efx_nic *efx, if (!found) { /* We don't care. */ netif_dbg(efx, drv, efx->net_dev, "Ignoring foreign filter that doesn't egdev us\n"); - rc = -EOPNOTSUPP; - goto release; + return -EOPNOTSUPP; } rc = efx_mae_match_check_caps(efx, &match.mask, NULL); if (rc) - goto release; + return rc; if (efx_tc_match_is_encap(&match.mask)) { enum efx_encap_type type; @@ -639,8 +638,7 @@ static int efx_tc_flower_replace_foreign(struct efx_nic *efx, if (type == EFX_ENCAP_TYPE_NONE) { NL_SET_ERR_MSG_MOD(extack, "Egress encap match on unsupported tunnel device"); - rc = -EOPNOTSUPP; - goto release; + return -EOPNOTSUPP; } rc = efx_mae_check_encap_type_supported(efx, type); @@ -648,25 +646,24 @@ static int efx_tc_flower_replace_foreign(struct efx_nic *efx, NL_SET_ERR_MSG_FMT_MOD(extack, "Firmware reports no support for %s encap match", efx_tc_encap_type_name(type)); - goto release; + return rc; } rc = efx_tc_flower_record_encap_match(efx, &match, type, extack); if (rc) - goto release; + return rc; } else { /* This is not a tunnel decap rule, ignore it */ netif_dbg(efx, drv, efx->net_dev, "Ignoring foreign filter without encap match\n"); - rc = -EOPNOTSUPP; - goto release; + return -EOPNOTSUPP; } rule = kzalloc(sizeof(*rule), GFP_USER); if (!rule) { rc = -ENOMEM; - goto release; + goto out_free; } INIT_LIST_HEAD(&rule->acts.list); rule->cookie = tc->cookie; @@ -678,7 +675,7 @@ static int efx_tc_flower_replace_foreign(struct efx_nic *efx, "Ignoring already-offloaded rule (cookie %lx)\n", tc->cookie); rc = -EEXIST; - goto release; + goto out_free; } act = kzalloc(sizeof(*act), GFP_USER); @@ -843,6 +840,7 @@ release: efx_tc_match_action_ht_params); efx_tc_free_action_set_list(efx, &rule->acts, false); } +out_free: kfree(rule); if (match.encap) efx_tc_flower_release_encap_match(efx, match.encap); @@ -899,8 +897,7 @@ static int efx_tc_flower_replace(struct efx_nic *efx, return rc; if (efx_tc_match_is_encap(&match.mask)) { NL_SET_ERR_MSG_MOD(extack, "Ingress enc_key matches not supported"); - rc = -EOPNOTSUPP; - goto release; + return -EOPNOTSUPP; } if (tc->common.chain_index) { @@ -924,9 +921,9 @@ static int efx_tc_flower_replace(struct efx_nic *efx, if (old) { netif_dbg(efx, drv, efx->net_dev, "Already offloaded rule (cookie %lx)\n", tc->cookie); - rc = -EEXIST; NL_SET_ERR_MSG_MOD(extack, "Rule already offloaded"); - goto release; + kfree(rule); + return -EEXIST; } /* Parse actions */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 0fca81507a77..52cab9de05f2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -7233,8 +7233,7 @@ int stmmac_dvr_probe(struct device *device, ndev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM; ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | - NETDEV_XDP_ACT_XSK_ZEROCOPY | - NETDEV_XDP_ACT_NDO_XMIT; + NETDEV_XDP_ACT_XSK_ZEROCOPY; ret = stmmac_tc_init(priv, priv); if (!ret) { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.c index 9d4d8c3dad0a..aa6f16d3df64 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.c @@ -117,6 +117,9 @@ int stmmac_xdp_set_prog(struct stmmac_priv *priv, struct bpf_prog *prog, return -EOPNOTSUPP; } + if (!prog) + xdp_features_clear_redirect_target(dev); + need_update = !!priv->xdp_prog != !!prog; if (if_running && need_update) stmmac_xdp_release(dev); @@ -131,5 +134,8 @@ int stmmac_xdp_set_prog(struct stmmac_priv *priv, struct bpf_prog *prog, if (if_running && need_update) stmmac_xdp_open(dev); + if (prog) + xdp_features_set_redirect_target(dev, false); + return 0; } diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c index 2ee80ed140b7..afa1d56d9095 100644 --- a/drivers/net/ipa/ipa_endpoint.c +++ b/drivers/net/ipa/ipa_endpoint.c @@ -119,7 +119,7 @@ enum ipa_status_field_id { }; /* Size in bytes of an IPA packet status structure */ -#define IPA_STATUS_SIZE sizeof(__le32[4]) +#define IPA_STATUS_SIZE sizeof(__le32[8]) /* IPA status structure decoder; looks up field values for a structure */ static u32 ipa_status_extract(struct ipa *ipa, const void *data, diff --git a/drivers/net/phy/mxl-gpy.c b/drivers/net/phy/mxl-gpy.c index 6301a9abfb95..ea1073adc5a1 100644 --- a/drivers/net/phy/mxl-gpy.c +++ b/drivers/net/phy/mxl-gpy.c @@ -274,13 +274,6 @@ static int gpy_config_init(struct phy_device *phydev) return ret < 0 ? ret : 0; } -static bool gpy_has_broken_mdint(struct phy_device *phydev) -{ - /* At least these PHYs are known to have broken interrupt handling */ - return phydev->drv->phy_id == PHY_ID_GPY215B || - phydev->drv->phy_id == PHY_ID_GPY215C; -} - static int gpy_probe(struct phy_device *phydev) { struct device *dev = &phydev->mdio.dev; @@ -300,8 +293,7 @@ static int gpy_probe(struct phy_device *phydev) phydev->priv = priv; mutex_init(&priv->mbox_lock); - if (gpy_has_broken_mdint(phydev) && - !device_property_present(dev, "maxlinear,use-broken-interrupts")) + if (!device_property_present(dev, "maxlinear,use-broken-interrupts")) phydev->dev_flags |= PHY_F_NO_IRQ; fw_version = phy_read(phydev, PHY_FWV); @@ -659,11 +651,9 @@ static irqreturn_t gpy_handle_interrupt(struct phy_device *phydev) * frame. Therefore, polling is the best we can do and won't do any more * harm. * It was observed that this bug happens on link state and link speed - * changes on a GPY215B and GYP215C independent of the firmware version - * (which doesn't mean that this list is exhaustive). + * changes independent of the firmware version. */ - if (gpy_has_broken_mdint(phydev) && - (reg & (PHY_IMASK_LSTC | PHY_IMASK_LSPC))) { + if (reg & (PHY_IMASK_LSTC | PHY_IMASK_LSPC)) { reg = gpy_mbox_read(phydev, REG_GPIO0_OUT); if (reg < 0) { phy_error(phydev); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 571e37e67f9c..f1865d047971 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1325,7 +1325,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x2001, 0x7e3d, 4)}, /* D-Link DWM-222 A2 */ {QMI_FIXED_INTF(0x2020, 0x2031, 4)}, /* Olicard 600 */ {QMI_FIXED_INTF(0x2020, 0x2033, 4)}, /* BroadMobi BM806U */ - {QMI_FIXED_INTF(0x2020, 0x2060, 4)}, /* BroadMobi BM818 */ + {QMI_QUIRK_SET_DTR(0x2020, 0x2060, 4)}, /* BroadMobi BM818 */ {QMI_FIXED_INTF(0x0f3d, 0x68a2, 8)}, /* Sierra Wireless MC7700 */ {QMI_FIXED_INTF(0x114f, 0x68a2, 8)}, /* Sierra Wireless MC7750 */ {QMI_FIXED_INTF(0x1199, 0x68a2, 8)}, /* Sierra Wireless MC7710 in QMI mode */ diff --git a/drivers/nfc/nfcsim.c b/drivers/nfc/nfcsim.c index 44eeb17ae48d..a55381f80cd6 100644 --- a/drivers/nfc/nfcsim.c +++ b/drivers/nfc/nfcsim.c @@ -336,10 +336,6 @@ static struct dentry *nfcsim_debugfs_root; static void nfcsim_debugfs_init(void) { nfcsim_debugfs_root = debugfs_create_dir("nfcsim", NULL); - - if (!nfcsim_debugfs_root) - pr_err("Could not create debugfs entry\n"); - } static void nfcsim_debugfs_remove(void) diff --git a/drivers/nvme/host/constants.c b/drivers/nvme/host/constants.c index bc523ca02254..5e4f8848dce0 100644 --- a/drivers/nvme/host/constants.c +++ b/drivers/nvme/host/constants.c @@ -21,7 +21,7 @@ static const char * const nvme_ops[] = { [nvme_cmd_resv_release] = "Reservation Release", [nvme_cmd_zone_mgmt_send] = "Zone Management Send", [nvme_cmd_zone_mgmt_recv] = "Zone Management Receive", - [nvme_cmd_zone_append] = "Zone Management Append", + [nvme_cmd_zone_append] = "Zone Append", }; static const char * const nvme_admin_ops[] = { diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 1f0cbb77b249..3ec38e2b9173 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -397,7 +397,16 @@ void nvme_complete_rq(struct request *req) trace_nvme_complete_rq(req); nvme_cleanup_cmd(req); - if (ctrl->kas) + /* + * Completions of long-running commands should not be able to + * defer sending of periodic keep alives, since the controller + * may have completed processing such commands a long time ago + * (arbitrarily close to command submission time). + * req->deadline - req->timeout is the command submission time + * in jiffies. + */ + if (ctrl->kas && + req->deadline - req->timeout >= ctrl->ka_last_check_time) ctrl->comp_seen = true; switch (nvme_decide_disposition(req)) { @@ -1115,7 +1124,7 @@ u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode) } EXPORT_SYMBOL_NS_GPL(nvme_passthru_start, NVME_TARGET_PASSTHRU); -void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects, +void nvme_passthru_end(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u32 effects, struct nvme_command *cmd, int status) { if (effects & NVME_CMD_EFFECTS_CSE_MASK) { @@ -1132,6 +1141,8 @@ void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects, nvme_queue_scan(ctrl); flush_work(&ctrl->scan_work); } + if (ns) + return; switch (cmd->common.opcode) { case nvme_admin_set_features: @@ -1161,9 +1172,25 @@ EXPORT_SYMBOL_NS_GPL(nvme_passthru_end, NVME_TARGET_PASSTHRU); * The host should send Keep Alive commands at half of the Keep Alive Timeout * accounting for transport roundtrip times [..]. */ +static unsigned long nvme_keep_alive_work_period(struct nvme_ctrl *ctrl) +{ + unsigned long delay = ctrl->kato * HZ / 2; + + /* + * When using Traffic Based Keep Alive, we need to run + * nvme_keep_alive_work at twice the normal frequency, as one + * command completion can postpone sending a keep alive command + * by up to twice the delay between runs. + */ + if (ctrl->ctratt & NVME_CTRL_ATTR_TBKAS) + delay /= 2; + return delay; +} + static void nvme_queue_keep_alive_work(struct nvme_ctrl *ctrl) { - queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ / 2); + queue_delayed_work(nvme_wq, &ctrl->ka_work, + nvme_keep_alive_work_period(ctrl)); } static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq, @@ -1172,6 +1199,20 @@ static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq, struct nvme_ctrl *ctrl = rq->end_io_data; unsigned long flags; bool startka = false; + unsigned long rtt = jiffies - (rq->deadline - rq->timeout); + unsigned long delay = nvme_keep_alive_work_period(ctrl); + + /* + * Subtract off the keepalive RTT so nvme_keep_alive_work runs + * at the desired frequency. + */ + if (rtt <= delay) { + delay -= rtt; + } else { + dev_warn(ctrl->device, "long keepalive RTT (%u ms)\n", + jiffies_to_msecs(rtt)); + delay = 0; + } blk_mq_free_request(rq); @@ -1182,6 +1223,7 @@ static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq, return RQ_END_IO_NONE; } + ctrl->ka_last_check_time = jiffies; ctrl->comp_seen = false; spin_lock_irqsave(&ctrl->lock, flags); if (ctrl->state == NVME_CTRL_LIVE || @@ -1189,7 +1231,7 @@ static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq, startka = true; spin_unlock_irqrestore(&ctrl->lock, flags); if (startka) - nvme_queue_keep_alive_work(ctrl); + queue_delayed_work(nvme_wq, &ctrl->ka_work, delay); return RQ_END_IO_NONE; } @@ -1200,6 +1242,8 @@ static void nvme_keep_alive_work(struct work_struct *work) bool comp_seen = ctrl->comp_seen; struct request *rq; + ctrl->ka_last_check_time = jiffies; + if ((ctrl->ctratt & NVME_CTRL_ATTR_TBKAS) && comp_seen) { dev_dbg(ctrl->device, "reschedule traffic based keep-alive timer\n"); diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index 81c5c9e38477..f15e7330b75a 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -254,7 +254,7 @@ static int nvme_submit_user_cmd(struct request_queue *q, blk_mq_free_request(req); if (effects) - nvme_passthru_end(ctrl, effects, cmd, ret); + nvme_passthru_end(ctrl, ns, effects, cmd, ret); return ret; } diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index a2d4f59e0535..8657811f8b88 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -328,6 +328,7 @@ struct nvme_ctrl { struct delayed_work ka_work; struct delayed_work failfast_work; struct nvme_command ka_cmd; + unsigned long ka_last_check_time; struct work_struct fw_act_work; unsigned long events; @@ -1077,7 +1078,7 @@ u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode); u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode); int nvme_execute_rq(struct request *rq, bool at_head); -void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects, +void nvme_passthru_end(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u32 effects, struct nvme_command *cmd, int status); struct nvme_ctrl *nvme_ctrl_from_file(struct file *file); struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid); diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c index 511c980d538d..71a9c1cc57f5 100644 --- a/drivers/nvme/target/passthru.c +++ b/drivers/nvme/target/passthru.c @@ -243,7 +243,7 @@ static void nvmet_passthru_execute_cmd_work(struct work_struct *w) blk_mq_free_request(rq); if (effects) - nvme_passthru_end(ctrl, effects, req->cmd, status); + nvme_passthru_end(ctrl, ns, effects, req->cmd, status); } static enum rq_end_io_ret nvmet_passthru_req_done(struct request *rq, diff --git a/drivers/phy/amlogic/phy-meson-g12a-mipi-dphy-analog.c b/drivers/phy/amlogic/phy-meson-g12a-mipi-dphy-analog.c index c14089fa7db4..cabdddbbabfd 100644 --- a/drivers/phy/amlogic/phy-meson-g12a-mipi-dphy-analog.c +++ b/drivers/phy/amlogic/phy-meson-g12a-mipi-dphy-analog.c @@ -70,7 +70,7 @@ static int phy_g12a_mipi_dphy_analog_power_on(struct phy *phy) HHI_MIPI_CNTL1_BANDGAP); regmap_write(priv->regmap, HHI_MIPI_CNTL2, - FIELD_PREP(HHI_MIPI_CNTL2_DIF_TX_CTL0, 0x459) | + FIELD_PREP(HHI_MIPI_CNTL2_DIF_TX_CTL0, 0x45a) | FIELD_PREP(HHI_MIPI_CNTL2_DIF_TX_CTL1, 0x2680)); reg = DSI_LANE_CLK; diff --git a/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c b/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c index caa953780bee..8aa7251de4a9 100644 --- a/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c +++ b/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c @@ -237,11 +237,11 @@ static int mtk_hdmi_pll_calc(struct mtk_hdmi_phy *hdmi_phy, struct clk_hw *hw, */ if (tmds_clk < 54 * MEGA) txposdiv = 8; - else if (tmds_clk >= 54 * MEGA && tmds_clk < 148.35 * MEGA) + else if (tmds_clk >= 54 * MEGA && (tmds_clk * 100) < 14835 * MEGA) txposdiv = 4; - else if (tmds_clk >= 148.35 * MEGA && tmds_clk < 296.7 * MEGA) + else if ((tmds_clk * 100) >= 14835 * MEGA && (tmds_clk * 10) < 2967 * MEGA) txposdiv = 2; - else if (tmds_clk >= 296.7 * MEGA && tmds_clk <= 594 * MEGA) + else if ((tmds_clk * 10) >= 2967 * MEGA && tmds_clk <= 594 * MEGA) txposdiv = 1; else return -EINVAL; @@ -324,12 +324,12 @@ static int mtk_hdmi_pll_drv_setting(struct clk_hw *hw) clk_channel_bias = 0x34; /* 20mA */ impedance_en = 0xf; impedance = 0x36; /* 100ohm */ - } else if (pixel_clk >= 74.175 * MEGA && pixel_clk <= 300 * MEGA) { + } else if (((u64)pixel_clk * 1000) >= 74175 * MEGA && pixel_clk <= 300 * MEGA) { data_channel_bias = 0x34; /* 20mA */ clk_channel_bias = 0x2c; /* 16mA */ impedance_en = 0xf; impedance = 0x36; /* 100ohm */ - } else if (pixel_clk >= 27 * MEGA && pixel_clk < 74.175 * MEGA) { + } else if (pixel_clk >= 27 * MEGA && ((u64)pixel_clk * 1000) < 74175 * MEGA) { data_channel_bias = 0x14; /* 10mA */ clk_channel_bias = 0x14; /* 10mA */ impedance_en = 0x0; diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c index 6850e04c329b..87b17e5877ab 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c @@ -2472,7 +2472,7 @@ static int qmp_combo_com_init(struct qmp_combo *qmp) ret = regulator_bulk_enable(cfg->num_vregs, qmp->vregs); if (ret) { dev_err(qmp->dev, "failed to enable regulators, err=%d\n", ret); - goto err_unlock; + goto err_decrement_count; } ret = reset_control_bulk_assert(cfg->num_resets, qmp->resets); @@ -2522,7 +2522,8 @@ err_assert_reset: reset_control_bulk_assert(cfg->num_resets, qmp->resets); err_disable_regulators: regulator_bulk_disable(cfg->num_vregs, qmp->vregs); -err_unlock: +err_decrement_count: + qmp->init_count--; mutex_unlock(&qmp->phy_mutex); return ret; diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcie-msm8996.c b/drivers/phy/qualcomm/phy-qcom-qmp-pcie-msm8996.c index 09824be088c9..0c603bc06e09 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-pcie-msm8996.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcie-msm8996.c @@ -379,7 +379,7 @@ static int qmp_pcie_msm8996_com_init(struct qmp_phy *qphy) ret = regulator_bulk_enable(cfg->num_vregs, qmp->vregs); if (ret) { dev_err(qmp->dev, "failed to enable regulators, err=%d\n", ret); - goto err_unlock; + goto err_decrement_count; } ret = reset_control_bulk_assert(cfg->num_resets, qmp->resets); @@ -409,7 +409,8 @@ err_assert_reset: reset_control_bulk_assert(cfg->num_resets, qmp->resets); err_disable_regulators: regulator_bulk_disable(cfg->num_vregs, qmp->vregs); -err_unlock: +err_decrement_count: + qmp->init_count--; mutex_unlock(&qmp->phy_mutex); return ret; diff --git a/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c b/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c index a59063596214..6c237f3cc66d 100644 --- a/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c +++ b/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c @@ -115,11 +115,11 @@ struct phy_override_seq { * * @cfg_ahb_clk: AHB2PHY interface clock * @ref_clk: phy reference clock - * @iface_clk: phy interface clock * @phy_reset: phy reset control * @vregs: regulator supplies bulk data * @phy_initialized: if PHY has been initialized correctly * @mode: contains the current mode the PHY is in + * @update_seq_cfg: tuning parameters for phy init */ struct qcom_snps_hsphy { struct phy *phy; diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index a92af08e7864..074273020849 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -256,7 +256,7 @@ void vhost_work_queue(struct vhost_dev *dev, struct vhost_work *work) * test_and_set_bit() implies a memory barrier. */ llist_add(&work->node, &dev->worker->work_list); - wake_up_process(dev->worker->vtsk->task); + vhost_task_wake(dev->worker->vtsk); } } EXPORT_SYMBOL_GPL(vhost_work_queue); @@ -333,31 +333,19 @@ static void vhost_vq_reset(struct vhost_dev *dev, __vhost_vq_meta_reset(vq); } -static int vhost_worker(void *data) +static bool vhost_worker(void *data) { struct vhost_worker *worker = data; struct vhost_work *work, *work_next; struct llist_node *node; - for (;;) { - /* mb paired w/ kthread_stop */ - set_current_state(TASK_INTERRUPTIBLE); - - if (vhost_task_should_stop(worker->vtsk)) { - __set_current_state(TASK_RUNNING); - break; - } - - node = llist_del_all(&worker->work_list); - if (!node) - schedule(); - + node = llist_del_all(&worker->work_list); + if (node) { node = llist_reverse_order(node); /* make sure flag is seen after deletion */ smp_wmb(); llist_for_each_entry_safe(work, work_next, node, node) { clear_bit(VHOST_WORK_QUEUED, &work->flags); - __set_current_state(TASK_RUNNING); kcov_remote_start_common(worker->kcov_handle); work->fn(work); kcov_remote_stop(); @@ -365,7 +353,7 @@ static int vhost_worker(void *data) } } - return 0; + return !!node; } static void vhost_vq_free_iovecs(struct vhost_virtqueue *vq) diff --git a/drivers/video/fbdev/arcfb.c b/drivers/video/fbdev/arcfb.c index 024d0ee4f04f..08d15e408413 100644 --- a/drivers/video/fbdev/arcfb.c +++ b/drivers/video/fbdev/arcfb.c @@ -590,7 +590,7 @@ err_fb_alloc: return retval; } -static int arcfb_remove(struct platform_device *dev) +static void arcfb_remove(struct platform_device *dev) { struct fb_info *info = platform_get_drvdata(dev); @@ -601,12 +601,11 @@ static int arcfb_remove(struct platform_device *dev) vfree((void __force *)info->screen_base); framebuffer_release(info); } - return 0; } static struct platform_driver arcfb_driver = { .probe = arcfb_probe, - .remove = arcfb_remove, + .remove_new = arcfb_remove, .driver = { .name = "arcfb", }, diff --git a/drivers/video/fbdev/au1100fb.c b/drivers/video/fbdev/au1100fb.c index 519313b8bb00..648d6cac86e8 100644 --- a/drivers/video/fbdev/au1100fb.c +++ b/drivers/video/fbdev/au1100fb.c @@ -520,13 +520,10 @@ failed: return -ENODEV; } -int au1100fb_drv_remove(struct platform_device *dev) +void au1100fb_drv_remove(struct platform_device *dev) { struct au1100fb_device *fbdev = NULL; - if (!dev) - return -ENODEV; - fbdev = platform_get_drvdata(dev); #if !defined(CONFIG_FRAMEBUFFER_CONSOLE) && defined(CONFIG_LOGO) @@ -543,8 +540,6 @@ int au1100fb_drv_remove(struct platform_device *dev) clk_disable_unprepare(fbdev->lcdclk); clk_put(fbdev->lcdclk); } - - return 0; } #ifdef CONFIG_PM @@ -593,9 +588,9 @@ static struct platform_driver au1100fb_driver = { .name = "au1100-lcd", }, .probe = au1100fb_drv_probe, - .remove = au1100fb_drv_remove, + .remove_new = au1100fb_drv_remove, .suspend = au1100fb_drv_suspend, - .resume = au1100fb_drv_resume, + .resume = au1100fb_drv_resume, }; module_platform_driver(au1100fb_driver); diff --git a/drivers/video/fbdev/au1200fb.c b/drivers/video/fbdev/au1200fb.c index b6b22fa4a8a0..aed88ce45bf0 100644 --- a/drivers/video/fbdev/au1200fb.c +++ b/drivers/video/fbdev/au1200fb.c @@ -1765,7 +1765,7 @@ failed: return ret; } -static int au1200fb_drv_remove(struct platform_device *dev) +static void au1200fb_drv_remove(struct platform_device *dev) { struct au1200fb_platdata *pd = platform_get_drvdata(dev); struct fb_info *fbi; @@ -1788,8 +1788,6 @@ static int au1200fb_drv_remove(struct platform_device *dev) } free_irq(platform_get_irq(dev, 0), (void *)dev); - - return 0; } #ifdef CONFIG_PM @@ -1840,7 +1838,7 @@ static struct platform_driver au1200fb_driver = { .pm = AU1200FB_PMOPS, }, .probe = au1200fb_drv_probe, - .remove = au1200fb_drv_remove, + .remove_new = au1200fb_drv_remove, }; module_platform_driver(au1200fb_driver); diff --git a/drivers/video/fbdev/broadsheetfb.c b/drivers/video/fbdev/broadsheetfb.c index 55e62dd96f9b..b518cacbf7cd 100644 --- a/drivers/video/fbdev/broadsheetfb.c +++ b/drivers/video/fbdev/broadsheetfb.c @@ -1193,7 +1193,7 @@ err: } -static int broadsheetfb_remove(struct platform_device *dev) +static void broadsheetfb_remove(struct platform_device *dev) { struct fb_info *info = platform_get_drvdata(dev); @@ -1209,12 +1209,11 @@ static int broadsheetfb_remove(struct platform_device *dev) module_put(par->board->owner); framebuffer_release(info); } - return 0; } static struct platform_driver broadsheetfb_driver = { .probe = broadsheetfb_probe, - .remove = broadsheetfb_remove, + .remove_new = broadsheetfb_remove, .driver = { .name = "broadsheetfb", }, diff --git a/drivers/video/fbdev/bw2.c b/drivers/video/fbdev/bw2.c index 9cbadcd18b25..025d663dc6fd 100644 --- a/drivers/video/fbdev/bw2.c +++ b/drivers/video/fbdev/bw2.c @@ -352,7 +352,7 @@ out_err: return err; } -static int bw2_remove(struct platform_device *op) +static void bw2_remove(struct platform_device *op) { struct fb_info *info = dev_get_drvdata(&op->dev); struct bw2_par *par = info->par; @@ -363,8 +363,6 @@ static int bw2_remove(struct platform_device *op) of_iounmap(&op->resource[0], info->screen_base, info->fix.smem_len); framebuffer_release(info); - - return 0; } static const struct of_device_id bw2_match[] = { @@ -381,7 +379,7 @@ static struct platform_driver bw2_driver = { .of_match_table = bw2_match, }, .probe = bw2_probe, - .remove = bw2_remove, + .remove_new = bw2_remove, }; static int __init bw2_init(void) diff --git a/drivers/video/fbdev/core/bitblit.c b/drivers/video/fbdev/core/bitblit.c index f98e8f298bc1..8587c9da0670 100644 --- a/drivers/video/fbdev/core/bitblit.c +++ b/drivers/video/fbdev/core/bitblit.c @@ -247,6 +247,9 @@ static void bit_cursor(struct vc_data *vc, struct fb_info *info, int mode, cursor.set = 0; + if (!vc->vc_font.data) + return; + c = scr_readw((u16 *) vc->vc_pos); attribute = get_attribute(info, c); src = vc->vc_font.data + ((c & charmask) * (w * vc->vc_font.height)); diff --git a/drivers/video/fbdev/imsttfb.c b/drivers/video/fbdev/imsttfb.c index 975dd682fae4..ee7d01ad1406 100644 --- a/drivers/video/fbdev/imsttfb.c +++ b/drivers/video/fbdev/imsttfb.c @@ -1452,9 +1452,13 @@ static int init_imstt(struct fb_info *info) FBINFO_HWACCEL_FILLRECT | FBINFO_HWACCEL_YPAN; - fb_alloc_cmap(&info->cmap, 0, 0); + if (fb_alloc_cmap(&info->cmap, 0, 0)) { + framebuffer_release(info); + return -ENODEV; + } if (register_framebuffer(info) < 0) { + fb_dealloc_cmap(&info->cmap); framebuffer_release(info); return -ENODEV; } @@ -1531,8 +1535,10 @@ static int imsttfb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto error; info->pseudo_palette = par->palette; ret = init_imstt(info); - if (!ret) - pci_set_drvdata(pdev, info); + if (ret) + goto error; + + pci_set_drvdata(pdev, info); return ret; error: diff --git a/drivers/video/fbdev/matrox/matroxfb_maven.c b/drivers/video/fbdev/matrox/matroxfb_maven.c index 727a10a59811..b15a8ad92ba7 100644 --- a/drivers/video/fbdev/matrox/matroxfb_maven.c +++ b/drivers/video/fbdev/matrox/matroxfb_maven.c @@ -1291,7 +1291,7 @@ static struct i2c_driver maven_driver={ .driver = { .name = "maven", }, - .probe_new = maven_probe, + .probe = maven_probe, .remove = maven_remove, .id_table = maven_id, }; diff --git a/drivers/video/fbdev/ssd1307fb.c b/drivers/video/fbdev/ssd1307fb.c index 046b9990d27c..132d1a205011 100644 --- a/drivers/video/fbdev/ssd1307fb.c +++ b/drivers/video/fbdev/ssd1307fb.c @@ -844,7 +844,7 @@ static const struct i2c_device_id ssd1307fb_i2c_id[] = { MODULE_DEVICE_TABLE(i2c, ssd1307fb_i2c_id); static struct i2c_driver ssd1307fb_driver = { - .probe_new = ssd1307fb_probe, + .probe = ssd1307fb_probe, .remove = ssd1307fb_remove, .id_table = ssd1307fb_i2c_id, .driver = { diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c index 5379c4714905..b3ad0f51e616 100644 --- a/fs/btrfs/bio.c +++ b/fs/btrfs/bio.c @@ -330,7 +330,7 @@ static void btrfs_end_bio_work(struct work_struct *work) if (bbio->inode && !(bbio->bio.bi_opf & REQ_META)) btrfs_check_read_bio(bbio, bbio->bio.bi_private); else - bbio->end_io(bbio); + btrfs_orig_bbio_end_io(bbio); } static void btrfs_simple_end_io(struct bio *bio) @@ -811,10 +811,6 @@ void btrfs_submit_repair_write(struct btrfs_bio *bbio, int mirror_num, bool dev_ goto fail; if (dev_replace) { - if (btrfs_op(&bbio->bio) == BTRFS_MAP_WRITE && btrfs_is_zoned(fs_info)) { - bbio->bio.bi_opf &= ~REQ_OP_WRITE; - bbio->bio.bi_opf |= REQ_OP_ZONE_APPEND; - } ASSERT(smap.dev == fs_info->dev_replace.srcdev); smap.dev = fs_info->dev_replace.tgtdev; } diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 6de6dcf2743e..2b1b227505f3 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -96,7 +96,7 @@ static void csum_tree_block(struct extent_buffer *buf, u8 *result) crypto_shash_update(shash, kaddr + BTRFS_CSUM_SIZE, first_page_part - BTRFS_CSUM_SIZE); - for (i = 1; i < num_pages; i++) { + for (i = 1; i < num_pages && INLINE_EXTENT_BUFFER_PAGES > 1; i++) { kaddr = page_address(buf->pages[i]); crypto_shash_update(shash, kaddr, PAGE_SIZE); } diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index dd37cba58022..7c666517d3d3 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -1137,6 +1137,35 @@ static void scrub_write_endio(struct btrfs_bio *bbio) wake_up(&stripe->io_wait); } +static void scrub_submit_write_bio(struct scrub_ctx *sctx, + struct scrub_stripe *stripe, + struct btrfs_bio *bbio, bool dev_replace) +{ + struct btrfs_fs_info *fs_info = sctx->fs_info; + u32 bio_len = bbio->bio.bi_iter.bi_size; + u32 bio_off = (bbio->bio.bi_iter.bi_sector << SECTOR_SHIFT) - + stripe->logical; + + fill_writer_pointer_gap(sctx, stripe->physical + bio_off); + atomic_inc(&stripe->pending_io); + btrfs_submit_repair_write(bbio, stripe->mirror_num, dev_replace); + if (!btrfs_is_zoned(fs_info)) + return; + /* + * For zoned writeback, queue depth must be 1, thus we must wait for + * the write to finish before the next write. + */ + wait_scrub_stripe_io(stripe); + + /* + * And also need to update the write pointer if write finished + * successfully. + */ + if (!test_bit(bio_off >> fs_info->sectorsize_bits, + &stripe->write_error_bitmap)) + sctx->write_pointer += bio_len; +} + /* * Submit the write bio(s) for the sectors specified by @write_bitmap. * @@ -1155,7 +1184,6 @@ static void scrub_write_sectors(struct scrub_ctx *sctx, struct scrub_stripe *str { struct btrfs_fs_info *fs_info = stripe->bg->fs_info; struct btrfs_bio *bbio = NULL; - const bool zoned = btrfs_is_zoned(fs_info); int sector_nr; for_each_set_bit(sector_nr, &write_bitmap, stripe->nr_sectors) { @@ -1168,13 +1196,7 @@ static void scrub_write_sectors(struct scrub_ctx *sctx, struct scrub_stripe *str /* Cannot merge with previous sector, submit the current one. */ if (bbio && sector_nr && !test_bit(sector_nr - 1, &write_bitmap)) { - fill_writer_pointer_gap(sctx, stripe->physical + - (sector_nr << fs_info->sectorsize_bits)); - atomic_inc(&stripe->pending_io); - btrfs_submit_repair_write(bbio, stripe->mirror_num, dev_replace); - /* For zoned writeback, queue depth must be 1. */ - if (zoned) - wait_scrub_stripe_io(stripe); + scrub_submit_write_bio(sctx, stripe, bbio, dev_replace); bbio = NULL; } if (!bbio) { @@ -1187,14 +1209,8 @@ static void scrub_write_sectors(struct scrub_ctx *sctx, struct scrub_stripe *str ret = bio_add_page(&bbio->bio, page, fs_info->sectorsize, pgoff); ASSERT(ret == fs_info->sectorsize); } - if (bbio) { - fill_writer_pointer_gap(sctx, bbio->bio.bi_iter.bi_sector << - SECTOR_SHIFT); - atomic_inc(&stripe->pending_io); - btrfs_submit_repair_write(bbio, stripe->mirror_num, dev_replace); - if (zoned) - wait_scrub_stripe_io(stripe); - } + if (bbio) + scrub_submit_write_bio(sctx, stripe, bbio, dev_replace); } /* diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 9b212e8c70cc..d2755d5e338b 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -6158,7 +6158,7 @@ static int log_delayed_deletions_incremental(struct btrfs_trans_handle *trans, { struct btrfs_root *log = inode->root->log_root; const struct btrfs_delayed_item *curr; - u64 last_range_start; + u64 last_range_start = 0; u64 last_range_end = 0; struct btrfs_key key; diff --git a/fs/coredump.c b/fs/coredump.c index ece7badf701b..88740c51b942 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -371,7 +371,9 @@ static int zap_process(struct task_struct *start, int exit_code) if (t != current && !(t->flags & PF_POSTCOREDUMP)) { sigaddset(&t->pending.signal, SIGKILL); signal_wake_up(t, 1); - nr++; + /* The vhost_worker does not particpate in coredumps */ + if ((t->flags & (PF_USER_WORKER | PF_IO_WORKER)) != PF_USER_WORKER) + nr++; } } diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 6948d673bba2..8104a21b001a 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -918,11 +918,13 @@ do { \ * where the second inode has larger inode number * than the first * I_DATA_SEM_QUOTA - Used for quota inodes only + * I_DATA_SEM_EA - Used for ea_inodes only */ enum { I_DATA_SEM_NORMAL = 0, I_DATA_SEM_OTHER, I_DATA_SEM_QUOTA, + I_DATA_SEM_EA }; @@ -2901,7 +2903,8 @@ typedef enum { EXT4_IGET_NORMAL = 0, EXT4_IGET_SPECIAL = 0x0001, /* OK to iget a system inode */ EXT4_IGET_HANDLE = 0x0002, /* Inode # is from a handle */ - EXT4_IGET_BAD = 0x0004 /* Allow to iget a bad inode */ + EXT4_IGET_BAD = 0x0004, /* Allow to iget a bad inode */ + EXT4_IGET_EA_INODE = 0x0008 /* Inode should contain an EA value */ } ext4_iget_flags; extern struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index f65fdb27ce14..2a143209aa0c 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -108,6 +108,13 @@ static int ext4_fsync_journal(struct inode *inode, bool datasync, journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; tid_t commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid; + /* + * Fastcommit does not really support fsync on directories or other + * special files. Force a full commit. + */ + if (!S_ISREG(inode->i_mode)) + return ext4_force_commit(inode->i_sb); + if (journal->j_flags & JBD2_BARRIER && !jbd2_trans_will_send_data_barrier(journal, commit_tid)) *needs_barrier = true; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index ce5f21b6c2b3..02de439bf1f0 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4641,6 +4641,24 @@ static inline void ext4_inode_set_iversion_queried(struct inode *inode, u64 val) inode_set_iversion_queried(inode, val); } +static const char *check_igot_inode(struct inode *inode, ext4_iget_flags flags) + +{ + if (flags & EXT4_IGET_EA_INODE) { + if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) + return "missing EA_INODE flag"; + if (ext4_test_inode_state(inode, EXT4_STATE_XATTR) || + EXT4_I(inode)->i_file_acl) + return "ea_inode with extended attributes"; + } else { + if ((EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) + return "unexpected EA_INODE flag"; + } + if (is_bad_inode(inode) && !(flags & EXT4_IGET_BAD)) + return "unexpected bad inode w/o EXT4_IGET_BAD"; + return NULL; +} + struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, ext4_iget_flags flags, const char *function, unsigned int line) @@ -4650,6 +4668,7 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, struct ext4_inode_info *ei; struct ext4_super_block *es = EXT4_SB(sb)->s_es; struct inode *inode; + const char *err_str; journal_t *journal = EXT4_SB(sb)->s_journal; long ret; loff_t size; @@ -4677,8 +4696,14 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, inode = iget_locked(sb, ino); if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + if (!(inode->i_state & I_NEW)) { + if ((err_str = check_igot_inode(inode, flags)) != NULL) { + ext4_error_inode(inode, function, line, 0, err_str); + iput(inode); + return ERR_PTR(-EFSCORRUPTED); + } return inode; + } ei = EXT4_I(inode); iloc.bh = NULL; @@ -4944,10 +4969,9 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, if (IS_CASEFOLDED(inode) && !ext4_has_feature_casefold(inode->i_sb)) ext4_error_inode(inode, function, line, 0, "casefold flag without casefold feature"); - if (is_bad_inode(inode) && !(flags & EXT4_IGET_BAD)) { - ext4_error_inode(inode, function, line, 0, - "bad inode without EXT4_IGET_BAD flag"); - ret = -EUCLEAN; + if ((err_str = check_igot_inode(inode, flags)) != NULL) { + ext4_error_inode(inode, function, line, 0, err_str); + ret = -EFSCORRUPTED; goto bad_inode; } diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 7b2e36d103cb..20f67a260df5 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2062,7 +2062,7 @@ static void ext4_mb_check_limits(struct ext4_allocation_context *ac, if (bex->fe_len < gex->fe_len) return; - if (finish_group) + if (finish_group || ac->ac_found > sbi->s_mb_min_to_scan) ext4_mb_use_best_found(ac, e4b); } @@ -2074,6 +2074,20 @@ static void ext4_mb_check_limits(struct ext4_allocation_context *ac, * in the context. Later, the best found extent will be used, if * mballoc can't find good enough extent. * + * The algorithm used is roughly as follows: + * + * * If free extent found is exactly as big as goal, then + * stop the scan and use it immediately + * + * * If free extent found is smaller than goal, then keep retrying + * upto a max of sbi->s_mb_max_to_scan times (default 200). After + * that stop scanning and use whatever we have. + * + * * If free extent found is bigger than goal, then keep retrying + * upto a max of sbi->s_mb_min_to_scan times (default 10) before + * stopping the scan and using the extent. + * + * * FIXME: real allocation policy is to be designed yet! */ static void ext4_mb_measure_extent(struct ext4_allocation_context *ac, diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 9680fe753e59..56a5d1c469fc 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -6589,18 +6589,6 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) } /* - * Reinitialize lazy itable initialization thread based on - * current settings - */ - if (sb_rdonly(sb) || !test_opt(sb, INIT_INODE_TABLE)) - ext4_unregister_li_request(sb); - else { - ext4_group_t first_not_zeroed; - first_not_zeroed = ext4_has_uninit_itable(sb); - ext4_register_li_request(sb, first_not_zeroed); - } - - /* * Handle creation of system zone data early because it can fail. * Releasing of existing data is done when we are sure remount will * succeed. @@ -6637,6 +6625,18 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) if (enable_rw) sb->s_flags &= ~SB_RDONLY; + /* + * Reinitialize lazy itable initialization thread based on + * current settings + */ + if (sb_rdonly(sb) || !test_opt(sb, INIT_INODE_TABLE)) + ext4_unregister_li_request(sb); + else { + ext4_group_t first_not_zeroed; + first_not_zeroed = ext4_has_uninit_itable(sb); + ext4_register_li_request(sb, first_not_zeroed); + } + if (!ext4_has_feature_mmp(sb) || sb_rdonly(sb)) ext4_stop_mmpd(sbi); diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index dfc2e223bd10..13d7f17a9c8c 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -121,7 +121,11 @@ ext4_expand_inode_array(struct ext4_xattr_inode_array **ea_inode_array, #ifdef CONFIG_LOCKDEP void ext4_xattr_inode_set_class(struct inode *ea_inode) { + struct ext4_inode_info *ei = EXT4_I(ea_inode); + lockdep_set_subclass(&ea_inode->i_rwsem, 1); + (void) ei; /* shut up clang warning if !CONFIG_LOCKDEP */ + lockdep_set_subclass(&ei->i_data_sem, I_DATA_SEM_EA); } #endif @@ -433,7 +437,7 @@ static int ext4_xattr_inode_iget(struct inode *parent, unsigned long ea_ino, return -EFSCORRUPTED; } - inode = ext4_iget(parent->i_sb, ea_ino, EXT4_IGET_NORMAL); + inode = ext4_iget(parent->i_sb, ea_ino, EXT4_IGET_EA_INODE); if (IS_ERR(inode)) { err = PTR_ERR(inode); ext4_error(parent->i_sb, @@ -441,23 +445,6 @@ static int ext4_xattr_inode_iget(struct inode *parent, unsigned long ea_ino, err); return err; } - - if (is_bad_inode(inode)) { - ext4_error(parent->i_sb, - "error while reading EA inode %lu is_bad_inode", - ea_ino); - err = -EIO; - goto error; - } - - if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) { - ext4_error(parent->i_sb, - "EA inode %lu does not have EXT4_EA_INODE_FL flag", - ea_ino); - err = -EINVAL; - goto error; - } - ext4_xattr_inode_set_class(inode); /* @@ -478,9 +465,6 @@ static int ext4_xattr_inode_iget(struct inode *parent, unsigned long ea_ino, *ea_inode = inode; return 0; -error: - iput(inode); - return err; } /* Remove entry from mbcache when EA inode is getting evicted */ @@ -1556,11 +1540,11 @@ ext4_xattr_inode_cache_find(struct inode *inode, const void *value, while (ce) { ea_inode = ext4_iget(inode->i_sb, ce->e_value, - EXT4_IGET_NORMAL); - if (!IS_ERR(ea_inode) && - !is_bad_inode(ea_inode) && - (EXT4_I(ea_inode)->i_flags & EXT4_EA_INODE_FL) && - i_size_read(ea_inode) == value_len && + EXT4_IGET_EA_INODE); + if (IS_ERR(ea_inode)) + goto next_entry; + ext4_xattr_inode_set_class(ea_inode); + if (i_size_read(ea_inode) == value_len && !ext4_xattr_inode_read(ea_inode, ea_data, value_len) && !ext4_xattr_inode_verify_hashes(ea_inode, NULL, ea_data, value_len) && @@ -1570,9 +1554,8 @@ ext4_xattr_inode_cache_find(struct inode *inode, const void *value, kvfree(ea_data); return ea_inode; } - - if (!IS_ERR(ea_inode)) - iput(ea_inode); + iput(ea_inode); + next_entry: ce = mb_cache_entry_find_next(ea_inode_cache, ce); } kvfree(ea_data); diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index c159817d1282..b4fd7a7062d5 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -690,16 +690,11 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred if (err != 0 || fd < 0) return -EINVAL; - if (svc_alien_sock(net, fd)) { - printk(KERN_ERR "%s: socket net is different to NFSd's one\n", __func__); - return -EINVAL; - } - err = nfsd_create_serv(net); if (err != 0) return err; - err = svc_addsock(nn->nfsd_serv, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred); + err = svc_addsock(nn->nfsd_serv, net, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred); if (err >= 0 && !nn->nfsd_serv->sv_nrthreads && !xchg(&nn->keep_active, 1)) diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index bb9d47172162..db67f8e19344 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -536,7 +536,15 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, inode_lock(inode); for (retries = 1;;) { - host_err = __nfsd_setattr(dentry, iap); + struct iattr attrs; + + /* + * notify_change() can alter its iattr argument, making + * @iap unsuitable for submission multiple times. Make a + * copy for every loop iteration. + */ + attrs = *iap; + host_err = __nfsd_setattr(dentry, &attrs); if (host_err != -EAGAIN || !retries--) break; if (!nfsd_wait_for_delegreturn(rqstp, inode)) diff --git a/fs/smb/client/ioctl.c b/fs/smb/client/ioctl.c index cb3be58cd55e..fff092bbc7a3 100644 --- a/fs/smb/client/ioctl.c +++ b/fs/smb/client/ioctl.c @@ -321,7 +321,11 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) struct tcon_link *tlink; struct cifs_sb_info *cifs_sb; __u64 ExtAttrBits = 0; +#ifdef CONFIG_CIFS_POSIX +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY __u64 caps; +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ +#endif /* CONFIG_CIFS_POSIX */ xid = get_xid(); @@ -331,9 +335,9 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) if (pSMBFile == NULL) break; tcon = tlink_tcon(pSMBFile->tlink); - caps = le64_to_cpu(tcon->fsUnixInfo.Capability); #ifdef CONFIG_CIFS_POSIX #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY + caps = le64_to_cpu(tcon->fsUnixInfo.Capability); if (CIFS_UNIX_EXTATTR_CAP & caps) { __u64 ExtAttrMask = 0; rc = CIFSGetExtAttr(xid, tcon, diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 5065398665f1..6e3be58cfe49 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -618,7 +618,6 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, * Add a new one instead */ spin_lock(&ses->iface_lock); - iface = niface = NULL; list_for_each_entry_safe(iface, niface, &ses->iface_list, iface_head) { ret = iface_cmp(iface, &tmp_iface); diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 9ed61b6f9b21..7063b395d22f 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -3725,7 +3725,7 @@ SMB2_change_notify(const unsigned int xid, struct cifs_tcon *tcon, if (*out_data == NULL) { rc = -ENOMEM; goto cnotify_exit; - } else + } else if (plen) *plen = le32_to_cpu(smb_rsp->OutputBufferLength); } diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 6d1ccb999893..db181bdad73a 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -157,13 +157,42 @@ static struct oplock_info *opinfo_get_list(struct ksmbd_inode *ci) rcu_read_lock(); opinfo = list_first_or_null_rcu(&ci->m_op_list, struct oplock_info, op_entry); - if (opinfo && !atomic_inc_not_zero(&opinfo->refcount)) - opinfo = NULL; + if (opinfo) { + if (!atomic_inc_not_zero(&opinfo->refcount)) + opinfo = NULL; + else { + atomic_inc(&opinfo->conn->r_count); + if (ksmbd_conn_releasing(opinfo->conn)) { + atomic_dec(&opinfo->conn->r_count); + atomic_dec(&opinfo->refcount); + opinfo = NULL; + } + } + } + rcu_read_unlock(); return opinfo; } +static void opinfo_conn_put(struct oplock_info *opinfo) +{ + struct ksmbd_conn *conn; + + if (!opinfo) + return; + + conn = opinfo->conn; + /* + * Checking waitqueue to dropping pending requests on + * disconnection. waitqueue_active is safe because it + * uses atomic operation for condition. + */ + if (!atomic_dec_return(&conn->r_count) && waitqueue_active(&conn->r_count_q)) + wake_up(&conn->r_count_q); + opinfo_put(opinfo); +} + void opinfo_put(struct oplock_info *opinfo) { if (!atomic_dec_and_test(&opinfo->refcount)) @@ -666,13 +695,6 @@ static void __smb2_oplock_break_noti(struct work_struct *wk) out: ksmbd_free_work_struct(work); - /* - * Checking waitqueue to dropping pending requests on - * disconnection. waitqueue_active is safe because it - * uses atomic operation for condition. - */ - if (!atomic_dec_return(&conn->r_count) && waitqueue_active(&conn->r_count_q)) - wake_up(&conn->r_count_q); } /** @@ -706,7 +728,6 @@ static int smb2_oplock_break_noti(struct oplock_info *opinfo) work->conn = conn; work->sess = opinfo->sess; - atomic_inc(&conn->r_count); if (opinfo->op_state == OPLOCK_ACK_WAIT) { INIT_WORK(&work->work, __smb2_oplock_break_noti); ksmbd_queue_work(work); @@ -776,13 +797,6 @@ static void __smb2_lease_break_noti(struct work_struct *wk) out: ksmbd_free_work_struct(work); - /* - * Checking waitqueue to dropping pending requests on - * disconnection. waitqueue_active is safe because it - * uses atomic operation for condition. - */ - if (!atomic_dec_return(&conn->r_count) && waitqueue_active(&conn->r_count_q)) - wake_up(&conn->r_count_q); } /** @@ -822,7 +836,6 @@ static int smb2_lease_break_noti(struct oplock_info *opinfo) work->conn = conn; work->sess = opinfo->sess; - atomic_inc(&conn->r_count); if (opinfo->op_state == OPLOCK_ACK_WAIT) { list_for_each_safe(tmp, t, &opinfo->interim_list) { struct ksmbd_work *in_work; @@ -1144,8 +1157,10 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, } prev_opinfo = opinfo_get_list(ci); if (!prev_opinfo || - (prev_opinfo->level == SMB2_OPLOCK_LEVEL_NONE && lctx)) + (prev_opinfo->level == SMB2_OPLOCK_LEVEL_NONE && lctx)) { + opinfo_conn_put(prev_opinfo); goto set_lev; + } prev_op_has_lease = prev_opinfo->is_lease; if (prev_op_has_lease) prev_op_state = prev_opinfo->o_lease->state; @@ -1153,19 +1168,19 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, if (share_ret < 0 && prev_opinfo->level == SMB2_OPLOCK_LEVEL_EXCLUSIVE) { err = share_ret; - opinfo_put(prev_opinfo); + opinfo_conn_put(prev_opinfo); goto err_out; } if (prev_opinfo->level != SMB2_OPLOCK_LEVEL_BATCH && prev_opinfo->level != SMB2_OPLOCK_LEVEL_EXCLUSIVE) { - opinfo_put(prev_opinfo); + opinfo_conn_put(prev_opinfo); goto op_break_not_needed; } list_add(&work->interim_entry, &prev_opinfo->interim_list); err = oplock_break(prev_opinfo, SMB2_OPLOCK_LEVEL_II); - opinfo_put(prev_opinfo); + opinfo_conn_put(prev_opinfo); if (err == -ENOENT) goto set_lev; /* Check all oplock was freed by close */ @@ -1228,14 +1243,14 @@ static void smb_break_all_write_oplock(struct ksmbd_work *work, return; if (brk_opinfo->level != SMB2_OPLOCK_LEVEL_BATCH && brk_opinfo->level != SMB2_OPLOCK_LEVEL_EXCLUSIVE) { - opinfo_put(brk_opinfo); + opinfo_conn_put(brk_opinfo); return; } brk_opinfo->open_trunc = is_trunc; list_add(&work->interim_entry, &brk_opinfo->interim_list); oplock_break(brk_opinfo, SMB2_OPLOCK_LEVEL_II); - opinfo_put(brk_opinfo); + opinfo_conn_put(brk_opinfo); } /** @@ -1263,6 +1278,13 @@ void smb_break_all_levII_oplock(struct ksmbd_work *work, struct ksmbd_file *fp, list_for_each_entry_rcu(brk_op, &ci->m_op_list, op_entry) { if (!atomic_inc_not_zero(&brk_op->refcount)) continue; + + atomic_inc(&brk_op->conn->r_count); + if (ksmbd_conn_releasing(brk_op->conn)) { + atomic_dec(&brk_op->conn->r_count); + continue; + } + rcu_read_unlock(); if (brk_op->is_lease && (brk_op->o_lease->state & (~(SMB2_LEASE_READ_CACHING_LE | @@ -1292,7 +1314,7 @@ void smb_break_all_levII_oplock(struct ksmbd_work *work, struct ksmbd_file *fp, brk_op->open_trunc = is_trunc; oplock_break(brk_op, SMB2_OPLOCK_LEVEL_NONE); next: - opinfo_put(brk_op); + opinfo_conn_put(brk_op); rcu_read_lock(); } rcu_read_unlock(); diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 717bcd20545b..7a81541de602 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -326,13 +326,9 @@ int smb2_set_rsp_credits(struct ksmbd_work *work) if (hdr->Command == SMB2_NEGOTIATE) aux_max = 1; else - aux_max = conn->vals->max_credits - credit_charge; + aux_max = conn->vals->max_credits - conn->total_credits; credits_granted = min_t(unsigned short, credits_requested, aux_max); - if (conn->vals->max_credits - conn->total_credits < credits_granted) - credits_granted = conn->vals->max_credits - - conn->total_credits; - conn->total_credits += credits_granted; work->credits_granted += credits_granted; @@ -849,13 +845,14 @@ static void assemble_neg_contexts(struct ksmbd_conn *conn, static __le32 decode_preauth_ctxt(struct ksmbd_conn *conn, struct smb2_preauth_neg_context *pneg_ctxt, - int len_of_ctxts) + int ctxt_len) { /* * sizeof(smb2_preauth_neg_context) assumes SMB311_SALT_SIZE Salt, * which may not be present. Only check for used HashAlgorithms[1]. */ - if (len_of_ctxts < MIN_PREAUTH_CTXT_DATA_LEN) + if (ctxt_len < + sizeof(struct smb2_neg_context) + MIN_PREAUTH_CTXT_DATA_LEN) return STATUS_INVALID_PARAMETER; if (pneg_ctxt->HashAlgorithms != SMB2_PREAUTH_INTEGRITY_SHA512) @@ -867,15 +864,23 @@ static __le32 decode_preauth_ctxt(struct ksmbd_conn *conn, static void decode_encrypt_ctxt(struct ksmbd_conn *conn, struct smb2_encryption_neg_context *pneg_ctxt, - int len_of_ctxts) + int ctxt_len) { - int cph_cnt = le16_to_cpu(pneg_ctxt->CipherCount); - int i, cphs_size = cph_cnt * sizeof(__le16); + int cph_cnt; + int i, cphs_size; + + if (sizeof(struct smb2_encryption_neg_context) > ctxt_len) { + pr_err("Invalid SMB2_ENCRYPTION_CAPABILITIES context size\n"); + return; + } conn->cipher_type = 0; + cph_cnt = le16_to_cpu(pneg_ctxt->CipherCount); + cphs_size = cph_cnt * sizeof(__le16); + if (sizeof(struct smb2_encryption_neg_context) + cphs_size > - len_of_ctxts) { + ctxt_len) { pr_err("Invalid cipher count(%d)\n", cph_cnt); return; } @@ -923,15 +928,22 @@ static void decode_compress_ctxt(struct ksmbd_conn *conn, static void decode_sign_cap_ctxt(struct ksmbd_conn *conn, struct smb2_signing_capabilities *pneg_ctxt, - int len_of_ctxts) + int ctxt_len) { - int sign_algo_cnt = le16_to_cpu(pneg_ctxt->SigningAlgorithmCount); - int i, sign_alos_size = sign_algo_cnt * sizeof(__le16); + int sign_algo_cnt; + int i, sign_alos_size; + + if (sizeof(struct smb2_signing_capabilities) > ctxt_len) { + pr_err("Invalid SMB2_SIGNING_CAPABILITIES context length\n"); + return; + } conn->signing_negotiated = false; + sign_algo_cnt = le16_to_cpu(pneg_ctxt->SigningAlgorithmCount); + sign_alos_size = sign_algo_cnt * sizeof(__le16); if (sizeof(struct smb2_signing_capabilities) + sign_alos_size > - len_of_ctxts) { + ctxt_len) { pr_err("Invalid signing algorithm count(%d)\n", sign_algo_cnt); return; } @@ -969,18 +981,16 @@ static __le32 deassemble_neg_contexts(struct ksmbd_conn *conn, len_of_ctxts = len_of_smb - offset; while (i++ < neg_ctxt_cnt) { - int clen; - - /* check that offset is not beyond end of SMB */ - if (len_of_ctxts == 0) - break; + int clen, ctxt_len; if (len_of_ctxts < sizeof(struct smb2_neg_context)) break; pctx = (struct smb2_neg_context *)((char *)pctx + offset); clen = le16_to_cpu(pctx->DataLength); - if (clen + sizeof(struct smb2_neg_context) > len_of_ctxts) + ctxt_len = clen + sizeof(struct smb2_neg_context); + + if (ctxt_len > len_of_ctxts) break; if (pctx->ContextType == SMB2_PREAUTH_INTEGRITY_CAPABILITIES) { @@ -991,7 +1001,7 @@ static __le32 deassemble_neg_contexts(struct ksmbd_conn *conn, status = decode_preauth_ctxt(conn, (struct smb2_preauth_neg_context *)pctx, - len_of_ctxts); + ctxt_len); if (status != STATUS_SUCCESS) break; } else if (pctx->ContextType == SMB2_ENCRYPTION_CAPABILITIES) { @@ -1002,7 +1012,7 @@ static __le32 deassemble_neg_contexts(struct ksmbd_conn *conn, decode_encrypt_ctxt(conn, (struct smb2_encryption_neg_context *)pctx, - len_of_ctxts); + ctxt_len); } else if (pctx->ContextType == SMB2_COMPRESSION_CAPABILITIES) { ksmbd_debug(SMB, "deassemble SMB2_COMPRESSION_CAPABILITIES context\n"); @@ -1021,9 +1031,10 @@ static __le32 deassemble_neg_contexts(struct ksmbd_conn *conn, } else if (pctx->ContextType == SMB2_SIGNING_CAPABILITIES) { ksmbd_debug(SMB, "deassemble SMB2_SIGNING_CAPABILITIES context\n"); + decode_sign_cap_ctxt(conn, (struct smb2_signing_capabilities *)pctx, - len_of_ctxts); + ctxt_len); } /* offsets must be 8 byte aligned */ @@ -1057,16 +1068,16 @@ int smb2_handle_negotiate(struct ksmbd_work *work) return rc; } - if (req->DialectCount == 0) { - pr_err("malformed packet\n"); + smb2_buf_len = get_rfc1002_len(work->request_buf); + smb2_neg_size = offsetof(struct smb2_negotiate_req, Dialects); + if (smb2_neg_size > smb2_buf_len) { rsp->hdr.Status = STATUS_INVALID_PARAMETER; rc = -EINVAL; goto err_out; } - smb2_buf_len = get_rfc1002_len(work->request_buf); - smb2_neg_size = offsetof(struct smb2_negotiate_req, Dialects); - if (smb2_neg_size > smb2_buf_len) { + if (req->DialectCount == 0) { + pr_err("malformed packet\n"); rsp->hdr.Status = STATUS_INVALID_PARAMETER; rc = -EINVAL; goto err_out; @@ -4358,21 +4369,6 @@ static int get_file_basic_info(struct smb2_query_info_rsp *rsp, return 0; } -static unsigned long long get_allocation_size(struct inode *inode, - struct kstat *stat) -{ - unsigned long long alloc_size = 0; - - if (!S_ISDIR(stat->mode)) { - if ((inode->i_blocks << 9) <= stat->size) - alloc_size = stat->size; - else - alloc_size = inode->i_blocks << 9; - } - - return alloc_size; -} - static void get_file_standard_info(struct smb2_query_info_rsp *rsp, struct ksmbd_file *fp, void *rsp_org) { @@ -4387,7 +4383,7 @@ static void get_file_standard_info(struct smb2_query_info_rsp *rsp, sinfo = (struct smb2_file_standard_info *)rsp->Buffer; delete_pending = ksmbd_inode_pending_delete(fp); - sinfo->AllocationSize = cpu_to_le64(get_allocation_size(inode, &stat)); + sinfo->AllocationSize = cpu_to_le64(inode->i_blocks << 9); sinfo->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size); sinfo->NumberOfLinks = cpu_to_le32(get_nlink(&stat) - delete_pending); sinfo->DeletePending = delete_pending; @@ -4452,7 +4448,7 @@ static int get_file_all_info(struct ksmbd_work *work, file_info->Attributes = fp->f_ci->m_fattr; file_info->Pad1 = 0; file_info->AllocationSize = - cpu_to_le64(get_allocation_size(inode, &stat)); + cpu_to_le64(inode->i_blocks << 9); file_info->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size); file_info->NumberOfLinks = cpu_to_le32(get_nlink(&stat) - delete_pending); @@ -4641,7 +4637,7 @@ static int get_file_network_open_info(struct smb2_query_info_rsp *rsp, file_info->ChangeTime = cpu_to_le64(time); file_info->Attributes = fp->f_ci->m_fattr; file_info->AllocationSize = - cpu_to_le64(get_allocation_size(inode, &stat)); + cpu_to_le64(inode->i_blocks << 9); file_info->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size); file_info->Reserved = cpu_to_le32(0); rsp->OutputBufferLength = @@ -5506,7 +5502,7 @@ static int smb2_create_link(struct ksmbd_work *work, { char *link_name = NULL, *target_name = NULL, *pathname = NULL; struct path path; - bool file_present = true; + bool file_present = false; int rc; if (buf_len < (u64)sizeof(struct smb2_file_link_info) + @@ -5539,8 +5535,8 @@ static int smb2_create_link(struct ksmbd_work *work, if (rc) { if (rc != -ENOENT) goto out; - file_present = false; - } + } else + file_present = true; if (file_info->ReplaceIfExists) { if (file_present) { diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index 778c152708e4..6f302919e9f7 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -86,12 +86,14 @@ static int ksmbd_vfs_path_lookup_locked(struct ksmbd_share_config *share_conf, err = vfs_path_parent_lookup(filename, flags, &parent_path, &last, &type, root_share_path); - putname(filename); - if (err) + if (err) { + putname(filename); return err; + } if (unlikely(type != LAST_NORM)) { path_put(&parent_path); + putname(filename); return -ENOENT; } @@ -108,12 +110,14 @@ static int ksmbd_vfs_path_lookup_locked(struct ksmbd_share_config *share_conf, path->dentry = d; path->mnt = share_conf->vfs_path.mnt; path_put(&parent_path); + putname(filename); return 0; err_out: inode_unlock(parent_path.dentry->d_inode); path_put(&parent_path); + putname(filename); return -ENOENT; } @@ -743,6 +747,7 @@ retry: rd.new_dir = new_path.dentry->d_inode, rd.new_dentry = new_dentry, rd.flags = flags, + rd.delegated_inode = NULL, err = vfs_rename(&rd); if (err) ksmbd_debug(VFS, "vfs_rename failed err %d\n", err); diff --git a/include/linux/cper.h b/include/linux/cper.h index eacb7dd7b3af..c1a7dc325121 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -572,4 +572,10 @@ void cper_print_proc_ia(const char *pfx, int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg); int cper_dimm_err_location(struct cper_mem_err_compact *mem, char *msg); +struct acpi_hest_generic_status; +void cper_estatus_print(const char *pfx, + const struct acpi_hest_generic_status *estatus); +int cper_estatus_check_header(const struct acpi_hest_generic_status *estatus); +int cper_estatus_check(const struct acpi_hest_generic_status *estatus); + #endif diff --git a/include/linux/efi.h b/include/linux/efi.h index 7aa62c92185f..571d1a6e1b74 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1338,4 +1338,6 @@ bool efi_config_table_is_usable(const efi_guid_t *guid, unsigned long table) return xen_efi_config_table_is_usable(guid, table); } +umode_t efi_attr_is_visible(struct kobject *kobj, struct attribute *attr, int n); + #endif /* _LINUX_EFI_H */ diff --git a/include/linux/firewire.h b/include/linux/firewire.h index 1716c01c4e54..efb6e2cf2034 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -391,7 +391,7 @@ struct fw_iso_packet { u32 tag:2; /* tx: Tag in packet header */ u32 sy:4; /* tx: Sy in packet header */ u32 header_length:8; /* Length of immediate header */ - u32 header[0]; /* tx: Top of 1394 isoch. data_block */ + u32 header[]; /* tx: Top of 1394 isoch. data_block */ }; #define FW_ISO_CONTEXT_TRANSMIT 0 diff --git a/include/linux/fs.h b/include/linux/fs.h index 86b50271b4f7..133f0640fb24 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2566,12 +2566,6 @@ static inline int deny_write_access(struct file *file) struct inode *inode = file_inode(file); return atomic_dec_unless_positive(&inode->i_writecount) ? 0 : -ETXTBSY; } -static inline int exclusive_deny_write_access(struct file *file) -{ - int old = 0; - struct inode *inode = file_inode(file); - return atomic_try_cmpxchg(&inode->i_writecount, &old, -1) ? 0 : -ETXTBSY; -} static inline void put_write_access(struct inode * inode) { atomic_dec(&inode->i_writecount); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index a4c4f737f9c1..94d2be5848ae 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1093,6 +1093,7 @@ void mlx5_cmdif_debugfs_cleanup(struct mlx5_core_dev *dev); int mlx5_core_create_psv(struct mlx5_core_dev *dev, u32 pdn, int npsvs, u32 *sig_index); int mlx5_core_destroy_psv(struct mlx5_core_dev *dev, int psv_num); +__be32 mlx5_core_get_terminate_scatter_list_mkey(struct mlx5_core_dev *dev); void mlx5_core_put_rsc(struct mlx5_core_rsc_common *common); int mlx5_query_odp_caps(struct mlx5_core_dev *dev, struct mlx5_odp_caps *odp_caps); diff --git a/include/linux/pe.h b/include/linux/pe.h index 5e1e11540870..fdf9c95709ba 100644 --- a/include/linux/pe.h +++ b/include/linux/pe.h @@ -11,25 +11,26 @@ #include <linux/types.h> /* - * Linux EFI stub v1.0 adds the following functionality: - * - Loading initrd from the LINUX_EFI_INITRD_MEDIA_GUID device path, - * - Loading/starting the kernel from firmware that targets a different - * machine type, via the entrypoint exposed in the .compat PE/COFF section. + * Starting from version v3.0, the major version field should be interpreted as + * a bit mask of features supported by the kernel's EFI stub: + * - 0x1: initrd loading from the LINUX_EFI_INITRD_MEDIA_GUID device path, + * - 0x2: initrd loading using the initrd= command line option, where the file + * may be specified using device path notation, and is not required to + * reside on the same volume as the loaded kernel image. * * The recommended way of loading and starting v1.0 or later kernels is to use * the LoadImage() and StartImage() EFI boot services, and expose the initrd * via the LINUX_EFI_INITRD_MEDIA_GUID device path. * - * Versions older than v1.0 support initrd loading via the image load options - * (using initrd=, limited to the volume from which the kernel itself was - * loaded), or via arch specific means (bootparams, DT, etc). + * Versions older than v1.0 may support initrd loading via the image load + * options (using initrd=, limited to the volume from which the kernel itself + * was loaded), or only via arch specific means (bootparams, DT, etc). * - * On x86, LoadImage() and StartImage() can be omitted if the EFI handover - * protocol is implemented, which can be inferred from the version, - * handover_offset and xloadflags fields in the bootparams structure. + * The minor version field must remain 0x0. + * (https://lore.kernel.org/all/efd6f2d4-547c-1378-1faa-53c044dbd297@gmail.com/) */ -#define LINUX_EFISTUB_MAJOR_VERSION 0x1 -#define LINUX_EFISTUB_MINOR_VERSION 0x1 +#define LINUX_EFISTUB_MAJOR_VERSION 0x3 +#define LINUX_EFISTUB_MINOR_VERSION 0x0 /* * LINUX_PE_MAGIC appears at offset 0x38 into the MS-DOS header of EFI bootable diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 537cbf9a2ade..e0f5ac90a228 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -29,7 +29,6 @@ struct kernel_clone_args { u32 io_thread:1; u32 user_worker:1; u32 no_files:1; - u32 ignore_signals:1; unsigned long stack; unsigned long stack_size; unsigned long tls; diff --git a/include/linux/sched/vhost_task.h b/include/linux/sched/vhost_task.h index 6123c10b99cf..837a23624a66 100644 --- a/include/linux/sched/vhost_task.h +++ b/include/linux/sched/vhost_task.h @@ -2,22 +2,13 @@ #ifndef _LINUX_VHOST_TASK_H #define _LINUX_VHOST_TASK_H -#include <linux/completion.h> -struct task_struct; +struct vhost_task; -struct vhost_task { - int (*fn)(void *data); - void *data; - struct completion exited; - unsigned long flags; - struct task_struct *task; -}; - -struct vhost_task *vhost_task_create(int (*fn)(void *), void *arg, +struct vhost_task *vhost_task_create(bool (*fn)(void *), void *arg, const char *name); void vhost_task_start(struct vhost_task *vtsk); void vhost_task_stop(struct vhost_task *vtsk); -bool vhost_task_should_stop(struct vhost_task *vtsk); +void vhost_task_wake(struct vhost_task *vtsk); #endif diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index d16ae621782c..a7116048a4d4 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -61,10 +61,9 @@ int svc_recv(struct svc_rqst *, long); void svc_send(struct svc_rqst *rqstp); void svc_drop(struct svc_rqst *); void svc_sock_update_bufs(struct svc_serv *serv); -bool svc_alien_sock(struct net *net, int fd); -int svc_addsock(struct svc_serv *serv, const int fd, - char *name_return, const size_t len, - const struct cred *cred); +int svc_addsock(struct svc_serv *serv, struct net *net, + const int fd, char *name_return, const size_t len, + const struct cred *cred); void svc_init_xprt_sock(void); void svc_cleanup_xprt_sock(void); struct svc_xprt *svc_sock_create(struct svc_serv *serv, int prot); diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 0e373222a6df..7c4a0b72334e 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -806,6 +806,7 @@ enum { FILTER_TRACE_FN, FILTER_COMM, FILTER_CPU, + FILTER_STACKTRACE, }; extern int trace_event_raw_init(struct trace_event_call *call); diff --git a/include/linux/user_events.h b/include/linux/user_events.h index 2847f5a18a86..8afa8c3a0973 100644 --- a/include/linux/user_events.h +++ b/include/linux/user_events.h @@ -17,9 +17,10 @@ #ifdef CONFIG_USER_EVENTS struct user_event_mm { - struct list_head link; + struct list_head mms_link; struct list_head enablers; struct mm_struct *mm; + /* Used for one-shot lists, protected by event_mutex */ struct user_event_mm *next; refcount_t refcnt; refcount_t tasks; diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index cd386aa7c7cc..9eef19972845 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -347,10 +347,8 @@ struct mana_tx_qp { struct mana_ethtool_stats { u64 stop_queue; u64 wake_queue; - u64 tx_cqes; u64 tx_cqe_err; u64 tx_cqe_unknown_type; - u64 rx_cqes; u64 rx_coalesced_err; u64 rx_cqe_unknown_type; }; diff --git a/include/net/sock.h b/include/net/sock.h index 656ea89f60ff..b418425d7230 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -336,6 +336,7 @@ struct sk_filter; * @sk_cgrp_data: cgroup data for this cgroup * @sk_memcg: this socket's memory cgroup association * @sk_write_pending: a write to stream socket waits to start + * @sk_wait_pending: number of threads blocked on this socket * @sk_state_change: callback to indicate change in the state of the sock * @sk_data_ready: callback to indicate there is data to be processed * @sk_write_space: callback to indicate there is bf sending space available @@ -428,6 +429,7 @@ struct sock { unsigned int sk_napi_id; #endif int sk_rcvbuf; + int sk_wait_pending; struct sk_filter __rcu *sk_filter; union { @@ -1174,6 +1176,7 @@ static inline void sock_rps_reset_rxhash(struct sock *sk) #define sk_wait_event(__sk, __timeo, __condition, __wait) \ ({ int __rc; \ + __sk->sk_wait_pending++; \ release_sock(__sk); \ __rc = __condition; \ if (!__rc) { \ @@ -1183,6 +1186,7 @@ static inline void sock_rps_reset_rxhash(struct sock *sk) } \ sched_annotate_sleep(); \ lock_sock(__sk); \ + __sk->sk_wait_pending--; \ __rc = __condition; \ __rc; \ }) diff --git a/include/net/tcp.h b/include/net/tcp.h index 18a038d16434..5066e4586cf0 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -632,6 +632,7 @@ void tcp_reset(struct sock *sk, struct sk_buff *skb); void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb); void tcp_fin(struct sock *sk); void tcp_check_space(struct sock *sk); +void tcp_sack_compress_send_ack(struct sock *sk); /* tcp_timer.c */ void tcp_init_xmit_timers(struct sock *); diff --git a/io_uring/epoll.c b/io_uring/epoll.c index 9aa74d2c80bc..89bff2068a19 100644 --- a/io_uring/epoll.c +++ b/io_uring/epoll.c @@ -25,10 +25,6 @@ int io_epoll_ctl_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_epoll *epoll = io_kiocb_to_cmd(req, struct io_epoll); - pr_warn_once("%s: epoll_ctl support in io_uring is deprecated and will " - "be removed in a future Linux kernel version.\n", - current->comm); - if (sqe->buf_index || sqe->splice_fd_in) return -EINVAL; diff --git a/kernel/exit.c b/kernel/exit.c index 34b90e2e7cf7..edb50b4c9972 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -411,7 +411,10 @@ static void coredump_task_exit(struct task_struct *tsk) tsk->flags |= PF_POSTCOREDUMP; core_state = tsk->signal->core_state; spin_unlock_irq(&tsk->sighand->siglock); - if (core_state) { + + /* The vhost_worker does not particpate in coredumps */ + if (core_state && + ((tsk->flags & (PF_IO_WORKER | PF_USER_WORKER)) != PF_USER_WORKER)) { struct core_thread self; self.task = current; diff --git a/kernel/fork.c b/kernel/fork.c index ed4e01daccaa..81cba91f30bb 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2336,16 +2336,16 @@ __latent_entropy struct task_struct *copy_process( p->flags &= ~PF_KTHREAD; if (args->kthread) p->flags |= PF_KTHREAD; - if (args->user_worker) - p->flags |= PF_USER_WORKER; - if (args->io_thread) { + if (args->user_worker) { /* - * Mark us an IO worker, and block any signal that isn't + * Mark us a user worker, and block any signal that isn't * fatal or STOP */ - p->flags |= PF_IO_WORKER; + p->flags |= PF_USER_WORKER; siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP)); } + if (args->io_thread) + p->flags |= PF_IO_WORKER; if (args->name) strscpy_pad(p->comm, args->name, sizeof(p->comm)); @@ -2517,9 +2517,6 @@ __latent_entropy struct task_struct *copy_process( if (retval) goto bad_fork_cleanup_io; - if (args->ignore_signals) - ignore_signals(p); - stackleak_task_init(p); if (pid != &init_struct_pid) { diff --git a/kernel/module/decompress.c b/kernel/module/decompress.c index e97232b125eb..8a5d6d63b06c 100644 --- a/kernel/module/decompress.c +++ b/kernel/module/decompress.c @@ -257,7 +257,7 @@ static ssize_t module_zstd_decompress(struct load_info *info, do { struct page *page = module_get_next_page(info); - if (!IS_ERR(page)) { + if (IS_ERR(page)) { retval = PTR_ERR(page); goto out; } diff --git a/kernel/module/main.c b/kernel/module/main.c index b4c7e925fdb0..4e2cf784cf8c 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -1521,14 +1521,14 @@ static void __layout_sections(struct module *mod, struct load_info *info, bool i MOD_RODATA, MOD_RO_AFTER_INIT, MOD_DATA, - MOD_INVALID, /* This is needed to match the masks array */ + MOD_DATA, }; static const int init_m_to_mem_type[] = { MOD_INIT_TEXT, MOD_INIT_RODATA, MOD_INVALID, MOD_INIT_DATA, - MOD_INVALID, /* This is needed to match the masks array */ + MOD_INIT_DATA, }; for (m = 0; m < ARRAY_SIZE(masks); ++m) { @@ -3057,13 +3057,25 @@ SYSCALL_DEFINE3(init_module, void __user *, umod, return load_module(&info, uargs, 0); } -static int file_init_module(struct file *file, const char __user * uargs, int flags) +SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) { struct load_info info = { }; void *buf = NULL; int len; + int err; + + err = may_init_module(); + if (err) + return err; + + pr_debug("finit_module: fd=%d, uargs=%p, flags=%i\n", fd, uargs, flags); - len = kernel_read_file(file, 0, &buf, INT_MAX, NULL, + if (flags & ~(MODULE_INIT_IGNORE_MODVERSIONS + |MODULE_INIT_IGNORE_VERMAGIC + |MODULE_INIT_COMPRESSED_FILE)) + return -EINVAL; + + len = kernel_read_file_from_fd(fd, 0, &buf, INT_MAX, NULL, READING_MODULE); if (len < 0) { mod_stat_inc(&failed_kreads); @@ -3072,7 +3084,7 @@ static int file_init_module(struct file *file, const char __user * uargs, int fl } if (flags & MODULE_INIT_COMPRESSED_FILE) { - int err = module_decompress(&info, buf, len); + err = module_decompress(&info, buf, len); vfree(buf); /* compressed data is no longer needed */ if (err) { mod_stat_inc(&failed_decompress); @@ -3087,46 +3099,6 @@ static int file_init_module(struct file *file, const char __user * uargs, int fl return load_module(&info, uargs, flags); } -/* - * kernel_read_file() will already deny write access, but module - * loading wants _exclusive_ access to the file, so we do that - * here, along with basic sanity checks. - */ -static int prepare_file_for_module_load(struct file *file) -{ - if (!file || !(file->f_mode & FMODE_READ)) - return -EBADF; - if (!S_ISREG(file_inode(file)->i_mode)) - return -EINVAL; - return exclusive_deny_write_access(file); -} - -SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) -{ - struct fd f; - int err; - - err = may_init_module(); - if (err) - return err; - - pr_debug("finit_module: fd=%d, uargs=%p, flags=%i\n", fd, uargs, flags); - - if (flags & ~(MODULE_INIT_IGNORE_MODVERSIONS - |MODULE_INIT_IGNORE_VERMAGIC - |MODULE_INIT_COMPRESSED_FILE)) - return -EINVAL; - - f = fdget(fd); - err = prepare_file_for_module_load(f.file); - if (!err) { - err = file_init_module(f.file, uargs, flags); - allow_write_access(f.file); - } - fdput(f); - return err; -} - /* Keep in sync with MODULE_FLAGS_BUF_SIZE !!! */ char *module_flags(struct module *mod, char *buf, bool show_state) { diff --git a/kernel/signal.c b/kernel/signal.c index 8f6330f0e9ca..2547fa73bde5 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1368,7 +1368,9 @@ int zap_other_threads(struct task_struct *p) while_each_thread(p, t) { task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK); - count++; + /* Don't require de_thread to wait for the vhost_worker */ + if ((t->flags & (PF_IO_WORKER | PF_USER_WORKER)) != PF_USER_WORKER) + count++; /* Don't bother with already dead threads */ if (t->exit_state) @@ -2861,11 +2863,11 @@ relock: } /* - * PF_IO_WORKER threads will catch and exit on fatal signals + * PF_USER_WORKER threads will catch and exit on fatal signals * themselves. They have cleanup that must be performed, so * we cannot call do_exit() on their behalf. */ - if (current->flags & PF_IO_WORKER) + if (current->flags & PF_USER_WORKER) goto out; /* diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index ebc59781456a..64a4dde073ef 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -60,6 +60,7 @@ */ bool ring_buffer_expanded; +#ifdef CONFIG_FTRACE_STARTUP_TEST /* * We need to change this state when a selftest is running. * A selftest will lurk into the ring-buffer to count the @@ -75,7 +76,6 @@ static bool __read_mostly tracing_selftest_running; */ bool __read_mostly tracing_selftest_disabled; -#ifdef CONFIG_FTRACE_STARTUP_TEST void __init disable_tracing_selftest(const char *reason) { if (!tracing_selftest_disabled) { @@ -83,6 +83,9 @@ void __init disable_tracing_selftest(const char *reason) pr_info("Ftrace startup test is disabled due to %s\n", reason); } } +#else +#define tracing_selftest_running 0 +#define tracing_selftest_disabled 0 #endif /* Pipe tracepoints to printk */ @@ -1051,7 +1054,10 @@ int __trace_array_puts(struct trace_array *tr, unsigned long ip, if (!(tr->trace_flags & TRACE_ITER_PRINTK)) return 0; - if (unlikely(tracing_selftest_running || tracing_disabled)) + if (unlikely(tracing_selftest_running && tr == &global_trace)) + return 0; + + if (unlikely(tracing_disabled)) return 0; alloc = sizeof(*entry) + size + 2; /* possible \n added */ @@ -2041,6 +2047,24 @@ static int run_tracer_selftest(struct tracer *type) return 0; } +static int do_run_tracer_selftest(struct tracer *type) +{ + int ret; + + /* + * Tests can take a long time, especially if they are run one after the + * other, as does happen during bootup when all the tracers are + * registered. This could cause the soft lockup watchdog to trigger. + */ + cond_resched(); + + tracing_selftest_running = true; + ret = run_tracer_selftest(type); + tracing_selftest_running = false; + + return ret; +} + static __init int init_trace_selftests(void) { struct trace_selftests *p, *n; @@ -2092,6 +2116,10 @@ static inline int run_tracer_selftest(struct tracer *type) { return 0; } +static inline int do_run_tracer_selftest(struct tracer *type) +{ + return 0; +} #endif /* CONFIG_FTRACE_STARTUP_TEST */ static void add_tracer_options(struct trace_array *tr, struct tracer *t); @@ -2127,8 +2155,6 @@ int __init register_tracer(struct tracer *type) mutex_lock(&trace_types_lock); - tracing_selftest_running = true; - for (t = trace_types; t; t = t->next) { if (strcmp(type->name, t->name) == 0) { /* already found */ @@ -2157,7 +2183,7 @@ int __init register_tracer(struct tracer *type) /* store the tracer for __set_tracer_option */ type->flags->trace = type; - ret = run_tracer_selftest(type); + ret = do_run_tracer_selftest(type); if (ret < 0) goto out; @@ -2166,7 +2192,6 @@ int __init register_tracer(struct tracer *type) add_tracer_options(&global_trace, type); out: - tracing_selftest_running = false; mutex_unlock(&trace_types_lock); if (ret || !default_bootup_tracer) @@ -3490,7 +3515,7 @@ __trace_array_vprintk(struct trace_buffer *buffer, unsigned int trace_ctx; char *tbuffer; - if (tracing_disabled || tracing_selftest_running) + if (tracing_disabled) return 0; /* Don't pollute graph traces with trace_vprintk internals */ @@ -3538,6 +3563,9 @@ __printf(3, 0) int trace_array_vprintk(struct trace_array *tr, unsigned long ip, const char *fmt, va_list args) { + if (tracing_selftest_running && tr == &global_trace) + return 0; + return __trace_array_vprintk(tr->array_buffer.buffer, ip, fmt, args); } @@ -5752,7 +5780,7 @@ static const char readme_msg[] = "\t table using the key(s) and value(s) named, and the value of a\n" "\t sum called 'hitcount' is incremented. Keys and values\n" "\t correspond to fields in the event's format description. Keys\n" - "\t can be any field, or the special string 'stacktrace'.\n" + "\t can be any field, or the special string 'common_stacktrace'.\n" "\t Compound keys consisting of up to two fields can be specified\n" "\t by the 'keys' keyword. Values must correspond to numeric\n" "\t fields. Sort keys consisting of up to two fields can be\n" diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 654ffa40457a..57e539d47989 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -194,6 +194,8 @@ static int trace_define_generic_fields(void) __generic_field(int, common_cpu, FILTER_CPU); __generic_field(char *, COMM, FILTER_COMM); __generic_field(char *, comm, FILTER_COMM); + __generic_field(char *, stacktrace, FILTER_STACKTRACE); + __generic_field(char *, STACKTRACE, FILTER_STACKTRACE); return ret; } diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 486cca3c2b75..b97d3ad832f1 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -1364,7 +1364,7 @@ static const char *hist_field_name(struct hist_field *field, if (field->field) field_name = field->field->name; else - field_name = "stacktrace"; + field_name = "common_stacktrace"; } else if (field->flags & HIST_FIELD_FL_HITCOUNT) field_name = "hitcount"; @@ -2367,7 +2367,7 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file, hist_data->enable_timestamps = true; if (*flags & HIST_FIELD_FL_TIMESTAMP_USECS) hist_data->attrs->ts_in_usecs = true; - } else if (strcmp(field_name, "stacktrace") == 0) { + } else if (strcmp(field_name, "common_stacktrace") == 0) { *flags |= HIST_FIELD_FL_STACKTRACE; } else if (strcmp(field_name, "common_cpu") == 0) *flags |= HIST_FIELD_FL_CPU; @@ -2378,11 +2378,15 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file, if (!field || !field->size) { /* * For backward compatibility, if field_name - * was "cpu", then we treat this the same as - * common_cpu. This also works for "CPU". + * was "cpu" or "stacktrace", then we treat this + * the same as common_cpu and common_stacktrace + * respectively. This also works for "CPU", and + * "STACKTRACE". */ if (field && field->filter_type == FILTER_CPU) { *flags |= HIST_FIELD_FL_CPU; + } else if (field && field->filter_type == FILTER_STACKTRACE) { + *flags |= HIST_FIELD_FL_STACKTRACE; } else { hist_err(tr, HIST_ERR_FIELD_NOT_FOUND, errpos(field_name)); @@ -4238,13 +4242,19 @@ static int __create_val_field(struct hist_trigger_data *hist_data, goto out; } - /* Some types cannot be a value */ - if (hist_field->flags & (HIST_FIELD_FL_GRAPH | HIST_FIELD_FL_PERCENT | - HIST_FIELD_FL_BUCKET | HIST_FIELD_FL_LOG2 | - HIST_FIELD_FL_SYM | HIST_FIELD_FL_SYM_OFFSET | - HIST_FIELD_FL_SYSCALL | HIST_FIELD_FL_STACKTRACE)) { - hist_err(file->tr, HIST_ERR_BAD_FIELD_MODIFIER, errpos(field_str)); - ret = -EINVAL; + /* values and variables should not have some modifiers */ + if (hist_field->flags & HIST_FIELD_FL_VAR) { + /* Variable */ + if (hist_field->flags & (HIST_FIELD_FL_GRAPH | HIST_FIELD_FL_PERCENT | + HIST_FIELD_FL_BUCKET | HIST_FIELD_FL_LOG2)) + goto err; + } else { + /* Value */ + if (hist_field->flags & (HIST_FIELD_FL_GRAPH | HIST_FIELD_FL_PERCENT | + HIST_FIELD_FL_BUCKET | HIST_FIELD_FL_LOG2 | + HIST_FIELD_FL_SYM | HIST_FIELD_FL_SYM_OFFSET | + HIST_FIELD_FL_SYSCALL | HIST_FIELD_FL_STACKTRACE)) + goto err; } hist_data->fields[val_idx] = hist_field; @@ -4256,6 +4266,9 @@ static int __create_val_field(struct hist_trigger_data *hist_data, ret = -EINVAL; out: return ret; + err: + hist_err(file->tr, HIST_ERR_BAD_FIELD_MODIFIER, errpos(field_str)); + return -EINVAL; } static int create_val_field(struct hist_trigger_data *hist_data, @@ -5385,7 +5398,7 @@ static void hist_trigger_print_key(struct seq_file *m, if (key_field->field) seq_printf(m, "%s.stacktrace", key_field->field->name); else - seq_puts(m, "stacktrace:\n"); + seq_puts(m, "common_stacktrace:\n"); hist_trigger_stacktrace_print(m, key + key_field->offset, HIST_STACKTRACE_DEPTH); @@ -5968,7 +5981,7 @@ static int event_hist_trigger_print(struct seq_file *m, if (field->field) seq_printf(m, "%s.stacktrace", field->field->name); else - seq_puts(m, "stacktrace"); + seq_puts(m, "common_stacktrace"); } else hist_field_print(m, field); } diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index b1ecd7677642..dbb14705d0d3 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -96,12 +96,12 @@ struct user_event { * these to track enablement sites that are tied to an event. */ struct user_event_enabler { - struct list_head link; + struct list_head mm_enablers_link; struct user_event *event; unsigned long addr; /* Track enable bit, flags, etc. Aligned for bitops. */ - unsigned int values; + unsigned long values; }; /* Bits 0-5 are for the bit to update upon enable/disable (0-63 allowed) */ @@ -116,7 +116,9 @@ struct user_event_enabler { /* Only duplicate the bit value */ #define ENABLE_VAL_DUP_MASK ENABLE_VAL_BIT_MASK -#define ENABLE_BITOPS(e) ((unsigned long *)&(e)->values) +#define ENABLE_BITOPS(e) (&(e)->values) + +#define ENABLE_BIT(e) ((int)((e)->values & ENABLE_VAL_BIT_MASK)) /* Used for asynchronous faulting in of pages */ struct user_event_enabler_fault { @@ -153,7 +155,7 @@ struct user_event_file_info { #define VALIDATOR_REL (1 << 1) struct user_event_validator { - struct list_head link; + struct list_head user_event_link; int offset; int flags; }; @@ -259,7 +261,7 @@ error: static void user_event_enabler_destroy(struct user_event_enabler *enabler) { - list_del_rcu(&enabler->link); + list_del_rcu(&enabler->mm_enablers_link); /* No longer tracking the event via the enabler */ refcount_dec(&enabler->event->refcnt); @@ -423,9 +425,9 @@ static int user_event_enabler_write(struct user_event_mm *mm, /* Update bit atomically, user tracers must be atomic as well */ if (enabler->event && enabler->event->status) - set_bit(enabler->values & ENABLE_VAL_BIT_MASK, ptr); + set_bit(ENABLE_BIT(enabler), ptr); else - clear_bit(enabler->values & ENABLE_VAL_BIT_MASK, ptr); + clear_bit(ENABLE_BIT(enabler), ptr); kunmap_local(kaddr); unpin_user_pages_dirty_lock(&page, 1, true); @@ -437,11 +439,9 @@ static bool user_event_enabler_exists(struct user_event_mm *mm, unsigned long uaddr, unsigned char bit) { struct user_event_enabler *enabler; - struct user_event_enabler *next; - list_for_each_entry_safe(enabler, next, &mm->enablers, link) { - if (enabler->addr == uaddr && - (enabler->values & ENABLE_VAL_BIT_MASK) == bit) + list_for_each_entry(enabler, &mm->enablers, mm_enablers_link) { + if (enabler->addr == uaddr && ENABLE_BIT(enabler) == bit) return true; } @@ -451,23 +451,36 @@ static bool user_event_enabler_exists(struct user_event_mm *mm, static void user_event_enabler_update(struct user_event *user) { struct user_event_enabler *enabler; - struct user_event_mm *mm = user_event_mm_get_all(user); struct user_event_mm *next; + struct user_event_mm *mm; int attempt; + lockdep_assert_held(&event_mutex); + + /* + * We need to build a one-shot list of all the mms that have an + * enabler for the user_event passed in. This list is only valid + * while holding the event_mutex. The only reason for this is due + * to the global mm list being RCU protected and we use methods + * which can wait (mmap_read_lock and pin_user_pages_remote). + * + * NOTE: user_event_mm_get_all() increments the ref count of each + * mm that is added to the list to prevent removal timing windows. + * We must always put each mm after they are used, which may wait. + */ + mm = user_event_mm_get_all(user); + while (mm) { next = mm->next; mmap_read_lock(mm->mm); - rcu_read_lock(); - list_for_each_entry_rcu(enabler, &mm->enablers, link) { + list_for_each_entry(enabler, &mm->enablers, mm_enablers_link) { if (enabler->event == user) { attempt = 0; user_event_enabler_write(mm, enabler, true, &attempt); } } - rcu_read_unlock(); mmap_read_unlock(mm->mm); user_event_mm_put(mm); mm = next; @@ -495,7 +508,9 @@ static bool user_event_enabler_dup(struct user_event_enabler *orig, enabler->values = orig->values & ENABLE_VAL_DUP_MASK; refcount_inc(&enabler->event->refcnt); - list_add_rcu(&enabler->link, &mm->enablers); + + /* Enablers not exposed yet, RCU not required */ + list_add(&enabler->mm_enablers_link, &mm->enablers); return true; } @@ -514,6 +529,14 @@ static struct user_event_mm *user_event_mm_get_all(struct user_event *user) struct user_event_mm *mm; /* + * We use the mm->next field to build a one-shot list from the global + * RCU protected list. To build this list the event_mutex must be held. + * This lets us build a list without requiring allocs that could fail + * when user based events are most wanted for diagnostics. + */ + lockdep_assert_held(&event_mutex); + + /* * We do not want to block fork/exec while enablements are being * updated, so we use RCU to walk the current tasks that have used * user_events ABI for 1 or more events. Each enabler found in each @@ -525,23 +548,24 @@ static struct user_event_mm *user_event_mm_get_all(struct user_event *user) */ rcu_read_lock(); - list_for_each_entry_rcu(mm, &user_event_mms, link) - list_for_each_entry_rcu(enabler, &mm->enablers, link) + list_for_each_entry_rcu(mm, &user_event_mms, mms_link) { + list_for_each_entry_rcu(enabler, &mm->enablers, mm_enablers_link) { if (enabler->event == user) { mm->next = found; found = user_event_mm_get(mm); break; } + } + } rcu_read_unlock(); return found; } -static struct user_event_mm *user_event_mm_create(struct task_struct *t) +static struct user_event_mm *user_event_mm_alloc(struct task_struct *t) { struct user_event_mm *user_mm; - unsigned long flags; user_mm = kzalloc(sizeof(*user_mm), GFP_KERNEL_ACCOUNT); @@ -553,12 +577,6 @@ static struct user_event_mm *user_event_mm_create(struct task_struct *t) refcount_set(&user_mm->refcnt, 1); refcount_set(&user_mm->tasks, 1); - spin_lock_irqsave(&user_event_mms_lock, flags); - list_add_rcu(&user_mm->link, &user_event_mms); - spin_unlock_irqrestore(&user_event_mms_lock, flags); - - t->user_event_mm = user_mm; - /* * The lifetime of the memory descriptor can slightly outlast * the task lifetime if a ref to the user_event_mm is taken @@ -572,6 +590,17 @@ static struct user_event_mm *user_event_mm_create(struct task_struct *t) return user_mm; } +static void user_event_mm_attach(struct user_event_mm *user_mm, struct task_struct *t) +{ + unsigned long flags; + + spin_lock_irqsave(&user_event_mms_lock, flags); + list_add_rcu(&user_mm->mms_link, &user_event_mms); + spin_unlock_irqrestore(&user_event_mms_lock, flags); + + t->user_event_mm = user_mm; +} + static struct user_event_mm *current_user_event_mm(void) { struct user_event_mm *user_mm = current->user_event_mm; @@ -579,10 +608,12 @@ static struct user_event_mm *current_user_event_mm(void) if (user_mm) goto inc; - user_mm = user_event_mm_create(current); + user_mm = user_event_mm_alloc(current); if (!user_mm) goto error; + + user_event_mm_attach(user_mm, current); inc: refcount_inc(&user_mm->refcnt); error: @@ -593,7 +624,7 @@ static void user_event_mm_destroy(struct user_event_mm *mm) { struct user_event_enabler *enabler, *next; - list_for_each_entry_safe(enabler, next, &mm->enablers, link) + list_for_each_entry_safe(enabler, next, &mm->enablers, mm_enablers_link) user_event_enabler_destroy(enabler); mmdrop(mm->mm); @@ -630,7 +661,7 @@ void user_event_mm_remove(struct task_struct *t) /* Remove the mm from the list, so it can no longer be enabled */ spin_lock_irqsave(&user_event_mms_lock, flags); - list_del_rcu(&mm->link); + list_del_rcu(&mm->mms_link); spin_unlock_irqrestore(&user_event_mms_lock, flags); /* @@ -670,7 +701,7 @@ void user_event_mm_remove(struct task_struct *t) void user_event_mm_dup(struct task_struct *t, struct user_event_mm *old_mm) { - struct user_event_mm *mm = user_event_mm_create(t); + struct user_event_mm *mm = user_event_mm_alloc(t); struct user_event_enabler *enabler; if (!mm) @@ -678,16 +709,18 @@ void user_event_mm_dup(struct task_struct *t, struct user_event_mm *old_mm) rcu_read_lock(); - list_for_each_entry_rcu(enabler, &old_mm->enablers, link) + list_for_each_entry_rcu(enabler, &old_mm->enablers, mm_enablers_link) { if (!user_event_enabler_dup(enabler, mm)) goto error; + } rcu_read_unlock(); + user_event_mm_attach(mm, t); return; error: rcu_read_unlock(); - user_event_mm_remove(t); + user_event_mm_destroy(mm); } static bool current_user_event_enabler_exists(unsigned long uaddr, @@ -748,7 +781,7 @@ retry: */ if (!*write_result) { refcount_inc(&enabler->event->refcnt); - list_add_rcu(&enabler->link, &user_mm->enablers); + list_add_rcu(&enabler->mm_enablers_link, &user_mm->enablers); } mutex_unlock(&event_mutex); @@ -904,8 +937,8 @@ static void user_event_destroy_validators(struct user_event *user) struct user_event_validator *validator, *next; struct list_head *head = &user->validators; - list_for_each_entry_safe(validator, next, head, link) { - list_del(&validator->link); + list_for_each_entry_safe(validator, next, head, user_event_link) { + list_del(&validator->user_event_link); kfree(validator); } } @@ -959,7 +992,7 @@ add_validator: validator->offset = offset; /* Want sequential access when validating */ - list_add_tail(&validator->link, &user->validators); + list_add_tail(&validator->user_event_link, &user->validators); add_field: field->type = type; @@ -1349,7 +1382,7 @@ static int user_event_validate(struct user_event *user, void *data, int len) void *pos, *end = data + len; u32 loc, offset, size; - list_for_each_entry(validator, head, link) { + list_for_each_entry(validator, head, user_event_link) { pos = data + validator->offset; /* Already done min_size check, no bounds check here */ @@ -2270,9 +2303,9 @@ static long user_events_ioctl_unreg(unsigned long uarg) */ mutex_lock(&event_mutex); - list_for_each_entry_safe(enabler, next, &mm->enablers, link) + list_for_each_entry_safe(enabler, next, &mm->enablers, mm_enablers_link) { if (enabler->addr == reg.disable_addr && - (enabler->values & ENABLE_VAL_BIT_MASK) == reg.disable_bit) { + ENABLE_BIT(enabler) == reg.disable_bit) { set_bit(ENABLE_VAL_FREEING_BIT, ENABLE_BITOPS(enabler)); if (!test_bit(ENABLE_VAL_FAULTING_BIT, ENABLE_BITOPS(enabler))) @@ -2281,6 +2314,7 @@ static long user_events_ioctl_unreg(unsigned long uarg) /* Removed at least one */ ret = 0; } + } mutex_unlock(&event_mutex); diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index efbbec2caff8..e97e3fa5cbed 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -1652,6 +1652,8 @@ static enum hrtimer_restart timerlat_irq(struct hrtimer *timer) osnoise_stop_tracing(); notify_new_max_latency(diff); + wake_up_process(tlat->kthread); + return HRTIMER_NORESTART; } } diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index ef8ed3b65d05..6a4ecfb1da43 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -308,7 +308,7 @@ trace_probe_primary_from_call(struct trace_event_call *call) { struct trace_probe_event *tpe = trace_probe_event_from_call(call); - return list_first_entry(&tpe->probes, struct trace_probe, list); + return list_first_entry_or_null(&tpe->probes, struct trace_probe, list); } static inline struct list_head *trace_probe_probe_list(struct trace_probe *tp) diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index a931d9aaea26..529590499b1f 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -848,6 +848,12 @@ trace_selftest_startup_function_graph(struct tracer *trace, } #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + /* + * These tests can take some time to run. Make sure on non PREEMPT + * kernels, we do not trigger the softlockup detector. + */ + cond_resched(); + tracing_reset_online_cpus(&tr->array_buffer); set_graph_array(tr); @@ -869,6 +875,8 @@ trace_selftest_startup_function_graph(struct tracer *trace, if (ret) goto out; + cond_resched(); + ret = register_ftrace_graph(&fgraph_ops); if (ret) { warn_failed_init_tracer(trace, ret); @@ -891,6 +899,8 @@ trace_selftest_startup_function_graph(struct tracer *trace, if (ret) goto out; + cond_resched(); + tracing_start(); if (!ret && !count) { diff --git a/kernel/vhost_task.c b/kernel/vhost_task.c index b7cbd66f889e..f80d5c51ae67 100644 --- a/kernel/vhost_task.c +++ b/kernel/vhost_task.c @@ -12,58 +12,88 @@ enum vhost_task_flags { VHOST_TASK_FLAGS_STOP, }; +struct vhost_task { + bool (*fn)(void *data); + void *data; + struct completion exited; + unsigned long flags; + struct task_struct *task; +}; + static int vhost_task_fn(void *data) { struct vhost_task *vtsk = data; - int ret; + bool dead = false; + + for (;;) { + bool did_work; + + /* mb paired w/ vhost_task_stop */ + if (test_bit(VHOST_TASK_FLAGS_STOP, &vtsk->flags)) + break; + + if (!dead && signal_pending(current)) { + struct ksignal ksig; + /* + * Calling get_signal will block in SIGSTOP, + * or clear fatal_signal_pending, but remember + * what was set. + * + * This thread won't actually exit until all + * of the file descriptors are closed, and + * the release function is called. + */ + dead = get_signal(&ksig); + if (dead) + clear_thread_flag(TIF_SIGPENDING); + } + + did_work = vtsk->fn(vtsk->data); + if (!did_work) { + set_current_state(TASK_INTERRUPTIBLE); + schedule(); + } + } - ret = vtsk->fn(vtsk->data); complete(&vtsk->exited); - do_exit(ret); + do_exit(0); +} + +/** + * vhost_task_wake - wakeup the vhost_task + * @vtsk: vhost_task to wake + * + * wake up the vhost_task worker thread + */ +void vhost_task_wake(struct vhost_task *vtsk) +{ + wake_up_process(vtsk->task); } +EXPORT_SYMBOL_GPL(vhost_task_wake); /** * vhost_task_stop - stop a vhost_task * @vtsk: vhost_task to stop * - * Callers must call vhost_task_should_stop and return from their worker - * function when it returns true; + * vhost_task_fn ensures the worker thread exits after + * VHOST_TASK_FLAGS_SOP becomes true. */ void vhost_task_stop(struct vhost_task *vtsk) { - pid_t pid = vtsk->task->pid; - set_bit(VHOST_TASK_FLAGS_STOP, &vtsk->flags); - wake_up_process(vtsk->task); + vhost_task_wake(vtsk); /* * Make sure vhost_task_fn is no longer accessing the vhost_task before - * freeing it below. If userspace crashed or exited without closing, - * then the vhost_task->task could already be marked dead so - * kernel_wait will return early. + * freeing it below. */ wait_for_completion(&vtsk->exited); - /* - * If we are just closing/removing a device and the parent process is - * not exiting then reap the task. - */ - kernel_wait4(pid, NULL, __WCLONE, NULL); kfree(vtsk); } EXPORT_SYMBOL_GPL(vhost_task_stop); /** - * vhost_task_should_stop - should the vhost task return from the work function - * @vtsk: vhost_task to stop - */ -bool vhost_task_should_stop(struct vhost_task *vtsk) -{ - return test_bit(VHOST_TASK_FLAGS_STOP, &vtsk->flags); -} -EXPORT_SYMBOL_GPL(vhost_task_should_stop); - -/** - * vhost_task_create - create a copy of a process to be used by the kernel - * @fn: thread stack + * vhost_task_create - create a copy of a task to be used by the kernel + * @fn: vhost worker function * @arg: data to be passed to fn * @name: the thread's name * @@ -71,17 +101,17 @@ EXPORT_SYMBOL_GPL(vhost_task_should_stop); * failure. The returned task is inactive, and the caller must fire it up * through vhost_task_start(). */ -struct vhost_task *vhost_task_create(int (*fn)(void *), void *arg, +struct vhost_task *vhost_task_create(bool (*fn)(void *), void *arg, const char *name) { struct kernel_clone_args args = { - .flags = CLONE_FS | CLONE_UNTRACED | CLONE_VM, + .flags = CLONE_FS | CLONE_UNTRACED | CLONE_VM | + CLONE_THREAD | CLONE_SIGHAND, .exit_signal = 0, .fn = vhost_task_fn, .name = name, .user_worker = 1, .no_files = 1, - .ignore_signals = 1, }; struct vhost_task *vtsk; struct task_struct *tsk; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 653901a1bf75..41de3a2f29e1 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2385,6 +2385,37 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[], if (tb[IFLA_BROADCAST] && nla_len(tb[IFLA_BROADCAST]) < dev->addr_len) return -EINVAL; + + if (tb[IFLA_GSO_MAX_SIZE] && + nla_get_u32(tb[IFLA_GSO_MAX_SIZE]) > dev->tso_max_size) { + NL_SET_ERR_MSG(extack, "too big gso_max_size"); + return -EINVAL; + } + + if (tb[IFLA_GSO_MAX_SEGS] && + (nla_get_u32(tb[IFLA_GSO_MAX_SEGS]) > GSO_MAX_SEGS || + nla_get_u32(tb[IFLA_GSO_MAX_SEGS]) > dev->tso_max_segs)) { + NL_SET_ERR_MSG(extack, "too big gso_max_segs"); + return -EINVAL; + } + + if (tb[IFLA_GRO_MAX_SIZE] && + nla_get_u32(tb[IFLA_GRO_MAX_SIZE]) > GRO_MAX_SIZE) { + NL_SET_ERR_MSG(extack, "too big gro_max_size"); + return -EINVAL; + } + + if (tb[IFLA_GSO_IPV4_MAX_SIZE] && + nla_get_u32(tb[IFLA_GSO_IPV4_MAX_SIZE]) > dev->tso_max_size) { + NL_SET_ERR_MSG(extack, "too big gso_ipv4_max_size"); + return -EINVAL; + } + + if (tb[IFLA_GRO_IPV4_MAX_SIZE] && + nla_get_u32(tb[IFLA_GRO_IPV4_MAX_SIZE]) > GRO_MAX_SIZE) { + NL_SET_ERR_MSG(extack, "too big gro_ipv4_max_size"); + return -EINVAL; + } } if (tb[IFLA_AF_SPEC]) { @@ -2858,11 +2889,6 @@ static int do_setlink(const struct sk_buff *skb, if (tb[IFLA_GSO_MAX_SIZE]) { u32 max_size = nla_get_u32(tb[IFLA_GSO_MAX_SIZE]); - if (max_size > dev->tso_max_size) { - err = -EINVAL; - goto errout; - } - if (dev->gso_max_size ^ max_size) { netif_set_gso_max_size(dev, max_size); status |= DO_SETLINK_MODIFIED; @@ -2872,11 +2898,6 @@ static int do_setlink(const struct sk_buff *skb, if (tb[IFLA_GSO_MAX_SEGS]) { u32 max_segs = nla_get_u32(tb[IFLA_GSO_MAX_SEGS]); - if (max_segs > GSO_MAX_SEGS || max_segs > dev->tso_max_segs) { - err = -EINVAL; - goto errout; - } - if (dev->gso_max_segs ^ max_segs) { netif_set_gso_max_segs(dev, max_segs); status |= DO_SETLINK_MODIFIED; @@ -2895,11 +2916,6 @@ static int do_setlink(const struct sk_buff *skb, if (tb[IFLA_GSO_IPV4_MAX_SIZE]) { u32 max_size = nla_get_u32(tb[IFLA_GSO_IPV4_MAX_SIZE]); - if (max_size > dev->tso_max_size) { - err = -EINVAL; - goto errout; - } - if (dev->gso_ipv4_max_size ^ max_size) { netif_set_gso_ipv4_max_size(dev, max_size); status |= DO_SETLINK_MODIFIED; @@ -3285,6 +3301,7 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname, struct net_device *dev; unsigned int num_tx_queues = 1; unsigned int num_rx_queues = 1; + int err; if (tb[IFLA_NUM_TX_QUEUES]) num_tx_queues = nla_get_u32(tb[IFLA_NUM_TX_QUEUES]); @@ -3320,13 +3337,18 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname, if (!dev) return ERR_PTR(-ENOMEM); + err = validate_linkmsg(dev, tb, extack); + if (err < 0) { + free_netdev(dev); + return ERR_PTR(err); + } + dev_net_set(dev, net); dev->rtnl_link_ops = ops; dev->rtnl_link_state = RTNL_LINK_INITIALIZING; if (tb[IFLA_MTU]) { u32 mtu = nla_get_u32(tb[IFLA_MTU]); - int err; err = dev_validate_mtu(dev, mtu, extack); if (err) { diff --git a/net/core/sock.c b/net/core/sock.c index 5440e67bcfe3..24f2761bdb1d 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2381,7 +2381,6 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) { u32 max_segs = 1; - sk_dst_set(sk, dst); sk->sk_route_caps = dst->dev->features; if (sk_is_tcp(sk)) sk->sk_route_caps |= NETIF_F_GSO; @@ -2400,6 +2399,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) } } sk->sk_gso_max_segs = max_segs; + sk_dst_set(sk, dst); } EXPORT_SYMBOL_GPL(sk_setup_caps); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index c4aab3aacbd8..4a76ebf793b8 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -586,6 +586,7 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) add_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending += writebias; + sk->sk_wait_pending++; /* Basic assumption: if someone sets sk->sk_err, he _must_ * change state of the socket from TCP_SYN_*. @@ -601,6 +602,7 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) } remove_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending -= writebias; + sk->sk_wait_pending--; return timeo; } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 65ad4251f6fd..1386787eaf1a 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1142,6 +1142,7 @@ struct sock *inet_csk_clone_lock(const struct sock *sk, if (newsk) { struct inet_connection_sock *newicsk = inet_csk(newsk); + newsk->sk_wait_pending = 0; inet_sk_set_state(newsk, TCP_SYN_RECV); newicsk->icsk_bind_hash = NULL; newicsk->icsk_bind2_hash = NULL; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index a60f6f4e7cd9..8d20d9221238 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3081,6 +3081,12 @@ int tcp_disconnect(struct sock *sk, int flags) int old_state = sk->sk_state; u32 seq; + /* Deny disconnect if other threads are blocked in sk_wait_event() + * or inet_wait_for_connect(). + */ + if (sk->sk_wait_pending) + return -EBUSY; + if (old_state != TCP_CLOSE) tcp_set_state(sk, TCP_CLOSE); @@ -4072,7 +4078,8 @@ int do_tcp_getsockopt(struct sock *sk, int level, switch (optname) { case TCP_MAXSEG: val = tp->mss_cache; - if (!val && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) + if (tp->rx_opt.user_mss && + ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) val = tp->rx_opt.user_mss; if (tp->repair) val = tp->rx_opt.mss_clamp; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 61b6710f337a..bf8b22218dd4 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4530,7 +4530,7 @@ static void tcp_sack_maybe_coalesce(struct tcp_sock *tp) } } -static void tcp_sack_compress_send_ack(struct sock *sk) +void tcp_sack_compress_send_ack(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index b839c2f91292..39eb947fe392 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -290,9 +290,19 @@ static int tcp_write_timeout(struct sock *sk) void tcp_delack_timer_handler(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_sock *tp = tcp_sk(sk); - if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) || - !(icsk->icsk_ack.pending & ICSK_ACK_TIMER)) + if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) + return; + + /* Handling the sack compression case */ + if (tp->compressed_ack) { + tcp_mstamp_refresh(tp); + tcp_sack_compress_send_ack(sk); + return; + } + + if (!(icsk->icsk_ack.pending & ICSK_ACK_TIMER)) return; if (time_after(icsk->icsk_ack.timeout, jiffies)) { @@ -312,7 +322,7 @@ void tcp_delack_timer_handler(struct sock *sk) inet_csk_exit_pingpong_mode(sk); icsk->icsk_ack.ato = TCP_ATO_MIN; } - tcp_mstamp_refresh(tcp_sk(sk)); + tcp_mstamp_refresh(tp); tcp_send_ack(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKS); } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 08dc53f56bc2..67311e7d5b21 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -90,8 +90,8 @@ static int __mptcp_socket_create(struct mptcp_sock *msk) if (err) return err; - msk->first = ssock->sk; - msk->subflow = ssock; + WRITE_ONCE(msk->first, ssock->sk); + WRITE_ONCE(msk->subflow, ssock); subflow = mptcp_subflow_ctx(ssock->sk); list_add(&subflow->node, &msk->conn_list); sock_hold(ssock->sk); @@ -603,7 +603,7 @@ static bool mptcp_check_data_fin(struct sock *sk) WRITE_ONCE(msk->ack_seq, msk->ack_seq + 1); WRITE_ONCE(msk->rcv_data_fin, 0); - sk->sk_shutdown |= RCV_SHUTDOWN; + WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | RCV_SHUTDOWN); smp_mb__before_atomic(); /* SHUTDOWN must be visible first */ switch (sk->sk_state) { @@ -825,6 +825,13 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) mptcp_data_unlock(sk); } +static void mptcp_subflow_joined(struct mptcp_sock *msk, struct sock *ssk) +{ + mptcp_subflow_ctx(ssk)->map_seq = READ_ONCE(msk->ack_seq); + WRITE_ONCE(msk->allow_infinite_fallback, false); + mptcp_event(MPTCP_EVENT_SUB_ESTABLISHED, msk, ssk, GFP_ATOMIC); +} + static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk) { struct sock *sk = (struct sock *)msk; @@ -839,6 +846,7 @@ static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk) mptcp_sock_graft(ssk, sk->sk_socket); mptcp_sockopt_sync_locked(msk, ssk); + mptcp_subflow_joined(msk, ssk); return true; } @@ -910,7 +918,7 @@ static void mptcp_check_for_eof(struct mptcp_sock *msk) /* hopefully temporary hack: propagate shutdown status * to msk, when all subflows agree on it */ - sk->sk_shutdown |= RCV_SHUTDOWN; + WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | RCV_SHUTDOWN); smp_mb__before_atomic(); /* SHUTDOWN must be visible first */ sk->sk_data_ready(sk); @@ -1702,7 +1710,6 @@ static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, lock_sock(ssk); msg->msg_flags |= MSG_DONTWAIT; - msk->connect_flags = O_NONBLOCK; msk->fastopening = 1; ret = tcp_sendmsg_fastopen(ssk, msg, copied_syn, len, NULL); msk->fastopening = 0; @@ -2283,7 +2290,7 @@ static void mptcp_dispose_initial_subflow(struct mptcp_sock *msk) { if (msk->subflow) { iput(SOCK_INODE(msk->subflow)); - msk->subflow = NULL; + WRITE_ONCE(msk->subflow, NULL); } } @@ -2420,7 +2427,7 @@ out_release: sock_put(ssk); if (ssk == msk->first) - msk->first = NULL; + WRITE_ONCE(msk->first, NULL); out: if (ssk == msk->last_snd) @@ -2527,7 +2534,7 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk) } inet_sk_state_store(sk, TCP_CLOSE); - sk->sk_shutdown = SHUTDOWN_MASK; + WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); smp_mb__before_atomic(); /* SHUTDOWN must be visible first */ set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags); @@ -2721,7 +2728,7 @@ static int __mptcp_init_sock(struct sock *sk) WRITE_ONCE(msk->rmem_released, 0); msk->timer_ival = TCP_RTO_MIN; - msk->first = NULL; + WRITE_ONCE(msk->first, NULL); inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss; WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk))); WRITE_ONCE(msk->allow_infinite_fallback, true); @@ -2959,7 +2966,7 @@ bool __mptcp_close(struct sock *sk, long timeout) bool do_cancel_work = false; int subflows_alive = 0; - sk->sk_shutdown = SHUTDOWN_MASK; + WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) { mptcp_listen_inuse_dec(sk); @@ -3039,7 +3046,7 @@ static void mptcp_close(struct sock *sk, long timeout) sock_put(sk); } -void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk) +static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk) { #if IS_ENABLED(CONFIG_MPTCP_IPV6) const struct ipv6_pinfo *ssk6 = inet6_sk(ssk); @@ -3102,7 +3109,7 @@ static int mptcp_disconnect(struct sock *sk, int flags) mptcp_pm_data_reset(msk); mptcp_ca_reset(sk); - sk->sk_shutdown = 0; + WRITE_ONCE(sk->sk_shutdown, 0); sk_error_report(sk); return 0; } @@ -3116,9 +3123,10 @@ static struct ipv6_pinfo *mptcp_inet6_sk(const struct sock *sk) } #endif -struct sock *mptcp_sk_clone(const struct sock *sk, - const struct mptcp_options_received *mp_opt, - struct request_sock *req) +struct sock *mptcp_sk_clone_init(const struct sock *sk, + const struct mptcp_options_received *mp_opt, + struct sock *ssk, + struct request_sock *req) { struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); struct sock *nsk = sk_clone_lock(sk, GFP_ATOMIC); @@ -3137,7 +3145,7 @@ struct sock *mptcp_sk_clone(const struct sock *sk, msk = mptcp_sk(nsk); msk->local_key = subflow_req->local_key; msk->token = subflow_req->token; - msk->subflow = NULL; + WRITE_ONCE(msk->subflow, NULL); msk->in_accept_queue = 1; WRITE_ONCE(msk->fully_established, false); if (mp_opt->suboptions & OPTION_MPTCP_CSUMREQD) @@ -3150,10 +3158,30 @@ struct sock *mptcp_sk_clone(const struct sock *sk, msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq; sock_reset_flag(nsk, SOCK_RCU_FREE); - /* will be fully established after successful MPC subflow creation */ - inet_sk_state_store(nsk, TCP_SYN_RECV); - security_inet_csk_clone(nsk, req); + + /* this can't race with mptcp_close(), as the msk is + * not yet exposted to user-space + */ + inet_sk_state_store(nsk, TCP_ESTABLISHED); + + /* The msk maintain a ref to each subflow in the connections list */ + WRITE_ONCE(msk->first, ssk); + list_add(&mptcp_subflow_ctx(ssk)->node, &msk->conn_list); + sock_hold(ssk); + + /* new mpc subflow takes ownership of the newly + * created mptcp socket + */ + mptcp_token_accept(subflow_req, msk); + + /* set msk addresses early to ensure mptcp_pm_get_local_id() + * uses the correct data + */ + mptcp_copy_inaddrs(nsk, ssk); + mptcp_propagate_sndbuf(nsk, ssk); + + mptcp_rcv_space_init(msk, ssk); bh_unlock_sock(nsk); /* note: the newly allocated socket refcount is 2 now */ @@ -3185,7 +3213,7 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err, struct socket *listener; struct sock *newsk; - listener = msk->subflow; + listener = READ_ONCE(msk->subflow); if (WARN_ON_ONCE(!listener)) { *err = -EINVAL; return NULL; @@ -3465,14 +3493,16 @@ bool mptcp_finish_join(struct sock *ssk) return false; } - if (!list_empty(&subflow->node)) - goto out; + /* active subflow, already present inside the conn_list */ + if (!list_empty(&subflow->node)) { + mptcp_subflow_joined(msk, ssk); + return true; + } if (!mptcp_pm_allow_new_subflow(msk)) goto err_prohibited; - /* active connections are already on conn_list. - * If we can't acquire msk socket lock here, let the release callback + /* If we can't acquire msk socket lock here, let the release callback * handle it */ mptcp_data_lock(parent); @@ -3495,11 +3525,6 @@ err_prohibited: return false; } - subflow->map_seq = READ_ONCE(msk->ack_seq); - WRITE_ONCE(msk->allow_infinite_fallback, false); - -out: - mptcp_event(MPTCP_EVENT_SUB_ESTABLISHED, msk, ssk, GFP_ATOMIC); return true; } @@ -3617,9 +3642,9 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) * acquired the subflow socket lock, too. */ if (msk->fastopening) - err = __inet_stream_connect(ssock, uaddr, addr_len, msk->connect_flags, 1); + err = __inet_stream_connect(ssock, uaddr, addr_len, O_NONBLOCK, 1); else - err = inet_stream_connect(ssock, uaddr, addr_len, msk->connect_flags); + err = inet_stream_connect(ssock, uaddr, addr_len, O_NONBLOCK); inet_sk(sk)->defer_connect = inet_sk(ssock->sk)->defer_connect; /* on successful connect, the msk state will be moved to established by @@ -3632,12 +3657,10 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) mptcp_copy_inaddrs(sk, ssock->sk); - /* unblocking connect, mptcp-level inet_stream_connect will error out - * without changing the socket state, update it here. + /* silence EINPROGRESS and let the caller inet_stream_connect + * handle the connection in progress */ - if (err == -EINPROGRESS) - sk->sk_socket->state = ssock->state; - return err; + return 0; } static struct proto mptcp_prot = { @@ -3696,18 +3719,6 @@ unlock: return err; } -static int mptcp_stream_connect(struct socket *sock, struct sockaddr *uaddr, - int addr_len, int flags) -{ - int ret; - - lock_sock(sock->sk); - mptcp_sk(sock->sk)->connect_flags = flags; - ret = __inet_stream_connect(sock, uaddr, addr_len, flags, 0); - release_sock(sock->sk); - return ret; -} - static int mptcp_listen(struct socket *sock, int backlog) { struct mptcp_sock *msk = mptcp_sk(sock->sk); @@ -3751,10 +3762,10 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, pr_debug("msk=%p", msk); - /* buggy applications can call accept on socket states other then LISTEN + /* Buggy applications can call accept on socket states other then LISTEN * but no need to allocate the first subflow just to error out. */ - ssock = msk->subflow; + ssock = READ_ONCE(msk->subflow); if (!ssock) return -EINVAL; @@ -3800,9 +3811,6 @@ static __poll_t mptcp_check_writeable(struct mptcp_sock *msk) { struct sock *sk = (struct sock *)msk; - if (unlikely(sk->sk_shutdown & SEND_SHUTDOWN)) - return EPOLLOUT | EPOLLWRNORM; - if (sk_stream_is_writeable(sk)) return EPOLLOUT | EPOLLWRNORM; @@ -3820,6 +3828,7 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock, struct sock *sk = sock->sk; struct mptcp_sock *msk; __poll_t mask = 0; + u8 shutdown; int state; msk = mptcp_sk(sk); @@ -3828,23 +3837,30 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock, state = inet_sk_state_load(sk); pr_debug("msk=%p state=%d flags=%lx", msk, state, msk->flags); if (state == TCP_LISTEN) { - if (WARN_ON_ONCE(!msk->subflow || !msk->subflow->sk)) + struct socket *ssock = READ_ONCE(msk->subflow); + + if (WARN_ON_ONCE(!ssock || !ssock->sk)) return 0; - return inet_csk_listen_poll(msk->subflow->sk); + return inet_csk_listen_poll(ssock->sk); } + shutdown = READ_ONCE(sk->sk_shutdown); + if (shutdown == SHUTDOWN_MASK || state == TCP_CLOSE) + mask |= EPOLLHUP; + if (shutdown & RCV_SHUTDOWN) + mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; + if (state != TCP_SYN_SENT && state != TCP_SYN_RECV) { mask |= mptcp_check_readable(msk); - mask |= mptcp_check_writeable(msk); + if (shutdown & SEND_SHUTDOWN) + mask |= EPOLLOUT | EPOLLWRNORM; + else + mask |= mptcp_check_writeable(msk); } else if (state == TCP_SYN_SENT && inet_sk(sk)->defer_connect) { /* cf tcp_poll() note about TFO */ mask |= EPOLLOUT | EPOLLWRNORM; } - if (sk->sk_shutdown == SHUTDOWN_MASK || state == TCP_CLOSE) - mask |= EPOLLHUP; - if (sk->sk_shutdown & RCV_SHUTDOWN) - mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; /* This barrier is coupled with smp_wmb() in __mptcp_error_report() */ smp_rmb(); @@ -3859,7 +3875,7 @@ static const struct proto_ops mptcp_stream_ops = { .owner = THIS_MODULE, .release = inet_release, .bind = mptcp_bind, - .connect = mptcp_stream_connect, + .connect = inet_stream_connect, .socketpair = sock_no_socketpair, .accept = mptcp_stream_accept, .getname = inet_getname, @@ -3954,7 +3970,7 @@ static const struct proto_ops mptcp_v6_stream_ops = { .owner = THIS_MODULE, .release = inet6_release, .bind = mptcp_bind, - .connect = mptcp_stream_connect, + .connect = inet_stream_connect, .socketpair = sock_no_socketpair, .accept = mptcp_stream_accept, .getname = inet6_getname, diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 2d7b2c80a164..c5255258bfb3 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -297,7 +297,6 @@ struct mptcp_sock { nodelay:1, fastopening:1, in_accept_queue:1; - int connect_flags; struct work_struct work; struct sk_buff *ooo_last_skb; struct rb_root out_of_order_queue; @@ -306,7 +305,11 @@ struct mptcp_sock { struct list_head rtx_queue; struct mptcp_data_frag *first_pending; struct list_head join_list; - struct socket *subflow; /* outgoing connect/listener/!mp_capable */ + struct socket *subflow; /* outgoing connect/listener/!mp_capable + * The mptcp ops can safely dereference, using suitable + * ONCE annotation, the subflow outside the socket + * lock as such sock is freed after close(). + */ struct sock *first; struct mptcp_pm_data pm; struct { @@ -613,7 +616,6 @@ int mptcp_is_checksum_enabled(const struct net *net); int mptcp_allow_join_id0(const struct net *net); unsigned int mptcp_stale_loss_cnt(const struct net *net); int mptcp_get_pm_type(const struct net *net); -void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk); void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow, const struct mptcp_options_received *mp_opt); bool __mptcp_retransmit_pending_data(struct sock *sk); @@ -683,9 +685,10 @@ void __init mptcp_proto_init(void); int __init mptcp_proto_v6_init(void); #endif -struct sock *mptcp_sk_clone(const struct sock *sk, - const struct mptcp_options_received *mp_opt, - struct request_sock *req); +struct sock *mptcp_sk_clone_init(const struct sock *sk, + const struct mptcp_options_received *mp_opt, + struct sock *ssk, + struct request_sock *req); void mptcp_get_options(const struct sk_buff *skb, struct mptcp_options_received *mp_opt); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index ba065b66551a..4688daa6b38b 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -815,38 +815,12 @@ create_child: ctx->setsockopt_seq = listener->setsockopt_seq; if (ctx->mp_capable) { - ctx->conn = mptcp_sk_clone(listener->conn, &mp_opt, req); + ctx->conn = mptcp_sk_clone_init(listener->conn, &mp_opt, child, req); if (!ctx->conn) goto fallback; owner = mptcp_sk(ctx->conn); - - /* this can't race with mptcp_close(), as the msk is - * not yet exposted to user-space - */ - inet_sk_state_store(ctx->conn, TCP_ESTABLISHED); - - /* record the newly created socket as the first msk - * subflow, but don't link it yet into conn_list - */ - WRITE_ONCE(owner->first, child); - - /* new mpc subflow takes ownership of the newly - * created mptcp socket - */ - owner->setsockopt_seq = ctx->setsockopt_seq; mptcp_pm_new_connection(owner, child, 1); - mptcp_token_accept(subflow_req, owner); - - /* set msk addresses early to ensure mptcp_pm_get_local_id() - * uses the correct data - */ - mptcp_copy_inaddrs(ctx->conn, child); - mptcp_propagate_sndbuf(ctx->conn, child); - - mptcp_rcv_space_init(owner, child); - list_add(&ctx->node, &owner->conn_list); - sock_hold(child); /* with OoO packets we can reach here without ingress * mpc option diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index c87804112d0c..3a1e0fd5bf14 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1779,7 +1779,7 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname, break; } } - if (put_user(ALIGN(nlk->ngroups / 8, sizeof(u32)), optlen)) + if (put_user(ALIGN(BITS_TO_BYTES(nlk->ngroups), sizeof(u32)), optlen)) err = -EFAULT; netlink_unlock_table(); return err; diff --git a/net/netrom/nr_subr.c b/net/netrom/nr_subr.c index 3f99b432ea70..e2d2af924cff 100644 --- a/net/netrom/nr_subr.c +++ b/net/netrom/nr_subr.c @@ -123,7 +123,7 @@ void nr_write_internal(struct sock *sk, int frametype) unsigned char *dptr; int len, timeout; - len = NR_NETWORK_LEN + NR_TRANSPORT_LEN; + len = NR_TRANSPORT_LEN; switch (frametype & 0x0F) { case NR_CONNREQ: @@ -141,7 +141,8 @@ void nr_write_internal(struct sock *sk, int frametype) return; } - if ((skb = alloc_skb(len, GFP_ATOMIC)) == NULL) + skb = alloc_skb(NR_NETWORK_LEN + len, GFP_ATOMIC); + if (!skb) return; /* @@ -149,7 +150,7 @@ void nr_write_internal(struct sock *sk, int frametype) */ skb_reserve(skb, NR_NETWORK_LEN); - dptr = skb_put(skb, skb_tailroom(skb)); + dptr = skb_put(skb, len); switch (frametype & 0x0F) { case NR_CONNREQ: diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 94c6a1ffa459..a2dbeb264f26 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3201,6 +3201,9 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, lock_sock(sk); spin_lock(&po->bind_lock); + if (!proto) + proto = po->num; + rcu_read_lock(); if (po->fanout) { @@ -3299,7 +3302,7 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data_min)); name[sizeof(uaddr->sa_data_min)] = 0; - return packet_do_bind(sk, name, 0, pkt_sk(sk)->num); + return packet_do_bind(sk, name, 0, 0); } static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) @@ -3316,8 +3319,7 @@ static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len if (sll->sll_family != AF_PACKET) return -EINVAL; - return packet_do_bind(sk, NULL, sll->sll_ifindex, - sll->sll_protocol ? : pkt_sk(sk)->num); + return packet_do_bind(sk, NULL, sll->sll_ifindex, sll->sll_protocol); } static struct proto packet_proto = { diff --git a/net/packet/diag.c b/net/packet/diag.c index d0c4eda4cdc6..f6b200cb3c06 100644 --- a/net/packet/diag.c +++ b/net/packet/diag.c @@ -143,7 +143,7 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, rp = nlmsg_data(nlh); rp->pdiag_family = AF_PACKET; rp->pdiag_type = sk->sk_type; - rp->pdiag_num = ntohs(po->num); + rp->pdiag_num = ntohs(READ_ONCE(po->num)); rp->pdiag_ino = sk_ino; sock_diag_save_cookie(sk, rp->pdiag_cookie); diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 31f738d65f1c..da0b3b5157d5 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -980,6 +980,7 @@ static int __init af_rxrpc_init(void) BUILD_BUG_ON(sizeof(struct rxrpc_skb_priv) > sizeof_field(struct sk_buff, cb)); ret = -ENOMEM; + rxrpc_gen_version_string(); rxrpc_call_jar = kmem_cache_create( "rxrpc_call_jar", sizeof(struct rxrpc_call), 0, SLAB_HWCACHE_ALIGN, NULL); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 5d44dc08f66d..e8e14c6f904d 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -1068,6 +1068,7 @@ int rxrpc_get_server_data_key(struct rxrpc_connection *, const void *, time64_t, /* * local_event.c */ +void rxrpc_gen_version_string(void); void rxrpc_send_version_request(struct rxrpc_local *local, struct rxrpc_host_header *hdr, struct sk_buff *skb); diff --git a/net/rxrpc/local_event.c b/net/rxrpc/local_event.c index 5e69ea6b233d..993c69f97488 100644 --- a/net/rxrpc/local_event.c +++ b/net/rxrpc/local_event.c @@ -16,7 +16,16 @@ #include <generated/utsrelease.h> #include "ar-internal.h" -static const char rxrpc_version_string[65] = "linux-" UTS_RELEASE " AF_RXRPC"; +static char rxrpc_version_string[65]; // "linux-" UTS_RELEASE " AF_RXRPC"; + +/* + * Generate the VERSION packet string. + */ +void rxrpc_gen_version_string(void) +{ + snprintf(rxrpc_version_string, sizeof(rxrpc_version_string), + "linux-%.49s AF_RXRPC", UTS_RELEASE); +} /* * Reply to a version request diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 9dbc43388e57..815c3e416bc5 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1153,6 +1153,9 @@ static int fl_set_geneve_opt(const struct nlattr *nla, struct fl_flow_key *key, if (option_len > sizeof(struct geneve_opt)) data_len = option_len - sizeof(struct geneve_opt); + if (key->enc_opts.len > FLOW_DIS_TUN_OPTS_MAX - 4) + return -ERANGE; + opt = (struct geneve_opt *)&key->enc_opts.data[key->enc_opts.len]; memset(opt, 0xff, option_len); opt->length = data_len / 4; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index fdb8f429333d..014209b1dd58 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1252,7 +1252,12 @@ static struct Qdisc *qdisc_create(struct net_device *dev, sch->parent = parent; if (handle == TC_H_INGRESS) { - sch->flags |= TCQ_F_INGRESS; + if (!(sch->flags & TCQ_F_INGRESS)) { + NL_SET_ERR_MSG(extack, + "Specified parent ID is reserved for ingress and clsact Qdiscs"); + err = -EINVAL; + goto err_out3; + } handle = TC_H_MAKE(TC_H_INGRESS, 0); } else { if (handle == 0) { @@ -1591,11 +1596,20 @@ replay: NL_SET_ERR_MSG(extack, "Invalid qdisc name"); return -EINVAL; } + if (q->flags & TCQ_F_INGRESS) { + NL_SET_ERR_MSG(extack, + "Cannot regraft ingress or clsact Qdiscs"); + return -EINVAL; + } if (q == p || (p && check_loop(q, p, 0))) { NL_SET_ERR_MSG(extack, "Qdisc parent/child loop detected"); return -ELOOP; } + if (clid == TC_H_INGRESS) { + NL_SET_ERR_MSG(extack, "Ingress cannot graft directly"); + return -EINVAL; + } qdisc_refcount_inc(q); goto graft; } else { diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index 84838128b9c5..e43a45499372 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -80,6 +80,9 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt, struct net_device *dev = qdisc_dev(sch); int err; + if (sch->parent != TC_H_INGRESS) + return -EOPNOTSUPP; + net_inc_ingress_queue(); mini_qdisc_pair_init(&q->miniqp, sch, &dev->miniq_ingress); @@ -101,6 +104,9 @@ static void ingress_destroy(struct Qdisc *sch) { struct ingress_sched_data *q = qdisc_priv(sch); + if (sch->parent != TC_H_INGRESS) + return; + tcf_block_put_ext(q->block, sch, &q->block_info); net_dec_ingress_queue(); } @@ -134,7 +140,7 @@ static struct Qdisc_ops ingress_qdisc_ops __read_mostly = { .cl_ops = &ingress_class_ops, .id = "ingress", .priv_size = sizeof(struct ingress_sched_data), - .static_flags = TCQ_F_CPUSTATS, + .static_flags = TCQ_F_INGRESS | TCQ_F_CPUSTATS, .init = ingress_init, .destroy = ingress_destroy, .dump = ingress_dump, @@ -219,6 +225,9 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt, struct net_device *dev = qdisc_dev(sch); int err; + if (sch->parent != TC_H_CLSACT) + return -EOPNOTSUPP; + net_inc_ingress_queue(); net_inc_egress_queue(); @@ -248,6 +257,9 @@ static void clsact_destroy(struct Qdisc *sch) { struct clsact_sched_data *q = qdisc_priv(sch); + if (sch->parent != TC_H_CLSACT) + return; + tcf_block_put_ext(q->egress_block, sch, &q->egress_block_info); tcf_block_put_ext(q->ingress_block, sch, &q->ingress_block_info); @@ -269,7 +281,7 @@ static struct Qdisc_ops clsact_qdisc_ops __read_mostly = { .cl_ops = &clsact_class_ops, .id = "clsact", .priv_size = sizeof(struct clsact_sched_data), - .static_flags = TCQ_F_CPUSTATS, + .static_flags = TCQ_F_INGRESS | TCQ_F_CPUSTATS, .init = clsact_init, .destroy = clsact_destroy, .dump = ingress_dump, diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index a0840b8c935b..7a8d9163d186 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -578,7 +578,10 @@ static struct smc_buf_desc *smc_llc_get_next_rmb(struct smc_link_group *lgr, { struct smc_buf_desc *buf_next; - if (!buf_pos || list_is_last(&buf_pos->list, &lgr->rmbs[*buf_lst])) { + if (!buf_pos) + return _smc_llc_get_next_rmb(lgr, buf_lst); + + if (list_is_last(&buf_pos->list, &lgr->rmbs[*buf_lst])) { (*buf_lst)++; return _smc_llc_get_next_rmb(lgr, buf_lst); } @@ -614,6 +617,8 @@ static int smc_llc_fill_ext_v2(struct smc_llc_msg_add_link_v2_ext *ext, goto out; buf_pos = smc_llc_get_first_rmb(lgr, &buf_lst); for (i = 0; i < ext->num_rkeys; i++) { + while (buf_pos && !(buf_pos)->used) + buf_pos = smc_llc_get_next_rmb(lgr, &buf_lst, buf_pos); if (!buf_pos) break; rmb = buf_pos; @@ -623,8 +628,6 @@ static int smc_llc_fill_ext_v2(struct smc_llc_msg_add_link_v2_ext *ext, cpu_to_be64((uintptr_t)rmb->cpu_addr) : cpu_to_be64((u64)sg_dma_address(rmb->sgt[lnk_idx].sgl)); buf_pos = smc_llc_get_next_rmb(lgr, &buf_lst, buf_pos); - while (buf_pos && !(buf_pos)->used) - buf_pos = smc_llc_get_next_rmb(lgr, &buf_lst, buf_pos); } len += i * sizeof(ext->rt[0]); out: diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 63fe7a338992..f77cebe2c071 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1480,25 +1480,10 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, return svsk; } -bool svc_alien_sock(struct net *net, int fd) -{ - int err; - struct socket *sock = sockfd_lookup(fd, &err); - bool ret = false; - - if (!sock) - goto out; - if (sock_net(sock->sk) != net) - ret = true; - sockfd_put(sock); -out: - return ret; -} -EXPORT_SYMBOL_GPL(svc_alien_sock); - /** * svc_addsock - add a listener socket to an RPC service * @serv: pointer to RPC service to which to add a new listener + * @net: caller's network namespace * @fd: file descriptor of the new listener * @name_return: pointer to buffer to fill in with name of listener * @len: size of the buffer @@ -1508,8 +1493,8 @@ EXPORT_SYMBOL_GPL(svc_alien_sock); * Name is terminated with '\n'. On error, returns a negative errno * value. */ -int svc_addsock(struct svc_serv *serv, const int fd, char *name_return, - const size_t len, const struct cred *cred) +int svc_addsock(struct svc_serv *serv, struct net *net, const int fd, + char *name_return, const size_t len, const struct cred *cred) { int err = 0; struct socket *so = sockfd_lookup(fd, &err); @@ -1520,6 +1505,9 @@ int svc_addsock(struct svc_serv *serv, const int fd, char *name_return, if (!so) return err; + err = -EINVAL; + if (sock_net(so->sk) != net) + goto out; err = -EAFNOSUPPORT; if ((so->sk->sk_family != PF_INET) && (so->sk->sk_family != PF_INET6)) goto out; diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index da95abbb7ea3..f37f4a0fcd3c 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -20,7 +20,9 @@ static void tls_strp_abort_strp(struct tls_strparser *strp, int err) strp->stopped = 1; /* Report an error on the lower socket */ - strp->sk->sk_err = -err; + WRITE_ONCE(strp->sk->sk_err, -err); + /* Paired with smp_rmb() in tcp_poll() */ + smp_wmb(); sk_error_report(strp->sk); } diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 6e6a7c37d685..1a53c8f481e9 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -70,7 +70,9 @@ noinline void tls_err_abort(struct sock *sk, int err) { WARN_ON_ONCE(err >= 0); /* sk->sk_err should contain a positive error code. */ - sk->sk_err = -err; + WRITE_ONCE(sk->sk_err, -err); + /* Paired with smp_rmb() in tcp_poll() */ + smp_wmb(); sk_error_report(sk); } diff --git a/security/selinux/Makefile b/security/selinux/Makefile index 0aecf9334ec3..8b21520bd4b9 100644 --- a/security/selinux/Makefile +++ b/security/selinux/Makefile @@ -26,5 +26,9 @@ quiet_cmd_flask = GEN $(obj)/flask.h $(obj)/av_permissions.h cmd_flask = $< $(obj)/flask.h $(obj)/av_permissions.h targets += flask.h av_permissions.h -$(obj)/flask.h $(obj)/av_permissions.h &: scripts/selinux/genheaders/genheaders FORCE +# once make >= 4.3 is required, we can use grouped targets in the rule below, +# which basically involves adding both headers and a '&' before the colon, see +# the example below: +# $(obj)/flask.h $(obj)/av_permissions.h &: scripts/selinux/... +$(obj)/flask.h: scripts/selinux/genheaders/genheaders FORCE $(call if_changed,flask) diff --git a/tools/include/linux/coresight-pmu.h b/tools/include/linux/coresight-pmu.h index cef3b1c25335..51ac441a37c3 100644 --- a/tools/include/linux/coresight-pmu.h +++ b/tools/include/linux/coresight-pmu.h @@ -21,19 +21,6 @@ */ #define CORESIGHT_LEGACY_CPU_TRACE_ID(cpu) (0x10 + (cpu * 2)) -/* CoreSight trace ID is currently the bottom 7 bits of the value */ -#define CORESIGHT_TRACE_ID_VAL_MASK GENMASK(6, 0) - -/* - * perf record will set the legacy meta data values as unused initially. - * This allows perf report to manage the decoders created when dynamic - * allocation in operation. - */ -#define CORESIGHT_TRACE_ID_UNUSED_FLAG BIT(31) - -/* Value to set for unused trace ID values */ -#define CORESIGHT_TRACE_ID_UNUSED_VAL 0x7F - /* * Below are the definition of bit offsets for perf option, and works as * arbitrary values for all ETM versions. diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h index 4b7f2df66b99..e682ab628dfa 100644 --- a/tools/include/uapi/linux/in.h +++ b/tools/include/uapi/linux/in.h @@ -163,6 +163,7 @@ struct in_addr { #define IP_MULTICAST_ALL 49 #define IP_UNICAST_IF 50 #define IP_LOCAL_PORT_RANGE 51 +#define IP_PROTOCOL 52 #define MCAST_EXCLUDE 0 #define MCAST_INCLUDE 1 diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py index aa77bcae4807..3144f33196be 100644 --- a/tools/net/ynl/lib/ynl.py +++ b/tools/net/ynl/lib/ynl.py @@ -591,8 +591,9 @@ class YnlFamily(SpecFamily): print('Unexpected message: ' + repr(gm)) continue - rsp.append(self._decode(gm.raw_attrs, op.attr_set.name) - | gm.fixed_header_attrs) + rsp_msg = self._decode(gm.raw_attrs, op.attr_set.name) + rsp_msg.update(gm.fixed_header_attrs) + rsp.append(rsp_msg) if not rsp: return None diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 70268442f7ee..a794d9eca93d 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -927,6 +927,7 @@ ifndef NO_DEMANGLE EXTLIBS += -lstdc++ CFLAGS += -DHAVE_CXA_DEMANGLE_SUPPORT CXXFLAGS += -DHAVE_CXA_DEMANGLE_SUPPORT + $(call detected,CONFIG_CXX_DEMANGLE) endif ifdef BUILD_NONDISTRO ifeq ($(filter -liberty,$(EXTLIBS)),) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 1593c5dcaa9e..f48794816d82 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -181,7 +181,6 @@ HOSTCC ?= gcc HOSTLD ?= ld HOSTAR ?= ar CLANG ?= clang -LLVM_STRIP ?= llvm-strip PKG_CONFIG = $(CROSS_COMPILE)pkg-config @@ -1083,7 +1082,7 @@ $(BPFTOOL): | $(SKEL_TMP_OUT) $(SKEL_TMP_OUT)/%.bpf.o: util/bpf_skel/%.bpf.c $(LIBBPF) | $(SKEL_TMP_OUT) $(QUIET_CLANG)$(CLANG) -g -O2 -target bpf -Wall -Werror $(BPF_INCLUDE) $(TOOLS_UAPI_INCLUDE) \ - -c $(filter util/bpf_skel/%.bpf.c,$^) -o $@ && $(LLVM_STRIP) -g $@ + -c $(filter util/bpf_skel/%.bpf.c,$^) -o $@ $(SKEL_OUT)/%.skel.h: $(SKEL_TMP_OUT)/%.bpf.o | $(BPFTOOL) $(QUIET_GENSKEL)$(BPFTOOL) gen skeleton $< > $@ diff --git a/tools/perf/arch/arm/util/pmu.c b/tools/perf/arch/arm/util/pmu.c index 860a8b42b4b5..a9623b128ece 100644 --- a/tools/perf/arch/arm/util/pmu.c +++ b/tools/perf/arch/arm/util/pmu.c @@ -12,7 +12,7 @@ #include "arm-spe.h" #include "hisi-ptt.h" #include "../../../util/pmu.h" -#include "../cs-etm.h" +#include "../../../util/cs-etm.h" struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused) diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index 810e3376c7d6..f9906f52e4fa 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -1175,7 +1175,7 @@ int cmd_ftrace(int argc, const char **argv) OPT_BOOLEAN('b', "use-bpf", &ftrace.target.use_bpf, "Use BPF to measure function latency"), #endif - OPT_BOOLEAN('n', "--use-nsec", &ftrace.use_nsec, + OPT_BOOLEAN('n', "use-nsec", &ftrace.use_nsec, "Use nano-second histogram"), OPT_PARENT(common_options), }; diff --git a/tools/perf/util/Build b/tools/perf/util/Build index bd18fe5f2719..f9df1df1eec0 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -214,7 +214,7 @@ perf-$(CONFIG_ZSTD) += zstd.o perf-$(CONFIG_LIBCAP) += cap.o -perf-y += demangle-cxx.o +perf-$(CONFIG_CXX_DEMANGLE) += demangle-cxx.o perf-y += demangle-ocaml.o perf-y += demangle-java.o perf-y += demangle-rust.o diff --git a/tools/perf/util/bpf_skel/sample_filter.bpf.c b/tools/perf/util/bpf_skel/sample_filter.bpf.c index cffe493af1ed..fb94f5280626 100644 --- a/tools/perf/util/bpf_skel/sample_filter.bpf.c +++ b/tools/perf/util/bpf_skel/sample_filter.bpf.c @@ -25,7 +25,7 @@ struct perf_sample_data___new { } __attribute__((preserve_access_index)); /* new kernel perf_mem_data_src definition */ -union perf_mem_data_src__new { +union perf_mem_data_src___new { __u64 val; struct { __u64 mem_op:5, /* type of opcode */ @@ -108,7 +108,7 @@ static inline __u64 perf_get_sample(struct bpf_perf_event_data_kern *kctx, if (entry->part == 7) return kctx->data->data_src.mem_blk; if (entry->part == 8) { - union perf_mem_data_src__new *data = (void *)&kctx->data->data_src; + union perf_mem_data_src___new *data = (void *)&kctx->data->data_src; if (bpf_core_field_exists(data->mem_hops)) return data->mem_hops; diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h index 70cac0375b34..ecca40787ac9 100644 --- a/tools/perf/util/cs-etm.h +++ b/tools/perf/util/cs-etm.h @@ -227,6 +227,19 @@ struct cs_etm_packet_queue { #define INFO_HEADER_SIZE (sizeof(((struct perf_record_auxtrace_info *)0)->type) + \ sizeof(((struct perf_record_auxtrace_info *)0)->reserved__)) +/* CoreSight trace ID is currently the bottom 7 bits of the value */ +#define CORESIGHT_TRACE_ID_VAL_MASK GENMASK(6, 0) + +/* + * perf record will set the legacy meta data values as unused initially. + * This allows perf report to manage the decoders created when dynamic + * allocation in operation. + */ +#define CORESIGHT_TRACE_ID_UNUSED_FLAG BIT(31) + +/* Value to set for unused trace ID values */ +#define CORESIGHT_TRACE_ID_UNUSED_VAL 0x7F + int cs_etm__process_auxtrace_info(union perf_event *event, struct perf_session *session); struct perf_event_attr *cs_etm_get_default_config(struct perf_pmu *pmu); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 2f5910b31fa9..c2dbb5647e75 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -282,6 +282,7 @@ void evsel__init(struct evsel *evsel, evsel->bpf_fd = -1; INIT_LIST_HEAD(&evsel->config_terms); INIT_LIST_HEAD(&evsel->bpf_counter_list); + INIT_LIST_HEAD(&evsel->bpf_filters); perf_evsel__object.init(evsel); evsel->sample_size = __evsel__sample_size(attr->sample_type); evsel__calc_id_pos(evsel); diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index df8928745fc6..0f54f28a69c2 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -151,10 +151,8 @@ struct evsel { */ struct bpf_counter_ops *bpf_counter_ops; - union { - struct list_head bpf_counter_list; /* for perf-stat -b */ - struct list_head bpf_filters; /* for perf-record --filter */ - }; + struct list_head bpf_counter_list; /* for perf-stat -b */ + struct list_head bpf_filters; /* for perf-record --filter */ /* for perf-stat --use-bpf */ int bperf_leader_prog_fd; diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index b2ed9cc52265..63882a4db5c7 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -31,6 +31,13 @@ #include <bfd.h> #endif +#if defined(HAVE_LIBBFD_SUPPORT) || defined(HAVE_CPLUS_DEMANGLE_SUPPORT) +#ifndef DMGL_PARAMS +#define DMGL_PARAMS (1 << 0) /* Include function args */ +#define DMGL_ANSI (1 << 1) /* Include const, volatile, etc */ +#endif +#endif + #ifndef EM_AARCH64 #define EM_AARCH64 183 /* ARM 64 bit */ #endif @@ -271,6 +278,26 @@ static bool want_demangle(bool is_kernel_sym) return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle; } +/* + * Demangle C++ function signature, typically replaced by demangle-cxx.cpp + * version. + */ +__weak char *cxx_demangle_sym(const char *str __maybe_unused, bool params __maybe_unused, + bool modifiers __maybe_unused) +{ +#ifdef HAVE_LIBBFD_SUPPORT + int flags = (params ? DMGL_PARAMS : 0) | (modifiers ? DMGL_ANSI : 0); + + return bfd_demangle(NULL, str, flags); +#elif defined(HAVE_CPLUS_DEMANGLE_SUPPORT) + int flags = (params ? DMGL_PARAMS : 0) | (modifiers ? DMGL_ANSI : 0); + + return cplus_demangle(str, flags); +#else + return NULL; +#endif +} + static char *demangle_sym(struct dso *dso, int kmodule, const char *elf_name) { char *demangled = NULL; diff --git a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc index e2ff3bf4df80..2de7c61d1ae3 100644 --- a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc +++ b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc @@ -9,18 +9,33 @@ fail() { #msg exit_fail } -echo "Test event filter function name" +sample_events() { + echo > trace + echo 1 > events/kmem/kmem_cache_free/enable + echo 1 > tracing_on + ls > /dev/null + echo 0 > tracing_on + echo 0 > events/kmem/kmem_cache_free/enable +} + echo 0 > tracing_on echo 0 > events/enable + +echo "Get the most frequently calling function" +sample_events + +target_func=`cut -d: -f3 trace | sed 's/call_site=\([^+]*\)+0x.*/\1/' | sort | uniq -c | sort | tail -n 1 | sed 's/^[ 0-9]*//'` +if [ -z "$target_func" ]; then + exit_fail +fi echo > trace -echo 'call_site.function == exit_mmap' > events/kmem/kmem_cache_free/filter -echo 1 > events/kmem/kmem_cache_free/enable -echo 1 > tracing_on -ls > /dev/null -echo 0 > events/kmem/kmem_cache_free/enable -hitcnt=`grep kmem_cache_free trace| grep exit_mmap | wc -l` -misscnt=`grep kmem_cache_free trace| grep -v exit_mmap | wc -l` +echo "Test event filter function name" +echo "call_site.function == $target_func" > events/kmem/kmem_cache_free/filter +sample_events + +hitcnt=`grep kmem_cache_free trace| grep $target_func | wc -l` +misscnt=`grep kmem_cache_free trace| grep -v $target_func | wc -l` if [ $hitcnt -eq 0 ]; then exit_fail @@ -30,20 +45,14 @@ if [ $misscnt -gt 0 ]; then exit_fail fi -address=`grep ' exit_mmap$' /proc/kallsyms | cut -d' ' -f1` +address=`grep " ${target_func}\$" /proc/kallsyms | cut -d' ' -f1` echo "Test event filter function address" -echo 0 > tracing_on -echo 0 > events/enable -echo > trace echo "call_site.function == 0x$address" > events/kmem/kmem_cache_free/filter -echo 1 > events/kmem/kmem_cache_free/enable -echo 1 > tracing_on -sleep 1 -echo 0 > events/kmem/kmem_cache_free/enable +sample_events -hitcnt=`grep kmem_cache_free trace| grep exit_mmap | wc -l` -misscnt=`grep kmem_cache_free trace| grep -v exit_mmap | wc -l` +hitcnt=`grep kmem_cache_free trace| grep $target_func | wc -l` +misscnt=`grep kmem_cache_free trace| grep -v $target_func | wc -l` if [ $hitcnt -eq 0 ]; then exit_fail diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack-legacy.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack-legacy.tc new file mode 100644 index 000000000000..d0cd91a93069 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack-legacy.tc @@ -0,0 +1,24 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: event trigger - test inter-event histogram trigger trace action with dynamic string param (legacy stack) +# requires: set_event synthetic_events events/sched/sched_process_exec/hist "long[] stack' >> synthetic_events":README + +fail() { #msg + echo $1 + exit_fail +} + +echo "Test create synthetic event with stack" + +# Test the old stacktrace keyword (for backward compatibility) +echo 's:wake_lat pid_t pid; u64 delta; unsigned long[] stack;' > dynamic_events +echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=stacktrace if prev_state == 1||prev_state == 2' >> events/sched/sched_switch/trigger +echo 'hist:keys=prev_pid:delta=common_timestamp.usecs-$ts,s=$st:onmax($delta).trace(wake_lat,prev_pid,$delta,$s)' >> events/sched/sched_switch/trigger +echo 1 > events/synthetic/wake_lat/enable +sleep 1 + +if ! grep -q "=>.*sched" trace; then + fail "Failed to create synthetic event with stack" +fi + +exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack.tc index 755dbe94ccf4..8f1cc9a86a06 100644 --- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack.tc +++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack.tc @@ -1,7 +1,7 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 # description: event trigger - test inter-event histogram trigger trace action with dynamic string param -# requires: set_event synthetic_events events/sched/sched_process_exec/hist "long[]' >> synthetic_events":README +# requires: set_event synthetic_events events/sched/sched_process_exec/hist "can be any field, or the special string 'common_stacktrace'":README fail() { #msg echo $1 @@ -10,9 +10,8 @@ fail() { #msg echo "Test create synthetic event with stack" - echo 's:wake_lat pid_t pid; u64 delta; unsigned long[] stack;' > dynamic_events -echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=stacktrace if prev_state == 1||prev_state == 2' >> events/sched/sched_switch/trigger +echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=common_stacktrace if prev_state == 1||prev_state == 2' >> events/sched/sched_switch/trigger echo 'hist:keys=prev_pid:delta=common_timestamp.usecs-$ts,s=$st:onmax($delta).trace(wake_lat,prev_pid,$delta,$s)' >> events/sched/sched_switch/trigger echo 1 > events/synthetic/wake_lat/enable sleep 1 diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile index 43a723626126..7b936a926859 100644 --- a/tools/testing/selftests/net/mptcp/Makefile +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -9,7 +9,7 @@ TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \ TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt mptcp_inq -TEST_FILES := settings +TEST_FILES := mptcp_lib.sh settings EXTRA_CLEAN := *.pcap diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh index ef628b16fe9b..4eacdb1ab962 100755 --- a/tools/testing/selftests/net/mptcp/diag.sh +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + sec=$(date +%s) rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) ns="ns1-$rndh" @@ -31,6 +33,8 @@ cleanup() ip netns del $ns } +mptcp_lib_check_mptcp + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index a43d3e2f59bb..c1f7bac19942 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + time_start=$(date +%s) optstring="S:R:d:e:l:r:h4cm:f:tC" @@ -141,6 +143,8 @@ cleanup() done } +mptcp_lib_check_mptcp + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 26310c17b4c6..96f63172b8fe 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -10,6 +10,8 @@ # because it's invoked by variable name, see how the "tests" array is used #shellcheck disable=SC2317 +. "$(dirname "${0}")/mptcp_lib.sh" + ret=0 sin="" sinfail="" @@ -17,6 +19,7 @@ sout="" cin="" cinfail="" cinsent="" +tmpfile="" cout="" capout="" ns1="" @@ -136,6 +139,8 @@ cleanup_partial() check_tools() { + mptcp_lib_check_mptcp + if ! ip -Version &> /dev/null; then echo "SKIP: Could not run test without ip tool" exit $ksft_skip @@ -175,6 +180,7 @@ cleanup() { rm -f "$cin" "$cout" "$sinfail" rm -f "$sin" "$sout" "$cinsent" "$cinfail" + rm -f "$tmpfile" rm -rf $evts_ns1 $evts_ns2 cleanup_partial } @@ -383,9 +389,16 @@ check_transfer() fail_test return 1 fi - bytes="--bytes=${bytes}" + + # note: BusyBox's "cmp" command doesn't support --bytes + tmpfile=$(mktemp) + head --bytes="$bytes" "$in" > "$tmpfile" + mv "$tmpfile" "$in" + head --bytes="$bytes" "$out" > "$tmpfile" + mv "$tmpfile" "$out" + tmpfile="" fi - cmp -l "$in" "$out" ${bytes} | while read -r i a b; do + cmp -l "$in" "$out" | while read -r i a b; do local sum=$((0${a} + 0${b})) if [ $check_invert -eq 0 ] || [ $sum -ne $((0xff)) ]; then echo "[ FAIL ] $what does not match (in, out):" diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh new file mode 100644 index 000000000000..3286536b79d5 --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -0,0 +1,40 @@ +#! /bin/bash +# SPDX-License-Identifier: GPL-2.0 + +readonly KSFT_FAIL=1 +readonly KSFT_SKIP=4 + +# SELFTESTS_MPTCP_LIB_EXPECT_ALL_FEATURES env var can be set when validating all +# features using the last version of the kernel and the selftests to make sure +# a test is not being skipped by mistake. +mptcp_lib_expect_all_features() { + [ "${SELFTESTS_MPTCP_LIB_EXPECT_ALL_FEATURES:-}" = "1" ] +} + +# $1: msg +mptcp_lib_fail_if_expected_feature() { + if mptcp_lib_expect_all_features; then + echo "ERROR: missing feature: ${*}" + exit ${KSFT_FAIL} + fi + + return 1 +} + +# $1: file +mptcp_lib_has_file() { + local f="${1}" + + if [ -f "${f}" ]; then + return 0 + fi + + mptcp_lib_fail_if_expected_feature "${f} file not found" +} + +mptcp_lib_check_mptcp() { + if ! mptcp_lib_has_file "/proc/sys/net/mptcp/enabled"; then + echo "SKIP: MPTCP support is not available" + exit ${KSFT_SKIP} + fi +} diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh index 1b70c0a304ce..ff5adbb9c7f2 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + ret=0 sin="" sout="" @@ -84,6 +86,8 @@ cleanup() rm -f "$sin" "$sout" } +mptcp_lib_check_mptcp + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index 89839d1ff9d8..32f7533e0919 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + ksft_skip=4 ret=0 @@ -34,6 +36,8 @@ cleanup() ip netns del $ns1 } +mptcp_lib_check_mptcp + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index 9f22f7e5027d..36a3c9d92e20 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + sec=$(date +%s) rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) ns1="ns1-$rndh" @@ -34,6 +36,8 @@ cleanup() done } +mptcp_lib_check_mptcp + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index b1eb7bce599d..8092399d911f 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -1,6 +1,10 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + +mptcp_lib_check_mptcp + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Cannot not run test without ip tool" |