diff options
1040 files changed, 23369 insertions, 9466 deletions
diff --git a/.gitignore b/.gitignore index 705e09913dc2..1be78fd8163b 100644 --- a/.gitignore +++ b/.gitignore @@ -127,3 +127,7 @@ all.config # Kdevelop4 *.kdev4 + +#Automatically generated by ASN.1 compiler +net/ipv4/netfilter/nf_nat_snmp_basic-asn1.c +net/ipv4/netfilter/nf_nat_snmp_basic-asn1.h diff --git a/Documentation/ABI/testing/sysfs-devices-platform-dock b/Documentation/ABI/testing/sysfs-devices-platform-dock new file mode 100644 index 000000000000..1d8c18f905c7 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-devices-platform-dock @@ -0,0 +1,39 @@ +What: /sys/devices/platform/dock.N/docked +Date: Dec, 2006 +KernelVersion: 2.6.19 +Contact: linux-acpi@vger.kernel.org +Description: + (RO) Value 1 or 0 indicates whether the software believes the + laptop is docked in a docking station. + +What: /sys/devices/platform/dock.N/undock +Date: Dec, 2006 +KernelVersion: 2.6.19 +Contact: linux-acpi@vger.kernel.org +Description: + (WO) Writing to this file causes the software to initiate an + undock request to the firmware. + +What: /sys/devices/platform/dock.N/uid +Date: Feb, 2007 +KernelVersion: v2.6.21 +Contact: linux-acpi@vger.kernel.org +Description: + (RO) Displays the docking station the laptop is docked to. + +What: /sys/devices/platform/dock.N/flags +Date: May, 2007 +KernelVersion: v2.6.21 +Contact: linux-acpi@vger.kernel.org +Description: + (RO) Show dock station flags, useful for checking if undock + request has been made by the user (from the immediate_undock + option). + +What: /sys/devices/platform/dock.N/type +Date: Aug, 2008 +KernelVersion: v2.6.27 +Contact: linux-acpi@vger.kernel.org +Description: + (RO) Display the dock station type- dock_station, ata_bay or + battery_bay. diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index bfd29bc8d37a..4ed63b6cfb15 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -108,6 +108,8 @@ Description: CPU topology files that describe a logical CPU's relationship What: /sys/devices/system/cpu/cpuidle/current_driver /sys/devices/system/cpu/cpuidle/current_governer_ro + /sys/devices/system/cpu/cpuidle/available_governors + /sys/devices/system/cpu/cpuidle/current_governor Date: September 2007 Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org> Description: Discover cpuidle policy and mechanism @@ -119,13 +121,84 @@ Description: Discover cpuidle policy and mechanism Idle policy (governor) is differentiated from idle mechanism (driver) - current_driver: displays current idle mechanism + current_driver: (RO) displays current idle mechanism - current_governor_ro: displays current idle policy + current_governor_ro: (RO) displays current idle policy + + With the cpuidle_sysfs_switch boot option enabled (meant for + developer testing), the following three attributes are visible + instead: + + current_driver: same as described above + + available_governors: (RO) displays a space separated list of + available governors + + current_governor: (RW) displays current idle policy. Users can + switch the governor at runtime by writing to this file. See files in Documentation/cpuidle/ for more information. +What: /sys/devices/system/cpu/cpuX/cpuidle/stateN/name + /sys/devices/system/cpu/cpuX/cpuidle/stateN/latency + /sys/devices/system/cpu/cpuX/cpuidle/stateN/power + /sys/devices/system/cpu/cpuX/cpuidle/stateN/time + /sys/devices/system/cpu/cpuX/cpuidle/stateN/usage +Date: September 2007 +KernelVersion: v2.6.24 +Contact: Linux power management list <linux-pm@vger.kernel.org> +Description: + The directory /sys/devices/system/cpu/cpuX/cpuidle contains per + logical CPU specific cpuidle information for each online cpu X. + The processor idle states which are available for use have the + following attributes: + + name: (RO) Name of the idle state (string). + + latency: (RO) The latency to exit out of this idle state (in + microseconds). + + power: (RO) The power consumed while in this idle state (in + milliwatts). + + time: (RO) The total time spent in this idle state (in microseconds). + + usage: (RO) Number of times this state was entered (a count). + + +What: /sys/devices/system/cpu/cpuX/cpuidle/stateN/desc +Date: February 2008 +KernelVersion: v2.6.25 +Contact: Linux power management list <linux-pm@vger.kernel.org> +Description: + (RO) A small description about the idle state (string). + + +What: /sys/devices/system/cpu/cpuX/cpuidle/stateN/disable +Date: March 2012 +KernelVersion: v3.10 +Contact: Linux power management list <linux-pm@vger.kernel.org> +Description: + (RW) Option to disable this idle state (bool). The behavior and + the effect of the disable variable depends on the implementation + of a particular governor. In the ladder governor, for example, + it is not coherent, i.e. if one is disabling a light state, then + all deeper states are disabled as well, but the disable variable + does not reflect it. Likewise, if one enables a deep state but a + lighter state still is disabled, then this has no effect. + + +What: /sys/devices/system/cpu/cpuX/cpuidle/stateN/residency +Date: March 2014 +KernelVersion: v3.15 +Contact: Linux power management list <linux-pm@vger.kernel.org> +Description: + (RO) Display the target residency i.e. the minimum amount of + time (in microseconds) this cpu should spend in this idle state + to make the transition worth the effort. + + What: /sys/devices/system/cpu/cpu#/cpufreq/* Date: pre-git history Contact: linux-pm@vger.kernel.org diff --git a/Documentation/ABI/testing/sysfs-platform-dptf b/Documentation/ABI/testing/sysfs-platform-dptf new file mode 100644 index 000000000000..325dc0667dbb --- /dev/null +++ b/Documentation/ABI/testing/sysfs-platform-dptf @@ -0,0 +1,40 @@ +What: /sys/bus/platform/devices/INT3407:00/dptf_power/charger_type +Date: Jul, 2016 +KernelVersion: v4.10 +Contact: linux-acpi@vger.kernel.org +Description: + (RO) The charger type - Traditional, Hybrid or NVDC. + +What: /sys/bus/platform/devices/INT3407:00/dptf_power/adapter_rating_mw +Date: Jul, 2016 +KernelVersion: v4.10 +Contact: linux-acpi@vger.kernel.org +Description: + (RO) Adapter rating in milliwatts (the maximum Adapter power). + Must be 0 if no AC Adaptor is plugged in. + +What: /sys/bus/platform/devices/INT3407:00/dptf_power/max_platform_power_mw +Date: Jul, 2016 +KernelVersion: v4.10 +Contact: linux-acpi@vger.kernel.org +Description: + (RO) Maximum platform power that can be supported by the battery + in milliwatts. + +What: /sys/bus/platform/devices/INT3407:00/dptf_power/platform_power_source +Date: Jul, 2016 +KernelVersion: v4.10 +Contact: linux-acpi@vger.kernel.org +Description: + (RO) Display the platform power source + 0x00 = DC + 0x01 = AC + 0x02 = USB + 0x03 = Wireless Charger + +What: /sys/bus/platform/devices/INT3407:00/dptf_power/battery_steady_power +Date: Jul, 2016 +KernelVersion: v4.10 +Contact: linux-acpi@vger.kernel.org +Description: + (RO) The maximum sustained power for battery in milliwatts. diff --git a/Documentation/atomic_bitops.txt b/Documentation/atomic_bitops.txt index 5550bfdcce5f..be70b32c95d9 100644 --- a/Documentation/atomic_bitops.txt +++ b/Documentation/atomic_bitops.txt @@ -58,7 +58,12 @@ Like with atomic_t, the rule of thumb is: - RMW operations that have a return value are fully ordered. -Except for test_and_set_bit_lock() which has ACQUIRE semantics and + - RMW operations that are conditional are unordered on FAILURE, + otherwise the above rules apply. In the case of test_and_{}_bit() operations, + if the bit in memory is unchanged by the operation then it is deemed to have + failed. + +Except for a successful test_and_set_bit_lock() which has ACQUIRE semantics and clear_bit_unlock() which has RELEASE semantics. Since a platform only has a single means of achieving atomic operations diff --git a/Documentation/devicetree/bindings/net/ieee802154/mcr20a.txt b/Documentation/devicetree/bindings/net/ieee802154/mcr20a.txt new file mode 100644 index 000000000000..2aaef567c5be --- /dev/null +++ b/Documentation/devicetree/bindings/net/ieee802154/mcr20a.txt @@ -0,0 +1,23 @@ +* MCR20A IEEE 802.15.4 * + +Required properties: + - compatible: should be "nxp,mcr20a" + - spi-max-frequency: maximal bus speed, should be set to a frequency + lower than 9000000 depends sync or async operation mode + - reg: the chipselect index + - interrupts: the interrupt generated by the device. Non high-level + can occur deadlocks while handling isr. + +Optional properties: + - rst_b-gpio: GPIO spec for the RST_B pin + +Example: + + mcr20a@0 { + compatible = "nxp,mcr20a"; + spi-max-frequency = <9000000>; + reg = <0>; + interrupts = <17 2>; + interrupt-parent = <&gpio>; + rst_b-gpio = <&gpio 27 1> + }; diff --git a/Documentation/devicetree/bindings/net/ti,dp83867.txt b/Documentation/devicetree/bindings/net/ti,dp83867.txt index 02c4353b5cf2..9ef9338aaee1 100644 --- a/Documentation/devicetree/bindings/net/ti,dp83867.txt +++ b/Documentation/devicetree/bindings/net/ti,dp83867.txt @@ -25,6 +25,8 @@ Optional property: software needs to take when this pin is strapped in these modes. See data manual for details. + - ti,clk-output-sel - Muxing option for CLK_OUT pin - see dt-bindings/net/ti-dp83867.h + for applicable values. Note: ti,min-output-impedance and ti,max-output-impedance are mutually exclusive. When both properties are present ti,max-output-impedance diff --git a/Documentation/devicetree/bindings/power/mti,mips-cpc.txt b/Documentation/devicetree/bindings/power/mti,mips-cpc.txt new file mode 100644 index 000000000000..c6b82511ae8a --- /dev/null +++ b/Documentation/devicetree/bindings/power/mti,mips-cpc.txt @@ -0,0 +1,8 @@ +Binding for MIPS Cluster Power Controller (CPC). + +This binding allows a system to specify where the CPC registers are +located. + +Required properties: +compatible : Should be "mti,mips-cpc". +regs: Should describe the address & size of the CPC register region. diff --git a/Documentation/features/sched/membarrier-sync-core/arch-support.txt b/Documentation/features/sched/membarrier-sync-core/arch-support.txt new file mode 100644 index 000000000000..2c815a7f1ba7 --- /dev/null +++ b/Documentation/features/sched/membarrier-sync-core/arch-support.txt @@ -0,0 +1,62 @@ +# +# Feature name: membarrier-sync-core +# Kconfig: ARCH_HAS_MEMBARRIER_SYNC_CORE +# description: arch supports core serializing membarrier +# +# Architecture requirements +# +# * arm64 +# +# Rely on eret context synchronization when returning from IPI handler, and +# when returning to user-space. +# +# * x86 +# +# x86-32 uses IRET as return from interrupt, which takes care of the IPI. +# However, it uses both IRET and SYSEXIT to go back to user-space. The IRET +# instruction is core serializing, but not SYSEXIT. +# +# x86-64 uses IRET as return from interrupt, which takes care of the IPI. +# However, it can return to user-space through either SYSRETL (compat code), +# SYSRETQ, or IRET. +# +# Given that neither SYSRET{L,Q}, nor SYSEXIT, are core serializing, we rely +# instead on write_cr3() performed by switch_mm() to provide core serialization +# after changing the current mm, and deal with the special case of kthread -> +# uthread (temporarily keeping current mm into active_mm) by issuing a +# sync_core_before_usermode() in that specific case. +# + ----------------------- + | arch |status| + ----------------------- + | alpha: | TODO | + | arc: | TODO | + | arm: | TODO | + | arm64: | ok | + | blackfin: | TODO | + | c6x: | TODO | + | cris: | TODO | + | frv: | TODO | + | h8300: | TODO | + | hexagon: | TODO | + | ia64: | TODO | + | m32r: | TODO | + | m68k: | TODO | + | metag: | TODO | + | microblaze: | TODO | + | mips: | TODO | + | mn10300: | TODO | + | nios2: | TODO | + | openrisc: | TODO | + | parisc: | TODO | + | powerpc: | TODO | + | s390: | TODO | + | score: | TODO | + | sh: | TODO | + | sparc: | TODO | + | tile: | TODO | + | um: | TODO | + | unicore32: | TODO | + | x86: | ok | + | xtensa: | TODO | + ----------------------- diff --git a/Documentation/gpu/tve200.rst b/Documentation/gpu/tve200.rst index 69b17b324e12..152ea9398f7e 100644 --- a/Documentation/gpu/tve200.rst +++ b/Documentation/gpu/tve200.rst @@ -3,4 +3,4 @@ ================================== .. kernel-doc:: drivers/gpu/drm/tve200/tve200_drv.c - :doc: Faraday TV Encoder 200 + :doc: Faraday TV Encoder TVE200 DRM Driver diff --git a/Documentation/i2c/busses/i2c-i801 b/Documentation/i2c/busses/i2c-i801 index d47702456926..65514c251318 100644 --- a/Documentation/i2c/busses/i2c-i801 +++ b/Documentation/i2c/busses/i2c-i801 @@ -28,8 +28,10 @@ Supported adapters: * Intel Wildcat Point (PCH) * Intel Wildcat Point-LP (PCH) * Intel BayTrail (SOC) + * Intel Braswell (SOC) * Intel Sunrise Point-H (PCH) * Intel Sunrise Point-LP (PCH) + * Intel Kaby Lake-H (PCH) * Intel DNV (SOC) * Intel Broxton (SOC) * Intel Lewisburg (PCH) diff --git a/Documentation/locking/mutex-design.txt b/Documentation/locking/mutex-design.txt index 60c482df1a38..818aca19612f 100644 --- a/Documentation/locking/mutex-design.txt +++ b/Documentation/locking/mutex-design.txt @@ -21,37 +21,23 @@ Implementation -------------- Mutexes are represented by 'struct mutex', defined in include/linux/mutex.h -and implemented in kernel/locking/mutex.c. These locks use a three -state atomic counter (->count) to represent the different possible -transitions that can occur during the lifetime of a lock: - - 1: unlocked - 0: locked, no waiters - negative: locked, with potential waiters - -In its most basic form it also includes a wait-queue and a spinlock -that serializes access to it. CONFIG_SMP systems can also include -a pointer to the lock task owner (->owner) as well as a spinner MCS -lock (->osq), both described below in (ii). +and implemented in kernel/locking/mutex.c. These locks use an atomic variable +(->owner) to keep track of the lock state during its lifetime. Field owner +actually contains 'struct task_struct *' to the current lock owner and it is +therefore NULL if not currently owned. Since task_struct pointers are aligned +at at least L1_CACHE_BYTES, low bits (3) are used to store extra state (e.g., +if waiter list is non-empty). In its most basic form it also includes a +wait-queue and a spinlock that serializes access to it. Furthermore, +CONFIG_MUTEX_SPIN_ON_OWNER=y systems use a spinner MCS lock (->osq), described +below in (ii). When acquiring a mutex, there are three possible paths that can be taken, depending on the state of the lock: -(i) fastpath: tries to atomically acquire the lock by decrementing the - counter. If it was already taken by another task it goes to the next - possible path. This logic is architecture specific. On x86-64, the - locking fastpath is 2 instructions: - - 0000000000000e10 <mutex_lock>: - e21: f0 ff 0b lock decl (%rbx) - e24: 79 08 jns e2e <mutex_lock+0x1e> - - the unlocking fastpath is equally tight: - - 0000000000000bc0 <mutex_unlock>: - bc8: f0 ff 07 lock incl (%rdi) - bcb: 7f 0a jg bd7 <mutex_unlock+0x17> - +(i) fastpath: tries to atomically acquire the lock by cmpxchg()ing the owner with + the current task. This only works in the uncontended case (cmpxchg() checks + against 0UL, so all 3 state bits above have to be 0). If the lock is + contended it goes to the next possible path. (ii) midpath: aka optimistic spinning, tries to spin for acquisition while the lock owner is running and there are no other tasks ready @@ -143,11 +129,10 @@ Test if the mutex is taken: Disadvantages ------------- -Unlike its original design and purpose, 'struct mutex' is larger than -most locks in the kernel. E.g: on x86-64 it is 40 bytes, almost twice -as large as 'struct semaphore' (24 bytes) and tied, along with rwsems, -for the largest lock in the kernel. Larger structure sizes mean more -CPU cache and memory footprint. +Unlike its original design and purpose, 'struct mutex' is among the largest +locks in the kernel. E.g: on x86-64 it is 32 bytes, where 'struct semaphore' +is 24 bytes and rw_semaphore is 40 bytes. Larger structure sizes mean more CPU +cache and memory footprint. When to use mutexes ------------------- diff --git a/Documentation/networking/segmentation-offloads.txt b/Documentation/networking/segmentation-offloads.txt index 2f09455a993a..d47480b61ac6 100644 --- a/Documentation/networking/segmentation-offloads.txt +++ b/Documentation/networking/segmentation-offloads.txt @@ -13,6 +13,7 @@ The following technologies are described: * Generic Segmentation Offload - GSO * Generic Receive Offload - GRO * Partial Generic Segmentation Offload - GSO_PARTIAL + * SCTP accelleration with GSO - GSO_BY_FRAGS TCP Segmentation Offload ======================== @@ -49,6 +50,10 @@ datagram into multiple IPv4 fragments. Many of the requirements for UDP fragmentation offload are the same as TSO. However the IPv4 ID for fragments should not increment as a single IPv4 datagram is fragmented. +UFO is deprecated: modern kernels will no longer generate UFO skbs, but can +still receive them from tuntap and similar devices. Offload of UDP-based +tunnel protocols is still supported. + IPIP, SIT, GRE, UDP Tunnel, and Remote Checksum Offloads ======================================================== @@ -83,10 +88,10 @@ SKB_GSO_UDP_TUNNEL_CSUM. These two additional tunnel types reflect the fact that the outer header also requests to have a non-zero checksum included in the outer header. -Finally there is SKB_GSO_REMCSUM which indicates that a given tunnel header -has requested a remote checksum offload. In this case the inner headers -will be left with a partial checksum and only the outer header checksum -will be computed. +Finally there is SKB_GSO_TUNNEL_REMCSUM which indicates that a given tunnel +header has requested a remote checksum offload. In this case the inner +headers will be left with a partial checksum and only the outer header +checksum will be computed. Generic Segmentation Offload ============================ @@ -128,3 +133,28 @@ values for if the header was simply duplicated. The one exception to this is the outer IPv4 ID field. It is up to the device drivers to guarantee that the IPv4 ID field is incremented in the case that a given header does not have the DF bit set. + +SCTP accelleration with GSO +=========================== + +SCTP - despite the lack of hardware support - can still take advantage of +GSO to pass one large packet through the network stack, rather than +multiple small packets. + +This requires a different approach to other offloads, as SCTP packets +cannot be just segmented to (P)MTU. Rather, the chunks must be contained in +IP segments, padding respected. So unlike regular GSO, SCTP can't just +generate a big skb, set gso_size to the fragmentation point and deliver it +to IP layer. + +Instead, the SCTP protocol layer builds an skb with the segments correctly +padded and stored as chained skbs, and skb_segment() splits based on those. +To signal this, gso_size is set to the special value GSO_BY_FRAGS. + +Therefore, any code in the core networking stack must be aware of the +possibility that gso_size will be GSO_BY_FRAGS and handle that case +appropriately. (For size checks, the skb_gso_validate_*_len family of +helpers do this automatically.) + +This also affects drivers with the NETIF_F_FRAGLIST & NETIF_F_GSO_SCTP bits +set. Note also that NETIF_F_GSO_SCTP is included in NETIF_F_GSO_SOFTWARE. diff --git a/MAINTAINERS b/MAINTAINERS index 3bdc260e36b7..e0b39004edc0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7909,7 +7909,6 @@ S: Maintained F: scripts/leaking_addresses.pl LED SUBSYSTEM -M: Richard Purdie <rpurdie@rpsys.net> M: Jacek Anaszewski <jacek.anaszewski@gmail.com> M: Pavel Machek <pavel@ucw.cz> L: linux-leds@vger.kernel.org @@ -8593,6 +8592,15 @@ S: Maintained F: Documentation/ABI/testing/sysfs-bus-iio-potentiometer-mcp4531 F: drivers/iio/potentiometer/mcp4531.c +MCR20A IEEE-802.15.4 RADIO DRIVER +M: Xue Liu <liuxuenetmail@gmail.com> +L: linux-wpan@vger.kernel.org +W: https://github.com/xueliu/mcr20a-linux +S: Maintained +F: drivers/net/ieee802154/mcr20a.c +F: drivers/net/ieee802154/mcr20a.h +F: Documentation/devicetree/bindings/net/ieee802154/mcr20a.txt + MEASUREMENT COMPUTING CIO-DAC IIO DRIVER M: William Breathitt Gray <vilhelm.gray@gmail.com> L: linux-iio@vger.kernel.org @@ -9206,6 +9214,7 @@ MIPS GENERIC PLATFORM M: Paul Burton <paul.burton@mips.com> L: linux-mips@linux-mips.org S: Supported +F: Documentation/devicetree/bindings/power/mti,mips-cpc.txt F: arch/mips/generic/ F: arch/mips/tools/generic-board-config.sh @@ -9945,6 +9954,7 @@ F: drivers/nfc/nxp-nci OBJTOOL M: Josh Poimboeuf <jpoimboe@redhat.com> +M: Peter Zijlstra <peterz@infradead.org> S: Supported F: tools/objtool/ @@ -2,7 +2,7 @@ VERSION = 4 PATCHLEVEL = 16 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc2 NAME = Fearless Coyote # *DOCUMENTATION* diff --git a/arch/arc/include/asm/bug.h b/arch/arc/include/asm/bug.h index ea022d47896c..21ec82466d62 100644 --- a/arch/arc/include/asm/bug.h +++ b/arch/arc/include/asm/bug.h @@ -23,7 +23,8 @@ void die(const char *str, struct pt_regs *regs, unsigned long address); #define BUG() do { \ pr_warn("BUG: failure at %s:%d/%s()!\n", __FILE__, __LINE__, __func__); \ - dump_stack(); \ + barrier_before_unreachable(); \ + __builtin_trap(); \ } while (0) #define HAVE_ARCH_BUG diff --git a/arch/arm/boot/dts/armada-370-rd.dts b/arch/arm/boot/dts/armada-370-rd.dts index 8b2fa9a49967..c28afb242393 100644 --- a/arch/arm/boot/dts/armada-370-rd.dts +++ b/arch/arm/boot/dts/armada-370-rd.dts @@ -56,6 +56,7 @@ /dts-v1/; #include <dt-bindings/input/input.h> +#include <dt-bindings/interrupt-controller/irq.h> #include <dt-bindings/gpio/gpio.h> #include "armada-370.dtsi" @@ -243,6 +244,8 @@ #address-cells = <1>; #size-cells = <0>; reg = <0x10>; + interrupt-controller; + #interrupt-cells = <2>; ports { #address-cells = <1>; @@ -278,6 +281,35 @@ }; }; }; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + switchphy0: switchphy@0 { + reg = <0>; + interrupt-parent = <&switch>; + interrupts = <0 IRQ_TYPE_LEVEL_HIGH>; + }; + + switchphy1: switchphy@1 { + reg = <1>; + interrupt-parent = <&switch>; + interrupts = <1 IRQ_TYPE_LEVEL_HIGH>; + }; + + switchphy2: switchphy@2 { + reg = <2>; + interrupt-parent = <&switch>; + interrupts = <2 IRQ_TYPE_LEVEL_HIGH>; + }; + + switchphy3: switchphy@3 { + reg = <3>; + interrupt-parent = <&switch>; + interrupts = <3 IRQ_TYPE_LEVEL_HIGH>; + }; + }; }; }; diff --git a/arch/arm/mach-ux500/cpu-db8500.c b/arch/arm/mach-ux500/cpu-db8500.c index 57058ac46f49..7e5d7a083707 100644 --- a/arch/arm/mach-ux500/cpu-db8500.c +++ b/arch/arm/mach-ux500/cpu-db8500.c @@ -23,7 +23,6 @@ #include <linux/of.h> #include <linux/of_address.h> #include <linux/of_platform.h> -#include <linux/perf/arm_pmu.h> #include <linux/regulator/machine.h> #include <asm/outercache.h> @@ -112,37 +111,6 @@ static void ux500_restart(enum reboot_mode mode, const char *cmd) prcmu_system_reset(0); } -/* - * The PMU IRQ lines of two cores are wired together into a single interrupt. - * Bounce the interrupt to the other core if it's not ours. - */ -static irqreturn_t db8500_pmu_handler(int irq, void *dev, irq_handler_t handler) -{ - irqreturn_t ret = handler(irq, dev); - int other = !smp_processor_id(); - - if (ret == IRQ_NONE && cpu_online(other)) - irq_set_affinity(irq, cpumask_of(other)); - - /* - * We should be able to get away with the amount of IRQ_NONEs we give, - * while still having the spurious IRQ detection code kick in if the - * interrupt really starts hitting spuriously. - */ - return ret; -} - -static struct arm_pmu_platdata db8500_pmu_platdata = { - .handle_irq = db8500_pmu_handler, - .irq_flags = IRQF_NOBALANCING | IRQF_NO_THREAD, -}; - -static struct of_dev_auxdata u8500_auxdata_lookup[] __initdata = { - /* Requires call-back bindings. */ - OF_DEV_AUXDATA("arm,cortex-a9-pmu", 0, "arm-pmu", &db8500_pmu_platdata), - {}, -}; - static struct of_dev_auxdata u8540_auxdata_lookup[] __initdata = { OF_DEV_AUXDATA("stericsson,db8500-prcmu", 0x80157000, "db8500-prcmu", NULL), {}, @@ -165,9 +133,6 @@ static void __init u8500_init_machine(void) if (of_machine_is_compatible("st-ericsson,u8540")) of_platform_populate(NULL, u8500_local_bus_nodes, u8540_auxdata_lookup, NULL); - else - of_platform_populate(NULL, u8500_local_bus_nodes, - u8500_auxdata_lookup, NULL); } static const char * stericsson_dt_platform_compat[] = { diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index be7bd19c87ec..350c76a1d15b 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -20,7 +20,7 @@ #define MPIDR_UP_BITMASK (0x1 << 30) #define MPIDR_MT_BITMASK (0x1 << 24) -#define MPIDR_HWID_BITMASK 0xff00ffffff +#define MPIDR_HWID_BITMASK UL(0xff00ffffff) #define MPIDR_LEVEL_BITS_SHIFT 3 #define MPIDR_LEVEL_BITS (1 << MPIDR_LEVEL_BITS_SHIFT) diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h index 1dca41bea16a..e73f68569624 100644 --- a/arch/arm64/include/asm/hugetlb.h +++ b/arch/arm64/include/asm/hugetlb.h @@ -22,7 +22,7 @@ static inline pte_t huge_ptep_get(pte_t *ptep) { - return *ptep; + return READ_ONCE(*ptep); } diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 9679067a1574..7faed6e48b46 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -185,42 +185,42 @@ static inline pmd_t kvm_s2pmd_mkexec(pmd_t pmd) return pmd; } -static inline void kvm_set_s2pte_readonly(pte_t *pte) +static inline void kvm_set_s2pte_readonly(pte_t *ptep) { pteval_t old_pteval, pteval; - pteval = READ_ONCE(pte_val(*pte)); + pteval = READ_ONCE(pte_val(*ptep)); do { old_pteval = pteval; pteval &= ~PTE_S2_RDWR; pteval |= PTE_S2_RDONLY; - pteval = cmpxchg_relaxed(&pte_val(*pte), old_pteval, pteval); + pteval = cmpxchg_relaxed(&pte_val(*ptep), old_pteval, pteval); } while (pteval != old_pteval); } -static inline bool kvm_s2pte_readonly(pte_t *pte) +static inline bool kvm_s2pte_readonly(pte_t *ptep) { - return (pte_val(*pte) & PTE_S2_RDWR) == PTE_S2_RDONLY; + return (READ_ONCE(pte_val(*ptep)) & PTE_S2_RDWR) == PTE_S2_RDONLY; } -static inline bool kvm_s2pte_exec(pte_t *pte) +static inline bool kvm_s2pte_exec(pte_t *ptep) { - return !(pte_val(*pte) & PTE_S2_XN); + return !(READ_ONCE(pte_val(*ptep)) & PTE_S2_XN); } -static inline void kvm_set_s2pmd_readonly(pmd_t *pmd) +static inline void kvm_set_s2pmd_readonly(pmd_t *pmdp) { - kvm_set_s2pte_readonly((pte_t *)pmd); + kvm_set_s2pte_readonly((pte_t *)pmdp); } -static inline bool kvm_s2pmd_readonly(pmd_t *pmd) +static inline bool kvm_s2pmd_readonly(pmd_t *pmdp) { - return kvm_s2pte_readonly((pte_t *)pmd); + return kvm_s2pte_readonly((pte_t *)pmdp); } -static inline bool kvm_s2pmd_exec(pmd_t *pmd) +static inline bool kvm_s2pmd_exec(pmd_t *pmdp) { - return !(pmd_val(*pmd) & PMD_S2_XN); + return !(READ_ONCE(pmd_val(*pmdp)) & PMD_S2_XN); } static inline bool kvm_page_empty(void *ptr) diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index 8d3331985d2e..39ec0b8a689e 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -141,13 +141,13 @@ static inline void cpu_install_idmap(void) * Atomically replaces the active TTBR1_EL1 PGD with a new VA-compatible PGD, * avoiding the possibility of conflicting TLB entries being allocated. */ -static inline void cpu_replace_ttbr1(pgd_t *pgd) +static inline void cpu_replace_ttbr1(pgd_t *pgdp) { typedef void (ttbr_replace_func)(phys_addr_t); extern ttbr_replace_func idmap_cpu_replace_ttbr1; ttbr_replace_func *replace_phys; - phys_addr_t pgd_phys = virt_to_phys(pgd); + phys_addr_t pgd_phys = virt_to_phys(pgdp); replace_phys = (void *)__pa_symbol(idmap_cpu_replace_ttbr1); diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h index e9d9f1b006ef..2e05bcd944c8 100644 --- a/arch/arm64/include/asm/pgalloc.h +++ b/arch/arm64/include/asm/pgalloc.h @@ -36,23 +36,23 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) return (pmd_t *)__get_free_page(PGALLOC_GFP); } -static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) +static inline void pmd_free(struct mm_struct *mm, pmd_t *pmdp) { - BUG_ON((unsigned long)pmd & (PAGE_SIZE-1)); - free_page((unsigned long)pmd); + BUG_ON((unsigned long)pmdp & (PAGE_SIZE-1)); + free_page((unsigned long)pmdp); } -static inline void __pud_populate(pud_t *pud, phys_addr_t pmd, pudval_t prot) +static inline void __pud_populate(pud_t *pudp, phys_addr_t pmdp, pudval_t prot) { - set_pud(pud, __pud(__phys_to_pud_val(pmd) | prot)); + set_pud(pudp, __pud(__phys_to_pud_val(pmdp) | prot)); } -static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) +static inline void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmdp) { - __pud_populate(pud, __pa(pmd), PMD_TYPE_TABLE); + __pud_populate(pudp, __pa(pmdp), PMD_TYPE_TABLE); } #else -static inline void __pud_populate(pud_t *pud, phys_addr_t pmd, pudval_t prot) +static inline void __pud_populate(pud_t *pudp, phys_addr_t pmdp, pudval_t prot) { BUILD_BUG(); } @@ -65,30 +65,30 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) return (pud_t *)__get_free_page(PGALLOC_GFP); } -static inline void pud_free(struct mm_struct *mm, pud_t *pud) +static inline void pud_free(struct mm_struct *mm, pud_t *pudp) { - BUG_ON((unsigned long)pud & (PAGE_SIZE-1)); - free_page((unsigned long)pud); + BUG_ON((unsigned long)pudp & (PAGE_SIZE-1)); + free_page((unsigned long)pudp); } -static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pud, pgdval_t prot) +static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pudp, pgdval_t prot) { - set_pgd(pgdp, __pgd(__phys_to_pgd_val(pud) | prot)); + set_pgd(pgdp, __pgd(__phys_to_pgd_val(pudp) | prot)); } -static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud) +static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgdp, pud_t *pudp) { - __pgd_populate(pgd, __pa(pud), PUD_TYPE_TABLE); + __pgd_populate(pgdp, __pa(pudp), PUD_TYPE_TABLE); } #else -static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pud, pgdval_t prot) +static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pudp, pgdval_t prot) { BUILD_BUG(); } #endif /* CONFIG_PGTABLE_LEVELS > 3 */ extern pgd_t *pgd_alloc(struct mm_struct *mm); -extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); +extern void pgd_free(struct mm_struct *mm, pgd_t *pgdp); static inline pte_t * pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr) @@ -114,10 +114,10 @@ pte_alloc_one(struct mm_struct *mm, unsigned long addr) /* * Free a PTE table. */ -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) +static inline void pte_free_kernel(struct mm_struct *mm, pte_t *ptep) { - if (pte) - free_page((unsigned long)pte); + if (ptep) + free_page((unsigned long)ptep); } static inline void pte_free(struct mm_struct *mm, pgtable_t pte) @@ -126,10 +126,10 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t pte) __free_page(pte); } -static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t pte, +static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t ptep, pmdval_t prot) { - set_pmd(pmdp, __pmd(__phys_to_pmd_val(pte) | prot)); + set_pmd(pmdp, __pmd(__phys_to_pmd_val(ptep) | prot)); } /* diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 094374c82db0..7e2c27e63cd8 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -218,7 +218,7 @@ static inline pmd_t pmd_mkcont(pmd_t pmd) static inline void set_pte(pte_t *ptep, pte_t pte) { - *ptep = pte; + WRITE_ONCE(*ptep, pte); /* * Only if the new pte is valid and kernel, otherwise TLB maintenance @@ -250,6 +250,8 @@ extern void __sync_icache_dcache(pte_t pteval, unsigned long addr); static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { + pte_t old_pte; + if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte)) __sync_icache_dcache(pte, addr); @@ -258,14 +260,15 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, * hardware updates of the pte (ptep_set_access_flags safely changes * valid ptes without going through an invalid entry). */ - if (IS_ENABLED(CONFIG_DEBUG_VM) && pte_valid(*ptep) && pte_valid(pte) && + old_pte = READ_ONCE(*ptep); + if (IS_ENABLED(CONFIG_DEBUG_VM) && pte_valid(old_pte) && pte_valid(pte) && (mm == current->active_mm || atomic_read(&mm->mm_users) > 1)) { VM_WARN_ONCE(!pte_young(pte), "%s: racy access flag clearing: 0x%016llx -> 0x%016llx", - __func__, pte_val(*ptep), pte_val(pte)); - VM_WARN_ONCE(pte_write(*ptep) && !pte_dirty(pte), + __func__, pte_val(old_pte), pte_val(pte)); + VM_WARN_ONCE(pte_write(old_pte) && !pte_dirty(pte), "%s: racy dirty state clearing: 0x%016llx -> 0x%016llx", - __func__, pte_val(*ptep), pte_val(pte)); + __func__, pte_val(old_pte), pte_val(pte)); } set_pte(ptep, pte); @@ -431,7 +434,7 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, static inline void set_pmd(pmd_t *pmdp, pmd_t pmd) { - *pmdp = pmd; + WRITE_ONCE(*pmdp, pmd); dsb(ishst); isb(); } @@ -482,7 +485,7 @@ static inline phys_addr_t pmd_page_paddr(pmd_t pmd) static inline void set_pud(pud_t *pudp, pud_t pud) { - *pudp = pud; + WRITE_ONCE(*pudp, pud); dsb(ishst); isb(); } @@ -500,7 +503,7 @@ static inline phys_addr_t pud_page_paddr(pud_t pud) /* Find an entry in the second-level page table. */ #define pmd_index(addr) (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1)) -#define pmd_offset_phys(dir, addr) (pud_page_paddr(*(dir)) + pmd_index(addr) * sizeof(pmd_t)) +#define pmd_offset_phys(dir, addr) (pud_page_paddr(READ_ONCE(*(dir))) + pmd_index(addr) * sizeof(pmd_t)) #define pmd_offset(dir, addr) ((pmd_t *)__va(pmd_offset_phys((dir), (addr)))) #define pmd_set_fixmap(addr) ((pmd_t *)set_fixmap_offset(FIX_PMD, addr)) @@ -535,7 +538,7 @@ static inline phys_addr_t pud_page_paddr(pud_t pud) static inline void set_pgd(pgd_t *pgdp, pgd_t pgd) { - *pgdp = pgd; + WRITE_ONCE(*pgdp, pgd); dsb(ishst); } @@ -552,7 +555,7 @@ static inline phys_addr_t pgd_page_paddr(pgd_t pgd) /* Find an entry in the frst-level page table. */ #define pud_index(addr) (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)) -#define pud_offset_phys(dir, addr) (pgd_page_paddr(*(dir)) + pud_index(addr) * sizeof(pud_t)) +#define pud_offset_phys(dir, addr) (pgd_page_paddr(READ_ONCE(*(dir))) + pud_index(addr) * sizeof(pud_t)) #define pud_offset(dir, addr) ((pud_t *)__va(pud_offset_phys((dir), (addr)))) #define pud_set_fixmap(addr) ((pud_t *)set_fixmap_offset(FIX_PUD, addr)) diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h index 472ef944e932..902f9edacbea 100644 --- a/arch/arm64/include/asm/stacktrace.h +++ b/arch/arm64/include/asm/stacktrace.h @@ -28,7 +28,7 @@ struct stackframe { unsigned long fp; unsigned long pc; #ifdef CONFIG_FUNCTION_GRAPH_TRACER - unsigned int graph; + int graph; #endif }; diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index 543e11f0f657..e66b0fca99c2 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -72,15 +72,15 @@ static inline void set_fs(mm_segment_t fs) * This is equivalent to the following test: * (u65)addr + (u65)size <= (u65)current->addr_limit + 1 */ -static inline unsigned long __range_ok(unsigned long addr, unsigned long size) +static inline unsigned long __range_ok(const void __user *addr, unsigned long size) { - unsigned long limit = current_thread_info()->addr_limit; + unsigned long ret, limit = current_thread_info()->addr_limit; __chk_user_ptr(addr); asm volatile( // A + B <= C + 1 for all A,B,C, in four easy steps: // 1: X = A + B; X' = X % 2^64 - " adds %0, %0, %2\n" + " adds %0, %3, %2\n" // 2: Set C = 0 if X > 2^64, to guarantee X' > C in step 4 " csel %1, xzr, %1, hi\n" // 3: Set X' = ~0 if X >= 2^64. For X == 2^64, this decrements X' @@ -92,9 +92,9 @@ static inline unsigned long __range_ok(unsigned long addr, unsigned long size) // testing X' - C == 0, subject to the previous adjustments. " sbcs xzr, %0, %1\n" " cset %0, ls\n" - : "+r" (addr), "+r" (limit) : "Ir" (size) : "cc"); + : "=&r" (ret), "+r" (limit) : "Ir" (size), "0" (addr) : "cc"); - return addr; + return ret; } /* @@ -104,7 +104,7 @@ static inline unsigned long __range_ok(unsigned long addr, unsigned long size) */ #define untagged_addr(addr) sign_extend64(addr, 55) -#define access_ok(type, addr, size) __range_ok((unsigned long)(addr), size) +#define access_ok(type, addr, size) __range_ok(addr, size) #define user_addr_max get_fs #define _ASM_EXTABLE(from, to) \ diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c index c33b5e4010ab..68450e954d47 100644 --- a/arch/arm64/kernel/armv8_deprecated.c +++ b/arch/arm64/kernel/armv8_deprecated.c @@ -370,6 +370,7 @@ static unsigned int __kprobes aarch32_check_condition(u32 opcode, u32 psr) static int swp_handler(struct pt_regs *regs, u32 instr) { u32 destreg, data, type, address = 0; + const void __user *user_ptr; int rn, rt2, res = 0; perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, regs->pc); @@ -401,7 +402,8 @@ static int swp_handler(struct pt_regs *regs, u32 instr) aarch32_insn_extract_reg_num(instr, A32_RT2_OFFSET), data); /* Check access in reasonable access range for both SWP and SWPB */ - if (!access_ok(VERIFY_WRITE, (address & ~3), 4)) { + user_ptr = (const void __user *)(unsigned long)(address & ~3); + if (!access_ok(VERIFY_WRITE, user_ptr, 4)) { pr_debug("SWP{B} emulation: access to 0x%08x not allowed!\n", address); goto fault; diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 07823595b7f0..52f15cd896e1 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -408,6 +408,15 @@ const struct arm64_cpu_capabilities arm64_errata[] = { }, { .capability = ARM64_HARDEN_BRANCH_PREDICTOR, + MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR), + .enable = qcom_enable_link_stack_sanitization, + }, + { + .capability = ARM64_HARDEN_BP_POST_GUEST_EXIT, + MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR), + }, + { + .capability = ARM64_HARDEN_BRANCH_PREDICTOR, MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN), .enable = enable_smccc_arch_workaround_1, }, diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 29b1f873e337..2985a067fc13 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -199,9 +199,11 @@ static const struct arm64_ftr_bits ftr_id_aa64mmfr2[] = { }; static const struct arm64_ftr_bits ftr_ctr[] = { - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, 31, 1, 1), /* RAO */ + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, 31, 1, 1), /* RES1 */ + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 29, 1, 1), /* DIC */ + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 28, 1, 1), /* IDC */ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, 24, 4, 0), /* CWG */ - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0), /* ERG */ + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, 20, 4, 0), /* ERG */ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 1), /* DminLine */ /* * Linux can handle differing I-cache policies. Userspace JITs will diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index f85ac58d08a3..a8bf1c892b90 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -90,7 +90,7 @@ static int __init set_permissions(pte_t *ptep, pgtable_t token, unsigned long addr, void *data) { efi_memory_desc_t *md = data; - pte_t pte = *ptep; + pte_t pte = READ_ONCE(*ptep); if (md->attribute & EFI_MEMORY_RO) pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index f20cf7e99249..1ec5f28c39fc 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -202,10 +202,10 @@ static int create_safe_exec_page(void *src_start, size_t length, gfp_t mask) { int rc = 0; - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; + pgd_t *pgdp; + pud_t *pudp; + pmd_t *pmdp; + pte_t *ptep; unsigned long dst = (unsigned long)allocator(mask); if (!dst) { @@ -216,38 +216,38 @@ static int create_safe_exec_page(void *src_start, size_t length, memcpy((void *)dst, src_start, length); flush_icache_range(dst, dst + length); - pgd = pgd_offset_raw(allocator(mask), dst_addr); - if (pgd_none(*pgd)) { - pud = allocator(mask); - if (!pud) { + pgdp = pgd_offset_raw(allocator(mask), dst_addr); + if (pgd_none(READ_ONCE(*pgdp))) { + pudp = allocator(mask); + if (!pudp) { rc = -ENOMEM; goto out; } - pgd_populate(&init_mm, pgd, pud); + pgd_populate(&init_mm, pgdp, pudp); } - pud = pud_offset(pgd, dst_addr); - if (pud_none(*pud)) { - pmd = allocator(mask); - if (!pmd) { + pudp = pud_offset(pgdp, dst_addr); + if (pud_none(READ_ONCE(*pudp))) { + pmdp = allocator(mask); + if (!pmdp) { rc = -ENOMEM; goto out; } - pud_populate(&init_mm, pud, pmd); + pud_populate(&init_mm, pudp, pmdp); } - pmd = pmd_offset(pud, dst_addr); - if (pmd_none(*pmd)) { - pte = allocator(mask); - if (!pte) { + pmdp = pmd_offset(pudp, dst_addr); + if (pmd_none(READ_ONCE(*pmdp))) { + ptep = allocator(mask); + if (!ptep) { rc = -ENOMEM; goto out; } - pmd_populate_kernel(&init_mm, pmd, pte); + pmd_populate_kernel(&init_mm, pmdp, ptep); } - pte = pte_offset_kernel(pmd, dst_addr); - set_pte(pte, pfn_pte(virt_to_pfn(dst), PAGE_KERNEL_EXEC)); + ptep = pte_offset_kernel(pmdp, dst_addr); + set_pte(ptep, pfn_pte(virt_to_pfn(dst), PAGE_KERNEL_EXEC)); /* * Load our new page tables. A strict BBM approach requires that we @@ -263,7 +263,7 @@ static int create_safe_exec_page(void *src_start, size_t length, */ cpu_set_reserved_ttbr0(); local_flush_tlb_all(); - write_sysreg(phys_to_ttbr(virt_to_phys(pgd)), ttbr0_el1); + write_sysreg(phys_to_ttbr(virt_to_phys(pgdp)), ttbr0_el1); isb(); *phys_dst_addr = virt_to_phys((void *)dst); @@ -320,9 +320,9 @@ int swsusp_arch_suspend(void) return ret; } -static void _copy_pte(pte_t *dst_pte, pte_t *src_pte, unsigned long addr) +static void _copy_pte(pte_t *dst_ptep, pte_t *src_ptep, unsigned long addr) { - pte_t pte = *src_pte; + pte_t pte = READ_ONCE(*src_ptep); if (pte_valid(pte)) { /* @@ -330,7 +330,7 @@ static void _copy_pte(pte_t *dst_pte, pte_t *src_pte, unsigned long addr) * read only (code, rodata). Clear the RDONLY bit from * the temporary mappings we use during restore. */ - set_pte(dst_pte, pte_mkwrite(pte)); + set_pte(dst_ptep, pte_mkwrite(pte)); } else if (debug_pagealloc_enabled() && !pte_none(pte)) { /* * debug_pagealloc will removed the PTE_VALID bit if @@ -343,112 +343,116 @@ static void _copy_pte(pte_t *dst_pte, pte_t *src_pte, unsigned long addr) */ BUG_ON(!pfn_valid(pte_pfn(pte))); - set_pte(dst_pte, pte_mkpresent(pte_mkwrite(pte))); + set_pte(dst_ptep, pte_mkpresent(pte_mkwrite(pte))); } } -static int copy_pte(pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long start, +static int copy_pte(pmd_t *dst_pmdp, pmd_t *src_pmdp, unsigned long start, unsigned long end) { - pte_t *src_pte; - pte_t *dst_pte; + pte_t *src_ptep; + pte_t *dst_ptep; unsigned long addr = start; - dst_pte = (pte_t *)get_safe_page(GFP_ATOMIC); - if (!dst_pte) + dst_ptep = (pte_t *)get_safe_page(GFP_ATOMIC); + if (!dst_ptep) return -ENOMEM; - pmd_populate_kernel(&init_mm, dst_pmd, dst_pte); - dst_pte = pte_offset_kernel(dst_pmd, start); + pmd_populate_kernel(&init_mm, dst_pmdp, dst_ptep); + dst_ptep = pte_offset_kernel(dst_pmdp, start); - src_pte = pte_offset_kernel(src_pmd, start); + src_ptep = pte_offset_kernel(src_pmdp, start); do { - _copy_pte(dst_pte, src_pte, addr); - } while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end); + _copy_pte(dst_ptep, src_ptep, addr); + } while (dst_ptep++, src_ptep++, addr += PAGE_SIZE, addr != end); return 0; } -static int copy_pmd(pud_t *dst_pud, pud_t *src_pud, unsigned long start, +static int copy_pmd(pud_t *dst_pudp, pud_t *src_pudp, unsigned long start, unsigned long end) { - pmd_t *src_pmd; - pmd_t *dst_pmd; + pmd_t *src_pmdp; + pmd_t *dst_pmdp; unsigned long next; unsigned long addr = start; - if (pud_none(*dst_pud)) { - dst_pmd = (pmd_t *)get_safe_page(GFP_ATOMIC); - if (!dst_pmd) + if (pud_none(READ_ONCE(*dst_pudp))) { + dst_pmdp = (pmd_t *)get_safe_page(GFP_ATOMIC); + if (!dst_pmdp) return -ENOMEM; - pud_populate(&init_mm, dst_pud, dst_pmd); + pud_populate(&init_mm, dst_pudp, dst_pmdp); } - dst_pmd = pmd_offset(dst_pud, start); + dst_pmdp = pmd_offset(dst_pudp, start); - src_pmd = pmd_offset(src_pud, start); + src_pmdp = pmd_offset(src_pudp, start); do { + pmd_t pmd = READ_ONCE(*src_pmdp); + next = pmd_addr_end(addr, end); - if (pmd_none(*src_pmd)) + if (pmd_none(pmd)) continue; - if (pmd_table(*src_pmd)) { - if (copy_pte(dst_pmd, src_pmd, addr, next)) + if (pmd_table(pmd)) { + if (copy_pte(dst_pmdp, src_pmdp, addr, next)) return -ENOMEM; } else { - set_pmd(dst_pmd, - __pmd(pmd_val(*src_pmd) & ~PMD_SECT_RDONLY)); + set_pmd(dst_pmdp, + __pmd(pmd_val(pmd) & ~PMD_SECT_RDONLY)); } - } while (dst_pmd++, src_pmd++, addr = next, addr != end); + } while (dst_pmdp++, src_pmdp++, addr = next, addr != end); return 0; } -static int copy_pud(pgd_t *dst_pgd, pgd_t *src_pgd, unsigned long start, +static int copy_pud(pgd_t *dst_pgdp, pgd_t *src_pgdp, unsigned long start, unsigned long end) { - pud_t *dst_pud; - pud_t *src_pud; + pud_t *dst_pudp; + pud_t *src_pudp; unsigned long next; unsigned long addr = start; - if (pgd_none(*dst_pgd)) { - dst_pud = (pud_t *)get_safe_page(GFP_ATOMIC); - if (!dst_pud) + if (pgd_none(READ_ONCE(*dst_pgdp))) { + dst_pudp = (pud_t *)get_safe_page(GFP_ATOMIC); + if (!dst_pudp) return -ENOMEM; - pgd_populate(&init_mm, dst_pgd, dst_pud); + pgd_populate(&init_mm, dst_pgdp, dst_pudp); } - dst_pud = pud_offset(dst_pgd, start); + dst_pudp = pud_offset(dst_pgdp, start); - src_pud = pud_offset(src_pgd, start); + src_pudp = pud_offset(src_pgdp, start); do { + pud_t pud = READ_ONCE(*src_pudp); + next = pud_addr_end(addr, end); - if (pud_none(*src_pud)) + if (pud_none(pud)) continue; - if (pud_table(*(src_pud))) { - if (copy_pmd(dst_pud, src_pud, addr, next)) + if (pud_table(pud)) { + if (copy_pmd(dst_pudp, src_pudp, addr, next)) return -ENOMEM; } else { - set_pud(dst_pud, - __pud(pud_val(*src_pud) & ~PMD_SECT_RDONLY)); + set_pud(dst_pudp, + __pud(pud_val(pud) & ~PMD_SECT_RDONLY)); } - } while (dst_pud++, src_pud++, addr = next, addr != end); + } while (dst_pudp++, src_pudp++, addr = next, addr != end); return 0; } -static int copy_page_tables(pgd_t *dst_pgd, unsigned long start, +static int copy_page_tables(pgd_t *dst_pgdp, unsigned long start, unsigned long end) { unsigned long next; unsigned long addr = start; - pgd_t *src_pgd = pgd_offset_k(start); + pgd_t *src_pgdp = pgd_offset_k(start); - dst_pgd = pgd_offset_raw(dst_pgd, start); + dst_pgdp = pgd_offset_raw(dst_pgdp, start); do { next = pgd_addr_end(addr, end); - if (pgd_none(*src_pgd)) + if (pgd_none(READ_ONCE(*src_pgdp))) continue; - if (copy_pud(dst_pgd, src_pgd, addr, next)) + if (copy_pud(dst_pgdp, src_pgdp, addr, next)) return -ENOMEM; - } while (dst_pgd++, src_pgd++, addr = next, addr != end); + } while (dst_pgdp++, src_pgdp++, addr = next, addr != end); return 0; } diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 75b220ba73a3..85a251b6dfa8 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -908,9 +908,9 @@ static void __armv8pmu_probe_pmu(void *info) int pmuver; dfr0 = read_sysreg(id_aa64dfr0_el1); - pmuver = cpuid_feature_extract_signed_field(dfr0, + pmuver = cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_PMUVER_SHIFT); - if (pmuver < 1) + if (pmuver == 0xf || pmuver == 0) return; probe->present = true; diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index ad8aeb098b31..c0da6efe5465 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -220,8 +220,15 @@ void __show_regs(struct pt_regs *regs) show_regs_print_info(KERN_DEFAULT); print_pstate(regs); - printk("pc : %pS\n", (void *)regs->pc); - printk("lr : %pS\n", (void *)lr); + + if (!user_mode(regs)) { + printk("pc : %pS\n", (void *)regs->pc); + printk("lr : %pS\n", (void *)lr); + } else { + printk("pc : %016llx\n", regs->pc); + printk("lr : %016llx\n", lr); + } + printk("sp : %016llx\n", sp); i = top_reg; diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index 76809ccd309c..d5718a060672 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -59,6 +59,11 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) #ifdef CONFIG_FUNCTION_GRAPH_TRACER if (tsk->ret_stack && (frame->pc == (unsigned long)return_to_handler)) { + if (WARN_ON_ONCE(frame->graph == -1)) + return -EINVAL; + if (frame->graph < -1) + frame->graph += FTRACE_NOTRACE_DEPTH; + /* * This is a case where function graph tracer has * modified a return address (LR) in a stack frame diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c index 8b8bbd3eaa52..a382b2a1b84e 100644 --- a/arch/arm64/kernel/sys_compat.c +++ b/arch/arm64/kernel/sys_compat.c @@ -57,7 +57,7 @@ do_compat_cache_op(unsigned long start, unsigned long end, int flags) if (end < start || flags) return -EINVAL; - if (!access_ok(VERIFY_READ, start, end - start)) + if (!access_ok(VERIFY_READ, (const void __user *)start, end - start)) return -EFAULT; return __do_compat_cache_op(start, end); diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c index a4391280fba9..f258636273c9 100644 --- a/arch/arm64/kernel/time.c +++ b/arch/arm64/kernel/time.c @@ -52,7 +52,7 @@ unsigned long profile_pc(struct pt_regs *regs) frame.fp = regs->regs[29]; frame.pc = regs->pc; #ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame.graph = -1; /* no task info */ + frame.graph = current->curr_ret_stack; #endif do { int ret = unwind_frame(NULL, &frame); diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index bbb0fde2780e..eb2d15147e8d 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -57,7 +57,7 @@ static const char *handler[]= { "Error" }; -int show_unhandled_signals = 1; +int show_unhandled_signals = 0; static void dump_backtrace_entry(unsigned long where) { @@ -526,14 +526,6 @@ asmlinkage long do_ni_syscall(struct pt_regs *regs) } #endif - if (show_unhandled_signals_ratelimited()) { - pr_info("%s[%d]: syscall %d\n", current->comm, - task_pid_nr(current), regs->syscallno); - dump_instr("", regs); - if (user_mode(regs)) - __show_regs(regs); - } - return sys_ni_syscall(); } diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index 116252a8d3a5..870f4b1587f9 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -407,8 +407,10 @@ again: u32 midr = read_cpuid_id(); /* Apply BTAC predictors mitigation to all Falkor chips */ - if ((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR_V1) + if (((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR) || + ((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR_V1)) { __qcom_hyp_sanitize_btac_predictors(); + } } fp_enabled = __fpsimd_enabled(); diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c index 7b60d62ac593..65dfc8571bf8 100644 --- a/arch/arm64/mm/dump.c +++ b/arch/arm64/mm/dump.c @@ -286,48 +286,52 @@ static void note_page(struct pg_state *st, unsigned long addr, unsigned level, } -static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start) +static void walk_pte(struct pg_state *st, pmd_t *pmdp, unsigned long start) { - pte_t *pte = pte_offset_kernel(pmd, 0UL); + pte_t *ptep = pte_offset_kernel(pmdp, 0UL); unsigned long addr; unsigned i; - for (i = 0; i < PTRS_PER_PTE; i++, pte++) { + for (i = 0; i < PTRS_PER_PTE; i++, ptep++) { addr = start + i * PAGE_SIZE; - note_page(st, addr, 4, pte_val(*pte)); + note_page(st, addr, 4, READ_ONCE(pte_val(*ptep))); } } -static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start) +static void walk_pmd(struct pg_state *st, pud_t *pudp, unsigned long start) { - pmd_t *pmd = pmd_offset(pud, 0UL); + pmd_t *pmdp = pmd_offset(pudp, 0UL); unsigned long addr; unsigned i; - for (i = 0; i < PTRS_PER_PMD; i++, pmd++) { + for (i = 0; i < PTRS_PER_PMD; i++, pmdp++) { + pmd_t pmd = READ_ONCE(*pmdp); + addr = start + i * PMD_SIZE; - if (pmd_none(*pmd) || pmd_sect(*pmd)) { - note_page(st, addr, 3, pmd_val(*pmd)); + if (pmd_none(pmd) || pmd_sect(pmd)) { + note_page(st, addr, 3, pmd_val(pmd)); } else { - BUG_ON(pmd_bad(*pmd)); - walk_pte(st, pmd, addr); + BUG_ON(pmd_bad(pmd)); + walk_pte(st, pmdp, addr); } } } -static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start) +static void walk_pud(struct pg_state *st, pgd_t *pgdp, unsigned long start) { - pud_t *pud = pud_offset(pgd, 0UL); + pud_t *pudp = pud_offset(pgdp, 0UL); unsigned long addr; unsigned i; - for (i = 0; i < PTRS_PER_PUD; i++, pud++) { + for (i = 0; i < PTRS_PER_PUD; i++, pudp++) { + pud_t pud = READ_ONCE(*pudp); + addr = start + i * PUD_SIZE; - if (pud_none(*pud) || pud_sect(*pud)) { - note_page(st, addr, 2, pud_val(*pud)); + if (pud_none(pud) || pud_sect(pud)) { + note_page(st, addr, 2, pud_val(pud)); } else { - BUG_ON(pud_bad(*pud)); - walk_pmd(st, pud, addr); + BUG_ON(pud_bad(pud)); + walk_pmd(st, pudp, addr); } } } @@ -335,17 +339,19 @@ static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start) static void walk_pgd(struct pg_state *st, struct mm_struct *mm, unsigned long start) { - pgd_t *pgd = pgd_offset(mm, 0UL); + pgd_t *pgdp = pgd_offset(mm, 0UL); unsigned i; unsigned long addr; - for (i = 0; i < PTRS_PER_PGD; i++, pgd++) { + for (i = 0; i < PTRS_PER_PGD; i++, pgdp++) { + pgd_t pgd = READ_ONCE(*pgdp); + addr = start + i * PGDIR_SIZE; - if (pgd_none(*pgd)) { - note_page(st, addr, 1, pgd_val(*pgd)); + if (pgd_none(pgd)) { + note_page(st, addr, 1, pgd_val(pgd)); } else { - BUG_ON(pgd_bad(*pgd)); - walk_pud(st, pgd, addr); + BUG_ON(pgd_bad(pgd)); + walk_pud(st, pgdp, addr); } } } diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index f76bb2c3c943..bff11553eb05 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -130,7 +130,8 @@ static void mem_abort_decode(unsigned int esr) void show_pte(unsigned long addr) { struct mm_struct *mm; - pgd_t *pgd; + pgd_t *pgdp; + pgd_t pgd; if (addr < TASK_SIZE) { /* TTBR0 */ @@ -149,33 +150,37 @@ void show_pte(unsigned long addr) return; } - pr_alert("%s pgtable: %luk pages, %u-bit VAs, pgd = %p\n", + pr_alert("%s pgtable: %luk pages, %u-bit VAs, pgdp = %p\n", mm == &init_mm ? "swapper" : "user", PAGE_SIZE / SZ_1K, VA_BITS, mm->pgd); - pgd = pgd_offset(mm, addr); - pr_alert("[%016lx] *pgd=%016llx", addr, pgd_val(*pgd)); + pgdp = pgd_offset(mm, addr); + pgd = READ_ONCE(*pgdp); + pr_alert("[%016lx] pgd=%016llx", addr, pgd_val(pgd)); do { - pud_t *pud; - pmd_t *pmd; - pte_t *pte; + pud_t *pudp, pud; + pmd_t *pmdp, pmd; + pte_t *ptep, pte; - if (pgd_none(*pgd) || pgd_bad(*pgd)) + if (pgd_none(pgd) || pgd_bad(pgd)) break; - pud = pud_offset(pgd, addr); - pr_cont(", *pud=%016llx", pud_val(*pud)); - if (pud_none(*pud) || pud_bad(*pud)) + pudp = pud_offset(pgdp, addr); + pud = READ_ONCE(*pudp); + pr_cont(", pud=%016llx", pud_val(pud)); + if (pud_none(pud) || pud_bad(pud)) break; - pmd = pmd_offset(pud, addr); - pr_cont(", *pmd=%016llx", pmd_val(*pmd)); - if (pmd_none(*pmd) || pmd_bad(*pmd)) + pmdp = pmd_offset(pudp, addr); + pmd = READ_ONCE(*pmdp); + pr_cont(", pmd=%016llx", pmd_val(pmd)); + if (pmd_none(pmd) || pmd_bad(pmd)) break; - pte = pte_offset_map(pmd, addr); - pr_cont(", *pte=%016llx", pte_val(*pte)); - pte_unmap(pte); + ptep = pte_offset_map(pmdp, addr); + pte = READ_ONCE(*ptep); + pr_cont(", pte=%016llx", pte_val(pte)); + pte_unmap(ptep); } while(0); pr_cont("\n"); @@ -196,8 +201,9 @@ int ptep_set_access_flags(struct vm_area_struct *vma, pte_t entry, int dirty) { pteval_t old_pteval, pteval; + pte_t pte = READ_ONCE(*ptep); - if (pte_same(*ptep, entry)) + if (pte_same(pte, entry)) return 0; /* only preserve the access flags and write permission */ @@ -210,7 +216,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma, * (calculated as: a & b == ~(~a | ~b)). */ pte_val(entry) ^= PTE_RDONLY; - pteval = READ_ONCE(pte_val(*ptep)); + pteval = pte_val(pte); do { old_pteval = pteval; pteval ^= PTE_RDONLY; diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 6cb0fa92a651..ecc6818191df 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -54,14 +54,14 @@ static inline pgprot_t pte_pgprot(pte_t pte) static int find_num_contig(struct mm_struct *mm, unsigned long addr, pte_t *ptep, size_t *pgsize) { - pgd_t *pgd = pgd_offset(mm, addr); - pud_t *pud; - pmd_t *pmd; + pgd_t *pgdp = pgd_offset(mm, addr); + pud_t *pudp; + pmd_t *pmdp; *pgsize = PAGE_SIZE; - pud = pud_offset(pgd, addr); - pmd = pmd_offset(pud, addr); - if ((pte_t *)pmd == ptep) { + pudp = pud_offset(pgdp, addr); + pmdp = pmd_offset(pudp, addr); + if ((pte_t *)pmdp == ptep) { *pgsize = PMD_SIZE; return CONT_PMDS; } @@ -181,11 +181,8 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, clear_flush(mm, addr, ptep, pgsize, ncontig); - for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) { - pr_debug("%s: set pte %p to 0x%llx\n", __func__, ptep, - pte_val(pfn_pte(pfn, hugeprot))); + for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot)); - } } void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr, @@ -203,20 +200,20 @@ void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz) { - pgd_t *pgd; - pud_t *pud; - pte_t *pte = NULL; - - pr_debug("%s: addr:0x%lx sz:0x%lx\n", __func__, addr, sz); - pgd = pgd_offset(mm, addr); - pud = pud_alloc(mm, pgd, addr); - if (!pud) + pgd_t *pgdp; + pud_t *pudp; + pmd_t *pmdp; + pte_t *ptep = NULL; + + pgdp = pgd_offset(mm, addr); + pudp = pud_alloc(mm, pgdp, addr); + if (!pudp) return NULL; if (sz == PUD_SIZE) { - pte = (pte_t *)pud; + ptep = (pte_t *)pudp; } else if (sz == (PAGE_SIZE * CONT_PTES)) { - pmd_t *pmd = pmd_alloc(mm, pud, addr); + pmdp = pmd_alloc(mm, pudp, addr); WARN_ON(addr & (sz - 1)); /* @@ -226,60 +223,55 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, * will be no pte_unmap() to correspond with this * pte_alloc_map(). */ - pte = pte_alloc_map(mm, pmd, addr); + ptep = pte_alloc_map(mm, pmdp, addr); } else if (sz == PMD_SIZE) { if (IS_ENABLED(CONFIG_ARCH_WANT_HUGE_PMD_SHARE) && - pud_none(*pud)) - pte = huge_pmd_share(mm, addr, pud); + pud_none(READ_ONCE(*pudp))) + ptep = huge_pmd_share(mm, addr, pudp); else - pte = (pte_t *)pmd_alloc(mm, pud, addr); + ptep = (pte_t *)pmd_alloc(mm, pudp, addr); } else if (sz == (PMD_SIZE * CONT_PMDS)) { - pmd_t *pmd; - - pmd = pmd_alloc(mm, pud, addr); + pmdp = pmd_alloc(mm, pudp, addr); WARN_ON(addr & (sz - 1)); - return (pte_t *)pmd; + return (pte_t *)pmdp; } - pr_debug("%s: addr:0x%lx sz:0x%lx ret pte=%p/0x%llx\n", __func__, addr, - sz, pte, pte_val(*pte)); - return pte; + return ptep; } pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) { - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; + pgd_t *pgdp; + pud_t *pudp, pud; + pmd_t *pmdp, pmd; - pgd = pgd_offset(mm, addr); - pr_debug("%s: addr:0x%lx pgd:%p\n", __func__, addr, pgd); - if (!pgd_present(*pgd)) + pgdp = pgd_offset(mm, addr); + if (!pgd_present(READ_ONCE(*pgdp))) return NULL; - pud = pud_offset(pgd, addr); - if (sz != PUD_SIZE && pud_none(*pud)) + pudp = pud_offset(pgdp, addr); + pud = READ_ONCE(*pudp); + if (sz != PUD_SIZE && pud_none(pud)) return NULL; /* hugepage or swap? */ - if (pud_huge(*pud) || !pud_present(*pud)) - return (pte_t *)pud; + if (pud_huge(pud) || !pud_present(pud)) + return (pte_t *)pudp; /* table; check the next level */ if (sz == CONT_PMD_SIZE) addr &= CONT_PMD_MASK; - pmd = pmd_offset(pud, addr); + pmdp = pmd_offset(pudp, addr); + pmd = READ_ONCE(*pmdp); if (!(sz == PMD_SIZE || sz == CONT_PMD_SIZE) && - pmd_none(*pmd)) + pmd_none(pmd)) return NULL; - if (pmd_huge(*pmd) || !pmd_present(*pmd)) - return (pte_t *)pmd; + if (pmd_huge(pmd) || !pmd_present(pmd)) + return (pte_t *)pmdp; - if (sz == CONT_PTE_SIZE) { - pte_t *pte = pte_offset_kernel(pmd, (addr & CONT_PTE_MASK)); - return pte; - } + if (sz == CONT_PTE_SIZE) + return pte_offset_kernel(pmdp, (addr & CONT_PTE_MASK)); return NULL; } @@ -367,7 +359,7 @@ void huge_ptep_set_wrprotect(struct mm_struct *mm, size_t pgsize; pte_t pte; - if (!pte_cont(*ptep)) { + if (!pte_cont(READ_ONCE(*ptep))) { ptep_set_wrprotect(mm, addr, ptep); return; } @@ -391,7 +383,7 @@ void huge_ptep_clear_flush(struct vm_area_struct *vma, size_t pgsize; int ncontig; - if (!pte_cont(*ptep)) { + if (!pte_cont(READ_ONCE(*ptep))) { ptep_clear_flush(vma, addr, ptep); return; } diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index 6e02e6fb4c7b..dabfc1ecda3d 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -44,92 +44,92 @@ static phys_addr_t __init kasan_alloc_zeroed_page(int node) return __pa(p); } -static pte_t *__init kasan_pte_offset(pmd_t *pmd, unsigned long addr, int node, +static pte_t *__init kasan_pte_offset(pmd_t *pmdp, unsigned long addr, int node, bool early) { - if (pmd_none(*pmd)) { + if (pmd_none(READ_ONCE(*pmdp))) { phys_addr_t pte_phys = early ? __pa_symbol(kasan_zero_pte) : kasan_alloc_zeroed_page(node); - __pmd_populate(pmd, pte_phys, PMD_TYPE_TABLE); + __pmd_populate(pmdp, pte_phys, PMD_TYPE_TABLE); } - return early ? pte_offset_kimg(pmd, addr) - : pte_offset_kernel(pmd, addr); + return early ? pte_offset_kimg(pmdp, addr) + : pte_offset_kernel(pmdp, addr); } -static pmd_t *__init kasan_pmd_offset(pud_t *pud, unsigned long addr, int node, +static pmd_t *__init kasan_pmd_offset(pud_t *pudp, unsigned long addr, int node, bool early) { - if (pud_none(*pud)) { + if (pud_none(READ_ONCE(*pudp))) { phys_addr_t pmd_phys = early ? __pa_symbol(kasan_zero_pmd) : kasan_alloc_zeroed_page(node); - __pud_populate(pud, pmd_phys, PMD_TYPE_TABLE); + __pud_populate(pudp, pmd_phys, PMD_TYPE_TABLE); } - return early ? pmd_offset_kimg(pud, addr) : pmd_offset(pud, addr); + return early ? pmd_offset_kimg(pudp, addr) : pmd_offset(pudp, addr); } -static pud_t *__init kasan_pud_offset(pgd_t *pgd, unsigned long addr, int node, +static pud_t *__init kasan_pud_offset(pgd_t *pgdp, unsigned long addr, int node, bool early) { - if (pgd_none(*pgd)) { + if (pgd_none(READ_ONCE(*pgdp))) { phys_addr_t pud_phys = early ? __pa_symbol(kasan_zero_pud) : kasan_alloc_zeroed_page(node); - __pgd_populate(pgd, pud_phys, PMD_TYPE_TABLE); + __pgd_populate(pgdp, pud_phys, PMD_TYPE_TABLE); } - return early ? pud_offset_kimg(pgd, addr) : pud_offset(pgd, addr); + return early ? pud_offset_kimg(pgdp, addr) : pud_offset(pgdp, addr); } -static void __init kasan_pte_populate(pmd_t *pmd, unsigned long addr, +static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr, unsigned long end, int node, bool early) { unsigned long next; - pte_t *pte = kasan_pte_offset(pmd, addr, node, early); + pte_t *ptep = kasan_pte_offset(pmdp, addr, node, early); do { phys_addr_t page_phys = early ? __pa_symbol(kasan_zero_page) : kasan_alloc_zeroed_page(node); next = addr + PAGE_SIZE; - set_pte(pte, pfn_pte(__phys_to_pfn(page_phys), PAGE_KERNEL)); - } while (pte++, addr = next, addr != end && pte_none(*pte)); + set_pte(ptep, pfn_pte(__phys_to_pfn(page_phys), PAGE_KERNEL)); + } while (ptep++, addr = next, addr != end && pte_none(READ_ONCE(*ptep))); } -static void __init kasan_pmd_populate(pud_t *pud, unsigned long addr, +static void __init kasan_pmd_populate(pud_t *pudp, unsigned long addr, unsigned long end, int node, bool early) { unsigned long next; - pmd_t *pmd = kasan_pmd_offset(pud, addr, node, early); + pmd_t *pmdp = kasan_pmd_offset(pudp, addr, node, early); do { next = pmd_addr_end(addr, end); - kasan_pte_populate(pmd, addr, next, node, early); - } while (pmd++, addr = next, addr != end && pmd_none(*pmd)); + kasan_pte_populate(pmdp, addr, next, node, early); + } while (pmdp++, addr = next, addr != end && pmd_none(READ_ONCE(*pmdp))); } -static void __init kasan_pud_populate(pgd_t *pgd, unsigned long addr, +static void __init kasan_pud_populate(pgd_t *pgdp, unsigned long addr, unsigned long end, int node, bool early) { unsigned long next; - pud_t *pud = kasan_pud_offset(pgd, addr, node, early); + pud_t *pudp = kasan_pud_offset(pgdp, addr, node, early); do { next = pud_addr_end(addr, end); - kasan_pmd_populate(pud, addr, next, node, early); - } while (pud++, addr = next, addr != end && pud_none(*pud)); + kasan_pmd_populate(pudp, addr, next, node, early); + } while (pudp++, addr = next, addr != end && pud_none(READ_ONCE(*pudp))); } static void __init kasan_pgd_populate(unsigned long addr, unsigned long end, int node, bool early) { unsigned long next; - pgd_t *pgd; + pgd_t *pgdp; - pgd = pgd_offset_k(addr); + pgdp = pgd_offset_k(addr); do { next = pgd_addr_end(addr, end); - kasan_pud_populate(pgd, addr, next, node, early); - } while (pgd++, addr = next, addr != end); + kasan_pud_populate(pgdp, addr, next, node, early); + } while (pgdp++, addr = next, addr != end); } /* The early shadow maps everything to a single page of zeroes */ @@ -155,14 +155,14 @@ static void __init kasan_map_populate(unsigned long start, unsigned long end, */ void __init kasan_copy_shadow(pgd_t *pgdir) { - pgd_t *pgd, *pgd_new, *pgd_end; + pgd_t *pgdp, *pgdp_new, *pgdp_end; - pgd = pgd_offset_k(KASAN_SHADOW_START); - pgd_end = pgd_offset_k(KASAN_SHADOW_END); - pgd_new = pgd_offset_raw(pgdir, KASAN_SHADOW_START); + pgdp = pgd_offset_k(KASAN_SHADOW_START); + pgdp_end = pgd_offset_k(KASAN_SHADOW_END); + pgdp_new = pgd_offset_raw(pgdir, KASAN_SHADOW_START); do { - set_pgd(pgd_new, *pgd); - } while (pgd++, pgd_new++, pgd != pgd_end); + set_pgd(pgdp_new, READ_ONCE(*pgdp)); + } while (pgdp++, pgdp_new++, pgdp != pgdp_end); } static void __init clear_pgds(unsigned long start, diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 4694cda823c9..84a019f55022 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -125,45 +125,48 @@ static bool pgattr_change_is_safe(u64 old, u64 new) return ((old ^ new) & ~mask) == 0; } -static void init_pte(pmd_t *pmd, unsigned long addr, unsigned long end, +static void init_pte(pmd_t *pmdp, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot) { - pte_t *pte; + pte_t *ptep; - pte = pte_set_fixmap_offset(pmd, addr); + ptep = pte_set_fixmap_offset(pmdp, addr); do { - pte_t old_pte = *pte; + pte_t old_pte = READ_ONCE(*ptep); - set_pte(pte, pfn_pte(__phys_to_pfn(phys), prot)); + set_pte(ptep, pfn_pte(__phys_to_pfn(phys), prot)); /* * After the PTE entry has been populated once, we * only allow updates to the permission attributes. */ - BUG_ON(!pgattr_change_is_safe(pte_val(old_pte), pte_val(*pte))); + BUG_ON(!pgattr_change_is_safe(pte_val(old_pte), + READ_ONCE(pte_val(*ptep)))); phys += PAGE_SIZE; - } while (pte++, addr += PAGE_SIZE, addr != end); + } while (ptep++, addr += PAGE_SIZE, addr != end); pte_clear_fixmap(); } -static void alloc_init_cont_pte(pmd_t *pmd, unsigned long addr, +static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot, phys_addr_t (*pgtable_alloc)(void), int flags) { unsigned long next; + pmd_t pmd = READ_ONCE(*pmdp); - BUG_ON(pmd_sect(*pmd)); - if (pmd_none(*pmd)) { + BUG_ON(pmd_sect(pmd)); + if (pmd_none(pmd)) { phys_addr_t pte_phys; BUG_ON(!pgtable_alloc); pte_phys = pgtable_alloc(); - __pmd_populate(pmd, pte_phys, PMD_TYPE_TABLE); + __pmd_populate(pmdp, pte_phys, PMD_TYPE_TABLE); + pmd = READ_ONCE(*pmdp); } - BUG_ON(pmd_bad(*pmd)); + BUG_ON(pmd_bad(pmd)); do { pgprot_t __prot = prot; @@ -175,67 +178,69 @@ static void alloc_init_cont_pte(pmd_t *pmd, unsigned long addr, (flags & NO_CONT_MAPPINGS) == 0) __prot = __pgprot(pgprot_val(prot) | PTE_CONT); - init_pte(pmd, addr, next, phys, __prot); + init_pte(pmdp, addr, next, phys, __prot); phys += next - addr; } while (addr = next, addr != end); } -static void init_pmd(pud_t *pud, unsigned long addr, unsigned long end, +static void init_pmd(pud_t *pudp, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot, phys_addr_t (*pgtable_alloc)(void), int flags) { unsigned long next; - pmd_t *pmd; + pmd_t *pmdp; - pmd = pmd_set_fixmap_offset(pud, addr); + pmdp = pmd_set_fixmap_offset(pudp, addr); do { - pmd_t old_pmd = *pmd; + pmd_t old_pmd = READ_ONCE(*pmdp); next = pmd_addr_end(addr, end); /* try section mapping first */ if (((addr | next | phys) & ~SECTION_MASK) == 0 && (flags & NO_BLOCK_MAPPINGS) == 0) { - pmd_set_huge(pmd, phys, prot); + pmd_set_huge(pmdp, phys, prot); /* * After the PMD entry has been populated once, we * only allow updates to the permission attributes. */ BUG_ON(!pgattr_change_is_safe(pmd_val(old_pmd), - pmd_val(*pmd))); + READ_ONCE(pmd_val(*pmdp)))); } else { - alloc_init_cont_pte(pmd, addr, next, phys, prot, + alloc_init_cont_pte(pmdp, addr, next, phys, prot, pgtable_alloc, flags); BUG_ON(pmd_val(old_pmd) != 0 && - pmd_val(old_pmd) != pmd_val(*pmd)); + pmd_val(old_pmd) != READ_ONCE(pmd_val(*pmdp))); } phys += next - addr; - } while (pmd++, addr = next, addr != end); + } while (pmdp++, addr = next, addr != end); pmd_clear_fixmap(); } -static void alloc_init_cont_pmd(pud_t *pud, unsigned long addr, +static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot, phys_addr_t (*pgtable_alloc)(void), int flags) { unsigned long next; + pud_t pud = READ_ONCE(*pudp); /* * Check for initial section mappings in the pgd/pud. */ - BUG_ON(pud_sect(*pud)); - if (pud_none(*pud)) { + BUG_ON(pud_sect(pud)); + if (pud_none(pud)) { phys_addr_t pmd_phys; BUG_ON(!pgtable_alloc); pmd_phys = pgtable_alloc(); - __pud_populate(pud, pmd_phys, PUD_TYPE_TABLE); + __pud_populate(pudp, pmd_phys, PUD_TYPE_TABLE); + pud = READ_ONCE(*pudp); } - BUG_ON(pud_bad(*pud)); + BUG_ON(pud_bad(pud)); do { pgprot_t __prot = prot; @@ -247,7 +252,7 @@ static void alloc_init_cont_pmd(pud_t *pud, unsigned long addr, (flags & NO_CONT_MAPPINGS) == 0) __prot = __pgprot(pgprot_val(prot) | PTE_CONT); - init_pmd(pud, addr, next, phys, __prot, pgtable_alloc, flags); + init_pmd(pudp, addr, next, phys, __prot, pgtable_alloc, flags); phys += next - addr; } while (addr = next, addr != end); @@ -265,25 +270,27 @@ static inline bool use_1G_block(unsigned long addr, unsigned long next, return true; } -static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end, - phys_addr_t phys, pgprot_t prot, - phys_addr_t (*pgtable_alloc)(void), - int flags) +static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end, + phys_addr_t phys, pgprot_t prot, + phys_addr_t (*pgtable_alloc)(void), + int flags) { - pud_t *pud; unsigned long next; + pud_t *pudp; + pgd_t pgd = READ_ONCE(*pgdp); - if (pgd_none(*pgd)) { + if (pgd_none(pgd)) { phys_addr_t pud_phys; BUG_ON(!pgtable_alloc); pud_phys = pgtable_alloc(); - __pgd_populate(pgd, pud_phys, PUD_TYPE_TABLE); + __pgd_populate(pgdp, pud_phys, PUD_TYPE_TABLE); + pgd = READ_ONCE(*pgdp); } - BUG_ON(pgd_bad(*pgd)); + BUG_ON(pgd_bad(pgd)); - pud = pud_set_fixmap_offset(pgd, addr); + pudp = pud_set_fixmap_offset(pgdp, addr); do { - pud_t old_pud = *pud; + pud_t old_pud = READ_ONCE(*pudp); next = pud_addr_end(addr, end); @@ -292,23 +299,23 @@ static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end, */ if (use_1G_block(addr, next, phys) && (flags & NO_BLOCK_MAPPINGS) == 0) { - pud_set_huge(pud, phys, prot); + pud_set_huge(pudp, phys, prot); /* * After the PUD entry has been populated once, we * only allow updates to the permission attributes. */ BUG_ON(!pgattr_change_is_safe(pud_val(old_pud), - pud_val(*pud))); + READ_ONCE(pud_val(*pudp)))); } else { - alloc_init_cont_pmd(pud, addr, next, phys, prot, + alloc_init_cont_pmd(pudp, addr, next, phys, prot, pgtable_alloc, flags); BUG_ON(pud_val(old_pud) != 0 && - pud_val(old_pud) != pud_val(*pud)); + pud_val(old_pud) != READ_ONCE(pud_val(*pudp))); } phys += next - addr; - } while (pud++, addr = next, addr != end); + } while (pudp++, addr = next, addr != end); pud_clear_fixmap(); } @@ -320,7 +327,7 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, int flags) { unsigned long addr, length, end, next; - pgd_t *pgd = pgd_offset_raw(pgdir, virt); + pgd_t *pgdp = pgd_offset_raw(pgdir, virt); /* * If the virtual and physical address don't have the same offset @@ -336,10 +343,10 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, end = addr + length; do { next = pgd_addr_end(addr, end); - alloc_init_pud(pgd, addr, next, phys, prot, pgtable_alloc, + alloc_init_pud(pgdp, addr, next, phys, prot, pgtable_alloc, flags); phys += next - addr; - } while (pgd++, addr = next, addr != end); + } while (pgdp++, addr = next, addr != end); } static phys_addr_t pgd_pgtable_alloc(void) @@ -401,10 +408,10 @@ static void update_mapping_prot(phys_addr_t phys, unsigned long virt, flush_tlb_kernel_range(virt, virt + size); } -static void __init __map_memblock(pgd_t *pgd, phys_addr_t start, +static void __init __map_memblock(pgd_t *pgdp, phys_addr_t start, phys_addr_t end, pgprot_t prot, int flags) { - __create_pgd_mapping(pgd, start, __phys_to_virt(start), end - start, + __create_pgd_mapping(pgdp, start, __phys_to_virt(start), end - start, prot, early_pgtable_alloc, flags); } @@ -418,7 +425,7 @@ void __init mark_linear_text_alias_ro(void) PAGE_KERNEL_RO); } -static void __init map_mem(pgd_t *pgd) +static void __init map_mem(pgd_t *pgdp) { phys_addr_t kernel_start = __pa_symbol(_text); phys_addr_t kernel_end = __pa_symbol(__init_begin); @@ -451,7 +458,7 @@ static void __init map_mem(pgd_t *pgd) if (memblock_is_nomap(reg)) continue; - __map_memblock(pgd, start, end, PAGE_KERNEL, flags); + __map_memblock(pgdp, start, end, PAGE_KERNEL, flags); } /* @@ -464,7 +471,7 @@ static void __init map_mem(pgd_t *pgd) * Note that contiguous mappings cannot be remapped in this way, * so we should avoid them here. */ - __map_memblock(pgd, kernel_start, kernel_end, + __map_memblock(pgdp, kernel_start, kernel_end, PAGE_KERNEL, NO_CONT_MAPPINGS); memblock_clear_nomap(kernel_start, kernel_end - kernel_start); @@ -475,7 +482,7 @@ static void __init map_mem(pgd_t *pgd) * through /sys/kernel/kexec_crash_size interface. */ if (crashk_res.end) { - __map_memblock(pgd, crashk_res.start, crashk_res.end + 1, + __map_memblock(pgdp, crashk_res.start, crashk_res.end + 1, PAGE_KERNEL, NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS); memblock_clear_nomap(crashk_res.start, @@ -499,7 +506,7 @@ void mark_rodata_ro(void) debug_checkwx(); } -static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end, +static void __init map_kernel_segment(pgd_t *pgdp, void *va_start, void *va_end, pgprot_t prot, struct vm_struct *vma, int flags, unsigned long vm_flags) { @@ -509,7 +516,7 @@ static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end, BUG_ON(!PAGE_ALIGNED(pa_start)); BUG_ON(!PAGE_ALIGNED(size)); - __create_pgd_mapping(pgd, pa_start, (unsigned long)va_start, size, prot, + __create_pgd_mapping(pgdp, pa_start, (unsigned long)va_start, size, prot, early_pgtable_alloc, flags); if (!(vm_flags & VM_NO_GUARD)) @@ -562,7 +569,7 @@ core_initcall(map_entry_trampoline); /* * Create fine-grained mappings for the kernel. */ -static void __init map_kernel(pgd_t *pgd) +static void __init map_kernel(pgd_t *pgdp) { static struct vm_struct vmlinux_text, vmlinux_rodata, vmlinux_inittext, vmlinux_initdata, vmlinux_data; @@ -578,24 +585,24 @@ static void __init map_kernel(pgd_t *pgd) * Only rodata will be remapped with different permissions later on, * all other segments are allowed to use contiguous mappings. */ - map_kernel_segment(pgd, _text, _etext, text_prot, &vmlinux_text, 0, + map_kernel_segment(pgdp, _text, _etext, text_prot, &vmlinux_text, 0, VM_NO_GUARD); - map_kernel_segment(pgd, __start_rodata, __inittext_begin, PAGE_KERNEL, + map_kernel_segment(pgdp, __start_rodata, __inittext_begin, PAGE_KERNEL, &vmlinux_rodata, NO_CONT_MAPPINGS, VM_NO_GUARD); - map_kernel_segment(pgd, __inittext_begin, __inittext_end, text_prot, + map_kernel_segment(pgdp, __inittext_begin, __inittext_end, text_prot, &vmlinux_inittext, 0, VM_NO_GUARD); - map_kernel_segment(pgd, __initdata_begin, __initdata_end, PAGE_KERNEL, + map_kernel_segment(pgdp, __initdata_begin, __initdata_end, PAGE_KERNEL, &vmlinux_initdata, 0, VM_NO_GUARD); - map_kernel_segment(pgd, _data, _end, PAGE_KERNEL, &vmlinux_data, 0, 0); + map_kernel_segment(pgdp, _data, _end, PAGE_KERNEL, &vmlinux_data, 0, 0); - if (!pgd_val(*pgd_offset_raw(pgd, FIXADDR_START))) { + if (!READ_ONCE(pgd_val(*pgd_offset_raw(pgdp, FIXADDR_START)))) { /* * The fixmap falls in a separate pgd to the kernel, and doesn't * live in the carveout for the swapper_pg_dir. We can simply * re-use the existing dir for the fixmap. */ - set_pgd(pgd_offset_raw(pgd, FIXADDR_START), - *pgd_offset_k(FIXADDR_START)); + set_pgd(pgd_offset_raw(pgdp, FIXADDR_START), + READ_ONCE(*pgd_offset_k(FIXADDR_START))); } else if (CONFIG_PGTABLE_LEVELS > 3) { /* * The fixmap shares its top level pgd entry with the kernel @@ -604,14 +611,15 @@ static void __init map_kernel(pgd_t *pgd) * entry instead. */ BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES)); - pud_populate(&init_mm, pud_set_fixmap_offset(pgd, FIXADDR_START), + pud_populate(&init_mm, + pud_set_fixmap_offset(pgdp, FIXADDR_START), lm_alias(bm_pmd)); pud_clear_fixmap(); } else { BUG(); } - kasan_copy_shadow(pgd); + kasan_copy_shadow(pgdp); } /* @@ -621,10 +629,10 @@ static void __init map_kernel(pgd_t *pgd) void __init paging_init(void) { phys_addr_t pgd_phys = early_pgtable_alloc(); - pgd_t *pgd = pgd_set_fixmap(pgd_phys); + pgd_t *pgdp = pgd_set_fixmap(pgd_phys); - map_kernel(pgd); - map_mem(pgd); + map_kernel(pgdp); + map_mem(pgdp); /* * We want to reuse the original swapper_pg_dir so we don't have to @@ -635,7 +643,7 @@ void __init paging_init(void) * To do this we need to go via a temporary pgd. */ cpu_replace_ttbr1(__va(pgd_phys)); - memcpy(swapper_pg_dir, pgd, PGD_SIZE); + memcpy(swapper_pg_dir, pgdp, PGD_SIZE); cpu_replace_ttbr1(lm_alias(swapper_pg_dir)); pgd_clear_fixmap(); @@ -655,37 +663,40 @@ void __init paging_init(void) */ int kern_addr_valid(unsigned long addr) { - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; + pgd_t *pgdp; + pud_t *pudp, pud; + pmd_t *pmdp, pmd; + pte_t *ptep, pte; if ((((long)addr) >> VA_BITS) != -1UL) return 0; - pgd = pgd_offset_k(addr); - if (pgd_none(*pgd)) + pgdp = pgd_offset_k(addr); + if (pgd_none(READ_ONCE(*pgdp))) return 0; - pud = pud_offset(pgd, addr); - if (pud_none(*pud)) + pudp = pud_offset(pgdp, addr); + pud = READ_ONCE(*pudp); + if (pud_none(pud)) return 0; - if (pud_sect(*pud)) - return pfn_valid(pud_pfn(*pud)); + if (pud_sect(pud)) + return pfn_valid(pud_pfn(pud)); - pmd = pmd_offset(pud, addr); - if (pmd_none(*pmd)) + pmdp = pmd_offset(pudp, addr); + pmd = READ_ONCE(*pmdp); + if (pmd_none(pmd)) return 0; - if (pmd_sect(*pmd)) - return pfn_valid(pmd_pfn(*pmd)); + if (pmd_sect(pmd)) + return pfn_valid(pmd_pfn(pmd)); - pte = pte_offset_kernel(pmd, addr); - if (pte_none(*pte)) + ptep = pte_offset_kernel(pmdp, addr); + pte = READ_ONCE(*ptep); + if (pte_none(pte)) return 0; - return pfn_valid(pte_pfn(*pte)); + return pfn_valid(pte_pfn(pte)); } #ifdef CONFIG_SPARSEMEM_VMEMMAP #if !ARM64_SWAPPER_USES_SECTION_MAPS @@ -700,32 +711,32 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, { unsigned long addr = start; unsigned long next; - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; + pgd_t *pgdp; + pud_t *pudp; + pmd_t *pmdp; do { next = pmd_addr_end(addr, end); - pgd = vmemmap_pgd_populate(addr, node); - if (!pgd) + pgdp = vmemmap_pgd_populate(addr, node); + if (!pgdp) return -ENOMEM; - pud = vmemmap_pud_populate(pgd, addr, node); - if (!pud) + pudp = vmemmap_pud_populate(pgdp, addr, node); + if (!pudp) return -ENOMEM; - pmd = pmd_offset(pud, addr); - if (pmd_none(*pmd)) { + pmdp = pmd_offset(pudp, addr); + if (pmd_none(READ_ONCE(*pmdp))) { void *p = NULL; p = vmemmap_alloc_block_buf(PMD_SIZE, node); if (!p) return -ENOMEM; - pmd_set_huge(pmd, __pa(p), __pgprot(PROT_SECT_NORMAL)); + pmd_set_huge(pmdp, __pa(p), __pgprot(PROT_SECT_NORMAL)); } else - vmemmap_verify((pte_t *)pmd, node, addr, next); + vmemmap_verify((pte_t *)pmdp, node, addr, next); } while (addr = next, addr != end); return 0; @@ -739,20 +750,22 @@ void vmemmap_free(unsigned long start, unsigned long end, static inline pud_t * fixmap_pud(unsigned long addr) { - pgd_t *pgd = pgd_offset_k(addr); + pgd_t *pgdp = pgd_offset_k(addr); + pgd_t pgd = READ_ONCE(*pgdp); - BUG_ON(pgd_none(*pgd) || pgd_bad(*pgd)); + BUG_ON(pgd_none(pgd) || pgd_bad(pgd)); - return pud_offset_kimg(pgd, addr); + return pud_offset_kimg(pgdp, addr); } static inline pmd_t * fixmap_pmd(unsigned long addr) { - pud_t *pud = fixmap_pud(addr); + pud_t *pudp = fixmap_pud(addr); + pud_t pud = READ_ONCE(*pudp); - BUG_ON(pud_none(*pud) || pud_bad(*pud)); + BUG_ON(pud_none(pud) || pud_bad(pud)); - return pmd_offset_kimg(pud, addr); + return pmd_offset_kimg(pudp, addr); } static inline pte_t * fixmap_pte(unsigned long addr) @@ -768,30 +781,31 @@ static inline pte_t * fixmap_pte(unsigned long addr) */ void __init early_fixmap_init(void) { - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; + pgd_t *pgdp, pgd; + pud_t *pudp; + pmd_t *pmdp; unsigned long addr = FIXADDR_START; - pgd = pgd_offset_k(addr); + pgdp = pgd_offset_k(addr); + pgd = READ_ONCE(*pgdp); if (CONFIG_PGTABLE_LEVELS > 3 && - !(pgd_none(*pgd) || pgd_page_paddr(*pgd) == __pa_symbol(bm_pud))) { + !(pgd_none(pgd) || pgd_page_paddr(pgd) == __pa_symbol(bm_pud))) { /* * We only end up here if the kernel mapping and the fixmap * share the top level pgd entry, which should only happen on * 16k/4 levels configurations. */ BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES)); - pud = pud_offset_kimg(pgd, addr); + pudp = pud_offset_kimg(pgdp, addr); } else { - if (pgd_none(*pgd)) - __pgd_populate(pgd, __pa_symbol(bm_pud), PUD_TYPE_TABLE); - pud = fixmap_pud(addr); + if (pgd_none(pgd)) + __pgd_populate(pgdp, __pa_symbol(bm_pud), PUD_TYPE_TABLE); + pudp = fixmap_pud(addr); } - if (pud_none(*pud)) - __pud_populate(pud, __pa_symbol(bm_pmd), PMD_TYPE_TABLE); - pmd = fixmap_pmd(addr); - __pmd_populate(pmd, __pa_symbol(bm_pte), PMD_TYPE_TABLE); + if (pud_none(READ_ONCE(*pudp))) + __pud_populate(pudp, __pa_symbol(bm_pmd), PMD_TYPE_TABLE); + pmdp = fixmap_pmd(addr); + __pmd_populate(pmdp, __pa_symbol(bm_pte), PMD_TYPE_TABLE); /* * The boot-ioremap range spans multiple pmds, for which @@ -800,11 +814,11 @@ void __init early_fixmap_init(void) BUILD_BUG_ON((__fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT) != (__fix_to_virt(FIX_BTMAP_END) >> PMD_SHIFT)); - if ((pmd != fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN))) - || pmd != fixmap_pmd(fix_to_virt(FIX_BTMAP_END))) { + if ((pmdp != fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN))) + || pmdp != fixmap_pmd(fix_to_virt(FIX_BTMAP_END))) { WARN_ON(1); - pr_warn("pmd %p != %p, %p\n", - pmd, fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)), + pr_warn("pmdp %p != %p, %p\n", + pmdp, fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)), fixmap_pmd(fix_to_virt(FIX_BTMAP_END))); pr_warn("fix_to_virt(FIX_BTMAP_BEGIN): %08lx\n", fix_to_virt(FIX_BTMAP_BEGIN)); @@ -824,16 +838,16 @@ void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags) { unsigned long addr = __fix_to_virt(idx); - pte_t *pte; + pte_t *ptep; BUG_ON(idx <= FIX_HOLE || idx >= __end_of_fixed_addresses); - pte = fixmap_pte(addr); + ptep = fixmap_pte(addr); if (pgprot_val(flags)) { - set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, flags)); + set_pte(ptep, pfn_pte(phys >> PAGE_SHIFT, flags)); } else { - pte_clear(&init_mm, addr, pte); + pte_clear(&init_mm, addr, ptep); flush_tlb_kernel_range(addr, addr+PAGE_SIZE); } } @@ -915,36 +929,46 @@ int __init arch_ioremap_pmd_supported(void) return 1; } -int pud_set_huge(pud_t *pud, phys_addr_t phys, pgprot_t prot) +int pud_set_huge(pud_t *pudp, phys_addr_t phys, pgprot_t prot) { pgprot_t sect_prot = __pgprot(PUD_TYPE_SECT | pgprot_val(mk_sect_prot(prot))); + + /* ioremap_page_range doesn't honour BBM */ + if (pud_present(READ_ONCE(*pudp))) + return 0; + BUG_ON(phys & ~PUD_MASK); - set_pud(pud, pfn_pud(__phys_to_pfn(phys), sect_prot)); + set_pud(pudp, pfn_pud(__phys_to_pfn(phys), sect_prot)); return 1; } -int pmd_set_huge(pmd_t *pmd, phys_addr_t phys, pgprot_t prot) +int pmd_set_huge(pmd_t *pmdp, phys_addr_t phys, pgprot_t prot) { pgprot_t sect_prot = __pgprot(PMD_TYPE_SECT | pgprot_val(mk_sect_prot(prot))); + + /* ioremap_page_range doesn't honour BBM */ + if (pmd_present(READ_ONCE(*pmdp))) + return 0; + BUG_ON(phys & ~PMD_MASK); - set_pmd(pmd, pfn_pmd(__phys_to_pfn(phys), sect_prot)); + set_pmd(pmdp, pfn_pmd(__phys_to_pfn(phys), sect_prot)); return 1; } -int pud_clear_huge(pud_t *pud) +int pud_clear_huge(pud_t *pudp) { - if (!pud_sect(*pud)) + if (!pud_sect(READ_ONCE(*pudp))) return 0; - pud_clear(pud); + pud_clear(pudp); return 1; } -int pmd_clear_huge(pmd_t *pmd) +int pmd_clear_huge(pmd_t *pmdp) { - if (!pmd_sect(*pmd)) + if (!pmd_sect(READ_ONCE(*pmdp))) return 0; - pmd_clear(pmd); + pmd_clear(pmdp); return 1; } diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index a682a0a2a0fa..a56359373d8b 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -29,7 +29,7 @@ static int change_page_range(pte_t *ptep, pgtable_t token, unsigned long addr, void *data) { struct page_change_data *cdata = data; - pte_t pte = *ptep; + pte_t pte = READ_ONCE(*ptep); pte = clear_pte_bit(pte, cdata->clear_mask); pte = set_pte_bit(pte, cdata->set_mask); @@ -156,30 +156,32 @@ void __kernel_map_pages(struct page *page, int numpages, int enable) */ bool kernel_page_present(struct page *page) { - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; + pgd_t *pgdp; + pud_t *pudp, pud; + pmd_t *pmdp, pmd; + pte_t *ptep; unsigned long addr = (unsigned long)page_address(page); - pgd = pgd_offset_k(addr); - if (pgd_none(*pgd)) + pgdp = pgd_offset_k(addr); + if (pgd_none(READ_ONCE(*pgdp))) return false; - pud = pud_offset(pgd, addr); - if (pud_none(*pud)) + pudp = pud_offset(pgdp, addr); + pud = READ_ONCE(*pudp); + if (pud_none(pud)) return false; - if (pud_sect(*pud)) + if (pud_sect(pud)) return true; - pmd = pmd_offset(pud, addr); - if (pmd_none(*pmd)) + pmdp = pmd_offset(pudp, addr); + pmd = READ_ONCE(*pmdp); + if (pmd_none(pmd)) return false; - if (pmd_sect(*pmd)) + if (pmd_sect(pmd)) return true; - pte = pte_offset_kernel(pmd, addr); - return pte_valid(*pte); + ptep = pte_offset_kernel(pmdp, addr); + return pte_valid(READ_ONCE(*ptep)); } #endif /* CONFIG_HIBERNATION */ #endif /* CONFIG_DEBUG_PAGEALLOC */ diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 71baed7e592a..c0af47617299 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -205,7 +205,8 @@ ENDPROC(idmap_cpu_replace_ttbr1) dc cvac, cur_\()\type\()p // Ensure any existing dirty dmb sy // lines are written back before ldr \type, [cur_\()\type\()p] // loading the entry - tbz \type, #0, next_\()\type // Skip invalid entries + tbz \type, #0, skip_\()\type // Skip invalid and + tbnz \type, #11, skip_\()\type // non-global entries .endm .macro __idmap_kpti_put_pgtable_ent_ng, type @@ -265,8 +266,9 @@ ENTRY(idmap_kpti_install_ng_mappings) add end_pgdp, cur_pgdp, #(PTRS_PER_PGD * 8) do_pgd: __idmap_kpti_get_pgtable_ent pgd tbnz pgd, #1, walk_puds - __idmap_kpti_put_pgtable_ent_ng pgd next_pgd: + __idmap_kpti_put_pgtable_ent_ng pgd +skip_pgd: add cur_pgdp, cur_pgdp, #8 cmp cur_pgdp, end_pgdp b.ne do_pgd @@ -294,8 +296,9 @@ walk_puds: add end_pudp, cur_pudp, #(PTRS_PER_PUD * 8) do_pud: __idmap_kpti_get_pgtable_ent pud tbnz pud, #1, walk_pmds - __idmap_kpti_put_pgtable_ent_ng pud next_pud: + __idmap_kpti_put_pgtable_ent_ng pud +skip_pud: add cur_pudp, cur_pudp, 8 cmp cur_pudp, end_pudp b.ne do_pud @@ -314,8 +317,9 @@ walk_pmds: add end_pmdp, cur_pmdp, #(PTRS_PER_PMD * 8) do_pmd: __idmap_kpti_get_pgtable_ent pmd tbnz pmd, #1, walk_ptes - __idmap_kpti_put_pgtable_ent_ng pmd next_pmd: + __idmap_kpti_put_pgtable_ent_ng pmd +skip_pmd: add cur_pmdp, cur_pmdp, #8 cmp cur_pmdp, end_pmdp b.ne do_pmd @@ -333,7 +337,7 @@ walk_ptes: add end_ptep, cur_ptep, #(PTRS_PER_PTE * 8) do_pte: __idmap_kpti_get_pgtable_ent pte __idmap_kpti_put_pgtable_ent_ng pte -next_pte: +skip_pte: add cur_ptep, cur_ptep, #8 cmp cur_ptep, end_ptep b.ne do_pte diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 1d4f1da7c58f..a93350451e8e 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -250,8 +250,9 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) off = offsetof(struct bpf_array, map.max_entries); emit_a64_mov_i64(tmp, off, ctx); emit(A64_LDR32(tmp, r2, tmp), ctx); + emit(A64_MOV(0, r3, r3), ctx); emit(A64_CMP(0, r3, tmp), ctx); - emit(A64_B_(A64_COND_GE, jmp_offset), ctx); + emit(A64_B_(A64_COND_CS, jmp_offset), ctx); /* if (tail_call_cnt > MAX_TAIL_CALL_CNT) * goto out; @@ -259,7 +260,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) */ emit_a64_mov_i64(tmp, MAX_TAIL_CALL_CNT, ctx); emit(A64_CMP(1, tcc, tmp), ctx); - emit(A64_B_(A64_COND_GT, jmp_offset), ctx); + emit(A64_B_(A64_COND_HI, jmp_offset), ctx); emit(A64_ADD_I(1, tcc, tcc, 1), ctx); /* prog = array->ptrs[index]; diff --git a/arch/cris/include/arch-v10/arch/bug.h b/arch/cris/include/arch-v10/arch/bug.h index 905afeacfedf..06da9d49152a 100644 --- a/arch/cris/include/arch-v10/arch/bug.h +++ b/arch/cris/include/arch-v10/arch/bug.h @@ -44,18 +44,25 @@ struct bug_frame { * not be used like this with newer versions of gcc. */ #define BUG() \ +do { \ __asm__ __volatile__ ("clear.d [" __stringify(BUG_MAGIC) "]\n\t"\ "movu.w " __stringify(__LINE__) ",$r0\n\t"\ "jump 0f\n\t" \ ".section .rodata\n" \ "0:\t.string \"" __FILE__ "\"\n\t" \ - ".previous") + ".previous"); \ + unreachable(); \ +} while (0) #endif #else /* This just causes an oops. */ -#define BUG() (*(int *)0 = 0) +#define BUG() \ +do { \ + barrier_before_unreachable(); \ + __builtin_trap(); \ +} while (0) #endif diff --git a/arch/ia64/include/asm/bug.h b/arch/ia64/include/asm/bug.h index bd3eeb8d1cfa..66b37a532765 100644 --- a/arch/ia64/include/asm/bug.h +++ b/arch/ia64/include/asm/bug.h @@ -4,7 +4,11 @@ #ifdef CONFIG_BUG #define ia64_abort() __builtin_trap() -#define BUG() do { printk("kernel BUG at %s:%d!\n", __FILE__, __LINE__); ia64_abort(); } while (0) +#define BUG() do { \ + printk("kernel BUG at %s:%d!\n", __FILE__, __LINE__); \ + barrier_before_unreachable(); \ + ia64_abort(); \ +} while (0) /* should this BUG be made generic? */ #define HAVE_ARCH_BUG diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile index 0b4c65a1af25..498f3da3f225 100644 --- a/arch/ia64/kernel/Makefile +++ b/arch/ia64/kernel/Makefile @@ -41,7 +41,6 @@ ifneq ($(CONFIG_IA64_ESI),) obj-y += esi_stub.o # must be in kernel proper endif obj-$(CONFIG_INTEL_IOMMU) += pci-dma.o -obj-$(CONFIG_SWIOTLB) += pci-swiotlb.o obj-$(CONFIG_BINFMT_ELF) += elfcore.o diff --git a/arch/m68k/include/asm/bug.h b/arch/m68k/include/asm/bug.h index b7e2bf1ba4a6..275dca1435bf 100644 --- a/arch/m68k/include/asm/bug.h +++ b/arch/m68k/include/asm/bug.h @@ -8,16 +8,19 @@ #ifndef CONFIG_SUN3 #define BUG() do { \ pr_crit("kernel BUG at %s:%d!\n", __FILE__, __LINE__); \ + barrier_before_unreachable(); \ __builtin_trap(); \ } while (0) #else #define BUG() do { \ pr_crit("kernel BUG at %s:%d!\n", __FILE__, __LINE__); \ + barrier_before_unreachable(); \ panic("BUG!"); \ } while (0) #endif #else #define BUG() do { \ + barrier_before_unreachable(); \ __builtin_trap(); \ } while (0) #endif diff --git a/arch/mips/boot/Makefile b/arch/mips/boot/Makefile index 1bd5c4f00d19..c22da16d67b8 100644 --- a/arch/mips/boot/Makefile +++ b/arch/mips/boot/Makefile @@ -126,6 +126,7 @@ $(obj)/vmlinux.its.S: $(addprefix $(srctree)/arch/mips/$(PLATFORM)/,$(ITS_INPUTS quiet_cmd_cpp_its_S = ITS $@ cmd_cpp_its_S = $(CPP) $(cpp_flags) -P -C -o $@ $< \ + -D__ASSEMBLY__ \ -DKERNEL_NAME="\"Linux $(KERNELRELEASE)\"" \ -DVMLINUX_BINARY="\"$(3)\"" \ -DVMLINUX_COMPRESSION="\"$(2)\"" \ diff --git a/arch/mips/include/asm/compat.h b/arch/mips/include/asm/compat.h index 946681db8dc3..9a0fa66b81ac 100644 --- a/arch/mips/include/asm/compat.h +++ b/arch/mips/include/asm/compat.h @@ -86,7 +86,6 @@ struct compat_flock { compat_off_t l_len; s32 l_sysid; compat_pid_t l_pid; - short __unused; s32 pad[4]; }; diff --git a/arch/mips/kernel/mips-cpc.c b/arch/mips/kernel/mips-cpc.c index 19c88d770054..fcf9af492d60 100644 --- a/arch/mips/kernel/mips-cpc.c +++ b/arch/mips/kernel/mips-cpc.c @@ -10,6 +10,8 @@ #include <linux/errno.h> #include <linux/percpu.h> +#include <linux/of.h> +#include <linux/of_address.h> #include <linux/spinlock.h> #include <asm/mips-cps.h> @@ -22,6 +24,17 @@ static DEFINE_PER_CPU_ALIGNED(unsigned long, cpc_core_lock_flags); phys_addr_t __weak mips_cpc_default_phys_base(void) { + struct device_node *cpc_node; + struct resource res; + int err; + + cpc_node = of_find_compatible_node(of_root, NULL, "mti,mips-cpc"); + if (cpc_node) { + err = of_address_to_resource(cpc_node, 0, &res); + if (!err) + return res.start; + } + return 0; } diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 85bc601e9a0d..5f8b0a9e30b3 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -375,6 +375,7 @@ static void __init bootmem_init(void) unsigned long reserved_end; unsigned long mapstart = ~0UL; unsigned long bootmap_size; + phys_addr_t ramstart = (phys_addr_t)ULLONG_MAX; bool bootmap_valid = false; int i; @@ -395,7 +396,8 @@ static void __init bootmem_init(void) max_low_pfn = 0; /* - * Find the highest page frame number we have available. + * Find the highest page frame number we have available + * and the lowest used RAM address */ for (i = 0; i < boot_mem_map.nr_map; i++) { unsigned long start, end; @@ -407,6 +409,8 @@ static void __init bootmem_init(void) end = PFN_DOWN(boot_mem_map.map[i].addr + boot_mem_map.map[i].size); + ramstart = min(ramstart, boot_mem_map.map[i].addr); + #ifndef CONFIG_HIGHMEM /* * Skip highmem here so we get an accurate max_low_pfn if low @@ -436,6 +440,13 @@ static void __init bootmem_init(void) mapstart = max(reserved_end, start); } + /* + * Reserve any memory between the start of RAM and PHYS_OFFSET + */ + if (ramstart > PHYS_OFFSET) + add_memory_region(PHYS_OFFSET, ramstart - PHYS_OFFSET, + BOOT_MEM_RESERVED); + if (min_low_pfn >= max_low_pfn) panic("Incorrect memory mapping !!!"); if (min_low_pfn > ARCH_PFN_OFFSET) { @@ -664,9 +675,6 @@ static int __init early_parse_mem(char *p) add_memory_region(start, size, BOOT_MEM_RAM); - if (start && start > PHYS_OFFSET) - add_memory_region(PHYS_OFFSET, start - PHYS_OFFSET, - BOOT_MEM_RESERVED); return 0; } early_param("mem", early_parse_mem); diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c index 87dcac2447c8..9d41732a9146 100644 --- a/arch/mips/kernel/smp-bmips.c +++ b/arch/mips/kernel/smp-bmips.c @@ -572,7 +572,7 @@ asmlinkage void __weak plat_wired_tlb_setup(void) */ } -void __init bmips_cpu_setup(void) +void bmips_cpu_setup(void) { void __iomem __maybe_unused *cbr = BMIPS_GET_CBR(); u32 __maybe_unused cfg; diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index 30a155c0a6b0..c615abdce119 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -16,6 +16,7 @@ #define PGD_INDEX_SIZE (32 - PGDIR_SHIFT) #define PMD_CACHE_INDEX PMD_INDEX_SIZE +#define PUD_CACHE_INDEX PUD_INDEX_SIZE #ifndef __ASSEMBLY__ #define PTE_TABLE_SIZE (sizeof(pte_t) << PTE_INDEX_SIZE) diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h index 949d691094a4..67c5475311ee 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-4k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h @@ -63,7 +63,8 @@ static inline int hash__hugepd_ok(hugepd_t hpd) * keeping the prototype consistent across the two formats. */ static inline unsigned long pte_set_hidx(pte_t *ptep, real_pte_t rpte, - unsigned int subpg_index, unsigned long hidx) + unsigned int subpg_index, unsigned long hidx, + int offset) { return (hidx << H_PAGE_F_GIX_SHIFT) & (H_PAGE_F_SECOND | H_PAGE_F_GIX); diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h index 338b7da468ce..3bcf269f8f55 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-64k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h @@ -45,7 +45,7 @@ * generic accessors and iterators here */ #define __real_pte __real_pte -static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep) +static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep, int offset) { real_pte_t rpte; unsigned long *hidxp; @@ -59,7 +59,7 @@ static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep) */ smp_rmb(); - hidxp = (unsigned long *)(ptep + PTRS_PER_PTE); + hidxp = (unsigned long *)(ptep + offset); rpte.hidx = *hidxp; return rpte; } @@ -86,9 +86,10 @@ static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index) * expected to modify the PTE bits accordingly and commit the PTE to memory. */ static inline unsigned long pte_set_hidx(pte_t *ptep, real_pte_t rpte, - unsigned int subpg_index, unsigned long hidx) + unsigned int subpg_index, + unsigned long hidx, int offset) { - unsigned long *hidxp = (unsigned long *)(ptep + PTRS_PER_PTE); + unsigned long *hidxp = (unsigned long *)(ptep + offset); rpte.hidx &= ~HIDX_BITS(0xfUL, subpg_index); *hidxp = rpte.hidx | HIDX_BITS(HIDX_SHIFT_BY_ONE(hidx), subpg_index); @@ -140,13 +141,18 @@ static inline int hash__remap_4k_pfn(struct vm_area_struct *vma, unsigned long a } #define H_PTE_TABLE_SIZE PTE_FRAG_SIZE -#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined (CONFIG_HUGETLB_PAGE) #define H_PMD_TABLE_SIZE ((sizeof(pmd_t) << PMD_INDEX_SIZE) + \ (sizeof(unsigned long) << PMD_INDEX_SIZE)) #else #define H_PMD_TABLE_SIZE (sizeof(pmd_t) << PMD_INDEX_SIZE) #endif +#ifdef CONFIG_HUGETLB_PAGE +#define H_PUD_TABLE_SIZE ((sizeof(pud_t) << PUD_INDEX_SIZE) + \ + (sizeof(unsigned long) << PUD_INDEX_SIZE)) +#else #define H_PUD_TABLE_SIZE (sizeof(pud_t) << PUD_INDEX_SIZE) +#endif #define H_PGD_TABLE_SIZE (sizeof(pgd_t) << PGD_INDEX_SIZE) #ifdef CONFIG_TRANSPARENT_HUGEPAGE diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h index 0920eff731b3..935adcd92a81 100644 --- a/arch/powerpc/include/asm/book3s/64/hash.h +++ b/arch/powerpc/include/asm/book3s/64/hash.h @@ -23,7 +23,8 @@ H_PUD_INDEX_SIZE + H_PGD_INDEX_SIZE + PAGE_SHIFT) #define H_PGTABLE_RANGE (ASM_CONST(1) << H_PGTABLE_EADDR_SIZE) -#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && defined(CONFIG_PPC_64K_PAGES) +#if (defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE)) && \ + defined(CONFIG_PPC_64K_PAGES) /* * only with hash 64k we need to use the second half of pmd page table * to store pointer to deposited pgtable_t @@ -33,6 +34,16 @@ #define H_PMD_CACHE_INDEX H_PMD_INDEX_SIZE #endif /* + * We store the slot details in the second half of page table. + * Increase the pud level table so that hugetlb ptes can be stored + * at pud level. + */ +#if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_PPC_64K_PAGES) +#define H_PUD_CACHE_INDEX (H_PUD_INDEX_SIZE + 1) +#else +#define H_PUD_CACHE_INDEX (H_PUD_INDEX_SIZE) +#endif +/* * Define the address range of the kernel non-linear virtual area */ #define H_KERN_VIRT_START ASM_CONST(0xD000000000000000) diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h index 1fcfa425cefa..4746bc68d446 100644 --- a/arch/powerpc/include/asm/book3s/64/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h @@ -73,10 +73,16 @@ static inline void radix__pgd_free(struct mm_struct *mm, pgd_t *pgd) static inline pgd_t *pgd_alloc(struct mm_struct *mm) { + pgd_t *pgd; + if (radix_enabled()) return radix__pgd_alloc(mm); - return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE), - pgtable_gfp_flags(mm, GFP_KERNEL)); + + pgd = kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE), + pgtable_gfp_flags(mm, GFP_KERNEL)); + memset(pgd, 0, PGD_TABLE_SIZE); + + return pgd; } static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) @@ -93,13 +99,13 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud) static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) { - return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE), + return kmem_cache_alloc(PGT_CACHE(PUD_CACHE_INDEX), pgtable_gfp_flags(mm, GFP_KERNEL)); } static inline void pud_free(struct mm_struct *mm, pud_t *pud) { - kmem_cache_free(PGT_CACHE(PUD_INDEX_SIZE), pud); + kmem_cache_free(PGT_CACHE(PUD_CACHE_INDEX), pud); } static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) @@ -115,7 +121,7 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, * ahead and flush the page walk cache */ flush_tlb_pgtable(tlb, address); - pgtable_free_tlb(tlb, pud, PUD_INDEX_SIZE); + pgtable_free_tlb(tlb, pud, PUD_CACHE_INDEX); } static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 51017726d495..a6b9f1d74600 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -232,11 +232,13 @@ extern unsigned long __pmd_index_size; extern unsigned long __pud_index_size; extern unsigned long __pgd_index_size; extern unsigned long __pmd_cache_index; +extern unsigned long __pud_cache_index; #define PTE_INDEX_SIZE __pte_index_size #define PMD_INDEX_SIZE __pmd_index_size #define PUD_INDEX_SIZE __pud_index_size #define PGD_INDEX_SIZE __pgd_index_size #define PMD_CACHE_INDEX __pmd_cache_index +#define PUD_CACHE_INDEX __pud_cache_index /* * Because of use of pte fragments and THP, size of page table * are not always derived out of index size above. @@ -348,7 +350,7 @@ extern unsigned long pci_io_base; */ #ifndef __real_pte -#define __real_pte(e,p) ((real_pte_t){(e)}) +#define __real_pte(e, p, o) ((real_pte_t){(e)}) #define __rpte_to_pte(r) ((r).pte) #define __rpte_to_hidx(r,index) (pte_val(__rpte_to_pte(r)) >> H_PAGE_F_GIX_SHIFT) diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index 176dfb73d42c..471b2274fbeb 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -645,7 +645,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) EXC_HV, SOFTEN_TEST_HV, bitmask) #define MASKABLE_RELON_EXCEPTION_HV_OOL(vec, label, bitmask) \ - MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_NOTEST_HV, vec, bitmask);\ + MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_TEST_HV, vec, bitmask);\ EXCEPTION_RELON_PROLOG_PSERIES_1(label, EXC_HV) /* diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index 88e5e8f17e98..855e17d158b1 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -30,6 +30,16 @@ #define PACA_IRQ_PMI 0x40 /* + * Some soft-masked interrupts must be hard masked until they are replayed + * (e.g., because the soft-masked handler does not clear the exception). + */ +#ifdef CONFIG_PPC_BOOK3S +#define PACA_IRQ_MUST_HARD_MASK (PACA_IRQ_EE|PACA_IRQ_PMI) +#else +#define PACA_IRQ_MUST_HARD_MASK (PACA_IRQ_EE) +#endif + +/* * flags for paca->irq_soft_mask */ #define IRQS_ENABLED 0 @@ -244,7 +254,7 @@ static inline bool lazy_irq_pending(void) static inline void may_hard_irq_enable(void) { get_paca()->irq_happened &= ~PACA_IRQ_HARD_DIS; - if (!(get_paca()->irq_happened & PACA_IRQ_EE)) + if (!(get_paca()->irq_happened & PACA_IRQ_MUST_HARD_MASK)) __hard_irq_enable(); } diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h index 9dcbfa6bbb91..d8b1e8e7e035 100644 --- a/arch/powerpc/include/asm/kexec.h +++ b/arch/powerpc/include/asm/kexec.h @@ -140,6 +140,12 @@ static inline bool kdump_in_progress(void) return false; } +static inline void crash_ipi_callback(struct pt_regs *regs) { } + +static inline void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *)) +{ +} + #endif /* CONFIG_KEXEC_CORE */ #endif /* ! __ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index 504a3c36ce5c..03bbd1149530 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -24,6 +24,7 @@ extern int icache_44x_need_flush; #define PGD_INDEX_SIZE (32 - PGDIR_SHIFT) #define PMD_CACHE_INDEX PMD_INDEX_SIZE +#define PUD_CACHE_INDEX PUD_INDEX_SIZE #ifndef __ASSEMBLY__ #define PTE_TABLE_SIZE (sizeof(pte_t) << PTE_INDEX_SIZE) diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h index abddf5830ad5..5c5f75d005ad 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h @@ -27,6 +27,7 @@ #else #define PMD_CACHE_INDEX PMD_INDEX_SIZE #endif +#define PUD_CACHE_INDEX PUD_INDEX_SIZE /* * Define the address range of the kernel non-linear virtual area diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 88187c285c70..9f421641a35c 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -44,6 +44,11 @@ extern int sysfs_add_device_to_node(struct device *dev, int nid); extern void sysfs_remove_device_from_node(struct device *dev, int nid); extern int numa_update_cpu_topology(bool cpus_locked); +static inline void update_numa_cpu_lookup_table(unsigned int cpu, int node) +{ + numa_cpu_lookup_table[cpu] = node; +} + static inline int early_cpu_to_node(int cpu) { int nid; @@ -76,12 +81,16 @@ static inline int numa_update_cpu_topology(bool cpus_locked) { return 0; } + +static inline void update_numa_cpu_lookup_table(unsigned int cpu, int node) {} + #endif /* CONFIG_NUMA */ #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR) extern int start_topology_update(void); extern int stop_topology_update(void); extern int prrn_is_enabled(void); +extern int find_and_online_cpu_nid(int cpu); #else static inline int start_topology_update(void) { @@ -95,6 +104,10 @@ static inline int prrn_is_enabled(void) { return 0; } +static inline int find_and_online_cpu_nid(int cpu) +{ + return 0; +} #endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */ #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_NEED_MULTIPLE_NODES) diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index ee832d344a5a..9b6e653e501a 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -943,6 +943,8 @@ kernel_dbg_exc: /* * An interrupt came in while soft-disabled; We mark paca->irq_happened * accordingly and if the interrupt is level sensitive, we hard disable + * hard disable (full_mask) corresponds to PACA_IRQ_MUST_HARD_MASK, so + * keep these in synch. */ .macro masked_interrupt_book3e paca_irq full_mask diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 243d072a225a..3ac87e53b3da 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1426,7 +1426,7 @@ EXC_COMMON_BEGIN(soft_nmi_common) * triggered and won't automatically refire. * - If it was a HMI we return immediately since we handled it in realmode * and it won't refire. - * - else we hard disable and return. + * - Else it is one of PACA_IRQ_MUST_HARD_MASK, so hard disable and return. * This is called with r10 containing the value to OR to the paca field. */ #define MASKED_INTERRUPT(_H) \ @@ -1441,8 +1441,8 @@ masked_##_H##interrupt: \ ori r10,r10,0xffff; \ mtspr SPRN_DEC,r10; \ b MASKED_DEC_HANDLER_LABEL; \ -1: andi. r10,r10,(PACA_IRQ_DBELL|PACA_IRQ_HMI); \ - bne 2f; \ +1: andi. r10,r10,PACA_IRQ_MUST_HARD_MASK; \ + beq 2f; \ mfspr r10,SPRN_##_H##SRR1; \ xori r10,r10,MSR_EE; /* clear MSR_EE */ \ mtspr SPRN_##_H##SRR1,r10; \ diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 5a8bfee6e187..04d0bbd7a1dd 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -788,7 +788,8 @@ static int register_cpu_online(unsigned int cpu) if (cpu_has_feature(CPU_FTR_PPCAS_ARCH_V2)) device_create_file(s, &dev_attr_pir); - if (cpu_has_feature(CPU_FTR_ARCH_206)) + if (cpu_has_feature(CPU_FTR_ARCH_206) && + !firmware_has_feature(FW_FEATURE_LPAR)) device_create_file(s, &dev_attr_tscr); #endif /* CONFIG_PPC64 */ @@ -873,7 +874,8 @@ static int unregister_cpu_online(unsigned int cpu) if (cpu_has_feature(CPU_FTR_PPCAS_ARCH_V2)) device_remove_file(s, &dev_attr_pir); - if (cpu_has_feature(CPU_FTR_ARCH_206)) + if (cpu_has_feature(CPU_FTR_ARCH_206) && + !firmware_has_feature(FW_FEATURE_LPAR)) device_remove_file(s, &dev_attr_tscr); #endif /* CONFIG_PPC64 */ diff --git a/arch/powerpc/mm/drmem.c b/arch/powerpc/mm/drmem.c index 1604110c4238..916844f99c64 100644 --- a/arch/powerpc/mm/drmem.c +++ b/arch/powerpc/mm/drmem.c @@ -216,6 +216,8 @@ static void __init __walk_drmem_v1_lmbs(const __be32 *prop, const __be32 *usm, u32 i, n_lmbs; n_lmbs = of_read_number(prop++, 1); + if (n_lmbs == 0) + return; for (i = 0; i < n_lmbs; i++) { read_drconf_v1_cell(&lmb, &prop); @@ -245,6 +247,8 @@ static void __init __walk_drmem_v2_lmbs(const __be32 *prop, const __be32 *usm, u32 i, j, lmb_sets; lmb_sets = of_read_number(prop++, 1); + if (lmb_sets == 0) + return; for (i = 0; i < lmb_sets; i++) { read_drconf_v2_cell(&dr_cell, &prop); @@ -354,6 +358,8 @@ static void __init init_drmem_v1_lmbs(const __be32 *prop) struct drmem_lmb *lmb; drmem_info->n_lmbs = of_read_number(prop++, 1); + if (drmem_info->n_lmbs == 0) + return; drmem_info->lmbs = kcalloc(drmem_info->n_lmbs, sizeof(*lmb), GFP_KERNEL); @@ -373,6 +379,8 @@ static void __init init_drmem_v2_lmbs(const __be32 *prop) int lmb_index; lmb_sets = of_read_number(prop++, 1); + if (lmb_sets == 0) + return; /* first pass, calculate the number of LMBs */ p = prop; diff --git a/arch/powerpc/mm/hash64_4k.c b/arch/powerpc/mm/hash64_4k.c index 5a69b51d08a3..d573d7d07f25 100644 --- a/arch/powerpc/mm/hash64_4k.c +++ b/arch/powerpc/mm/hash64_4k.c @@ -55,7 +55,7 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid, * need to add in 0x1 if it's a read-only user page */ rflags = htab_convert_pte_flags(new_pte); - rpte = __real_pte(__pte(old_pte), ptep); + rpte = __real_pte(__pte(old_pte), ptep, PTRS_PER_PTE); if (cpu_has_feature(CPU_FTR_NOEXECUTE) && !cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) @@ -117,7 +117,7 @@ repeat: return -1; } new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | H_PAGE_HASHPTE; - new_pte |= pte_set_hidx(ptep, rpte, 0, slot); + new_pte |= pte_set_hidx(ptep, rpte, 0, slot, PTRS_PER_PTE); } *ptep = __pte(new_pte & ~H_PAGE_BUSY); return 0; diff --git a/arch/powerpc/mm/hash64_64k.c b/arch/powerpc/mm/hash64_64k.c index 2253bbc6a599..e601d95c3b20 100644 --- a/arch/powerpc/mm/hash64_64k.c +++ b/arch/powerpc/mm/hash64_64k.c @@ -86,7 +86,7 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid, subpg_index = (ea & (PAGE_SIZE - 1)) >> shift; vpn = hpt_vpn(ea, vsid, ssize); - rpte = __real_pte(__pte(old_pte), ptep); + rpte = __real_pte(__pte(old_pte), ptep, PTRS_PER_PTE); /* *None of the sub 4k page is hashed */ @@ -214,7 +214,7 @@ repeat: return -1; } - new_pte |= pte_set_hidx(ptep, rpte, subpg_index, slot); + new_pte |= pte_set_hidx(ptep, rpte, subpg_index, slot, PTRS_PER_PTE); new_pte |= H_PAGE_HASHPTE; *ptep = __pte(new_pte & ~H_PAGE_BUSY); @@ -262,7 +262,7 @@ int __hash_page_64K(unsigned long ea, unsigned long access, } while (!pte_xchg(ptep, __pte(old_pte), __pte(new_pte))); rflags = htab_convert_pte_flags(new_pte); - rpte = __real_pte(__pte(old_pte), ptep); + rpte = __real_pte(__pte(old_pte), ptep, PTRS_PER_PTE); if (cpu_has_feature(CPU_FTR_NOEXECUTE) && !cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) @@ -327,7 +327,7 @@ repeat: } new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | H_PAGE_HASHPTE; - new_pte |= pte_set_hidx(ptep, rpte, 0, slot); + new_pte |= pte_set_hidx(ptep, rpte, 0, slot, PTRS_PER_PTE); } *ptep = __pte(new_pte & ~H_PAGE_BUSY); return 0; diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 7d07c7e17db6..cf290d415dcd 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -1008,6 +1008,7 @@ void __init hash__early_init_mmu(void) __pmd_index_size = H_PMD_INDEX_SIZE; __pud_index_size = H_PUD_INDEX_SIZE; __pgd_index_size = H_PGD_INDEX_SIZE; + __pud_cache_index = H_PUD_CACHE_INDEX; __pmd_cache_index = H_PMD_CACHE_INDEX; __pte_table_size = H_PTE_TABLE_SIZE; __pmd_table_size = H_PMD_TABLE_SIZE; diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c index 12511f5a015f..b320f5097a06 100644 --- a/arch/powerpc/mm/hugetlbpage-hash64.c +++ b/arch/powerpc/mm/hugetlbpage-hash64.c @@ -27,7 +27,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, unsigned long vpn; unsigned long old_pte, new_pte; unsigned long rflags, pa, sz; - long slot; + long slot, offset; BUG_ON(shift != mmu_psize_defs[mmu_psize].shift); @@ -63,7 +63,11 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, } while(!pte_xchg(ptep, __pte(old_pte), __pte(new_pte))); rflags = htab_convert_pte_flags(new_pte); - rpte = __real_pte(__pte(old_pte), ptep); + if (unlikely(mmu_psize == MMU_PAGE_16G)) + offset = PTRS_PER_PUD; + else + offset = PTRS_PER_PMD; + rpte = __real_pte(__pte(old_pte), ptep, offset); sz = ((1UL) << shift); if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) @@ -104,7 +108,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, return -1; } - new_pte |= pte_set_hidx(ptep, rpte, 0, slot); + new_pte |= pte_set_hidx(ptep, rpte, 0, slot, offset); } /* diff --git a/arch/powerpc/mm/init-common.c b/arch/powerpc/mm/init-common.c index eb8c6c8c4851..2b656e67f2ea 100644 --- a/arch/powerpc/mm/init-common.c +++ b/arch/powerpc/mm/init-common.c @@ -100,6 +100,6 @@ void pgtable_cache_init(void) * same size as either the pgd or pmd index except with THP enabled * on book3s 64 */ - if (PUD_INDEX_SIZE && !PGT_CACHE(PUD_INDEX_SIZE)) - pgtable_cache_add(PUD_INDEX_SIZE, pud_ctor); + if (PUD_CACHE_INDEX && !PGT_CACHE(PUD_CACHE_INDEX)) + pgtable_cache_add(PUD_CACHE_INDEX, pud_ctor); } diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 314d19ab9385..edd8d0bc9364 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -143,11 +143,6 @@ static void reset_numa_cpu_lookup_table(void) numa_cpu_lookup_table[cpu] = -1; } -static void update_numa_cpu_lookup_table(unsigned int cpu, int node) -{ - numa_cpu_lookup_table[cpu] = node; -} - static void map_cpu_to_node(int cpu, int node) { update_numa_cpu_lookup_table(cpu, node); diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index 573a9a2ee455..2e10a964e290 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -17,9 +17,11 @@ #include <linux/of_fdt.h> #include <linux/mm.h> #include <linux/string_helpers.h> +#include <linux/stop_machine.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> +#include <asm/mmu_context.h> #include <asm/dma.h> #include <asm/machdep.h> #include <asm/mmu.h> @@ -333,6 +335,22 @@ static void __init radix_init_pgtable(void) "r" (TLBIEL_INVAL_SET_LPID), "r" (0)); asm volatile("eieio; tlbsync; ptesync" : : : "memory"); trace_tlbie(0, 0, TLBIEL_INVAL_SET_LPID, 0, 2, 1, 1); + + /* + * The init_mm context is given the first available (non-zero) PID, + * which is the "guard PID" and contains no page table. PIDR should + * never be set to zero because that duplicates the kernel address + * space at the 0x0... offset (quadrant 0)! + * + * An arbitrary PID that may later be allocated by the PID allocator + * for userspace processes must not be used either, because that + * would cause stale user mappings for that PID on CPUs outside of + * the TLB invalidation scheme (because it won't be in mm_cpumask). + * + * So permanently carve out one PID for the purpose of a guard PID. + */ + init_mm.context.id = mmu_base_pid; + mmu_base_pid++; } static void __init radix_init_partition_table(void) @@ -535,6 +553,7 @@ void __init radix__early_init_mmu(void) __pmd_index_size = RADIX_PMD_INDEX_SIZE; __pud_index_size = RADIX_PUD_INDEX_SIZE; __pgd_index_size = RADIX_PGD_INDEX_SIZE; + __pud_cache_index = RADIX_PUD_INDEX_SIZE; __pmd_cache_index = RADIX_PMD_INDEX_SIZE; __pte_table_size = RADIX_PTE_TABLE_SIZE; __pmd_table_size = RADIX_PMD_TABLE_SIZE; @@ -579,7 +598,8 @@ void __init radix__early_init_mmu(void) radix_init_iamr(); radix_init_pgtable(); - + /* Switch to the guard PID before turning on MMU */ + radix__switch_mmu_context(NULL, &init_mm); if (cpu_has_feature(CPU_FTR_HVMODE)) tlbiel_all(); } @@ -604,6 +624,7 @@ void radix__early_init_mmu_secondary(void) } radix_init_iamr(); + radix__switch_mmu_context(NULL, &init_mm); if (cpu_has_feature(CPU_FTR_HVMODE)) tlbiel_all(); } @@ -666,6 +687,30 @@ static void free_pmd_table(pmd_t *pmd_start, pud_t *pud) pud_clear(pud); } +struct change_mapping_params { + pte_t *pte; + unsigned long start; + unsigned long end; + unsigned long aligned_start; + unsigned long aligned_end; +}; + +static int stop_machine_change_mapping(void *data) +{ + struct change_mapping_params *params = + (struct change_mapping_params *)data; + + if (!data) + return -1; + + spin_unlock(&init_mm.page_table_lock); + pte_clear(&init_mm, params->aligned_start, params->pte); + create_physical_mapping(params->aligned_start, params->start); + create_physical_mapping(params->end, params->aligned_end); + spin_lock(&init_mm.page_table_lock); + return 0; +} + static void remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end) { @@ -694,6 +739,52 @@ static void remove_pte_table(pte_t *pte_start, unsigned long addr, } } +/* + * clear the pte and potentially split the mapping helper + */ +static void split_kernel_mapping(unsigned long addr, unsigned long end, + unsigned long size, pte_t *pte) +{ + unsigned long mask = ~(size - 1); + unsigned long aligned_start = addr & mask; + unsigned long aligned_end = addr + size; + struct change_mapping_params params; + bool split_region = false; + + if ((end - addr) < size) { + /* + * We're going to clear the PTE, but not flushed + * the mapping, time to remap and flush. The + * effects if visible outside the processor or + * if we are running in code close to the + * mapping we cleared, we are in trouble. + */ + if (overlaps_kernel_text(aligned_start, addr) || + overlaps_kernel_text(end, aligned_end)) { + /* + * Hack, just return, don't pte_clear + */ + WARN_ONCE(1, "Linear mapping %lx->%lx overlaps kernel " + "text, not splitting\n", addr, end); + return; + } + split_region = true; + } + + if (split_region) { + params.pte = pte; + params.start = addr; + params.end = end; + params.aligned_start = addr & ~(size - 1); + params.aligned_end = min_t(unsigned long, aligned_end, + (unsigned long)__va(memblock_end_of_DRAM())); + stop_machine(stop_machine_change_mapping, ¶ms, NULL); + return; + } + + pte_clear(&init_mm, addr, pte); +} + static void remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end) { @@ -709,13 +800,7 @@ static void remove_pmd_table(pmd_t *pmd_start, unsigned long addr, continue; if (pmd_huge(*pmd)) { - if (!IS_ALIGNED(addr, PMD_SIZE) || - !IS_ALIGNED(next, PMD_SIZE)) { - WARN_ONCE(1, "%s: unaligned range\n", __func__); - continue; - } - - pte_clear(&init_mm, addr, (pte_t *)pmd); + split_kernel_mapping(addr, end, PMD_SIZE, (pte_t *)pmd); continue; } @@ -740,13 +825,7 @@ static void remove_pud_table(pud_t *pud_start, unsigned long addr, continue; if (pud_huge(*pud)) { - if (!IS_ALIGNED(addr, PUD_SIZE) || - !IS_ALIGNED(next, PUD_SIZE)) { - WARN_ONCE(1, "%s: unaligned range\n", __func__); - continue; - } - - pte_clear(&init_mm, addr, (pte_t *)pud); + split_kernel_mapping(addr, end, PUD_SIZE, (pte_t *)pud); continue; } @@ -772,13 +851,7 @@ static void remove_pagetable(unsigned long start, unsigned long end) continue; if (pgd_huge(*pgd)) { - if (!IS_ALIGNED(addr, PGDIR_SIZE) || - !IS_ALIGNED(next, PGDIR_SIZE)) { - WARN_ONCE(1, "%s: unaligned range\n", __func__); - continue; - } - - pte_clear(&init_mm, addr, (pte_t *)pgd); + split_kernel_mapping(addr, end, PGDIR_SIZE, (pte_t *)pgd); continue; } diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index c9a623c2d8a2..28c980eb4422 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -82,6 +82,8 @@ unsigned long __pgd_index_size; EXPORT_SYMBOL(__pgd_index_size); unsigned long __pmd_cache_index; EXPORT_SYMBOL(__pmd_cache_index); +unsigned long __pud_cache_index; +EXPORT_SYMBOL(__pud_cache_index); unsigned long __pte_table_size; EXPORT_SYMBOL(__pte_table_size); unsigned long __pmd_table_size; @@ -471,6 +473,8 @@ void mmu_partition_table_set_entry(unsigned int lpid, unsigned long dw0, if (old & PATB_HR) { asm volatile(PPC_TLBIE_5(%0,%1,2,0,1) : : "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid)); + asm volatile(PPC_TLBIE_5(%0,%1,2,1,1) : : + "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid)); trace_tlbie(lpid, 0, TLBIEL_INVAL_SET_LPID, lpid, 2, 0, 1); } else { asm volatile(PPC_TLBIE_5(%0,%1,2,0,0) : : diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c index 881ebd53ffc2..9b23f12e863c 100644 --- a/arch/powerpc/mm/tlb_hash64.c +++ b/arch/powerpc/mm/tlb_hash64.c @@ -51,7 +51,7 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr, unsigned int psize; int ssize; real_pte_t rpte; - int i; + int i, offset; i = batch->index; @@ -67,6 +67,10 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr, psize = get_slice_psize(mm, addr); /* Mask the address for the correct page size */ addr &= ~((1UL << mmu_psize_defs[psize].shift) - 1); + if (unlikely(psize == MMU_PAGE_16G)) + offset = PTRS_PER_PUD; + else + offset = PTRS_PER_PMD; #else BUG(); psize = pte_pagesize_index(mm, addr, pte); /* shutup gcc */ @@ -78,6 +82,7 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr, * support 64k pages, this might be different from the * hardware page size encoded in the slice table. */ addr &= PAGE_MASK; + offset = PTRS_PER_PTE; } @@ -91,7 +96,7 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr, } WARN_ON(vsid == 0); vpn = hpt_vpn(addr, vsid, ssize); - rpte = __real_pte(__pte(pte), ptep); + rpte = __real_pte(__pte(pte), ptep, offset); /* * Check if we have an active batch on this CPU. If not, just diff --git a/arch/powerpc/platforms/powernv/opal-imc.c b/arch/powerpc/platforms/powernv/opal-imc.c index dd4c9b8b8a81..f6f55ab4980e 100644 --- a/arch/powerpc/platforms/powernv/opal-imc.c +++ b/arch/powerpc/platforms/powernv/opal-imc.c @@ -199,9 +199,11 @@ static void disable_nest_pmu_counters(void) const struct cpumask *l_cpumask; get_online_cpus(); - for_each_online_node(nid) { + for_each_node_with_cpus(nid) { l_cpumask = cpumask_of_node(nid); - cpu = cpumask_first(l_cpumask); + cpu = cpumask_first_and(l_cpumask, cpu_online_mask); + if (cpu >= nr_cpu_ids) + continue; opal_imc_counters_stop(OPAL_IMC_COUNTERS_NEST, get_hard_smp_processor_id(cpu)); } diff --git a/arch/powerpc/platforms/powernv/vas-window.c b/arch/powerpc/platforms/powernv/vas-window.c index 2b3eb01ab110..b7c53a51c31b 100644 --- a/arch/powerpc/platforms/powernv/vas-window.c +++ b/arch/powerpc/platforms/powernv/vas-window.c @@ -1063,16 +1063,16 @@ struct vas_window *vas_tx_win_open(int vasid, enum vas_cop_type cop, rc = PTR_ERR(txwin->paste_kaddr); goto free_window; } + } else { + /* + * A user mapping must ensure that context switch issues + * CP_ABORT for this thread. + */ + rc = set_thread_uses_vas(); + if (rc) + goto free_window; } - /* - * Now that we have a send window, ensure context switch issues - * CP_ABORT for this thread. - */ - rc = -EINVAL; - if (set_thread_uses_vas() < 0) - goto free_window; - set_vinst_win(vinst, txwin); return txwin; diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index dceb51454d8d..652d3e96b812 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -36,6 +36,7 @@ #include <asm/xics.h> #include <asm/xive.h> #include <asm/plpar_wrappers.h> +#include <asm/topology.h> #include "pseries.h" #include "offline_states.h" @@ -331,6 +332,7 @@ static void pseries_remove_processor(struct device_node *np) BUG_ON(cpu_online(cpu)); set_cpu_present(cpu, false); set_hard_smp_processor_id(cpu, -1); + update_numa_cpu_lookup_table(cpu, -1); break; } if (cpu >= nr_cpu_ids) @@ -340,8 +342,6 @@ static void pseries_remove_processor(struct device_node *np) cpu_maps_update_done(); } -extern int find_and_online_cpu_nid(int cpu); - static int dlpar_online_cpu(struct device_node *dn) { int rc = 0; diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index 81d8614e7379..5e1ef9150182 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -49,6 +49,28 @@ static irqreturn_t ras_error_interrupt(int irq, void *dev_id); /* + * Enable the hotplug interrupt late because processing them may touch other + * devices or systems (e.g. hugepages) that have not been initialized at the + * subsys stage. + */ +int __init init_ras_hotplug_IRQ(void) +{ + struct device_node *np; + + /* Hotplug Events */ + np = of_find_node_by_path("/event-sources/hot-plug-events"); + if (np != NULL) { + if (dlpar_workqueue_init() == 0) + request_event_sources_irqs(np, ras_hotplug_interrupt, + "RAS_HOTPLUG"); + of_node_put(np); + } + + return 0; +} +machine_late_initcall(pseries, init_ras_hotplug_IRQ); + +/* * Initialize handlers for the set of interrupts caused by hardware errors * and power system events. */ @@ -66,15 +88,6 @@ static int __init init_ras_IRQ(void) of_node_put(np); } - /* Hotplug Events */ - np = of_find_node_by_path("/event-sources/hot-plug-events"); - if (np != NULL) { - if (dlpar_workqueue_init() == 0) - request_event_sources_irqs(np, ras_hotplug_interrupt, - "RAS_HOTPLUG"); - of_node_put(np); - } - /* EPOW Events */ np = of_find_node_by_path("/event-sources/epow-events"); if (np != NULL) { diff --git a/arch/powerpc/sysdev/xive/spapr.c b/arch/powerpc/sysdev/xive/spapr.c index d9c4c9366049..091f1d0d0af1 100644 --- a/arch/powerpc/sysdev/xive/spapr.c +++ b/arch/powerpc/sysdev/xive/spapr.c @@ -356,7 +356,8 @@ static int xive_spapr_configure_queue(u32 target, struct xive_q *q, u8 prio, rc = plpar_int_get_queue_info(0, target, prio, &esn_page, &esn_size); if (rc) { - pr_err("Error %lld getting queue info prio %d\n", rc, prio); + pr_err("Error %lld getting queue info CPU %d prio %d\n", rc, + target, prio); rc = -EIO; goto fail; } @@ -370,7 +371,8 @@ static int xive_spapr_configure_queue(u32 target, struct xive_q *q, u8 prio, /* Configure and enable the queue in HW */ rc = plpar_int_set_queue_config(flags, target, prio, qpage_phys, order); if (rc) { - pr_err("Error %lld setting queue for prio %d\n", rc, prio); + pr_err("Error %lld setting queue for CPU %d prio %d\n", rc, + target, prio); rc = -EIO; } else { q->qpage = qpage; @@ -389,8 +391,8 @@ static int xive_spapr_setup_queue(unsigned int cpu, struct xive_cpu *xc, if (IS_ERR(qpage)) return PTR_ERR(qpage); - return xive_spapr_configure_queue(cpu, q, prio, qpage, - xive_queue_shift); + return xive_spapr_configure_queue(get_hard_smp_processor_id(cpu), + q, prio, qpage, xive_queue_shift); } static void xive_spapr_cleanup_queue(unsigned int cpu, struct xive_cpu *xc, @@ -399,10 +401,12 @@ static void xive_spapr_cleanup_queue(unsigned int cpu, struct xive_cpu *xc, struct xive_q *q = &xc->queue[prio]; unsigned int alloc_order; long rc; + int hw_cpu = get_hard_smp_processor_id(cpu); - rc = plpar_int_set_queue_config(0, cpu, prio, 0, 0); + rc = plpar_int_set_queue_config(0, hw_cpu, prio, 0, 0); if (rc) - pr_err("Error %ld setting queue for prio %d\n", rc, prio); + pr_err("Error %ld setting queue for CPU %d prio %d\n", rc, + hw_cpu, prio); alloc_order = xive_alloc_order(xive_queue_shift); free_pages((unsigned long)q->qpage, alloc_order); diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index b6722c246d9c..04807c7f64cc 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -8,7 +8,6 @@ config RISCV select OF select OF_EARLY_FLATTREE select OF_IRQ - select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select ARCH_WANT_FRAME_POINTERS select CLONE_BACKWARDS select COMMON_CLK @@ -20,7 +19,6 @@ config RISCV select GENERIC_STRNLEN_USER select GENERIC_SMP_IDLE_THREAD select GENERIC_ATOMIC64 if !64BIT || !RISCV_ISA_A - select ARCH_WANT_OPTIONAL_GPIOLIB select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP select HAVE_DMA_API_DEBUG @@ -34,7 +32,6 @@ config RISCV select HAVE_ARCH_TRACEHOOK select MODULES_USE_ELF_RELA if MODULES select THREAD_INFO_IN_TASK - select RISCV_IRQ_INTC select RISCV_TIMER config MMU diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 87fc045be51f..56fa592cfa34 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -172,6 +172,9 @@ ENTRY(handle_exception) move a1, sp /* pt_regs */ tail do_IRQ 1: + /* Exceptions run with interrupts enabled */ + csrs sstatus, SR_SIE + /* Handle syscalls */ li t0, EXC_SYSCALL beq s4, t0, handle_syscall @@ -198,8 +201,6 @@ handle_syscall: */ addi s2, s2, 0x4 REG_S s2, PT_SEPC(sp) - /* System calls run with interrupts enabled */ - csrs sstatus, SR_SIE /* Trace syscalls, but only if requested by the user. */ REG_L t0, TASK_TI_FLAGS(tp) andi t0, t0, _TIF_SYSCALL_TRACE diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 226eeb190f90..6e07ed37bbff 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -64,7 +64,7 @@ ENTRY(_start) /* Start the kernel */ mv a0, s0 mv a1, s1 - call sbi_save + call parse_dtb tail start_kernel relocate: diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 09f7064e898c..c11f40c1b2a8 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -144,7 +144,7 @@ asmlinkage void __init setup_vm(void) #endif } -void __init sbi_save(unsigned int hartid, void *dtb) +void __init parse_dtb(unsigned int hartid, void *dtb) { early_init_dt_scan(__va(dtb)); } diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 6bf594ace663..8767e45f1b2b 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -430,6 +430,8 @@ config SPARC_LEON depends on SPARC32 select USB_EHCI_BIG_ENDIAN_MMIO select USB_EHCI_BIG_ENDIAN_DESC + select USB_UHCI_BIG_ENDIAN_MMIO + select USB_UHCI_BIG_ENDIAN_DESC ---help--- If you say Y here if you are running on a SPARC-LEON processor. The LEON processor is a synthesizable VHDL model of the diff --git a/arch/sparc/include/asm/bug.h b/arch/sparc/include/asm/bug.h index 6f17528356b2..ea53e418f6c0 100644 --- a/arch/sparc/include/asm/bug.h +++ b/arch/sparc/include/asm/bug.h @@ -9,10 +9,14 @@ void do_BUG(const char *file, int line); #define BUG() do { \ do_BUG(__FILE__, __LINE__); \ + barrier_before_unreachable(); \ __builtin_trap(); \ } while (0) #else -#define BUG() __builtin_trap() +#define BUG() do { \ + barrier_before_unreachable(); \ + __builtin_trap(); \ +} while (0) #endif #define HAVE_ARCH_BUG diff --git a/arch/x86/.gitignore b/arch/x86/.gitignore index aff152c87cf4..5a82bac5e0bc 100644 --- a/arch/x86/.gitignore +++ b/arch/x86/.gitignore @@ -1,6 +1,7 @@ boot/compressed/vmlinux tools/test_get_len tools/insn_sanity +tools/insn_decoder_test purgatory/kexec-purgatory.c purgatory/purgatory.ro diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 63bf349b2b24..c1236b187824 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -423,12 +423,6 @@ config X86_MPPARSE For old smp systems that do not have proper acpi support. Newer systems (esp with 64bit cpus) with acpi support, MADT and DSDT will override it -config X86_BIGSMP - bool "Support for big SMP systems with more than 8 CPUs" - depends on X86_32 && SMP - ---help--- - This option is needed for the systems that have more than 8 CPUs - config GOLDFISH def_bool y depends on X86_GOLDFISH @@ -460,6 +454,12 @@ config INTEL_RDT Say N if unsure. if X86_32 +config X86_BIGSMP + bool "Support for big SMP systems with more than 8 CPUs" + depends on SMP + ---help--- + This option is needed for the systems that have more than 8 CPUs + config X86_EXTENDED_PLATFORM bool "Support for extended (non-PC) x86 platforms" default y @@ -949,25 +949,66 @@ config MAXSMP Enable maximum number of CPUS and NUMA Nodes for this architecture. If unsure, say N. +# +# The maximum number of CPUs supported: +# +# The main config value is NR_CPUS, which defaults to NR_CPUS_DEFAULT, +# and which can be configured interactively in the +# [NR_CPUS_RANGE_BEGIN ... NR_CPUS_RANGE_END] range. +# +# The ranges are different on 32-bit and 64-bit kernels, depending on +# hardware capabilities and scalability features of the kernel. +# +# ( If MAXSMP is enabled we just use the highest possible value and disable +# interactive configuration. ) +# + +config NR_CPUS_RANGE_BEGIN + int + default NR_CPUS_RANGE_END if MAXSMP + default 1 if !SMP + default 2 + +config NR_CPUS_RANGE_END + int + depends on X86_32 + default 64 if SMP && X86_BIGSMP + default 8 if SMP && !X86_BIGSMP + default 1 if !SMP + +config NR_CPUS_RANGE_END + int + depends on X86_64 + default 8192 if SMP && ( MAXSMP || CPUMASK_OFFSTACK) + default 512 if SMP && (!MAXSMP && !CPUMASK_OFFSTACK) + default 1 if !SMP + +config NR_CPUS_DEFAULT + int + depends on X86_32 + default 32 if X86_BIGSMP + default 8 if SMP + default 1 if !SMP + +config NR_CPUS_DEFAULT + int + depends on X86_64 + default 8192 if MAXSMP + default 64 if SMP + default 1 if !SMP + config NR_CPUS int "Maximum number of CPUs" if SMP && !MAXSMP - range 2 8 if SMP && X86_32 && !X86_BIGSMP - range 2 64 if SMP && X86_32 && X86_BIGSMP - range 2 512 if SMP && !MAXSMP && !CPUMASK_OFFSTACK && X86_64 - range 2 8192 if SMP && !MAXSMP && CPUMASK_OFFSTACK && X86_64 - default "1" if !SMP - default "8192" if MAXSMP - default "32" if SMP && X86_BIGSMP - default "8" if SMP && X86_32 - default "64" if SMP + range NR_CPUS_RANGE_BEGIN NR_CPUS_RANGE_END + default NR_CPUS_DEFAULT ---help--- This allows you to specify the maximum number of CPUs which this kernel will support. If CPUMASK_OFFSTACK is enabled, the maximum supported value is 8192, otherwise the maximum value is 512. The minimum value which makes sense is 2. - This is purely to save memory - each supported CPU adds - approximately eight kilobytes to the kernel image. + This is purely to save memory: each supported CPU adds about 8KB + to the kernel image. config SCHED_SMT bool "SMT (Hyperthreading) scheduler support" @@ -1363,7 +1404,7 @@ config HIGHMEM4G config HIGHMEM64G bool "64GB" - depends on !M486 + depends on !M486 && !M586 && !M586TSC && !M586MMX && !MGEODE_LX && !MGEODEGX1 && !MCYRIXIII && !MELAN && !MWINCHIPC6 && !WINCHIP3D && !MK6 select X86_PAE ---help--- Select this if you have a 32-bit processor and more than 4 diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 65a9a4716e34..8b8d2297d486 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -374,7 +374,7 @@ config X86_TSC config X86_CMPXCHG64 def_bool y - depends on X86_PAE || X86_64 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MATOM + depends on X86_PAE || X86_64 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586TSC || M586MMX || MATOM || MGEODE_LX || MGEODEGX1 || MK6 || MK7 || MK8 # this should be set for all -march=.. options where the compiler # generates cmov. @@ -385,7 +385,7 @@ config X86_CMOV config X86_MINIMUM_CPU_FAMILY int default "64" if X86_64 - default "6" if X86_32 && X86_P6_NOP + default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCRUSOE || MCORE2 || MK7 || MK8) default "5" if X86_32 && X86_CMPXCHG64 default "4" diff --git a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c index 36870b26067a..d08805032f01 100644 --- a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c +++ b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c @@ -57,10 +57,12 @@ void sha512_mb_mgr_init_avx2(struct sha512_mb_mgr *state) { unsigned int j; - state->lens[0] = 0; - state->lens[1] = 1; - state->lens[2] = 2; - state->lens[3] = 3; + /* initially all lanes are unused */ + state->lens[0] = 0xFFFFFFFF00000000; + state->lens[1] = 0xFFFFFFFF00000001; + state->lens[2] = 0xFFFFFFFF00000002; + state->lens[3] = 0xFFFFFFFF00000003; + state->unused_lanes = 0xFF03020100; for (j = 0; j < 4; j++) state->ldata[j].job_in_lane = NULL; diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 3f48f695d5e6..dce7092ab24a 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -97,80 +97,69 @@ For 32-bit we have the following conventions - kernel is built with #define SIZEOF_PTREGS 21*8 - .macro ALLOC_PT_GPREGS_ON_STACK - addq $-(15*8), %rsp - .endm +.macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax + /* + * Push registers and sanitize registers of values that a + * speculation attack might otherwise want to exploit. The + * lower registers are likely clobbered well before they + * could be put to use in a speculative execution gadget. + * Interleave XOR with PUSH for better uop scheduling: + */ + pushq %rdi /* pt_regs->di */ + pushq %rsi /* pt_regs->si */ + pushq \rdx /* pt_regs->dx */ + pushq %rcx /* pt_regs->cx */ + pushq \rax /* pt_regs->ax */ + pushq %r8 /* pt_regs->r8 */ + xorq %r8, %r8 /* nospec r8 */ + pushq %r9 /* pt_regs->r9 */ + xorq %r9, %r9 /* nospec r9 */ + pushq %r10 /* pt_regs->r10 */ + xorq %r10, %r10 /* nospec r10 */ + pushq %r11 /* pt_regs->r11 */ + xorq %r11, %r11 /* nospec r11*/ + pushq %rbx /* pt_regs->rbx */ + xorl %ebx, %ebx /* nospec rbx*/ + pushq %rbp /* pt_regs->rbp */ + xorl %ebp, %ebp /* nospec rbp*/ + pushq %r12 /* pt_regs->r12 */ + xorq %r12, %r12 /* nospec r12*/ + pushq %r13 /* pt_regs->r13 */ + xorq %r13, %r13 /* nospec r13*/ + pushq %r14 /* pt_regs->r14 */ + xorq %r14, %r14 /* nospec r14*/ + pushq %r15 /* pt_regs->r15 */ + xorq %r15, %r15 /* nospec r15*/ + UNWIND_HINT_REGS +.endm - .macro SAVE_C_REGS_HELPER offset=0 rax=1 rcx=1 r8910=1 r11=1 - .if \r11 - movq %r11, 6*8+\offset(%rsp) - .endif - .if \r8910 - movq %r10, 7*8+\offset(%rsp) - movq %r9, 8*8+\offset(%rsp) - movq %r8, 9*8+\offset(%rsp) - .endif - .if \rax - movq %rax, 10*8+\offset(%rsp) - .endif - .if \rcx - movq %rcx, 11*8+\offset(%rsp) - .endif - movq %rdx, 12*8+\offset(%rsp) - movq %rsi, 13*8+\offset(%rsp) - movq %rdi, 14*8+\offset(%rsp) - UNWIND_HINT_REGS offset=\offset extra=0 - .endm - .macro SAVE_C_REGS offset=0 - SAVE_C_REGS_HELPER \offset, 1, 1, 1, 1 - .endm - .macro SAVE_C_REGS_EXCEPT_RAX_RCX offset=0 - SAVE_C_REGS_HELPER \offset, 0, 0, 1, 1 - .endm - .macro SAVE_C_REGS_EXCEPT_R891011 - SAVE_C_REGS_HELPER 0, 1, 1, 0, 0 - .endm - .macro SAVE_C_REGS_EXCEPT_RCX_R891011 - SAVE_C_REGS_HELPER 0, 1, 0, 0, 0 - .endm - .macro SAVE_C_REGS_EXCEPT_RAX_RCX_R11 - SAVE_C_REGS_HELPER 0, 0, 0, 1, 0 - .endm - - .macro SAVE_EXTRA_REGS offset=0 - movq %r15, 0*8+\offset(%rsp) - movq %r14, 1*8+\offset(%rsp) - movq %r13, 2*8+\offset(%rsp) - movq %r12, 3*8+\offset(%rsp) - movq %rbp, 4*8+\offset(%rsp) - movq %rbx, 5*8+\offset(%rsp) - UNWIND_HINT_REGS offset=\offset - .endm - - .macro POP_EXTRA_REGS +.macro POP_REGS pop_rdi=1 skip_r11rcx=0 popq %r15 popq %r14 popq %r13 popq %r12 popq %rbp popq %rbx - .endm - - .macro POP_C_REGS + .if \skip_r11rcx + popq %rsi + .else popq %r11 + .endif popq %r10 popq %r9 popq %r8 popq %rax + .if \skip_r11rcx + popq %rsi + .else popq %rcx + .endif popq %rdx popq %rsi + .if \pop_rdi popq %rdi - .endm - - .macro icebp - .byte 0xf1 - .endm + .endif +.endm /* * This is a sneaky trick to help the unwinder find pt_regs on the stack. The @@ -178,7 +167,7 @@ For 32-bit we have the following conventions - kernel is built with * is just setting the LSB, which makes it an invalid stack address and is also * a signal to the unwinder that it's a pt_regs pointer in disguise. * - * NOTE: This macro must be used *after* SAVE_EXTRA_REGS because it corrupts + * NOTE: This macro must be used *after* PUSH_AND_CLEAR_REGS because it corrupts * the original rbp. */ .macro ENCODE_FRAME_POINTER ptregs_offset=0 diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 30c8c5344c4a..8971bd64d515 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -213,7 +213,7 @@ ENTRY(entry_SYSCALL_64) swapgs /* - * This path is not taken when PAGE_TABLE_ISOLATION is disabled so it + * This path is only taken when PAGE_TABLE_ISOLATION is disabled so it * is not required to switch CR3. */ movq %rsp, PER_CPU_VAR(rsp_scratch) @@ -227,22 +227,8 @@ ENTRY(entry_SYSCALL_64) pushq %rcx /* pt_regs->ip */ GLOBAL(entry_SYSCALL_64_after_hwframe) pushq %rax /* pt_regs->orig_ax */ - pushq %rdi /* pt_regs->di */ - pushq %rsi /* pt_regs->si */ - pushq %rdx /* pt_regs->dx */ - pushq %rcx /* pt_regs->cx */ - pushq $-ENOSYS /* pt_regs->ax */ - pushq %r8 /* pt_regs->r8 */ - pushq %r9 /* pt_regs->r9 */ - pushq %r10 /* pt_regs->r10 */ - pushq %r11 /* pt_regs->r11 */ - pushq %rbx /* pt_regs->rbx */ - pushq %rbp /* pt_regs->rbp */ - pushq %r12 /* pt_regs->r12 */ - pushq %r13 /* pt_regs->r13 */ - pushq %r14 /* pt_regs->r14 */ - pushq %r15 /* pt_regs->r15 */ - UNWIND_HINT_REGS + + PUSH_AND_CLEAR_REGS rax=$-ENOSYS TRACE_IRQS_OFF @@ -321,15 +307,7 @@ GLOBAL(entry_SYSCALL_64_after_hwframe) syscall_return_via_sysret: /* rcx and r11 are already restored (see code above) */ UNWIND_HINT_EMPTY - POP_EXTRA_REGS - popq %rsi /* skip r11 */ - popq %r10 - popq %r9 - popq %r8 - popq %rax - popq %rsi /* skip rcx */ - popq %rdx - popq %rsi + POP_REGS pop_rdi=0 skip_r11rcx=1 /* * Now all regs are restored except RSP and RDI. @@ -559,9 +537,7 @@ END(irq_entries_start) call switch_to_thread_stack 1: - ALLOC_PT_GPREGS_ON_STACK - SAVE_C_REGS - SAVE_EXTRA_REGS + PUSH_AND_CLEAR_REGS ENCODE_FRAME_POINTER testb $3, CS(%rsp) @@ -622,15 +598,7 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode) ud2 1: #endif - POP_EXTRA_REGS - popq %r11 - popq %r10 - popq %r9 - popq %r8 - popq %rax - popq %rcx - popq %rdx - popq %rsi + POP_REGS pop_rdi=0 /* * The stack is now user RDI, orig_ax, RIP, CS, EFLAGS, RSP, SS. @@ -688,8 +656,7 @@ GLOBAL(restore_regs_and_return_to_kernel) ud2 1: #endif - POP_EXTRA_REGS - POP_C_REGS + POP_REGS addq $8, %rsp /* skip regs->orig_ax */ /* * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization @@ -908,7 +875,9 @@ ENTRY(\sym) pushq $-1 /* ORIG_RAX: no syscall to restart */ .endif - ALLOC_PT_GPREGS_ON_STACK + /* Save all registers in pt_regs */ + PUSH_AND_CLEAR_REGS + ENCODE_FRAME_POINTER .if \paranoid < 2 testb $3, CS(%rsp) /* If coming from userspace, switch stacks */ @@ -1121,9 +1090,7 @@ ENTRY(xen_failsafe_callback) addq $0x30, %rsp UNWIND_HINT_IRET_REGS pushq $-1 /* orig_ax = -1 => not a system call */ - ALLOC_PT_GPREGS_ON_STACK - SAVE_C_REGS - SAVE_EXTRA_REGS + PUSH_AND_CLEAR_REGS ENCODE_FRAME_POINTER jmp error_exit END(xen_failsafe_callback) @@ -1163,16 +1130,13 @@ idtentry machine_check do_mce has_error_code=0 paranoid=1 #endif /* - * Save all registers in pt_regs, and switch gs if needed. + * Switch gs if needed. * Use slow, but surefire "are we in kernel?" check. * Return: ebx=0: need swapgs on exit, ebx=1: otherwise */ ENTRY(paranoid_entry) UNWIND_HINT_FUNC cld - SAVE_C_REGS 8 - SAVE_EXTRA_REGS 8 - ENCODE_FRAME_POINTER 8 movl $1, %ebx movl $MSR_GS_BASE, %ecx rdmsr @@ -1211,21 +1175,18 @@ ENTRY(paranoid_exit) jmp .Lparanoid_exit_restore .Lparanoid_exit_no_swapgs: TRACE_IRQS_IRETQ_DEBUG + RESTORE_CR3 scratch_reg=%rbx save_reg=%r14 .Lparanoid_exit_restore: jmp restore_regs_and_return_to_kernel END(paranoid_exit) /* - * Save all registers in pt_regs, and switch gs if needed. + * Switch gs if needed. * Return: EBX=0: came from user mode; EBX=1: otherwise */ ENTRY(error_entry) - UNWIND_HINT_FUNC + UNWIND_HINT_REGS offset=8 cld - SAVE_C_REGS 8 - SAVE_EXTRA_REGS 8 - ENCODE_FRAME_POINTER 8 - xorl %ebx, %ebx testb $3, CS+8(%rsp) jz .Lerror_kernelspace @@ -1406,22 +1367,7 @@ ENTRY(nmi) pushq 1*8(%rdx) /* pt_regs->rip */ UNWIND_HINT_IRET_REGS pushq $-1 /* pt_regs->orig_ax */ - pushq %rdi /* pt_regs->di */ - pushq %rsi /* pt_regs->si */ - pushq (%rdx) /* pt_regs->dx */ - pushq %rcx /* pt_regs->cx */ - pushq %rax /* pt_regs->ax */ - pushq %r8 /* pt_regs->r8 */ - pushq %r9 /* pt_regs->r9 */ - pushq %r10 /* pt_regs->r10 */ - pushq %r11 /* pt_regs->r11 */ - pushq %rbx /* pt_regs->rbx */ - pushq %rbp /* pt_regs->rbp */ - pushq %r12 /* pt_regs->r12 */ - pushq %r13 /* pt_regs->r13 */ - pushq %r14 /* pt_regs->r14 */ - pushq %r15 /* pt_regs->r15 */ - UNWIND_HINT_REGS + PUSH_AND_CLEAR_REGS rdx=(%rdx) ENCODE_FRAME_POINTER /* @@ -1631,7 +1577,8 @@ end_repeat_nmi: * frame to point back to repeat_nmi. */ pushq $-1 /* ORIG_RAX: no syscall to restart */ - ALLOC_PT_GPREGS_ON_STACK + PUSH_AND_CLEAR_REGS + ENCODE_FRAME_POINTER /* * Use paranoid_entry to handle SWAPGS, but no need to use paranoid_exit @@ -1655,8 +1602,7 @@ end_repeat_nmi: nmi_swapgs: SWAPGS_UNSAFE_STACK nmi_restore: - POP_EXTRA_REGS - POP_C_REGS + POP_REGS /* * Skip orig_ax and the "outermost" frame to point RSP at the "iret" diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 98d5358e4041..fd65e016e413 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -85,15 +85,25 @@ ENTRY(entry_SYSENTER_compat) pushq %rcx /* pt_regs->cx */ pushq $-ENOSYS /* pt_regs->ax */ pushq $0 /* pt_regs->r8 = 0 */ + xorq %r8, %r8 /* nospec r8 */ pushq $0 /* pt_regs->r9 = 0 */ + xorq %r9, %r9 /* nospec r9 */ pushq $0 /* pt_regs->r10 = 0 */ + xorq %r10, %r10 /* nospec r10 */ pushq $0 /* pt_regs->r11 = 0 */ + xorq %r11, %r11 /* nospec r11 */ pushq %rbx /* pt_regs->rbx */ + xorl %ebx, %ebx /* nospec rbx */ pushq %rbp /* pt_regs->rbp (will be overwritten) */ + xorl %ebp, %ebp /* nospec rbp */ pushq $0 /* pt_regs->r12 = 0 */ + xorq %r12, %r12 /* nospec r12 */ pushq $0 /* pt_regs->r13 = 0 */ + xorq %r13, %r13 /* nospec r13 */ pushq $0 /* pt_regs->r14 = 0 */ + xorq %r14, %r14 /* nospec r14 */ pushq $0 /* pt_regs->r15 = 0 */ + xorq %r15, %r15 /* nospec r15 */ cld /* @@ -214,15 +224,25 @@ GLOBAL(entry_SYSCALL_compat_after_hwframe) pushq %rbp /* pt_regs->cx (stashed in bp) */ pushq $-ENOSYS /* pt_regs->ax */ pushq $0 /* pt_regs->r8 = 0 */ + xorq %r8, %r8 /* nospec r8 */ pushq $0 /* pt_regs->r9 = 0 */ + xorq %r9, %r9 /* nospec r9 */ pushq $0 /* pt_regs->r10 = 0 */ + xorq %r10, %r10 /* nospec r10 */ pushq $0 /* pt_regs->r11 = 0 */ + xorq %r11, %r11 /* nospec r11 */ pushq %rbx /* pt_regs->rbx */ + xorl %ebx, %ebx /* nospec rbx */ pushq %rbp /* pt_regs->rbp (will be overwritten) */ + xorl %ebp, %ebp /* nospec rbp */ pushq $0 /* pt_regs->r12 = 0 */ + xorq %r12, %r12 /* nospec r12 */ pushq $0 /* pt_regs->r13 = 0 */ + xorq %r13, %r13 /* nospec r13 */ pushq $0 /* pt_regs->r14 = 0 */ + xorq %r14, %r14 /* nospec r14 */ pushq $0 /* pt_regs->r15 = 0 */ + xorq %r15, %r15 /* nospec r15 */ /* * User mode is traced as though IRQs are on, and SYSENTER @@ -338,15 +358,25 @@ ENTRY(entry_INT80_compat) pushq %rcx /* pt_regs->cx */ pushq $-ENOSYS /* pt_regs->ax */ pushq $0 /* pt_regs->r8 = 0 */ + xorq %r8, %r8 /* nospec r8 */ pushq $0 /* pt_regs->r9 = 0 */ + xorq %r9, %r9 /* nospec r9 */ pushq $0 /* pt_regs->r10 = 0 */ + xorq %r10, %r10 /* nospec r10 */ pushq $0 /* pt_regs->r11 = 0 */ + xorq %r11, %r11 /* nospec r11 */ pushq %rbx /* pt_regs->rbx */ + xorl %ebx, %ebx /* nospec rbx */ pushq %rbp /* pt_regs->rbp */ + xorl %ebp, %ebp /* nospec rbp */ pushq %r12 /* pt_regs->r12 */ + xorq %r12, %r12 /* nospec r12 */ pushq %r13 /* pt_regs->r13 */ + xorq %r13, %r13 /* nospec r13 */ pushq %r14 /* pt_regs->r14 */ + xorq %r14, %r14 /* nospec r14 */ pushq %r15 /* pt_regs->r15 */ + xorq %r15, %r15 /* nospec r15 */ cld /* diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 731153a4681e..56457cb73448 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3559,7 +3559,7 @@ static int intel_snb_pebs_broken(int cpu) break; case INTEL_FAM6_SANDYBRIDGE_X: - switch (cpu_data(cpu).x86_mask) { + switch (cpu_data(cpu).x86_stepping) { case 6: rev = 0x618; break; case 7: rev = 0x70c; break; } diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index ae64d0b69729..cf372b90557e 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -1186,7 +1186,7 @@ void __init intel_pmu_lbr_init_atom(void) * on PMU interrupt */ if (boot_cpu_data.x86_model == 28 - && boot_cpu_data.x86_mask < 10) { + && boot_cpu_data.x86_stepping < 10) { pr_cont("LBR disabled due to erratum"); return; } diff --git a/arch/x86/events/intel/p6.c b/arch/x86/events/intel/p6.c index a5604c352930..408879b0c0d4 100644 --- a/arch/x86/events/intel/p6.c +++ b/arch/x86/events/intel/p6.c @@ -234,7 +234,7 @@ static __initconst const struct x86_pmu p6_pmu = { static __init void p6_pmu_rdpmc_quirk(void) { - if (boot_cpu_data.x86_mask < 9) { + if (boot_cpu_data.x86_stepping < 9) { /* * PPro erratum 26; fixed in stepping 9 and above. */ diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index 44f5d79d5105..11881726ed37 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -94,7 +94,7 @@ static inline unsigned int acpi_processor_cstate_check(unsigned int max_cstate) if (boot_cpu_data.x86 == 0x0F && boot_cpu_data.x86_vendor == X86_VENDOR_AMD && boot_cpu_data.x86_model <= 0x05 && - boot_cpu_data.x86_mask < 0x0A) + boot_cpu_data.x86_stepping < 0x0A) return 1; else if (boot_cpu_has(X86_BUG_AMD_APIC_C1E)) return 1; diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index 30d406146016..e1259f043ae9 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -40,7 +40,7 @@ static inline unsigned long array_index_mask_nospec(unsigned long index, asm ("cmp %1,%2; sbb %0,%0;" :"=r" (mask) - :"r"(size),"r" (index) + :"g"(size),"r" (index) :"cc"); return mask; } diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index 34d99af43994..6804d6642767 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -5,23 +5,20 @@ #include <linux/stringify.h> /* - * Since some emulators terminate on UD2, we cannot use it for WARN. - * Since various instruction decoders disagree on the length of UD1, - * we cannot use it either. So use UD0 for WARN. + * Despite that some emulators terminate on UD2, we use it for WARN(). * - * (binutils knows about "ud1" but {en,de}codes it as 2 bytes, whereas - * our kernel decoder thinks it takes a ModRM byte, which seems consistent - * with various things like the Intel SDM instruction encoding rules) + * Since various instruction decoders/specs disagree on the encoding of + * UD0/UD1. */ -#define ASM_UD0 ".byte 0x0f, 0xff" +#define ASM_UD0 ".byte 0x0f, 0xff" /* + ModRM (for Intel) */ #define ASM_UD1 ".byte 0x0f, 0xb9" /* + ModRM */ #define ASM_UD2 ".byte 0x0f, 0x0b" #define INSN_UD0 0xff0f #define INSN_UD2 0x0b0f -#define LEN_UD0 2 +#define LEN_UD2 2 #ifdef CONFIG_GENERIC_BUG @@ -77,7 +74,11 @@ do { \ unreachable(); \ } while (0) -#define __WARN_FLAGS(flags) _BUG_FLAGS(ASM_UD0, BUGFLAG_WARNING|(flags)) +#define __WARN_FLAGS(flags) \ +do { \ + _BUG_FLAGS(ASM_UD2, BUGFLAG_WARNING|(flags)); \ + annotate_reachable(); \ +} while (0) #include <asm-generic/bug.h> diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 70eddb3922ff..736771c9822e 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -148,45 +148,46 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); */ static __always_inline __pure bool _static_cpu_has(u16 bit) { - asm_volatile_goto("1: jmp 6f\n" - "2:\n" - ".skip -(((5f-4f) - (2b-1b)) > 0) * " - "((5f-4f) - (2b-1b)),0x90\n" - "3:\n" - ".section .altinstructions,\"a\"\n" - " .long 1b - .\n" /* src offset */ - " .long 4f - .\n" /* repl offset */ - " .word %P1\n" /* always replace */ - " .byte 3b - 1b\n" /* src len */ - " .byte 5f - 4f\n" /* repl len */ - " .byte 3b - 2b\n" /* pad len */ - ".previous\n" - ".section .altinstr_replacement,\"ax\"\n" - "4: jmp %l[t_no]\n" - "5:\n" - ".previous\n" - ".section .altinstructions,\"a\"\n" - " .long 1b - .\n" /* src offset */ - " .long 0\n" /* no replacement */ - " .word %P0\n" /* feature bit */ - " .byte 3b - 1b\n" /* src len */ - " .byte 0\n" /* repl len */ - " .byte 0\n" /* pad len */ - ".previous\n" - ".section .altinstr_aux,\"ax\"\n" - "6:\n" - " testb %[bitnum],%[cap_byte]\n" - " jnz %l[t_yes]\n" - " jmp %l[t_no]\n" - ".previous\n" - : : "i" (bit), "i" (X86_FEATURE_ALWAYS), - [bitnum] "i" (1 << (bit & 7)), - [cap_byte] "m" (((const char *)boot_cpu_data.x86_capability)[bit >> 3]) - : : t_yes, t_no); - t_yes: - return true; - t_no: - return false; + asm_volatile_goto("1: jmp 6f\n" + "2:\n" + ".skip -(((5f-4f) - (2b-1b)) > 0) * " + "((5f-4f) - (2b-1b)),0x90\n" + "3:\n" + ".section .altinstructions,\"a\"\n" + " .long 1b - .\n" /* src offset */ + " .long 4f - .\n" /* repl offset */ + " .word %P[always]\n" /* always replace */ + " .byte 3b - 1b\n" /* src len */ + " .byte 5f - 4f\n" /* repl len */ + " .byte 3b - 2b\n" /* pad len */ + ".previous\n" + ".section .altinstr_replacement,\"ax\"\n" + "4: jmp %l[t_no]\n" + "5:\n" + ".previous\n" + ".section .altinstructions,\"a\"\n" + " .long 1b - .\n" /* src offset */ + " .long 0\n" /* no replacement */ + " .word %P[feature]\n" /* feature bit */ + " .byte 3b - 1b\n" /* src len */ + " .byte 0\n" /* repl len */ + " .byte 0\n" /* pad len */ + ".previous\n" + ".section .altinstr_aux,\"ax\"\n" + "6:\n" + " testb %[bitnum],%[cap_byte]\n" + " jnz %l[t_yes]\n" + " jmp %l[t_no]\n" + ".previous\n" + : : [feature] "i" (bit), + [always] "i" (X86_FEATURE_ALWAYS), + [bitnum] "i" (1 << (bit & 7)), + [cap_byte] "m" (((const char *)boot_cpu_data.x86_capability)[bit >> 3]) + : : t_yes, t_no); +t_yes: + return true; +t_no: + return false; } #define static_cpu_has(bit) \ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 4d57894635f2..81a1be326571 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -6,6 +6,7 @@ #include <asm/alternative.h> #include <asm/alternative-asm.h> #include <asm/cpufeatures.h> +#include <asm/msr-index.h> #ifdef __ASSEMBLY__ @@ -164,11 +165,53 @@ static inline void vmexit_fill_RSB(void) static inline void indirect_branch_prediction_barrier(void) { - alternative_input("", - "call __ibp_barrier", - X86_FEATURE_USE_IBPB, - ASM_NO_INPUT_CLOBBER("eax", "ecx", "edx", "memory")); + asm volatile(ALTERNATIVE("", + "movl %[msr], %%ecx\n\t" + "movl %[val], %%eax\n\t" + "movl $0, %%edx\n\t" + "wrmsr", + X86_FEATURE_USE_IBPB) + : : [msr] "i" (MSR_IA32_PRED_CMD), + [val] "i" (PRED_CMD_IBPB) + : "eax", "ecx", "edx", "memory"); } #endif /* __ASSEMBLY__ */ + +/* + * Below is used in the eBPF JIT compiler and emits the byte sequence + * for the following assembly: + * + * With retpolines configured: + * + * callq do_rop + * spec_trap: + * pause + * lfence + * jmp spec_trap + * do_rop: + * mov %rax,(%rsp) + * retq + * + * Without retpolines configured: + * + * jmp *%rax + */ +#ifdef CONFIG_RETPOLINE +# define RETPOLINE_RAX_BPF_JIT_SIZE 17 +# define RETPOLINE_RAX_BPF_JIT() \ + EMIT1_off32(0xE8, 7); /* callq do_rop */ \ + /* spec_trap: */ \ + EMIT2(0xF3, 0x90); /* pause */ \ + EMIT3(0x0F, 0xAE, 0xE8); /* lfence */ \ + EMIT2(0xEB, 0xF9); /* jmp spec_trap */ \ + /* do_rop: */ \ + EMIT4(0x48, 0x89, 0x04, 0x24); /* mov %rax,(%rsp) */ \ + EMIT1(0xC3); /* retq */ +#else +# define RETPOLINE_RAX_BPF_JIT_SIZE 2 +# define RETPOLINE_RAX_BPF_JIT() \ + EMIT2(0xFF, 0xE0); /* jmp *%rax */ +#endif + #endif /* _ASM_X86_NOSPEC_BRANCH_H_ */ diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h index 4baa6bceb232..d652a3808065 100644 --- a/arch/x86/include/asm/page_64.h +++ b/arch/x86/include/asm/page_64.h @@ -52,10 +52,6 @@ static inline void clear_page(void *page) void copy_page(void *to, void *from); -#ifdef CONFIG_X86_MCE -#define arch_unmap_kpfn arch_unmap_kpfn -#endif - #endif /* !__ASSEMBLY__ */ #ifdef CONFIG_X86_VSYSCALL_EMULATION diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 892df375b615..554841fab717 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -297,9 +297,9 @@ static inline void __flush_tlb_global(void) { PVOP_VCALL0(pv_mmu_ops.flush_tlb_kernel); } -static inline void __flush_tlb_single(unsigned long addr) +static inline void __flush_tlb_one_user(unsigned long addr) { - PVOP_VCALL1(pv_mmu_ops.flush_tlb_single, addr); + PVOP_VCALL1(pv_mmu_ops.flush_tlb_one_user, addr); } static inline void flush_tlb_others(const struct cpumask *cpumask, diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 6ec54d01972d..f624f1f10316 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -217,7 +217,7 @@ struct pv_mmu_ops { /* TLB operations */ void (*flush_tlb_user)(void); void (*flush_tlb_kernel)(void); - void (*flush_tlb_single)(unsigned long addr); + void (*flush_tlb_one_user)(unsigned long addr); void (*flush_tlb_others)(const struct cpumask *cpus, const struct flush_tlb_info *info); diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h index e67c0620aec2..e55466760ff8 100644 --- a/arch/x86/include/asm/pgtable_32.h +++ b/arch/x86/include/asm/pgtable_32.h @@ -61,7 +61,7 @@ void paging_init(void); #define kpte_clear_flush(ptep, vaddr) \ do { \ pte_clear(&init_mm, (vaddr), (ptep)); \ - __flush_tlb_one((vaddr)); \ + __flush_tlb_one_kernel((vaddr)); \ } while (0) #endif /* !__ASSEMBLY__ */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 793bae7e7ce3..1bd9ed87606f 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -91,7 +91,7 @@ struct cpuinfo_x86 { __u8 x86; /* CPU family */ __u8 x86_vendor; /* CPU vendor */ __u8 x86_model; - __u8 x86_mask; + __u8 x86_stepping; #ifdef CONFIG_X86_64 /* Number of 4K pages in DTLB/ITLB combined(in pages): */ int x86_tlbsize; @@ -109,7 +109,7 @@ struct cpuinfo_x86 { char x86_vendor_id[16]; char x86_model_id[64]; /* in KB - valid for CPUS which support this call: */ - int x86_cache_size; + unsigned int x86_cache_size; int x86_cache_alignment; /* In bytes */ /* Cache QoS architectural values: */ int x86_cache_max_rmid; /* max index */ @@ -977,7 +977,4 @@ bool xen_set_default_idle(void); void stop_this_cpu(void *dummy); void df_debug(struct pt_regs *regs, long error_code); - -void __ibp_barrier(void); - #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 461f53d27708..a4189762b266 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -129,6 +129,7 @@ static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask) void cpu_disable_common(void); void native_smp_prepare_boot_cpu(void); void native_smp_prepare_cpus(unsigned int max_cpus); +void calculate_max_logical_packages(void); void native_smp_cpus_done(unsigned int max_cpus); void common_cpu_up(unsigned int cpunum, struct task_struct *tidle); int native_cpu_up(unsigned int cpunum, struct task_struct *tidle); diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 2b8f18ca5874..84137c22fdfa 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -140,7 +140,7 @@ static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid) #else #define __flush_tlb() __native_flush_tlb() #define __flush_tlb_global() __native_flush_tlb_global() -#define __flush_tlb_single(addr) __native_flush_tlb_single(addr) +#define __flush_tlb_one_user(addr) __native_flush_tlb_one_user(addr) #endif static inline bool tlb_defer_switch_to_init_mm(void) @@ -400,7 +400,7 @@ static inline void __native_flush_tlb_global(void) /* * flush one page in the user mapping */ -static inline void __native_flush_tlb_single(unsigned long addr) +static inline void __native_flush_tlb_one_user(unsigned long addr) { u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid); @@ -437,18 +437,31 @@ static inline void __flush_tlb_all(void) /* * flush one page in the kernel mapping */ -static inline void __flush_tlb_one(unsigned long addr) +static inline void __flush_tlb_one_kernel(unsigned long addr) { count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE); - __flush_tlb_single(addr); + + /* + * If PTI is off, then __flush_tlb_one_user() is just INVLPG or its + * paravirt equivalent. Even with PCID, this is sufficient: we only + * use PCID if we also use global PTEs for the kernel mapping, and + * INVLPG flushes global translations across all address spaces. + * + * If PTI is on, then the kernel is mapped with non-global PTEs, and + * __flush_tlb_one_user() will flush the given address for the current + * kernel address space and for its usermode counterpart, but it does + * not flush it for other address spaces. + */ + __flush_tlb_one_user(addr); if (!static_cpu_has(X86_FEATURE_PTI)) return; /* - * __flush_tlb_single() will have cleared the TLB entry for this ASID, - * but since kernel space is replicated across all, we must also - * invalidate all others. + * See above. We need to propagate the flush to all other address + * spaces. In principle, we only need to propagate it to kernelmode + * address spaces, but the extra bookkeeping we would need is not + * worth it. */ invalidate_other_asid(); } diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 6db28f17ff28..c88e0b127810 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -235,7 +235,7 @@ int amd_cache_northbridges(void) if (boot_cpu_data.x86 == 0x10 && boot_cpu_data.x86_model >= 0x8 && (boot_cpu_data.x86_model > 0x9 || - boot_cpu_data.x86_mask >= 0x1)) + boot_cpu_data.x86_stepping >= 0x1)) amd_northbridges.flags |= AMD_NB_L3_INDEX_DISABLE; if (boot_cpu_data.x86 == 0x15) diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 25ddf02598d2..b203af0855b5 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -546,7 +546,7 @@ static DEFINE_PER_CPU(struct clock_event_device, lapic_events); static u32 hsx_deadline_rev(void) { - switch (boot_cpu_data.x86_mask) { + switch (boot_cpu_data.x86_stepping) { case 0x02: return 0x3a; /* EP */ case 0x04: return 0x0f; /* EX */ } @@ -556,7 +556,7 @@ static u32 hsx_deadline_rev(void) static u32 bdx_deadline_rev(void) { - switch (boot_cpu_data.x86_mask) { + switch (boot_cpu_data.x86_stepping) { case 0x02: return 0x00000011; case 0x03: return 0x0700000e; case 0x04: return 0x0f00000c; @@ -568,7 +568,7 @@ static u32 bdx_deadline_rev(void) static u32 skx_deadline_rev(void) { - switch (boot_cpu_data.x86_mask) { + switch (boot_cpu_data.x86_stepping) { case 0x03: return 0x01000136; case 0x04: return 0x02000014; } diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 46b675aaf20b..f11910b44638 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -1176,16 +1176,25 @@ static void __init decode_gam_rng_tbl(unsigned long ptr) uv_gre_table = gre; for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) { + unsigned long size = ((unsigned long)(gre->limit - lgre) + << UV_GAM_RANGE_SHFT); + int order = 0; + char suffix[] = " KMGTPE"; + + while (size > 9999 && order < sizeof(suffix)) { + size /= 1024; + order++; + } + if (!index) { pr_info("UV: GAM Range Table...\n"); pr_info("UV: # %20s %14s %5s %4s %5s %3s %2s\n", "Range", "", "Size", "Type", "NASID", "SID", "PN"); } - pr_info("UV: %2d: 0x%014lx-0x%014lx %5luG %3d %04x %02x %02x\n", + pr_info("UV: %2d: 0x%014lx-0x%014lx %5lu%c %3d %04x %02x %02x\n", index++, (unsigned long)lgre << UV_GAM_RANGE_SHFT, (unsigned long)gre->limit << UV_GAM_RANGE_SHFT, - ((unsigned long)(gre->limit - lgre)) >> - (30 - UV_GAM_RANGE_SHFT), /* 64M -> 1G */ + size, suffix[order], gre->type, gre->nasid, gre->sockid, gre->pnode); lgre = gre->limit; diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index fa1261eefa16..f91ba53e06c8 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -18,7 +18,7 @@ void foo(void) OFFSET(CPUINFO_x86, cpuinfo_x86, x86); OFFSET(CPUINFO_x86_vendor, cpuinfo_x86, x86_vendor); OFFSET(CPUINFO_x86_model, cpuinfo_x86, x86_model); - OFFSET(CPUINFO_x86_mask, cpuinfo_x86, x86_mask); + OFFSET(CPUINFO_x86_stepping, cpuinfo_x86, x86_stepping); OFFSET(CPUINFO_cpuid_level, cpuinfo_x86, cpuid_level); OFFSET(CPUINFO_x86_capability, cpuinfo_x86, x86_capability); OFFSET(CPUINFO_x86_vendor_id, cpuinfo_x86, x86_vendor_id); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 5bddbdcbc4a3..f0e6456ca7d3 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -119,7 +119,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c) return; } - if (c->x86_model == 6 && c->x86_mask == 1) { + if (c->x86_model == 6 && c->x86_stepping == 1) { const int K6_BUG_LOOP = 1000000; int n; void (*f_vide)(void); @@ -149,7 +149,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c) /* K6 with old style WHCR */ if (c->x86_model < 8 || - (c->x86_model == 8 && c->x86_mask < 8)) { + (c->x86_model == 8 && c->x86_stepping < 8)) { /* We can only write allocate on the low 508Mb */ if (mbytes > 508) mbytes = 508; @@ -168,7 +168,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c) return; } - if ((c->x86_model == 8 && c->x86_mask > 7) || + if ((c->x86_model == 8 && c->x86_stepping > 7) || c->x86_model == 9 || c->x86_model == 13) { /* The more serious chips .. */ @@ -221,7 +221,7 @@ static void init_amd_k7(struct cpuinfo_x86 *c) * are more robust with CLK_CTL set to 200xxxxx instead of 600xxxxx * As per AMD technical note 27212 0.2 */ - if ((c->x86_model == 8 && c->x86_mask >= 1) || (c->x86_model > 8)) { + if ((c->x86_model == 8 && c->x86_stepping >= 1) || (c->x86_model > 8)) { rdmsr(MSR_K7_CLK_CTL, l, h); if ((l & 0xfff00000) != 0x20000000) { pr_info("CPU: CLK_CTL MSR was %x. Reprogramming to %x\n", @@ -241,12 +241,12 @@ static void init_amd_k7(struct cpuinfo_x86 *c) * but they are not certified as MP capable. */ /* Athlon 660/661 is valid. */ - if ((c->x86_model == 6) && ((c->x86_mask == 0) || - (c->x86_mask == 1))) + if ((c->x86_model == 6) && ((c->x86_stepping == 0) || + (c->x86_stepping == 1))) return; /* Duron 670 is valid */ - if ((c->x86_model == 7) && (c->x86_mask == 0)) + if ((c->x86_model == 7) && (c->x86_stepping == 0)) return; /* @@ -256,8 +256,8 @@ static void init_amd_k7(struct cpuinfo_x86 *c) * See http://www.heise.de/newsticker/data/jow-18.10.01-000 for * more. */ - if (((c->x86_model == 6) && (c->x86_mask >= 2)) || - ((c->x86_model == 7) && (c->x86_mask >= 1)) || + if (((c->x86_model == 6) && (c->x86_stepping >= 2)) || + ((c->x86_model == 7) && (c->x86_stepping >= 1)) || (c->x86_model > 7)) if (cpu_has(c, X86_FEATURE_MP)) return; @@ -628,7 +628,7 @@ static void early_init_amd(struct cpuinfo_x86 *c) /* Set MTRR capability flag if appropriate */ if (c->x86 == 5) if (c->x86_model == 13 || c->x86_model == 9 || - (c->x86_model == 8 && c->x86_mask >= 8)) + (c->x86_model == 8 && c->x86_stepping >= 8)) set_cpu_cap(c, X86_FEATURE_K6_MTRR); #endif #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_PCI) @@ -795,7 +795,7 @@ static void init_amd_zn(struct cpuinfo_x86 *c) * Fix erratum 1076: CPB feature bit not being set in CPUID. It affects * all up to and including B1. */ - if (c->x86_model <= 1 && c->x86_mask <= 1) + if (c->x86_model <= 1 && c->x86_stepping <= 1) set_cpu_cap(c, X86_FEATURE_CPB); } @@ -906,11 +906,11 @@ static unsigned int amd_size_cache(struct cpuinfo_x86 *c, unsigned int size) /* AMD errata T13 (order #21922) */ if ((c->x86 == 6)) { /* Duron Rev A0 */ - if (c->x86_model == 3 && c->x86_mask == 0) + if (c->x86_model == 3 && c->x86_stepping == 0) size = 64; /* Tbird rev A1/A2 */ if (c->x86_model == 4 && - (c->x86_mask == 0 || c->x86_mask == 1)) + (c->x86_stepping == 0 || c->x86_stepping == 1)) size = 256; } return size; @@ -1047,7 +1047,7 @@ static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) } /* OSVW unavailable or ID unknown, match family-model-stepping range */ - ms = (cpu->x86_model << 4) | cpu->x86_mask; + ms = (cpu->x86_model << 4) | cpu->x86_stepping; while ((range = *erratum++)) if ((cpu->x86 == AMD_MODEL_RANGE_FAMILY(range)) && (ms >= AMD_MODEL_RANGE_START(range)) && diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 71949bf2de5a..d71c8b54b696 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -162,8 +162,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) if (cmdline_find_option_bool(boot_command_line, "nospectre_v2")) return SPECTRE_V2_CMD_NONE; else { - ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, - sizeof(arg)); + ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, sizeof(arg)); if (ret < 0) return SPECTRE_V2_CMD_AUTO; @@ -175,8 +174,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) } if (i >= ARRAY_SIZE(mitigation_options)) { - pr_err("unknown option (%s). Switching to AUTO select\n", - mitigation_options[i].option); + pr_err("unknown option (%s). Switching to AUTO select\n", arg); return SPECTRE_V2_CMD_AUTO; } } @@ -185,8 +183,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) cmd == SPECTRE_V2_CMD_RETPOLINE_AMD || cmd == SPECTRE_V2_CMD_RETPOLINE_GENERIC) && !IS_ENABLED(CONFIG_RETPOLINE)) { - pr_err("%s selected but not compiled in. Switching to AUTO select\n", - mitigation_options[i].option); + pr_err("%s selected but not compiled in. Switching to AUTO select\n", mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; } @@ -256,14 +253,14 @@ static void __init spectre_v2_select_mitigation(void) goto retpoline_auto; break; } - pr_err("kernel not compiled with retpoline; no mitigation available!"); + pr_err("Spectre mitigation: kernel not compiled with retpoline; no mitigation available!"); return; retpoline_auto: if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { retpoline_amd: if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) { - pr_err("LFENCE not serializing. Switching to generic retpoline\n"); + pr_err("Spectre mitigation: LFENCE not serializing, switching to generic retpoline\n"); goto retpoline_generic; } mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_AMD : @@ -281,7 +278,7 @@ retpoline_auto: pr_info("%s\n", spectre_v2_strings[mode]); /* - * If neither SMEP or KPTI are available, there is a risk of + * If neither SMEP nor PTI are available, there is a risk of * hitting userspace addresses in the RSB after a context switch * from a shallow call stack to a deeper one. To prevent this fill * the entire RSB, even when using IBRS. @@ -295,21 +292,20 @@ retpoline_auto: if ((!boot_cpu_has(X86_FEATURE_PTI) && !boot_cpu_has(X86_FEATURE_SMEP)) || is_skylake_era()) { setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW); - pr_info("Filling RSB on context switch\n"); + pr_info("Spectre v2 mitigation: Filling RSB on context switch\n"); } /* Initialize Indirect Branch Prediction Barrier if supported */ if (boot_cpu_has(X86_FEATURE_IBPB)) { setup_force_cpu_cap(X86_FEATURE_USE_IBPB); - pr_info("Enabling Indirect Branch Prediction Barrier\n"); + pr_info("Spectre v2 mitigation: Enabling Indirect Branch Prediction Barrier\n"); } } #undef pr_fmt #ifdef CONFIG_SYSFS -ssize_t cpu_show_meltdown(struct device *dev, - struct device_attribute *attr, char *buf) +ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) { if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) return sprintf(buf, "Not affected\n"); @@ -318,16 +314,14 @@ ssize_t cpu_show_meltdown(struct device *dev, return sprintf(buf, "Vulnerable\n"); } -ssize_t cpu_show_spectre_v1(struct device *dev, - struct device_attribute *attr, char *buf) +ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf) { if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1)) return sprintf(buf, "Not affected\n"); return sprintf(buf, "Mitigation: __user pointer sanitization\n"); } -ssize_t cpu_show_spectre_v2(struct device *dev, - struct device_attribute *attr, char *buf) +ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf) { if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) return sprintf(buf, "Not affected\n"); @@ -337,9 +331,3 @@ ssize_t cpu_show_spectre_v2(struct device *dev, spectre_v2_module_string()); } #endif - -void __ibp_barrier(void) -{ - __wrmsr(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, 0); -} -EXPORT_SYMBOL_GPL(__ibp_barrier); diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index c578cd29c2d2..e5ec0f11c0de 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -140,7 +140,7 @@ static void init_centaur(struct cpuinfo_x86 *c) clear_cpu_cap(c, X86_FEATURE_TSC); break; case 8: - switch (c->x86_mask) { + switch (c->x86_stepping) { default: name = "2"; break; @@ -215,7 +215,7 @@ centaur_size_cache(struct cpuinfo_x86 *c, unsigned int size) * - Note, it seems this may only be in engineering samples. */ if ((c->x86 == 6) && (c->x86_model == 9) && - (c->x86_mask == 1) && (size == 65)) + (c->x86_stepping == 1) && (size == 65)) size -= 1; return size; } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index d63f4b5706e4..824aee0117bb 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -731,7 +731,7 @@ void cpu_detect(struct cpuinfo_x86 *c) cpuid(0x00000001, &tfms, &misc, &junk, &cap0); c->x86 = x86_family(tfms); c->x86_model = x86_model(tfms); - c->x86_mask = x86_stepping(tfms); + c->x86_stepping = x86_stepping(tfms); if (cap0 & (1<<19)) { c->x86_clflush_size = ((misc >> 8) & 0xff) * 8; @@ -1184,9 +1184,9 @@ static void identify_cpu(struct cpuinfo_x86 *c) int i; c->loops_per_jiffy = loops_per_jiffy; - c->x86_cache_size = -1; + c->x86_cache_size = 0; c->x86_vendor = X86_VENDOR_UNKNOWN; - c->x86_model = c->x86_mask = 0; /* So far unknown... */ + c->x86_model = c->x86_stepping = 0; /* So far unknown... */ c->x86_vendor_id[0] = '\0'; /* Unset */ c->x86_model_id[0] = '\0'; /* Unset */ c->x86_max_cores = 1; @@ -1378,8 +1378,8 @@ void print_cpu_info(struct cpuinfo_x86 *c) pr_cont(" (family: 0x%x, model: 0x%x", c->x86, c->x86_model); - if (c->x86_mask || c->cpuid_level >= 0) - pr_cont(", stepping: 0x%x)\n", c->x86_mask); + if (c->x86_stepping || c->cpuid_level >= 0) + pr_cont(", stepping: 0x%x)\n", c->x86_stepping); else pr_cont(")\n"); } diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index 6b4bb335641f..8949b7ae6d92 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -215,7 +215,7 @@ static void init_cyrix(struct cpuinfo_x86 *c) /* common case step number/rev -- exceptions handled below */ c->x86_model = (dir1 >> 4) + 1; - c->x86_mask = dir1 & 0xf; + c->x86_stepping = dir1 & 0xf; /* Now cook; the original recipe is by Channing Corn, from Cyrix. * We do the same thing for each generation: we work out diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 319bf989fad1..d19e903214b4 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -116,14 +116,13 @@ struct sku_microcode { u32 microcode; }; static const struct sku_microcode spectre_bad_microcodes[] = { - { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0B, 0x84 }, - { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0A, 0x84 }, - { INTEL_FAM6_KABYLAKE_DESKTOP, 0x09, 0x84 }, - { INTEL_FAM6_KABYLAKE_MOBILE, 0x0A, 0x84 }, - { INTEL_FAM6_KABYLAKE_MOBILE, 0x09, 0x84 }, + { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0B, 0x80 }, + { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0A, 0x80 }, + { INTEL_FAM6_KABYLAKE_DESKTOP, 0x09, 0x80 }, + { INTEL_FAM6_KABYLAKE_MOBILE, 0x0A, 0x80 }, + { INTEL_FAM6_KABYLAKE_MOBILE, 0x09, 0x80 }, { INTEL_FAM6_SKYLAKE_X, 0x03, 0x0100013e }, { INTEL_FAM6_SKYLAKE_X, 0x04, 0x0200003c }, - { INTEL_FAM6_SKYLAKE_MOBILE, 0x03, 0xc2 }, { INTEL_FAM6_SKYLAKE_DESKTOP, 0x03, 0xc2 }, { INTEL_FAM6_BROADWELL_CORE, 0x04, 0x28 }, { INTEL_FAM6_BROADWELL_GT3E, 0x01, 0x1b }, @@ -136,8 +135,6 @@ static const struct sku_microcode spectre_bad_microcodes[] = { { INTEL_FAM6_HASWELL_X, 0x02, 0x3b }, { INTEL_FAM6_HASWELL_X, 0x04, 0x10 }, { INTEL_FAM6_IVYBRIDGE_X, 0x04, 0x42a }, - /* Updated in the 20180108 release; blacklist until we know otherwise */ - { INTEL_FAM6_ATOM_GEMINI_LAKE, 0x01, 0x22 }, /* Observed in the wild */ { INTEL_FAM6_SANDYBRIDGE_X, 0x06, 0x61b }, { INTEL_FAM6_SANDYBRIDGE_X, 0x07, 0x712 }, @@ -149,7 +146,7 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c) for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) { if (c->x86_model == spectre_bad_microcodes[i].model && - c->x86_mask == spectre_bad_microcodes[i].stepping) + c->x86_stepping == spectre_bad_microcodes[i].stepping) return (c->microcode <= spectre_bad_microcodes[i].microcode); } return false; @@ -196,7 +193,7 @@ static void early_init_intel(struct cpuinfo_x86 *c) * need the microcode to have already been loaded... so if it is * not, recommend a BIOS update and disable large pages. */ - if (c->x86 == 6 && c->x86_model == 0x1c && c->x86_mask <= 2 && + if (c->x86 == 6 && c->x86_model == 0x1c && c->x86_stepping <= 2 && c->microcode < 0x20e) { pr_warn("Atom PSE erratum detected, BIOS microcode update recommended\n"); clear_cpu_cap(c, X86_FEATURE_PSE); @@ -212,7 +209,7 @@ static void early_init_intel(struct cpuinfo_x86 *c) /* CPUID workaround for 0F33/0F34 CPU */ if (c->x86 == 0xF && c->x86_model == 0x3 - && (c->x86_mask == 0x3 || c->x86_mask == 0x4)) + && (c->x86_stepping == 0x3 || c->x86_stepping == 0x4)) c->x86_phys_bits = 36; /* @@ -310,7 +307,7 @@ int ppro_with_ram_bug(void) if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 1 && - boot_cpu_data.x86_mask < 8) { + boot_cpu_data.x86_stepping < 8) { pr_info("Pentium Pro with Errata#50 detected. Taking evasive action.\n"); return 1; } @@ -327,7 +324,7 @@ static void intel_smp_check(struct cpuinfo_x86 *c) * Mask B, Pentium, but not Pentium MMX */ if (c->x86 == 5 && - c->x86_mask >= 1 && c->x86_mask <= 4 && + c->x86_stepping >= 1 && c->x86_stepping <= 4 && c->x86_model <= 3) { /* * Remember we have B step Pentia with bugs @@ -370,7 +367,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c) * SEP CPUID bug: Pentium Pro reports SEP but doesn't have it until * model 3 mask 3 */ - if ((c->x86<<8 | c->x86_model<<4 | c->x86_mask) < 0x633) + if ((c->x86<<8 | c->x86_model<<4 | c->x86_stepping) < 0x633) clear_cpu_cap(c, X86_FEATURE_SEP); /* @@ -388,7 +385,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c) * P4 Xeon erratum 037 workaround. * Hardware prefetcher may cause stale data to be loaded into the cache. */ - if ((c->x86 == 15) && (c->x86_model == 1) && (c->x86_mask == 1)) { + if ((c->x86 == 15) && (c->x86_model == 1) && (c->x86_stepping == 1)) { if (msr_set_bit(MSR_IA32_MISC_ENABLE, MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT) > 0) { pr_info("CPU: C0 stepping P4 Xeon detected.\n"); @@ -403,7 +400,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c) * Specification Update"). */ if (boot_cpu_has(X86_FEATURE_APIC) && (c->x86<<8 | c->x86_model<<4) == 0x520 && - (c->x86_mask < 0x6 || c->x86_mask == 0xb)) + (c->x86_stepping < 0x6 || c->x86_stepping == 0xb)) set_cpu_bug(c, X86_BUG_11AP); @@ -650,7 +647,7 @@ static void init_intel(struct cpuinfo_x86 *c) case 6: if (l2 == 128) p = "Celeron (Mendocino)"; - else if (c->x86_mask == 0 || c->x86_mask == 5) + else if (c->x86_stepping == 0 || c->x86_stepping == 5) p = "Celeron-A"; break; diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c index 410629f10ad3..589b948e6e01 100644 --- a/arch/x86/kernel/cpu/intel_rdt.c +++ b/arch/x86/kernel/cpu/intel_rdt.c @@ -819,7 +819,7 @@ static __init void rdt_quirks(void) cache_alloc_hsw_probe(); break; case INTEL_FAM6_SKYLAKE_X: - if (boot_cpu_data.x86_mask <= 4) + if (boot_cpu_data.x86_stepping <= 4) set_rdt_options("!cmt,!mbmtotal,!mbmlocal,!l3cat"); } } diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index aa0d5df9dc60..e956eb267061 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -115,4 +115,19 @@ static inline void mce_unregister_injector_chain(struct notifier_block *nb) { } extern struct mca_config mca_cfg; +#ifndef CONFIG_X86_64 +/* + * On 32-bit systems it would be difficult to safely unmap a poison page + * from the kernel 1:1 map because there are no non-canonical addresses that + * we can use to refer to the address without risking a speculative access. + * However, this isn't much of an issue because: + * 1) Few unmappable pages are in the 1:1 map. Most are in HIGHMEM which + * are only mapped into the kernel as needed + * 2) Few people would run a 32-bit kernel on a machine that supports + * recoverable errors because they have too much memory to boot 32-bit. + */ +static inline void mce_unmap_kpfn(unsigned long pfn) {} +#define mce_unmap_kpfn mce_unmap_kpfn +#endif + #endif /* __X86_MCE_INTERNAL_H__ */ diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 3a8e88a611eb..8ff94d1e2dce 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -105,6 +105,10 @@ static struct irq_work mce_irq_work; static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs); +#ifndef mce_unmap_kpfn +static void mce_unmap_kpfn(unsigned long pfn); +#endif + /* * CPU/chipset specific EDAC code can register a notifier call here to print * MCE errors in a human-readable form. @@ -234,7 +238,7 @@ static void __print_mce(struct mce *m) m->cs, m->ip); if (m->cs == __KERNEL_CS) - pr_cont("{%pS}", (void *)m->ip); + pr_cont("{%pS}", (void *)(unsigned long)m->ip); pr_cont("\n"); } @@ -590,7 +594,8 @@ static int srao_decode_notifier(struct notifier_block *nb, unsigned long val, if (mce_usable_address(mce) && (mce->severity == MCE_AO_SEVERITY)) { pfn = mce->addr >> PAGE_SHIFT; - memory_failure(pfn, 0); + if (!memory_failure(pfn, 0)) + mce_unmap_kpfn(pfn); } return NOTIFY_OK; @@ -1057,12 +1062,13 @@ static int do_memory_failure(struct mce *m) ret = memory_failure(m->addr >> PAGE_SHIFT, flags); if (ret) pr_err("Memory error not recovered"); + else + mce_unmap_kpfn(m->addr >> PAGE_SHIFT); return ret; } -#if defined(arch_unmap_kpfn) && defined(CONFIG_MEMORY_FAILURE) - -void arch_unmap_kpfn(unsigned long pfn) +#ifndef mce_unmap_kpfn +static void mce_unmap_kpfn(unsigned long pfn) { unsigned long decoy_addr; @@ -1073,7 +1079,7 @@ void arch_unmap_kpfn(unsigned long pfn) * We would like to just call: * set_memory_np((unsigned long)pfn_to_kaddr(pfn), 1); * but doing that would radically increase the odds of a - * speculative access to the posion page because we'd have + * speculative access to the poison page because we'd have * the virtual address of the kernel 1:1 mapping sitting * around in registers. * Instead we get tricky. We create a non-canonical address @@ -1098,7 +1104,6 @@ void arch_unmap_kpfn(unsigned long pfn) if (set_memory_np(decoy_addr, 1)) pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn); - } #endif diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index f7c55b0e753a..a15db2b4e0d6 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -921,7 +921,7 @@ static bool is_blacklisted(unsigned int cpu) */ if (c->x86 == 6 && c->x86_model == INTEL_FAM6_BROADWELL_X && - c->x86_mask == 0x01 && + c->x86_stepping == 0x01 && llc_size_per_core > 2621440 && c->microcode < 0x0b000021) { pr_err_once("Erratum BDF90: late loading with revision < 0x0b000021 (0x%x) disabled.\n", c->microcode); @@ -944,7 +944,7 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device, return UCODE_NFOUND; sprintf(name, "intel-ucode/%02x-%02x-%02x", - c->x86, c->x86_model, c->x86_mask); + c->x86, c->x86_model, c->x86_stepping); if (request_firmware_direct(&firmware, name, device)) { pr_debug("data file %s load failed\n", name); @@ -982,7 +982,7 @@ static struct microcode_ops microcode_intel_ops = { static int __init calc_llc_size_per_core(struct cpuinfo_x86 *c) { - u64 llc_size = c->x86_cache_size * 1024; + u64 llc_size = c->x86_cache_size * 1024ULL; do_div(llc_size, c->x86_max_cores); diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index fdc55215d44d..e12ee86906c6 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -859,7 +859,7 @@ int generic_validate_add_page(unsigned long base, unsigned long size, */ if (is_cpu(INTEL) && boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 1 && - boot_cpu_data.x86_mask <= 7) { + boot_cpu_data.x86_stepping <= 7) { if (base & ((1 << (22 - PAGE_SHIFT)) - 1)) { pr_warn("mtrr: base(0x%lx000) is not 4 MiB aligned\n", base); return -EINVAL; diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 40d5a8a75212..7468de429087 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -711,8 +711,8 @@ void __init mtrr_bp_init(void) if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && boot_cpu_data.x86 == 0xF && boot_cpu_data.x86_model == 0x3 && - (boot_cpu_data.x86_mask == 0x3 || - boot_cpu_data.x86_mask == 0x4)) + (boot_cpu_data.x86_stepping == 0x3 || + boot_cpu_data.x86_stepping == 0x4)) phys_addr = 36; size_or_mask = SIZE_OR_MASK_BITS(phys_addr); diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index e7ecedafa1c8..2c8522a39ed5 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -72,8 +72,8 @@ static int show_cpuinfo(struct seq_file *m, void *v) c->x86_model, c->x86_model_id[0] ? c->x86_model_id : "unknown"); - if (c->x86_mask || c->cpuid_level >= 0) - seq_printf(m, "stepping\t: %d\n", c->x86_mask); + if (c->x86_stepping || c->cpuid_level >= 0) + seq_printf(m, "stepping\t: %d\n", c->x86_stepping); else seq_puts(m, "stepping\t: unknown\n"); if (c->microcode) @@ -91,8 +91,8 @@ static int show_cpuinfo(struct seq_file *m, void *v) } /* Cache size */ - if (c->x86_cache_size >= 0) - seq_printf(m, "cache size\t: %d KB\n", c->x86_cache_size); + if (c->x86_cache_size) + seq_printf(m, "cache size\t: %u KB\n", c->x86_cache_size); show_cpuinfo_core(m, c, cpu); show_cpuinfo_misc(m, c); diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index c29020907886..b59e4fb40fd9 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -37,7 +37,7 @@ #define X86 new_cpu_data+CPUINFO_x86 #define X86_VENDOR new_cpu_data+CPUINFO_x86_vendor #define X86_MODEL new_cpu_data+CPUINFO_x86_model -#define X86_MASK new_cpu_data+CPUINFO_x86_mask +#define X86_STEPPING new_cpu_data+CPUINFO_x86_stepping #define X86_HARD_MATH new_cpu_data+CPUINFO_hard_math #define X86_CPUID new_cpu_data+CPUINFO_cpuid_level #define X86_CAPABILITY new_cpu_data+CPUINFO_x86_capability @@ -332,7 +332,7 @@ ENTRY(startup_32_smp) shrb $4,%al movb %al,X86_MODEL andb $0x0f,%cl # mask mask revision - movb %cl,X86_MASK + movb %cl,X86_STEPPING movl %edx,X86_CAPABILITY .Lis486: diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 1f790cf9d38f..3b7427aa7d85 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -542,6 +542,7 @@ int arch_kexec_apply_relocations_add(const Elf64_Ehdr *ehdr, goto overflow; break; case R_X86_64_PC32: + case R_X86_64_PLT32: value -= (u64)address; *(u32 *)location = value; break; diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index da0c160e5589..f58336af095c 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -191,6 +191,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, goto overflow; break; case R_X86_64_PC32: + case R_X86_64_PLT32: if (*(u32 *)loc != 0) goto invalid_relocation; val -= (u64)loc; diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 27d0a1712663..f1c5eb99d445 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -410,7 +410,7 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type) processor.apicver = mpc_default_type > 4 ? 0x10 : 0x01; processor.cpuflag = CPU_ENABLED; processor.cpufeature = (boot_cpu_data.x86 << 8) | - (boot_cpu_data.x86_model << 4) | boot_cpu_data.x86_mask; + (boot_cpu_data.x86_model << 4) | boot_cpu_data.x86_stepping; processor.featureflag = boot_cpu_data.x86_capability[CPUID_1_EDX]; processor.reserved[0] = 0; processor.reserved[1] = 0; diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 041096bdef86..99dc79e76bdc 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -200,9 +200,9 @@ static void native_flush_tlb_global(void) __native_flush_tlb_global(); } -static void native_flush_tlb_single(unsigned long addr) +static void native_flush_tlb_one_user(unsigned long addr) { - __native_flush_tlb_single(addr); + __native_flush_tlb_one_user(addr); } struct static_key paravirt_steal_enabled; @@ -401,7 +401,7 @@ struct pv_mmu_ops pv_mmu_ops __ro_after_init = { .flush_tlb_user = native_flush_tlb, .flush_tlb_kernel = native_flush_tlb_global, - .flush_tlb_single = native_flush_tlb_single, + .flush_tlb_one_user = native_flush_tlb_one_user, .flush_tlb_others = native_flush_tlb_others, .pgd_alloc = __paravirt_pgd_alloc, diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 6f27facbaa9b..9eee25d07586 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1281,11 +1281,10 @@ void __init native_smp_prepare_boot_cpu(void) cpu_set_state_online(me); } -void __init native_smp_cpus_done(unsigned int max_cpus) +void __init calculate_max_logical_packages(void) { int ncpus; - pr_debug("Boot done\n"); /* * Today neither Intel nor AMD support heterogenous systems so * extrapolate the boot cpu's data to all packages. @@ -1293,6 +1292,13 @@ void __init native_smp_cpus_done(unsigned int max_cpus) ncpus = cpu_data(0).booted_cores * topology_max_smt_threads(); __max_logical_packages = DIV_ROUND_UP(nr_cpu_ids, ncpus); pr_info("Max logical packages: %u\n", __max_logical_packages); +} + +void __init native_smp_cpus_done(unsigned int max_cpus) +{ + pr_debug("Boot done\n"); + + calculate_max_logical_packages(); if (x86_has_numa_in_package) set_sched_topology(x86_numa_in_package_topology); @@ -1430,7 +1436,6 @@ static void remove_siblinginfo(int cpu) cpumask_clear(cpu_llc_shared_mask(cpu)); cpumask_clear(topology_sibling_cpumask(cpu)); cpumask_clear(topology_core_cpumask(cpu)); - c->phys_proc_id = 0; c->cpu_core_id = 0; cpumask_clear_cpu(cpu, cpu_sibling_setup_mask); recompute_smt_state(); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 446c9ef8cfc3..3d9b2308e7fa 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -181,7 +181,7 @@ int fixup_bug(struct pt_regs *regs, int trapnr) break; case BUG_TRAP_TYPE_WARN: - regs->ip += LEN_UD0; + regs->ip += LEN_UD2; return 1; } diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 8eca1d04aeb8..46ff304140c7 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -5080,7 +5080,7 @@ void kvm_mmu_uninit_vm(struct kvm *kvm) typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head); /* The caller should hold mmu-lock before calling this function. */ -static bool +static __always_inline bool slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, int start_level, int end_level, gfn_t start_gfn, gfn_t end_gfn, bool lock_flush_tlb) @@ -5110,7 +5110,7 @@ slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot, return flush; } -static bool +static __always_inline bool slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, int start_level, int end_level, bool lock_flush_tlb) @@ -5121,7 +5121,7 @@ slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot, lock_flush_tlb); } -static bool +static __always_inline bool slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, bool lock_flush_tlb) { @@ -5129,7 +5129,7 @@ slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot, PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); } -static bool +static __always_inline bool slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, bool lock_flush_tlb) { @@ -5137,7 +5137,7 @@ slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot, PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); } -static bool +static __always_inline bool slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, bool lock_flush_tlb) { diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index f427723dc7db..3dec126aa302 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -10136,7 +10136,10 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu, (unsigned long)(vmcs12->posted_intr_desc_addr & (PAGE_SIZE - 1))); } - if (!nested_vmx_prepare_msr_bitmap(vcpu, vmcs12)) + if (nested_vmx_prepare_msr_bitmap(vcpu, vmcs12)) + vmcs_set_bits(CPU_BASED_VM_EXEC_CONTROL, + CPU_BASED_USE_MSR_BITMAPS); + else vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL, CPU_BASED_USE_MSR_BITMAPS); } @@ -10224,8 +10227,8 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, * updated to reflect this when L1 (or its L2s) actually write to * the MSR. */ - bool pred_cmd = msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD); - bool spec_ctrl = msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL); + bool pred_cmd = !msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD); + bool spec_ctrl = !msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL); /* Nothing to do if the MSR bitmap is not in use. */ if (!cpu_has_vmx_msr_bitmap() || diff --git a/arch/x86/lib/cpu.c b/arch/x86/lib/cpu.c index d6f848d1211d..2dd1fe13a37b 100644 --- a/arch/x86/lib/cpu.c +++ b/arch/x86/lib/cpu.c @@ -18,7 +18,7 @@ unsigned int x86_model(unsigned int sig) { unsigned int fam, model; - fam = x86_family(sig); + fam = x86_family(sig); model = (sig >> 4) & 0xf; diff --git a/arch/x86/lib/error-inject.c b/arch/x86/lib/error-inject.c index 7b881d03d0dd..3cdf06128d13 100644 --- a/arch/x86/lib/error-inject.c +++ b/arch/x86/lib/error-inject.c @@ -7,6 +7,7 @@ asmlinkage void just_return_func(void); asm( ".type just_return_func, @function\n" + ".globl just_return_func\n" "just_return_func:\n" " ret\n" ".size just_return_func, .-just_return_func\n" diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 1ab42c852069..8b72923f1d35 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -256,7 +256,7 @@ static void __set_pte_vaddr(pud_t *pud, unsigned long vaddr, pte_t new_pte) * It's enough to flush this one mapping. * (PGE mappings get flushed as well) */ - __flush_tlb_one(vaddr); + __flush_tlb_one_kernel(vaddr); } void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte) @@ -1193,8 +1193,8 @@ void __init mem_init(void) register_page_bootmem_info(); /* Register memory areas for /proc/kcore */ - kclist_add(&kcore_vsyscall, (void *)VSYSCALL_ADDR, - PAGE_SIZE, KCORE_OTHER); + if (get_gate_vma(&init_mm)) + kclist_add(&kcore_vsyscall, (void *)VSYSCALL_ADDR, PAGE_SIZE, KCORE_USER); mem_init_print_info(NULL); } diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index c45b6ec5357b..e2db83bebc3b 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -820,5 +820,5 @@ void __init __early_set_fixmap(enum fixed_addresses idx, set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, flags)); else pte_clear(&init_mm, addr, pte); - __flush_tlb_one(addr); + __flush_tlb_one_kernel(addr); } diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c index 58477ec3d66d..7c8686709636 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -168,7 +168,7 @@ static int clear_page_presence(struct kmmio_fault_page *f, bool clear) return -1; } - __flush_tlb_one(f->addr); + __flush_tlb_one_kernel(f->addr); return 0; } diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index c3c5274410a9..9bb7f0ab9fe6 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -63,7 +63,7 @@ void set_pte_vaddr(unsigned long vaddr, pte_t pteval) * It's enough to flush this one mapping. * (PGE mappings get flushed as well) */ - __flush_tlb_one(vaddr); + __flush_tlb_one_kernel(vaddr); } unsigned long __FIXADDR_TOP = 0xfffff000; diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 8dcc0607f805..7f1a51399674 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -498,7 +498,7 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f, * flush that changes context.tlb_gen from 2 to 3. If they get * processed on this CPU in reverse order, we'll see * local_tlb_gen == 1, mm_tlb_gen == 3, and end != TLB_FLUSH_ALL. - * If we were to use __flush_tlb_single() and set local_tlb_gen to + * If we were to use __flush_tlb_one_user() and set local_tlb_gen to * 3, we'd be break the invariant: we'd update local_tlb_gen above * 1 without the full flush that's needed for tlb_gen 2. * @@ -519,7 +519,7 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f, addr = f->start; while (addr < f->end) { - __flush_tlb_single(addr); + __flush_tlb_one_user(addr); addr += PAGE_SIZE; } if (local) @@ -666,7 +666,7 @@ static void do_kernel_range_flush(void *info) /* flush range by one by one 'invlpg' */ for (addr = f->start; addr < f->end; addr += PAGE_SIZE) - __flush_tlb_one(addr); + __flush_tlb_one_kernel(addr); } void flush_tlb_kernel_range(unsigned long start, unsigned long end) diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 4923d92f918d..cbf94d44f3d5 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -13,6 +13,7 @@ #include <linux/if_vlan.h> #include <asm/cacheflush.h> #include <asm/set_memory.h> +#include <asm/nospec-branch.h> #include <linux/bpf.h> /* @@ -60,7 +61,12 @@ static bool is_imm8(int value) static bool is_simm32(s64 value) { - return value == (s64) (s32) value; + return value == (s64)(s32)value; +} + +static bool is_uimm32(u64 value) +{ + return value == (u64)(u32)value; } /* mov dst, src */ @@ -211,7 +217,7 @@ struct jit_context { /* emit x64 prologue code for BPF program and check it's size. * bpf_tail_call helper will skip it while jumping into another program */ -static void emit_prologue(u8 **pprog, u32 stack_depth) +static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf) { u8 *prog = *pprog; int cnt = 0; @@ -246,18 +252,21 @@ static void emit_prologue(u8 **pprog, u32 stack_depth) /* mov qword ptr [rbp+24],r15 */ EMIT4(0x4C, 0x89, 0x7D, 24); - /* Clear the tail call counter (tail_call_cnt): for eBPF tail calls - * we need to reset the counter to 0. It's done in two instructions, - * resetting rax register to 0 (xor on eax gets 0 extended), and - * moving it to the counter location. - */ + if (!ebpf_from_cbpf) { + /* Clear the tail call counter (tail_call_cnt): for eBPF tail + * calls we need to reset the counter to 0. It's done in two + * instructions, resetting rax register to 0, and moving it + * to the counter location. + */ + + /* xor eax, eax */ + EMIT2(0x31, 0xc0); + /* mov qword ptr [rbp+32], rax */ + EMIT4(0x48, 0x89, 0x45, 32); - /* xor eax, eax */ - EMIT2(0x31, 0xc0); - /* mov qword ptr [rbp+32], rax */ - EMIT4(0x48, 0x89, 0x45, 32); + BUILD_BUG_ON(cnt != PROLOGUE_SIZE); + } - BUILD_BUG_ON(cnt != PROLOGUE_SIZE); *pprog = prog; } @@ -290,7 +299,7 @@ static void emit_bpf_tail_call(u8 **pprog) EMIT2(0x89, 0xD2); /* mov edx, edx */ EMIT3(0x39, 0x56, /* cmp dword ptr [rsi + 16], edx */ offsetof(struct bpf_array, map.max_entries)); -#define OFFSET1 43 /* number of bytes to jump */ +#define OFFSET1 (41 + RETPOLINE_RAX_BPF_JIT_SIZE) /* number of bytes to jump */ EMIT2(X86_JBE, OFFSET1); /* jbe out */ label1 = cnt; @@ -299,7 +308,7 @@ static void emit_bpf_tail_call(u8 **pprog) */ EMIT2_off32(0x8B, 0x85, 36); /* mov eax, dword ptr [rbp + 36] */ EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */ -#define OFFSET2 32 +#define OFFSET2 (30 + RETPOLINE_RAX_BPF_JIT_SIZE) EMIT2(X86_JA, OFFSET2); /* ja out */ label2 = cnt; EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */ @@ -313,7 +322,7 @@ static void emit_bpf_tail_call(u8 **pprog) * goto out; */ EMIT3(0x48, 0x85, 0xC0); /* test rax,rax */ -#define OFFSET3 10 +#define OFFSET3 (8 + RETPOLINE_RAX_BPF_JIT_SIZE) EMIT2(X86_JE, OFFSET3); /* je out */ label3 = cnt; @@ -326,7 +335,7 @@ static void emit_bpf_tail_call(u8 **pprog) * rdi == ctx (1st arg) * rax == prog->bpf_func + prologue_size */ - EMIT2(0xFF, 0xE0); /* jmp rax */ + RETPOLINE_RAX_BPF_JIT(); /* out: */ BUILD_BUG_ON(cnt - label1 != OFFSET1); @@ -355,6 +364,86 @@ static void emit_load_skb_data_hlen(u8 **pprog) *pprog = prog; } +static void emit_mov_imm32(u8 **pprog, bool sign_propagate, + u32 dst_reg, const u32 imm32) +{ + u8 *prog = *pprog; + u8 b1, b2, b3; + int cnt = 0; + + /* optimization: if imm32 is positive, use 'mov %eax, imm32' + * (which zero-extends imm32) to save 2 bytes. + */ + if (sign_propagate && (s32)imm32 < 0) { + /* 'mov %rax, imm32' sign extends imm32 */ + b1 = add_1mod(0x48, dst_reg); + b2 = 0xC7; + b3 = 0xC0; + EMIT3_off32(b1, b2, add_1reg(b3, dst_reg), imm32); + goto done; + } + + /* optimization: if imm32 is zero, use 'xor %eax, %eax' + * to save 3 bytes. + */ + if (imm32 == 0) { + if (is_ereg(dst_reg)) + EMIT1(add_2mod(0x40, dst_reg, dst_reg)); + b2 = 0x31; /* xor */ + b3 = 0xC0; + EMIT2(b2, add_2reg(b3, dst_reg, dst_reg)); + goto done; + } + + /* mov %eax, imm32 */ + if (is_ereg(dst_reg)) + EMIT1(add_1mod(0x40, dst_reg)); + EMIT1_off32(add_1reg(0xB8, dst_reg), imm32); +done: + *pprog = prog; +} + +static void emit_mov_imm64(u8 **pprog, u32 dst_reg, + const u32 imm32_hi, const u32 imm32_lo) +{ + u8 *prog = *pprog; + int cnt = 0; + + if (is_uimm32(((u64)imm32_hi << 32) | (u32)imm32_lo)) { + /* For emitting plain u32, where sign bit must not be + * propagated LLVM tends to load imm64 over mov32 + * directly, so save couple of bytes by just doing + * 'mov %eax, imm32' instead. + */ + emit_mov_imm32(&prog, false, dst_reg, imm32_lo); + } else { + /* movabsq %rax, imm64 */ + EMIT2(add_1mod(0x48, dst_reg), add_1reg(0xB8, dst_reg)); + EMIT(imm32_lo, 4); + EMIT(imm32_hi, 4); + } + + *pprog = prog; +} + +static void emit_mov_reg(u8 **pprog, bool is64, u32 dst_reg, u32 src_reg) +{ + u8 *prog = *pprog; + int cnt = 0; + + if (is64) { + /* mov dst, src */ + EMIT_mov(dst_reg, src_reg); + } else { + /* mov32 dst, src */ + if (is_ereg(dst_reg) || is_ereg(src_reg)) + EMIT1(add_2mod(0x40, dst_reg, src_reg)); + EMIT2(0x89, add_2reg(0xC0, dst_reg, src_reg)); + } + + *pprog = prog; +} + static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, int oldproglen, struct jit_context *ctx) { @@ -368,7 +457,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, int proglen = 0; u8 *prog = temp; - emit_prologue(&prog, bpf_prog->aux->stack_depth); + emit_prologue(&prog, bpf_prog->aux->stack_depth, + bpf_prog_was_classic(bpf_prog)); if (seen_ld_abs) emit_load_skb_data_hlen(&prog); @@ -377,7 +467,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, const s32 imm32 = insn->imm; u32 dst_reg = insn->dst_reg; u32 src_reg = insn->src_reg; - u8 b1 = 0, b2 = 0, b3 = 0; + u8 b2 = 0, b3 = 0; s64 jmp_offset; u8 jmp_cond; bool reload_skb_data; @@ -413,16 +503,11 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, EMIT2(b2, add_2reg(0xC0, dst_reg, src_reg)); break; - /* mov dst, src */ case BPF_ALU64 | BPF_MOV | BPF_X: - EMIT_mov(dst_reg, src_reg); - break; - - /* mov32 dst, src */ case BPF_ALU | BPF_MOV | BPF_X: - if (is_ereg(dst_reg) || is_ereg(src_reg)) - EMIT1(add_2mod(0x40, dst_reg, src_reg)); - EMIT2(0x89, add_2reg(0xC0, dst_reg, src_reg)); + emit_mov_reg(&prog, + BPF_CLASS(insn->code) == BPF_ALU64, + dst_reg, src_reg); break; /* neg dst */ @@ -485,58 +570,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, break; case BPF_ALU64 | BPF_MOV | BPF_K: - /* optimization: if imm32 is positive, - * use 'mov eax, imm32' (which zero-extends imm32) - * to save 2 bytes - */ - if (imm32 < 0) { - /* 'mov rax, imm32' sign extends imm32 */ - b1 = add_1mod(0x48, dst_reg); - b2 = 0xC7; - b3 = 0xC0; - EMIT3_off32(b1, b2, add_1reg(b3, dst_reg), imm32); - break; - } - case BPF_ALU | BPF_MOV | BPF_K: - /* optimization: if imm32 is zero, use 'xor <dst>,<dst>' - * to save 3 bytes. - */ - if (imm32 == 0) { - if (is_ereg(dst_reg)) - EMIT1(add_2mod(0x40, dst_reg, dst_reg)); - b2 = 0x31; /* xor */ - b3 = 0xC0; - EMIT2(b2, add_2reg(b3, dst_reg, dst_reg)); - break; - } - - /* mov %eax, imm32 */ - if (is_ereg(dst_reg)) - EMIT1(add_1mod(0x40, dst_reg)); - EMIT1_off32(add_1reg(0xB8, dst_reg), imm32); + emit_mov_imm32(&prog, BPF_CLASS(insn->code) == BPF_ALU64, + dst_reg, imm32); break; case BPF_LD | BPF_IMM | BPF_DW: - /* optimization: if imm64 is zero, use 'xor <dst>,<dst>' - * to save 7 bytes. - */ - if (insn[0].imm == 0 && insn[1].imm == 0) { - b1 = add_2mod(0x48, dst_reg, dst_reg); - b2 = 0x31; /* xor */ - b3 = 0xC0; - EMIT3(b1, b2, add_2reg(b3, dst_reg, dst_reg)); - - insn++; - i++; - break; - } - - /* movabsq %rax, imm64 */ - EMIT2(add_1mod(0x48, dst_reg), add_1reg(0xB8, dst_reg)); - EMIT(insn[0].imm, 4); - EMIT(insn[1].imm, 4); - + emit_mov_imm64(&prog, dst_reg, insn[1].imm, insn[0].imm); insn++; i++; break; @@ -593,36 +633,38 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, case BPF_ALU | BPF_MUL | BPF_X: case BPF_ALU64 | BPF_MUL | BPF_K: case BPF_ALU64 | BPF_MUL | BPF_X: - EMIT1(0x50); /* push rax */ - EMIT1(0x52); /* push rdx */ + { + bool is64 = BPF_CLASS(insn->code) == BPF_ALU64; + + if (dst_reg != BPF_REG_0) + EMIT1(0x50); /* push rax */ + if (dst_reg != BPF_REG_3) + EMIT1(0x52); /* push rdx */ /* mov r11, dst_reg */ EMIT_mov(AUX_REG, dst_reg); if (BPF_SRC(insn->code) == BPF_X) - /* mov rax, src_reg */ - EMIT_mov(BPF_REG_0, src_reg); + emit_mov_reg(&prog, is64, BPF_REG_0, src_reg); else - /* mov rax, imm32 */ - EMIT3_off32(0x48, 0xC7, 0xC0, imm32); + emit_mov_imm32(&prog, is64, BPF_REG_0, imm32); - if (BPF_CLASS(insn->code) == BPF_ALU64) + if (is64) EMIT1(add_1mod(0x48, AUX_REG)); else if (is_ereg(AUX_REG)) EMIT1(add_1mod(0x40, AUX_REG)); /* mul(q) r11 */ EMIT2(0xF7, add_1reg(0xE0, AUX_REG)); - /* mov r11, rax */ - EMIT_mov(AUX_REG, BPF_REG_0); - - EMIT1(0x5A); /* pop rdx */ - EMIT1(0x58); /* pop rax */ - - /* mov dst_reg, r11 */ - EMIT_mov(dst_reg, AUX_REG); + if (dst_reg != BPF_REG_3) + EMIT1(0x5A); /* pop rdx */ + if (dst_reg != BPF_REG_0) { + /* mov dst_reg, rax */ + EMIT_mov(dst_reg, BPF_REG_0); + EMIT1(0x58); /* pop rax */ + } break; - + } /* shifts */ case BPF_ALU | BPF_LSH | BPF_K: case BPF_ALU | BPF_RSH | BPF_K: @@ -640,7 +682,11 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, case BPF_RSH: b3 = 0xE8; break; case BPF_ARSH: b3 = 0xF8; break; } - EMIT3(0xC1, add_1reg(b3, dst_reg), imm32); + + if (imm32 == 1) + EMIT2(0xD1, add_1reg(b3, dst_reg)); + else + EMIT3(0xC1, add_1reg(b3, dst_reg), imm32); break; case BPF_ALU | BPF_LSH | BPF_X: diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index c2e9285d1bf1..db77e087adaf 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -299,7 +299,7 @@ static void bau_process_message(struct msg_desc *mdp, struct bau_control *bcp, local_flush_tlb(); stat->d_alltlb++; } else { - __flush_tlb_single(msg->address); + __flush_tlb_one_user(msg->address); stat->d_onetlb++; } stat->d_requestee++; diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index 5d73c443e778..220e97841e49 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -770,9 +770,12 @@ static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym, break; case R_X86_64_PC32: + case R_X86_64_PLT32: /* * PC relative relocations don't need to be adjusted unless * referencing a percpu symbol. + * + * NB: R_X86_64_PLT32 can be treated as R_X86_64_PC32. */ if (is_percpu_sym(sym, symname)) add_reloc(&relocs32neg, offset); diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index d85076223a69..aae88fec9941 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1300,12 +1300,12 @@ static void xen_flush_tlb(void) preempt_enable(); } -static void xen_flush_tlb_single(unsigned long addr) +static void xen_flush_tlb_one_user(unsigned long addr) { struct mmuext_op *op; struct multicall_space mcs; - trace_xen_mmu_flush_tlb_single(addr); + trace_xen_mmu_flush_tlb_one_user(addr); preempt_disable(); @@ -2370,7 +2370,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = { .flush_tlb_user = xen_flush_tlb, .flush_tlb_kernel = xen_flush_tlb, - .flush_tlb_single = xen_flush_tlb_single, + .flush_tlb_one_user = xen_flush_tlb_one_user, .flush_tlb_others = xen_flush_tlb_others, .pgd_alloc = xen_pgd_alloc, diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 77c959cf81e7..7a43b2ae19f1 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -122,6 +122,8 @@ void __init xen_smp_cpus_done(unsigned int max_cpus) if (xen_hvm_domain()) native_smp_cpus_done(max_cpus); + else + calculate_max_logical_packages(); if (xen_have_vcpu_info_placement) return; diff --git a/block/blk-mq.c b/block/blk-mq.c index df93102e2149..357492712b0e 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -3164,6 +3164,7 @@ static bool __blk_mq_poll(struct blk_mq_hw_ctx *hctx, struct request *rq) cpu_relax(); } + __set_current_state(TASK_RUNNING); return false; } diff --git a/certs/blacklist_nohashes.c b/certs/blacklist_nohashes.c index 73fd99098ad7..753b703ef0ef 100644 --- a/certs/blacklist_nohashes.c +++ b/certs/blacklist_nohashes.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include "blacklist.h" -const char __initdata *const blacklist_hashes[] = { +const char __initconst *const blacklist_hashes[] = { NULL }; diff --git a/crypto/asymmetric_keys/pkcs7_trust.c b/crypto/asymmetric_keys/pkcs7_trust.c index 1f4e25f10049..598906b1e28d 100644 --- a/crypto/asymmetric_keys/pkcs7_trust.c +++ b/crypto/asymmetric_keys/pkcs7_trust.c @@ -106,6 +106,7 @@ static int pkcs7_validate_trust_one(struct pkcs7_message *pkcs7, pr_devel("sinfo %u: Direct signer is key %x\n", sinfo->index, key_serial(key)); x509 = NULL; + sig = sinfo->sig; goto matched; } if (PTR_ERR(key) != -ENOKEY) diff --git a/crypto/asymmetric_keys/pkcs7_verify.c b/crypto/asymmetric_keys/pkcs7_verify.c index 39e6de0c2761..97c77f66b20d 100644 --- a/crypto/asymmetric_keys/pkcs7_verify.c +++ b/crypto/asymmetric_keys/pkcs7_verify.c @@ -270,7 +270,7 @@ static int pkcs7_verify_sig_chain(struct pkcs7_message *pkcs7, sinfo->index); return 0; } - ret = public_key_verify_signature(p->pub, p->sig); + ret = public_key_verify_signature(p->pub, x509->sig); if (ret < 0) return ret; x509->signer = p; @@ -366,8 +366,7 @@ static int pkcs7_verify_one(struct pkcs7_message *pkcs7, * * (*) -EBADMSG if some part of the message was invalid, or: * - * (*) 0 if no signature chains were found to be blacklisted or to contain - * unsupported crypto, or: + * (*) 0 if a signature chain passed verification, or: * * (*) -EKEYREJECTED if a blacklisted key was encountered, or: * @@ -423,8 +422,11 @@ int pkcs7_verify(struct pkcs7_message *pkcs7, for (sinfo = pkcs7->signed_infos; sinfo; sinfo = sinfo->next) { ret = pkcs7_verify_one(pkcs7, sinfo); - if (sinfo->blacklisted && actual_ret == -ENOPKG) - actual_ret = -EKEYREJECTED; + if (sinfo->blacklisted) { + if (actual_ret == -ENOPKG) + actual_ret = -EKEYREJECTED; + continue; + } if (ret < 0) { if (ret == -ENOPKG) { sinfo->unsupported_crypto = true; diff --git a/crypto/asymmetric_keys/public_key.c b/crypto/asymmetric_keys/public_key.c index de996586762a..e929fe1e4106 100644 --- a/crypto/asymmetric_keys/public_key.c +++ b/crypto/asymmetric_keys/public_key.c @@ -79,9 +79,11 @@ int public_key_verify_signature(const struct public_key *pkey, BUG_ON(!pkey); BUG_ON(!sig); - BUG_ON(!sig->digest); BUG_ON(!sig->s); + if (!sig->digest) + return -ENOPKG; + alg_name = sig->pkey_algo; if (strcmp(sig->pkey_algo, "rsa") == 0) { /* The data wangled by the RSA algorithm is typically padded diff --git a/crypto/asymmetric_keys/restrict.c b/crypto/asymmetric_keys/restrict.c index 86fb68508952..7c93c7728454 100644 --- a/crypto/asymmetric_keys/restrict.c +++ b/crypto/asymmetric_keys/restrict.c @@ -67,8 +67,9 @@ __setup("ca_keys=", ca_keys_setup); * * Returns 0 if the new certificate was accepted, -ENOKEY if we couldn't find a * matching parent certificate in the trusted list, -EKEYREJECTED if the - * signature check fails or the key is blacklisted and some other error if - * there is a matching certificate but the signature check cannot be performed. + * signature check fails or the key is blacklisted, -ENOPKG if the signature + * uses unsupported crypto, or some other error if there is a matching + * certificate but the signature check cannot be performed. */ int restrict_link_by_signature(struct key *dest_keyring, const struct key_type *type, @@ -88,6 +89,8 @@ int restrict_link_by_signature(struct key *dest_keyring, return -EOPNOTSUPP; sig = payload->data[asym_auth]; + if (!sig) + return -ENOPKG; if (!sig->auth_ids[0] && !sig->auth_ids[1]) return -ENOKEY; @@ -139,6 +142,8 @@ static int key_or_keyring_common(struct key *dest_keyring, return -EOPNOTSUPP; sig = payload->data[asym_auth]; + if (!sig) + return -ENOPKG; if (!sig->auth_ids[0] && !sig->auth_ids[1]) return -ENOKEY; @@ -222,9 +227,9 @@ static int key_or_keyring_common(struct key *dest_keyring, * * Returns 0 if the new certificate was accepted, -ENOKEY if we * couldn't find a matching parent certificate in the trusted list, - * -EKEYREJECTED if the signature check fails, and some other error if - * there is a matching certificate but the signature check cannot be - * performed. + * -EKEYREJECTED if the signature check fails, -ENOPKG if the signature uses + * unsupported crypto, or some other error if there is a matching certificate + * but the signature check cannot be performed. */ int restrict_link_by_key_or_keyring(struct key *dest_keyring, const struct key_type *type, @@ -249,9 +254,9 @@ int restrict_link_by_key_or_keyring(struct key *dest_keyring, * * Returns 0 if the new certificate was accepted, -ENOKEY if we * couldn't find a matching parent certificate in the trusted list, - * -EKEYREJECTED if the signature check fails, and some other error if - * there is a matching certificate but the signature check cannot be - * performed. + * -EKEYREJECTED if the signature check fails, -ENOPKG if the signature uses + * unsupported crypto, or some other error if there is a matching certificate + * but the signature check cannot be performed. */ int restrict_link_by_key_or_keyring_chain(struct key *dest_keyring, const struct key_type *type, diff --git a/crypto/sha3_generic.c b/crypto/sha3_generic.c index a965b9d80559..ded148783303 100644 --- a/crypto/sha3_generic.c +++ b/crypto/sha3_generic.c @@ -20,6 +20,20 @@ #include <crypto/sha3.h> #include <asm/unaligned.h> +/* + * On some 32-bit architectures (mn10300 and h8300), GCC ends up using + * over 1 KB of stack if we inline the round calculation into the loop + * in keccakf(). On the other hand, on 64-bit architectures with plenty + * of [64-bit wide] general purpose registers, not inlining it severely + * hurts performance. So let's use 64-bitness as a heuristic to decide + * whether to inline or not. + */ +#ifdef CONFIG_64BIT +#define SHA3_INLINE inline +#else +#define SHA3_INLINE noinline +#endif + #define KECCAK_ROUNDS 24 static const u64 keccakf_rndc[24] = { @@ -35,111 +49,115 @@ static const u64 keccakf_rndc[24] = { /* update the state with given number of rounds */ -static void __attribute__((__optimize__("O3"))) keccakf(u64 st[25]) +static SHA3_INLINE void keccakf_round(u64 st[25]) { u64 t[5], tt, bc[5]; - int round; - for (round = 0; round < KECCAK_ROUNDS; round++) { + /* Theta */ + bc[0] = st[0] ^ st[5] ^ st[10] ^ st[15] ^ st[20]; + bc[1] = st[1] ^ st[6] ^ st[11] ^ st[16] ^ st[21]; + bc[2] = st[2] ^ st[7] ^ st[12] ^ st[17] ^ st[22]; + bc[3] = st[3] ^ st[8] ^ st[13] ^ st[18] ^ st[23]; + bc[4] = st[4] ^ st[9] ^ st[14] ^ st[19] ^ st[24]; + + t[0] = bc[4] ^ rol64(bc[1], 1); + t[1] = bc[0] ^ rol64(bc[2], 1); + t[2] = bc[1] ^ rol64(bc[3], 1); + t[3] = bc[2] ^ rol64(bc[4], 1); + t[4] = bc[3] ^ rol64(bc[0], 1); + + st[0] ^= t[0]; + + /* Rho Pi */ + tt = st[1]; + st[ 1] = rol64(st[ 6] ^ t[1], 44); + st[ 6] = rol64(st[ 9] ^ t[4], 20); + st[ 9] = rol64(st[22] ^ t[2], 61); + st[22] = rol64(st[14] ^ t[4], 39); + st[14] = rol64(st[20] ^ t[0], 18); + st[20] = rol64(st[ 2] ^ t[2], 62); + st[ 2] = rol64(st[12] ^ t[2], 43); + st[12] = rol64(st[13] ^ t[3], 25); + st[13] = rol64(st[19] ^ t[4], 8); + st[19] = rol64(st[23] ^ t[3], 56); + st[23] = rol64(st[15] ^ t[0], 41); + st[15] = rol64(st[ 4] ^ t[4], 27); + st[ 4] = rol64(st[24] ^ t[4], 14); + st[24] = rol64(st[21] ^ t[1], 2); + st[21] = rol64(st[ 8] ^ t[3], 55); + st[ 8] = rol64(st[16] ^ t[1], 45); + st[16] = rol64(st[ 5] ^ t[0], 36); + st[ 5] = rol64(st[ 3] ^ t[3], 28); + st[ 3] = rol64(st[18] ^ t[3], 21); + st[18] = rol64(st[17] ^ t[2], 15); + st[17] = rol64(st[11] ^ t[1], 10); + st[11] = rol64(st[ 7] ^ t[2], 6); + st[ 7] = rol64(st[10] ^ t[0], 3); + st[10] = rol64( tt ^ t[1], 1); + + /* Chi */ + bc[ 0] = ~st[ 1] & st[ 2]; + bc[ 1] = ~st[ 2] & st[ 3]; + bc[ 2] = ~st[ 3] & st[ 4]; + bc[ 3] = ~st[ 4] & st[ 0]; + bc[ 4] = ~st[ 0] & st[ 1]; + st[ 0] ^= bc[ 0]; + st[ 1] ^= bc[ 1]; + st[ 2] ^= bc[ 2]; + st[ 3] ^= bc[ 3]; + st[ 4] ^= bc[ 4]; + + bc[ 0] = ~st[ 6] & st[ 7]; + bc[ 1] = ~st[ 7] & st[ 8]; + bc[ 2] = ~st[ 8] & st[ 9]; + bc[ 3] = ~st[ 9] & st[ 5]; + bc[ 4] = ~st[ 5] & st[ 6]; + st[ 5] ^= bc[ 0]; + st[ 6] ^= bc[ 1]; + st[ 7] ^= bc[ 2]; + st[ 8] ^= bc[ 3]; + st[ 9] ^= bc[ 4]; + + bc[ 0] = ~st[11] & st[12]; + bc[ 1] = ~st[12] & st[13]; + bc[ 2] = ~st[13] & st[14]; + bc[ 3] = ~st[14] & st[10]; + bc[ 4] = ~st[10] & st[11]; + st[10] ^= bc[ 0]; + st[11] ^= bc[ 1]; + st[12] ^= bc[ 2]; + st[13] ^= bc[ 3]; + st[14] ^= bc[ 4]; + + bc[ 0] = ~st[16] & st[17]; + bc[ 1] = ~st[17] & st[18]; + bc[ 2] = ~st[18] & st[19]; + bc[ 3] = ~st[19] & st[15]; + bc[ 4] = ~st[15] & st[16]; + st[15] ^= bc[ 0]; + st[16] ^= bc[ 1]; + st[17] ^= bc[ 2]; + st[18] ^= bc[ 3]; + st[19] ^= bc[ 4]; + + bc[ 0] = ~st[21] & st[22]; + bc[ 1] = ~st[22] & st[23]; + bc[ 2] = ~st[23] & st[24]; + bc[ 3] = ~st[24] & st[20]; + bc[ 4] = ~st[20] & st[21]; + st[20] ^= bc[ 0]; + st[21] ^= bc[ 1]; + st[22] ^= bc[ 2]; + st[23] ^= bc[ 3]; + st[24] ^= bc[ 4]; +} - /* Theta */ - bc[0] = st[0] ^ st[5] ^ st[10] ^ st[15] ^ st[20]; - bc[1] = st[1] ^ st[6] ^ st[11] ^ st[16] ^ st[21]; - bc[2] = st[2] ^ st[7] ^ st[12] ^ st[17] ^ st[22]; - bc[3] = st[3] ^ st[8] ^ st[13] ^ st[18] ^ st[23]; - bc[4] = st[4] ^ st[9] ^ st[14] ^ st[19] ^ st[24]; - - t[0] = bc[4] ^ rol64(bc[1], 1); - t[1] = bc[0] ^ rol64(bc[2], 1); - t[2] = bc[1] ^ rol64(bc[3], 1); - t[3] = bc[2] ^ rol64(bc[4], 1); - t[4] = bc[3] ^ rol64(bc[0], 1); - - st[0] ^= t[0]; - - /* Rho Pi */ - tt = st[1]; - st[ 1] = rol64(st[ 6] ^ t[1], 44); - st[ 6] = rol64(st[ 9] ^ t[4], 20); - st[ 9] = rol64(st[22] ^ t[2], 61); - st[22] = rol64(st[14] ^ t[4], 39); - st[14] = rol64(st[20] ^ t[0], 18); - st[20] = rol64(st[ 2] ^ t[2], 62); - st[ 2] = rol64(st[12] ^ t[2], 43); - st[12] = rol64(st[13] ^ t[3], 25); - st[13] = rol64(st[19] ^ t[4], 8); - st[19] = rol64(st[23] ^ t[3], 56); - st[23] = rol64(st[15] ^ t[0], 41); - st[15] = rol64(st[ 4] ^ t[4], 27); - st[ 4] = rol64(st[24] ^ t[4], 14); - st[24] = rol64(st[21] ^ t[1], 2); - st[21] = rol64(st[ 8] ^ t[3], 55); - st[ 8] = rol64(st[16] ^ t[1], 45); - st[16] = rol64(st[ 5] ^ t[0], 36); - st[ 5] = rol64(st[ 3] ^ t[3], 28); - st[ 3] = rol64(st[18] ^ t[3], 21); - st[18] = rol64(st[17] ^ t[2], 15); - st[17] = rol64(st[11] ^ t[1], 10); - st[11] = rol64(st[ 7] ^ t[2], 6); - st[ 7] = rol64(st[10] ^ t[0], 3); - st[10] = rol64( tt ^ t[1], 1); - - /* Chi */ - bc[ 0] = ~st[ 1] & st[ 2]; - bc[ 1] = ~st[ 2] & st[ 3]; - bc[ 2] = ~st[ 3] & st[ 4]; - bc[ 3] = ~st[ 4] & st[ 0]; - bc[ 4] = ~st[ 0] & st[ 1]; - st[ 0] ^= bc[ 0]; - st[ 1] ^= bc[ 1]; - st[ 2] ^= bc[ 2]; - st[ 3] ^= bc[ 3]; - st[ 4] ^= bc[ 4]; - - bc[ 0] = ~st[ 6] & st[ 7]; - bc[ 1] = ~st[ 7] & st[ 8]; - bc[ 2] = ~st[ 8] & st[ 9]; - bc[ 3] = ~st[ 9] & st[ 5]; - bc[ 4] = ~st[ 5] & st[ 6]; - st[ 5] ^= bc[ 0]; - st[ 6] ^= bc[ 1]; - st[ 7] ^= bc[ 2]; - st[ 8] ^= bc[ 3]; - st[ 9] ^= bc[ 4]; - - bc[ 0] = ~st[11] & st[12]; - bc[ 1] = ~st[12] & st[13]; - bc[ 2] = ~st[13] & st[14]; - bc[ 3] = ~st[14] & st[10]; - bc[ 4] = ~st[10] & st[11]; - st[10] ^= bc[ 0]; - st[11] ^= bc[ 1]; - st[12] ^= bc[ 2]; - st[13] ^= bc[ 3]; - st[14] ^= bc[ 4]; - - bc[ 0] = ~st[16] & st[17]; - bc[ 1] = ~st[17] & st[18]; - bc[ 2] = ~st[18] & st[19]; - bc[ 3] = ~st[19] & st[15]; - bc[ 4] = ~st[15] & st[16]; - st[15] ^= bc[ 0]; - st[16] ^= bc[ 1]; - st[17] ^= bc[ 2]; - st[18] ^= bc[ 3]; - st[19] ^= bc[ 4]; - - bc[ 0] = ~st[21] & st[22]; - bc[ 1] = ~st[22] & st[23]; - bc[ 2] = ~st[23] & st[24]; - bc[ 3] = ~st[24] & st[20]; - bc[ 4] = ~st[20] & st[21]; - st[20] ^= bc[ 0]; - st[21] ^= bc[ 1]; - st[22] ^= bc[ 2]; - st[23] ^= bc[ 3]; - st[24] ^= bc[ 4]; +static void __optimize("O3") keccakf(u64 st[25]) +{ + int round; + for (round = 0; round < KECCAK_ROUNDS; round++) { + keccakf_round(st); /* Iota */ st[0] ^= keccakf_rndc[round]; } diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index 676c9788e1c8..0dad0bd9327b 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -660,13 +660,15 @@ struct acpi_device *acpi_companion_match(const struct device *dev) * acpi_of_match_device - Match device object using the "compatible" property. * @adev: ACPI device object to match. * @of_match_table: List of device IDs to match against. + * @of_id: OF ID if matched * * If @dev has an ACPI companion which has ACPI_DT_NAMESPACE_HID in its list of * identifiers and a _DSD object with the "compatible" property, use that * property to match against the given list of identifiers. */ static bool acpi_of_match_device(struct acpi_device *adev, - const struct of_device_id *of_match_table) + const struct of_device_id *of_match_table, + const struct of_device_id **of_id) { const union acpi_object *of_compatible, *obj; int i, nval; @@ -690,8 +692,11 @@ static bool acpi_of_match_device(struct acpi_device *adev, const struct of_device_id *id; for (id = of_match_table; id->compatible[0]; id++) - if (!strcasecmp(obj->string.pointer, id->compatible)) + if (!strcasecmp(obj->string.pointer, id->compatible)) { + if (of_id) + *of_id = id; return true; + } } return false; @@ -762,10 +767,11 @@ static bool __acpi_match_device_cls(const struct acpi_device_id *id, return true; } -static const struct acpi_device_id *__acpi_match_device( - struct acpi_device *device, - const struct acpi_device_id *ids, - const struct of_device_id *of_ids) +static bool __acpi_match_device(struct acpi_device *device, + const struct acpi_device_id *acpi_ids, + const struct of_device_id *of_ids, + const struct acpi_device_id **acpi_id, + const struct of_device_id **of_id) { const struct acpi_device_id *id; struct acpi_hardware_id *hwid; @@ -775,30 +781,32 @@ static const struct acpi_device_id *__acpi_match_device( * driver for it. */ if (!device || !device->status.present) - return NULL; + return false; list_for_each_entry(hwid, &device->pnp.ids, list) { /* First, check the ACPI/PNP IDs provided by the caller. */ - for (id = ids; id->id[0] || id->cls; id++) { - if (id->id[0] && !strcmp((char *) id->id, hwid->id)) - return id; - else if (id->cls && __acpi_match_device_cls(id, hwid)) - return id; + if (acpi_ids) { + for (id = acpi_ids; id->id[0] || id->cls; id++) { + if (id->id[0] && !strcmp((char *)id->id, hwid->id)) + goto out_acpi_match; + if (id->cls && __acpi_match_device_cls(id, hwid)) + goto out_acpi_match; + } } /* * Next, check ACPI_DT_NAMESPACE_HID and try to match the * "compatible" property if found. - * - * The id returned by the below is not valid, but the only - * caller passing non-NULL of_ids here is only interested in - * whether or not the return value is NULL. */ - if (!strcmp(ACPI_DT_NAMESPACE_HID, hwid->id) - && acpi_of_match_device(device, of_ids)) - return id; + if (!strcmp(ACPI_DT_NAMESPACE_HID, hwid->id)) + return acpi_of_match_device(device, of_ids, of_id); } - return NULL; + return false; + +out_acpi_match: + if (acpi_id) + *acpi_id = id; + return true; } /** @@ -815,32 +823,29 @@ static const struct acpi_device_id *__acpi_match_device( const struct acpi_device_id *acpi_match_device(const struct acpi_device_id *ids, const struct device *dev) { - return __acpi_match_device(acpi_companion_match(dev), ids, NULL); + const struct acpi_device_id *id = NULL; + + __acpi_match_device(acpi_companion_match(dev), ids, NULL, &id, NULL); + return id; } EXPORT_SYMBOL_GPL(acpi_match_device); -void *acpi_get_match_data(const struct device *dev) +const void *acpi_device_get_match_data(const struct device *dev) { const struct acpi_device_id *match; - if (!dev->driver) - return NULL; - - if (!dev->driver->acpi_match_table) - return NULL; - match = acpi_match_device(dev->driver->acpi_match_table, dev); if (!match) return NULL; - return (void *)match->driver_data; + return (const void *)match->driver_data; } -EXPORT_SYMBOL_GPL(acpi_get_match_data); +EXPORT_SYMBOL_GPL(acpi_device_get_match_data); int acpi_match_device_ids(struct acpi_device *device, const struct acpi_device_id *ids) { - return __acpi_match_device(device, ids, NULL) ? 0 : -ENOENT; + return __acpi_match_device(device, ids, NULL, NULL, NULL) ? 0 : -ENOENT; } EXPORT_SYMBOL(acpi_match_device_ids); @@ -849,10 +854,12 @@ bool acpi_driver_match_device(struct device *dev, { if (!drv->acpi_match_table) return acpi_of_match_device(ACPI_COMPANION(dev), - drv->of_match_table); + drv->of_match_table, + NULL); - return !!__acpi_match_device(acpi_companion_match(dev), - drv->acpi_match_table, drv->of_match_table); + return __acpi_match_device(acpi_companion_match(dev), + drv->acpi_match_table, drv->of_match_table, + NULL, NULL); } EXPORT_SYMBOL_GPL(acpi_driver_match_device); diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index d9f38c645e4a..30a572956557 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1927,6 +1927,9 @@ static int acpi_ec_suspend_noirq(struct device *dev) ec->reference_count >= 1) acpi_set_gpe(NULL, ec->gpe, ACPI_GPE_DISABLE); + if (acpi_sleep_no_ec_events()) + acpi_ec_enter_noirq(ec); + return 0; } @@ -1934,6 +1937,9 @@ static int acpi_ec_resume_noirq(struct device *dev) { struct acpi_ec *ec = acpi_driver_data(to_acpi_device(dev)); + if (acpi_sleep_no_ec_events()) + acpi_ec_leave_noirq(ec); + if (ec_no_wakeup && test_bit(EC_FLAGS_STARTED, &ec->flags) && ec->reference_count >= 1) acpi_set_gpe(NULL, ec->gpe, ACPI_GPE_ENABLE); diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c index 466d1503aba0..5815356ea6ad 100644 --- a/drivers/acpi/property.c +++ b/drivers/acpi/property.c @@ -1271,11 +1271,11 @@ static int acpi_fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode, return 0; } -static void * +static const void * acpi_fwnode_device_get_match_data(const struct fwnode_handle *fwnode, const struct device *dev) { - return acpi_get_match_data(dev); + return acpi_device_get_match_data(dev); } #define DECLARE_ACPI_FWNODE_OPS(ops) \ diff --git a/drivers/acpi/spcr.c b/drivers/acpi/spcr.c index 89e97d21a89c..9d52743080a4 100644 --- a/drivers/acpi/spcr.c +++ b/drivers/acpi/spcr.c @@ -115,6 +115,7 @@ int __init acpi_parse_spcr(bool enable_earlycon, bool enable_console) table->serial_port.access_width))) { default: pr_err("Unexpected SPCR Access Width. Defaulting to byte size\n"); + /* fall through */ case 8: iotype = "mmio"; break; diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 15e3d3c2260d..764b63a5aade 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -1991,8 +1991,14 @@ static void binder_send_failed_reply(struct binder_transaction *t, &target_thread->reply_error.work); wake_up_interruptible(&target_thread->wait); } else { - WARN(1, "Unexpected reply error: %u\n", - target_thread->reply_error.cmd); + /* + * Cannot get here for normal operation, but + * we can if multiple synchronous transactions + * are sent without blocking for responses. + * Just ignore the 2nd error in this case. + */ + pr_warn("Unexpected reply error: %u\n", + target_thread->reply_error.cmd); } binder_inner_proc_unlock(target_thread->proc); binder_thread_dec_tmpref(target_thread); @@ -2193,7 +2199,7 @@ static void binder_transaction_buffer_release(struct binder_proc *proc, int debug_id = buffer->debug_id; binder_debug(BINDER_DEBUG_TRANSACTION, - "%d buffer release %d, size %zd-%zd, failed at %p\n", + "%d buffer release %d, size %zd-%zd, failed at %pK\n", proc->pid, buffer->debug_id, buffer->data_size, buffer->offsets_size, failed_at); @@ -3705,7 +3711,7 @@ static int binder_thread_write(struct binder_proc *proc, } } binder_debug(BINDER_DEBUG_DEAD_BINDER, - "%d:%d BC_DEAD_BINDER_DONE %016llx found %p\n", + "%d:%d BC_DEAD_BINDER_DONE %016llx found %pK\n", proc->pid, thread->pid, (u64)cookie, death); if (death == NULL) { @@ -4376,6 +4382,15 @@ static int binder_thread_release(struct binder_proc *proc, binder_inner_proc_unlock(thread->proc); + /* + * This is needed to avoid races between wake_up_poll() above and + * and ep_remove_waitqueue() called for other reasons (eg the epoll file + * descriptor being closed); ep_remove_waitqueue() holds an RCU read + * lock, so we can be sure it's done after calling synchronize_rcu(). + */ + if (thread->looper & BINDER_LOOPER_STATE_POLL) + synchronize_rcu(); + if (send_reply) binder_send_failed_reply(send_reply, BR_DEAD_REPLY); binder_release_work(proc, &thread->todo); @@ -4391,6 +4406,8 @@ static __poll_t binder_poll(struct file *filp, bool wait_for_proc_work; thread = binder_get_thread(proc); + if (!thread) + return POLLERR; binder_inner_proc_lock(thread->proc); thread->looper |= BINDER_LOOPER_STATE_POLL; @@ -5034,7 +5051,7 @@ static void print_binder_transaction_ilocked(struct seq_file *m, spin_lock(&t->lock); to_proc = t->to_proc; seq_printf(m, - "%s %d: %p from %d:%d to %d:%d code %x flags %x pri %ld r%d", + "%s %d: %pK from %d:%d to %d:%d code %x flags %x pri %ld r%d", prefix, t->debug_id, t, t->from ? t->from->proc->pid : 0, t->from ? t->from->pid : 0, @@ -5058,7 +5075,7 @@ static void print_binder_transaction_ilocked(struct seq_file *m, } if (buffer->target_node) seq_printf(m, " node %d", buffer->target_node->debug_id); - seq_printf(m, " size %zd:%zd data %p\n", + seq_printf(m, " size %zd:%zd data %pK\n", buffer->data_size, buffer->offsets_size, buffer->data); } diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c index 0277f36be85b..6e737142ceaa 100644 --- a/drivers/atm/idt77252.c +++ b/drivers/atm/idt77252.c @@ -3173,14 +3173,10 @@ static void init_sram(struct idt77252_dev *card) (u32) 0xffffffff); } - writel((SAR_FBQ0_LOW << 28) | 0x00000000 | 0x00000000 | - (SAR_FB_SIZE_0 / 48), SAR_REG_FBQS0); - writel((SAR_FBQ1_LOW << 28) | 0x00000000 | 0x00000000 | - (SAR_FB_SIZE_1 / 48), SAR_REG_FBQS1); - writel((SAR_FBQ2_LOW << 28) | 0x00000000 | 0x00000000 | - (SAR_FB_SIZE_2 / 48), SAR_REG_FBQS2); - writel((SAR_FBQ3_LOW << 28) | 0x00000000 | 0x00000000 | - (SAR_FB_SIZE_3 / 48), SAR_REG_FBQS3); + writel((SAR_FBQ0_LOW << 28) | (SAR_FB_SIZE_0 / 48), SAR_REG_FBQS0); + writel((SAR_FBQ1_LOW << 28) | (SAR_FB_SIZE_1 / 48), SAR_REG_FBQS1); + writel((SAR_FBQ2_LOW << 28) | (SAR_FB_SIZE_2 / 48), SAR_REG_FBQS2); + writel((SAR_FBQ3_LOW << 28) | (SAR_FB_SIZE_3 / 48), SAR_REG_FBQS3); /* Initialize rate table */ for (i = 0; i < 256; i++) { diff --git a/drivers/base/core.c b/drivers/base/core.c index b2261f92f2f1..5847364f25d9 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -310,6 +310,9 @@ static void __device_link_del(struct device_link *link) dev_info(link->consumer, "Dropping the link to %s\n", dev_name(link->supplier)); + if (link->flags & DL_FLAG_PM_RUNTIME) + pm_runtime_drop_link(link->consumer); + list_del(&link->s_node); list_del(&link->c_node); device_link_free(link); diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c index a8ac86e4d79e..6637fc319269 100644 --- a/drivers/base/power/wakeirq.c +++ b/drivers/base/power/wakeirq.c @@ -321,7 +321,8 @@ void dev_pm_arm_wake_irq(struct wake_irq *wirq) return; if (device_may_wakeup(wirq->dev)) { - if (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED) + if (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED && + !pm_runtime_status_suspended(wirq->dev)) enable_irq(wirq->irq); enable_irq_wake(wirq->irq); @@ -343,7 +344,8 @@ void dev_pm_disarm_wake_irq(struct wake_irq *wirq) if (device_may_wakeup(wirq->dev)) { disable_irq_wake(wirq->irq); - if (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED) + if (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED && + !pm_runtime_status_suspended(wirq->dev)) disable_irq_nosync(wirq->irq); } } diff --git a/drivers/base/property.c b/drivers/base/property.c index 302236281d83..8f205f6461ed 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -1410,9 +1410,8 @@ int fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode, } EXPORT_SYMBOL(fwnode_graph_parse_endpoint); -void *device_get_match_data(struct device *dev) +const void *device_get_match_data(struct device *dev) { - return fwnode_call_ptr_op(dev_fwnode(dev), device_get_match_data, - dev); + return fwnode_call_ptr_op(dev_fwnode(dev), device_get_match_data, dev); } EXPORT_SYMBOL_GPL(device_get_match_data); diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c index 204afe66de92..3d7a5c149af3 100644 --- a/drivers/bluetooth/ath3k.c +++ b/drivers/bluetooth/ath3k.c @@ -203,6 +203,12 @@ static const struct usb_device_id ath3k_blist_tbl[] = { { } /* Terminating entry */ }; +static inline void ath3k_log_failed_loading(int err, int len, int size) +{ + BT_ERR("Error in firmware loading err = %d, len = %d, size = %d", + err, len, size); +} + #define USB_REQ_DFU_DNLOAD 1 #define BULK_SIZE 4096 #define FW_HDR_SIZE 20 @@ -227,15 +233,16 @@ static int ath3k_load_firmware(struct usb_device *udev, return -ENOMEM; } - memcpy(send_buf, firmware->data, 20); + memcpy(send_buf, firmware->data, FW_HDR_SIZE); err = usb_control_msg(udev, pipe, USB_REQ_DFU_DNLOAD, USB_TYPE_VENDOR, - 0, 0, send_buf, 20, USB_CTRL_SET_TIMEOUT); + 0, 0, send_buf, FW_HDR_SIZE, + USB_CTRL_SET_TIMEOUT); if (err < 0) { BT_ERR("Can't change to loading configuration err"); goto error; } - sent += 20; - count -= 20; + sent += FW_HDR_SIZE; + count -= FW_HDR_SIZE; pipe = usb_sndbulkpipe(udev, 0x02); @@ -250,8 +257,7 @@ static int ath3k_load_firmware(struct usb_device *udev, &len, 3000); if (err || (len != size)) { - BT_ERR("Error in firmware loading err = %d," - "len = %d, size = %d", err, len, size); + ath3k_log_failed_loading(err, len, size); goto error; } @@ -350,8 +356,7 @@ static int ath3k_load_fwfile(struct usb_device *udev, err = usb_bulk_msg(udev, pipe, send_buf, size, &len, 3000); if (err || (len != size)) { - BT_ERR("Error in firmware loading err = %d," - "len = %d, size = %d", err, len, size); + ath3k_log_failed_loading(err, len, size); kfree(send_buf); return err; } @@ -398,7 +403,7 @@ static int ath3k_set_normal_mode(struct usb_device *udev) static int ath3k_load_patch(struct usb_device *udev) { unsigned char fw_state; - char filename[ATH3K_NAME_LEN] = {0}; + char filename[ATH3K_NAME_LEN]; const struct firmware *firmware; struct ath3k_version fw_version; __u32 pt_rom_version, pt_build_version; @@ -451,7 +456,7 @@ static int ath3k_load_patch(struct usb_device *udev) static int ath3k_load_syscfg(struct usb_device *udev) { unsigned char fw_state; - char filename[ATH3K_NAME_LEN] = {0}; + char filename[ATH3K_NAME_LEN]; const struct firmware *firmware; struct ath3k_version fw_version; int clk_value, ret; @@ -522,7 +527,6 @@ static int ath3k_probe(struct usb_interface *intf, /* load patch and sysconfig files for AR3012 */ if (id->driver_info & BTUSB_ATH3012) { - /* New firmware with patch and sysconfig files already loaded */ if (le16_to_cpu(udev->descriptor.bcdDevice) > 0x0001) return -ENODEV; @@ -565,7 +569,7 @@ static int ath3k_probe(struct usb_interface *intf, static void ath3k_disconnect(struct usb_interface *intf) { - BT_DBG("ath3k_disconnect intf %p", intf); + BT_DBG("%s intf %p", __func__, intf); } static struct usb_driver ath3k_driver = { diff --git a/drivers/bluetooth/btmrvl_main.c b/drivers/bluetooth/btmrvl_main.c index b280d466f05b..f6c694a1b9b0 100644 --- a/drivers/bluetooth/btmrvl_main.c +++ b/drivers/bluetooth/btmrvl_main.c @@ -183,7 +183,7 @@ static int btmrvl_send_sync_cmd(struct btmrvl_private *priv, u16 opcode, return -EFAULT; } - skb = bt_skb_alloc(HCI_COMMAND_HDR_SIZE + len, GFP_ATOMIC); + skb = bt_skb_alloc(HCI_COMMAND_HDR_SIZE + len, GFP_KERNEL); if (!skb) { BT_ERR("No free skb"); return -ENOMEM; diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c index 6e2ad748abba..437f080deaab 100644 --- a/drivers/bluetooth/btrtl.c +++ b/drivers/bluetooth/btrtl.c @@ -35,6 +35,60 @@ #define RTL_ROM_LMP_8761A 0x8761 #define RTL_ROM_LMP_8822B 0x8822 +#define IC_MATCH_FL_LMPSUBV (1 << 0) +#define IC_MATCH_FL_HCIREV (1 << 1) +#define IC_INFO(lmps, hcir) \ + .match_flags = IC_MATCH_FL_LMPSUBV | IC_MATCH_FL_HCIREV, \ + .lmp_subver = (lmps), \ + .hci_rev = (hcir) + +struct id_table { + __u16 match_flags; + __u16 lmp_subver; + __u16 hci_rev; + bool config_needed; + char *fw_name; + char *cfg_name; +}; + +static const struct id_table ic_id_table[] = { + /* 8723B */ + { IC_INFO(RTL_ROM_LMP_8723B, 0xb), + .config_needed = false, + .fw_name = "rtl_bt/rtl8723b_fw.bin", + .cfg_name = "rtl_bt/rtl8723b_config.bin" }, + + /* 8723D */ + { IC_INFO(RTL_ROM_LMP_8723B, 0xd), + .config_needed = true, + .fw_name = "rtl_bt/rtl8723d_fw.bin", + .cfg_name = "rtl_bt/rtl8723d_config.bin" }, + + /* 8821A */ + { IC_INFO(RTL_ROM_LMP_8821A, 0xa), + .config_needed = false, + .fw_name = "rtl_bt/rtl8821a_fw.bin", + .cfg_name = "rtl_bt/rtl8821a_config.bin" }, + + /* 8821C */ + { IC_INFO(RTL_ROM_LMP_8821A, 0xc), + .config_needed = false, + .fw_name = "rtl_bt/rtl8821c_fw.bin", + .cfg_name = "rtl_bt/rtl8821c_config.bin" }, + + /* 8761A */ + { IC_MATCH_FL_LMPSUBV, RTL_ROM_LMP_8761A, 0x0, + .config_needed = false, + .fw_name = "rtl_bt/rtl8761a_fw.bin", + .cfg_name = "rtl_bt/rtl8761a_config.bin" }, + + /* 8822B */ + { IC_INFO(RTL_ROM_LMP_8822B, 0xb), + .config_needed = true, + .fw_name = "rtl_bt/rtl8822b_fw.bin", + .cfg_name = "rtl_bt/rtl8822b_config.bin" }, + }; + static int rtl_read_rom_version(struct hci_dev *hdev, u8 *version) { struct rtl_rom_version_evt *rom_version; @@ -64,9 +118,9 @@ static int rtl_read_rom_version(struct hci_dev *hdev, u8 *version) return 0; } -static int rtl8723b_parse_firmware(struct hci_dev *hdev, u16 lmp_subver, - const struct firmware *fw, - unsigned char **_buf) +static int rtlbt_parse_firmware(struct hci_dev *hdev, u16 lmp_subver, + const struct firmware *fw, + unsigned char **_buf) { const u8 extension_sig[] = { 0x51, 0x04, 0xfd, 0x77 }; struct rtl_epatch_header *epatch_info; @@ -88,6 +142,8 @@ static int rtl8723b_parse_firmware(struct hci_dev *hdev, u16 lmp_subver, { RTL_ROM_LMP_8821A, 2 }, { RTL_ROM_LMP_8761A, 3 }, { RTL_ROM_LMP_8822B, 8 }, + { RTL_ROM_LMP_8723B, 9 }, /* 8723D */ + { RTL_ROM_LMP_8821A, 10 }, /* 8821C */ }; ret = rtl_read_rom_version(hdev, &rom_version); @@ -320,8 +376,8 @@ out: return ret; } -static int btrtl_setup_rtl8723b(struct hci_dev *hdev, u16 lmp_subver, - const char *fw_name) +static int btrtl_setup_rtl8723b(struct hci_dev *hdev, u16 hci_rev, + u16 lmp_subver) { unsigned char *fw_data = NULL; const struct firmware *fw; @@ -330,39 +386,40 @@ static int btrtl_setup_rtl8723b(struct hci_dev *hdev, u16 lmp_subver, u8 *cfg_buff = NULL; u8 *tbuff; char *cfg_name = NULL; - bool config_needed = false; + char *fw_name = NULL; + int i; + + for (i = 0; i < ARRAY_SIZE(ic_id_table); i++) { + if ((ic_id_table[i].match_flags & IC_MATCH_FL_LMPSUBV) && + (ic_id_table[i].lmp_subver != lmp_subver)) + continue; + if ((ic_id_table[i].match_flags & IC_MATCH_FL_HCIREV) && + (ic_id_table[i].hci_rev != hci_rev)) + continue; - switch (lmp_subver) { - case RTL_ROM_LMP_8723B: - cfg_name = "rtl_bt/rtl8723b_config.bin"; - break; - case RTL_ROM_LMP_8821A: - cfg_name = "rtl_bt/rtl8821a_config.bin"; - break; - case RTL_ROM_LMP_8761A: - cfg_name = "rtl_bt/rtl8761a_config.bin"; - break; - case RTL_ROM_LMP_8822B: - cfg_name = "rtl_bt/rtl8822b_config.bin"; - config_needed = true; - break; - default: - BT_ERR("%s: rtl: no config according to lmp_subver %04x", - hdev->name, lmp_subver); break; } + if (i >= ARRAY_SIZE(ic_id_table)) { + BT_ERR("%s: unknown IC info, lmp subver %04x, hci rev %04x", + hdev->name, lmp_subver, hci_rev); + return -EINVAL; + } + + cfg_name = ic_id_table[i].cfg_name; + if (cfg_name) { cfg_sz = rtl_load_config(hdev, cfg_name, &cfg_buff); if (cfg_sz < 0) { cfg_sz = 0; - if (config_needed) + if (ic_id_table[i].config_needed) BT_ERR("Necessary config file %s not found\n", cfg_name); } } else cfg_sz = 0; + fw_name = ic_id_table[i].fw_name; bt_dev_info(hdev, "rtl: loading %s", fw_name); ret = request_firmware(&fw, fw_name, &hdev->dev); if (ret < 0) { @@ -370,7 +427,7 @@ static int btrtl_setup_rtl8723b(struct hci_dev *hdev, u16 lmp_subver, goto err_req_fw; } - ret = rtl8723b_parse_firmware(hdev, lmp_subver, fw, &fw_data); + ret = rtlbt_parse_firmware(hdev, lmp_subver, fw, &fw_data); if (ret < 0) goto out; @@ -429,7 +486,7 @@ int btrtl_setup_realtek(struct hci_dev *hdev) { struct sk_buff *skb; struct hci_rp_read_local_version *resp; - u16 lmp_subver; + u16 hci_rev, lmp_subver; skb = btrtl_read_local_version(hdev); if (IS_ERR(skb)) @@ -441,6 +498,7 @@ int btrtl_setup_realtek(struct hci_dev *hdev) resp->hci_ver, resp->hci_rev, resp->lmp_ver, resp->lmp_subver); + hci_rev = le16_to_cpu(resp->hci_rev); lmp_subver = le16_to_cpu(resp->lmp_subver); kfree_skb(skb); @@ -455,17 +513,10 @@ int btrtl_setup_realtek(struct hci_dev *hdev) case RTL_ROM_LMP_3499: return btrtl_setup_rtl8723a(hdev); case RTL_ROM_LMP_8723B: - return btrtl_setup_rtl8723b(hdev, lmp_subver, - "rtl_bt/rtl8723b_fw.bin"); case RTL_ROM_LMP_8821A: - return btrtl_setup_rtl8723b(hdev, lmp_subver, - "rtl_bt/rtl8821a_fw.bin"); case RTL_ROM_LMP_8761A: - return btrtl_setup_rtl8723b(hdev, lmp_subver, - "rtl_bt/rtl8761a_fw.bin"); case RTL_ROM_LMP_8822B: - return btrtl_setup_rtl8723b(hdev, lmp_subver, - "rtl_bt/rtl8822b_fw.bin"); + return btrtl_setup_rtl8723b(hdev, hci_rev, lmp_subver); default: bt_dev_info(hdev, "rtl: assuming no firmware upload needed"); return 0; diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 2a55380ad730..c8e9ae6b99e1 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -339,6 +339,7 @@ static const struct usb_device_id blacklist_table[] = { /* Intel Bluetooth devices */ { USB_DEVICE(0x8087, 0x0025), .driver_info = BTUSB_INTEL_NEW }, + { USB_DEVICE(0x8087, 0x0026), .driver_info = BTUSB_INTEL_NEW }, { USB_DEVICE(0x8087, 0x07da), .driver_info = BTUSB_CSR }, { USB_DEVICE(0x8087, 0x07dc), .driver_info = BTUSB_INTEL }, { USB_DEVICE(0x8087, 0x0a2a), .driver_info = BTUSB_INTEL }, @@ -373,6 +374,9 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x13d3, 0x3461), .driver_info = BTUSB_REALTEK }, { USB_DEVICE(0x13d3, 0x3462), .driver_info = BTUSB_REALTEK }, + /* Additional Realtek 8822BE Bluetooth devices */ + { USB_DEVICE(0x0b05, 0x185c), .driver_info = BTUSB_REALTEK }, + /* Silicon Wave based devices */ { USB_DEVICE(0x0c10, 0x0000), .driver_info = BTUSB_SWAVE }, @@ -2057,6 +2061,8 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) case 0x0c: /* WsP */ case 0x11: /* JfP */ case 0x12: /* ThP */ + case 0x13: /* HrP */ + case 0x14: /* QnJ, IcP */ break; default: BT_ERR("%s: Unsupported Intel hardware variant (%u)", @@ -2149,6 +2155,8 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) break; case 0x11: /* JfP */ case 0x12: /* ThP */ + case 0x13: /* HrP */ + case 0x14: /* QnJ, IcP */ snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u-%u.sfi", le16_to_cpu(ver.hw_variant), le16_to_cpu(ver.hw_revision), @@ -2180,6 +2188,8 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) break; case 0x11: /* JfP */ case 0x12: /* ThP */ + case 0x13: /* HrP */ + case 0x14: /* QnJ, IcP */ snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u-%u.ddc", le16_to_cpu(ver.hw_variant), le16_to_cpu(ver.hw_revision), diff --git a/drivers/bluetooth/hci_ath.c b/drivers/bluetooth/hci_ath.c index 14ae7ee88acb..d568fbd94d6c 100644 --- a/drivers/bluetooth/hci_ath.c +++ b/drivers/bluetooth/hci_ath.c @@ -71,12 +71,12 @@ static int ath_wakeup_ar3k(struct tty_struct *tty) /* Clear RTS first */ tty->driver->ops->tiocmget(tty); tty->driver->ops->tiocmset(tty, 0x00, TIOCM_RTS); - mdelay(20); + msleep(20); /* Set RTS, wake up board */ tty->driver->ops->tiocmget(tty); tty->driver->ops->tiocmset(tty, TIOCM_RTS, 0x00); - mdelay(20); + msleep(20); status = tty->driver->ops->tiocmget(tty); return status; diff --git a/drivers/bluetooth/hci_ll.c b/drivers/bluetooth/hci_ll.c index 1b4417a623a4..2f30dcad96bd 100644 --- a/drivers/bluetooth/hci_ll.c +++ b/drivers/bluetooth/hci_ll.c @@ -650,7 +650,7 @@ static int download_firmware(struct ll_device *lldev) break; case ACTION_DELAY: /* sleep */ bt_dev_info(lldev->hu.hdev, "sleep command in scr"); - mdelay(((struct bts_action_delay *)action_ptr)->msec); + msleep(((struct bts_action_delay *)action_ptr)->msec); break; } len -= (sizeof(struct bts_action) + diff --git a/drivers/char/hw_random/via-rng.c b/drivers/char/hw_random/via-rng.c index d1f5bb534e0e..6e9df558325b 100644 --- a/drivers/char/hw_random/via-rng.c +++ b/drivers/char/hw_random/via-rng.c @@ -162,7 +162,7 @@ static int via_rng_init(struct hwrng *rng) /* Enable secondary noise source on CPUs where it is present. */ /* Nehemiah stepping 8 and higher */ - if ((c->x86_model == 9) && (c->x86_mask > 7)) + if ((c->x86_model == 9) && (c->x86_stepping > 7)) lo |= VIA_NOISESRC2; /* Esther */ diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index 3a2ca0f79daf..d0c34df0529c 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -629,7 +629,7 @@ static int acpi_cpufreq_blacklist(struct cpuinfo_x86 *c) if (c->x86_vendor == X86_VENDOR_INTEL) { if ((c->x86 == 15) && (c->x86_model == 6) && - (c->x86_mask == 8)) { + (c->x86_stepping == 8)) { pr_info("Intel(R) Xeon(R) 7100 Errata AL30, processors may lock up on frequency changes: disabling acpi-cpufreq\n"); return -ENODEV; } diff --git a/drivers/cpufreq/longhaul.c b/drivers/cpufreq/longhaul.c index 942632a27b50..f730b6528c18 100644 --- a/drivers/cpufreq/longhaul.c +++ b/drivers/cpufreq/longhaul.c @@ -775,7 +775,7 @@ static int longhaul_cpu_init(struct cpufreq_policy *policy) break; case 7: - switch (c->x86_mask) { + switch (c->x86_stepping) { case 0: longhaul_version = TYPE_LONGHAUL_V1; cpu_model = CPU_SAMUEL2; @@ -787,7 +787,7 @@ static int longhaul_cpu_init(struct cpufreq_policy *policy) break; case 1 ... 15: longhaul_version = TYPE_LONGHAUL_V2; - if (c->x86_mask < 8) { + if (c->x86_stepping < 8) { cpu_model = CPU_SAMUEL2; cpuname = "C3 'Samuel 2' [C5B]"; } else { @@ -814,7 +814,7 @@ static int longhaul_cpu_init(struct cpufreq_policy *policy) numscales = 32; memcpy(mults, nehemiah_mults, sizeof(nehemiah_mults)); memcpy(eblcr, nehemiah_eblcr, sizeof(nehemiah_eblcr)); - switch (c->x86_mask) { + switch (c->x86_stepping) { case 0 ... 1: cpu_model = CPU_NEHEMIAH; cpuname = "C3 'Nehemiah A' [C5XLOE]"; diff --git a/drivers/cpufreq/p4-clockmod.c b/drivers/cpufreq/p4-clockmod.c index fd77812313f3..a25741b1281b 100644 --- a/drivers/cpufreq/p4-clockmod.c +++ b/drivers/cpufreq/p4-clockmod.c @@ -168,7 +168,7 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy) #endif /* Errata workaround */ - cpuid = (c->x86 << 8) | (c->x86_model << 4) | c->x86_mask; + cpuid = (c->x86 << 8) | (c->x86_model << 4) | c->x86_stepping; switch (cpuid) { case 0x0f07: case 0x0f0a: diff --git a/drivers/cpufreq/powernow-k7.c b/drivers/cpufreq/powernow-k7.c index 80ac313e6c59..302e9ce793a0 100644 --- a/drivers/cpufreq/powernow-k7.c +++ b/drivers/cpufreq/powernow-k7.c @@ -131,7 +131,7 @@ static int check_powernow(void) return 0; } - if ((c->x86_model == 6) && (c->x86_mask == 0)) { + if ((c->x86_model == 6) && (c->x86_stepping == 0)) { pr_info("K7 660[A0] core detected, enabling errata workarounds\n"); have_a0 = 1; } diff --git a/drivers/cpufreq/speedstep-centrino.c b/drivers/cpufreq/speedstep-centrino.c index 41bc5397f4bb..4fa5adf16c70 100644 --- a/drivers/cpufreq/speedstep-centrino.c +++ b/drivers/cpufreq/speedstep-centrino.c @@ -37,7 +37,7 @@ struct cpu_id { __u8 x86; /* CPU family */ __u8 x86_model; /* model */ - __u8 x86_mask; /* stepping */ + __u8 x86_stepping; /* stepping */ }; enum { @@ -277,7 +277,7 @@ static int centrino_verify_cpu_id(const struct cpuinfo_x86 *c, { if ((c->x86 == x->x86) && (c->x86_model == x->x86_model) && - (c->x86_mask == x->x86_mask)) + (c->x86_stepping == x->x86_stepping)) return 1; return 0; } diff --git a/drivers/cpufreq/speedstep-lib.c b/drivers/cpufreq/speedstep-lib.c index 8085ec9000d1..e3a9962ee410 100644 --- a/drivers/cpufreq/speedstep-lib.c +++ b/drivers/cpufreq/speedstep-lib.c @@ -272,9 +272,9 @@ unsigned int speedstep_detect_processor(void) ebx = cpuid_ebx(0x00000001); ebx &= 0x000000FF; - pr_debug("ebx value is %x, x86_mask is %x\n", ebx, c->x86_mask); + pr_debug("ebx value is %x, x86_stepping is %x\n", ebx, c->x86_stepping); - switch (c->x86_mask) { + switch (c->x86_stepping) { case 4: /* * B-stepping [M-P4-M] @@ -361,7 +361,7 @@ unsigned int speedstep_detect_processor(void) msr_lo, msr_hi); if ((msr_hi & (1<<18)) && (relaxed_check ? 1 : (msr_hi & (3<<24)))) { - if (c->x86_mask == 0x01) { + if (c->x86_stepping == 0x01) { pr_debug("early PIII version\n"); return SPEEDSTEP_CPU_PIII_C_EARLY; } else diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c index 75d280cb2dc0..e843cf410373 100644 --- a/drivers/crypto/caam/ctrl.c +++ b/drivers/crypto/caam/ctrl.c @@ -228,12 +228,16 @@ static int instantiate_rng(struct device *ctrldev, int state_handle_mask, * without any error (HW optimizations for later * CAAM eras), then try again. */ + if (ret) + break; + rdsta_val = rd_reg32(&ctrl->r4tst[0].rdsta) & RDSTA_IFMASK; if ((status && status != JRSTA_SSRC_JUMP_HALT_CC) || - !(rdsta_val & (1 << sh_idx))) + !(rdsta_val & (1 << sh_idx))) { ret = -EAGAIN; - if (ret) break; + } + dev_info(ctrldev, "Instantiated RNG4 SH%d\n", sh_idx); /* Clear the contents before recreating the descriptor */ memset(desc, 0x00, CAAM_CMD_SZ * 7); diff --git a/drivers/crypto/padlock-aes.c b/drivers/crypto/padlock-aes.c index 4b6642a25df5..1c6cbda56afe 100644 --- a/drivers/crypto/padlock-aes.c +++ b/drivers/crypto/padlock-aes.c @@ -512,7 +512,7 @@ static int __init padlock_init(void) printk(KERN_NOTICE PFX "Using VIA PadLock ACE for AES algorithm.\n"); - if (c->x86 == 6 && c->x86_model == 15 && c->x86_mask == 2) { + if (c->x86 == 6 && c->x86_model == 15 && c->x86_stepping == 2) { ecb_fetch_blocks = MAX_ECB_FETCH_BLOCKS; cbc_fetch_blocks = MAX_CBC_FETCH_BLOCKS; printk(KERN_NOTICE PFX "VIA Nano stepping 2 detected: enabling workaround.\n"); diff --git a/drivers/crypto/s5p-sss.c b/drivers/crypto/s5p-sss.c index 188f44b7eb27..5d64c08b7f47 100644 --- a/drivers/crypto/s5p-sss.c +++ b/drivers/crypto/s5p-sss.c @@ -1922,15 +1922,21 @@ static void s5p_aes_crypt_start(struct s5p_aes_dev *dev, unsigned long mode) uint32_t aes_control; unsigned long flags; int err; + u8 *iv; aes_control = SSS_AES_KEY_CHANGE_MODE; if (mode & FLAGS_AES_DECRYPT) aes_control |= SSS_AES_MODE_DECRYPT; - if ((mode & FLAGS_AES_MODE_MASK) == FLAGS_AES_CBC) + if ((mode & FLAGS_AES_MODE_MASK) == FLAGS_AES_CBC) { aes_control |= SSS_AES_CHAIN_MODE_CBC; - else if ((mode & FLAGS_AES_MODE_MASK) == FLAGS_AES_CTR) + iv = req->info; + } else if ((mode & FLAGS_AES_MODE_MASK) == FLAGS_AES_CTR) { aes_control |= SSS_AES_CHAIN_MODE_CTR; + iv = req->info; + } else { + iv = NULL; /* AES_ECB */ + } if (dev->ctx->keylen == AES_KEYSIZE_192) aes_control |= SSS_AES_KEY_SIZE_192; @@ -1961,7 +1967,7 @@ static void s5p_aes_crypt_start(struct s5p_aes_dev *dev, unsigned long mode) goto outdata_error; SSS_AES_WRITE(dev, AES_CONTROL, aes_control); - s5p_set_aes(dev, dev->ctx->aes_key, req->info, dev->ctx->keylen); + s5p_set_aes(dev, dev->ctx->aes_key, iv, dev->ctx->keylen); s5p_set_dma_indata(dev, dev->sg_src); s5p_set_dma_outdata(dev, dev->sg_dst); diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-prng.c b/drivers/crypto/sunxi-ss/sun4i-ss-prng.c index 0d01d1624252..63d636424161 100644 --- a/drivers/crypto/sunxi-ss/sun4i-ss-prng.c +++ b/drivers/crypto/sunxi-ss/sun4i-ss-prng.c @@ -28,7 +28,7 @@ int sun4i_ss_prng_generate(struct crypto_rng *tfm, const u8 *src, algt = container_of(alg, struct sun4i_ss_alg_template, alg.rng); ss = algt->ss; - spin_lock(&ss->slock); + spin_lock_bh(&ss->slock); writel(mode, ss->base + SS_CTL); @@ -51,6 +51,6 @@ int sun4i_ss_prng_generate(struct crypto_rng *tfm, const u8 *src, } writel(0, ss->base + SS_CTL); - spin_unlock(&ss->slock); - return dlen; + spin_unlock_bh(&ss->slock); + return 0; } diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c index 9c80e0cb1664..6882fa2f8bad 100644 --- a/drivers/crypto/talitos.c +++ b/drivers/crypto/talitos.c @@ -1138,6 +1138,10 @@ static int talitos_sg_map(struct device *dev, struct scatterlist *src, struct talitos_private *priv = dev_get_drvdata(dev); bool is_sec1 = has_ftr_sec1(priv); + if (!src) { + to_talitos_ptr(ptr, 0, 0, is_sec1); + return 1; + } if (sg_count == 1) { to_talitos_ptr(ptr, sg_dma_address(src) + offset, len, is_sec1); return sg_count; diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index 8b16ec595fa7..329cb96f886f 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -3147,7 +3147,7 @@ static struct amd64_family_type *per_family_init(struct amd64_pvt *pvt) struct amd64_family_type *fam_type = NULL; pvt->ext_model = boot_cpu_data.x86_model >> 4; - pvt->stepping = boot_cpu_data.x86_mask; + pvt->stepping = boot_cpu_data.x86_stepping; pvt->model = boot_cpu_data.x86_model; pvt->fam = boot_cpu_data.x86; diff --git a/drivers/extcon/extcon-axp288.c b/drivers/extcon/extcon-axp288.c index 0a44d43802fe..3ec4c715e240 100644 --- a/drivers/extcon/extcon-axp288.c +++ b/drivers/extcon/extcon-axp288.c @@ -1,7 +1,6 @@ /* * extcon-axp288.c - X-Power AXP288 PMIC extcon cable detection driver * - * Copyright (C) 2016-2017 Hans de Goede <hdegoede@redhat.com> * Copyright (C) 2015 Intel Corporation * Author: Ramakrishna Pallala <ramakrishna.pallala@intel.com> * @@ -98,15 +97,13 @@ struct axp288_extcon_info { struct device *dev; struct regmap *regmap; struct regmap_irq_chip_data *regmap_irqc; - struct delayed_work det_work; int irq[EXTCON_IRQ_END]; struct extcon_dev *edev; unsigned int previous_cable; - bool first_detect_done; }; /* Power up/down reason string array */ -static char *axp288_pwr_up_down_info[] = { +static const char * const axp288_pwr_up_down_info[] = { "Last wake caused by user pressing the power button", "Last wake caused by a charger insertion", "Last wake caused by a battery insertion", @@ -124,7 +121,7 @@ static char *axp288_pwr_up_down_info[] = { */ static void axp288_extcon_log_rsi(struct axp288_extcon_info *info) { - char **rsi; + const char * const *rsi; unsigned int val, i, clear_mask = 0; int ret; @@ -140,25 +137,6 @@ static void axp288_extcon_log_rsi(struct axp288_extcon_info *info) regmap_write(info->regmap, AXP288_PS_BOOT_REASON_REG, clear_mask); } -static void axp288_chrg_detect_complete(struct axp288_extcon_info *info) -{ - /* - * We depend on other drivers to do things like mux the data lines, - * enable/disable vbus based on the id-pin, etc. Sometimes the BIOS has - * not set these things up correctly resulting in the initial charger - * cable type detection giving a wrong result and we end up not charging - * or charging at only 0.5A. - * - * So we schedule a second cable type detection after 2 seconds to - * give the other drivers time to load and do their thing. - */ - if (!info->first_detect_done) { - queue_delayed_work(system_wq, &info->det_work, - msecs_to_jiffies(2000)); - info->first_detect_done = true; - } -} - static int axp288_handle_chrg_det_event(struct axp288_extcon_info *info) { int ret, stat, cfg, pwr_stat; @@ -223,8 +201,6 @@ no_vbus: info->previous_cable = cable; } - axp288_chrg_detect_complete(info); - return 0; dev_det_ret: @@ -246,11 +222,8 @@ static irqreturn_t axp288_extcon_isr(int irq, void *data) return IRQ_HANDLED; } -static void axp288_extcon_det_work(struct work_struct *work) +static void axp288_extcon_enable(struct axp288_extcon_info *info) { - struct axp288_extcon_info *info = - container_of(work, struct axp288_extcon_info, det_work.work); - regmap_update_bits(info->regmap, AXP288_BC_GLOBAL_REG, BC_GLOBAL_RUN, 0); /* Enable the charger detection logic */ @@ -272,7 +245,6 @@ static int axp288_extcon_probe(struct platform_device *pdev) info->regmap = axp20x->regmap; info->regmap_irqc = axp20x->regmap_irqc; info->previous_cable = EXTCON_NONE; - INIT_DELAYED_WORK(&info->det_work, axp288_extcon_det_work); platform_set_drvdata(pdev, info); @@ -318,7 +290,7 @@ static int axp288_extcon_probe(struct platform_device *pdev) } /* Start charger cable type detection */ - queue_delayed_work(system_wq, &info->det_work, 0); + axp288_extcon_enable(info); return 0; } diff --git a/drivers/extcon/extcon-intel-int3496.c b/drivers/extcon/extcon-intel-int3496.c index c8691b5a9cb0..191e99f06a9a 100644 --- a/drivers/extcon/extcon-intel-int3496.c +++ b/drivers/extcon/extcon-intel-int3496.c @@ -153,8 +153,9 @@ static int int3496_probe(struct platform_device *pdev) return ret; } - /* queue initial processing of id-pin */ + /* process id-pin so that we start with the right status */ queue_delayed_work(system_wq, &data->work, 0); + flush_delayed_work(&data->work); platform_set_drvdata(pdev, data); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c index e2c3c5ec42d1..c53095b3b0fb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c @@ -568,6 +568,7 @@ static const struct amdgpu_px_quirk amdgpu_px_quirk_list[] = { /* HG _PR3 doesn't seem to work on this A+A weston board */ { 0x1002, 0x6900, 0x1002, 0x0124, AMDGPU_PX_QUIRK_FORCE_ATPX }, { 0x1002, 0x6900, 0x1028, 0x0812, AMDGPU_PX_QUIRK_FORCE_ATPX }, + { 0x1002, 0x6900, 0x1028, 0x0813, AMDGPU_PX_QUIRK_FORCE_ATPX }, { 0, 0, 0, 0, 0 }, }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c index 8ca3783f2deb..74d2efaec52f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c @@ -736,9 +736,11 @@ amdgpu_connector_lvds_detect(struct drm_connector *connector, bool force) enum drm_connector_status ret = connector_status_disconnected; int r; - r = pm_runtime_get_sync(connector->dev->dev); - if (r < 0) - return connector_status_disconnected; + if (!drm_kms_helper_is_poll_worker()) { + r = pm_runtime_get_sync(connector->dev->dev); + if (r < 0) + return connector_status_disconnected; + } if (encoder) { struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder); @@ -757,8 +759,12 @@ amdgpu_connector_lvds_detect(struct drm_connector *connector, bool force) /* check acpi lid status ??? */ amdgpu_connector_update_scratch_regs(connector, ret); - pm_runtime_mark_last_busy(connector->dev->dev); - pm_runtime_put_autosuspend(connector->dev->dev); + + if (!drm_kms_helper_is_poll_worker()) { + pm_runtime_mark_last_busy(connector->dev->dev); + pm_runtime_put_autosuspend(connector->dev->dev); + } + return ret; } @@ -868,9 +874,11 @@ amdgpu_connector_vga_detect(struct drm_connector *connector, bool force) enum drm_connector_status ret = connector_status_disconnected; int r; - r = pm_runtime_get_sync(connector->dev->dev); - if (r < 0) - return connector_status_disconnected; + if (!drm_kms_helper_is_poll_worker()) { + r = pm_runtime_get_sync(connector->dev->dev); + if (r < 0) + return connector_status_disconnected; + } encoder = amdgpu_connector_best_single_encoder(connector); if (!encoder) @@ -924,8 +932,10 @@ amdgpu_connector_vga_detect(struct drm_connector *connector, bool force) amdgpu_connector_update_scratch_regs(connector, ret); out: - pm_runtime_mark_last_busy(connector->dev->dev); - pm_runtime_put_autosuspend(connector->dev->dev); + if (!drm_kms_helper_is_poll_worker()) { + pm_runtime_mark_last_busy(connector->dev->dev); + pm_runtime_put_autosuspend(connector->dev->dev); + } return ret; } @@ -988,9 +998,11 @@ amdgpu_connector_dvi_detect(struct drm_connector *connector, bool force) enum drm_connector_status ret = connector_status_disconnected; bool dret = false, broken_edid = false; - r = pm_runtime_get_sync(connector->dev->dev); - if (r < 0) - return connector_status_disconnected; + if (!drm_kms_helper_is_poll_worker()) { + r = pm_runtime_get_sync(connector->dev->dev); + if (r < 0) + return connector_status_disconnected; + } if (!force && amdgpu_connector_check_hpd_status_unchanged(connector)) { ret = connector->status; @@ -1115,8 +1127,10 @@ out: amdgpu_connector_update_scratch_regs(connector, ret); exit: - pm_runtime_mark_last_busy(connector->dev->dev); - pm_runtime_put_autosuspend(connector->dev->dev); + if (!drm_kms_helper_is_poll_worker()) { + pm_runtime_mark_last_busy(connector->dev->dev); + pm_runtime_put_autosuspend(connector->dev->dev); + } return ret; } @@ -1359,9 +1373,11 @@ amdgpu_connector_dp_detect(struct drm_connector *connector, bool force) struct drm_encoder *encoder = amdgpu_connector_best_single_encoder(connector); int r; - r = pm_runtime_get_sync(connector->dev->dev); - if (r < 0) - return connector_status_disconnected; + if (!drm_kms_helper_is_poll_worker()) { + r = pm_runtime_get_sync(connector->dev->dev); + if (r < 0) + return connector_status_disconnected; + } if (!force && amdgpu_connector_check_hpd_status_unchanged(connector)) { ret = connector->status; @@ -1429,8 +1445,10 @@ amdgpu_connector_dp_detect(struct drm_connector *connector, bool force) amdgpu_connector_update_scratch_regs(connector, ret); out: - pm_runtime_mark_last_busy(connector->dev->dev); - pm_runtime_put_autosuspend(connector->dev->dev); + if (!drm_kms_helper_is_poll_worker()) { + pm_runtime_mark_last_busy(connector->dev->dev); + pm_runtime_put_autosuspend(connector->dev->dev); + } return ret; } diff --git a/drivers/gpu/drm/cirrus/cirrus_mode.c b/drivers/gpu/drm/cirrus/cirrus_mode.c index cd23b1b28259..c91b9b054e3f 100644 --- a/drivers/gpu/drm/cirrus/cirrus_mode.c +++ b/drivers/gpu/drm/cirrus/cirrus_mode.c @@ -294,22 +294,7 @@ static void cirrus_crtc_prepare(struct drm_crtc *crtc) { } -/* - * This is called after a mode is programmed. It should reverse anything done - * by the prepare function - */ -static void cirrus_crtc_commit(struct drm_crtc *crtc) -{ -} - -/* - * The core can pass us a set of gamma values to program. We actually only - * use this for 8-bit mode so can't perform smooth fades on deeper modes, - * but it's a requirement that we provide the function - */ -static int cirrus_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green, - u16 *blue, uint32_t size, - struct drm_modeset_acquire_ctx *ctx) +static void cirrus_crtc_load_lut(struct drm_crtc *crtc) { struct drm_device *dev = crtc->dev; struct cirrus_device *cdev = dev->dev_private; @@ -317,7 +302,7 @@ static int cirrus_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green, int i; if (!crtc->enabled) - return 0; + return; r = crtc->gamma_store; g = r + crtc->gamma_size; @@ -330,6 +315,27 @@ static int cirrus_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green, WREG8(PALETTE_DATA, *g++ >> 8); WREG8(PALETTE_DATA, *b++ >> 8); } +} + +/* + * This is called after a mode is programmed. It should reverse anything done + * by the prepare function + */ +static void cirrus_crtc_commit(struct drm_crtc *crtc) +{ + cirrus_crtc_load_lut(crtc); +} + +/* + * The core can pass us a set of gamma values to program. We actually only + * use this for 8-bit mode so can't perform smooth fades on deeper modes, + * but it's a requirement that we provide the function + */ +static int cirrus_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green, + u16 *blue, uint32_t size, + struct drm_modeset_acquire_ctx *ctx) +{ + cirrus_crtc_load_lut(crtc); return 0; } diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index ab4032167094..ae3cbfe9e01c 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -1878,6 +1878,8 @@ int drm_atomic_helper_setup_commit(struct drm_atomic_state *state, new_crtc_state->event->base.completion = &commit->flip_done; new_crtc_state->event->base.completion_release = release_crtc_commit; drm_crtc_commit_get(commit); + + commit->abort_completion = true; } for_each_oldnew_connector_in_state(state, conn, old_conn_state, new_conn_state, i) { @@ -3421,8 +3423,21 @@ EXPORT_SYMBOL(drm_atomic_helper_crtc_duplicate_state); void __drm_atomic_helper_crtc_destroy_state(struct drm_crtc_state *state) { if (state->commit) { + /* + * In the event that a non-blocking commit returns + * -ERESTARTSYS before the commit_tail work is queued, we will + * have an extra reference to the commit object. Release it, if + * the event has not been consumed by the worker. + * + * state->event may be freed, so we can't directly look at + * state->event->base.completion. + */ + if (state->event && state->commit->abort_completion) + drm_crtc_commit_put(state->commit); + kfree(state->commit->event); state->commit->event = NULL; + drm_crtc_commit_put(state->commit); } diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index ddd537914575..4f751a9d71a3 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -113,6 +113,9 @@ static const struct edid_quirk { /* AEO model 0 reports 8 bpc, but is a 6 bpc panel */ { "AEO", 0, EDID_QUIRK_FORCE_6BPC }, + /* CPT panel of Asus UX303LA reports 8 bpc, but is a 6 bpc panel */ + { "CPT", 0x17df, EDID_QUIRK_FORCE_6BPC }, + /* Belinea 10 15 55 */ { "MAX", 1516, EDID_QUIRK_PREFER_LARGE_60 }, { "MAX", 0x77e, EDID_QUIRK_PREFER_LARGE_60 }, @@ -162,6 +165,24 @@ static const struct edid_quirk { /* HTC Vive VR Headset */ { "HVR", 0xaa01, EDID_QUIRK_NON_DESKTOP }, + + /* Oculus Rift DK1, DK2, and CV1 VR Headsets */ + { "OVR", 0x0001, EDID_QUIRK_NON_DESKTOP }, + { "OVR", 0x0003, EDID_QUIRK_NON_DESKTOP }, + { "OVR", 0x0004, EDID_QUIRK_NON_DESKTOP }, + + /* Windows Mixed Reality Headsets */ + { "ACR", 0x7fce, EDID_QUIRK_NON_DESKTOP }, + { "HPN", 0x3515, EDID_QUIRK_NON_DESKTOP }, + { "LEN", 0x0408, EDID_QUIRK_NON_DESKTOP }, + { "LEN", 0xb800, EDID_QUIRK_NON_DESKTOP }, + { "FUJ", 0x1970, EDID_QUIRK_NON_DESKTOP }, + { "DEL", 0x7fce, EDID_QUIRK_NON_DESKTOP }, + { "SEC", 0x144a, EDID_QUIRK_NON_DESKTOP }, + { "AUS", 0xc102, EDID_QUIRK_NON_DESKTOP }, + + /* Sony PlayStation VR Headset */ + { "SNY", 0x0704, EDID_QUIRK_NON_DESKTOP }, }; /* diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c index 186c4e90cc1c..89eef1bb4ddc 100644 --- a/drivers/gpu/drm/drm_mm.c +++ b/drivers/gpu/drm/drm_mm.c @@ -836,9 +836,24 @@ struct drm_mm_node *drm_mm_scan_color_evict(struct drm_mm_scan *scan) if (!mm->color_adjust) return NULL; - hole = list_first_entry(&mm->hole_stack, typeof(*hole), hole_stack); - hole_start = __drm_mm_hole_node_start(hole); - hole_end = hole_start + hole->hole_size; + /* + * The hole found during scanning should ideally be the first element + * in the hole_stack list, but due to side-effects in the driver it + * may not be. + */ + list_for_each_entry(hole, &mm->hole_stack, hole_stack) { + hole_start = __drm_mm_hole_node_start(hole); + hole_end = hole_start + hole->hole_size; + + if (hole_start <= scan->hit_start && + hole_end >= scan->hit_end) + break; + } + + /* We should only be called after we found the hole previously */ + DRM_MM_BUG_ON(&hole->hole_stack == &mm->hole_stack); + if (unlikely(&hole->hole_stack == &mm->hole_stack)) + return NULL; DRM_MM_BUG_ON(hole_start > scan->hit_start); DRM_MM_BUG_ON(hole_end < scan->hit_end); diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c index 555fbe54d6e2..00b8445ba819 100644 --- a/drivers/gpu/drm/drm_probe_helper.c +++ b/drivers/gpu/drm/drm_probe_helper.c @@ -654,6 +654,26 @@ out: } /** + * drm_kms_helper_is_poll_worker - is %current task an output poll worker? + * + * Determine if %current task is an output poll worker. This can be used + * to select distinct code paths for output polling versus other contexts. + * + * One use case is to avoid a deadlock between the output poll worker and + * the autosuspend worker wherein the latter waits for polling to finish + * upon calling drm_kms_helper_poll_disable(), while the former waits for + * runtime suspend to finish upon calling pm_runtime_get_sync() in a + * connector ->detect hook. + */ +bool drm_kms_helper_is_poll_worker(void) +{ + struct work_struct *work = current_work(); + + return work && work->func == output_poll_execute; +} +EXPORT_SYMBOL(drm_kms_helper_is_poll_worker); + +/** * drm_kms_helper_poll_disable - disable output polling * @dev: drm_device * diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c index 2b8bf2dd6387..f68ef1b3a28c 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c +++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c @@ -286,7 +286,6 @@ static int g2d_init_cmdlist(struct g2d_data *g2d) node = kcalloc(G2D_CMDLIST_NUM, sizeof(*node), GFP_KERNEL); if (!node) { - dev_err(dev, "failed to allocate memory\n"); ret = -ENOMEM; goto err; } @@ -926,7 +925,7 @@ static void g2d_finish_event(struct g2d_data *g2d, u32 cmdlist_no) struct drm_device *drm_dev = g2d->subdrv.drm_dev; struct g2d_runqueue_node *runqueue_node = g2d->runqueue_node; struct drm_exynos_pending_g2d_event *e; - struct timeval now; + struct timespec64 now; if (list_empty(&runqueue_node->event_list)) return; @@ -934,9 +933,9 @@ static void g2d_finish_event(struct g2d_data *g2d, u32 cmdlist_no) e = list_first_entry(&runqueue_node->event_list, struct drm_exynos_pending_g2d_event, base.link); - do_gettimeofday(&now); + ktime_get_ts64(&now); e->event.tv_sec = now.tv_sec; - e->event.tv_usec = now.tv_usec; + e->event.tv_usec = now.tv_nsec / NSEC_PER_USEC; e->event.cmdlist_no = cmdlist_no; drm_send_event(drm_dev, &e->base); @@ -1358,10 +1357,9 @@ int exynos_g2d_exec_ioctl(struct drm_device *drm_dev, void *data, return -EFAULT; runqueue_node = kmem_cache_alloc(g2d->runqueue_slab, GFP_KERNEL); - if (!runqueue_node) { - dev_err(dev, "failed to allocate memory\n"); + if (!runqueue_node) return -ENOMEM; - } + run_cmdlist = &runqueue_node->run_cmdlist; event_list = &runqueue_node->event_list; INIT_LIST_HEAD(run_cmdlist); diff --git a/drivers/gpu/drm/exynos/exynos_drm_rotator.h b/drivers/gpu/drm/exynos/exynos_drm_rotator.h deleted file mode 100644 index 71a0b4c0c1e8..000000000000 --- a/drivers/gpu/drm/exynos/exynos_drm_rotator.h +++ /dev/null @@ -1,19 +0,0 @@ -/* - * Copyright (c) 2012 Samsung Electronics Co., Ltd. - * - * Authors: - * YoungJun Cho <yj44.cho@samsung.com> - * Eunchul Kim <chulspro.kim@samsung.com> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - */ - -#ifndef _EXYNOS_DRM_ROTATOR_H_ -#define _EXYNOS_DRM_ROTATOR_H_ - -/* TODO */ - -#endif diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c index a4b75a46f946..abd84cbcf1c2 100644 --- a/drivers/gpu/drm/exynos/exynos_hdmi.c +++ b/drivers/gpu/drm/exynos/exynos_hdmi.c @@ -1068,10 +1068,13 @@ static void hdmi_audio_config(struct hdmi_context *hdata) /* Configuration I2S input ports. Configure I2S_PIN_SEL_0~4 */ hdmi_reg_writeb(hdata, HDMI_I2S_PIN_SEL_0, HDMI_I2S_SEL_SCLK(5) | HDMI_I2S_SEL_LRCK(6)); - hdmi_reg_writeb(hdata, HDMI_I2S_PIN_SEL_1, HDMI_I2S_SEL_SDATA1(1) - | HDMI_I2S_SEL_SDATA2(4)); + + hdmi_reg_writeb(hdata, HDMI_I2S_PIN_SEL_1, HDMI_I2S_SEL_SDATA1(3) + | HDMI_I2S_SEL_SDATA0(4)); + hdmi_reg_writeb(hdata, HDMI_I2S_PIN_SEL_2, HDMI_I2S_SEL_SDATA3(1) | HDMI_I2S_SEL_SDATA2(2)); + hdmi_reg_writeb(hdata, HDMI_I2S_PIN_SEL_3, HDMI_I2S_SEL_DSD(0)); /* I2S_CON_1 & 2 */ diff --git a/drivers/gpu/drm/exynos/regs-fimc.h b/drivers/gpu/drm/exynos/regs-fimc.h index 30496134a3d0..d7cbe53c4c01 100644 --- a/drivers/gpu/drm/exynos/regs-fimc.h +++ b/drivers/gpu/drm/exynos/regs-fimc.h @@ -569,7 +569,7 @@ #define EXYNOS_CIIMGEFF_FIN_EMBOSSING (4 << 26) #define EXYNOS_CIIMGEFF_FIN_SILHOUETTE (5 << 26) #define EXYNOS_CIIMGEFF_FIN_MASK (7 << 26) -#define EXYNOS_CIIMGEFF_PAT_CBCR_MASK ((0xff < 13) | (0xff < 0)) +#define EXYNOS_CIIMGEFF_PAT_CBCR_MASK ((0xff << 13) | (0xff << 0)) /* Real input DMA size register */ #define EXYNOS_CIREAL_ISIZE_AUTOLOAD_ENABLE (1 << 31) diff --git a/drivers/gpu/drm/exynos/regs-hdmi.h b/drivers/gpu/drm/exynos/regs-hdmi.h index 04be0f7e8193..4420c203ac85 100644 --- a/drivers/gpu/drm/exynos/regs-hdmi.h +++ b/drivers/gpu/drm/exynos/regs-hdmi.h @@ -464,7 +464,7 @@ /* I2S_PIN_SEL_1 */ #define HDMI_I2S_SEL_SDATA1(x) (((x) & 0x7) << 4) -#define HDMI_I2S_SEL_SDATA2(x) ((x) & 0x7) +#define HDMI_I2S_SEL_SDATA0(x) ((x) & 0x7) /* I2S_PIN_SEL_2 */ #define HDMI_I2S_SEL_SDATA3(x) (((x) & 0x7) << 4) diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index 909499b73d03..021f722e2481 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -733,6 +733,25 @@ static ssize_t intel_vgpu_rw(struct mdev_device *mdev, char *buf, return ret == 0 ? count : ret; } +static bool gtt_entry(struct mdev_device *mdev, loff_t *ppos) +{ + struct intel_vgpu *vgpu = mdev_get_drvdata(mdev); + unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos); + struct intel_gvt *gvt = vgpu->gvt; + int offset; + + /* Only allow MMIO GGTT entry access */ + if (index != PCI_BASE_ADDRESS_0) + return false; + + offset = (u64)(*ppos & VFIO_PCI_OFFSET_MASK) - + intel_vgpu_get_bar_gpa(vgpu, PCI_BASE_ADDRESS_0); + + return (offset >= gvt->device_info.gtt_start_offset && + offset < gvt->device_info.gtt_start_offset + gvt_ggtt_sz(gvt)) ? + true : false; +} + static ssize_t intel_vgpu_read(struct mdev_device *mdev, char __user *buf, size_t count, loff_t *ppos) { @@ -742,7 +761,21 @@ static ssize_t intel_vgpu_read(struct mdev_device *mdev, char __user *buf, while (count) { size_t filled; - if (count >= 4 && !(*ppos % 4)) { + /* Only support GGTT entry 8 bytes read */ + if (count >= 8 && !(*ppos % 8) && + gtt_entry(mdev, ppos)) { + u64 val; + + ret = intel_vgpu_rw(mdev, (char *)&val, sizeof(val), + ppos, false); + if (ret <= 0) + goto read_err; + + if (copy_to_user(buf, &val, sizeof(val))) + goto read_err; + + filled = 8; + } else if (count >= 4 && !(*ppos % 4)) { u32 val; ret = intel_vgpu_rw(mdev, (char *)&val, sizeof(val), @@ -802,7 +835,21 @@ static ssize_t intel_vgpu_write(struct mdev_device *mdev, while (count) { size_t filled; - if (count >= 4 && !(*ppos % 4)) { + /* Only support GGTT entry 8 bytes write */ + if (count >= 8 && !(*ppos % 8) && + gtt_entry(mdev, ppos)) { + u64 val; + + if (copy_from_user(&val, buf, sizeof(val))) + goto write_err; + + ret = intel_vgpu_rw(mdev, (char *)&val, sizeof(val), + ppos, true); + if (ret <= 0) + goto write_err; + + filled = 8; + } else if (count >= 4 && !(*ppos % 4)) { u32 val; if (copy_from_user(&val, buf, sizeof(val))) diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c index 73ad6e90e49d..256f1bb522b7 100644 --- a/drivers/gpu/drm/i915/gvt/mmio_context.c +++ b/drivers/gpu/drm/i915/gvt/mmio_context.c @@ -118,6 +118,7 @@ static struct engine_mmio gen9_engine_mmio_list[] __cacheline_aligned = { {RCS, HALF_SLICE_CHICKEN3, 0xffff, true}, /* 0xe184 */ {RCS, GEN9_HALF_SLICE_CHICKEN5, 0xffff, true}, /* 0xe188 */ {RCS, GEN9_HALF_SLICE_CHICKEN7, 0xffff, true}, /* 0xe194 */ + {RCS, GEN8_ROW_CHICKEN, 0xffff, true}, /* 0xe4f0 */ {RCS, TRVATTL3PTRDW(0), 0, false}, /* 0x4de0 */ {RCS, TRVATTL3PTRDW(1), 0, false}, /* 0x4de4 */ {RCS, TRNULLDETCT, 0, false}, /* 0x4de8 */ diff --git a/drivers/gpu/drm/i915/gvt/trace.h b/drivers/gpu/drm/i915/gvt/trace.h index 7a2511538f34..736bd2bc5127 100644 --- a/drivers/gpu/drm/i915/gvt/trace.h +++ b/drivers/gpu/drm/i915/gvt/trace.h @@ -333,7 +333,7 @@ TRACE_EVENT(render_mmio, TP_PROTO(int old_id, int new_id, char *action, unsigned int reg, unsigned int old_val, unsigned int new_val), - TP_ARGS(old_id, new_id, action, reg, new_val, old_val), + TP_ARGS(old_id, new_id, action, reg, old_val, new_val), TP_STRUCT__entry( __field(int, old_id) diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 173d0095e3b2..2f5209de0391 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -1433,19 +1433,7 @@ void i915_driver_unload(struct drm_device *dev) intel_modeset_cleanup(dev); - /* - * free the memory space allocated for the child device - * config parsed from VBT - */ - if (dev_priv->vbt.child_dev && dev_priv->vbt.child_dev_num) { - kfree(dev_priv->vbt.child_dev); - dev_priv->vbt.child_dev = NULL; - dev_priv->vbt.child_dev_num = 0; - } - kfree(dev_priv->vbt.sdvo_lvds_vbt_mode); - dev_priv->vbt.sdvo_lvds_vbt_mode = NULL; - kfree(dev_priv->vbt.lfp_lvds_vbt_mode); - dev_priv->vbt.lfp_lvds_vbt_mode = NULL; + intel_bios_cleanup(dev_priv); vga_switcheroo_unregister_client(pdev); vga_client_register(pdev, NULL, NULL, NULL); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index a42deebedb0f..d307429a5ae0 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1349,6 +1349,7 @@ struct intel_vbt_data { u32 size; u8 *data; const u8 *sequence[MIPI_SEQ_MAX]; + u8 *deassert_seq; /* Used by fixup_mipi_sequences() */ } dsi; int crt_ddc_pin; @@ -3657,6 +3658,7 @@ extern void intel_i2c_reset(struct drm_i915_private *dev_priv); /* intel_bios.c */ void intel_bios_init(struct drm_i915_private *dev_priv); +void intel_bios_cleanup(struct drm_i915_private *dev_priv); bool intel_bios_is_valid_vbt(const void *buf, size_t size); bool intel_bios_is_tv_present(struct drm_i915_private *dev_priv); bool intel_bios_is_lvds_present(struct drm_i915_private *dev_priv, u8 *i2c_pin); diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c index 648e7536ff51..0c963fcf31ff 100644 --- a/drivers/gpu/drm/i915/i915_gem_context.c +++ b/drivers/gpu/drm/i915/i915_gem_context.c @@ -803,7 +803,7 @@ int i915_gem_context_setparam_ioctl(struct drm_device *dev, void *data, case I915_CONTEXT_PARAM_PRIORITY: { - int priority = args->value; + s64 priority = args->value; if (args->size) ret = -EINVAL; diff --git a/drivers/gpu/drm/i915/i915_oa_cflgt3.c b/drivers/gpu/drm/i915/i915_oa_cflgt3.c index 42ff06fe54a3..792facdb6702 100644 --- a/drivers/gpu/drm/i915/i915_oa_cflgt3.c +++ b/drivers/gpu/drm/i915/i915_oa_cflgt3.c @@ -84,9 +84,9 @@ show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf) void i915_perf_load_test_config_cflgt3(struct drm_i915_private *dev_priv) { - strncpy(dev_priv->perf.oa.test_config.uuid, + strlcpy(dev_priv->perf.oa.test_config.uuid, "577e8e2c-3fa0-4875-8743-3538d585e3b0", - UUID_STRING_LEN); + sizeof(dev_priv->perf.oa.test_config.uuid)); dev_priv->perf.oa.test_config.id = 1; dev_priv->perf.oa.test_config.mux_regs = mux_config_test_oa; diff --git a/drivers/gpu/drm/i915/i915_oa_cnl.c b/drivers/gpu/drm/i915/i915_oa_cnl.c index ff0ac3627cc4..ba9140c87cc0 100644 --- a/drivers/gpu/drm/i915/i915_oa_cnl.c +++ b/drivers/gpu/drm/i915/i915_oa_cnl.c @@ -96,9 +96,9 @@ show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf) void i915_perf_load_test_config_cnl(struct drm_i915_private *dev_priv) { - strncpy(dev_priv->perf.oa.test_config.uuid, + strlcpy(dev_priv->perf.oa.test_config.uuid, "db41edd4-d8e7-4730-ad11-b9a2d6833503", - UUID_STRING_LEN); + sizeof(dev_priv->perf.oa.test_config.uuid)); dev_priv->perf.oa.test_config.id = 1; dev_priv->perf.oa.test_config.mux_regs = mux_config_test_oa; diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index 55a8a1e29424..0e9b98c32b62 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -285,26 +285,41 @@ static u64 count_interrupts(struct drm_i915_private *i915) return sum; } -static void i915_pmu_event_destroy(struct perf_event *event) +static void engine_event_destroy(struct perf_event *event) { - WARN_ON(event->parent); + struct drm_i915_private *i915 = + container_of(event->pmu, typeof(*i915), pmu.base); + struct intel_engine_cs *engine; + + engine = intel_engine_lookup_user(i915, + engine_event_class(event), + engine_event_instance(event)); + if (WARN_ON_ONCE(!engine)) + return; + + if (engine_event_sample(event) == I915_SAMPLE_BUSY && + intel_engine_supports_stats(engine)) + intel_disable_engine_stats(engine); } -static int engine_event_init(struct perf_event *event) +static void i915_pmu_event_destroy(struct perf_event *event) { - struct drm_i915_private *i915 = - container_of(event->pmu, typeof(*i915), pmu.base); + WARN_ON(event->parent); - if (!intel_engine_lookup_user(i915, engine_event_class(event), - engine_event_instance(event))) - return -ENODEV; + if (is_engine_event(event)) + engine_event_destroy(event); +} - switch (engine_event_sample(event)) { +static int +engine_event_status(struct intel_engine_cs *engine, + enum drm_i915_pmu_engine_sample sample) +{ + switch (sample) { case I915_SAMPLE_BUSY: case I915_SAMPLE_WAIT: break; case I915_SAMPLE_SEMA: - if (INTEL_GEN(i915) < 6) + if (INTEL_GEN(engine->i915) < 6) return -ENODEV; break; default: @@ -314,6 +329,30 @@ static int engine_event_init(struct perf_event *event) return 0; } +static int engine_event_init(struct perf_event *event) +{ + struct drm_i915_private *i915 = + container_of(event->pmu, typeof(*i915), pmu.base); + struct intel_engine_cs *engine; + u8 sample; + int ret; + + engine = intel_engine_lookup_user(i915, engine_event_class(event), + engine_event_instance(event)); + if (!engine) + return -ENODEV; + + sample = engine_event_sample(event); + ret = engine_event_status(engine, sample); + if (ret) + return ret; + + if (sample == I915_SAMPLE_BUSY && intel_engine_supports_stats(engine)) + ret = intel_enable_engine_stats(engine); + + return ret; +} + static int i915_pmu_event_init(struct perf_event *event) { struct drm_i915_private *i915 = @@ -370,7 +409,94 @@ static int i915_pmu_event_init(struct perf_event *event) return 0; } -static u64 __i915_pmu_event_read(struct perf_event *event) +static u64 __get_rc6(struct drm_i915_private *i915) +{ + u64 val; + + val = intel_rc6_residency_ns(i915, + IS_VALLEYVIEW(i915) ? + VLV_GT_RENDER_RC6 : + GEN6_GT_GFX_RC6); + + if (HAS_RC6p(i915)) + val += intel_rc6_residency_ns(i915, GEN6_GT_GFX_RC6p); + + if (HAS_RC6pp(i915)) + val += intel_rc6_residency_ns(i915, GEN6_GT_GFX_RC6pp); + + return val; +} + +static u64 get_rc6(struct drm_i915_private *i915, bool locked) +{ +#if IS_ENABLED(CONFIG_PM) + unsigned long flags; + u64 val; + + if (intel_runtime_pm_get_if_in_use(i915)) { + val = __get_rc6(i915); + intel_runtime_pm_put(i915); + + /* + * If we are coming back from being runtime suspended we must + * be careful not to report a larger value than returned + * previously. + */ + + if (!locked) + spin_lock_irqsave(&i915->pmu.lock, flags); + + if (val >= i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur) { + i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur = 0; + i915->pmu.sample[__I915_SAMPLE_RC6].cur = val; + } else { + val = i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur; + } + + if (!locked) + spin_unlock_irqrestore(&i915->pmu.lock, flags); + } else { + struct pci_dev *pdev = i915->drm.pdev; + struct device *kdev = &pdev->dev; + unsigned long flags2; + + /* + * We are runtime suspended. + * + * Report the delta from when the device was suspended to now, + * on top of the last known real value, as the approximated RC6 + * counter value. + */ + if (!locked) + spin_lock_irqsave(&i915->pmu.lock, flags); + + spin_lock_irqsave(&kdev->power.lock, flags2); + + if (!i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur) + i915->pmu.suspended_jiffies_last = + kdev->power.suspended_jiffies; + + val = kdev->power.suspended_jiffies - + i915->pmu.suspended_jiffies_last; + val += jiffies - kdev->power.accounting_timestamp; + + spin_unlock_irqrestore(&kdev->power.lock, flags2); + + val = jiffies_to_nsecs(val); + val += i915->pmu.sample[__I915_SAMPLE_RC6].cur; + i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur = val; + + if (!locked) + spin_unlock_irqrestore(&i915->pmu.lock, flags); + } + + return val; +#else + return __get_rc6(i915); +#endif +} + +static u64 __i915_pmu_event_read(struct perf_event *event, bool locked) { struct drm_i915_private *i915 = container_of(event->pmu, typeof(*i915), pmu.base); @@ -387,7 +513,7 @@ static u64 __i915_pmu_event_read(struct perf_event *event) if (WARN_ON_ONCE(!engine)) { /* Do nothing */ } else if (sample == I915_SAMPLE_BUSY && - engine->pmu.busy_stats) { + intel_engine_supports_stats(engine)) { val = ktime_to_ns(intel_engine_get_busy_time(engine)); } else { val = engine->pmu.sample[sample].cur; @@ -408,18 +534,7 @@ static u64 __i915_pmu_event_read(struct perf_event *event) val = count_interrupts(i915); break; case I915_PMU_RC6_RESIDENCY: - intel_runtime_pm_get(i915); - val = intel_rc6_residency_ns(i915, - IS_VALLEYVIEW(i915) ? - VLV_GT_RENDER_RC6 : - GEN6_GT_GFX_RC6); - if (HAS_RC6p(i915)) - val += intel_rc6_residency_ns(i915, - GEN6_GT_GFX_RC6p); - if (HAS_RC6pp(i915)) - val += intel_rc6_residency_ns(i915, - GEN6_GT_GFX_RC6pp); - intel_runtime_pm_put(i915); + val = get_rc6(i915, locked); break; } } @@ -434,7 +549,7 @@ static void i915_pmu_event_read(struct perf_event *event) again: prev = local64_read(&hwc->prev_count); - new = __i915_pmu_event_read(event); + new = __i915_pmu_event_read(event, false); if (local64_cmpxchg(&hwc->prev_count, prev, new) != prev) goto again; @@ -442,12 +557,6 @@ again: local64_add(new - prev, &event->count); } -static bool engine_needs_busy_stats(struct intel_engine_cs *engine) -{ - return intel_engine_supports_stats(engine) && - (engine->pmu.enable & BIT(I915_SAMPLE_BUSY)); -} - static void i915_pmu_enable(struct perf_event *event) { struct drm_i915_private *i915 = @@ -487,21 +596,7 @@ static void i915_pmu_enable(struct perf_event *event) GEM_BUG_ON(sample >= I915_PMU_SAMPLE_BITS); GEM_BUG_ON(engine->pmu.enable_count[sample] == ~0); - if (engine->pmu.enable_count[sample]++ == 0) { - /* - * Enable engine busy stats tracking if needed or - * alternatively cancel the scheduled disable. - * - * If the delayed disable was pending, cancel it and - * in this case do not enable since it already is. - */ - if (engine_needs_busy_stats(engine) && - !engine->pmu.busy_stats) { - engine->pmu.busy_stats = true; - if (!cancel_delayed_work(&engine->pmu.disable_busy_stats)) - intel_enable_engine_stats(engine); - } - } + engine->pmu.enable_count[sample]++; } /* @@ -509,19 +604,11 @@ static void i915_pmu_enable(struct perf_event *event) * for all listeners. Even when the event was already enabled and has * an existing non-zero value. */ - local64_set(&event->hw.prev_count, __i915_pmu_event_read(event)); + local64_set(&event->hw.prev_count, __i915_pmu_event_read(event, true)); spin_unlock_irqrestore(&i915->pmu.lock, flags); } -static void __disable_busy_stats(struct work_struct *work) -{ - struct intel_engine_cs *engine = - container_of(work, typeof(*engine), pmu.disable_busy_stats.work); - - intel_disable_engine_stats(engine); -} - static void i915_pmu_disable(struct perf_event *event) { struct drm_i915_private *i915 = @@ -545,26 +632,8 @@ static void i915_pmu_disable(struct perf_event *event) * Decrement the reference count and clear the enabled * bitmask when the last listener on an event goes away. */ - if (--engine->pmu.enable_count[sample] == 0) { + if (--engine->pmu.enable_count[sample] == 0) engine->pmu.enable &= ~BIT(sample); - if (!engine_needs_busy_stats(engine) && - engine->pmu.busy_stats) { - engine->pmu.busy_stats = false; - /* - * We request a delayed disable to handle the - * rapid on/off cycles on events, which can - * happen when tools like perf stat start, in a - * nicer way. - * - * In addition, this also helps with busy stats - * accuracy with background CPU offline/online - * migration events. - */ - queue_delayed_work(system_wq, - &engine->pmu.disable_busy_stats, - round_jiffies_up_relative(HZ)); - } - } } GEM_BUG_ON(bit >= I915_PMU_MASK_BITS); @@ -797,8 +866,6 @@ static void i915_pmu_unregister_cpuhp_state(struct drm_i915_private *i915) void i915_pmu_register(struct drm_i915_private *i915) { - struct intel_engine_cs *engine; - enum intel_engine_id id; int ret; if (INTEL_GEN(i915) <= 2) { @@ -820,10 +887,6 @@ void i915_pmu_register(struct drm_i915_private *i915) hrtimer_init(&i915->pmu.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); i915->pmu.timer.function = i915_sample; - for_each_engine(engine, i915, id) - INIT_DELAYED_WORK(&engine->pmu.disable_busy_stats, - __disable_busy_stats); - ret = perf_pmu_register(&i915->pmu.base, "i915", -1); if (ret) goto err; @@ -843,9 +906,6 @@ err: void i915_pmu_unregister(struct drm_i915_private *i915) { - struct intel_engine_cs *engine; - enum intel_engine_id id; - if (!i915->pmu.base.event_init) return; @@ -853,11 +913,6 @@ void i915_pmu_unregister(struct drm_i915_private *i915) hrtimer_cancel(&i915->pmu.timer); - for_each_engine(engine, i915, id) { - GEM_BUG_ON(engine->pmu.busy_stats); - flush_delayed_work(&engine->pmu.disable_busy_stats); - } - i915_pmu_unregister_cpuhp_state(i915); perf_pmu_unregister(&i915->pmu.base); diff --git a/drivers/gpu/drm/i915/i915_pmu.h b/drivers/gpu/drm/i915/i915_pmu.h index 40c154d13565..bb62df15afa4 100644 --- a/drivers/gpu/drm/i915/i915_pmu.h +++ b/drivers/gpu/drm/i915/i915_pmu.h @@ -27,6 +27,8 @@ enum { __I915_SAMPLE_FREQ_ACT = 0, __I915_SAMPLE_FREQ_REQ, + __I915_SAMPLE_RC6, + __I915_SAMPLE_RC6_ESTIMATED, __I915_NUM_PMU_SAMPLERS }; @@ -94,6 +96,10 @@ struct i915_pmu { * struct intel_engine_cs. */ struct i915_pmu_sample sample[__I915_NUM_PMU_SAMPLERS]; + /** + * @suspended_jiffies_last: Cached suspend time from PM core. + */ + unsigned long suspended_jiffies_last; }; #ifdef CONFIG_PERF_EVENTS diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c index f7f771749e48..b49a2df44430 100644 --- a/drivers/gpu/drm/i915/intel_bios.c +++ b/drivers/gpu/drm/i915/intel_bios.c @@ -947,6 +947,86 @@ static int goto_next_sequence_v3(const u8 *data, int index, int total) return 0; } +/* + * Get len of pre-fixed deassert fragment from a v1 init OTP sequence, + * skip all delay + gpio operands and stop at the first DSI packet op. + */ +static int get_init_otp_deassert_fragment_len(struct drm_i915_private *dev_priv) +{ + const u8 *data = dev_priv->vbt.dsi.sequence[MIPI_SEQ_INIT_OTP]; + int index, len; + + if (WARN_ON(!data || dev_priv->vbt.dsi.seq_version != 1)) + return 0; + + /* index = 1 to skip sequence byte */ + for (index = 1; data[index] != MIPI_SEQ_ELEM_END; index += len) { + switch (data[index]) { + case MIPI_SEQ_ELEM_SEND_PKT: + return index == 1 ? 0 : index; + case MIPI_SEQ_ELEM_DELAY: + len = 5; /* 1 byte for operand + uint32 */ + break; + case MIPI_SEQ_ELEM_GPIO: + len = 3; /* 1 byte for op, 1 for gpio_nr, 1 for value */ + break; + default: + return 0; + } + } + + return 0; +} + +/* + * Some v1 VBT MIPI sequences do the deassert in the init OTP sequence. + * The deassert must be done before calling intel_dsi_device_ready, so for + * these devices we split the init OTP sequence into a deassert sequence and + * the actual init OTP part. + */ +static void fixup_mipi_sequences(struct drm_i915_private *dev_priv) +{ + u8 *init_otp; + int len; + + /* Limit this to VLV for now. */ + if (!IS_VALLEYVIEW(dev_priv)) + return; + + /* Limit this to v1 vid-mode sequences */ + if (dev_priv->vbt.dsi.config->is_cmd_mode || + dev_priv->vbt.dsi.seq_version != 1) + return; + + /* Only do this if there are otp and assert seqs and no deassert seq */ + if (!dev_priv->vbt.dsi.sequence[MIPI_SEQ_INIT_OTP] || + !dev_priv->vbt.dsi.sequence[MIPI_SEQ_ASSERT_RESET] || + dev_priv->vbt.dsi.sequence[MIPI_SEQ_DEASSERT_RESET]) + return; + + /* The deassert-sequence ends at the first DSI packet */ + len = get_init_otp_deassert_fragment_len(dev_priv); + if (!len) + return; + + DRM_DEBUG_KMS("Using init OTP fragment to deassert reset\n"); + + /* Copy the fragment, update seq byte and terminate it */ + init_otp = (u8 *)dev_priv->vbt.dsi.sequence[MIPI_SEQ_INIT_OTP]; + dev_priv->vbt.dsi.deassert_seq = kmemdup(init_otp, len + 1, GFP_KERNEL); + if (!dev_priv->vbt.dsi.deassert_seq) + return; + dev_priv->vbt.dsi.deassert_seq[0] = MIPI_SEQ_DEASSERT_RESET; + dev_priv->vbt.dsi.deassert_seq[len] = MIPI_SEQ_ELEM_END; + /* Use the copy for deassert */ + dev_priv->vbt.dsi.sequence[MIPI_SEQ_DEASSERT_RESET] = + dev_priv->vbt.dsi.deassert_seq; + /* Replace the last byte of the fragment with init OTP seq byte */ + init_otp[len - 1] = MIPI_SEQ_INIT_OTP; + /* And make MIPI_MIPI_SEQ_INIT_OTP point to it */ + dev_priv->vbt.dsi.sequence[MIPI_SEQ_INIT_OTP] = init_otp + len - 1; +} + static void parse_mipi_sequence(struct drm_i915_private *dev_priv, const struct bdb_header *bdb) @@ -1016,6 +1096,8 @@ parse_mipi_sequence(struct drm_i915_private *dev_priv, dev_priv->vbt.dsi.size = seq_size; dev_priv->vbt.dsi.seq_version = sequence->version; + fixup_mipi_sequences(dev_priv); + DRM_DEBUG_DRIVER("MIPI related VBT parsing complete\n"); return; @@ -1589,6 +1671,29 @@ out: } /** + * intel_bios_cleanup - Free any resources allocated by intel_bios_init() + * @dev_priv: i915 device instance + */ +void intel_bios_cleanup(struct drm_i915_private *dev_priv) +{ + kfree(dev_priv->vbt.child_dev); + dev_priv->vbt.child_dev = NULL; + dev_priv->vbt.child_dev_num = 0; + kfree(dev_priv->vbt.sdvo_lvds_vbt_mode); + dev_priv->vbt.sdvo_lvds_vbt_mode = NULL; + kfree(dev_priv->vbt.lfp_lvds_vbt_mode); + dev_priv->vbt.lfp_lvds_vbt_mode = NULL; + kfree(dev_priv->vbt.dsi.data); + dev_priv->vbt.dsi.data = NULL; + kfree(dev_priv->vbt.dsi.pps); + dev_priv->vbt.dsi.pps = NULL; + kfree(dev_priv->vbt.dsi.config); + dev_priv->vbt.dsi.config = NULL; + kfree(dev_priv->vbt.dsi.deassert_seq); + dev_priv->vbt.dsi.deassert_seq = NULL; +} + +/** * intel_bios_is_tv_present - is integrated TV present in VBT * @dev_priv: i915 device instance * diff --git a/drivers/gpu/drm/i915/intel_breadcrumbs.c b/drivers/gpu/drm/i915/intel_breadcrumbs.c index bd40fea16b4f..f54ddda9fdad 100644 --- a/drivers/gpu/drm/i915/intel_breadcrumbs.c +++ b/drivers/gpu/drm/i915/intel_breadcrumbs.c @@ -594,29 +594,16 @@ void intel_engine_remove_wait(struct intel_engine_cs *engine, spin_unlock_irq(&b->rb_lock); } -static bool signal_valid(const struct drm_i915_gem_request *request) -{ - return intel_wait_check_request(&request->signaling.wait, request); -} - static bool signal_complete(const struct drm_i915_gem_request *request) { if (!request) return false; - /* If another process served as the bottom-half it may have already - * signalled that this wait is already completed. - */ - if (intel_wait_complete(&request->signaling.wait)) - return signal_valid(request); - - /* Carefully check if the request is complete, giving time for the + /* + * Carefully check if the request is complete, giving time for the * seqno to be visible or if the GPU hung. */ - if (__i915_request_irq_complete(request)) - return true; - - return false; + return __i915_request_irq_complete(request); } static struct drm_i915_gem_request *to_signaler(struct rb_node *rb) @@ -659,9 +646,13 @@ static int intel_breadcrumbs_signaler(void *arg) request = i915_gem_request_get_rcu(request); rcu_read_unlock(); if (signal_complete(request)) { - local_bh_disable(); - dma_fence_signal(&request->fence); - local_bh_enable(); /* kick start the tasklets */ + if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, + &request->fence.flags)) { + local_bh_disable(); + dma_fence_signal(&request->fence); + GEM_BUG_ON(!i915_gem_request_completed(request)); + local_bh_enable(); /* kick start the tasklets */ + } spin_lock_irq(&b->rb_lock); diff --git a/drivers/gpu/drm/i915/intel_cdclk.c b/drivers/gpu/drm/i915/intel_cdclk.c index 5dc118f26b51..1704c8897afd 100644 --- a/drivers/gpu/drm/i915/intel_cdclk.c +++ b/drivers/gpu/drm/i915/intel_cdclk.c @@ -1952,6 +1952,14 @@ int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state) if (crtc_state->has_audio && INTEL_GEN(dev_priv) >= 9) min_cdclk = max(2 * 96000, min_cdclk); + /* + * On Valleyview some DSI panels lose (v|h)sync when the clock is lower + * than 320000KHz. + */ + if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DSI) && + IS_VALLEYVIEW(dev_priv)) + min_cdclk = max(320000, min_cdclk); + if (min_cdclk > dev_priv->max_cdclk_freq) { DRM_DEBUG_KMS("required cdclk (%d kHz) exceeds max (%d kHz)\n", min_cdclk, dev_priv->max_cdclk_freq); diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c index d790bdc227ff..fa960cfd2764 100644 --- a/drivers/gpu/drm/i915/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/intel_engine_cs.c @@ -1458,7 +1458,9 @@ static bool ring_is_idle(struct intel_engine_cs *engine) struct drm_i915_private *dev_priv = engine->i915; bool idle = true; - intel_runtime_pm_get(dev_priv); + /* If the whole device is asleep, the engine must be idle */ + if (!intel_runtime_pm_get_if_in_use(dev_priv)) + return true; /* First check that no commands are left in the ring */ if ((I915_READ_HEAD(engine) & HEAD_ADDR) != @@ -1943,16 +1945,22 @@ intel_engine_lookup_user(struct drm_i915_private *i915, u8 class, u8 instance) */ int intel_enable_engine_stats(struct intel_engine_cs *engine) { + struct intel_engine_execlists *execlists = &engine->execlists; unsigned long flags; + int err = 0; if (!intel_engine_supports_stats(engine)) return -ENODEV; + tasklet_disable(&execlists->tasklet); spin_lock_irqsave(&engine->stats.lock, flags); - if (engine->stats.enabled == ~0) - goto busy; + + if (unlikely(engine->stats.enabled == ~0)) { + err = -EBUSY; + goto unlock; + } + if (engine->stats.enabled++ == 0) { - struct intel_engine_execlists *execlists = &engine->execlists; const struct execlist_port *port = execlists->port; unsigned int num_ports = execlists_num_ports(execlists); @@ -1967,14 +1975,12 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine) if (engine->stats.active) engine->stats.start = engine->stats.enabled_at; } - spin_unlock_irqrestore(&engine->stats.lock, flags); - - return 0; -busy: +unlock: spin_unlock_irqrestore(&engine->stats.lock, flags); + tasklet_enable(&execlists->tasklet); - return -EBUSY; + return err; } static ktime_t __intel_engine_get_busy_time(struct intel_engine_cs *engine) diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index c5ff203e42d6..a0e7a6c2a57c 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -366,20 +366,6 @@ struct intel_engine_cs { */ #define I915_ENGINE_SAMPLE_MAX (I915_SAMPLE_SEMA + 1) struct i915_pmu_sample sample[I915_ENGINE_SAMPLE_MAX]; - /** - * @busy_stats: Has enablement of engine stats tracking been - * requested. - */ - bool busy_stats; - /** - * @disable_busy_stats: Work item for busy stats disabling. - * - * Same as with @enable_busy_stats action, with the difference - * that we delay it in case there are rapid enable-disable - * actions, which can happen during tool startup (like perf - * stat). - */ - struct delayed_work disable_busy_stats; } pmu; /* diff --git a/drivers/gpu/drm/meson/meson_crtc.c b/drivers/gpu/drm/meson/meson_crtc.c index 5155f0179b61..05520202c967 100644 --- a/drivers/gpu/drm/meson/meson_crtc.c +++ b/drivers/gpu/drm/meson/meson_crtc.c @@ -36,6 +36,7 @@ #include "meson_venc.h" #include "meson_vpp.h" #include "meson_viu.h" +#include "meson_canvas.h" #include "meson_registers.h" /* CRTC definition */ @@ -192,6 +193,11 @@ void meson_crtc_irq(struct meson_drm *priv) } else meson_vpp_disable_interlace_vscaler_osd1(priv); + meson_canvas_setup(priv, MESON_CANVAS_ID_OSD1, + priv->viu.osd1_addr, priv->viu.osd1_stride, + priv->viu.osd1_height, MESON_CANVAS_WRAP_NONE, + MESON_CANVAS_BLKMODE_LINEAR); + /* Enable OSD1 */ writel_bits_relaxed(VPP_OSD1_POSTBLEND, VPP_OSD1_POSTBLEND, priv->io_base + _REG(VPP_MISC)); diff --git a/drivers/gpu/drm/meson/meson_drv.h b/drivers/gpu/drm/meson/meson_drv.h index 5e8b392b9d1f..8450d6ac8c9b 100644 --- a/drivers/gpu/drm/meson/meson_drv.h +++ b/drivers/gpu/drm/meson/meson_drv.h @@ -43,6 +43,9 @@ struct meson_drm { bool osd1_commit; uint32_t osd1_ctrl_stat; uint32_t osd1_blk0_cfg[5]; + uint32_t osd1_addr; + uint32_t osd1_stride; + uint32_t osd1_height; } viu; struct { diff --git a/drivers/gpu/drm/meson/meson_plane.c b/drivers/gpu/drm/meson/meson_plane.c index d0a6ac8390f3..27bd3503e1e4 100644 --- a/drivers/gpu/drm/meson/meson_plane.c +++ b/drivers/gpu/drm/meson/meson_plane.c @@ -164,10 +164,9 @@ static void meson_plane_atomic_update(struct drm_plane *plane, /* Update Canvas with buffer address */ gem = drm_fb_cma_get_gem_obj(fb, 0); - meson_canvas_setup(priv, MESON_CANVAS_ID_OSD1, - gem->paddr, fb->pitches[0], - fb->height, MESON_CANVAS_WRAP_NONE, - MESON_CANVAS_BLKMODE_LINEAR); + priv->viu.osd1_addr = gem->paddr; + priv->viu.osd1_stride = fb->pitches[0]; + priv->viu.osd1_height = fb->height; spin_unlock_irqrestore(&priv->drm->event_lock, flags); } diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c index 69d6e61a01ec..6ed9cb053dfa 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.c +++ b/drivers/gpu/drm/nouveau/nouveau_connector.c @@ -570,9 +570,15 @@ nouveau_connector_detect(struct drm_connector *connector, bool force) nv_connector->edid = NULL; } - ret = pm_runtime_get_sync(connector->dev->dev); - if (ret < 0 && ret != -EACCES) - return conn_status; + /* Outputs are only polled while runtime active, so acquiring a + * runtime PM ref here is unnecessary (and would deadlock upon + * runtime suspend because it waits for polling to finish). + */ + if (!drm_kms_helper_is_poll_worker()) { + ret = pm_runtime_get_sync(connector->dev->dev); + if (ret < 0 && ret != -EACCES) + return conn_status; + } nv_encoder = nouveau_connector_ddc_detect(connector); if (nv_encoder && (i2c = nv_encoder->i2c) != NULL) { @@ -647,8 +653,10 @@ detect_analog: out: - pm_runtime_mark_last_busy(connector->dev->dev); - pm_runtime_put_autosuspend(connector->dev->dev); + if (!drm_kms_helper_is_poll_worker()) { + pm_runtime_mark_last_busy(connector->dev->dev); + pm_runtime_put_autosuspend(connector->dev->dev); + } return conn_status; } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c index bf62303571b3..3695cde669f8 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c @@ -301,7 +301,7 @@ nvkm_therm_attr_set(struct nvkm_therm *therm, void nvkm_therm_clkgate_enable(struct nvkm_therm *therm) { - if (!therm->func->clkgate_enable || !therm->clkgating_enabled) + if (!therm || !therm->func->clkgate_enable || !therm->clkgating_enabled) return; nvkm_debug(&therm->subdev, @@ -312,7 +312,7 @@ nvkm_therm_clkgate_enable(struct nvkm_therm *therm) void nvkm_therm_clkgate_fini(struct nvkm_therm *therm, bool suspend) { - if (!therm->func->clkgate_fini || !therm->clkgating_enabled) + if (!therm || !therm->func->clkgate_fini || !therm->clkgating_enabled) return; nvkm_debug(&therm->subdev, @@ -395,7 +395,7 @@ void nvkm_therm_clkgate_init(struct nvkm_therm *therm, const struct nvkm_therm_clkgate_pack *p) { - if (!therm->func->clkgate_init || !therm->clkgating_enabled) + if (!therm || !therm->func->clkgate_init || !therm->clkgating_enabled) return; therm->func->clkgate_init(therm, p); diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c index 5012f5e47a1e..2e2ca3c6b47d 100644 --- a/drivers/gpu/drm/radeon/radeon_connectors.c +++ b/drivers/gpu/drm/radeon/radeon_connectors.c @@ -899,9 +899,11 @@ radeon_lvds_detect(struct drm_connector *connector, bool force) enum drm_connector_status ret = connector_status_disconnected; int r; - r = pm_runtime_get_sync(connector->dev->dev); - if (r < 0) - return connector_status_disconnected; + if (!drm_kms_helper_is_poll_worker()) { + r = pm_runtime_get_sync(connector->dev->dev); + if (r < 0) + return connector_status_disconnected; + } if (encoder) { struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); @@ -924,8 +926,12 @@ radeon_lvds_detect(struct drm_connector *connector, bool force) /* check acpi lid status ??? */ radeon_connector_update_scratch_regs(connector, ret); - pm_runtime_mark_last_busy(connector->dev->dev); - pm_runtime_put_autosuspend(connector->dev->dev); + + if (!drm_kms_helper_is_poll_worker()) { + pm_runtime_mark_last_busy(connector->dev->dev); + pm_runtime_put_autosuspend(connector->dev->dev); + } + return ret; } @@ -1039,9 +1045,11 @@ radeon_vga_detect(struct drm_connector *connector, bool force) enum drm_connector_status ret = connector_status_disconnected; int r; - r = pm_runtime_get_sync(connector->dev->dev); - if (r < 0) - return connector_status_disconnected; + if (!drm_kms_helper_is_poll_worker()) { + r = pm_runtime_get_sync(connector->dev->dev); + if (r < 0) + return connector_status_disconnected; + } encoder = radeon_best_single_encoder(connector); if (!encoder) @@ -1108,8 +1116,10 @@ radeon_vga_detect(struct drm_connector *connector, bool force) radeon_connector_update_scratch_regs(connector, ret); out: - pm_runtime_mark_last_busy(connector->dev->dev); - pm_runtime_put_autosuspend(connector->dev->dev); + if (!drm_kms_helper_is_poll_worker()) { + pm_runtime_mark_last_busy(connector->dev->dev); + pm_runtime_put_autosuspend(connector->dev->dev); + } return ret; } @@ -1173,9 +1183,11 @@ radeon_tv_detect(struct drm_connector *connector, bool force) if (!radeon_connector->dac_load_detect) return ret; - r = pm_runtime_get_sync(connector->dev->dev); - if (r < 0) - return connector_status_disconnected; + if (!drm_kms_helper_is_poll_worker()) { + r = pm_runtime_get_sync(connector->dev->dev); + if (r < 0) + return connector_status_disconnected; + } encoder = radeon_best_single_encoder(connector); if (!encoder) @@ -1187,8 +1199,12 @@ radeon_tv_detect(struct drm_connector *connector, bool force) if (ret == connector_status_connected) ret = radeon_connector_analog_encoder_conflict_solve(connector, encoder, ret, false); radeon_connector_update_scratch_regs(connector, ret); - pm_runtime_mark_last_busy(connector->dev->dev); - pm_runtime_put_autosuspend(connector->dev->dev); + + if (!drm_kms_helper_is_poll_worker()) { + pm_runtime_mark_last_busy(connector->dev->dev); + pm_runtime_put_autosuspend(connector->dev->dev); + } + return ret; } @@ -1251,9 +1267,11 @@ radeon_dvi_detect(struct drm_connector *connector, bool force) enum drm_connector_status ret = connector_status_disconnected; bool dret = false, broken_edid = false; - r = pm_runtime_get_sync(connector->dev->dev); - if (r < 0) - return connector_status_disconnected; + if (!drm_kms_helper_is_poll_worker()) { + r = pm_runtime_get_sync(connector->dev->dev); + if (r < 0) + return connector_status_disconnected; + } if (radeon_connector->detected_hpd_without_ddc) { force = true; @@ -1436,8 +1454,10 @@ out: } exit: - pm_runtime_mark_last_busy(connector->dev->dev); - pm_runtime_put_autosuspend(connector->dev->dev); + if (!drm_kms_helper_is_poll_worker()) { + pm_runtime_mark_last_busy(connector->dev->dev); + pm_runtime_put_autosuspend(connector->dev->dev); + } return ret; } @@ -1688,9 +1708,11 @@ radeon_dp_detect(struct drm_connector *connector, bool force) if (radeon_dig_connector->is_mst) return connector_status_disconnected; - r = pm_runtime_get_sync(connector->dev->dev); - if (r < 0) - return connector_status_disconnected; + if (!drm_kms_helper_is_poll_worker()) { + r = pm_runtime_get_sync(connector->dev->dev); + if (r < 0) + return connector_status_disconnected; + } if (!force && radeon_check_hpd_status_unchanged(connector)) { ret = connector->status; @@ -1777,8 +1799,10 @@ radeon_dp_detect(struct drm_connector *connector, bool force) } out: - pm_runtime_mark_last_busy(connector->dev->dev); - pm_runtime_put_autosuspend(connector->dev->dev); + if (!drm_kms_helper_is_poll_worker()) { + pm_runtime_mark_last_busy(connector->dev->dev); + pm_runtime_put_autosuspend(connector->dev->dev); + } return ret; } diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c index 658fa2d3e40c..48685cddbad1 100644 --- a/drivers/gpu/ipu-v3/ipu-common.c +++ b/drivers/gpu/ipu-v3/ipu-common.c @@ -1089,7 +1089,7 @@ static void ipu_irq_handler(struct irq_desc *desc) { struct ipu_soc *ipu = irq_desc_get_handler_data(desc); struct irq_chip *chip = irq_desc_get_chip(desc); - const int int_reg[] = { 0, 1, 2, 3, 10, 11, 12, 13, 14}; + static const int int_reg[] = { 0, 1, 2, 3, 10, 11, 12, 13, 14}; chained_irq_enter(chip, desc); @@ -1102,7 +1102,7 @@ static void ipu_err_irq_handler(struct irq_desc *desc) { struct ipu_soc *ipu = irq_desc_get_handler_data(desc); struct irq_chip *chip = irq_desc_get_chip(desc); - const int int_reg[] = { 4, 5, 8, 9}; + static const int int_reg[] = { 4, 5, 8, 9}; chained_irq_enter(chip, desc); diff --git a/drivers/gpu/ipu-v3/ipu-cpmem.c b/drivers/gpu/ipu-v3/ipu-cpmem.c index bb9c087e6c0d..9f2d9ec42add 100644 --- a/drivers/gpu/ipu-v3/ipu-cpmem.c +++ b/drivers/gpu/ipu-v3/ipu-cpmem.c @@ -788,12 +788,14 @@ int ipu_cpmem_set_image(struct ipuv3_channel *ch, struct ipu_image *image) case V4L2_PIX_FMT_SGBRG8: case V4L2_PIX_FMT_SGRBG8: case V4L2_PIX_FMT_SRGGB8: + case V4L2_PIX_FMT_GREY: offset = image->rect.left + image->rect.top * pix->bytesperline; break; case V4L2_PIX_FMT_SBGGR16: case V4L2_PIX_FMT_SGBRG16: case V4L2_PIX_FMT_SGRBG16: case V4L2_PIX_FMT_SRGGB16: + case V4L2_PIX_FMT_Y16: offset = image->rect.left * 2 + image->rect.top * pix->bytesperline; break; diff --git a/drivers/gpu/ipu-v3/ipu-csi.c b/drivers/gpu/ipu-v3/ipu-csi.c index 24e12b87a0cb..caa05b0702e1 100644 --- a/drivers/gpu/ipu-v3/ipu-csi.c +++ b/drivers/gpu/ipu-v3/ipu-csi.c @@ -288,6 +288,7 @@ static int mbus_code_to_bus_cfg(struct ipu_csi_bus_config *cfg, u32 mbus_code) case MEDIA_BUS_FMT_SGBRG10_1X10: case MEDIA_BUS_FMT_SGRBG10_1X10: case MEDIA_BUS_FMT_SRGGB10_1X10: + case MEDIA_BUS_FMT_Y10_1X10: cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_BAYER; cfg->mipi_dt = MIPI_DT_RAW10; cfg->data_width = IPU_CSI_DATA_WIDTH_10; @@ -296,6 +297,7 @@ static int mbus_code_to_bus_cfg(struct ipu_csi_bus_config *cfg, u32 mbus_code) case MEDIA_BUS_FMT_SGBRG12_1X12: case MEDIA_BUS_FMT_SGRBG12_1X12: case MEDIA_BUS_FMT_SRGGB12_1X12: + case MEDIA_BUS_FMT_Y12_1X12: cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_BAYER; cfg->mipi_dt = MIPI_DT_RAW12; cfg->data_width = IPU_CSI_DATA_WIDTH_12; diff --git a/drivers/gpu/ipu-v3/ipu-pre.c b/drivers/gpu/ipu-v3/ipu-pre.c index f1cec3d70498..0f70e8847540 100644 --- a/drivers/gpu/ipu-v3/ipu-pre.c +++ b/drivers/gpu/ipu-v3/ipu-pre.c @@ -129,11 +129,14 @@ ipu_pre_lookup_by_phandle(struct device *dev, const char *name, int index) if (pre_node == pre->dev->of_node) { mutex_unlock(&ipu_pre_list_mutex); device_link_add(dev, pre->dev, DL_FLAG_AUTOREMOVE); + of_node_put(pre_node); return pre; } } mutex_unlock(&ipu_pre_list_mutex); + of_node_put(pre_node); + return NULL; } diff --git a/drivers/gpu/ipu-v3/ipu-prg.c b/drivers/gpu/ipu-v3/ipu-prg.c index 067365c733c6..97b99500153d 100644 --- a/drivers/gpu/ipu-v3/ipu-prg.c +++ b/drivers/gpu/ipu-v3/ipu-prg.c @@ -102,11 +102,14 @@ ipu_prg_lookup_by_phandle(struct device *dev, const char *name, int ipu_id) mutex_unlock(&ipu_prg_list_mutex); device_link_add(dev, prg->dev, DL_FLAG_AUTOREMOVE); prg->id = ipu_id; + of_node_put(prg_node); return prg; } } mutex_unlock(&ipu_prg_list_mutex); + of_node_put(prg_node); + return NULL; } diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 43ddcdfbd0da..9454ac134ce2 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -645,6 +645,9 @@ #define USB_DEVICE_ID_LD_MICROCASSYTIME 0x1033 #define USB_DEVICE_ID_LD_MICROCASSYTEMPERATURE 0x1035 #define USB_DEVICE_ID_LD_MICROCASSYPH 0x1038 +#define USB_DEVICE_ID_LD_POWERANALYSERCASSY 0x1040 +#define USB_DEVICE_ID_LD_CONVERTERCONTROLLERCASSY 0x1042 +#define USB_DEVICE_ID_LD_MACHINETESTCASSY 0x1043 #define USB_DEVICE_ID_LD_JWM 0x1080 #define USB_DEVICE_ID_LD_DMMP 0x1081 #define USB_DEVICE_ID_LD_UMIP 0x1090 diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index 5f6035a5ce36..e92b77fa574a 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -809,6 +809,9 @@ static const struct hid_device_id hid_ignore_list[] = { { HID_USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_MICROCASSYTIME) }, { HID_USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_MICROCASSYTEMPERATURE) }, { HID_USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_MICROCASSYPH) }, + { HID_USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_POWERANALYSERCASSY) }, + { HID_USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_CONVERTERCONTROLLERCASSY) }, + { HID_USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_MACHINETESTCASSY) }, { HID_USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_JWM) }, { HID_USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_DMMP) }, { HID_USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_UMIP) }, diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c index 4bdbf77f7197..72c338eb5fae 100644 --- a/drivers/hwmon/coretemp.c +++ b/drivers/hwmon/coretemp.c @@ -269,13 +269,13 @@ static int adjust_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev) for (i = 0; i < ARRAY_SIZE(tjmax_model_table); i++) { const struct tjmax_model *tm = &tjmax_model_table[i]; if (c->x86_model == tm->model && - (tm->mask == ANY || c->x86_mask == tm->mask)) + (tm->mask == ANY || c->x86_stepping == tm->mask)) return tm->tjmax; } /* Early chips have no MSR for TjMax */ - if (c->x86_model == 0xf && c->x86_mask < 4) + if (c->x86_model == 0xf && c->x86_stepping < 4) usemsr_ee = 0; if (c->x86_model > 0xe && usemsr_ee) { @@ -426,7 +426,7 @@ static int chk_ucode_version(unsigned int cpu) * Readings might stop update when processor visited too deep sleep, * fixed for stepping D0 (6EC). */ - if (c->x86_model == 0xe && c->x86_mask < 0xc && c->microcode < 0x39) { + if (c->x86_model == 0xe && c->x86_stepping < 0xc && c->microcode < 0x39) { pr_err("Errata AE18 not fixed, update BIOS or microcode of the CPU!\n"); return -ENODEV; } diff --git a/drivers/hwmon/hwmon-vid.c b/drivers/hwmon/hwmon-vid.c index ef91b8a67549..84e91286fc4f 100644 --- a/drivers/hwmon/hwmon-vid.c +++ b/drivers/hwmon/hwmon-vid.c @@ -293,7 +293,7 @@ u8 vid_which_vrm(void) if (c->x86 < 6) /* Any CPU with family lower than 6 */ return 0; /* doesn't have VID */ - vrm_ret = find_vrm(c->x86, c->x86_model, c->x86_mask, c->x86_vendor); + vrm_ret = find_vrm(c->x86, c->x86_model, c->x86_stepping, c->x86_vendor); if (vrm_ret == 134) vrm_ret = get_via_model_d_vrm(); if (vrm_ret == 0) diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c index 06b4e1c78bd8..051a72eecb24 100644 --- a/drivers/hwmon/k10temp.c +++ b/drivers/hwmon/k10temp.c @@ -129,7 +129,10 @@ static ssize_t temp1_input_show(struct device *dev, data->read_tempreg(data->pdev, ®val); temp = (regval >> 21) * 125; - temp -= data->temp_offset; + if (temp > data->temp_offset) + temp -= data->temp_offset; + else + temp = 0; return sprintf(buf, "%u\n", temp); } @@ -227,7 +230,7 @@ static bool has_erratum_319(struct pci_dev *pdev) * and AM3 formats, but that's the best we can do. */ return boot_cpu_data.x86_model < 4 || - (boot_cpu_data.x86_model == 4 && boot_cpu_data.x86_mask <= 2); + (boot_cpu_data.x86_model == 4 && boot_cpu_data.x86_stepping <= 2); } static int k10temp_probe(struct pci_dev *pdev, diff --git a/drivers/hwmon/k8temp.c b/drivers/hwmon/k8temp.c index 5a632bcf869b..e59f9113fb93 100644 --- a/drivers/hwmon/k8temp.c +++ b/drivers/hwmon/k8temp.c @@ -187,7 +187,7 @@ static int k8temp_probe(struct pci_dev *pdev, return -ENOMEM; model = boot_cpu_data.x86_model; - stepping = boot_cpu_data.x86_mask; + stepping = boot_cpu_data.x86_stepping; /* feature available since SH-C0, exclude older revisions */ if ((model == 4 && stepping == 0) || diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index a9805c7cb305..e2954fb86d65 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -123,8 +123,10 @@ config I2C_I801 Wildcat Point (PCH) Wildcat Point-LP (PCH) BayTrail (SOC) + Braswell (SOC) Sunrise Point-H (PCH) Sunrise Point-LP (PCH) + Kaby Lake-H (PCH) DNV (SOC) Broxton (SOC) Lewisburg (PCH) diff --git a/drivers/i2c/busses/i2c-bcm2835.c b/drivers/i2c/busses/i2c-bcm2835.c index cd07a69e2e93..44deae78913e 100644 --- a/drivers/i2c/busses/i2c-bcm2835.c +++ b/drivers/i2c/busses/i2c-bcm2835.c @@ -50,6 +50,9 @@ #define BCM2835_I2C_S_CLKT BIT(9) #define BCM2835_I2C_S_LEN BIT(10) /* Fake bit for SW error reporting */ +#define BCM2835_I2C_FEDL_SHIFT 16 +#define BCM2835_I2C_REDL_SHIFT 0 + #define BCM2835_I2C_CDIV_MIN 0x0002 #define BCM2835_I2C_CDIV_MAX 0xFFFE @@ -81,7 +84,7 @@ static inline u32 bcm2835_i2c_readl(struct bcm2835_i2c_dev *i2c_dev, u32 reg) static int bcm2835_i2c_set_divider(struct bcm2835_i2c_dev *i2c_dev) { - u32 divider; + u32 divider, redl, fedl; divider = DIV_ROUND_UP(clk_get_rate(i2c_dev->clk), i2c_dev->bus_clk_rate); @@ -100,6 +103,22 @@ static int bcm2835_i2c_set_divider(struct bcm2835_i2c_dev *i2c_dev) bcm2835_i2c_writel(i2c_dev, BCM2835_I2C_DIV, divider); + /* + * Number of core clocks to wait after falling edge before + * outputting the next data bit. Note that both FEDL and REDL + * can't be greater than CDIV/2. + */ + fedl = max(divider / 16, 1u); + + /* + * Number of core clocks to wait after rising edge before + * sampling the next incoming data bit. + */ + redl = max(divider / 4, 1u); + + bcm2835_i2c_writel(i2c_dev, BCM2835_I2C_DEL, + (fedl << BCM2835_I2C_FEDL_SHIFT) | + (redl << BCM2835_I2C_REDL_SHIFT)); return 0; } diff --git a/drivers/i2c/busses/i2c-designware-master.c b/drivers/i2c/busses/i2c-designware-master.c index ae691884d071..05732531829f 100644 --- a/drivers/i2c/busses/i2c-designware-master.c +++ b/drivers/i2c/busses/i2c-designware-master.c @@ -209,7 +209,7 @@ static void i2c_dw_xfer_init(struct dw_i2c_dev *dev) i2c_dw_disable_int(dev); /* Enable the adapter */ - __i2c_dw_enable(dev, true); + __i2c_dw_enable_and_wait(dev, true); /* Clear and enable interrupts */ dw_readl(dev, DW_IC_CLR_INTR); @@ -644,7 +644,7 @@ static int i2c_dw_init_recovery_info(struct dw_i2c_dev *dev) gpio = devm_gpiod_get(dev->dev, "scl", GPIOD_OUT_HIGH); if (IS_ERR(gpio)) { r = PTR_ERR(gpio); - if (r == -ENOENT) + if (r == -ENOENT || r == -ENOSYS) return 0; return r; } diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index 8eac00efadc1..692b34125866 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -58,6 +58,7 @@ * Wildcat Point (PCH) 0x8ca2 32 hard yes yes yes * Wildcat Point-LP (PCH) 0x9ca2 32 hard yes yes yes * BayTrail (SOC) 0x0f12 32 hard yes yes yes + * Braswell (SOC) 0x2292 32 hard yes yes yes * Sunrise Point-H (PCH) 0xa123 32 hard yes yes yes * Sunrise Point-LP (PCH) 0x9d23 32 hard yes yes yes * DNV (SOC) 0x19df 32 hard yes yes yes diff --git a/drivers/i2c/busses/i2c-sirf.c b/drivers/i2c/busses/i2c-sirf.c index 2fd8b6d00391..87197ece0f90 100644 --- a/drivers/i2c/busses/i2c-sirf.c +++ b/drivers/i2c/busses/i2c-sirf.c @@ -341,7 +341,7 @@ static int i2c_sirfsoc_probe(struct platform_device *pdev) platform_set_drvdata(pdev, adap); init_completion(&siic->done); - /* Controller Initalisation */ + /* Controller initialisation */ writel(SIRFSOC_I2C_RESET, siic->base + SIRFSOC_I2C_CTRL); while (readl(siic->base + SIRFSOC_I2C_CTRL) & SIRFSOC_I2C_RESET) @@ -369,7 +369,7 @@ static int i2c_sirfsoc_probe(struct platform_device *pdev) * but they start to affect the speed when clock is set to faster * frequencies. * Through the actual tests, use the different user_div value(which - * in the divider formular 'Fio / (Fi2c * user_div)') to adapt + * in the divider formula 'Fio / (Fi2c * user_div)') to adapt * the different ranges of i2c bus clock frequency, to make the SCL * more accurate. */ diff --git a/drivers/iio/adc/aspeed_adc.c b/drivers/iio/adc/aspeed_adc.c index 327a49ba1991..9515ca165dfd 100644 --- a/drivers/iio/adc/aspeed_adc.c +++ b/drivers/iio/adc/aspeed_adc.c @@ -243,7 +243,7 @@ static int aspeed_adc_probe(struct platform_device *pdev) ASPEED_ADC_INIT_POLLING_TIME, ASPEED_ADC_INIT_TIMEOUT); if (ret) - goto scaler_error; + goto poll_timeout_error; } /* Start all channels in normal mode. */ @@ -274,9 +274,10 @@ iio_register_error: writel(ASPEED_OPERATION_MODE_POWER_DOWN, data->base + ASPEED_REG_ENGINE_CONTROL); clk_disable_unprepare(data->clk_scaler->clk); -reset_error: - reset_control_assert(data->rst); clk_enable_error: +poll_timeout_error: + reset_control_assert(data->rst); +reset_error: clk_hw_unregister_divider(data->clk_scaler); scaler_error: clk_hw_unregister_divider(data->clk_prescaler); diff --git a/drivers/iio/adc/stm32-adc.c b/drivers/iio/adc/stm32-adc.c index 7f5def465340..9a2583caedaa 100644 --- a/drivers/iio/adc/stm32-adc.c +++ b/drivers/iio/adc/stm32-adc.c @@ -722,8 +722,6 @@ static int stm32h7_adc_enable(struct stm32_adc *adc) int ret; u32 val; - /* Clear ADRDY by writing one, then enable ADC */ - stm32_adc_set_bits(adc, STM32H7_ADC_ISR, STM32H7_ADRDY); stm32_adc_set_bits(adc, STM32H7_ADC_CR, STM32H7_ADEN); /* Poll for ADRDY to be set (after adc startup time) */ @@ -731,8 +729,11 @@ static int stm32h7_adc_enable(struct stm32_adc *adc) val & STM32H7_ADRDY, 100, STM32_ADC_TIMEOUT_US); if (ret) { - stm32_adc_clr_bits(adc, STM32H7_ADC_CR, STM32H7_ADEN); + stm32_adc_set_bits(adc, STM32H7_ADC_CR, STM32H7_ADDIS); dev_err(&indio_dev->dev, "Failed to enable ADC\n"); + } else { + /* Clear ADRDY by writing one */ + stm32_adc_set_bits(adc, STM32H7_ADC_ISR, STM32H7_ADRDY); } return ret; diff --git a/drivers/iio/imu/adis_trigger.c b/drivers/iio/imu/adis_trigger.c index 0dd5a381be64..457372f36791 100644 --- a/drivers/iio/imu/adis_trigger.c +++ b/drivers/iio/imu/adis_trigger.c @@ -46,6 +46,10 @@ int adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev) if (adis->trig == NULL) return -ENOMEM; + adis->trig->dev.parent = &adis->spi->dev; + adis->trig->ops = &adis_trigger_ops; + iio_trigger_set_drvdata(adis->trig, adis); + ret = request_irq(adis->spi->irq, &iio_trigger_generic_data_rdy_poll, IRQF_TRIGGER_RISING, @@ -54,9 +58,6 @@ int adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev) if (ret) goto error_free_trig; - adis->trig->dev.parent = &adis->spi->dev; - adis->trig->ops = &adis_trigger_ops; - iio_trigger_set_drvdata(adis->trig, adis); ret = iio_trigger_register(adis->trig); indio_dev->trig = iio_trigger_get(adis->trig); diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c index 79abf70a126d..cd5bfe39591b 100644 --- a/drivers/iio/industrialio-buffer.c +++ b/drivers/iio/industrialio-buffer.c @@ -175,7 +175,7 @@ __poll_t iio_buffer_poll(struct file *filp, struct iio_dev *indio_dev = filp->private_data; struct iio_buffer *rb = indio_dev->buffer; - if (!indio_dev->info) + if (!indio_dev->info || rb == NULL) return 0; poll_wait(filp, &rb->pollq, wait); diff --git a/drivers/iio/proximity/Kconfig b/drivers/iio/proximity/Kconfig index fcb1c4ba5e41..f726f9427602 100644 --- a/drivers/iio/proximity/Kconfig +++ b/drivers/iio/proximity/Kconfig @@ -68,6 +68,8 @@ config SX9500 config SRF08 tristate "Devantech SRF02/SRF08/SRF10 ultrasonic ranger sensor" + select IIO_BUFFER + select IIO_TRIGGERED_BUFFER depends on I2C help Say Y here to build a driver for Devantech SRF02/SRF08/SRF10 diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index e66963ca58bd..3ae32d1ddd27 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -4549,6 +4549,7 @@ static struct pernet_operations cma_pernet_operations = { .exit = cma_exit_net, .id = &cma_pernet_id, .size = sizeof(struct cma_pernet), + .async = true, }; static int __init cma_init(void) diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h index c4560d84dfae..25bb178f6074 100644 --- a/drivers/infiniband/core/core_priv.h +++ b/drivers/infiniband/core/core_priv.h @@ -305,16 +305,21 @@ void nldev_exit(void); static inline struct ib_qp *_ib_create_qp(struct ib_device *dev, struct ib_pd *pd, struct ib_qp_init_attr *attr, - struct ib_udata *udata) + struct ib_udata *udata, + struct ib_uobject *uobj) { struct ib_qp *qp; + if (!dev->create_qp) + return ERR_PTR(-EOPNOTSUPP); + qp = dev->create_qp(pd, attr, udata); if (IS_ERR(qp)) return qp; qp->device = dev; qp->pd = pd; + qp->uobject = uobj; /* * We don't track XRC QPs for now, because they don't have PD * and more importantly they are created internaly by driver, diff --git a/drivers/infiniband/core/rdma_core.c b/drivers/infiniband/core/rdma_core.c index 85b5ee4defa4..d8eead5d106d 100644 --- a/drivers/infiniband/core/rdma_core.c +++ b/drivers/infiniband/core/rdma_core.c @@ -141,7 +141,12 @@ static struct ib_uobject *alloc_uobj(struct ib_ucontext *context, */ uobj->context = context; uobj->type = type; - atomic_set(&uobj->usecnt, 0); + /* + * Allocated objects start out as write locked to deny any other + * syscalls from accessing them until they are committed. See + * rdma_alloc_commit_uobject + */ + atomic_set(&uobj->usecnt, -1); kref_init(&uobj->ref); return uobj; @@ -196,7 +201,15 @@ static struct ib_uobject *lookup_get_idr_uobject(const struct uverbs_obj_type *t goto free; } - uverbs_uobject_get(uobj); + /* + * The idr_find is guaranteed to return a pointer to something that + * isn't freed yet, or NULL, as the free after idr_remove goes through + * kfree_rcu(). However the object may still have been released and + * kfree() could be called at any time. + */ + if (!kref_get_unless_zero(&uobj->ref)) + uobj = ERR_PTR(-ENOENT); + free: rcu_read_unlock(); return uobj; @@ -399,13 +412,13 @@ static int __must_check remove_commit_fd_uobject(struct ib_uobject *uobj, return ret; } -static void lockdep_check(struct ib_uobject *uobj, bool exclusive) +static void assert_uverbs_usecnt(struct ib_uobject *uobj, bool exclusive) { #ifdef CONFIG_LOCKDEP if (exclusive) - WARN_ON(atomic_read(&uobj->usecnt) > 0); + WARN_ON(atomic_read(&uobj->usecnt) != -1); else - WARN_ON(atomic_read(&uobj->usecnt) == -1); + WARN_ON(atomic_read(&uobj->usecnt) <= 0); #endif } @@ -444,7 +457,7 @@ int __must_check rdma_remove_commit_uobject(struct ib_uobject *uobj) WARN(true, "ib_uverbs: Cleanup is running while removing an uobject\n"); return 0; } - lockdep_check(uobj, true); + assert_uverbs_usecnt(uobj, true); ret = _rdma_remove_commit_uobject(uobj, RDMA_REMOVE_DESTROY); up_read(&ucontext->cleanup_rwsem); @@ -474,16 +487,17 @@ int rdma_explicit_destroy(struct ib_uobject *uobject) WARN(true, "ib_uverbs: Cleanup is running while removing an uobject\n"); return 0; } - lockdep_check(uobject, true); + assert_uverbs_usecnt(uobject, true); ret = uobject->type->type_class->remove_commit(uobject, RDMA_REMOVE_DESTROY); if (ret) - return ret; + goto out; uobject->type = &null_obj_type; +out: up_read(&ucontext->cleanup_rwsem); - return 0; + return ret; } static void alloc_commit_idr_uobject(struct ib_uobject *uobj) @@ -527,6 +541,10 @@ int rdma_alloc_commit_uobject(struct ib_uobject *uobj) return ret; } + /* matches atomic_set(-1) in alloc_uobj */ + assert_uverbs_usecnt(uobj, true); + atomic_set(&uobj->usecnt, 0); + uobj->type->type_class->alloc_commit(uobj); up_read(&uobj->context->cleanup_rwsem); @@ -561,7 +579,7 @@ static void lookup_put_fd_uobject(struct ib_uobject *uobj, bool exclusive) void rdma_lookup_put_uobject(struct ib_uobject *uobj, bool exclusive) { - lockdep_check(uobj, exclusive); + assert_uverbs_usecnt(uobj, exclusive); uobj->type->type_class->lookup_put(uobj, exclusive); /* * In order to unlock an object, either decrease its usecnt for diff --git a/drivers/infiniband/core/restrack.c b/drivers/infiniband/core/restrack.c index 857637bf46da..3dbc4e4cca41 100644 --- a/drivers/infiniband/core/restrack.c +++ b/drivers/infiniband/core/restrack.c @@ -7,7 +7,6 @@ #include <rdma/restrack.h> #include <linux/mutex.h> #include <linux/sched/task.h> -#include <linux/uaccess.h> #include <linux/pid_namespace.h> void rdma_restrack_init(struct rdma_restrack_root *res) @@ -63,7 +62,6 @@ static struct ib_device *res_to_dev(struct rdma_restrack_entry *res) { enum rdma_restrack_type type = res->type; struct ib_device *dev; - struct ib_xrcd *xrcd; struct ib_pd *pd; struct ib_cq *cq; struct ib_qp *qp; @@ -81,10 +79,6 @@ static struct ib_device *res_to_dev(struct rdma_restrack_entry *res) qp = container_of(res, struct ib_qp, res); dev = qp->device; break; - case RDMA_RESTRACK_XRCD: - xrcd = container_of(res, struct ib_xrcd, res); - dev = xrcd->device; - break; default: WARN_ONCE(true, "Wrong resource tracking type %u\n", type); return NULL; @@ -93,6 +87,21 @@ static struct ib_device *res_to_dev(struct rdma_restrack_entry *res) return dev; } +static bool res_is_user(struct rdma_restrack_entry *res) +{ + switch (res->type) { + case RDMA_RESTRACK_PD: + return container_of(res, struct ib_pd, res)->uobject; + case RDMA_RESTRACK_CQ: + return container_of(res, struct ib_cq, res)->uobject; + case RDMA_RESTRACK_QP: + return container_of(res, struct ib_qp, res)->uobject; + default: + WARN_ONCE(true, "Wrong resource tracking type %u\n", res->type); + return false; + } +} + void rdma_restrack_add(struct rdma_restrack_entry *res) { struct ib_device *dev = res_to_dev(res); @@ -100,7 +109,7 @@ void rdma_restrack_add(struct rdma_restrack_entry *res) if (!dev) return; - if (!uaccess_kernel()) { + if (res_is_user(res)) { get_task_struct(current); res->task = current; res->kern_name = NULL; diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index 256934d1f64f..a148de35df8d 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -562,9 +562,10 @@ ssize_t ib_uverbs_open_xrcd(struct ib_uverbs_file *file, if (f.file) fdput(f); + mutex_unlock(&file->device->xrcd_tree_mutex); + uobj_alloc_commit(&obj->uobject); - mutex_unlock(&file->device->xrcd_tree_mutex); return in_len; err_copy: @@ -603,10 +604,8 @@ ssize_t ib_uverbs_close_xrcd(struct ib_uverbs_file *file, uobj = uobj_get_write(uobj_get_type(xrcd), cmd.xrcd_handle, file->ucontext); - if (IS_ERR(uobj)) { - mutex_unlock(&file->device->xrcd_tree_mutex); + if (IS_ERR(uobj)) return PTR_ERR(uobj); - } ret = uobj_remove_commit(uobj); return ret ?: in_len; @@ -979,6 +978,9 @@ static struct ib_ucq_object *create_cq(struct ib_uverbs_file *file, struct ib_uverbs_ex_create_cq_resp resp; struct ib_cq_init_attr attr = {}; + if (!ib_dev->create_cq) + return ERR_PTR(-EOPNOTSUPP); + if (cmd->comp_vector >= file->device->num_comp_vectors) return ERR_PTR(-EINVAL); @@ -1030,14 +1032,14 @@ static struct ib_ucq_object *create_cq(struct ib_uverbs_file *file, resp.response_length = offsetof(typeof(resp), response_length) + sizeof(resp.response_length); + cq->res.type = RDMA_RESTRACK_CQ; + rdma_restrack_add(&cq->res); + ret = cb(file, obj, &resp, ucore, context); if (ret) goto err_cb; uobj_alloc_commit(&obj->uobject); - cq->res.type = RDMA_RESTRACK_CQ; - rdma_restrack_add(&cq->res); - return obj; err_cb: @@ -1518,7 +1520,8 @@ static int create_qp(struct ib_uverbs_file *file, if (cmd->qp_type == IB_QPT_XRC_TGT) qp = ib_create_qp(pd, &attr); else - qp = _ib_create_qp(device, pd, &attr, uhw); + qp = _ib_create_qp(device, pd, &attr, uhw, + &obj->uevent.uobject); if (IS_ERR(qp)) { ret = PTR_ERR(qp); @@ -1550,8 +1553,10 @@ static int create_qp(struct ib_uverbs_file *file, atomic_inc(&attr.srq->usecnt); if (ind_tbl) atomic_inc(&ind_tbl->usecnt); + } else { + /* It is done in _ib_create_qp for other QP types */ + qp->uobject = &obj->uevent.uobject; } - qp->uobject = &obj->uevent.uobject; obj->uevent.uobject.object = qp; @@ -1971,8 +1976,15 @@ static int modify_qp(struct ib_uverbs_file *file, goto release_qp; } + if ((cmd->base.attr_mask & IB_QP_AV) && + !rdma_is_port_valid(qp->device, cmd->base.dest.port_num)) { + ret = -EINVAL; + goto release_qp; + } + if ((cmd->base.attr_mask & IB_QP_ALT_PATH) && - !rdma_is_port_valid(qp->device, cmd->base.alt_port_num)) { + (!rdma_is_port_valid(qp->device, cmd->base.alt_port_num) || + !rdma_is_port_valid(qp->device, cmd->base.alt_dest.port_num))) { ret = -EINVAL; goto release_qp; } @@ -2941,6 +2953,11 @@ int ib_uverbs_ex_create_wq(struct ib_uverbs_file *file, wq_init_attr.create_flags = cmd.create_flags; obj->uevent.events_reported = 0; INIT_LIST_HEAD(&obj->uevent.event_list); + + if (!pd->device->create_wq) { + err = -EOPNOTSUPP; + goto err_put_cq; + } wq = pd->device->create_wq(pd, &wq_init_attr, uhw); if (IS_ERR(wq)) { err = PTR_ERR(wq); @@ -3084,7 +3101,12 @@ int ib_uverbs_ex_modify_wq(struct ib_uverbs_file *file, wq_attr.flags = cmd.flags; wq_attr.flags_mask = cmd.flags_mask; } + if (!wq->device->modify_wq) { + ret = -EOPNOTSUPP; + goto out; + } ret = wq->device->modify_wq(wq, &wq_attr, cmd.attr_mask, uhw); +out: uobj_put_obj_read(wq); return ret; } @@ -3181,6 +3203,11 @@ int ib_uverbs_ex_create_rwq_ind_table(struct ib_uverbs_file *file, init_attr.log_ind_tbl_size = cmd.log_ind_tbl_size; init_attr.ind_tbl = wqs; + + if (!ib_dev->create_rwq_ind_table) { + err = -EOPNOTSUPP; + goto err_uobj; + } rwq_ind_tbl = ib_dev->create_rwq_ind_table(ib_dev, &init_attr, uhw); if (IS_ERR(rwq_ind_tbl)) { @@ -3770,6 +3797,9 @@ int ib_uverbs_ex_query_device(struct ib_uverbs_file *file, struct ib_device_attr attr = {0}; int err; + if (!ib_dev->query_device) + return -EOPNOTSUPP; + if (ucore->inlen < sizeof(cmd)) return -EINVAL; diff --git a/drivers/infiniband/core/uverbs_ioctl.c b/drivers/infiniband/core/uverbs_ioctl.c index d96dc1d17be1..339b85145044 100644 --- a/drivers/infiniband/core/uverbs_ioctl.c +++ b/drivers/infiniband/core/uverbs_ioctl.c @@ -59,6 +59,9 @@ static int uverbs_process_attr(struct ib_device *ibdev, return 0; } + if (test_bit(attr_id, attr_bundle_h->valid_bitmap)) + return -EINVAL; + spec = &attr_spec_bucket->attrs[attr_id]; e = &elements[attr_id]; e->uattr = uattr_ptr; diff --git a/drivers/infiniband/core/uverbs_ioctl_merge.c b/drivers/infiniband/core/uverbs_ioctl_merge.c index 062485f9300d..62e1eb1d2a28 100644 --- a/drivers/infiniband/core/uverbs_ioctl_merge.c +++ b/drivers/infiniband/core/uverbs_ioctl_merge.c @@ -114,6 +114,7 @@ static size_t get_elements_above_id(const void **iters, short min = SHRT_MAX; const void *elem; int i, j, last_stored = -1; + unsigned int equal_min = 0; for_each_element(elem, i, j, elements, num_elements, num_offset, data_offset) { @@ -136,6 +137,10 @@ static size_t get_elements_above_id(const void **iters, */ iters[last_stored == i ? num_iters - 1 : num_iters++] = elem; last_stored = i; + if (min == GET_ID(id)) + equal_min++; + else + equal_min = 1; min = GET_ID(id); } @@ -146,15 +151,10 @@ static size_t get_elements_above_id(const void **iters, * Therefore, we need to clean the beginning of the array to make sure * all ids of final elements are equal to min. */ - for (i = num_iters - 1; i >= 0 && - GET_ID(*(u16 *)(iters[i] + id_offset)) == min; i--) - ; - - num_iters -= i + 1; - memmove(iters, iters + i + 1, sizeof(*iters) * num_iters); + memmove(iters, iters + num_iters - equal_min, sizeof(*iters) * equal_min); *min_id = min; - return num_iters; + return equal_min; } #define find_max_element_entry_id(num_elements, elements, num_objects_fld, \ @@ -322,7 +322,7 @@ static struct uverbs_method_spec *build_method_with_attrs(const struct uverbs_me hash = kzalloc(sizeof(*hash) + ALIGN(sizeof(*hash->attrs) * (attr_max_bucket + 1), sizeof(long)) + - BITS_TO_LONGS(attr_max_bucket) * sizeof(long), + BITS_TO_LONGS(attr_max_bucket + 1) * sizeof(long), GFP_KERNEL); if (!hash) { res = -ENOMEM; @@ -509,7 +509,7 @@ static struct uverbs_object_spec *build_object_with_methods(const struct uverbs_ * first handler which != NULL. This also defines the * set of flags used for this handler. */ - for (i = num_object_defs - 1; + for (i = num_method_defs - 1; i >= 0 && !method_defs[i]->handler; i--) ; hash->methods[min_id++] = method; diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 395a3b091229..b1ca223aa380 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -650,12 +650,21 @@ static int verify_command_mask(struct ib_device *ib_dev, __u32 command) return -1; } +static bool verify_command_idx(u32 command, bool extended) +{ + if (extended) + return command < ARRAY_SIZE(uverbs_ex_cmd_table); + + return command < ARRAY_SIZE(uverbs_cmd_table); +} + static ssize_t ib_uverbs_write(struct file *filp, const char __user *buf, size_t count, loff_t *pos) { struct ib_uverbs_file *file = filp->private_data; struct ib_device *ib_dev; struct ib_uverbs_cmd_hdr hdr; + bool extended_command; __u32 command; __u32 flags; int srcu_key; @@ -688,6 +697,15 @@ static ssize_t ib_uverbs_write(struct file *filp, const char __user *buf, } command = hdr.command & IB_USER_VERBS_CMD_COMMAND_MASK; + flags = (hdr.command & + IB_USER_VERBS_CMD_FLAGS_MASK) >> IB_USER_VERBS_CMD_FLAGS_SHIFT; + + extended_command = flags & IB_USER_VERBS_CMD_FLAG_EXTENDED; + if (!verify_command_idx(command, extended_command)) { + ret = -EINVAL; + goto out; + } + if (verify_command_mask(ib_dev, command)) { ret = -EOPNOTSUPP; goto out; @@ -699,12 +717,8 @@ static ssize_t ib_uverbs_write(struct file *filp, const char __user *buf, goto out; } - flags = (hdr.command & - IB_USER_VERBS_CMD_FLAGS_MASK) >> IB_USER_VERBS_CMD_FLAGS_SHIFT; - if (!flags) { - if (command >= ARRAY_SIZE(uverbs_cmd_table) || - !uverbs_cmd_table[command]) { + if (!uverbs_cmd_table[command]) { ret = -EINVAL; goto out; } @@ -725,8 +739,7 @@ static ssize_t ib_uverbs_write(struct file *filp, const char __user *buf, struct ib_udata uhw; size_t written_count = count; - if (command >= ARRAY_SIZE(uverbs_ex_cmd_table) || - !uverbs_ex_cmd_table[command]) { + if (!uverbs_ex_cmd_table[command]) { ret = -ENOSYS; goto out; } @@ -942,6 +955,7 @@ static const struct file_operations uverbs_fops = { .llseek = no_llseek, #if IS_ENABLED(CONFIG_INFINIBAND_EXP_USER_ACCESS) .unlocked_ioctl = ib_uverbs_ioctl, + .compat_ioctl = ib_uverbs_ioctl, #endif }; @@ -954,6 +968,7 @@ static const struct file_operations uverbs_mmap_fops = { .llseek = no_llseek, #if IS_ENABLED(CONFIG_INFINIBAND_EXP_USER_ACCESS) .unlocked_ioctl = ib_uverbs_ioctl, + .compat_ioctl = ib_uverbs_ioctl, #endif }; diff --git a/drivers/infiniband/core/uverbs_std_types.c b/drivers/infiniband/core/uverbs_std_types.c index cab0ac3556eb..df1360e6774f 100644 --- a/drivers/infiniband/core/uverbs_std_types.c +++ b/drivers/infiniband/core/uverbs_std_types.c @@ -234,15 +234,18 @@ static void create_udata(struct uverbs_attr_bundle *ctx, uverbs_attr_get(ctx, UVERBS_UHW_OUT); if (!IS_ERR(uhw_in)) { - udata->inbuf = uhw_in->ptr_attr.ptr; udata->inlen = uhw_in->ptr_attr.len; + if (uverbs_attr_ptr_is_inline(uhw_in)) + udata->inbuf = &uhw_in->uattr->data; + else + udata->inbuf = u64_to_user_ptr(uhw_in->ptr_attr.data); } else { udata->inbuf = NULL; udata->inlen = 0; } if (!IS_ERR(uhw_out)) { - udata->outbuf = uhw_out->ptr_attr.ptr; + udata->outbuf = u64_to_user_ptr(uhw_out->ptr_attr.data); udata->outlen = uhw_out->ptr_attr.len; } else { udata->outbuf = NULL; @@ -323,7 +326,8 @@ static int uverbs_create_cq_handler(struct ib_device *ib_dev, cq->res.type = RDMA_RESTRACK_CQ; rdma_restrack_add(&cq->res); - ret = uverbs_copy_to(attrs, CREATE_CQ_RESP_CQE, &cq->cqe); + ret = uverbs_copy_to(attrs, CREATE_CQ_RESP_CQE, &cq->cqe, + sizeof(cq->cqe)); if (ret) goto err_cq; @@ -375,7 +379,7 @@ static int uverbs_destroy_cq_handler(struct ib_device *ib_dev, resp.comp_events_reported = obj->comp_events_reported; resp.async_events_reported = obj->async_events_reported; - return uverbs_copy_to(attrs, DESTROY_CQ_RESP, &resp); + return uverbs_copy_to(attrs, DESTROY_CQ_RESP, &resp, sizeof(resp)); } static DECLARE_UVERBS_METHOD( diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index 16ebc6372c31..93025d2009b8 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -887,7 +887,7 @@ struct ib_qp *ib_create_qp(struct ib_pd *pd, if (qp_init_attr->cap.max_rdma_ctxs) rdma_rw_init_qp(device, qp_init_attr); - qp = _ib_create_qp(device, pd, qp_init_attr, NULL); + qp = _ib_create_qp(device, pd, qp_init_attr, NULL, NULL); if (IS_ERR(qp)) return qp; @@ -898,7 +898,6 @@ struct ib_qp *ib_create_qp(struct ib_pd *pd, } qp->real_qp = qp; - qp->uobject = NULL; qp->qp_type = qp_init_attr->qp_type; qp->rwq_ind_tbl = qp_init_attr->rwq_ind_tbl; diff --git a/drivers/infiniband/hw/bnxt_re/bnxt_re.h b/drivers/infiniband/hw/bnxt_re/bnxt_re.h index ca32057e886f..3eb7a8387116 100644 --- a/drivers/infiniband/hw/bnxt_re/bnxt_re.h +++ b/drivers/infiniband/hw/bnxt_re/bnxt_re.h @@ -120,7 +120,6 @@ struct bnxt_re_dev { #define BNXT_RE_FLAG_HAVE_L2_REF 3 #define BNXT_RE_FLAG_RCFW_CHANNEL_EN 4 #define BNXT_RE_FLAG_QOS_WORK_REG 5 -#define BNXT_RE_FLAG_TASK_IN_PROG 6 #define BNXT_RE_FLAG_ISSUE_ROCE_STATS 29 struct net_device *netdev; unsigned int version, major, minor; @@ -158,6 +157,7 @@ struct bnxt_re_dev { atomic_t srq_count; atomic_t mr_count; atomic_t mw_count; + atomic_t sched_count; /* Max of 2 lossless traffic class supported per port */ u16 cosq[2]; diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index ae9e9ff54826..643174d949a8 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -174,10 +174,8 @@ int bnxt_re_query_device(struct ib_device *ibdev, ib_attr->max_pd = dev_attr->max_pd; ib_attr->max_qp_rd_atom = dev_attr->max_qp_rd_atom; ib_attr->max_qp_init_rd_atom = dev_attr->max_qp_init_rd_atom; - if (dev_attr->is_atomic) { - ib_attr->atomic_cap = IB_ATOMIC_HCA; - ib_attr->masked_atomic_cap = IB_ATOMIC_HCA; - } + ib_attr->atomic_cap = IB_ATOMIC_NONE; + ib_attr->masked_atomic_cap = IB_ATOMIC_NONE; ib_attr->max_ee_rd_atom = 0; ib_attr->max_res_rd_atom = 0; @@ -787,20 +785,51 @@ int bnxt_re_query_ah(struct ib_ah *ib_ah, struct rdma_ah_attr *ah_attr) return 0; } +static unsigned long bnxt_re_lock_cqs(struct bnxt_re_qp *qp) + __acquires(&qp->scq->cq_lock) __acquires(&qp->rcq->cq_lock) +{ + unsigned long flags; + + spin_lock_irqsave(&qp->scq->cq_lock, flags); + if (qp->rcq != qp->scq) + spin_lock(&qp->rcq->cq_lock); + else + __acquire(&qp->rcq->cq_lock); + + return flags; +} + +static void bnxt_re_unlock_cqs(struct bnxt_re_qp *qp, + unsigned long flags) + __releases(&qp->scq->cq_lock) __releases(&qp->rcq->cq_lock) +{ + if (qp->rcq != qp->scq) + spin_unlock(&qp->rcq->cq_lock); + else + __release(&qp->rcq->cq_lock); + spin_unlock_irqrestore(&qp->scq->cq_lock, flags); +} + /* Queue Pairs */ int bnxt_re_destroy_qp(struct ib_qp *ib_qp) { struct bnxt_re_qp *qp = container_of(ib_qp, struct bnxt_re_qp, ib_qp); struct bnxt_re_dev *rdev = qp->rdev; int rc; + unsigned int flags; bnxt_qplib_flush_cqn_wq(&qp->qplib_qp); - bnxt_qplib_del_flush_qp(&qp->qplib_qp); rc = bnxt_qplib_destroy_qp(&rdev->qplib_res, &qp->qplib_qp); if (rc) { dev_err(rdev_to_dev(rdev), "Failed to destroy HW QP"); return rc; } + + flags = bnxt_re_lock_cqs(qp); + bnxt_qplib_clean_qp(&qp->qplib_qp); + bnxt_re_unlock_cqs(qp, flags); + bnxt_qplib_free_qp_res(&rdev->qplib_res, &qp->qplib_qp); + if (ib_qp->qp_type == IB_QPT_GSI && rdev->qp1_sqp) { rc = bnxt_qplib_destroy_ah(&rdev->qplib_res, &rdev->sqp_ah->qplib_ah); @@ -810,7 +839,7 @@ int bnxt_re_destroy_qp(struct ib_qp *ib_qp) return rc; } - bnxt_qplib_del_flush_qp(&qp->qplib_qp); + bnxt_qplib_clean_qp(&qp->qplib_qp); rc = bnxt_qplib_destroy_qp(&rdev->qplib_res, &rdev->qp1_sqp->qplib_qp); if (rc) { @@ -1069,6 +1098,7 @@ struct ib_qp *bnxt_re_create_qp(struct ib_pd *ib_pd, goto fail; } qp->qplib_qp.scq = &cq->qplib_cq; + qp->scq = cq; } if (qp_init_attr->recv_cq) { @@ -1080,6 +1110,7 @@ struct ib_qp *bnxt_re_create_qp(struct ib_pd *ib_pd, goto fail; } qp->qplib_qp.rcq = &cq->qplib_cq; + qp->rcq = cq; } if (qp_init_attr->srq) { @@ -1185,7 +1216,7 @@ struct ib_qp *bnxt_re_create_qp(struct ib_pd *ib_pd, rc = bnxt_qplib_create_qp(&rdev->qplib_res, &qp->qplib_qp); if (rc) { dev_err(rdev_to_dev(rdev), "Failed to create HW QP"); - goto fail; + goto free_umem; } } @@ -1213,6 +1244,13 @@ struct ib_qp *bnxt_re_create_qp(struct ib_pd *ib_pd, return &qp->ib_qp; qp_destroy: bnxt_qplib_destroy_qp(&rdev->qplib_res, &qp->qplib_qp); +free_umem: + if (udata) { + if (qp->rumem) + ib_umem_release(qp->rumem); + if (qp->sumem) + ib_umem_release(qp->sumem); + } fail: kfree(qp); return ERR_PTR(rc); @@ -1603,7 +1641,7 @@ int bnxt_re_modify_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr, dev_dbg(rdev_to_dev(rdev), "Move QP = %p out of flush list\n", qp); - bnxt_qplib_del_flush_qp(&qp->qplib_qp); + bnxt_qplib_clean_qp(&qp->qplib_qp); } } if (qp_attr_mask & IB_QP_EN_SQD_ASYNC_NOTIFY) { diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.h b/drivers/infiniband/hw/bnxt_re/ib_verbs.h index 423ebe012f95..b88a48d43a9d 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.h +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.h @@ -89,6 +89,8 @@ struct bnxt_re_qp { /* QP1 */ u32 send_psn; struct ib_ud_header qp1_hdr; + struct bnxt_re_cq *scq; + struct bnxt_re_cq *rcq; }; struct bnxt_re_cq { diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index 508d00a5a106..33a448036c2e 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -656,7 +656,6 @@ static void bnxt_re_dev_remove(struct bnxt_re_dev *rdev) mutex_unlock(&bnxt_re_dev_lock); synchronize_rcu(); - flush_workqueue(bnxt_re_wq); ib_dealloc_device(&rdev->ibdev); /* rdev is gone */ @@ -1441,7 +1440,7 @@ static void bnxt_re_task(struct work_struct *work) break; } smp_mb__before_atomic(); - clear_bit(BNXT_RE_FLAG_TASK_IN_PROG, &rdev->flags); + atomic_dec(&rdev->sched_count); kfree(re_work); } @@ -1503,7 +1502,7 @@ static int bnxt_re_netdev_event(struct notifier_block *notifier, /* netdev notifier will call NETDEV_UNREGISTER again later since * we are still holding the reference to the netdev */ - if (test_bit(BNXT_RE_FLAG_TASK_IN_PROG, &rdev->flags)) + if (atomic_read(&rdev->sched_count) > 0) goto exit; bnxt_re_ib_unreg(rdev, false); bnxt_re_remove_one(rdev); @@ -1523,7 +1522,7 @@ static int bnxt_re_netdev_event(struct notifier_block *notifier, re_work->vlan_dev = (real_dev == netdev ? NULL : netdev); INIT_WORK(&re_work->work, bnxt_re_task); - set_bit(BNXT_RE_FLAG_TASK_IN_PROG, &rdev->flags); + atomic_inc(&rdev->sched_count); queue_work(bnxt_re_wq, &re_work->work); } } @@ -1578,6 +1577,11 @@ static void __exit bnxt_re_mod_exit(void) */ list_for_each_entry_safe_reverse(rdev, next, &to_be_deleted, list) { dev_info(rdev_to_dev(rdev), "Unregistering Device"); + /* + * Flush out any scheduled tasks before destroying the + * resources + */ + flush_workqueue(bnxt_re_wq); bnxt_re_dev_stop(rdev); bnxt_re_ib_unreg(rdev, true); bnxt_re_remove_one(rdev); diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index 1b0e94697fe3..3ea5b9624f6b 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -173,7 +173,7 @@ static void __bnxt_qplib_del_flush_qp(struct bnxt_qplib_qp *qp) } } -void bnxt_qplib_del_flush_qp(struct bnxt_qplib_qp *qp) +void bnxt_qplib_clean_qp(struct bnxt_qplib_qp *qp) { unsigned long flags; @@ -1419,7 +1419,6 @@ int bnxt_qplib_destroy_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_rcfw *rcfw = res->rcfw; struct cmdq_destroy_qp req; struct creq_destroy_qp_resp resp; - unsigned long flags; u16 cmd_flags = 0; int rc; @@ -1437,19 +1436,12 @@ int bnxt_qplib_destroy_qp(struct bnxt_qplib_res *res, return rc; } - /* Must walk the associated CQs to nullified the QP ptr */ - spin_lock_irqsave(&qp->scq->hwq.lock, flags); - - __clean_cq(qp->scq, (u64)(unsigned long)qp); - - if (qp->rcq && qp->rcq != qp->scq) { - spin_lock(&qp->rcq->hwq.lock); - __clean_cq(qp->rcq, (u64)(unsigned long)qp); - spin_unlock(&qp->rcq->hwq.lock); - } - - spin_unlock_irqrestore(&qp->scq->hwq.lock, flags); + return 0; +} +void bnxt_qplib_free_qp_res(struct bnxt_qplib_res *res, + struct bnxt_qplib_qp *qp) +{ bnxt_qplib_free_qp_hdr_buf(res, qp); bnxt_qplib_free_hwq(res->pdev, &qp->sq.hwq); kfree(qp->sq.swq); @@ -1462,7 +1454,6 @@ int bnxt_qplib_destroy_qp(struct bnxt_qplib_res *res, if (qp->orrq.max_elements) bnxt_qplib_free_hwq(res->pdev, &qp->orrq); - return 0; } void *bnxt_qplib_get_qp1_sq_buf(struct bnxt_qplib_qp *qp, diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.h b/drivers/infiniband/hw/bnxt_re/qplib_fp.h index 211b27a8f9e2..ca0a2ffa3509 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.h @@ -478,6 +478,9 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp); int bnxt_qplib_modify_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp); int bnxt_qplib_query_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp); int bnxt_qplib_destroy_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp); +void bnxt_qplib_clean_qp(struct bnxt_qplib_qp *qp); +void bnxt_qplib_free_qp_res(struct bnxt_qplib_res *res, + struct bnxt_qplib_qp *qp); void *bnxt_qplib_get_qp1_sq_buf(struct bnxt_qplib_qp *qp, struct bnxt_qplib_sge *sge); void *bnxt_qplib_get_qp1_rq_buf(struct bnxt_qplib_qp *qp, @@ -500,7 +503,6 @@ void bnxt_qplib_req_notify_cq(struct bnxt_qplib_cq *cq, u32 arm_type); void bnxt_qplib_free_nq(struct bnxt_qplib_nq *nq); int bnxt_qplib_alloc_nq(struct pci_dev *pdev, struct bnxt_qplib_nq *nq); void bnxt_qplib_add_flush_qp(struct bnxt_qplib_qp *qp); -void bnxt_qplib_del_flush_qp(struct bnxt_qplib_qp *qp); void bnxt_qplib_acquire_cq_locks(struct bnxt_qplib_qp *qp, unsigned long *flags); void bnxt_qplib_release_cq_locks(struct bnxt_qplib_qp *qp, diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c index c015c1861351..03057983341f 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c @@ -52,18 +52,6 @@ const struct bnxt_qplib_gid bnxt_qplib_gid_zero = {{ 0, 0, 0, 0, 0, 0, 0, 0, /* Device */ -static bool bnxt_qplib_is_atomic_cap(struct bnxt_qplib_rcfw *rcfw) -{ - int rc; - u16 pcie_ctl2; - - rc = pcie_capability_read_word(rcfw->pdev, PCI_EXP_DEVCTL2, - &pcie_ctl2); - if (rc) - return false; - return !!(pcie_ctl2 & PCI_EXP_DEVCTL2_ATOMIC_REQ); -} - static void bnxt_qplib_query_version(struct bnxt_qplib_rcfw *rcfw, char *fw_ver) { @@ -165,7 +153,7 @@ int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw, attr->tqm_alloc_reqs[i * 4 + 3] = *(++tqm_alloc); } - attr->is_atomic = bnxt_qplib_is_atomic_cap(rcfw); + attr->is_atomic = 0; bail: bnxt_qplib_rcfw_free_sbuf(rcfw, sbuf); return rc; diff --git a/drivers/infiniband/hw/usnic/usnic_transport.c b/drivers/infiniband/hw/usnic/usnic_transport.c index de318389a301..67de94343cb4 100644 --- a/drivers/infiniband/hw/usnic/usnic_transport.c +++ b/drivers/infiniband/hw/usnic/usnic_transport.c @@ -174,14 +174,13 @@ void usnic_transport_put_socket(struct socket *sock) int usnic_transport_sock_get_addr(struct socket *sock, int *proto, uint32_t *addr, uint16_t *port) { - int len; int err; struct sockaddr_in sock_addr; err = sock->ops->getname(sock, (struct sockaddr *)&sock_addr, - &len, 0); - if (err) + 0); + if (err < 0) return err; if (sock_addr.sin_family != AF_INET) diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c index faa9478c14a6..f95b97646c25 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c @@ -114,6 +114,7 @@ struct ib_cq *pvrdma_create_cq(struct ib_device *ibdev, union pvrdma_cmd_resp rsp; struct pvrdma_cmd_create_cq *cmd = &req.create_cq; struct pvrdma_cmd_create_cq_resp *resp = &rsp.create_cq_resp; + struct pvrdma_create_cq_resp cq_resp = {0}; struct pvrdma_create_cq ucmd; BUILD_BUG_ON(sizeof(struct pvrdma_cqe) != 64); @@ -197,6 +198,7 @@ struct ib_cq *pvrdma_create_cq(struct ib_device *ibdev, cq->ibcq.cqe = resp->cqe; cq->cq_handle = resp->cq_handle; + cq_resp.cqn = resp->cq_handle; spin_lock_irqsave(&dev->cq_tbl_lock, flags); dev->cq_tbl[cq->cq_handle % dev->dsr->caps.max_cq] = cq; spin_unlock_irqrestore(&dev->cq_tbl_lock, flags); @@ -205,7 +207,7 @@ struct ib_cq *pvrdma_create_cq(struct ib_device *ibdev, cq->uar = &(to_vucontext(context)->uar); /* Copy udata back. */ - if (ib_copy_to_udata(udata, &cq->cq_handle, sizeof(__u32))) { + if (ib_copy_to_udata(udata, &cq_resp, sizeof(cq_resp))) { dev_warn(&dev->pdev->dev, "failed to copy back udata\n"); pvrdma_destroy_cq(&cq->ibcq); diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c index 5acebb1ef631..af235967a9c2 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c @@ -113,6 +113,7 @@ struct ib_srq *pvrdma_create_srq(struct ib_pd *pd, union pvrdma_cmd_resp rsp; struct pvrdma_cmd_create_srq *cmd = &req.create_srq; struct pvrdma_cmd_create_srq_resp *resp = &rsp.create_srq_resp; + struct pvrdma_create_srq_resp srq_resp = {0}; struct pvrdma_create_srq ucmd; unsigned long flags; int ret; @@ -204,12 +205,13 @@ struct ib_srq *pvrdma_create_srq(struct ib_pd *pd, } srq->srq_handle = resp->srqn; + srq_resp.srqn = resp->srqn; spin_lock_irqsave(&dev->srq_tbl_lock, flags); dev->srq_tbl[srq->srq_handle % dev->dsr->caps.max_srq] = srq; spin_unlock_irqrestore(&dev->srq_tbl_lock, flags); /* Copy udata back. */ - if (ib_copy_to_udata(udata, &srq->srq_handle, sizeof(__u32))) { + if (ib_copy_to_udata(udata, &srq_resp, sizeof(srq_resp))) { dev_warn(&dev->pdev->dev, "failed to copy back udata\n"); pvrdma_destroy_srq(&srq->ibsrq); return ERR_PTR(-EINVAL); diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c index 16b96616ef7e..a51463cd2f37 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c @@ -447,6 +447,7 @@ struct ib_pd *pvrdma_alloc_pd(struct ib_device *ibdev, union pvrdma_cmd_resp rsp; struct pvrdma_cmd_create_pd *cmd = &req.create_pd; struct pvrdma_cmd_create_pd_resp *resp = &rsp.create_pd_resp; + struct pvrdma_alloc_pd_resp pd_resp = {0}; int ret; void *ptr; @@ -475,9 +476,10 @@ struct ib_pd *pvrdma_alloc_pd(struct ib_device *ibdev, pd->privileged = !context; pd->pd_handle = resp->pd_handle; pd->pdn = resp->pd_handle; + pd_resp.pdn = resp->pd_handle; if (context) { - if (ib_copy_to_udata(udata, &pd->pdn, sizeof(__u32))) { + if (ib_copy_to_udata(udata, &pd_resp, sizeof(pd_resp))) { dev_warn(&dev->pdev->dev, "failed to copy back protection domain\n"); pvrdma_dealloc_pd(&pd->ibpd); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_fs.c b/drivers/infiniband/ulp/ipoib/ipoib_fs.c index 11f74cbe6660..ea302b054601 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_fs.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_fs.c @@ -281,8 +281,6 @@ void ipoib_delete_debug_files(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); - WARN_ONCE(!priv->mcg_dentry, "null mcg debug file\n"); - WARN_ONCE(!priv->path_dentry, "null path debug file\n"); debugfs_remove(priv->mcg_dentry); debugfs_remove(priv->path_dentry); priv->mcg_dentry = priv->path_dentry = NULL; diff --git a/drivers/irqchip/irq-bcm7038-l1.c b/drivers/irqchip/irq-bcm7038-l1.c index 55cfb986225b..faf734ff4cf3 100644 --- a/drivers/irqchip/irq-bcm7038-l1.c +++ b/drivers/irqchip/irq-bcm7038-l1.c @@ -339,9 +339,6 @@ int __init bcm7038_l1_of_init(struct device_node *dn, goto out_unmap; } - pr_info("registered BCM7038 L1 intc (mem: 0x%p, IRQs: %d)\n", - intc->cpus[0]->map_base, IRQS_PER_WORD * intc->n_words); - return 0; out_unmap: diff --git a/drivers/irqchip/irq-bcm7120-l2.c b/drivers/irqchip/irq-bcm7120-l2.c index 983640eba418..8968e5e93fcb 100644 --- a/drivers/irqchip/irq-bcm7120-l2.c +++ b/drivers/irqchip/irq-bcm7120-l2.c @@ -318,9 +318,6 @@ static int __init bcm7120_l2_intc_probe(struct device_node *dn, } } - pr_info("registered %s intc (mem: 0x%p, parent IRQ(s): %d)\n", - intc_name, data->map_base[0], data->num_parent_irqs); - return 0; out_free_domain: diff --git a/drivers/irqchip/irq-brcmstb-l2.c b/drivers/irqchip/irq-brcmstb-l2.c index 691d20eb0bec..0e65f609352e 100644 --- a/drivers/irqchip/irq-brcmstb-l2.c +++ b/drivers/irqchip/irq-brcmstb-l2.c @@ -262,9 +262,6 @@ static int __init brcmstb_l2_intc_of_init(struct device_node *np, ct->chip.irq_set_wake = irq_gc_set_wake; } - pr_info("registered L2 intc (mem: 0x%p, parent irq: %d)\n", - base, parent_irq); - return 0; out_free_domain: diff --git a/drivers/irqchip/irq-gic-v2m.c b/drivers/irqchip/irq-gic-v2m.c index 993a8426a453..1ff38aff9f29 100644 --- a/drivers/irqchip/irq-gic-v2m.c +++ b/drivers/irqchip/irq-gic-v2m.c @@ -94,7 +94,7 @@ static struct irq_chip gicv2m_msi_irq_chip = { static struct msi_domain_info gicv2m_msi_domain_info = { .flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | - MSI_FLAG_PCI_MSIX), + MSI_FLAG_PCI_MSIX | MSI_FLAG_MULTI_PCI_MSI), .chip = &gicv2m_msi_irq_chip, }; @@ -155,18 +155,12 @@ static int gicv2m_irq_gic_domain_alloc(struct irq_domain *domain, return 0; } -static void gicv2m_unalloc_msi(struct v2m_data *v2m, unsigned int hwirq) +static void gicv2m_unalloc_msi(struct v2m_data *v2m, unsigned int hwirq, + int nr_irqs) { - int pos; - - pos = hwirq - v2m->spi_start; - if (pos < 0 || pos >= v2m->nr_spis) { - pr_err("Failed to teardown msi. Invalid hwirq %d\n", hwirq); - return; - } - spin_lock(&v2m_lock); - __clear_bit(pos, v2m->bm); + bitmap_release_region(v2m->bm, hwirq - v2m->spi_start, + get_count_order(nr_irqs)); spin_unlock(&v2m_lock); } @@ -174,13 +168,13 @@ static int gicv2m_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs, void *args) { struct v2m_data *v2m = NULL, *tmp; - int hwirq, offset, err = 0; + int hwirq, offset, i, err = 0; spin_lock(&v2m_lock); list_for_each_entry(tmp, &v2m_nodes, entry) { - offset = find_first_zero_bit(tmp->bm, tmp->nr_spis); - if (offset < tmp->nr_spis) { - __set_bit(offset, tmp->bm); + offset = bitmap_find_free_region(tmp->bm, tmp->nr_spis, + get_count_order(nr_irqs)); + if (offset >= 0) { v2m = tmp; break; } @@ -192,16 +186,21 @@ static int gicv2m_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, hwirq = v2m->spi_start + offset; - err = gicv2m_irq_gic_domain_alloc(domain, virq, hwirq); - if (err) { - gicv2m_unalloc_msi(v2m, hwirq); - return err; - } + for (i = 0; i < nr_irqs; i++) { + err = gicv2m_irq_gic_domain_alloc(domain, virq + i, hwirq + i); + if (err) + goto fail; - irq_domain_set_hwirq_and_chip(domain, virq, hwirq, - &gicv2m_irq_chip, v2m); + irq_domain_set_hwirq_and_chip(domain, virq + i, hwirq + i, + &gicv2m_irq_chip, v2m); + } return 0; + +fail: + irq_domain_free_irqs_parent(domain, virq, nr_irqs); + gicv2m_unalloc_msi(v2m, hwirq, get_count_order(nr_irqs)); + return err; } static void gicv2m_irq_domain_free(struct irq_domain *domain, @@ -210,8 +209,7 @@ static void gicv2m_irq_domain_free(struct irq_domain *domain, struct irq_data *d = irq_domain_get_irq_data(domain, virq); struct v2m_data *v2m = irq_data_get_irq_chip_data(d); - BUG_ON(nr_irqs != 1); - gicv2m_unalloc_msi(v2m, d->hwirq); + gicv2m_unalloc_msi(v2m, d->hwirq, nr_irqs); irq_domain_free_irqs_parent(domain, virq, nr_irqs); } diff --git a/drivers/irqchip/irq-gic-v3-its-pci-msi.c b/drivers/irqchip/irq-gic-v3-its-pci-msi.c index 14a8c0a7e095..25a98de5cfb2 100644 --- a/drivers/irqchip/irq-gic-v3-its-pci-msi.c +++ b/drivers/irqchip/irq-gic-v3-its-pci-msi.c @@ -132,6 +132,8 @@ static int __init its_pci_of_msi_init(void) for (np = of_find_matching_node(NULL, its_device_id); np; np = of_find_matching_node(np, its_device_id)) { + if (!of_device_is_available(np)) + continue; if (!of_property_read_bool(np, "msi-controller")) continue; diff --git a/drivers/irqchip/irq-gic-v3-its-platform-msi.c b/drivers/irqchip/irq-gic-v3-its-platform-msi.c index 833a90fe33ae..8881a053c173 100644 --- a/drivers/irqchip/irq-gic-v3-its-platform-msi.c +++ b/drivers/irqchip/irq-gic-v3-its-platform-msi.c @@ -154,6 +154,8 @@ static void __init its_pmsi_of_init(void) for (np = of_find_matching_node(NULL, its_device_id); np; np = of_find_matching_node(np, its_device_id)) { + if (!of_device_is_available(np)) + continue; if (!of_property_read_bool(np, "msi-controller")) continue; diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 06f025fd5726..1d3056f53747 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -3314,6 +3314,8 @@ static int __init its_of_probe(struct device_node *node) for (np = of_find_matching_node(node, its_device_id); np; np = of_find_matching_node(np, its_device_id)) { + if (!of_device_is_available(np)) + continue; if (!of_property_read_bool(np, "msi-controller")) { pr_warn("%pOF: no msi-controller property, ITS ignored\n", np); diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index a57c0fbbd34a..d99cc07903ec 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -673,7 +673,7 @@ static void gic_send_sgi(u64 cluster_id, u16 tlist, unsigned int irq) MPIDR_TO_SGI_RS(cluster_id) | tlist << ICC_SGI1R_TARGET_LIST_SHIFT); - pr_debug("CPU%d: ICC_SGI1R_EL1 %llx\n", smp_processor_id(), val); + pr_devel("CPU%d: ICC_SGI1R_EL1 %llx\n", smp_processor_id(), val); gic_write_sgi1r(val); } @@ -688,7 +688,7 @@ static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq) * Ensure that stores to Normal memory are visible to the * other CPUs before issuing the IPI. */ - smp_wmb(); + wmb(); for_each_cpu(cpu, mask) { u64 cluster_id = MPIDR_TO_SGI_CLUSTER_ID(cpu_logical_map(cpu)); diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index ef92a4d2038e..d32268cc1174 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -424,8 +424,6 @@ static int gic_shared_irq_domain_map(struct irq_domain *d, unsigned int virq, spin_lock_irqsave(&gic_lock, flags); write_gic_map_pin(intr, GIC_MAP_PIN_MAP_TO_PIN | gic_cpu_pin); write_gic_map_vp(intr, BIT(mips_cm_vp_id(cpu))); - gic_clear_pcpu_masks(intr); - set_bit(intr, per_cpu_ptr(pcpu_masks, cpu)); irq_data_update_effective_affinity(data, cpumask_of(cpu)); spin_unlock_irqrestore(&gic_lock, flags); diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c index c5603d1a07d6..1f8f489b4167 100644 --- a/drivers/isdn/mISDN/socket.c +++ b/drivers/isdn/mISDN/socket.c @@ -560,7 +560,7 @@ done: static int data_sock_getname(struct socket *sock, struct sockaddr *addr, - int *addr_len, int peer) + int peer) { struct sockaddr_mISDN *maddr = (struct sockaddr_mISDN *) addr; struct sock *sk = sock->sk; @@ -570,14 +570,13 @@ data_sock_getname(struct socket *sock, struct sockaddr *addr, lock_sock(sk); - *addr_len = sizeof(*maddr); maddr->family = AF_ISDN; maddr->dev = _pms(sk)->dev->id; maddr->channel = _pms(sk)->ch.nr; maddr->sapi = _pms(sk)->ch.addr & 0xff; maddr->tei = (_pms(sk)->ch.addr >> 8) & 0xff; release_sock(sk); - return 0; + return sizeof(*maddr); } static const struct proto_ops data_sock_ops = { diff --git a/drivers/macintosh/macio_asic.c b/drivers/macintosh/macio_asic.c index 62f541f968f6..07074820a167 100644 --- a/drivers/macintosh/macio_asic.c +++ b/drivers/macintosh/macio_asic.c @@ -375,6 +375,7 @@ static struct macio_dev * macio_add_one_device(struct macio_chip *chip, dev->ofdev.dev.of_node = np; dev->ofdev.archdata.dma_mask = 0xffffffffUL; dev->ofdev.dev.dma_mask = &dev->ofdev.archdata.dma_mask; + dev->ofdev.dev.coherent_dma_mask = dev->ofdev.archdata.dma_mask; dev->ofdev.dev.parent = parent; dev->ofdev.dev.bus = &macio_bus_type; dev->ofdev.dev.release = macio_release_dev; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index d6de00f367ef..68136806d365 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -903,7 +903,8 @@ static void dec_pending(struct dm_io *io, blk_status_t error) queue_io(md, bio); } else { /* done with normal IO or empty flush */ - bio->bi_status = io_error; + if (io_error) + bio->bi_status = io_error; bio_endio(bio); } } diff --git a/drivers/message/fusion/mptctl.c b/drivers/message/fusion/mptctl.c index 8d12017b9893..4470630dd545 100644 --- a/drivers/message/fusion/mptctl.c +++ b/drivers/message/fusion/mptctl.c @@ -2687,6 +2687,8 @@ mptctl_hp_targetinfo(unsigned long arg) __FILE__, __LINE__, iocnum); return -ENODEV; } + if (karg.hdr.id >= MPT_MAX_FC_DEVICES) + return -EINVAL; dctlprintk(ioc, printk(MYIOC_s_DEBUG_FMT "mptctl_hp_targetinfo called.\n", ioc->name)); diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c index 3e5eabdae8d9..772d02922529 100644 --- a/drivers/misc/mei/bus.c +++ b/drivers/misc/mei/bus.c @@ -548,12 +548,6 @@ int mei_cldev_disable(struct mei_cl_device *cldev) goto out; } - if (bus->dev_state == MEI_DEV_POWER_DOWN) { - dev_dbg(bus->dev, "Device is powering down, don't bother with disconnection\n"); - err = 0; - goto out; - } - err = mei_cl_disconnect(cl); if (err < 0) dev_err(bus->dev, "Could not disconnect from the ME client\n"); diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c index be64969d986a..7e60c1817c31 100644 --- a/drivers/misc/mei/client.c +++ b/drivers/misc/mei/client.c @@ -945,6 +945,12 @@ int mei_cl_disconnect(struct mei_cl *cl) return 0; } + if (dev->dev_state == MEI_DEV_POWER_DOWN) { + cl_dbg(dev, cl, "Device is powering down, don't bother with disconnection\n"); + mei_cl_set_disconnected(cl); + return 0; + } + rets = pm_runtime_get(dev->dev); if (rets < 0 && rets != -EINPROGRESS) { pm_runtime_put_noidle(dev->dev); diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h index 0ccccbaf530d..e4b10b2d1a08 100644 --- a/drivers/misc/mei/hw-me-regs.h +++ b/drivers/misc/mei/hw-me-regs.h @@ -132,6 +132,11 @@ #define MEI_DEV_ID_KBP 0xA2BA /* Kaby Point */ #define MEI_DEV_ID_KBP_2 0xA2BB /* Kaby Point 2 */ +#define MEI_DEV_ID_CNP_LP 0x9DE0 /* Cannon Point LP */ +#define MEI_DEV_ID_CNP_LP_4 0x9DE4 /* Cannon Point LP 4 (iTouch) */ +#define MEI_DEV_ID_CNP_H 0xA360 /* Cannon Point H */ +#define MEI_DEV_ID_CNP_H_4 0xA364 /* Cannon Point H 4 (iTouch) */ + /* * MEI HW Section */ diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index 4a0ccda4d04b..ea4e152270a3 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -98,6 +98,11 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_KBP, MEI_ME_PCH8_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_KBP_2, MEI_ME_PCH8_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_CNP_LP, MEI_ME_PCH8_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_CNP_LP_4, MEI_ME_PCH8_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_CNP_H, MEI_ME_PCH8_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_CNP_H_4, MEI_ME_PCH8_CFG)}, + /* required last entry */ {0, } }; diff --git a/drivers/misc/ocxl/file.c b/drivers/misc/ocxl/file.c index d9aa407db06a..2dd2db9bc1c9 100644 --- a/drivers/misc/ocxl/file.c +++ b/drivers/misc/ocxl/file.c @@ -277,7 +277,7 @@ static ssize_t afu_read(struct file *file, char __user *buf, size_t count, struct ocxl_context *ctx = file->private_data; struct ocxl_kernel_event_header header; ssize_t rc; - size_t used = 0; + ssize_t used = 0; DEFINE_WAIT(event_wait); memset(&header, 0, sizeof(header)); diff --git a/drivers/mmc/host/bcm2835.c b/drivers/mmc/host/bcm2835.c index 229dc18f0581..768972af8b85 100644 --- a/drivers/mmc/host/bcm2835.c +++ b/drivers/mmc/host/bcm2835.c @@ -1265,7 +1265,8 @@ static int bcm2835_add_host(struct bcm2835_host *host) char pio_limit_string[20]; int ret; - mmc->f_max = host->max_clk; + if (!mmc->f_max || mmc->f_max > host->max_clk) + mmc->f_max = host->max_clk; mmc->f_min = host->max_clk / SDCDIV_MAX_CDIV; mmc->max_busy_timeout = ~0 / (mmc->f_max / 1000); diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c index 22438ebfe4e6..4f972b879fe6 100644 --- a/drivers/mmc/host/meson-gx-mmc.c +++ b/drivers/mmc/host/meson-gx-mmc.c @@ -717,22 +717,6 @@ static int meson_mmc_clk_phase_tuning(struct mmc_host *mmc, u32 opcode, static int meson_mmc_execute_tuning(struct mmc_host *mmc, u32 opcode) { struct meson_host *host = mmc_priv(mmc); - int ret; - - /* - * If this is the initial tuning, try to get a sane Rx starting - * phase before doing the actual tuning. - */ - if (!mmc->doing_retune) { - ret = meson_mmc_clk_phase_tuning(mmc, opcode, host->rx_clk); - - if (ret) - return ret; - } - - ret = meson_mmc_clk_phase_tuning(mmc, opcode, host->tx_clk); - if (ret) - return ret; return meson_mmc_clk_phase_tuning(mmc, opcode, host->rx_clk); } @@ -763,9 +747,8 @@ static void meson_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) if (!IS_ERR(mmc->supply.vmmc)) mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, ios->vdd); - /* Reset phases */ + /* Reset rx phase */ clk_set_phase(host->rx_clk, 0); - clk_set_phase(host->tx_clk, 270); break; diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig index e6b8c59f2c0d..736ac887303c 100644 --- a/drivers/mtd/nand/Kconfig +++ b/drivers/mtd/nand/Kconfig @@ -328,7 +328,7 @@ config MTD_NAND_MARVELL tristate "NAND controller support on Marvell boards" depends on PXA3xx || ARCH_MMP || PLAT_ORION || ARCH_MVEBU || \ COMPILE_TEST - depends on HAS_IOMEM + depends on HAS_IOMEM && HAS_DMA help This enables the NAND flash controller driver for Marvell boards, including: diff --git a/drivers/mtd/nand/vf610_nfc.c b/drivers/mtd/nand/vf610_nfc.c index 80d31a58e558..f367144f3c6f 100644 --- a/drivers/mtd/nand/vf610_nfc.c +++ b/drivers/mtd/nand/vf610_nfc.c @@ -752,10 +752,8 @@ static int vf610_nfc_probe(struct platform_device *pdev) if (mtd->oobsize > 64) mtd->oobsize = 64; - /* - * mtd->ecclayout is not specified here because we're using the - * default large page ECC layout defined in NAND core. - */ + /* Use default large page ECC layout defined in NAND core */ + mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops); if (chip->ecc.strength == 32) { nfc->ecc_mode = ECC_60_BYTE; chip->ecc.bytes = 60; diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 944ec3c9282c..08b85215c2be 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -149,9 +149,9 @@ config MACVTAP config IPVLAN tristate "IP-VLAN support" depends on INET - depends on IPV6 + depends on IPV6 || !IPV6 depends on NETFILTER - depends on NET_L3_MASTER_DEV + select NET_L3_MASTER_DEV ---help--- This allows one to create virtual devices off of a main interface and packets will be delivered based on the dest L3 (IPv6/IPv4 addr) diff --git a/drivers/net/Space.c b/drivers/net/Space.c index 11fe71278f40..64333ec999ac 100644 --- a/drivers/net/Space.c +++ b/drivers/net/Space.c @@ -114,9 +114,6 @@ static struct devprobe2 m68k_probes[] __initdata = { #ifdef CONFIG_MVME147_NET /* MVME147 internal Ethernet */ {mvme147lance_probe, 0}, #endif -#ifdef CONFIG_MAC8390 /* NuBus NS8390-based cards */ - {mac8390_probe, 0}, -#endif #ifdef CONFIG_MAC89x0 {mac89x0_probe, 0}, #endif diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index c669554d70bb..4c19d23dd282 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4791,6 +4791,7 @@ static struct pernet_operations bond_net_ops = { .exit = bond_net_exit, .id = &bond_net_id, .size = sizeof(struct bond_net), + .async = true, }; static int __init bonding_init(void) diff --git a/drivers/net/dsa/mv88e6xxx/Kconfig b/drivers/net/dsa/mv88e6xxx/Kconfig index 1aaa7a95ebc4..ae9e7f7cb31c 100644 --- a/drivers/net/dsa/mv88e6xxx/Kconfig +++ b/drivers/net/dsa/mv88e6xxx/Kconfig @@ -18,3 +18,13 @@ config NET_DSA_MV88E6XXX_GLOBAL2 It is required on most chips. If the chip you compile the support for doesn't have such registers set, say N here. In doubt, say Y. + +config NET_DSA_MV88E6XXX_PTP + bool "PTP support for Marvell 88E6xxx" + default n + depends on NET_DSA_MV88E6XXX_GLOBAL2 + imply NETWORK_PHY_TIMESTAMPING + imply PTP_1588_CLOCK + help + Say Y to enable PTP hardware timestamping on Marvell 88E6xxx switch + chips that support it. diff --git a/drivers/net/dsa/mv88e6xxx/Makefile b/drivers/net/dsa/mv88e6xxx/Makefile index 58a4a0014e59..50de304abe2f 100644 --- a/drivers/net/dsa/mv88e6xxx/Makefile +++ b/drivers/net/dsa/mv88e6xxx/Makefile @@ -5,6 +5,10 @@ mv88e6xxx-objs += global1.o mv88e6xxx-objs += global1_atu.o mv88e6xxx-objs += global1_vtu.o mv88e6xxx-$(CONFIG_NET_DSA_MV88E6XXX_GLOBAL2) += global2.o +mv88e6xxx-$(CONFIG_NET_DSA_MV88E6XXX_GLOBAL2) += global2_avb.o +mv88e6xxx-$(CONFIG_NET_DSA_MV88E6XXX_GLOBAL2) += global2_scratch.o +mv88e6xxx-$(CONFIG_NET_DSA_MV88E6XXX_PTP) += hwtstamp.o mv88e6xxx-objs += phy.o mv88e6xxx-objs += port.o +mv88e6xxx-$(CONFIG_NET_DSA_MV88E6XXX_PTP) += ptp.o mv88e6xxx-objs += serdes.o diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index eb328bade225..24486f96dd39 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -36,8 +36,10 @@ #include "chip.h" #include "global1.h" #include "global2.h" +#include "hwtstamp.h" #include "phy.h" #include "port.h" +#include "ptp.h" #include "serdes.h" static void assert_reg_lock(struct mv88e6xxx_chip *chip) @@ -251,9 +253,8 @@ static void mv88e6xxx_g1_irq_unmask(struct irq_data *d) chip->g1_irq.masked &= ~(1 << n); } -static irqreturn_t mv88e6xxx_g1_irq_thread_fn(int irq, void *dev_id) +static irqreturn_t mv88e6xxx_g1_irq_thread_work(struct mv88e6xxx_chip *chip) { - struct mv88e6xxx_chip *chip = dev_id; unsigned int nhandled = 0; unsigned int sub_irq; unsigned int n; @@ -278,6 +279,13 @@ out: return (nhandled > 0 ? IRQ_HANDLED : IRQ_NONE); } +static irqreturn_t mv88e6xxx_g1_irq_thread_fn(int irq, void *dev_id) +{ + struct mv88e6xxx_chip *chip = dev_id; + + return mv88e6xxx_g1_irq_thread_work(chip); +} + static void mv88e6xxx_g1_irq_bus_lock(struct irq_data *d) { struct mv88e6xxx_chip *chip = irq_data_get_irq_chip_data(d); @@ -333,7 +341,7 @@ static const struct irq_domain_ops mv88e6xxx_g1_irq_domain_ops = { .xlate = irq_domain_xlate_twocell, }; -static void mv88e6xxx_g1_irq_free(struct mv88e6xxx_chip *chip) +static void mv88e6xxx_g1_irq_free_common(struct mv88e6xxx_chip *chip) { int irq, virq; u16 mask; @@ -342,8 +350,6 @@ static void mv88e6xxx_g1_irq_free(struct mv88e6xxx_chip *chip) mask &= ~GENMASK(chip->g1_irq.nirqs, 0); mv88e6xxx_g1_write(chip, MV88E6XXX_G1_CTL1, mask); - free_irq(chip->irq, chip); - for (irq = 0; irq < chip->g1_irq.nirqs; irq++) { virq = irq_find_mapping(chip->g1_irq.domain, irq); irq_dispose_mapping(virq); @@ -352,7 +358,14 @@ static void mv88e6xxx_g1_irq_free(struct mv88e6xxx_chip *chip) irq_domain_remove(chip->g1_irq.domain); } -static int mv88e6xxx_g1_irq_setup(struct mv88e6xxx_chip *chip) +static void mv88e6xxx_g1_irq_free(struct mv88e6xxx_chip *chip) +{ + mv88e6xxx_g1_irq_free(chip); + + free_irq(chip->irq, chip); +} + +static int mv88e6xxx_g1_irq_setup_common(struct mv88e6xxx_chip *chip) { int err, irq, virq; u16 reg, mask; @@ -385,13 +398,6 @@ static int mv88e6xxx_g1_irq_setup(struct mv88e6xxx_chip *chip) if (err) goto out_disable; - err = request_threaded_irq(chip->irq, NULL, - mv88e6xxx_g1_irq_thread_fn, - IRQF_ONESHOT | IRQF_TRIGGER_FALLING, - dev_name(chip->dev), chip); - if (err) - goto out_disable; - return 0; out_disable: @@ -409,6 +415,62 @@ out_mapping: return err; } +static int mv88e6xxx_g1_irq_setup(struct mv88e6xxx_chip *chip) +{ + int err; + + err = mv88e6xxx_g1_irq_setup_common(chip); + if (err) + return err; + + err = request_threaded_irq(chip->irq, NULL, + mv88e6xxx_g1_irq_thread_fn, + IRQF_ONESHOT | IRQF_TRIGGER_FALLING, + dev_name(chip->dev), chip); + if (err) + mv88e6xxx_g1_irq_free_common(chip); + + return err; +} + +static void mv88e6xxx_irq_poll(struct kthread_work *work) +{ + struct mv88e6xxx_chip *chip = container_of(work, + struct mv88e6xxx_chip, + irq_poll_work.work); + mv88e6xxx_g1_irq_thread_work(chip); + + kthread_queue_delayed_work(chip->kworker, &chip->irq_poll_work, + msecs_to_jiffies(100)); +} + +static int mv88e6xxx_irq_poll_setup(struct mv88e6xxx_chip *chip) +{ + int err; + + err = mv88e6xxx_g1_irq_setup_common(chip); + if (err) + return err; + + kthread_init_delayed_work(&chip->irq_poll_work, + mv88e6xxx_irq_poll); + + chip->kworker = kthread_create_worker(0, dev_name(chip->dev)); + if (IS_ERR(chip->kworker)) + return PTR_ERR(chip->kworker); + + kthread_queue_delayed_work(chip->kworker, &chip->irq_poll_work, + msecs_to_jiffies(100)); + + return 0; +} + +static void mv88e6xxx_irq_poll_free(struct mv88e6xxx_chip *chip) +{ + kthread_cancel_delayed_work_sync(&chip->irq_poll_work); + kthread_destroy_worker(chip->kworker); +} + int mv88e6xxx_wait(struct mv88e6xxx_chip *chip, int addr, int reg, u16 mask) { int i; @@ -712,9 +774,12 @@ static void mv88e6xxx_stats_get_stats(struct mv88e6xxx_chip *chip, int port, for (i = 0, j = 0; i < ARRAY_SIZE(mv88e6xxx_hw_stats); i++) { stat = &mv88e6xxx_hw_stats[i]; if (stat->type & types) { + mutex_lock(&chip->reg_lock); data[j] = _mv88e6xxx_get_ethtool_stat(chip, stat, port, bank1_select, histogram); + mutex_unlock(&chip->reg_lock); + j++; } } @@ -762,14 +827,13 @@ static void mv88e6xxx_get_ethtool_stats(struct dsa_switch *ds, int port, mutex_lock(&chip->reg_lock); ret = mv88e6xxx_stats_snapshot(chip, port); - if (ret < 0) { - mutex_unlock(&chip->reg_lock); + mutex_unlock(&chip->reg_lock); + + if (ret < 0) return; - } mv88e6xxx_get_stats(chip, port, data); - mutex_unlock(&chip->reg_lock); } static int mv88e6xxx_stats_set_histogram(struct mv88e6xxx_chip *chip) @@ -1433,7 +1497,9 @@ static int mv88e6xxx_port_db_dump_fid(struct mv88e6xxx_chip *chip, eth_broadcast_addr(addr.mac); do { + mutex_lock(&chip->reg_lock); err = mv88e6xxx_g1_atu_getnext(chip, fid, &addr); + mutex_unlock(&chip->reg_lock); if (err) return err; @@ -1466,7 +1532,10 @@ static int mv88e6xxx_port_db_dump(struct mv88e6xxx_chip *chip, int port, int err; /* Dump port's default Filtering Information Database (VLAN ID 0) */ + mutex_lock(&chip->reg_lock); err = mv88e6xxx_port_get_fid(chip, port, &fid); + mutex_unlock(&chip->reg_lock); + if (err) return err; @@ -1476,7 +1545,9 @@ static int mv88e6xxx_port_db_dump(struct mv88e6xxx_chip *chip, int port, /* Dump VLANs' Filtering Information Databases */ do { + mutex_lock(&chip->reg_lock); err = mv88e6xxx_vtu_getnext(chip, &vlan); + mutex_unlock(&chip->reg_lock); if (err) return err; @@ -1496,13 +1567,8 @@ static int mv88e6xxx_port_fdb_dump(struct dsa_switch *ds, int port, dsa_fdb_dump_cb_t *cb, void *data) { struct mv88e6xxx_chip *chip = ds->priv; - int err; - - mutex_lock(&chip->reg_lock); - err = mv88e6xxx_port_db_dump(chip, port, cb, data); - mutex_unlock(&chip->reg_lock); - return err; + return mv88e6xxx_port_db_dump(chip, port, cb, data); } static int mv88e6xxx_bridge_map(struct mv88e6xxx_chip *chip, @@ -2092,6 +2158,17 @@ static int mv88e6xxx_setup(struct dsa_switch *ds) if (err) goto unlock; + /* Setup PTP Hardware Clock and timestamping */ + if (chip->info->ptp_support) { + err = mv88e6xxx_ptp_setup(chip); + if (err) + goto unlock; + + err = mv88e6xxx_hwtstamp_setup(chip); + if (err) + goto unlock; + } + unlock: mutex_unlock(&chip->reg_lock); @@ -2148,6 +2225,15 @@ static int mv88e6xxx_mdio_register(struct mv88e6xxx_chip *chip, struct mii_bus *bus; int err; + if (external) { + mutex_lock(&chip->reg_lock); + err = mv88e6xxx_g2_scratch_gpio_set_smi(chip, true); + mutex_unlock(&chip->reg_lock); + + if (err) + return err; + } + bus = devm_mdiobus_alloc_size(chip->dev, sizeof(*mdio_bus)); if (!bus) return -ENOMEM; @@ -2472,6 +2558,7 @@ static const struct mv88e6xxx_ops mv88e6141_ops = { .reset = mv88e6352_g1_reset, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, + .gpio_ops = &mv88e6352_gpio_ops, }; static const struct mv88e6xxx_ops mv88e6161_ops = { @@ -2602,6 +2689,7 @@ static const struct mv88e6xxx_ops mv88e6172_ops = { .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, .serdes_power = mv88e6352_serdes_power, + .gpio_ops = &mv88e6352_gpio_ops, }; static const struct mv88e6xxx_ops mv88e6175_ops = { @@ -2673,6 +2761,7 @@ static const struct mv88e6xxx_ops mv88e6176_ops = { .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, .serdes_power = mv88e6352_serdes_power, + .gpio_ops = &mv88e6352_gpio_ops, }; static const struct mv88e6xxx_ops mv88e6185_ops = { @@ -2736,6 +2825,7 @@ static const struct mv88e6xxx_ops mv88e6190_ops = { .vtu_getnext = mv88e6390_g1_vtu_getnext, .vtu_loadpurge = mv88e6390_g1_vtu_loadpurge, .serdes_power = mv88e6390_serdes_power, + .gpio_ops = &mv88e6352_gpio_ops, }; static const struct mv88e6xxx_ops mv88e6190x_ops = { @@ -2771,6 +2861,7 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = { .vtu_getnext = mv88e6390_g1_vtu_getnext, .vtu_loadpurge = mv88e6390_g1_vtu_loadpurge, .serdes_power = mv88e6390_serdes_power, + .gpio_ops = &mv88e6352_gpio_ops, }; static const struct mv88e6xxx_ops mv88e6191_ops = { @@ -2843,6 +2934,8 @@ static const struct mv88e6xxx_ops mv88e6240_ops = { .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, .serdes_power = mv88e6352_serdes_power, + .gpio_ops = &mv88e6352_gpio_ops, + .avb_ops = &mv88e6352_avb_ops, }; static const struct mv88e6xxx_ops mv88e6290_ops = { @@ -2879,6 +2972,8 @@ static const struct mv88e6xxx_ops mv88e6290_ops = { .vtu_getnext = mv88e6390_g1_vtu_getnext, .vtu_loadpurge = mv88e6390_g1_vtu_loadpurge, .serdes_power = mv88e6390_serdes_power, + .gpio_ops = &mv88e6352_gpio_ops, + .avb_ops = &mv88e6390_avb_ops, }; static const struct mv88e6xxx_ops mv88e6320_ops = { @@ -2913,6 +3008,8 @@ static const struct mv88e6xxx_ops mv88e6320_ops = { .reset = mv88e6352_g1_reset, .vtu_getnext = mv88e6185_g1_vtu_getnext, .vtu_loadpurge = mv88e6185_g1_vtu_loadpurge, + .gpio_ops = &mv88e6352_gpio_ops, + .avb_ops = &mv88e6352_avb_ops, }; static const struct mv88e6xxx_ops mv88e6321_ops = { @@ -2945,6 +3042,8 @@ static const struct mv88e6xxx_ops mv88e6321_ops = { .reset = mv88e6352_g1_reset, .vtu_getnext = mv88e6185_g1_vtu_getnext, .vtu_loadpurge = mv88e6185_g1_vtu_loadpurge, + .gpio_ops = &mv88e6352_gpio_ops, + .avb_ops = &mv88e6352_avb_ops, }; static const struct mv88e6xxx_ops mv88e6341_ops = { @@ -2981,6 +3080,8 @@ static const struct mv88e6xxx_ops mv88e6341_ops = { .reset = mv88e6352_g1_reset, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, + .gpio_ops = &mv88e6352_gpio_ops, + .avb_ops = &mv88e6390_avb_ops, }; static const struct mv88e6xxx_ops mv88e6350_ops = { @@ -3049,6 +3150,7 @@ static const struct mv88e6xxx_ops mv88e6351_ops = { .reset = mv88e6352_g1_reset, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, + .avb_ops = &mv88e6352_avb_ops, }; static const struct mv88e6xxx_ops mv88e6352_ops = { @@ -3086,6 +3188,8 @@ static const struct mv88e6xxx_ops mv88e6352_ops = { .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, .serdes_power = mv88e6352_serdes_power, + .gpio_ops = &mv88e6352_gpio_ops, + .avb_ops = &mv88e6352_avb_ops, }; static const struct mv88e6xxx_ops mv88e6390_ops = { @@ -3124,6 +3228,8 @@ static const struct mv88e6xxx_ops mv88e6390_ops = { .vtu_getnext = mv88e6390_g1_vtu_getnext, .vtu_loadpurge = mv88e6390_g1_vtu_loadpurge, .serdes_power = mv88e6390_serdes_power, + .gpio_ops = &mv88e6352_gpio_ops, + .avb_ops = &mv88e6390_avb_ops, }; static const struct mv88e6xxx_ops mv88e6390x_ops = { @@ -3162,6 +3268,8 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = { .vtu_getnext = mv88e6390_g1_vtu_getnext, .vtu_loadpurge = mv88e6390_g1_vtu_loadpurge, .serdes_power = mv88e6390_serdes_power, + .gpio_ops = &mv88e6352_gpio_ops, + .avb_ops = &mv88e6390_avb_ops, }; static const struct mv88e6xxx_info mv88e6xxx_table[] = { @@ -3267,6 +3375,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .name = "Marvell 88E6341", .num_databases = 4096, .num_ports = 6, + .num_gpio = 11, .max_vid = 4095, .port_base_addr = 0x10, .global1_addr = 0x1b, @@ -3346,6 +3455,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .name = "Marvell 88E6172", .num_databases = 4096, .num_ports = 7, + .num_gpio = 15, .max_vid = 4095, .port_base_addr = 0x10, .global1_addr = 0x1b, @@ -3386,6 +3496,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .name = "Marvell 88E6176", .num_databases = 4096, .num_ports = 7, + .num_gpio = 15, .max_vid = 4095, .port_base_addr = 0x10, .global1_addr = 0x1b, @@ -3424,6 +3535,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .name = "Marvell 88E6190", .num_databases = 4096, .num_ports = 11, /* 10 + Z80 */ + .num_gpio = 16, .max_vid = 8191, .port_base_addr = 0x0, .global1_addr = 0x1b, @@ -3444,6 +3556,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .name = "Marvell 88E6190X", .num_databases = 4096, .num_ports = 11, /* 10 + Z80 */ + .num_gpio = 16, .max_vid = 8191, .port_base_addr = 0x0, .global1_addr = 0x1b, @@ -3475,6 +3588,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .pvt = true, .multi_chip = true, .tag_protocol = DSA_TAG_PROTO_DSA, + .ptp_support = true, .ops = &mv88e6191_ops, }, @@ -3484,6 +3598,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .name = "Marvell 88E6240", .num_databases = 4096, .num_ports = 7, + .num_gpio = 15, .max_vid = 4095, .port_base_addr = 0x10, .global1_addr = 0x1b, @@ -3495,6 +3610,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .pvt = true, .multi_chip = true, .tag_protocol = DSA_TAG_PROTO_EDSA, + .ptp_support = true, .ops = &mv88e6240_ops, }, @@ -3504,6 +3620,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .name = "Marvell 88E6290", .num_databases = 4096, .num_ports = 11, /* 10 + Z80 */ + .num_gpio = 16, .max_vid = 8191, .port_base_addr = 0x0, .global1_addr = 0x1b, @@ -3515,6 +3632,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .pvt = true, .multi_chip = true, .tag_protocol = DSA_TAG_PROTO_DSA, + .ptp_support = true, .ops = &mv88e6290_ops, }, @@ -3524,6 +3642,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .name = "Marvell 88E6320", .num_databases = 4096, .num_ports = 7, + .num_gpio = 15, .max_vid = 4095, .port_base_addr = 0x10, .global1_addr = 0x1b, @@ -3534,6 +3653,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .pvt = true, .multi_chip = true, .tag_protocol = DSA_TAG_PROTO_EDSA, + .ptp_support = true, .ops = &mv88e6320_ops, }, @@ -3543,6 +3663,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .name = "Marvell 88E6321", .num_databases = 4096, .num_ports = 7, + .num_gpio = 15, .max_vid = 4095, .port_base_addr = 0x10, .global1_addr = 0x1b, @@ -3552,6 +3673,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .atu_move_port_mask = 0xf, .multi_chip = true, .tag_protocol = DSA_TAG_PROTO_EDSA, + .ptp_support = true, .ops = &mv88e6321_ops, }, @@ -3561,6 +3683,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .name = "Marvell 88E6341", .num_databases = 4096, .num_ports = 6, + .num_gpio = 11, .max_vid = 4095, .port_base_addr = 0x10, .global1_addr = 0x1b, @@ -3571,6 +3694,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .pvt = true, .multi_chip = true, .tag_protocol = DSA_TAG_PROTO_EDSA, + .ptp_support = true, .ops = &mv88e6341_ops, }, @@ -3620,6 +3744,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .name = "Marvell 88E6352", .num_databases = 4096, .num_ports = 7, + .num_gpio = 15, .max_vid = 4095, .port_base_addr = 0x10, .global1_addr = 0x1b, @@ -3631,6 +3756,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .pvt = true, .multi_chip = true, .tag_protocol = DSA_TAG_PROTO_EDSA, + .ptp_support = true, .ops = &mv88e6352_ops, }, [MV88E6390] = { @@ -3639,6 +3765,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .name = "Marvell 88E6390", .num_databases = 4096, .num_ports = 11, /* 10 + Z80 */ + .num_gpio = 16, .max_vid = 8191, .port_base_addr = 0x0, .global1_addr = 0x1b, @@ -3650,6 +3777,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .pvt = true, .multi_chip = true, .tag_protocol = DSA_TAG_PROTO_DSA, + .ptp_support = true, .ops = &mv88e6390_ops, }, [MV88E6390X] = { @@ -3658,6 +3786,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .name = "Marvell 88E6390X", .num_databases = 4096, .num_ports = 11, /* 10 + Z80 */ + .num_gpio = 16, .max_vid = 8191, .port_base_addr = 0x0, .global1_addr = 0x1b, @@ -3669,6 +3798,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .pvt = true, .multi_chip = true, .tag_protocol = DSA_TAG_PROTO_DSA, + .ptp_support = true, .ops = &mv88e6390x_ops, }, }; @@ -3880,6 +4010,11 @@ static const struct dsa_switch_ops mv88e6xxx_switch_ops = { .port_mdb_del = mv88e6xxx_port_mdb_del, .crosschip_bridge_join = mv88e6xxx_crosschip_bridge_join, .crosschip_bridge_leave = mv88e6xxx_crosschip_bridge_leave, + .port_hwtstamp_set = mv88e6xxx_port_hwtstamp_set, + .port_hwtstamp_get = mv88e6xxx_port_hwtstamp_get, + .port_txtstamp = mv88e6xxx_port_txtstamp, + .port_rxtstamp = mv88e6xxx_port_rxtstamp, + .get_ts_info = mv88e6xxx_get_ts_info, }; static struct dsa_switch_driver mv88e6xxx_switch_drv = { @@ -3959,33 +4094,34 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev) goto out; } - if (chip->irq > 0) { - /* Has to be performed before the MDIO bus is created, - * because the PHYs will link there interrupts to these - * interrupt controllers - */ - mutex_lock(&chip->reg_lock); + /* Has to be performed before the MDIO bus is created, because + * the PHYs will link there interrupts to these interrupt + * controllers + */ + mutex_lock(&chip->reg_lock); + if (chip->irq > 0) err = mv88e6xxx_g1_irq_setup(chip); - mutex_unlock(&chip->reg_lock); - - if (err) - goto out; - - if (chip->info->g2_irqs > 0) { - err = mv88e6xxx_g2_irq_setup(chip); - if (err) - goto out_g1_irq; - } + else + err = mv88e6xxx_irq_poll_setup(chip); + mutex_unlock(&chip->reg_lock); - err = mv88e6xxx_g1_atu_prob_irq_setup(chip); - if (err) - goto out_g2_irq; + if (err) + goto out; - err = mv88e6xxx_g1_vtu_prob_irq_setup(chip); + if (chip->info->g2_irqs > 0) { + err = mv88e6xxx_g2_irq_setup(chip); if (err) - goto out_g1_atu_prob_irq; + goto out_g1_irq; } + err = mv88e6xxx_g1_atu_prob_irq_setup(chip); + if (err) + goto out_g2_irq; + + err = mv88e6xxx_g1_vtu_prob_irq_setup(chip); + if (err) + goto out_g1_atu_prob_irq; + err = mv88e6xxx_mdios_register(chip, np); if (err) goto out_g1_vtu_prob_irq; @@ -3999,20 +4135,19 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev) out_mdio: mv88e6xxx_mdios_unregister(chip); out_g1_vtu_prob_irq: - if (chip->irq > 0) - mv88e6xxx_g1_vtu_prob_irq_free(chip); + mv88e6xxx_g1_vtu_prob_irq_free(chip); out_g1_atu_prob_irq: - if (chip->irq > 0) - mv88e6xxx_g1_atu_prob_irq_free(chip); + mv88e6xxx_g1_atu_prob_irq_free(chip); out_g2_irq: - if (chip->info->g2_irqs > 0 && chip->irq > 0) + if (chip->info->g2_irqs > 0) mv88e6xxx_g2_irq_free(chip); out_g1_irq: - if (chip->irq > 0) { - mutex_lock(&chip->reg_lock); + mutex_lock(&chip->reg_lock); + if (chip->irq > 0) mv88e6xxx_g1_irq_free(chip); - mutex_unlock(&chip->reg_lock); - } + else + mv88e6xxx_irq_poll_free(chip); + mutex_unlock(&chip->reg_lock); out: return err; } @@ -4022,6 +4157,11 @@ static void mv88e6xxx_remove(struct mdio_device *mdiodev) struct dsa_switch *ds = dev_get_drvdata(&mdiodev->dev); struct mv88e6xxx_chip *chip = ds->priv; + if (chip->info->ptp_support) { + mv88e6xxx_hwtstamp_free(chip); + mv88e6xxx_ptp_free(chip); + } + mv88e6xxx_phy_destroy(chip); mv88e6xxx_unregister_switch(chip); mv88e6xxx_mdios_unregister(chip); diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h index 3dba6e90adcf..d6a1391dc268 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.h +++ b/drivers/net/dsa/mv88e6xxx/chip.h @@ -15,7 +15,10 @@ #include <linux/if_vlan.h> #include <linux/irq.h> #include <linux/gpio/consumer.h> +#include <linux/kthread.h> #include <linux/phy.h> +#include <linux/ptp_clock_kernel.h> +#include <linux/timecounter.h> #include <net/dsa.h> #ifndef UINT64_MAX @@ -39,6 +42,8 @@ #define MV88E6XXX_MAX_PVT_SWITCHES 32 #define MV88E6XXX_MAX_PVT_PORTS 16 +#define MV88E6XXX_MAX_GPIO 16 + enum mv88e6xxx_egress_mode { MV88E6XXX_EGRESS_MODE_UNMODIFIED, MV88E6XXX_EGRESS_MODE_UNTAGGED, @@ -105,6 +110,7 @@ struct mv88e6xxx_info { const char *name; unsigned int num_databases; unsigned int num_ports; + unsigned int num_gpio; unsigned int max_vid; unsigned int port_base_addr; unsigned int global1_addr; @@ -126,6 +132,9 @@ struct mv88e6xxx_info { */ u8 atu_move_port_mask; const struct mv88e6xxx_ops *ops; + + /* Supports PTP */ + bool ptp_support; }; struct mv88e6xxx_atu_entry { @@ -146,6 +155,8 @@ struct mv88e6xxx_vtu_entry { struct mv88e6xxx_bus_ops; struct mv88e6xxx_irq_ops; +struct mv88e6xxx_gpio_ops; +struct mv88e6xxx_avb_ops; struct mv88e6xxx_irq { u16 masked; @@ -154,6 +165,32 @@ struct mv88e6xxx_irq { unsigned int nirqs; }; +/* state flags for mv88e6xxx_port_hwtstamp::state */ +enum { + MV88E6XXX_HWTSTAMP_ENABLED, + MV88E6XXX_HWTSTAMP_TX_IN_PROGRESS, +}; + +struct mv88e6xxx_port_hwtstamp { + /* Port index */ + int port_id; + + /* Timestamping state */ + unsigned long state; + + /* Resources for receive timestamping */ + struct sk_buff_head rx_queue; + struct sk_buff_head rx_queue2; + + /* Resources for transmit timestamping */ + unsigned long tx_tstamp_start; + struct sk_buff *tx_skb; + u16 tx_seq_id; + + /* Current timestamp configuration */ + struct hwtstamp_config tstamp_config; +}; + struct mv88e6xxx_chip { const struct mv88e6xxx_info *info; @@ -209,6 +246,28 @@ struct mv88e6xxx_chip { int watchdog_irq; int atu_prob_irq; int vtu_prob_irq; + struct kthread_worker *kworker; + struct kthread_delayed_work irq_poll_work; + + /* GPIO resources */ + u8 gpio_data[2]; + + /* This cyclecounter abstracts the switch PTP time. + * reg_lock must be held for any operation that read()s. + */ + struct cyclecounter tstamp_cc; + struct timecounter tstamp_tc; + struct delayed_work overflow_work; + + struct ptp_clock *ptp_clock; + struct ptp_clock_info ptp_clock_info; + struct delayed_work tai_event_work; + struct ptp_pin_desc pin_config[MV88E6XXX_MAX_GPIO]; + u16 trig_config; + u16 evcap_config; + + /* Per-port timestamping resources. */ + struct mv88e6xxx_port_hwtstamp port_hwtstamp[DSA_MAX_PORTS]; }; struct mv88e6xxx_bus_ops { @@ -344,6 +403,12 @@ struct mv88e6xxx_ops { struct mv88e6xxx_vtu_entry *entry); int (*vtu_loadpurge)(struct mv88e6xxx_chip *chip, struct mv88e6xxx_vtu_entry *entry); + + /* GPIO operations */ + const struct mv88e6xxx_gpio_ops *gpio_ops; + + /* Interface to the AVB/PTP registers */ + const struct mv88e6xxx_avb_ops *avb_ops; }; struct mv88e6xxx_irq_ops { @@ -355,6 +420,42 @@ struct mv88e6xxx_irq_ops { void (*irq_free)(struct mv88e6xxx_chip *chip); }; +struct mv88e6xxx_gpio_ops { + /* Get/set data on GPIO pin */ + int (*get_data)(struct mv88e6xxx_chip *chip, unsigned int pin); + int (*set_data)(struct mv88e6xxx_chip *chip, unsigned int pin, + int value); + + /* get/set GPIO direction */ + int (*get_dir)(struct mv88e6xxx_chip *chip, unsigned int pin); + int (*set_dir)(struct mv88e6xxx_chip *chip, unsigned int pin, + bool input); + + /* get/set GPIO pin control */ + int (*get_pctl)(struct mv88e6xxx_chip *chip, unsigned int pin, + int *func); + int (*set_pctl)(struct mv88e6xxx_chip *chip, unsigned int pin, + int func); +}; + +struct mv88e6xxx_avb_ops { + /* Access port-scoped Precision Time Protocol registers */ + int (*port_ptp_read)(struct mv88e6xxx_chip *chip, int port, int addr, + u16 *data, int len); + int (*port_ptp_write)(struct mv88e6xxx_chip *chip, int port, int addr, + u16 data); + + /* Access global Precision Time Protocol registers */ + int (*ptp_read)(struct mv88e6xxx_chip *chip, int addr, u16 *data, + int len); + int (*ptp_write)(struct mv88e6xxx_chip *chip, int addr, u16 data); + + /* Access global Time Application Interface registers */ + int (*tai_read)(struct mv88e6xxx_chip *chip, int addr, u16 *data, + int len); + int (*tai_write)(struct mv88e6xxx_chip *chip, int addr, u16 data); +}; + #define STATS_TYPE_PORT BIT(0) #define STATS_TYPE_BANK0 BIT(1) #define STATS_TYPE_BANK1 BIT(2) @@ -386,6 +487,11 @@ static inline u16 mv88e6xxx_port_mask(struct mv88e6xxx_chip *chip) return GENMASK(mv88e6xxx_num_ports(chip) - 1, 0); } +static inline unsigned int mv88e6xxx_num_gpio(struct mv88e6xxx_chip *chip) +{ + return chip->info->num_gpio; +} + int mv88e6xxx_read(struct mv88e6xxx_chip *chip, int addr, int reg, u16 *val); int mv88e6xxx_write(struct mv88e6xxx_chip *chip, int addr, int reg, u16 val); int mv88e6xxx_update(struct mv88e6xxx_chip *chip, int addr, int reg, diff --git a/drivers/net/dsa/mv88e6xxx/global2.c b/drivers/net/dsa/mv88e6xxx/global2.c index af0727877825..5f370f1fc7c4 100644 --- a/drivers/net/dsa/mv88e6xxx/global2.c +++ b/drivers/net/dsa/mv88e6xxx/global2.c @@ -20,22 +20,22 @@ #include "global1.h" /* for MV88E6XXX_G1_STS_IRQ_DEVICE */ #include "global2.h" -static int mv88e6xxx_g2_read(struct mv88e6xxx_chip *chip, int reg, u16 *val) +int mv88e6xxx_g2_read(struct mv88e6xxx_chip *chip, int reg, u16 *val) { return mv88e6xxx_read(chip, chip->info->global2_addr, reg, val); } -static int mv88e6xxx_g2_write(struct mv88e6xxx_chip *chip, int reg, u16 val) +int mv88e6xxx_g2_write(struct mv88e6xxx_chip *chip, int reg, u16 val) { return mv88e6xxx_write(chip, chip->info->global2_addr, reg, val); } -static int mv88e6xxx_g2_update(struct mv88e6xxx_chip *chip, int reg, u16 update) +int mv88e6xxx_g2_update(struct mv88e6xxx_chip *chip, int reg, u16 update) { return mv88e6xxx_update(chip, chip->info->global2_addr, reg, update); } -static int mv88e6xxx_g2_wait(struct mv88e6xxx_chip *chip, int reg, u16 mask) +int mv88e6xxx_g2_wait(struct mv88e6xxx_chip *chip, int reg, u16 mask) { return mv88e6xxx_wait(chip, chip->info->global2_addr, reg, mask); } @@ -798,6 +798,7 @@ int mv88e6xxx_g2_smi_phy_write(struct mv88e6xxx_chip *chip, struct mii_bus *bus, val); } +/* Offset 0x1B: Watchdog Control */ static int mv88e6097_watchdog_action(struct mv88e6xxx_chip *chip, int irq) { u16 reg; diff --git a/drivers/net/dsa/mv88e6xxx/global2.h b/drivers/net/dsa/mv88e6xxx/global2.h index 669f59017b12..aa3f0a736966 100644 --- a/drivers/net/dsa/mv88e6xxx/global2.h +++ b/drivers/net/dsa/mv88e6xxx/global2.h @@ -149,7 +149,26 @@ #define MV88E6390_G2_EEPROM_ADDR_MASK 0xffff /* Offset 0x16: AVB Command Register */ -#define MV88E6352_G2_AVB_CMD 0x16 +#define MV88E6352_G2_AVB_CMD 0x16 +#define MV88E6352_G2_AVB_CMD_BUSY 0x8000 +#define MV88E6352_G2_AVB_CMD_OP_READ 0x4000 +#define MV88E6352_G2_AVB_CMD_OP_READ_INCR 0x6000 +#define MV88E6352_G2_AVB_CMD_OP_WRITE 0x3000 +#define MV88E6390_G2_AVB_CMD_OP_READ 0x0000 +#define MV88E6390_G2_AVB_CMD_OP_READ_INCR 0x4000 +#define MV88E6390_G2_AVB_CMD_OP_WRITE 0x6000 +#define MV88E6352_G2_AVB_CMD_PORT_MASK 0x0f00 +#define MV88E6352_G2_AVB_CMD_PORT_TAIGLOBAL 0xe +#define MV88E6352_G2_AVB_CMD_PORT_PTPGLOBAL 0xf +#define MV88E6390_G2_AVB_CMD_PORT_MASK 0x1f00 +#define MV88E6390_G2_AVB_CMD_PORT_TAIGLOBAL 0x1e +#define MV88E6390_G2_AVB_CMD_PORT_PTPGLOBAL 0x1f +#define MV88E6352_G2_AVB_CMD_BLOCK_PTP 0 +#define MV88E6352_G2_AVB_CMD_BLOCK_AVB 1 +#define MV88E6352_G2_AVB_CMD_BLOCK_QAV 2 +#define MV88E6352_G2_AVB_CMD_BLOCK_QVB 3 +#define MV88E6352_G2_AVB_CMD_BLOCK_MASK 0x00e0 +#define MV88E6352_G2_AVB_CMD_ADDR_MASK 0x001f /* Offset 0x17: AVB Data Register */ #define MV88E6352_G2_AVB_DATA 0x17 @@ -223,6 +242,40 @@ #define MV88E6352_G2_NOEGR_POLICY 0x2000 #define MV88E6390_G2_LAG_ID_4 0x2000 +/* Scratch/Misc registers accessed through MV88E6XXX_G2_SCRATCH_MISC */ +/* Offset 0x02: Misc Configuration */ +#define MV88E6352_G2_SCRATCH_MISC_CFG 0x02 +#define MV88E6352_G2_SCRATCH_MISC_CFG_NORMALSMI 0x80 +/* Offset 0x60-0x61: GPIO Configuration */ +#define MV88E6352_G2_SCRATCH_GPIO_CFG0 0x60 +#define MV88E6352_G2_SCRATCH_GPIO_CFG1 0x61 +/* Offset 0x62-0x63: GPIO Direction */ +#define MV88E6352_G2_SCRATCH_GPIO_DIR0 0x62 +#define MV88E6352_G2_SCRATCH_GPIO_DIR1 0x63 +#define MV88E6352_G2_SCRATCH_GPIO_DIR_OUT 0 +#define MV88E6352_G2_SCRATCH_GPIO_DIR_IN 1 +/* Offset 0x64-0x65: GPIO Data */ +#define MV88E6352_G2_SCRATCH_GPIO_DATA0 0x64 +#define MV88E6352_G2_SCRATCH_GPIO_DATA1 0x65 +/* Offset 0x68-0x6F: GPIO Pin Control */ +#define MV88E6352_G2_SCRATCH_GPIO_PCTL0 0x68 +#define MV88E6352_G2_SCRATCH_GPIO_PCTL1 0x69 +#define MV88E6352_G2_SCRATCH_GPIO_PCTL2 0x6A +#define MV88E6352_G2_SCRATCH_GPIO_PCTL3 0x6B +#define MV88E6352_G2_SCRATCH_GPIO_PCTL4 0x6C +#define MV88E6352_G2_SCRATCH_GPIO_PCTL5 0x6D +#define MV88E6352_G2_SCRATCH_GPIO_PCTL6 0x6E +#define MV88E6352_G2_SCRATCH_GPIO_PCTL7 0x6F +#define MV88E6352_G2_SCRATCH_CONFIG_DATA0 0x70 +#define MV88E6352_G2_SCRATCH_CONFIG_DATA1 0x71 +#define MV88E6352_G2_SCRATCH_CONFIG_DATA1_NO_CPU BIT(2) +#define MV88E6352_G2_SCRATCH_CONFIG_DATA2 0x72 +#define MV88E6352_G2_SCRATCH_CONFIG_DATA2_P0_MODE_MASK 0x3 + +#define MV88E6352_G2_SCRATCH_GPIO_PCTL_GPIO 0 +#define MV88E6352_G2_SCRATCH_GPIO_PCTL_TRIG 1 +#define MV88E6352_G2_SCRATCH_GPIO_PCTL_EVREQ 2 + #ifdef CONFIG_NET_DSA_MV88E6XXX_GLOBAL2 static inline int mv88e6xxx_g2_require(struct mv88e6xxx_chip *chip) @@ -230,6 +283,11 @@ static inline int mv88e6xxx_g2_require(struct mv88e6xxx_chip *chip) return 0; } +int mv88e6xxx_g2_read(struct mv88e6xxx_chip *chip, int reg, u16 *val); +int mv88e6xxx_g2_write(struct mv88e6xxx_chip *chip, int reg, u16 val); +int mv88e6xxx_g2_update(struct mv88e6xxx_chip *chip, int reg, u16 update); +int mv88e6xxx_g2_wait(struct mv88e6xxx_chip *chip, int reg, u16 mask); + int mv88e6352_g2_irl_init_all(struct mv88e6xxx_chip *chip, int port); int mv88e6390_g2_irl_init_all(struct mv88e6xxx_chip *chip, int port); @@ -267,6 +325,14 @@ int mv88e6xxx_g2_pot_clear(struct mv88e6xxx_chip *chip); extern const struct mv88e6xxx_irq_ops mv88e6097_watchdog_ops; extern const struct mv88e6xxx_irq_ops mv88e6390_watchdog_ops; +extern const struct mv88e6xxx_avb_ops mv88e6352_avb_ops; +extern const struct mv88e6xxx_avb_ops mv88e6390_avb_ops; + +extern const struct mv88e6xxx_gpio_ops mv88e6352_gpio_ops; + +int mv88e6xxx_g2_scratch_gpio_set_smi(struct mv88e6xxx_chip *chip, + bool external); + #else /* !CONFIG_NET_DSA_MV88E6XXX_GLOBAL2 */ static inline int mv88e6xxx_g2_require(struct mv88e6xxx_chip *chip) @@ -279,6 +345,26 @@ static inline int mv88e6xxx_g2_require(struct mv88e6xxx_chip *chip) return 0; } +static inline int mv88e6xxx_g2_read(struct mv88e6xxx_chip *chip, int reg, u16 *val) +{ + return -EOPNOTSUPP; +} + +static inline int mv88e6xxx_g2_write(struct mv88e6xxx_chip *chip, int reg, u16 val) +{ + return -EOPNOTSUPP; +} + +static inline int mv88e6xxx_g2_update(struct mv88e6xxx_chip *chip, int reg, u16 update) +{ + return -EOPNOTSUPP; +} + +static inline int mv88e6xxx_g2_wait(struct mv88e6xxx_chip *chip, int reg, u16 mask) +{ + return -EOPNOTSUPP; +} + static inline int mv88e6352_g2_irl_init_all(struct mv88e6xxx_chip *chip, int port) { @@ -382,6 +468,17 @@ static inline int mv88e6xxx_g2_pot_clear(struct mv88e6xxx_chip *chip) static const struct mv88e6xxx_irq_ops mv88e6097_watchdog_ops = {}; static const struct mv88e6xxx_irq_ops mv88e6390_watchdog_ops = {}; +static const struct mv88e6xxx_avb_ops mv88e6352_avb_ops = {}; +static const struct mv88e6xxx_avb_ops mv88e6390_avb_ops = {}; + +static const struct mv88e6xxx_gpio_ops mv88e6352_gpio_ops = {}; + +static inline int mv88e6xxx_g2_scratch_gpio_set_smi(struct mv88e6xxx_chip *chip, + bool external) +{ + return -EOPNOTSUPP; +} + #endif /* CONFIG_NET_DSA_MV88E6XXX_GLOBAL2 */ #endif /* _MV88E6XXX_GLOBAL2_H */ diff --git a/drivers/net/dsa/mv88e6xxx/global2_avb.c b/drivers/net/dsa/mv88e6xxx/global2_avb.c new file mode 100644 index 000000000000..2e398ccb88ca --- /dev/null +++ b/drivers/net/dsa/mv88e6xxx/global2_avb.c @@ -0,0 +1,193 @@ +/* + * Marvell 88E6xxx Switch Global 2 Registers support + * + * Copyright (c) 2008 Marvell Semiconductor + * + * Copyright (c) 2016-2017 Savoir-faire Linux Inc. + * Vivien Didelot <vivien.didelot@savoirfairelinux.com> + * + * Copyright (c) 2017 National Instruments + * Brandon Streiff <brandon.streiff@ni.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include "global2.h" + +/* Offset 0x16: AVB Command Register + * Offset 0x17: AVB Data Register + * + * There are two different versions of this register interface: + * "6352": 3-bit "op" field, 4-bit "port" field. + * "6390": 2-bit "op" field, 5-bit "port" field. + * + * The "op" codes are different between the two, as well as the special + * port fields for global PTP and TAI configuration. + */ + +/* mv88e6xxx_g2_avb_read -- Read one or multiple 16-bit words. + * The hardware supports snapshotting up to four contiguous registers. + */ +static int mv88e6xxx_g2_avb_read(struct mv88e6xxx_chip *chip, u16 readop, + u16 *data, int len) +{ + int err; + int i; + + /* Hardware can only snapshot four words. */ + if (len > 4) + return -E2BIG; + + err = mv88e6xxx_g2_update(chip, MV88E6352_G2_AVB_CMD, readop); + if (err) + return err; + + for (i = 0; i < len; ++i) { + err = mv88e6xxx_g2_read(chip, MV88E6352_G2_AVB_DATA, + &data[i]); + if (err) + return err; + } + + return 0; +} + +/* mv88e6xxx_g2_avb_write -- Write one 16-bit word. */ +static int mv88e6xxx_g2_avb_write(struct mv88e6xxx_chip *chip, u16 writeop, + u16 data) +{ + int err; + + err = mv88e6xxx_g2_write(chip, MV88E6352_G2_AVB_DATA, data); + if (err) + return err; + + return mv88e6xxx_g2_update(chip, MV88E6352_G2_AVB_CMD, writeop); +} + +static int mv88e6352_g2_avb_port_ptp_read(struct mv88e6xxx_chip *chip, + int port, int addr, u16 *data, + int len) +{ + u16 readop = (len == 1 ? MV88E6352_G2_AVB_CMD_OP_READ : + MV88E6352_G2_AVB_CMD_OP_READ_INCR) | + (port << 8) | (MV88E6352_G2_AVB_CMD_BLOCK_PTP << 5) | + addr; + + return mv88e6xxx_g2_avb_read(chip, readop, data, len); +} + +static int mv88e6352_g2_avb_port_ptp_write(struct mv88e6xxx_chip *chip, + int port, int addr, u16 data) +{ + u16 writeop = MV88E6352_G2_AVB_CMD_OP_WRITE | (port << 8) | + (MV88E6352_G2_AVB_CMD_BLOCK_PTP << 5) | addr; + + return mv88e6xxx_g2_avb_write(chip, writeop, data); +} + +static int mv88e6352_g2_avb_ptp_read(struct mv88e6xxx_chip *chip, int addr, + u16 *data, int len) +{ + return mv88e6352_g2_avb_port_ptp_read(chip, + MV88E6352_G2_AVB_CMD_PORT_PTPGLOBAL, + addr, data, len); +} + +static int mv88e6352_g2_avb_ptp_write(struct mv88e6xxx_chip *chip, int addr, + u16 data) +{ + return mv88e6352_g2_avb_port_ptp_write(chip, + MV88E6352_G2_AVB_CMD_PORT_PTPGLOBAL, + addr, data); +} + +static int mv88e6352_g2_avb_tai_read(struct mv88e6xxx_chip *chip, int addr, + u16 *data, int len) +{ + return mv88e6352_g2_avb_port_ptp_read(chip, + MV88E6352_G2_AVB_CMD_PORT_TAIGLOBAL, + addr, data, len); +} + +static int mv88e6352_g2_avb_tai_write(struct mv88e6xxx_chip *chip, int addr, + u16 data) +{ + return mv88e6352_g2_avb_port_ptp_write(chip, + MV88E6352_G2_AVB_CMD_PORT_TAIGLOBAL, + addr, data); +} + +const struct mv88e6xxx_avb_ops mv88e6352_avb_ops = { + .port_ptp_read = mv88e6352_g2_avb_port_ptp_read, + .port_ptp_write = mv88e6352_g2_avb_port_ptp_write, + .ptp_read = mv88e6352_g2_avb_ptp_read, + .ptp_write = mv88e6352_g2_avb_ptp_write, + .tai_read = mv88e6352_g2_avb_tai_read, + .tai_write = mv88e6352_g2_avb_tai_write, +}; + +static int mv88e6390_g2_avb_port_ptp_read(struct mv88e6xxx_chip *chip, + int port, int addr, u16 *data, + int len) +{ + u16 readop = (len == 1 ? MV88E6390_G2_AVB_CMD_OP_READ : + MV88E6390_G2_AVB_CMD_OP_READ_INCR) | + (port << 8) | (MV88E6352_G2_AVB_CMD_BLOCK_PTP << 5) | + addr; + + return mv88e6xxx_g2_avb_read(chip, readop, data, len); +} + +static int mv88e6390_g2_avb_port_ptp_write(struct mv88e6xxx_chip *chip, + int port, int addr, u16 data) +{ + u16 writeop = MV88E6390_G2_AVB_CMD_OP_WRITE | (port << 8) | + (MV88E6352_G2_AVB_CMD_BLOCK_PTP << 5) | addr; + + return mv88e6xxx_g2_avb_write(chip, writeop, data); +} + +static int mv88e6390_g2_avb_ptp_read(struct mv88e6xxx_chip *chip, int addr, + u16 *data, int len) +{ + return mv88e6390_g2_avb_port_ptp_read(chip, + MV88E6390_G2_AVB_CMD_PORT_PTPGLOBAL, + addr, data, len); +} + +static int mv88e6390_g2_avb_ptp_write(struct mv88e6xxx_chip *chip, int addr, + u16 data) +{ + return mv88e6390_g2_avb_port_ptp_write(chip, + MV88E6390_G2_AVB_CMD_PORT_PTPGLOBAL, + addr, data); +} + +static int mv88e6390_g2_avb_tai_read(struct mv88e6xxx_chip *chip, int addr, + u16 *data, int len) +{ + return mv88e6390_g2_avb_port_ptp_read(chip, + MV88E6390_G2_AVB_CMD_PORT_TAIGLOBAL, + addr, data, len); +} + +static int mv88e6390_g2_avb_tai_write(struct mv88e6xxx_chip *chip, int addr, + u16 data) +{ + return mv88e6390_g2_avb_port_ptp_write(chip, + MV88E6390_G2_AVB_CMD_PORT_TAIGLOBAL, + addr, data); +} + +const struct mv88e6xxx_avb_ops mv88e6390_avb_ops = { + .port_ptp_read = mv88e6390_g2_avb_port_ptp_read, + .port_ptp_write = mv88e6390_g2_avb_port_ptp_write, + .ptp_read = mv88e6390_g2_avb_ptp_read, + .ptp_write = mv88e6390_g2_avb_ptp_write, + .tai_read = mv88e6390_g2_avb_tai_read, + .tai_write = mv88e6390_g2_avb_tai_write, +}; diff --git a/drivers/net/dsa/mv88e6xxx/global2_scratch.c b/drivers/net/dsa/mv88e6xxx/global2_scratch.c new file mode 100644 index 000000000000..3f92b8892dc7 --- /dev/null +++ b/drivers/net/dsa/mv88e6xxx/global2_scratch.c @@ -0,0 +1,291 @@ +/* + * Marvell 88E6xxx Switch Global 2 Scratch & Misc Registers support + * + * Copyright (c) 2008 Marvell Semiconductor + * + * Copyright (c) 2017 National Instruments + * Brandon Streiff <brandon.streiff@ni.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include "chip.h" +#include "global2.h" + +/* Offset 0x1A: Scratch and Misc. Register */ +static int mv88e6xxx_g2_scratch_read(struct mv88e6xxx_chip *chip, int reg, + u8 *data) +{ + u16 value; + int err; + + err = mv88e6xxx_g2_write(chip, MV88E6XXX_G2_SCRATCH_MISC_MISC, + reg << 8); + if (err) + return err; + + err = mv88e6xxx_g2_read(chip, MV88E6XXX_G2_SCRATCH_MISC_MISC, &value); + if (err) + return err; + + *data = (value & MV88E6XXX_G2_SCRATCH_MISC_DATA_MASK); + + return 0; +} + +static int mv88e6xxx_g2_scratch_write(struct mv88e6xxx_chip *chip, int reg, + u8 data) +{ + u16 value = (reg << 8) | data; + + return mv88e6xxx_g2_update(chip, MV88E6XXX_G2_SCRATCH_MISC_MISC, value); +} + +/** + * mv88e6xxx_g2_scratch_gpio_get_bit - get a bit + * @chip: chip private data + * @nr: bit index + * @set: is bit set? + */ +static int mv88e6xxx_g2_scratch_get_bit(struct mv88e6xxx_chip *chip, + int base_reg, unsigned int offset, + int *set) +{ + int reg = base_reg + (offset / 8); + u8 mask = (1 << (offset & 0x7)); + u8 val; + int err; + + err = mv88e6xxx_g2_scratch_read(chip, reg, &val); + if (err) + return err; + + *set = !!(mask & val); + + return 0; +} + +/** + * mv88e6xxx_g2_scratch_gpio_set_bit - set (or clear) a bit + * @chip: chip private data + * @nr: bit index + * @set: set if true, clear if false + * + * Helper function for dealing with the direction and data registers. + */ +static int mv88e6xxx_g2_scratch_set_bit(struct mv88e6xxx_chip *chip, + int base_reg, unsigned int offset, + int set) +{ + int reg = base_reg + (offset / 8); + u8 mask = (1 << (offset & 0x7)); + u8 val; + int err; + + err = mv88e6xxx_g2_scratch_read(chip, reg, &val); + if (err) + return err; + + if (set) + val |= mask; + else + val &= ~mask; + + return mv88e6xxx_g2_scratch_write(chip, reg, val); +} + +/** + * mv88e6352_g2_scratch_gpio_get_data - get data on gpio pin + * @chip: chip private data + * @pin: gpio index + * + * Return: 0 for low, 1 for high, negative error + */ +static int mv88e6352_g2_scratch_gpio_get_data(struct mv88e6xxx_chip *chip, + unsigned int pin) +{ + int val = 0; + int err; + + err = mv88e6xxx_g2_scratch_get_bit(chip, + MV88E6352_G2_SCRATCH_GPIO_DATA0, + pin, &val); + if (err) + return err; + + return val; +} + +/** + * mv88e6352_g2_scratch_gpio_set_data - set data on gpio pin + * @chip: chip private data + * @pin: gpio index + * @value: value to set + */ +static int mv88e6352_g2_scratch_gpio_set_data(struct mv88e6xxx_chip *chip, + unsigned int pin, int value) +{ + u8 mask = (1 << (pin & 0x7)); + int offset = (pin / 8); + int reg; + + reg = MV88E6352_G2_SCRATCH_GPIO_DATA0 + offset; + + if (value) + chip->gpio_data[offset] |= mask; + else + chip->gpio_data[offset] &= ~mask; + + return mv88e6xxx_g2_scratch_write(chip, reg, chip->gpio_data[offset]); +} + +/** + * mv88e6352_g2_scratch_gpio_get_dir - get direction of gpio pin + * @chip: chip private data + * @pin: gpio index + * + * Return: 0 for output, 1 for input (same as GPIOF_DIR_XXX). + */ +static int mv88e6352_g2_scratch_gpio_get_dir(struct mv88e6xxx_chip *chip, + unsigned int pin) +{ + int val = 0; + int err; + + err = mv88e6xxx_g2_scratch_get_bit(chip, + MV88E6352_G2_SCRATCH_GPIO_DIR0, + pin, &val); + if (err) + return err; + + return val; +} + +/** + * mv88e6352_g2_scratch_gpio_set_dir - set direction of gpio pin + * @chip: chip private data + * @pin: gpio index + */ +static int mv88e6352_g2_scratch_gpio_set_dir(struct mv88e6xxx_chip *chip, + unsigned int pin, bool input) +{ + int value = (input ? MV88E6352_G2_SCRATCH_GPIO_DIR_IN : + MV88E6352_G2_SCRATCH_GPIO_DIR_OUT); + + return mv88e6xxx_g2_scratch_set_bit(chip, + MV88E6352_G2_SCRATCH_GPIO_DIR0, + pin, value); +} + +/** + * mv88e6352_g2_scratch_gpio_get_pctl - get pin control setting + * @chip: chip private data + * @pin: gpio index + * @func: function number + * + * Note that the function numbers themselves may vary by chipset. + */ +static int mv88e6352_g2_scratch_gpio_get_pctl(struct mv88e6xxx_chip *chip, + unsigned int pin, int *func) +{ + int reg = MV88E6352_G2_SCRATCH_GPIO_PCTL0 + (pin / 2); + int offset = (pin & 0x1) ? 4 : 0; + u8 mask = (0x7 << offset); + int err; + u8 val; + + err = mv88e6xxx_g2_scratch_read(chip, reg, &val); + if (err) + return err; + + *func = (val & mask) >> offset; + + return 0; +} + +/** + * mv88e6352_g2_scratch_gpio_set_pctl - set pin control setting + * @chip: chip private data + * @pin: gpio index + * @func: function number + */ +static int mv88e6352_g2_scratch_gpio_set_pctl(struct mv88e6xxx_chip *chip, + unsigned int pin, int func) +{ + int reg = MV88E6352_G2_SCRATCH_GPIO_PCTL0 + (pin / 2); + int offset = (pin & 0x1) ? 4 : 0; + u8 mask = (0x7 << offset); + int err; + u8 val; + + err = mv88e6xxx_g2_scratch_read(chip, reg, &val); + if (err) + return err; + + val = (val & ~mask) | ((func & mask) << offset); + + return mv88e6xxx_g2_scratch_write(chip, reg, val); +} + +const struct mv88e6xxx_gpio_ops mv88e6352_gpio_ops = { + .get_data = mv88e6352_g2_scratch_gpio_get_data, + .set_data = mv88e6352_g2_scratch_gpio_set_data, + .get_dir = mv88e6352_g2_scratch_gpio_get_dir, + .set_dir = mv88e6352_g2_scratch_gpio_set_dir, + .get_pctl = mv88e6352_g2_scratch_gpio_get_pctl, + .set_pctl = mv88e6352_g2_scratch_gpio_set_pctl, +}; + +/** + * mv88e6xxx_g2_gpio_set_smi - set gpio muxing for external smi + * @chip: chip private data + * @external: set mux for external smi, or free for gpio usage + * + * Some mv88e6xxx models have GPIO pins that may be configured as + * an external SMI interface, or they may be made free for other + * GPIO uses. + */ +int mv88e6xxx_g2_scratch_gpio_set_smi(struct mv88e6xxx_chip *chip, + bool external) +{ + int misc_cfg = MV88E6352_G2_SCRATCH_MISC_CFG; + int config_data1 = MV88E6352_G2_SCRATCH_CONFIG_DATA1; + int config_data2 = MV88E6352_G2_SCRATCH_CONFIG_DATA2; + bool no_cpu; + u8 p0_mode; + int err; + u8 val; + + err = mv88e6xxx_g2_scratch_read(chip, config_data2, &val); + if (err) + return err; + + p0_mode = val & MV88E6352_G2_SCRATCH_CONFIG_DATA2_P0_MODE_MASK; + + if (p0_mode == 0x01 || p0_mode == 0x02) + return -EBUSY; + + err = mv88e6xxx_g2_scratch_read(chip, config_data1, &val); + if (err) + return err; + + no_cpu = !!(val & MV88E6352_G2_SCRATCH_CONFIG_DATA1_NO_CPU); + + err = mv88e6xxx_g2_scratch_read(chip, misc_cfg, &val); + if (err) + return err; + + /* NO_CPU being 0 inverts the meaning of the bit */ + if (!no_cpu) + external = !external; + + if (external) + val |= MV88E6352_G2_SCRATCH_MISC_CFG_NORMALSMI; + else + val &= ~MV88E6352_G2_SCRATCH_MISC_CFG_NORMALSMI; + + return mv88e6xxx_g2_scratch_write(chip, misc_cfg, val); +} diff --git a/drivers/net/dsa/mv88e6xxx/hwtstamp.c b/drivers/net/dsa/mv88e6xxx/hwtstamp.c new file mode 100644 index 000000000000..ac7694c71266 --- /dev/null +++ b/drivers/net/dsa/mv88e6xxx/hwtstamp.c @@ -0,0 +1,576 @@ +/* + * Marvell 88E6xxx Switch hardware timestamping support + * + * Copyright (c) 2008 Marvell Semiconductor + * + * Copyright (c) 2017 National Instruments + * Erik Hons <erik.hons@ni.com> + * Brandon Streiff <brandon.streiff@ni.com> + * Dane Wagner <dane.wagner@ni.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include "chip.h" +#include "global2.h" +#include "hwtstamp.h" +#include "ptp.h" +#include <linux/ptp_classify.h> + +#define SKB_PTP_TYPE(__skb) (*(unsigned int *)((__skb)->cb)) + +static int mv88e6xxx_port_ptp_read(struct mv88e6xxx_chip *chip, int port, + int addr, u16 *data, int len) +{ + if (!chip->info->ops->avb_ops->port_ptp_read) + return -EOPNOTSUPP; + + return chip->info->ops->avb_ops->port_ptp_read(chip, port, addr, + data, len); +} + +static int mv88e6xxx_port_ptp_write(struct mv88e6xxx_chip *chip, int port, + int addr, u16 data) +{ + if (!chip->info->ops->avb_ops->port_ptp_write) + return -EOPNOTSUPP; + + return chip->info->ops->avb_ops->port_ptp_write(chip, port, addr, + data); +} + +static int mv88e6xxx_ptp_write(struct mv88e6xxx_chip *chip, int addr, + u16 data) +{ + if (!chip->info->ops->avb_ops->ptp_write) + return -EOPNOTSUPP; + + return chip->info->ops->avb_ops->ptp_write(chip, addr, data); +} + +/* TX_TSTAMP_TIMEOUT: This limits the time spent polling for a TX + * timestamp. When working properly, hardware will produce a timestamp + * within 1ms. Software may enounter delays due to MDIO contention, so + * the timeout is set accordingly. + */ +#define TX_TSTAMP_TIMEOUT msecs_to_jiffies(20) + +int mv88e6xxx_get_ts_info(struct dsa_switch *ds, int port, + struct ethtool_ts_info *info) +{ + struct mv88e6xxx_chip *chip = ds->priv; + + if (!chip->info->ptp_support) + return -EOPNOTSUPP; + + info->so_timestamping = + SOF_TIMESTAMPING_TX_HARDWARE | + SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; + info->phc_index = ptp_clock_index(chip->ptp_clock); + info->tx_types = + (1 << HWTSTAMP_TX_OFF) | + (1 << HWTSTAMP_TX_ON); + info->rx_filters = + (1 << HWTSTAMP_FILTER_NONE) | + (1 << HWTSTAMP_FILTER_PTP_V2_L4_EVENT) | + (1 << HWTSTAMP_FILTER_PTP_V2_L4_SYNC) | + (1 << HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ) | + (1 << HWTSTAMP_FILTER_PTP_V2_L2_EVENT) | + (1 << HWTSTAMP_FILTER_PTP_V2_L2_SYNC) | + (1 << HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ) | + (1 << HWTSTAMP_FILTER_PTP_V2_EVENT) | + (1 << HWTSTAMP_FILTER_PTP_V2_SYNC) | + (1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ); + + return 0; +} + +static int mv88e6xxx_set_hwtstamp_config(struct mv88e6xxx_chip *chip, int port, + struct hwtstamp_config *config) +{ + struct mv88e6xxx_port_hwtstamp *ps = &chip->port_hwtstamp[port]; + bool tstamp_enable = false; + u16 port_config0; + int err; + + /* Prevent the TX/RX paths from trying to interact with the + * timestamp hardware while we reconfigure it. + */ + clear_bit_unlock(MV88E6XXX_HWTSTAMP_ENABLED, &ps->state); + + /* reserved for future extensions */ + if (config->flags) + return -EINVAL; + + switch (config->tx_type) { + case HWTSTAMP_TX_OFF: + tstamp_enable = false; + break; + case HWTSTAMP_TX_ON: + tstamp_enable = true; + break; + default: + return -ERANGE; + } + + /* The switch supports timestamping both L2 and L4; one cannot be + * disabled independently of the other. + */ + switch (config->rx_filter) { + case HWTSTAMP_FILTER_NONE: + tstamp_enable = false; + break; + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + break; + case HWTSTAMP_FILTER_ALL: + default: + config->rx_filter = HWTSTAMP_FILTER_NONE; + return -ERANGE; + } + + if (tstamp_enable) { + /* Disable transportSpecific value matching, so that packets + * with either 1588 (0) and 802.1AS (1) will be timestamped. + */ + port_config0 = MV88E6XXX_PORT_PTP_CFG0_DISABLE_TSPEC_MATCH; + } else { + /* Disable PTP. This disables both RX and TX timestamping. */ + port_config0 = MV88E6XXX_PORT_PTP_CFG0_DISABLE_PTP; + } + + mutex_lock(&chip->reg_lock); + err = mv88e6xxx_port_ptp_write(chip, port, MV88E6XXX_PORT_PTP_CFG0, + port_config0); + mutex_unlock(&chip->reg_lock); + + if (err < 0) + return err; + + /* Once hardware has been configured, enable timestamp checks + * in the RX/TX paths. + */ + if (tstamp_enable) + set_bit(MV88E6XXX_HWTSTAMP_ENABLED, &ps->state); + + return 0; +} + +int mv88e6xxx_port_hwtstamp_set(struct dsa_switch *ds, int port, + struct ifreq *ifr) +{ + struct mv88e6xxx_chip *chip = ds->priv; + struct mv88e6xxx_port_hwtstamp *ps = &chip->port_hwtstamp[port]; + struct hwtstamp_config config; + int err; + + if (!chip->info->ptp_support) + return -EOPNOTSUPP; + + if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) + return -EFAULT; + + err = mv88e6xxx_set_hwtstamp_config(chip, port, &config); + if (err) + return err; + + /* Save the chosen configuration to be returned later. */ + memcpy(&ps->tstamp_config, &config, sizeof(config)); + + return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? + -EFAULT : 0; +} + +int mv88e6xxx_port_hwtstamp_get(struct dsa_switch *ds, int port, + struct ifreq *ifr) +{ + struct mv88e6xxx_chip *chip = ds->priv; + struct mv88e6xxx_port_hwtstamp *ps = &chip->port_hwtstamp[port]; + struct hwtstamp_config *config = &ps->tstamp_config; + + if (!chip->info->ptp_support) + return -EOPNOTSUPP; + + return copy_to_user(ifr->ifr_data, config, sizeof(*config)) ? + -EFAULT : 0; +} + +/* Get the start of the PTP header in this skb */ +static u8 *parse_ptp_header(struct sk_buff *skb, unsigned int type) +{ + u8 *data = skb_mac_header(skb); + unsigned int offset = 0; + + if (type & PTP_CLASS_VLAN) + offset += VLAN_HLEN; + + switch (type & PTP_CLASS_PMASK) { + case PTP_CLASS_IPV4: + offset += ETH_HLEN + IPV4_HLEN(data + offset) + UDP_HLEN; + break; + case PTP_CLASS_IPV6: + offset += ETH_HLEN + IP6_HLEN + UDP_HLEN; + break; + case PTP_CLASS_L2: + offset += ETH_HLEN; + break; + default: + return NULL; + } + + /* Ensure that the entire header is present in this packet. */ + if (skb->len + ETH_HLEN < offset + 34) + return NULL; + + return data + offset; +} + +/* Returns a pointer to the PTP header if the caller should time stamp, + * or NULL if the caller should not. + */ +static u8 *mv88e6xxx_should_tstamp(struct mv88e6xxx_chip *chip, int port, + struct sk_buff *skb, unsigned int type) +{ + struct mv88e6xxx_port_hwtstamp *ps = &chip->port_hwtstamp[port]; + u8 *hdr; + + if (!chip->info->ptp_support) + return NULL; + + hdr = parse_ptp_header(skb, type); + if (!hdr) + return NULL; + + if (!test_bit(MV88E6XXX_HWTSTAMP_ENABLED, &ps->state)) + return NULL; + + return hdr; +} + +static int mv88e6xxx_ts_valid(u16 status) +{ + if (!(status & MV88E6XXX_PTP_TS_VALID)) + return 0; + if (status & MV88E6XXX_PTP_TS_STATUS_MASK) + return 0; + return 1; +} + +static int seq_match(struct sk_buff *skb, u16 ts_seqid) +{ + unsigned int type = SKB_PTP_TYPE(skb); + u8 *hdr = parse_ptp_header(skb, type); + __be16 *seqid; + + seqid = (__be16 *)(hdr + OFF_PTP_SEQUENCE_ID); + + return ts_seqid == ntohs(*seqid); +} + +static void mv88e6xxx_get_rxts(struct mv88e6xxx_chip *chip, + struct mv88e6xxx_port_hwtstamp *ps, + struct sk_buff *skb, u16 reg, + struct sk_buff_head *rxq) +{ + u16 buf[4] = { 0 }, status, seq_id; + u64 ns, timelo, timehi; + struct skb_shared_hwtstamps *shwt; + int err; + + mutex_lock(&chip->reg_lock); + err = mv88e6xxx_port_ptp_read(chip, ps->port_id, + reg, buf, ARRAY_SIZE(buf)); + mutex_unlock(&chip->reg_lock); + if (err) + pr_err("failed to get the receive time stamp\n"); + + status = buf[0]; + timelo = buf[1]; + timehi = buf[2]; + seq_id = buf[3]; + + if (status & MV88E6XXX_PTP_TS_VALID) { + mutex_lock(&chip->reg_lock); + err = mv88e6xxx_port_ptp_write(chip, ps->port_id, reg, 0); + mutex_unlock(&chip->reg_lock); + if (err) + pr_err("failed to clear the receive status\n"); + } + /* Since the device can only handle one time stamp at a time, + * we purge any extra frames from the queue. + */ + for ( ; skb; skb = skb_dequeue(rxq)) { + if (mv88e6xxx_ts_valid(status) && seq_match(skb, seq_id)) { + ns = timehi << 16 | timelo; + + mutex_lock(&chip->reg_lock); + ns = timecounter_cyc2time(&chip->tstamp_tc, ns); + mutex_unlock(&chip->reg_lock); + shwt = skb_hwtstamps(skb); + memset(shwt, 0, sizeof(*shwt)); + shwt->hwtstamp = ns_to_ktime(ns); + status &= ~MV88E6XXX_PTP_TS_VALID; + } + netif_rx_ni(skb); + } +} + +static void mv88e6xxx_rxtstamp_work(struct mv88e6xxx_chip *chip, + struct mv88e6xxx_port_hwtstamp *ps) +{ + struct sk_buff *skb; + + skb = skb_dequeue(&ps->rx_queue); + + if (skb) + mv88e6xxx_get_rxts(chip, ps, skb, MV88E6XXX_PORT_PTP_ARR0_STS, + &ps->rx_queue); + + skb = skb_dequeue(&ps->rx_queue2); + if (skb) + mv88e6xxx_get_rxts(chip, ps, skb, MV88E6XXX_PORT_PTP_ARR1_STS, + &ps->rx_queue2); +} + +static int is_pdelay_resp(u8 *msgtype) +{ + return (*msgtype & 0xf) == 3; +} + +bool mv88e6xxx_port_rxtstamp(struct dsa_switch *ds, int port, + struct sk_buff *skb, unsigned int type) +{ + struct mv88e6xxx_port_hwtstamp *ps; + struct mv88e6xxx_chip *chip; + u8 *hdr; + + chip = ds->priv; + ps = &chip->port_hwtstamp[port]; + + if (ps->tstamp_config.rx_filter != HWTSTAMP_FILTER_PTP_V2_EVENT) + return false; + + hdr = mv88e6xxx_should_tstamp(chip, port, skb, type); + if (!hdr) + return false; + + SKB_PTP_TYPE(skb) = type; + + if (is_pdelay_resp(hdr)) + skb_queue_tail(&ps->rx_queue2, skb); + else + skb_queue_tail(&ps->rx_queue, skb); + + ptp_schedule_worker(chip->ptp_clock, 0); + + return true; +} + +static int mv88e6xxx_txtstamp_work(struct mv88e6xxx_chip *chip, + struct mv88e6xxx_port_hwtstamp *ps) +{ + struct skb_shared_hwtstamps shhwtstamps; + u16 departure_block[4], status; + struct sk_buff *tmp_skb; + u32 time_raw; + int err; + u64 ns; + + if (!ps->tx_skb) + return 0; + + mutex_lock(&chip->reg_lock); + err = mv88e6xxx_port_ptp_read(chip, ps->port_id, + MV88E6XXX_PORT_PTP_DEP_STS, + departure_block, + ARRAY_SIZE(departure_block)); + mutex_unlock(&chip->reg_lock); + + if (err) + goto free_and_clear_skb; + + if (!(departure_block[0] & MV88E6XXX_PTP_TS_VALID)) { + if (time_is_before_jiffies(ps->tx_tstamp_start + + TX_TSTAMP_TIMEOUT)) { + dev_warn(chip->dev, "p%d: clearing tx timestamp hang\n", + ps->port_id); + goto free_and_clear_skb; + } + /* The timestamp should be available quickly, while getting it + * is high priority and time bounded to only 10ms. A poll is + * warranted so restart the work. + */ + return 1; + } + + /* We have the timestamp; go ahead and clear valid now */ + mutex_lock(&chip->reg_lock); + mv88e6xxx_port_ptp_write(chip, ps->port_id, + MV88E6XXX_PORT_PTP_DEP_STS, 0); + mutex_unlock(&chip->reg_lock); + + status = departure_block[0] & MV88E6XXX_PTP_TS_STATUS_MASK; + if (status != MV88E6XXX_PTP_TS_STATUS_NORMAL) { + dev_warn(chip->dev, "p%d: tx timestamp overrun\n", ps->port_id); + goto free_and_clear_skb; + } + + if (departure_block[3] != ps->tx_seq_id) { + dev_warn(chip->dev, "p%d: unexpected seq. id\n", ps->port_id); + goto free_and_clear_skb; + } + + memset(&shhwtstamps, 0, sizeof(shhwtstamps)); + time_raw = ((u32)departure_block[2] << 16) | departure_block[1]; + mutex_lock(&chip->reg_lock); + ns = timecounter_cyc2time(&chip->tstamp_tc, time_raw); + mutex_unlock(&chip->reg_lock); + shhwtstamps.hwtstamp = ns_to_ktime(ns); + + dev_dbg(chip->dev, + "p%d: txtstamp %llx status 0x%04x skb ID 0x%04x hw ID 0x%04x\n", + ps->port_id, ktime_to_ns(shhwtstamps.hwtstamp), + departure_block[0], ps->tx_seq_id, departure_block[3]); + + /* skb_complete_tx_timestamp() will free up the client to make + * another timestamp-able transmit. We have to be ready for it + * -- by clearing the ps->tx_skb "flag" -- beforehand. + */ + + tmp_skb = ps->tx_skb; + ps->tx_skb = NULL; + clear_bit_unlock(MV88E6XXX_HWTSTAMP_TX_IN_PROGRESS, &ps->state); + skb_complete_tx_timestamp(tmp_skb, &shhwtstamps); + + return 0; + +free_and_clear_skb: + dev_kfree_skb_any(ps->tx_skb); + ps->tx_skb = NULL; + clear_bit_unlock(MV88E6XXX_HWTSTAMP_TX_IN_PROGRESS, &ps->state); + + return 0; +} + +long mv88e6xxx_hwtstamp_work(struct ptp_clock_info *ptp) +{ + struct mv88e6xxx_chip *chip = ptp_to_chip(ptp); + struct dsa_switch *ds = chip->ds; + struct mv88e6xxx_port_hwtstamp *ps; + int i, restart = 0; + + for (i = 0; i < ds->num_ports; i++) { + if (!dsa_is_user_port(ds, i)) + continue; + + ps = &chip->port_hwtstamp[i]; + if (test_bit(MV88E6XXX_HWTSTAMP_TX_IN_PROGRESS, &ps->state)) + restart |= mv88e6xxx_txtstamp_work(chip, ps); + + mv88e6xxx_rxtstamp_work(chip, ps); + } + + return restart ? 1 : -1; +} + +bool mv88e6xxx_port_txtstamp(struct dsa_switch *ds, int port, + struct sk_buff *clone, unsigned int type) +{ + struct mv88e6xxx_chip *chip = ds->priv; + struct mv88e6xxx_port_hwtstamp *ps = &chip->port_hwtstamp[port]; + __be16 *seq_ptr; + u8 *hdr; + + if (!(skb_shinfo(clone)->tx_flags & SKBTX_HW_TSTAMP)) + return false; + + hdr = mv88e6xxx_should_tstamp(chip, port, clone, type); + if (!hdr) + return false; + + seq_ptr = (__be16 *)(hdr + OFF_PTP_SEQUENCE_ID); + + if (test_and_set_bit_lock(MV88E6XXX_HWTSTAMP_TX_IN_PROGRESS, + &ps->state)) + return false; + + ps->tx_skb = clone; + ps->tx_tstamp_start = jiffies; + ps->tx_seq_id = be16_to_cpup(seq_ptr); + + ptp_schedule_worker(chip->ptp_clock, 0); + return true; +} + +static int mv88e6xxx_hwtstamp_port_setup(struct mv88e6xxx_chip *chip, int port) +{ + struct mv88e6xxx_port_hwtstamp *ps = &chip->port_hwtstamp[port]; + + ps->port_id = port; + + skb_queue_head_init(&ps->rx_queue); + skb_queue_head_init(&ps->rx_queue2); + + return mv88e6xxx_port_ptp_write(chip, port, MV88E6XXX_PORT_PTP_CFG0, + MV88E6XXX_PORT_PTP_CFG0_DISABLE_PTP); +} + +int mv88e6xxx_hwtstamp_setup(struct mv88e6xxx_chip *chip) +{ + int err; + int i; + + /* Disable timestamping on all ports. */ + for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) { + err = mv88e6xxx_hwtstamp_port_setup(chip, i); + if (err) + return err; + } + + /* MV88E6XXX_PTP_MSG_TYPE is a mask of PTP message types to + * timestamp. This affects all ports that have timestamping enabled, + * but the timestamp config is per-port; thus we configure all events + * here and only support the HWTSTAMP_FILTER_*_EVENT filter types. + */ + err = mv88e6xxx_ptp_write(chip, MV88E6XXX_PTP_MSGTYPE, + MV88E6XXX_PTP_MSGTYPE_ALL_EVENT); + if (err) + return err; + + /* Use ARRIVAL1 for peer delay response messages. */ + err = mv88e6xxx_ptp_write(chip, MV88E6XXX_PTP_TS_ARRIVAL_PTR, + MV88E6XXX_PTP_MSGTYPE_PDLAY_RES); + if (err) + return err; + + /* 88E6341 devices default to timestamping at the PHY, but this has + * a hardware issue that results in unreliable timestamps. Force + * these devices to timestamp at the MAC. + */ + if (chip->info->family == MV88E6XXX_FAMILY_6341) { + u16 val = MV88E6341_PTP_CFG_UPDATE | + MV88E6341_PTP_CFG_MODE_IDX | + MV88E6341_PTP_CFG_MODE_TS_AT_MAC; + err = mv88e6xxx_ptp_write(chip, MV88E6341_PTP_CFG, val); + if (err) + return err; + } + + return 0; +} + +void mv88e6xxx_hwtstamp_free(struct mv88e6xxx_chip *chip) +{ +} diff --git a/drivers/net/dsa/mv88e6xxx/hwtstamp.h b/drivers/net/dsa/mv88e6xxx/hwtstamp.h new file mode 100644 index 000000000000..bc71c9212a08 --- /dev/null +++ b/drivers/net/dsa/mv88e6xxx/hwtstamp.h @@ -0,0 +1,172 @@ +/* + * Marvell 88E6xxx Switch hardware timestamping support + * + * Copyright (c) 2008 Marvell Semiconductor + * + * Copyright (c) 2017 National Instruments + * Erik Hons <erik.hons@ni.com> + * Brandon Streiff <brandon.streiff@ni.com> + * Dane Wagner <dane.wagner@ni.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef _MV88E6XXX_HWTSTAMP_H +#define _MV88E6XXX_HWTSTAMP_H + +#include "chip.h" + +/* Global PTP registers */ +/* Offset 0x00: PTP EtherType */ +#define MV88E6XXX_PTP_ETHERTYPE 0x00 + +/* Offset 0x01: Message Type Timestamp Enables */ +#define MV88E6XXX_PTP_MSGTYPE 0x01 +#define MV88E6XXX_PTP_MSGTYPE_SYNC 0x0001 +#define MV88E6XXX_PTP_MSGTYPE_DELAY_REQ 0x0002 +#define MV88E6XXX_PTP_MSGTYPE_PDLAY_REQ 0x0004 +#define MV88E6XXX_PTP_MSGTYPE_PDLAY_RES 0x0008 +#define MV88E6XXX_PTP_MSGTYPE_ALL_EVENT 0x000f + +/* Offset 0x02: Timestamp Arrival Capture Pointers */ +#define MV88E6XXX_PTP_TS_ARRIVAL_PTR 0x02 + +/* Offset 0x07: PTP Global Configuration */ +#define MV88E6341_PTP_CFG 0x07 +#define MV88E6341_PTP_CFG_UPDATE 0x8000 +#define MV88E6341_PTP_CFG_IDX_MASK 0x7f00 +#define MV88E6341_PTP_CFG_DATA_MASK 0x00ff +#define MV88E6341_PTP_CFG_MODE_IDX 0x0 +#define MV88E6341_PTP_CFG_MODE_TS_AT_PHY 0x00 +#define MV88E6341_PTP_CFG_MODE_TS_AT_MAC 0x80 + +/* Offset 0x08: PTP Interrupt Status */ +#define MV88E6XXX_PTP_IRQ_STATUS 0x08 + +/* Per-Port PTP Registers */ +/* Offset 0x00: PTP Configuration 0 */ +#define MV88E6XXX_PORT_PTP_CFG0 0x00 +#define MV88E6XXX_PORT_PTP_CFG0_TSPEC_SHIFT 12 +#define MV88E6XXX_PORT_PTP_CFG0_TSPEC_MASK 0xf000 +#define MV88E6XXX_PORT_PTP_CFG0_TSPEC_1588 0x0000 +#define MV88E6XXX_PORT_PTP_CFG0_TSPEC_8021AS 0x1000 +#define MV88E6XXX_PORT_PTP_CFG0_DISABLE_TSPEC_MATCH 0x0800 +#define MV88E6XXX_PORT_PTP_CFG0_DISABLE_OVERWRITE 0x0002 +#define MV88E6XXX_PORT_PTP_CFG0_DISABLE_PTP 0x0001 + +/* Offset 0x01: PTP Configuration 1 */ +#define MV88E6XXX_PORT_PTP_CFG1 0x01 + +/* Offset 0x02: PTP Configuration 2 */ +#define MV88E6XXX_PORT_PTP_CFG2 0x02 +#define MV88E6XXX_PORT_PTP_CFG2_EMBED_ARRIVAL 0x1000 +#define MV88E6XXX_PORT_PTP_CFG2_DEP_IRQ_EN 0x0002 +#define MV88E6XXX_PORT_PTP_CFG2_ARR_IRQ_EN 0x0001 + +/* Offset 0x03: PTP LED Configuration */ +#define MV88E6XXX_PORT_PTP_LED_CFG 0x03 + +/* Offset 0x08: PTP Arrival 0 Status */ +#define MV88E6XXX_PORT_PTP_ARR0_STS 0x08 + +/* Offset 0x09/0x0A: PTP Arrival 0 Time */ +#define MV88E6XXX_PORT_PTP_ARR0_TIME_LO 0x09 +#define MV88E6XXX_PORT_PTP_ARR0_TIME_HI 0x0a + +/* Offset 0x0B: PTP Arrival 0 Sequence ID */ +#define MV88E6XXX_PORT_PTP_ARR0_SEQID 0x0b + +/* Offset 0x0C: PTP Arrival 1 Status */ +#define MV88E6XXX_PORT_PTP_ARR1_STS 0x0c + +/* Offset 0x0D/0x0E: PTP Arrival 1 Time */ +#define MV88E6XXX_PORT_PTP_ARR1_TIME_LO 0x0d +#define MV88E6XXX_PORT_PTP_ARR1_TIME_HI 0x0e + +/* Offset 0x0F: PTP Arrival 1 Sequence ID */ +#define MV88E6XXX_PORT_PTP_ARR1_SEQID 0x0f + +/* Offset 0x10: PTP Departure Status */ +#define MV88E6XXX_PORT_PTP_DEP_STS 0x10 + +/* Offset 0x11/0x12: PTP Deperture Time */ +#define MV88E6XXX_PORT_PTP_DEP_TIME_LO 0x11 +#define MV88E6XXX_PORT_PTP_DEP_TIME_HI 0x12 + +/* Offset 0x13: PTP Departure Sequence ID */ +#define MV88E6XXX_PORT_PTP_DEP_SEQID 0x13 + +/* Status fields for arrival and depature timestamp status registers */ +#define MV88E6XXX_PTP_TS_STATUS_MASK 0x0006 +#define MV88E6XXX_PTP_TS_STATUS_NORMAL 0x0000 +#define MV88E6XXX_PTP_TS_STATUS_OVERWITTEN 0x0002 +#define MV88E6XXX_PTP_TS_STATUS_DISCARDED 0x0004 +#define MV88E6XXX_PTP_TS_VALID 0x0001 + +#ifdef CONFIG_NET_DSA_MV88E6XXX_PTP + +int mv88e6xxx_port_hwtstamp_set(struct dsa_switch *ds, int port, + struct ifreq *ifr); +int mv88e6xxx_port_hwtstamp_get(struct dsa_switch *ds, int port, + struct ifreq *ifr); + +bool mv88e6xxx_port_rxtstamp(struct dsa_switch *ds, int port, + struct sk_buff *clone, unsigned int type); +bool mv88e6xxx_port_txtstamp(struct dsa_switch *ds, int port, + struct sk_buff *clone, unsigned int type); + +int mv88e6xxx_get_ts_info(struct dsa_switch *ds, int port, + struct ethtool_ts_info *info); + +int mv88e6xxx_hwtstamp_setup(struct mv88e6xxx_chip *chip); +void mv88e6xxx_hwtstamp_free(struct mv88e6xxx_chip *chip); + +#else /* !CONFIG_NET_DSA_MV88E6XXX_PTP */ + +static inline int mv88e6xxx_port_hwtstamp_set(struct dsa_switch *ds, + int port, struct ifreq *ifr) +{ + return -EOPNOTSUPP; +} + +static inline int mv88e6xxx_port_hwtstamp_get(struct dsa_switch *ds, + int port, struct ifreq *ifr) +{ + return -EOPNOTSUPP; +} + +static inline bool mv88e6xxx_port_rxtstamp(struct dsa_switch *ds, int port, + struct sk_buff *clone, + unsigned int type) +{ + return false; +} + +static inline bool mv88e6xxx_port_txtstamp(struct dsa_switch *ds, int port, + struct sk_buff *clone, + unsigned int type) +{ + return false; +} + +static inline int mv88e6xxx_get_ts_info(struct dsa_switch *ds, int port, + struct ethtool_ts_info *info) +{ + return -EOPNOTSUPP; +} + +static inline int mv88e6xxx_hwtstamp_setup(struct mv88e6xxx_chip *chip) +{ + return 0; +} + +static inline void mv88e6xxx_hwtstamp_free(struct mv88e6xxx_chip *chip) +{ +} + +#endif /* CONFIG_NET_DSA_MV88E6XXX_PTP */ + +#endif /* _MV88E6XXX_HWTSTAMP_H */ diff --git a/drivers/net/dsa/mv88e6xxx/ptp.c b/drivers/net/dsa/mv88e6xxx/ptp.c new file mode 100644 index 000000000000..bd85e2c390e1 --- /dev/null +++ b/drivers/net/dsa/mv88e6xxx/ptp.c @@ -0,0 +1,381 @@ +/* + * Marvell 88E6xxx Switch PTP support + * + * Copyright (c) 2008 Marvell Semiconductor + * + * Copyright (c) 2017 National Instruments + * Erik Hons <erik.hons@ni.com> + * Brandon Streiff <brandon.streiff@ni.com> + * Dane Wagner <dane.wagner@ni.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include "chip.h" +#include "global2.h" +#include "ptp.h" + +/* Raw timestamps are in units of 8-ns clock periods. */ +#define CC_SHIFT 28 +#define CC_MULT (8 << CC_SHIFT) +#define CC_MULT_NUM (1 << 9) +#define CC_MULT_DEM 15625ULL + +#define TAI_EVENT_WORK_INTERVAL msecs_to_jiffies(100) + +#define cc_to_chip(cc) container_of(cc, struct mv88e6xxx_chip, tstamp_cc) +#define dw_overflow_to_chip(dw) container_of(dw, struct mv88e6xxx_chip, \ + overflow_work) +#define dw_tai_event_to_chip(dw) container_of(dw, struct mv88e6xxx_chip, \ + tai_event_work) + +static int mv88e6xxx_tai_read(struct mv88e6xxx_chip *chip, int addr, + u16 *data, int len) +{ + if (!chip->info->ops->avb_ops->tai_read) + return -EOPNOTSUPP; + + return chip->info->ops->avb_ops->tai_read(chip, addr, data, len); +} + +static int mv88e6xxx_tai_write(struct mv88e6xxx_chip *chip, int addr, u16 data) +{ + if (!chip->info->ops->avb_ops->tai_write) + return -EOPNOTSUPP; + + return chip->info->ops->avb_ops->tai_write(chip, addr, data); +} + +/* TODO: places where this are called should be using pinctrl */ +static int mv88e6xxx_set_gpio_func(struct mv88e6xxx_chip *chip, int pin, + int func, int input) +{ + int err; + + if (!chip->info->ops->gpio_ops) + return -EOPNOTSUPP; + + err = chip->info->ops->gpio_ops->set_dir(chip, pin, input); + if (err) + return err; + + return chip->info->ops->gpio_ops->set_pctl(chip, pin, func); +} + +static u64 mv88e6xxx_ptp_clock_read(const struct cyclecounter *cc) +{ + struct mv88e6xxx_chip *chip = cc_to_chip(cc); + u16 phc_time[2]; + int err; + + err = mv88e6xxx_tai_read(chip, MV88E6XXX_TAI_TIME_LO, phc_time, + ARRAY_SIZE(phc_time)); + if (err) + return 0; + else + return ((u32)phc_time[1] << 16) | phc_time[0]; +} + +/* mv88e6xxx_config_eventcap - configure TAI event capture + * @event: PTP_CLOCK_PPS (internal) or PTP_CLOCK_EXTTS (external) + * @rising: zero for falling-edge trigger, else rising-edge trigger + * + * This will also reset the capture sequence counter. + */ +static int mv88e6xxx_config_eventcap(struct mv88e6xxx_chip *chip, int event, + int rising) +{ + u16 global_config; + u16 cap_config; + int err; + + chip->evcap_config = MV88E6XXX_TAI_CFG_CAP_OVERWRITE | + MV88E6XXX_TAI_CFG_CAP_CTR_START; + if (!rising) + chip->evcap_config |= MV88E6XXX_TAI_CFG_EVREQ_FALLING; + + global_config = (chip->evcap_config | chip->trig_config); + err = mv88e6xxx_tai_write(chip, MV88E6XXX_TAI_CFG, global_config); + if (err) + return err; + + if (event == PTP_CLOCK_PPS) { + cap_config = MV88E6XXX_TAI_EVENT_STATUS_CAP_TRIG; + } else if (event == PTP_CLOCK_EXTTS) { + /* if STATUS_CAP_TRIG is unset we capture PTP_EVREQ events */ + cap_config = 0; + } else { + return -EINVAL; + } + + /* Write the capture config; this also clears the capture counter */ + err = mv88e6xxx_tai_write(chip, MV88E6XXX_TAI_EVENT_STATUS, + cap_config); + + return err; +} + +static void mv88e6xxx_tai_event_work(struct work_struct *ugly) +{ + struct delayed_work *dw = to_delayed_work(ugly); + struct mv88e6xxx_chip *chip = dw_tai_event_to_chip(dw); + struct ptp_clock_event ev; + u16 status[4]; + u32 raw_ts; + int err; + + mutex_lock(&chip->reg_lock); + err = mv88e6xxx_tai_read(chip, MV88E6XXX_TAI_EVENT_STATUS, + status, ARRAY_SIZE(status)); + mutex_unlock(&chip->reg_lock); + + if (err) { + dev_err(chip->dev, "failed to read TAI status register\n"); + return; + } + if (status[0] & MV88E6XXX_TAI_EVENT_STATUS_ERROR) { + dev_warn(chip->dev, "missed event capture\n"); + return; + } + if (!(status[0] & MV88E6XXX_TAI_EVENT_STATUS_VALID)) + goto out; + + raw_ts = ((u32)status[2] << 16) | status[1]; + + /* Clear the valid bit so the next timestamp can come in */ + status[0] &= ~MV88E6XXX_TAI_EVENT_STATUS_VALID; + mutex_lock(&chip->reg_lock); + err = mv88e6xxx_tai_write(chip, MV88E6XXX_TAI_EVENT_STATUS, status[0]); + mutex_unlock(&chip->reg_lock); + + /* This is an external timestamp */ + ev.type = PTP_CLOCK_EXTTS; + + /* We only have one timestamping channel. */ + ev.index = 0; + mutex_lock(&chip->reg_lock); + ev.timestamp = timecounter_cyc2time(&chip->tstamp_tc, raw_ts); + mutex_unlock(&chip->reg_lock); + + ptp_clock_event(chip->ptp_clock, &ev); +out: + schedule_delayed_work(&chip->tai_event_work, TAI_EVENT_WORK_INTERVAL); +} + +static int mv88e6xxx_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) +{ + struct mv88e6xxx_chip *chip = ptp_to_chip(ptp); + int neg_adj = 0; + u32 diff, mult; + u64 adj; + + if (scaled_ppm < 0) { + neg_adj = 1; + scaled_ppm = -scaled_ppm; + } + mult = CC_MULT; + adj = CC_MULT_NUM; + adj *= scaled_ppm; + diff = div_u64(adj, CC_MULT_DEM); + + mutex_lock(&chip->reg_lock); + + timecounter_read(&chip->tstamp_tc); + chip->tstamp_cc.mult = neg_adj ? mult - diff : mult + diff; + + mutex_unlock(&chip->reg_lock); + + return 0; +} + +static int mv88e6xxx_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) +{ + struct mv88e6xxx_chip *chip = ptp_to_chip(ptp); + + mutex_lock(&chip->reg_lock); + timecounter_adjtime(&chip->tstamp_tc, delta); + mutex_unlock(&chip->reg_lock); + + return 0; +} + +static int mv88e6xxx_ptp_gettime(struct ptp_clock_info *ptp, + struct timespec64 *ts) +{ + struct mv88e6xxx_chip *chip = ptp_to_chip(ptp); + u64 ns; + + mutex_lock(&chip->reg_lock); + ns = timecounter_read(&chip->tstamp_tc); + mutex_unlock(&chip->reg_lock); + + *ts = ns_to_timespec64(ns); + + return 0; +} + +static int mv88e6xxx_ptp_settime(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + struct mv88e6xxx_chip *chip = ptp_to_chip(ptp); + u64 ns; + + ns = timespec64_to_ns(ts); + + mutex_lock(&chip->reg_lock); + timecounter_init(&chip->tstamp_tc, &chip->tstamp_cc, ns); + mutex_unlock(&chip->reg_lock); + + return 0; +} + +static int mv88e6xxx_ptp_enable_extts(struct mv88e6xxx_chip *chip, + struct ptp_clock_request *rq, int on) +{ + int rising = (rq->extts.flags & PTP_RISING_EDGE); + int func; + int pin; + int err; + + pin = ptp_find_pin(chip->ptp_clock, PTP_PF_EXTTS, rq->extts.index); + + if (pin < 0) + return -EBUSY; + + mutex_lock(&chip->reg_lock); + + if (on) { + func = MV88E6352_G2_SCRATCH_GPIO_PCTL_EVREQ; + + err = mv88e6xxx_set_gpio_func(chip, pin, func, true); + if (err) + goto out; + + schedule_delayed_work(&chip->tai_event_work, + TAI_EVENT_WORK_INTERVAL); + + err = mv88e6xxx_config_eventcap(chip, PTP_CLOCK_EXTTS, rising); + } else { + func = MV88E6352_G2_SCRATCH_GPIO_PCTL_GPIO; + + err = mv88e6xxx_set_gpio_func(chip, pin, func, true); + + cancel_delayed_work_sync(&chip->tai_event_work); + } + +out: + mutex_unlock(&chip->reg_lock); + + return err; +} + +static int mv88e6xxx_ptp_enable(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, int on) +{ + struct mv88e6xxx_chip *chip = ptp_to_chip(ptp); + + switch (rq->type) { + case PTP_CLK_REQ_EXTTS: + return mv88e6xxx_ptp_enable_extts(chip, rq, on); + default: + return -EOPNOTSUPP; + } +} + +static int mv88e6xxx_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin, + enum ptp_pin_function func, unsigned int chan) +{ + switch (func) { + case PTP_PF_NONE: + case PTP_PF_EXTTS: + break; + case PTP_PF_PEROUT: + case PTP_PF_PHYSYNC: + return -EOPNOTSUPP; + } + return 0; +} + +/* With a 125MHz input clock, the 32-bit timestamp counter overflows in ~34.3 + * seconds; this task forces periodic reads so that we don't miss any. + */ +#define MV88E6XXX_TAI_OVERFLOW_PERIOD (HZ * 16) +static void mv88e6xxx_ptp_overflow_check(struct work_struct *work) +{ + struct delayed_work *dw = to_delayed_work(work); + struct mv88e6xxx_chip *chip = dw_overflow_to_chip(dw); + struct timespec64 ts; + + mv88e6xxx_ptp_gettime(&chip->ptp_clock_info, &ts); + + schedule_delayed_work(&chip->overflow_work, + MV88E6XXX_TAI_OVERFLOW_PERIOD); +} + +int mv88e6xxx_ptp_setup(struct mv88e6xxx_chip *chip) +{ + int i; + + /* Set up the cycle counter */ + memset(&chip->tstamp_cc, 0, sizeof(chip->tstamp_cc)); + chip->tstamp_cc.read = mv88e6xxx_ptp_clock_read; + chip->tstamp_cc.mask = CYCLECOUNTER_MASK(32); + chip->tstamp_cc.mult = CC_MULT; + chip->tstamp_cc.shift = CC_SHIFT; + + timecounter_init(&chip->tstamp_tc, &chip->tstamp_cc, + ktime_to_ns(ktime_get_real())); + + INIT_DELAYED_WORK(&chip->overflow_work, mv88e6xxx_ptp_overflow_check); + INIT_DELAYED_WORK(&chip->tai_event_work, mv88e6xxx_tai_event_work); + + chip->ptp_clock_info.owner = THIS_MODULE; + snprintf(chip->ptp_clock_info.name, sizeof(chip->ptp_clock_info.name), + dev_name(chip->dev)); + chip->ptp_clock_info.max_adj = 1000000; + + chip->ptp_clock_info.n_ext_ts = 1; + chip->ptp_clock_info.n_per_out = 0; + chip->ptp_clock_info.n_pins = mv88e6xxx_num_gpio(chip); + chip->ptp_clock_info.pps = 0; + + for (i = 0; i < chip->ptp_clock_info.n_pins; ++i) { + struct ptp_pin_desc *ppd = &chip->pin_config[i]; + + snprintf(ppd->name, sizeof(ppd->name), "mv88e6xxx_gpio%d", i); + ppd->index = i; + ppd->func = PTP_PF_NONE; + } + chip->ptp_clock_info.pin_config = chip->pin_config; + + chip->ptp_clock_info.adjfine = mv88e6xxx_ptp_adjfine; + chip->ptp_clock_info.adjtime = mv88e6xxx_ptp_adjtime; + chip->ptp_clock_info.gettime64 = mv88e6xxx_ptp_gettime; + chip->ptp_clock_info.settime64 = mv88e6xxx_ptp_settime; + chip->ptp_clock_info.enable = mv88e6xxx_ptp_enable; + chip->ptp_clock_info.verify = mv88e6xxx_ptp_verify; + chip->ptp_clock_info.do_aux_work = mv88e6xxx_hwtstamp_work; + + chip->ptp_clock = ptp_clock_register(&chip->ptp_clock_info, chip->dev); + if (IS_ERR(chip->ptp_clock)) + return PTR_ERR(chip->ptp_clock); + + schedule_delayed_work(&chip->overflow_work, + MV88E6XXX_TAI_OVERFLOW_PERIOD); + + return 0; +} + +void mv88e6xxx_ptp_free(struct mv88e6xxx_chip *chip) +{ + if (chip->ptp_clock) { + cancel_delayed_work_sync(&chip->overflow_work); + cancel_delayed_work_sync(&chip->tai_event_work); + + ptp_clock_unregister(chip->ptp_clock); + chip->ptp_clock = NULL; + } +} diff --git a/drivers/net/dsa/mv88e6xxx/ptp.h b/drivers/net/dsa/mv88e6xxx/ptp.h new file mode 100644 index 000000000000..10f271ab650d --- /dev/null +++ b/drivers/net/dsa/mv88e6xxx/ptp.h @@ -0,0 +1,108 @@ +/* + * Marvell 88E6xxx Switch PTP support + * + * Copyright (c) 2008 Marvell Semiconductor + * + * Copyright (c) 2017 National Instruments + * Erik Hons <erik.hons@ni.com> + * Brandon Streiff <brandon.streiff@ni.com> + * Dane Wagner <dane.wagner@ni.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef _MV88E6XXX_PTP_H +#define _MV88E6XXX_PTP_H + +#include "chip.h" + +/* Offset 0x00: TAI Global Config */ +#define MV88E6XXX_TAI_CFG 0x00 +#define MV88E6XXX_TAI_CFG_CAP_OVERWRITE 0x8000 +#define MV88E6XXX_TAI_CFG_CAP_CTR_START 0x4000 +#define MV88E6XXX_TAI_CFG_EVREQ_FALLING 0x2000 +#define MV88E6XXX_TAI_CFG_TRIG_ACTIVE_LO 0x1000 +#define MV88E6XXX_TAI_CFG_IRL_ENABLE 0x0400 +#define MV88E6XXX_TAI_CFG_TRIG_IRQ_EN 0x0200 +#define MV88E6XXX_TAI_CFG_EVREQ_IRQ_EN 0x0100 +#define MV88E6XXX_TAI_CFG_TRIG_LOCK 0x0080 +#define MV88E6XXX_TAI_CFG_BLOCK_UPDATE 0x0008 +#define MV88E6XXX_TAI_CFG_MULTI_PTP 0x0004 +#define MV88E6XXX_TAI_CFG_TRIG_MODE_ONESHOT 0x0002 +#define MV88E6XXX_TAI_CFG_TRIG_ENABLE 0x0001 + +/* Offset 0x01: Timestamp Clock Period (ps) */ +#define MV88E6XXX_TAI_CLOCK_PERIOD 0x01 + +/* Offset 0x02/0x03: Trigger Generation Amount */ +#define MV88E6XXX_TAI_TRIG_GEN_AMOUNT_LO 0x02 +#define MV88E6XXX_TAI_TRIG_GEN_AMOUNT_HI 0x03 + +/* Offset 0x04: Clock Compensation */ +#define MV88E6XXX_TAI_TRIG_CLOCK_COMP 0x04 + +/* Offset 0x05: Trigger Configuration */ +#define MV88E6XXX_TAI_TRIG_CFG 0x05 + +/* Offset 0x06: Ingress Rate Limiter Clock Generation Amount */ +#define MV88E6XXX_TAI_IRL_AMOUNT 0x06 + +/* Offset 0x07: Ingress Rate Limiter Compensation */ +#define MV88E6XXX_TAI_IRL_COMP 0x07 + +/* Offset 0x08: Ingress Rate Limiter Compensation */ +#define MV88E6XXX_TAI_IRL_COMP_PS 0x08 + +/* Offset 0x09: Event Status */ +#define MV88E6XXX_TAI_EVENT_STATUS 0x09 +#define MV88E6XXX_TAI_EVENT_STATUS_CAP_TRIG 0x4000 +#define MV88E6XXX_TAI_EVENT_STATUS_ERROR 0x0200 +#define MV88E6XXX_TAI_EVENT_STATUS_VALID 0x0100 +#define MV88E6XXX_TAI_EVENT_STATUS_CTR_MASK 0x00ff + +/* Offset 0x0A/0x0B: Event Time */ +#define MV88E6XXX_TAI_EVENT_TIME_LO 0x0a +#define MV88E6XXX_TAI_EVENT_TYPE_HI 0x0b + +/* Offset 0x0E/0x0F: PTP Global Time */ +#define MV88E6XXX_TAI_TIME_LO 0x0e +#define MV88E6XXX_TAI_TIME_HI 0x0f + +/* Offset 0x10/0x11: Trig Generation Time */ +#define MV88E6XXX_TAI_TRIG_TIME_LO 0x10 +#define MV88E6XXX_TAI_TRIG_TIME_HI 0x11 + +/* Offset 0x12: Lock Status */ +#define MV88E6XXX_TAI_LOCK_STATUS 0x12 + +#ifdef CONFIG_NET_DSA_MV88E6XXX_PTP + +long mv88e6xxx_hwtstamp_work(struct ptp_clock_info *ptp); +int mv88e6xxx_ptp_setup(struct mv88e6xxx_chip *chip); +void mv88e6xxx_ptp_free(struct mv88e6xxx_chip *chip); + +#define ptp_to_chip(ptp) container_of(ptp, struct mv88e6xxx_chip, \ + ptp_clock_info) + +#else /* !CONFIG_NET_DSA_MV88E6XXX_PTP */ + +static inline long mv88e6xxx_hwtstamp_work(struct ptp_clock_info *ptp) +{ + return -1; +} + +static inline int mv88e6xxx_ptp_setup(struct mv88e6xxx_chip *chip) +{ + return 0; +} + +static inline void mv88e6xxx_ptp_free(struct mv88e6xxx_chip *chip) +{ +} + +#endif /* CONFIG_NET_DSA_MV88E6XXX_PTP */ + +#endif /* _MV88E6XXX_PTP_H */ diff --git a/drivers/net/ethernet/8390/Makefile b/drivers/net/ethernet/8390/Makefile index f975c2fc88a3..1d650e66cc6e 100644 --- a/drivers/net/ethernet/8390/Makefile +++ b/drivers/net/ethernet/8390/Makefile @@ -7,8 +7,8 @@ obj-$(CONFIG_MAC8390) += mac8390.o obj-$(CONFIG_APNE) += apne.o 8390.o obj-$(CONFIG_ARM_ETHERH) += etherh.o obj-$(CONFIG_AX88796) += ax88796.o -obj-$(CONFIG_HYDRA) += hydra.o 8390.o -obj-$(CONFIG_MCF8390) += mcf8390.o 8390.o +obj-$(CONFIG_HYDRA) += hydra.o +obj-$(CONFIG_MCF8390) += mcf8390.o obj-$(CONFIG_NE2000) += ne.o 8390p.o obj-$(CONFIG_NE2K_PCI) += ne2k-pci.o 8390.o obj-$(CONFIG_PCMCIA_AXNET) += axnet_cs.o 8390.o @@ -16,4 +16,4 @@ obj-$(CONFIG_PCMCIA_PCNET) += pcnet_cs.o 8390.o obj-$(CONFIG_STNIC) += stnic.o 8390.o obj-$(CONFIG_ULTRA) += smc-ultra.o 8390.o obj-$(CONFIG_WD80x3) += wd.o 8390.o -obj-$(CONFIG_ZORRO8390) += zorro8390.o 8390.o +obj-$(CONFIG_ZORRO8390) += zorro8390.o diff --git a/drivers/net/ethernet/8390/ax88796.c b/drivers/net/ethernet/8390/ax88796.c index 245554707163..da61cf3cb3a9 100644 --- a/drivers/net/ethernet/8390/ax88796.c +++ b/drivers/net/ethernet/8390/ax88796.c @@ -77,8 +77,6 @@ static unsigned char version[] = "ax88796.c: Copyright 2005,2007 Simtec Electron #define AX_GPOC_PPDSET BIT(6) -static u32 ax_msg_enable; - /* device private data */ struct ax_device { @@ -747,7 +745,6 @@ static int ax_init_dev(struct net_device *dev) ei_local->block_output = &ax_block_output; ei_local->get_8390_hdr = &ax_get_8390_hdr; ei_local->priv = 0; - ei_local->msg_enable = ax_msg_enable; dev->netdev_ops = &ax_netdev_ops; dev->ethtool_ops = &ax_ethtool_ops; diff --git a/drivers/net/ethernet/8390/axnet_cs.c b/drivers/net/ethernet/8390/axnet_cs.c index 7bddb8efb6d5..d422a124cd7c 100644 --- a/drivers/net/ethernet/8390/axnet_cs.c +++ b/drivers/net/ethernet/8390/axnet_cs.c @@ -104,7 +104,6 @@ static void AX88190_init(struct net_device *dev, int startp); static int ax_open(struct net_device *dev); static int ax_close(struct net_device *dev); static irqreturn_t ax_interrupt(int irq, void *dev_id); -static u32 axnet_msg_enable; /*====================================================================*/ @@ -151,7 +150,6 @@ static int axnet_probe(struct pcmcia_device *link) return -ENOMEM; ei_local = netdev_priv(dev); - ei_local->msg_enable = axnet_msg_enable; spin_lock_init(&ei_local->page_lock); info = PRIV(dev); diff --git a/drivers/net/ethernet/8390/etherh.c b/drivers/net/ethernet/8390/etherh.c index 11cbf22ad201..32e9627e3880 100644 --- a/drivers/net/ethernet/8390/etherh.c +++ b/drivers/net/ethernet/8390/etherh.c @@ -64,8 +64,6 @@ static char version[] = #include "lib8390.c" -static u32 etherh_msg_enable; - struct etherh_priv { void __iomem *ioc_fast; void __iomem *memc; @@ -502,18 +500,6 @@ etherh_close(struct net_device *dev) } /* - * Initialisation - */ - -static void __init etherh_banner(void) -{ - static int version_printed; - - if ((etherh_msg_enable & NETIF_MSG_DRV) && (version_printed++ == 0)) - pr_info("%s", version); -} - -/* * Read the ethernet address string from the on board rom. * This is an ascii string... */ @@ -671,8 +657,6 @@ etherh_probe(struct expansion_card *ec, const struct ecard_id *id) struct etherh_priv *eh; int ret; - etherh_banner(); - ret = ecard_request_resources(ec); if (ret) goto out; @@ -757,7 +741,6 @@ etherh_probe(struct expansion_card *ec, const struct ecard_id *id) ei_local->block_output = etherh_block_output; ei_local->get_8390_hdr = etherh_get_header; ei_local->interface_num = 0; - ei_local->msg_enable = etherh_msg_enable; etherh_reset(dev); __NS8390_init(dev, 0); diff --git a/drivers/net/ethernet/8390/hydra.c b/drivers/net/ethernet/8390/hydra.c index 8ae249195301..941754ea78ec 100644 --- a/drivers/net/ethernet/8390/hydra.c +++ b/drivers/net/ethernet/8390/hydra.c @@ -66,7 +66,6 @@ static void hydra_block_input(struct net_device *dev, int count, static void hydra_block_output(struct net_device *dev, int count, const unsigned char *buf, int start_page); static void hydra_remove_one(struct zorro_dev *z); -static u32 hydra_msg_enable; static struct zorro_device_id hydra_zorro_tbl[] = { { ZORRO_PROD_HYDRA_SYSTEMS_AMIGANET }, @@ -119,7 +118,6 @@ static int hydra_init(struct zorro_dev *z) int start_page, stop_page; int j; int err; - struct ei_device *ei_local; static u32 hydra_offsets[16] = { 0x00, 0x02, 0x04, 0x06, 0x08, 0x0a, 0x0c, 0x0e, @@ -138,8 +136,6 @@ static int hydra_init(struct zorro_dev *z) start_page = NESM_START_PG; stop_page = NESM_STOP_PG; - ei_local = netdev_priv(dev); - ei_local->msg_enable = hydra_msg_enable; dev->base_addr = ioaddr; dev->irq = IRQ_AMIGA_PORTS; diff --git a/drivers/net/ethernet/8390/lib8390.c b/drivers/net/ethernet/8390/lib8390.c index 60f8e2c8e726..5d9bbde9fe68 100644 --- a/drivers/net/ethernet/8390/lib8390.c +++ b/drivers/net/ethernet/8390/lib8390.c @@ -975,6 +975,8 @@ static void ethdev_setup(struct net_device *dev) ether_setup(dev); spin_lock_init(&ei_local->page_lock); + + ei_local->msg_enable = msg_enable; } /** diff --git a/drivers/net/ethernet/8390/mac8390.c b/drivers/net/ethernet/8390/mac8390.c index 2f91ce8dc614..b6d735bf8011 100644 --- a/drivers/net/ethernet/8390/mac8390.c +++ b/drivers/net/ethernet/8390/mac8390.c @@ -123,8 +123,7 @@ enum mac8390_access { }; extern int mac8390_memtest(struct net_device *dev); -static int mac8390_initdev(struct net_device *dev, - struct nubus_rsrc *ndev, +static int mac8390_initdev(struct net_device *dev, struct nubus_board *board, enum mac8390_type type); static int mac8390_open(struct net_device *dev); @@ -168,9 +167,8 @@ static void slow_sane_block_output(struct net_device *dev, int count, const unsigned char *buf, int start_page); static void word_memcpy_tocard(unsigned long tp, const void *fp, int count); static void word_memcpy_fromcard(void *tp, unsigned long fp, int count); -static u32 mac8390_msg_enable; -static enum mac8390_type __init mac8390_ident(struct nubus_rsrc *fres) +static enum mac8390_type mac8390_ident(struct nubus_rsrc *fres) { switch (fres->dr_sw) { case NUBUS_DRSW_3COM: @@ -236,7 +234,7 @@ static enum mac8390_type __init mac8390_ident(struct nubus_rsrc *fres) return MAC8390_NONE; } -static enum mac8390_access __init mac8390_testio(volatile unsigned long membase) +static enum mac8390_access mac8390_testio(unsigned long membase) { unsigned long outdata = 0xA5A0B5B0; unsigned long indata = 0x00000000; @@ -254,7 +252,7 @@ static enum mac8390_access __init mac8390_testio(volatile unsigned long membase) return ACCESS_UNKNOWN; } -static int __init mac8390_memsize(unsigned long membase) +static int mac8390_memsize(unsigned long membase) { unsigned long flags; int i, j; @@ -290,36 +288,34 @@ static int __init mac8390_memsize(unsigned long membase) return i * 0x1000; } -static bool __init mac8390_init(struct net_device *dev, - struct nubus_rsrc *ndev, - enum mac8390_type cardtype) +static bool mac8390_rsrc_init(struct net_device *dev, + struct nubus_rsrc *fres, + enum mac8390_type cardtype) { + struct nubus_board *board = fres->board; struct nubus_dir dir; struct nubus_dirent ent; int offset; volatile unsigned short *i; - printk_once(KERN_INFO pr_fmt("%s"), version); - - dev->irq = SLOT2IRQ(ndev->board->slot); + dev->irq = SLOT2IRQ(board->slot); /* This is getting to be a habit */ - dev->base_addr = (ndev->board->slot_addr | - ((ndev->board->slot & 0xf) << 20)); + dev->base_addr = board->slot_addr | ((board->slot & 0xf) << 20); /* * Get some Nubus info - we will trust the card's idea * of where its memory and registers are. */ - if (nubus_get_func_dir(ndev, &dir) == -1) { - pr_err("%s: Unable to get Nubus functional directory for slot %X!\n", - dev->name, ndev->board->slot); + if (nubus_get_func_dir(fres, &dir) == -1) { + dev_err(&board->dev, + "Unable to get Nubus functional directory\n"); return false; } /* Get the MAC address */ if (nubus_find_rsrc(&dir, NUBUS_RESID_MAC_ADDRESS, &ent) == -1) { - pr_info("%s: Couldn't get MAC address!\n", dev->name); + dev_info(&board->dev, "MAC address resource not found\n"); return false; } @@ -329,8 +325,8 @@ static bool __init mac8390_init(struct net_device *dev, nubus_rewinddir(&dir); if (nubus_find_rsrc(&dir, NUBUS_RESID_MINOR_BASEOS, &ent) == -1) { - pr_err("%s: Memory offset resource for slot %X not found!\n", - dev->name, ndev->board->slot); + dev_err(&board->dev, + "Memory offset resource not found\n"); return false; } nubus_get_rsrc_mem(&offset, &ent, 4); @@ -340,8 +336,8 @@ static bool __init mac8390_init(struct net_device *dev, nubus_rewinddir(&dir); if (nubus_find_rsrc(&dir, NUBUS_RESID_MINOR_LENGTH, &ent) == -1) { - pr_info("%s: Memory length resource for slot %X not found, probing\n", - dev->name, ndev->board->slot); + dev_info(&board->dev, + "Memory length resource not found, probing\n"); offset = mac8390_memsize(dev->mem_start); } else { nubus_get_rsrc_mem(&offset, &ent, 4); @@ -351,25 +347,25 @@ static bool __init mac8390_init(struct net_device *dev, switch (cardtype) { case MAC8390_KINETICS: case MAC8390_DAYNA: /* it's the same */ - dev->base_addr = (int)(ndev->board->slot_addr + + dev->base_addr = (int)(board->slot_addr + DAYNA_8390_BASE); - dev->mem_start = (int)(ndev->board->slot_addr + + dev->mem_start = (int)(board->slot_addr + DAYNA_8390_MEM); dev->mem_end = dev->mem_start + mac8390_memsize(dev->mem_start); break; case MAC8390_INTERLAN: - dev->base_addr = (int)(ndev->board->slot_addr + + dev->base_addr = (int)(board->slot_addr + INTERLAN_8390_BASE); - dev->mem_start = (int)(ndev->board->slot_addr + + dev->mem_start = (int)(board->slot_addr + INTERLAN_8390_MEM); dev->mem_end = dev->mem_start + mac8390_memsize(dev->mem_start); break; case MAC8390_CABLETRON: - dev->base_addr = (int)(ndev->board->slot_addr + + dev->base_addr = (int)(board->slot_addr + CABLETRON_8390_BASE); - dev->mem_start = (int)(ndev->board->slot_addr + + dev->mem_start = (int)(board->slot_addr + CABLETRON_8390_MEM); /* The base address is unreadable if 0x00 * has been written to the command register @@ -384,8 +380,8 @@ static bool __init mac8390_init(struct net_device *dev, break; default: - pr_err("Card type %s is unsupported, sorry\n", - ndev->board->name); + dev_err(&board->dev, + "No known base address for card type\n"); return false; } } @@ -393,91 +389,83 @@ static bool __init mac8390_init(struct net_device *dev, return true; } -struct net_device * __init mac8390_probe(int unit) +static int mac8390_device_probe(struct nubus_board *board) { struct net_device *dev; - struct nubus_rsrc *ndev = NULL; int err = -ENODEV; - struct ei_device *ei_local; - - static unsigned int slots; - - enum mac8390_type cardtype; - - /* probably should check for Nubus instead */ - - if (!MACH_IS_MAC) - return ERR_PTR(-ENODEV); + struct nubus_rsrc *fres; + enum mac8390_type cardtype = MAC8390_NONE; dev = ____alloc_ei_netdev(0); if (!dev) - return ERR_PTR(-ENOMEM); - - if (unit >= 0) - sprintf(dev->name, "eth%d", unit); + return -ENOMEM; - for_each_func_rsrc(ndev) { - if (ndev->category != NUBUS_CAT_NETWORK || - ndev->type != NUBUS_TYPE_ETHERNET) - continue; + SET_NETDEV_DEV(dev, &board->dev); - /* Have we seen it already? */ - if (slots & (1 << ndev->board->slot)) + for_each_board_func_rsrc(board, fres) { + if (fres->category != NUBUS_CAT_NETWORK || + fres->type != NUBUS_TYPE_ETHERNET) continue; - slots |= 1 << ndev->board->slot; - cardtype = mac8390_ident(ndev); + cardtype = mac8390_ident(fres); if (cardtype == MAC8390_NONE) continue; - if (!mac8390_init(dev, ndev, cardtype)) - continue; - - /* Do the nasty 8390 stuff */ - if (!mac8390_initdev(dev, ndev, cardtype)) + if (mac8390_rsrc_init(dev, fres, cardtype)) break; } - - if (!ndev) + if (!fres) goto out; - ei_local = netdev_priv(dev); - ei_local->msg_enable = mac8390_msg_enable; + err = mac8390_initdev(dev, board, cardtype); + if (err) + goto out; err = register_netdev(dev); if (err) goto out; - return dev; + + nubus_set_drvdata(board, dev); + return 0; out: free_netdev(dev); - return ERR_PTR(err); + return err; +} + +static int mac8390_device_remove(struct nubus_board *board) +{ + struct net_device *dev = nubus_get_drvdata(board); + + unregister_netdev(dev); + free_netdev(dev); + return 0; } -#ifdef MODULE +static struct nubus_driver mac8390_driver = { + .probe = mac8390_device_probe, + .remove = mac8390_device_remove, + .driver = { + .name = KBUILD_MODNAME, + .owner = THIS_MODULE, + } +}; + MODULE_AUTHOR("David Huggins-Daines <dhd@debian.org> and others"); MODULE_DESCRIPTION("Macintosh NS8390-based Nubus Ethernet driver"); MODULE_LICENSE("GPL"); -static struct net_device *dev_mac8390; - -int __init init_module(void) +static int __init mac8390_init(void) { - dev_mac8390 = mac8390_probe(-1); - if (IS_ERR(dev_mac8390)) { - pr_warn("mac8390: No card found\n"); - return PTR_ERR(dev_mac8390); - } - return 0; + return nubus_driver_register(&mac8390_driver); } +module_init(mac8390_init); -void __exit cleanup_module(void) +static void __exit mac8390_exit(void) { - unregister_netdev(dev_mac8390); - free_netdev(dev_mac8390); + nubus_driver_unregister(&mac8390_driver); } - -#endif /* MODULE */ +module_exit(mac8390_exit); static const struct net_device_ops mac8390_netdev_ops = { .ndo_open = mac8390_open, @@ -493,9 +481,8 @@ static const struct net_device_ops mac8390_netdev_ops = { #endif }; -static int __init mac8390_initdev(struct net_device *dev, - struct nubus_rsrc *ndev, - enum mac8390_type type) +static int mac8390_initdev(struct net_device *dev, struct nubus_board *board, + enum mac8390_type type) { static u32 fwrd4_offsets[16] = { 0, 4, 8, 12, @@ -546,7 +533,8 @@ static int __init mac8390_initdev(struct net_device *dev, case MAC8390_APPLE: switch (mac8390_testio(dev->mem_start)) { case ACCESS_UNKNOWN: - pr_err("Don't know how to access card memory!\n"); + dev_err(&board->dev, + "Don't know how to access card memory\n"); return -ENODEV; case ACCESS_16: @@ -612,21 +600,18 @@ static int __init mac8390_initdev(struct net_device *dev, break; default: - pr_err("Card type %s is unsupported, sorry\n", - ndev->board->name); + dev_err(&board->dev, "Unsupported card type\n"); return -ENODEV; } __NS8390_init(dev, 0); /* Good, done, now spit out some messages */ - pr_info("%s: %s in slot %X (type %s)\n", - dev->name, ndev->board->name, ndev->board->slot, - cardname[type]); - pr_info("MAC %pM IRQ %d, %d KB shared memory at %#lx, %d-bit access.\n", - dev->dev_addr, dev->irq, - (unsigned int)(dev->mem_end - dev->mem_start) >> 10, - dev->mem_start, access_bitmode ? 32 : 16); + dev_info(&board->dev, "%s (type %s)\n", board->name, cardname[type]); + dev_info(&board->dev, "MAC %pM, IRQ %d, %d KB shared memory at %#lx, %d-bit access.\n", + dev->dev_addr, dev->irq, + (unsigned int)(dev->mem_end - dev->mem_start) >> 10, + dev->mem_start, access_bitmode ? 32 : 16); return 0; } diff --git a/drivers/net/ethernet/8390/mcf8390.c b/drivers/net/ethernet/8390/mcf8390.c index 4bb967bc879e..4ad8031ab669 100644 --- a/drivers/net/ethernet/8390/mcf8390.c +++ b/drivers/net/ethernet/8390/mcf8390.c @@ -38,7 +38,6 @@ static const char version[] = #define NESM_START_PG 0x40 /* First page of TX buffer */ #define NESM_STOP_PG 0x80 /* Last page +1 of RX ring */ -static u32 mcf8390_msg_enable; #ifdef NE2000_ODDOFFSET /* @@ -407,7 +406,6 @@ static int mcf8390_init(struct net_device *dev) static int mcf8390_probe(struct platform_device *pdev) { struct net_device *dev; - struct ei_device *ei_local; struct resource *mem, *irq; resource_size_t msize; int ret; @@ -435,8 +433,6 @@ static int mcf8390_probe(struct platform_device *pdev) SET_NETDEV_DEV(dev, &pdev->dev); platform_set_drvdata(pdev, dev); - ei_local = netdev_priv(dev); - ei_local->msg_enable = mcf8390_msg_enable; dev->irq = irq->start; dev->base_addr = mem->start; diff --git a/drivers/net/ethernet/8390/ne.c b/drivers/net/ethernet/8390/ne.c index 66f47987e2a2..4cdff6e6af89 100644 --- a/drivers/net/ethernet/8390/ne.c +++ b/drivers/net/ethernet/8390/ne.c @@ -485,7 +485,7 @@ static int __init ne_probe1(struct net_device *dev, unsigned long ioaddr) mdelay(10); /* wait 10ms for interrupt to propagate */ outb_p(0x00, ioaddr + EN0_IMR); /* Mask it again. */ dev->irq = probe_irq_off(cookie); - if (netif_msg_probe(ei_local)) + if (ne_msg_enable & NETIF_MSG_PROBE) pr_cont(" autoirq is %d", dev->irq); } else if (dev->irq == 2) /* Fixup for users that don't know that IRQ 2 is really IRQ 9, diff --git a/drivers/net/ethernet/8390/pcnet_cs.c b/drivers/net/ethernet/8390/pcnet_cs.c index bcad4a7fac9f..61e43802b9a5 100644 --- a/drivers/net/ethernet/8390/pcnet_cs.c +++ b/drivers/net/ethernet/8390/pcnet_cs.c @@ -66,7 +66,6 @@ #define PCNET_RDC_TIMEOUT (2*HZ/100) /* Max wait in jiffies for Tx RDC */ static const char *if_names[] = { "auto", "10baseT", "10base2"}; -static u32 pcnet_msg_enable; /*====================================================================*/ @@ -556,7 +555,6 @@ static int pcnet_config(struct pcmcia_device *link) int start_pg, stop_pg, cm_offset; int has_shmem = 0; struct hw_info *local_hw_info; - struct ei_device *ei_local; dev_dbg(&link->dev, "pcnet_config\n"); @@ -606,8 +604,6 @@ static int pcnet_config(struct pcmcia_device *link) mii_phy_probe(dev); SET_NETDEV_DEV(dev, &link->dev); - ei_local = netdev_priv(dev); - ei_local->msg_enable = pcnet_msg_enable; if (register_netdev(dev) != 0) { pr_notice("register_netdev() failed\n"); diff --git a/drivers/net/ethernet/8390/wd.c b/drivers/net/ethernet/8390/wd.c index 6efa2722f850..fb17c2c7e1dd 100644 --- a/drivers/net/ethernet/8390/wd.c +++ b/drivers/net/ethernet/8390/wd.c @@ -299,7 +299,7 @@ static int __init wd_probe1(struct net_device *dev, int ioaddr) outb_p(0x00, nic_addr+EN0_IMR); /* Mask all intrs. again. */ - if (netif_msg_drv(ei_local)) + if (wd_msg_enable & NETIF_MSG_PROBE) pr_cont(" autoirq is %d", dev->irq); if (dev->irq < 2) dev->irq = word16 ? 10 : 5; diff --git a/drivers/net/ethernet/8390/zorro8390.c b/drivers/net/ethernet/8390/zorro8390.c index 6d93956b293b..35a500a21521 100644 --- a/drivers/net/ethernet/8390/zorro8390.c +++ b/drivers/net/ethernet/8390/zorro8390.c @@ -44,8 +44,6 @@ static const char version[] = "8390.c:v1.10cvs 9/23/94 Donald Becker (becker@cesdis.gsfc.nasa.gov)\n"; -static u32 zorro8390_msg_enable; - #include "lib8390.c" #define DRV_NAME "zorro8390" @@ -296,7 +294,6 @@ static int zorro8390_init(struct net_device *dev, unsigned long board, int err; unsigned char SA_prom[32]; int start_page, stop_page; - struct ei_device *ei_local = netdev_priv(dev); static u32 zorro8390_offsets[16] = { 0x00, 0x02, 0x04, 0x06, 0x08, 0x0a, 0x0c, 0x0e, 0x10, 0x12, 0x14, 0x16, 0x18, 0x1a, 0x1c, 0x1e, @@ -388,8 +385,6 @@ static int zorro8390_init(struct net_device *dev, unsigned long board, dev->netdev_ops = &zorro8390_netdev_ops; __NS8390_init(dev, 0); - ei_local->msg_enable = zorro8390_msg_enable; - err = register_netdev(dev); if (err) { free_irq(IRQ_AMIGA_PORTS, dev); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c index 3e5833cf1fab..eb23f9ba1a9a 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c @@ -426,6 +426,8 @@ static int xgbe_pci_resume(struct pci_dev *pdev) struct net_device *netdev = pdata->netdev; int ret = 0; + XP_IOWRITE(pdata, XP_INT_EN, 0x1fffff); + pdata->lpm_ctrl &= ~MDIO_CTRL1_LPOWER; XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL1, pdata->lpm_ctrl); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c index 22889fc158f2..87c4308b52a7 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c @@ -226,6 +226,10 @@ static int aq_pci_probe(struct pci_dev *pdev, goto err_ioremap; self->aq_hw = kzalloc(sizeof(*self->aq_hw), GFP_KERNEL); + if (!self->aq_hw) { + err = -ENOMEM; + goto err_ioremap; + } self->aq_hw->aq_nic_cfg = aq_nic_get_cfg(self); for (bar = 0; bar < 4; ++bar) { @@ -235,19 +239,19 @@ static int aq_pci_probe(struct pci_dev *pdev, mmio_pa = pci_resource_start(pdev, bar); if (mmio_pa == 0U) { err = -EIO; - goto err_ioremap; + goto err_free_aq_hw; } reg_sz = pci_resource_len(pdev, bar); if ((reg_sz <= 24 /*ATL_REGS_SIZE*/)) { err = -EIO; - goto err_ioremap; + goto err_free_aq_hw; } self->aq_hw->mmio = ioremap_nocache(mmio_pa, reg_sz); if (!self->aq_hw->mmio) { err = -EIO; - goto err_ioremap; + goto err_free_aq_hw; } break; } @@ -255,7 +259,7 @@ static int aq_pci_probe(struct pci_dev *pdev, if (bar == 4) { err = -EIO; - goto err_ioremap; + goto err_free_aq_hw; } numvecs = min((u8)AQ_CFG_VECS_DEF, @@ -290,6 +294,8 @@ err_register: aq_pci_free_irq_vectors(self); err_hwinit: iounmap(self->aq_hw->mmio); +err_free_aq_hw: + kfree(self->aq_hw); err_ioremap: free_netdev(ndev); err_pci_func: diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/Makefile b/drivers/net/ethernet/aquantia/atlantic/hw_atl/Makefile new file mode 100644 index 000000000000..805fa28f391a --- /dev/null +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +# kbuild requires Makefile in a directory to build individual objects diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index a77ee2f8fb8d..c1841db1b500 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -820,7 +820,7 @@ static int tg3_ape_event_lock(struct tg3 *tp, u32 timeout_us) tg3_ape_unlock(tp, TG3_APE_LOCK_MEM); - udelay(10); + usleep_range(10, 20); timeout_us -= (timeout_us > 10) ? 10 : timeout_us; } @@ -922,8 +922,8 @@ static int tg3_ape_send_event(struct tg3 *tp, u32 event) if (!(apedata & APE_FW_STATUS_READY)) return -EAGAIN; - /* Wait for up to 1 millisecond for APE to service previous event. */ - err = tg3_ape_event_lock(tp, 1000); + /* Wait for up to 20 millisecond for APE to service previous event. */ + err = tg3_ape_event_lock(tp, 20000); if (err) return err; @@ -946,6 +946,7 @@ static void tg3_ape_driver_state_change(struct tg3 *tp, int kind) switch (kind) { case RESET_KIND_INIT: + tg3_ape_write32(tp, TG3_APE_HOST_HEARTBEAT_COUNT, tp->ape_hb++); tg3_ape_write32(tp, TG3_APE_HOST_SEG_SIG, APE_HOST_SEG_SIG_MAGIC); tg3_ape_write32(tp, TG3_APE_HOST_SEG_LEN, @@ -962,13 +963,6 @@ static void tg3_ape_driver_state_change(struct tg3 *tp, int kind) event = APE_EVENT_STATUS_STATE_START; break; case RESET_KIND_SHUTDOWN: - /* With the interface we are currently using, - * APE does not track driver state. Wiping - * out the HOST SEGMENT SIGNATURE forces - * the APE to assume OS absent status. - */ - tg3_ape_write32(tp, TG3_APE_HOST_SEG_SIG, 0x0); - if (device_may_wakeup(&tp->pdev->dev) && tg3_flag(tp, WOL_ENABLE)) { tg3_ape_write32(tp, TG3_APE_HOST_WOL_SPEED, @@ -990,6 +984,18 @@ static void tg3_ape_driver_state_change(struct tg3 *tp, int kind) tg3_ape_send_event(tp, event); } +static void tg3_send_ape_heartbeat(struct tg3 *tp, + unsigned long interval) +{ + /* Check if hb interval has exceeded */ + if (!tg3_flag(tp, ENABLE_APE) || + time_before(jiffies, tp->ape_hb_jiffies + interval)) + return; + + tg3_ape_write32(tp, TG3_APE_HOST_HEARTBEAT_COUNT, tp->ape_hb++); + tp->ape_hb_jiffies = jiffies; +} + static void tg3_disable_ints(struct tg3 *tp) { int i; @@ -7262,6 +7268,7 @@ static int tg3_poll_msix(struct napi_struct *napi, int budget) } } + tg3_send_ape_heartbeat(tp, TG3_APE_HB_INTERVAL << 1); return work_done; tx_recovery: @@ -7344,6 +7351,7 @@ static int tg3_poll(struct napi_struct *napi, int budget) } } + tg3_send_ape_heartbeat(tp, TG3_APE_HB_INTERVAL << 1); return work_done; tx_recovery: @@ -10732,7 +10740,7 @@ static int tg3_reset_hw(struct tg3 *tp, bool reset_phy) if (tg3_flag(tp, ENABLE_APE)) /* Write our heartbeat update interval to APE. */ tg3_ape_write32(tp, TG3_APE_HOST_HEARTBEAT_INT_MS, - APE_HOST_HEARTBEAT_INT_DISABLE); + APE_HOST_HEARTBEAT_INT_5SEC); tg3_write_sig_post_reset(tp, RESET_KIND_INIT); @@ -11077,6 +11085,9 @@ static void tg3_timer(struct timer_list *t) tp->asf_counter = tp->asf_multiplier; } + /* Update the APE heartbeat every 5 seconds.*/ + tg3_send_ape_heartbeat(tp, TG3_APE_HB_INTERVAL); + spin_unlock(&tp->lock); restart_timer: @@ -16653,6 +16664,8 @@ static int tg3_get_invariants(struct tg3 *tp, const struct pci_device_id *ent) pci_state_reg); tg3_ape_lock_init(tp); + tp->ape_hb_interval = + msecs_to_jiffies(APE_HOST_HEARTBEAT_INT_5SEC); } /* Set up tp->grc_local_ctrl before calling diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h index 47f51cc0566d..1d61aa3efda1 100644 --- a/drivers/net/ethernet/broadcom/tg3.h +++ b/drivers/net/ethernet/broadcom/tg3.h @@ -2508,6 +2508,7 @@ #define TG3_APE_LOCK_PHY3 5 #define TG3_APE_LOCK_GPIO 7 +#define TG3_APE_HB_INTERVAL (tp->ape_hb_interval) #define TG3_EEPROM_SB_F1R2_MBA_OFF 0x10 @@ -3423,6 +3424,10 @@ struct tg3 { struct device *hwmon_dev; bool link_up; bool pcierr_recovery; + + u32 ape_hb; + unsigned long ape_hb_interval; + unsigned long ape_hb_jiffies; }; /* Accessor macros for chip and asic attributes diff --git a/drivers/net/ethernet/cavium/common/cavium_ptp.c b/drivers/net/ethernet/cavium/common/cavium_ptp.c index c87c9c684a33..d59497a7bdce 100644 --- a/drivers/net/ethernet/cavium/common/cavium_ptp.c +++ b/drivers/net/ethernet/cavium/common/cavium_ptp.c @@ -75,6 +75,8 @@ EXPORT_SYMBOL(cavium_ptp_get); void cavium_ptp_put(struct cavium_ptp *ptp) { + if (!ptp) + return; pci_dev_put(ptp->pdev); } EXPORT_SYMBOL(cavium_ptp_put); diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index b68cde9f17d2..7d9c5ffbd041 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -67,11 +67,6 @@ module_param(cpi_alg, int, S_IRUGO); MODULE_PARM_DESC(cpi_alg, "PFC algorithm (0=none, 1=VLAN, 2=VLAN16, 3=IP Diffserv)"); -struct nicvf_xdp_tx { - u64 dma_addr; - u8 qidx; -}; - static inline u8 nicvf_netdev_qidx(struct nicvf *nic, u8 qidx) { if (nic->sqs_mode) @@ -507,29 +502,14 @@ static int nicvf_init_resources(struct nicvf *nic) return 0; } -static void nicvf_unmap_page(struct nicvf *nic, struct page *page, u64 dma_addr) -{ - /* Check if it's a recycled page, if not unmap the DMA mapping. - * Recycled page holds an extra reference. - */ - if (page_ref_count(page) == 1) { - dma_addr &= PAGE_MASK; - dma_unmap_page_attrs(&nic->pdev->dev, dma_addr, - RCV_FRAG_LEN + XDP_HEADROOM, - DMA_FROM_DEVICE, - DMA_ATTR_SKIP_CPU_SYNC); - } -} - static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog, struct cqe_rx_t *cqe_rx, struct snd_queue *sq, struct rcv_queue *rq, struct sk_buff **skb) { struct xdp_buff xdp; struct page *page; - struct nicvf_xdp_tx *xdp_tx = NULL; u32 action; - u16 len, err, offset = 0; + u16 len, offset = 0; u64 dma_addr, cpu_addr; void *orig_data; @@ -543,7 +523,7 @@ static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog, cpu_addr = (u64)phys_to_virt(cpu_addr); page = virt_to_page((void *)cpu_addr); - xdp.data_hard_start = page_address(page) + RCV_BUF_HEADROOM; + xdp.data_hard_start = page_address(page); xdp.data = (void *)cpu_addr; xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + len; @@ -563,7 +543,18 @@ static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog, switch (action) { case XDP_PASS: - nicvf_unmap_page(nic, page, dma_addr); + /* Check if it's a recycled page, if not + * unmap the DMA mapping. + * + * Recycled page holds an extra reference. + */ + if (page_ref_count(page) == 1) { + dma_addr &= PAGE_MASK; + dma_unmap_page_attrs(&nic->pdev->dev, dma_addr, + RCV_FRAG_LEN + XDP_PACKET_HEADROOM, + DMA_FROM_DEVICE, + DMA_ATTR_SKIP_CPU_SYNC); + } /* Build SKB and pass on packet to network stack */ *skb = build_skb(xdp.data, @@ -576,20 +567,6 @@ static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog, case XDP_TX: nicvf_xdp_sq_append_pkt(nic, sq, (u64)xdp.data, dma_addr, len); return true; - case XDP_REDIRECT: - /* Save DMA address for use while transmitting */ - xdp_tx = (struct nicvf_xdp_tx *)page_address(page); - xdp_tx->dma_addr = dma_addr; - xdp_tx->qidx = nicvf_netdev_qidx(nic, cqe_rx->rq_idx); - - err = xdp_do_redirect(nic->pnicvf->netdev, &xdp, prog); - if (!err) - return true; - - /* Free the page on error */ - nicvf_unmap_page(nic, page, dma_addr); - put_page(page); - break; default: bpf_warn_invalid_xdp_action(action); /* fall through */ @@ -597,7 +574,18 @@ static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog, trace_xdp_exception(nic->netdev, prog, action); /* fall through */ case XDP_DROP: - nicvf_unmap_page(nic, page, dma_addr); + /* Check if it's a recycled page, if not + * unmap the DMA mapping. + * + * Recycled page holds an extra reference. + */ + if (page_ref_count(page) == 1) { + dma_addr &= PAGE_MASK; + dma_unmap_page_attrs(&nic->pdev->dev, dma_addr, + RCV_FRAG_LEN + XDP_PACKET_HEADROOM, + DMA_FROM_DEVICE, + DMA_ATTR_SKIP_CPU_SYNC); + } put_page(page); return true; } @@ -1864,50 +1852,6 @@ static int nicvf_xdp(struct net_device *netdev, struct netdev_bpf *xdp) } } -static int nicvf_xdp_xmit(struct net_device *netdev, struct xdp_buff *xdp) -{ - struct nicvf *nic = netdev_priv(netdev); - struct nicvf *snic = nic; - struct nicvf_xdp_tx *xdp_tx; - struct snd_queue *sq; - struct page *page; - int err, qidx; - - if (!netif_running(netdev) || !nic->xdp_prog) - return -EINVAL; - - page = virt_to_page(xdp->data); - xdp_tx = (struct nicvf_xdp_tx *)page_address(page); - qidx = xdp_tx->qidx; - - if (xdp_tx->qidx >= nic->xdp_tx_queues) - return -EINVAL; - - /* Get secondary Qset's info */ - if (xdp_tx->qidx >= MAX_SND_QUEUES_PER_QS) { - qidx = xdp_tx->qidx / MAX_SND_QUEUES_PER_QS; - snic = (struct nicvf *)nic->snicvf[qidx - 1]; - if (!snic) - return -EINVAL; - qidx = xdp_tx->qidx % MAX_SND_QUEUES_PER_QS; - } - - sq = &snic->qs->sq[qidx]; - err = nicvf_xdp_sq_append_pkt(snic, sq, (u64)xdp->data, - xdp_tx->dma_addr, - xdp->data_end - xdp->data); - if (err) - return -ENOMEM; - - nicvf_xdp_sq_doorbell(snic, sq, qidx); - return 0; -} - -static void nicvf_xdp_flush(struct net_device *dev) -{ - return; -} - static int nicvf_config_hwtstamp(struct net_device *netdev, struct ifreq *ifr) { struct hwtstamp_config config; @@ -1986,8 +1930,6 @@ static const struct net_device_ops nicvf_netdev_ops = { .ndo_fix_features = nicvf_fix_features, .ndo_set_features = nicvf_set_features, .ndo_bpf = nicvf_xdp, - .ndo_xdp_xmit = nicvf_xdp_xmit, - .ndo_xdp_flush = nicvf_xdp_flush, .ndo_do_ioctl = nicvf_ioctl, }; diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c index 3eae9ff9b53a..d42704d07484 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c @@ -204,7 +204,7 @@ static inline int nicvf_alloc_rcv_buffer(struct nicvf *nic, struct rbdr *rbdr, /* Reserve space for header modifications by BPF program */ if (rbdr->is_xdp) - buf_len += XDP_HEADROOM; + buf_len += XDP_PACKET_HEADROOM; /* Check if it's recycled */ if (pgcache) @@ -224,9 +224,8 @@ ret: nic->rb_page = NULL; return -ENOMEM; } - if (pgcache) - pgcache->dma_addr = *rbuf + XDP_HEADROOM; + pgcache->dma_addr = *rbuf + XDP_PACKET_HEADROOM; nic->rb_page_offset += buf_len; } @@ -1244,7 +1243,7 @@ int nicvf_xdp_sq_append_pkt(struct nicvf *nic, struct snd_queue *sq, int qentry; if (subdesc_cnt > sq->xdp_free_cnt) - return -1; + return 0; qentry = nicvf_get_sq_desc(sq, subdesc_cnt); @@ -1255,7 +1254,7 @@ int nicvf_xdp_sq_append_pkt(struct nicvf *nic, struct snd_queue *sq, sq->xdp_desc_cnt += subdesc_cnt; - return 0; + return 1; } /* Calculate no of SQ subdescriptors needed to transmit all @@ -1656,7 +1655,7 @@ static void nicvf_unmap_rcv_buffer(struct nicvf *nic, u64 dma_addr, if (page_ref_count(page) != 1) return; - len += XDP_HEADROOM; + len += XDP_PACKET_HEADROOM; /* Receive buffers in XDP mode are mapped from page start */ dma_addr &= PAGE_MASK; } diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h index ce1eed7a6d63..5e9a03cf1b4d 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h @@ -11,7 +11,6 @@ #include <linux/netdevice.h> #include <linux/iommu.h> -#include <linux/bpf.h> #include <net/xdp.h> #include "q_struct.h" @@ -94,9 +93,6 @@ #define RCV_FRAG_LEN (SKB_DATA_ALIGN(DMA_BUFFER_LEN + NET_SKB_PAD) + \ SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) -#define RCV_BUF_HEADROOM 128 /* To store dma address for XDP redirect */ -#define XDP_HEADROOM (XDP_PACKET_HEADROOM + RCV_BUF_HEADROOM) - #define MAX_CQES_FOR_TX ((SND_QUEUE_LEN / MIN_SQ_DESC_PER_PKT_XMIT) * \ MAX_CQE_PER_PKT_XMIT) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c index 557fd8bfd54e..9da6f57901a9 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c @@ -472,7 +472,7 @@ int cudbg_collect_cim_la(struct cudbg_init *pdbg_init, if (is_t6(padap->params.chip)) { size = padap->params.cim_la_size / 10 + 1; - size *= 11 * sizeof(u32); + size *= 10 * sizeof(u32); } else { size = padap->params.cim_la_size / 8; size *= 8 * sizeof(u32); @@ -878,6 +878,86 @@ static int cudbg_get_payload_range(struct adapter *padap, u8 mem_type, &payload->start, &payload->end); } +static int cudbg_memory_read(struct cudbg_init *pdbg_init, int win, + int mtype, u32 addr, u32 len, void *hbuf) +{ + u32 win_pf, memoffset, mem_aperture, mem_base; + struct adapter *adap = pdbg_init->adap; + u32 pos, offset, resid; + u32 *res_buf; + u64 *buf; + int ret; + + /* Argument sanity checks ... + */ + if (addr & 0x3 || (uintptr_t)hbuf & 0x3) + return -EINVAL; + + buf = (u64 *)hbuf; + + /* Try to do 64-bit reads. Residual will be handled later. */ + resid = len & 0x7; + len -= resid; + + ret = t4_memory_rw_init(adap, win, mtype, &memoffset, &mem_base, + &mem_aperture); + if (ret) + return ret; + + addr = addr + memoffset; + win_pf = is_t4(adap->params.chip) ? 0 : PFNUM_V(adap->pf); + + pos = addr & ~(mem_aperture - 1); + offset = addr - pos; + + /* Set up initial PCI-E Memory Window to cover the start of our + * transfer. + */ + t4_memory_update_win(adap, win, pos | win_pf); + + /* Transfer data from the adapter */ + while (len > 0) { + *buf++ = le64_to_cpu((__force __le64) + t4_read_reg64(adap, mem_base + offset)); + offset += sizeof(u64); + len -= sizeof(u64); + + /* If we've reached the end of our current window aperture, + * move the PCI-E Memory Window on to the next. + */ + if (offset == mem_aperture) { + pos += mem_aperture; + offset = 0; + t4_memory_update_win(adap, win, pos | win_pf); + } + } + + res_buf = (u32 *)buf; + /* Read residual in 32-bit multiples */ + while (resid > sizeof(u32)) { + *res_buf++ = le32_to_cpu((__force __le32) + t4_read_reg(adap, mem_base + offset)); + offset += sizeof(u32); + resid -= sizeof(u32); + + /* If we've reached the end of our current window aperture, + * move the PCI-E Memory Window on to the next. + */ + if (offset == mem_aperture) { + pos += mem_aperture; + offset = 0; + t4_memory_update_win(adap, win, pos | win_pf); + } + } + + /* Transfer residual < 32-bits */ + if (resid) + t4_memory_rw_residual(adap, resid, mem_base + offset, + (u8 *)res_buf, T4_MEMORY_READ); + + return 0; +} + #define CUDBG_YIELD_ITERATION 256 static int cudbg_read_fw_mem(struct cudbg_init *pdbg_init, @@ -937,10 +1017,8 @@ static int cudbg_read_fw_mem(struct cudbg_init *pdbg_init, goto skip_read; spin_lock(&padap->win0_lock); - rc = t4_memory_rw(padap, MEMWIN_NIC, mem_type, - bytes_read, bytes, - (__be32 *)temp_buff.data, - 1); + rc = cudbg_memory_read(pdbg_init, MEMWIN_NIC, mem_type, + bytes_read, bytes, temp_buff.data); spin_unlock(&padap->win0_lock); if (rc) { cudbg_err->sys_err = rc; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index 9040e13ce4b7..d3fa53db61ee 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -1488,6 +1488,11 @@ u32 t4_read_pcie_cfg4(struct adapter *adap, int reg); u32 t4_get_util_window(struct adapter *adap); void t4_setup_memwin(struct adapter *adap, u32 memwin_base, u32 window); +int t4_memory_rw_init(struct adapter *adap, int win, int mtype, u32 *mem_off, + u32 *mem_base, u32 *mem_aperture); +void t4_memory_update_win(struct adapter *adap, int win, u32 addr); +void t4_memory_rw_residual(struct adapter *adap, u32 off, u32 addr, u8 *buf, + int dir); #define T4_MEMORY_WRITE 0 #define T4_MEMORY_READ 1 int t4_memory_rw(struct adapter *adap, int win, int mtype, u32 addr, u32 len, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c index 30485f9a598f..143686c60234 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c @@ -102,7 +102,7 @@ static u32 cxgb4_get_entity_length(struct adapter *adap, u32 entity) case CUDBG_CIM_LA: if (is_t6(adap->params.chip)) { len = adap->params.cim_la_size / 10 + 1; - len *= 11 * sizeof(u32); + len *= 10 * sizeof(u32); } else { len = adap->params.cim_la_size / 8; len *= 8 * sizeof(u32); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 56bc626ef006..7b452e85de2a 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -4982,9 +4982,10 @@ static int cxgb4_iov_configure(struct pci_dev *pdev, int num_vfs) pcie_fw = readl(adap->regs + PCIE_FW_A); /* Check if cxgb4 is the MASTER and fw is initialized */ - if (!(pcie_fw & PCIE_FW_INIT_F) || + if (num_vfs && + (!(pcie_fw & PCIE_FW_INIT_F) || !(pcie_fw & PCIE_FW_MASTER_VLD_F) || - PCIE_FW_MASTER_G(pcie_fw) != CXGB4_UNIFIED_PF) { + PCIE_FW_MASTER_G(pcie_fw) != CXGB4_UNIFIED_PF)) { dev_warn(&pdev->dev, "cxgb4 driver needs to be MASTER to support SRIOV\n"); return -EOPNOTSUPP; @@ -5599,24 +5600,24 @@ static void remove_one(struct pci_dev *pdev) #if IS_ENABLED(CONFIG_IPV6) t4_cleanup_clip_tbl(adapter); #endif - iounmap(adapter->regs); if (!is_t4(adapter->params.chip)) iounmap(adapter->bar2); - pci_disable_pcie_error_reporting(pdev); - if ((adapter->flags & DEV_ENABLED)) { - pci_disable_device(pdev); - adapter->flags &= ~DEV_ENABLED; - } - pci_release_regions(pdev); - kfree(adapter->mbox_log); - synchronize_rcu(); - kfree(adapter); } #ifdef CONFIG_PCI_IOV else { cxgb4_iov_configure(adapter->pdev, 0); } #endif + iounmap(adapter->regs); + pci_disable_pcie_error_reporting(pdev); + if ((adapter->flags & DEV_ENABLED)) { + pci_disable_device(pdev); + adapter->flags &= ~DEV_ENABLED; + } + pci_release_regions(pdev); + kfree(adapter->mbox_log); + synchronize_rcu(); + kfree(adapter); } /* "Shutdown" quiesces the device, stopping Ingress Packet and Interrupt diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 047609ef0515..bd41f93f73ed 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -484,6 +484,117 @@ static int t4_edc_err_read(struct adapter *adap, int idx) } /** + * t4_memory_rw_init - Get memory window relative offset, base, and size. + * @adap: the adapter + * @win: PCI-E Memory Window to use + * @mtype: memory type: MEM_EDC0, MEM_EDC1 or MEM_MC + * @mem_off: memory relative offset with respect to @mtype. + * @mem_base: configured memory base address. + * @mem_aperture: configured memory window aperture. + * + * Get the configured memory window's relative offset, base, and size. + */ +int t4_memory_rw_init(struct adapter *adap, int win, int mtype, u32 *mem_off, + u32 *mem_base, u32 *mem_aperture) +{ + u32 edc_size, mc_size, mem_reg; + + /* Offset into the region of memory which is being accessed + * MEM_EDC0 = 0 + * MEM_EDC1 = 1 + * MEM_MC = 2 -- MEM_MC for chips with only 1 memory controller + * MEM_MC1 = 3 -- for chips with 2 memory controllers (e.g. T5) + * MEM_HMA = 4 + */ + edc_size = EDRAM0_SIZE_G(t4_read_reg(adap, MA_EDRAM0_BAR_A)); + if (mtype == MEM_HMA) { + *mem_off = 2 * (edc_size * 1024 * 1024); + } else if (mtype != MEM_MC1) { + *mem_off = (mtype * (edc_size * 1024 * 1024)); + } else { + mc_size = EXT_MEM0_SIZE_G(t4_read_reg(adap, + MA_EXT_MEMORY0_BAR_A)); + *mem_off = (MEM_MC0 * edc_size + mc_size) * 1024 * 1024; + } + + /* Each PCI-E Memory Window is programmed with a window size -- or + * "aperture" -- which controls the granularity of its mapping onto + * adapter memory. We need to grab that aperture in order to know + * how to use the specified window. The window is also programmed + * with the base address of the Memory Window in BAR0's address + * space. For T4 this is an absolute PCI-E Bus Address. For T5 + * the address is relative to BAR0. + */ + mem_reg = t4_read_reg(adap, + PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_BASE_WIN_A, + win)); + /* a dead adapter will return 0xffffffff for PIO reads */ + if (mem_reg == 0xffffffff) + return -ENXIO; + + *mem_aperture = 1 << (WINDOW_G(mem_reg) + WINDOW_SHIFT_X); + *mem_base = PCIEOFST_G(mem_reg) << PCIEOFST_SHIFT_X; + if (is_t4(adap->params.chip)) + *mem_base -= adap->t4_bar0; + + return 0; +} + +/** + * t4_memory_update_win - Move memory window to specified address. + * @adap: the adapter + * @win: PCI-E Memory Window to use + * @addr: location to move. + * + * Move memory window to specified address. + */ +void t4_memory_update_win(struct adapter *adap, int win, u32 addr) +{ + t4_write_reg(adap, + PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_OFFSET_A, win), + addr); + /* Read it back to ensure that changes propagate before we + * attempt to use the new value. + */ + t4_read_reg(adap, + PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_OFFSET_A, win)); +} + +/** + * t4_memory_rw_residual - Read/Write residual data. + * @adap: the adapter + * @off: relative offset within residual to start read/write. + * @addr: address within indicated memory type. + * @buf: host memory buffer + * @dir: direction of transfer T4_MEMORY_READ (1) or T4_MEMORY_WRITE (0) + * + * Read/Write residual data less than 32-bits. + */ +void t4_memory_rw_residual(struct adapter *adap, u32 off, u32 addr, u8 *buf, + int dir) +{ + union { + u32 word; + char byte[4]; + } last; + unsigned char *bp; + int i; + + if (dir == T4_MEMORY_READ) { + last.word = le32_to_cpu((__force __le32) + t4_read_reg(adap, addr)); + for (bp = (unsigned char *)buf, i = off; i < 4; i++) + bp[i] = last.byte[i]; + } else { + last.word = *buf; + for (i = off; i < 4; i++) + last.byte[i] = 0; + t4_write_reg(adap, addr, + (__force u32)cpu_to_le32(last.word)); + } +} + +/** * t4_memory_rw - read/write EDC 0, EDC 1 or MC via PCIE memory window * @adap: the adapter * @win: PCI-E Memory Window to use @@ -504,8 +615,9 @@ int t4_memory_rw(struct adapter *adap, int win, int mtype, u32 addr, u32 len, void *hbuf, int dir) { u32 pos, offset, resid, memoffset; - u32 edc_size, mc_size, win_pf, mem_reg, mem_aperture, mem_base; + u32 win_pf, mem_aperture, mem_base; u32 *buf; + int ret; /* Argument sanity checks ... */ @@ -521,59 +633,26 @@ int t4_memory_rw(struct adapter *adap, int win, int mtype, u32 addr, resid = len & 0x3; len -= resid; - /* Offset into the region of memory which is being accessed - * MEM_EDC0 = 0 - * MEM_EDC1 = 1 - * MEM_MC = 2 -- MEM_MC for chips with only 1 memory controller - * MEM_MC1 = 3 -- for chips with 2 memory controllers (e.g. T5) - * MEM_HMA = 4 - */ - edc_size = EDRAM0_SIZE_G(t4_read_reg(adap, MA_EDRAM0_BAR_A)); - if (mtype == MEM_HMA) { - memoffset = 2 * (edc_size * 1024 * 1024); - } else if (mtype != MEM_MC1) { - memoffset = (mtype * (edc_size * 1024 * 1024)); - } else { - mc_size = EXT_MEM0_SIZE_G(t4_read_reg(adap, - MA_EXT_MEMORY0_BAR_A)); - memoffset = (MEM_MC0 * edc_size + mc_size) * 1024 * 1024; - } + ret = t4_memory_rw_init(adap, win, mtype, &memoffset, &mem_base, + &mem_aperture); + if (ret) + return ret; /* Determine the PCIE_MEM_ACCESS_OFFSET */ addr = addr + memoffset; - /* Each PCI-E Memory Window is programmed with a window size -- or - * "aperture" -- which controls the granularity of its mapping onto - * adapter memory. We need to grab that aperture in order to know - * how to use the specified window. The window is also programmed - * with the base address of the Memory Window in BAR0's address - * space. For T4 this is an absolute PCI-E Bus Address. For T5 - * the address is relative to BAR0. - */ - mem_reg = t4_read_reg(adap, - PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_BASE_WIN_A, - win)); - mem_aperture = 1 << (WINDOW_G(mem_reg) + WINDOW_SHIFT_X); - mem_base = PCIEOFST_G(mem_reg) << PCIEOFST_SHIFT_X; - if (is_t4(adap->params.chip)) - mem_base -= adap->t4_bar0; win_pf = is_t4(adap->params.chip) ? 0 : PFNUM_V(adap->pf); /* Calculate our initial PCI-E Memory Window Position and Offset into * that Window. */ - pos = addr & ~(mem_aperture-1); + pos = addr & ~(mem_aperture - 1); offset = addr - pos; /* Set up initial PCI-E Memory Window to cover the start of our - * transfer. (Read it back to ensure that changes propagate before we - * attempt to use the new value.) + * transfer. */ - t4_write_reg(adap, - PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_OFFSET_A, win), - pos | win_pf); - t4_read_reg(adap, - PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_OFFSET_A, win)); + t4_memory_update_win(adap, win, pos | win_pf); /* Transfer data to/from the adapter as long as there's an integral * number of 32-bit transfers to complete. @@ -628,12 +707,7 @@ int t4_memory_rw(struct adapter *adap, int win, int mtype, u32 addr, if (offset == mem_aperture) { pos += mem_aperture; offset = 0; - t4_write_reg(adap, - PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_OFFSET_A, - win), pos | win_pf); - t4_read_reg(adap, - PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_OFFSET_A, - win)); + t4_memory_update_win(adap, win, pos | win_pf); } } @@ -642,28 +716,9 @@ int t4_memory_rw(struct adapter *adap, int win, int mtype, u32 addr, * residual amount. The PCI-E Memory Window has already been moved * above (if necessary) to cover this final transfer. */ - if (resid) { - union { - u32 word; - char byte[4]; - } last; - unsigned char *bp; - int i; - - if (dir == T4_MEMORY_READ) { - last.word = le32_to_cpu( - (__force __le32)t4_read_reg(adap, - mem_base + offset)); - for (bp = (unsigned char *)buf, i = resid; i < 4; i++) - bp[i] = last.byte[i]; - } else { - last.word = *buf; - for (i = resid; i < 4; i++) - last.byte[i] = 0; - t4_write_reg(adap, mem_base + offset, - (__force u32)cpu_to_le32(last.word)); - } - } + if (resid) + t4_memory_rw_residual(adap, resid, mem_base + offset, + (u8 *)buf, dir); return 0; } @@ -2637,7 +2692,6 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size) } #define EEPROM_STAT_ADDR 0x7bfc -#define VPD_SIZE 0x800 #define VPD_BASE 0x400 #define VPD_BASE_OLD 0 #define VPD_LEN 1024 @@ -2704,15 +2758,6 @@ int t4_get_raw_vpd_params(struct adapter *adapter, struct vpd_params *p) if (!vpd) return -ENOMEM; - /* We have two VPD data structures stored in the adapter VPD area. - * By default, Linux calculates the size of the VPD area by traversing - * the first VPD area at offset 0x0, so we need to tell the OS what - * our real VPD size is. - */ - ret = pci_set_vpd_size(adapter->pdev, VPD_SIZE); - if (ret < 0) - goto out; - /* Card information normally starts at VPD_BASE but early cards had * it at 0. */ diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index 7caa8da48421..159dc2df878d 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -454,6 +454,16 @@ static void dpaa_set_rx_mode(struct net_device *net_dev) err); } + if (!!(net_dev->flags & IFF_ALLMULTI) != priv->mac_dev->allmulti) { + priv->mac_dev->allmulti = !priv->mac_dev->allmulti; + err = priv->mac_dev->set_allmulti(priv->mac_dev->fman_mac, + priv->mac_dev->allmulti); + if (err < 0) + netif_err(priv, drv, net_dev, + "mac_dev->set_allmulti() = %d\n", + err); + } + err = priv->mac_dev->set_multi(net_dev, priv->mac_dev); if (err < 0) netif_err(priv, drv, net_dev, "mac_dev->set_multi() = %d\n", @@ -1916,8 +1926,10 @@ static int skb_to_sg_fd(struct dpaa_priv *priv, goto csum_failed; } + /* SGT[0] is used by the linear part */ sgt = (struct qm_sg_entry *)(sgt_buf + priv->tx_headroom); - qm_sg_entry_set_len(&sgt[0], skb_headlen(skb)); + frag_len = skb_headlen(skb); + qm_sg_entry_set_len(&sgt[0], frag_len); sgt[0].bpid = FSL_DPAA_BPID_INV; sgt[0].offset = 0; addr = dma_map_single(dev, skb->data, @@ -1930,9 +1942,9 @@ static int skb_to_sg_fd(struct dpaa_priv *priv, qm_sg_entry_set64(&sgt[0], addr); /* populate the rest of SGT entries */ - frag = &skb_shinfo(skb)->frags[0]; - frag_len = frag->size; - for (i = 1; i <= nr_frags; i++, frag++) { + for (i = 0; i < nr_frags; i++) { + frag = &skb_shinfo(skb)->frags[i]; + frag_len = frag->size; WARN_ON(!skb_frag_page(frag)); addr = skb_frag_dma_map(dev, frag, 0, frag_len, dma_dir); @@ -1942,15 +1954,16 @@ static int skb_to_sg_fd(struct dpaa_priv *priv, goto sg_map_failed; } - qm_sg_entry_set_len(&sgt[i], frag_len); - sgt[i].bpid = FSL_DPAA_BPID_INV; - sgt[i].offset = 0; + qm_sg_entry_set_len(&sgt[i + 1], frag_len); + sgt[i + 1].bpid = FSL_DPAA_BPID_INV; + sgt[i + 1].offset = 0; /* keep the offset in the address */ - qm_sg_entry_set64(&sgt[i], addr); - frag_len = frag->size; + qm_sg_entry_set64(&sgt[i + 1], addr); } - qm_sg_entry_set_f(&sgt[i - 1], frag_len); + + /* Set the final bit in the last used entry of the SGT */ + qm_sg_entry_set_f(&sgt[nr_frags], frag_len); qm_fd_set_sg(fd, priv->tx_headroom, skb->len); @@ -2052,19 +2065,23 @@ static int dpaa_start_xmit(struct sk_buff *skb, struct net_device *net_dev) /* MAX_SKB_FRAGS is equal or larger than our dpaa_SGT_MAX_ENTRIES; * make sure we don't feed FMan with more fragments than it supports. */ - if (nonlinear && - likely(skb_shinfo(skb)->nr_frags < DPAA_SGT_MAX_ENTRIES)) { - /* Just create a S/G fd based on the skb */ - err = skb_to_sg_fd(priv, skb, &fd); - percpu_priv->tx_frag_skbuffs++; - } else { + if (unlikely(nonlinear && + (skb_shinfo(skb)->nr_frags >= DPAA_SGT_MAX_ENTRIES))) { /* If the egress skb contains more fragments than we support * we have no choice but to linearize it ourselves. */ - if (unlikely(nonlinear) && __skb_linearize(skb)) + if (__skb_linearize(skb)) goto enomem; - /* Finally, create a contig FD from this skb */ + nonlinear = skb_is_nonlinear(skb); + } + + if (nonlinear) { + /* Just create a S/G fd based on the skb */ + err = skb_to_sg_fd(priv, skb, &fd); + percpu_priv->tx_frag_skbuffs++; + } else { + /* Create a contig FD from this skb */ err = skb_to_contig_fd(priv, skb, &fd, &offset); } if (unlikely(err < 0)) @@ -2201,14 +2218,8 @@ static enum qman_cb_dqrr_result rx_error_dqrr(struct qman_portal *portal, if (dpaa_eth_napi_schedule(percpu_priv, portal)) return qman_cb_dqrr_stop; - if (dpaa_eth_refill_bpools(priv)) - /* Unable to refill the buffer pool due to insufficient - * system memory. Just release the frame back into the pool, - * otherwise we'll soon end up with an empty buffer pool. - */ - dpaa_fd_release(net_dev, &dq->fd); - else - dpaa_rx_error(net_dev, priv, percpu_priv, &dq->fd, fq->fqid); + dpaa_eth_refill_bpools(priv); + dpaa_rx_error(net_dev, priv, percpu_priv, &dq->fd, fq->fqid); return qman_cb_dqrr_consume; } @@ -2766,7 +2777,7 @@ static int dpaa_eth_probe(struct platform_device *pdev) priv->channel = (u16)channel; - /* Start a thread that will walk the CPUs with affine portals + /* Walk the CPUs with affine portals * and add this pool channel to each's dequeue mask. */ dpaa_eth_add_channel(priv->channel); diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c index faea674094b9..85306d1b2acf 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c @@ -211,7 +211,7 @@ static int dpaa_set_pauseparam(struct net_device *net_dev, if (epause->rx_pause) newadv = ADVERTISED_Pause | ADVERTISED_Asym_Pause; if (epause->tx_pause) - newadv |= ADVERTISED_Asym_Pause; + newadv ^= ADVERTISED_Asym_Pause; oldadv = phydev->advertising & (ADVERTISED_Pause | ADVERTISED_Asym_Pause); diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.c b/drivers/net/ethernet/freescale/fman/fman_dtsec.c index ea43b4974149..9a581faaa742 100644 --- a/drivers/net/ethernet/freescale/fman/fman_dtsec.c +++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.c @@ -1117,6 +1117,25 @@ int dtsec_add_hash_mac_address(struct fman_mac *dtsec, enet_addr_t *eth_addr) return 0; } +int dtsec_set_allmulti(struct fman_mac *dtsec, bool enable) +{ + u32 tmp; + struct dtsec_regs __iomem *regs = dtsec->regs; + + if (!is_init_done(dtsec->dtsec_drv_param)) + return -EINVAL; + + tmp = ioread32be(®s->rctrl); + if (enable) + tmp |= RCTRL_MPROM; + else + tmp &= ~RCTRL_MPROM; + + iowrite32be(tmp, ®s->rctrl); + + return 0; +} + int dtsec_del_hash_mac_address(struct fman_mac *dtsec, enet_addr_t *eth_addr) { struct dtsec_regs __iomem *regs = dtsec->regs; diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.h b/drivers/net/ethernet/freescale/fman/fman_dtsec.h index c4467c072058..1a689adf5a22 100644 --- a/drivers/net/ethernet/freescale/fman/fman_dtsec.h +++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.h @@ -55,5 +55,6 @@ int dtsec_set_exception(struct fman_mac *dtsec, int dtsec_add_hash_mac_address(struct fman_mac *dtsec, enet_addr_t *eth_addr); int dtsec_del_hash_mac_address(struct fman_mac *dtsec, enet_addr_t *eth_addr); int dtsec_get_version(struct fman_mac *dtsec, u32 *mac_version); +int dtsec_set_allmulti(struct fman_mac *dtsec, bool enable); #endif /* __DTSEC_H */ diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c index c0296880feba..446a97b792e3 100644 --- a/drivers/net/ethernet/freescale/fman/fman_memac.c +++ b/drivers/net/ethernet/freescale/fman/fman_memac.c @@ -350,6 +350,7 @@ struct fman_mac { struct fman_rev_info fm_rev_info; bool basex_if; struct phy_device *pcsphy; + bool allmulti_enabled; }; static void add_addr_in_paddr(struct memac_regs __iomem *regs, u8 *adr, @@ -940,6 +941,29 @@ int memac_add_hash_mac_address(struct fman_mac *memac, enet_addr_t *eth_addr) return 0; } +int memac_set_allmulti(struct fman_mac *memac, bool enable) +{ + u32 entry; + struct memac_regs __iomem *regs = memac->regs; + + if (!is_init_done(memac->memac_drv_param)) + return -EINVAL; + + if (enable) { + for (entry = 0; entry < HASH_TABLE_SIZE; entry++) + iowrite32be(entry | HASH_CTRL_MCAST_EN, + ®s->hashtable_ctrl); + } else { + for (entry = 0; entry < HASH_TABLE_SIZE; entry++) + iowrite32be(entry & ~HASH_CTRL_MCAST_EN, + ®s->hashtable_ctrl); + } + + memac->allmulti_enabled = enable; + + return 0; +} + int memac_del_hash_mac_address(struct fman_mac *memac, enet_addr_t *eth_addr) { struct memac_regs __iomem *regs = memac->regs; @@ -963,8 +987,12 @@ int memac_del_hash_mac_address(struct fman_mac *memac, enet_addr_t *eth_addr) break; } } - if (list_empty(&memac->multicast_addr_hash->lsts[hash])) - iowrite32be(hash & ~HASH_CTRL_MCAST_EN, ®s->hashtable_ctrl); + + if (!memac->allmulti_enabled) { + if (list_empty(&memac->multicast_addr_hash->lsts[hash])) + iowrite32be(hash & ~HASH_CTRL_MCAST_EN, + ®s->hashtable_ctrl); + } return 0; } diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.h b/drivers/net/ethernet/freescale/fman/fman_memac.h index c4a66469a907..b5a50338ed9a 100644 --- a/drivers/net/ethernet/freescale/fman/fman_memac.h +++ b/drivers/net/ethernet/freescale/fman/fman_memac.h @@ -57,5 +57,6 @@ int memac_set_exception(struct fman_mac *memac, enum fman_mac_exceptions exception, bool enable); int memac_add_hash_mac_address(struct fman_mac *memac, enet_addr_t *eth_addr); int memac_del_hash_mac_address(struct fman_mac *memac, enet_addr_t *eth_addr); +int memac_set_allmulti(struct fman_mac *memac, bool enable); #endif /* __MEMAC_H */ diff --git a/drivers/net/ethernet/freescale/fman/fman_tgec.c b/drivers/net/ethernet/freescale/fman/fman_tgec.c index 4b0f3a50b293..284735d4ebe9 100644 --- a/drivers/net/ethernet/freescale/fman/fman_tgec.c +++ b/drivers/net/ethernet/freescale/fman/fman_tgec.c @@ -217,6 +217,7 @@ struct fman_mac { struct tgec_cfg *cfg; void *fm; struct fman_rev_info fm_rev_info; + bool allmulti_enabled; }; static void set_mac_address(struct tgec_regs __iomem *regs, u8 *adr) @@ -564,6 +565,29 @@ int tgec_add_hash_mac_address(struct fman_mac *tgec, enet_addr_t *eth_addr) return 0; } +int tgec_set_allmulti(struct fman_mac *tgec, bool enable) +{ + u32 entry; + struct tgec_regs __iomem *regs = tgec->regs; + + if (!is_init_done(tgec->cfg)) + return -EINVAL; + + if (enable) { + for (entry = 0; entry < TGEC_HASH_TABLE_SIZE; entry++) + iowrite32be(entry | TGEC_HASH_MCAST_EN, + ®s->hashtable_ctrl); + } else { + for (entry = 0; entry < TGEC_HASH_TABLE_SIZE; entry++) + iowrite32be(entry & ~TGEC_HASH_MCAST_EN, + ®s->hashtable_ctrl); + } + + tgec->allmulti_enabled = enable; + + return 0; +} + int tgec_del_hash_mac_address(struct fman_mac *tgec, enet_addr_t *eth_addr) { struct tgec_regs __iomem *regs = tgec->regs; @@ -591,9 +615,12 @@ int tgec_del_hash_mac_address(struct fman_mac *tgec, enet_addr_t *eth_addr) break; } } - if (list_empty(&tgec->multicast_addr_hash->lsts[hash])) - iowrite32be((hash & ~TGEC_HASH_MCAST_EN), - ®s->hashtable_ctrl); + + if (!tgec->allmulti_enabled) { + if (list_empty(&tgec->multicast_addr_hash->lsts[hash])) + iowrite32be((hash & ~TGEC_HASH_MCAST_EN), + ®s->hashtable_ctrl); + } return 0; } diff --git a/drivers/net/ethernet/freescale/fman/fman_tgec.h b/drivers/net/ethernet/freescale/fman/fman_tgec.h index 514bba9f47ce..cbbd3b422a98 100644 --- a/drivers/net/ethernet/freescale/fman/fman_tgec.h +++ b/drivers/net/ethernet/freescale/fman/fman_tgec.h @@ -51,5 +51,6 @@ int tgec_set_exception(struct fman_mac *tgec, int tgec_add_hash_mac_address(struct fman_mac *tgec, enet_addr_t *eth_addr); int tgec_del_hash_mac_address(struct fman_mac *tgec, enet_addr_t *eth_addr); int tgec_get_version(struct fman_mac *tgec, u32 *mac_version); +int tgec_set_allmulti(struct fman_mac *tgec, bool enable); #endif /* __TGEC_H */ diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c index 88c0a0636b44..4829dcd9e077 100644 --- a/drivers/net/ethernet/freescale/fman/mac.c +++ b/drivers/net/ethernet/freescale/fman/mac.c @@ -470,6 +470,7 @@ static void setup_dtsec(struct mac_device *mac_dev) mac_dev->set_tx_pause = dtsec_set_tx_pause_frames; mac_dev->set_rx_pause = dtsec_accept_rx_pause_frames; mac_dev->set_exception = dtsec_set_exception; + mac_dev->set_allmulti = dtsec_set_allmulti; mac_dev->set_multi = set_multi; mac_dev->start = start; mac_dev->stop = stop; @@ -488,6 +489,7 @@ static void setup_tgec(struct mac_device *mac_dev) mac_dev->set_tx_pause = tgec_set_tx_pause_frames; mac_dev->set_rx_pause = tgec_accept_rx_pause_frames; mac_dev->set_exception = tgec_set_exception; + mac_dev->set_allmulti = tgec_set_allmulti; mac_dev->set_multi = set_multi; mac_dev->start = start; mac_dev->stop = stop; @@ -506,6 +508,7 @@ static void setup_memac(struct mac_device *mac_dev) mac_dev->set_tx_pause = memac_set_tx_pause_frames; mac_dev->set_rx_pause = memac_accept_rx_pause_frames; mac_dev->set_exception = memac_set_exception; + mac_dev->set_allmulti = memac_set_allmulti; mac_dev->set_multi = set_multi; mac_dev->start = start; mac_dev->stop = stop; diff --git a/drivers/net/ethernet/freescale/fman/mac.h b/drivers/net/ethernet/freescale/fman/mac.h index eefb3357e304..b520cec120ee 100644 --- a/drivers/net/ethernet/freescale/fman/mac.h +++ b/drivers/net/ethernet/freescale/fman/mac.h @@ -59,6 +59,7 @@ struct mac_device { bool rx_pause_active; bool tx_pause_active; bool promisc; + bool allmulti; int (*init)(struct mac_device *mac_dev); int (*start)(struct mac_device *mac_dev); @@ -66,6 +67,7 @@ struct mac_device { void (*adjust_link)(struct mac_device *mac_dev); int (*set_promisc)(struct fman_mac *mac_dev, bool enable); int (*change_addr)(struct fman_mac *mac_dev, enet_addr_t *enet_addr); + int (*set_allmulti)(struct fman_mac *mac_dev, bool enable); int (*set_multi)(struct net_device *net_dev, struct mac_device *mac_dev); int (*set_rx_pause)(struct fman_mac *mac_dev, bool en); diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 3bdeb295514b..f5c87bd35fa1 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -2934,29 +2934,17 @@ static bool gfar_add_rx_frag(struct gfar_rx_buff *rxb, u32 lstatus, { int size = lstatus & BD_LENGTH_MASK; struct page *page = rxb->page; - bool last = !!(lstatus & BD_LFLAG(RXBD_LAST)); - - /* Remove the FCS from the packet length */ - if (last) - size -= ETH_FCS_LEN; if (likely(first)) { skb_put(skb, size); } else { /* the last fragments' length contains the full frame length */ - if (last) + if (lstatus & BD_LFLAG(RXBD_LAST)) size -= skb->len; - /* Add the last fragment if it contains something other than - * the FCS, otherwise drop it and trim off any part of the FCS - * that was already received. - */ - if (size > 0) - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, - rxb->page_offset + RXBUF_ALIGNMENT, - size, GFAR_RXB_TRUESIZE); - else if (size < 0) - pskb_trim(skb, skb->len + size); + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, + rxb->page_offset + RXBUF_ALIGNMENT, + size, GFAR_RXB_TRUESIZE); } /* try reuse page */ @@ -3069,6 +3057,9 @@ static void gfar_process_frame(struct net_device *ndev, struct sk_buff *skb) if (priv->padding) skb_pull(skb, priv->padding); + /* Trim off the FCS */ + pskb_trim(skb, skb->len - ETH_FCS_LEN); + if (ndev->features & NETIF_F_RXCSUM) gfar_rx_checksum(skb, fcb); diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 27447260215d..765407179fdd 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -90,7 +90,7 @@ MODULE_VERSION(IBMVNIC_DRIVER_VERSION); static int ibmvnic_version = IBMVNIC_INITIAL_VERSION; static int ibmvnic_remove(struct vio_dev *); -static void release_sub_crqs(struct ibmvnic_adapter *); +static void release_sub_crqs(struct ibmvnic_adapter *, bool); static int ibmvnic_reset_crq(struct ibmvnic_adapter *); static int ibmvnic_send_crq_init(struct ibmvnic_adapter *); static int ibmvnic_reenable_crq_queue(struct ibmvnic_adapter *); @@ -111,7 +111,7 @@ static int ibmvnic_poll(struct napi_struct *napi, int data); static void send_map_query(struct ibmvnic_adapter *adapter); static void send_request_map(struct ibmvnic_adapter *, dma_addr_t, __be32, u8); static void send_request_unmap(struct ibmvnic_adapter *, u8); -static void send_login(struct ibmvnic_adapter *adapter); +static int send_login(struct ibmvnic_adapter *adapter); static void send_cap_queries(struct ibmvnic_adapter *adapter); static int init_sub_crqs(struct ibmvnic_adapter *); static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter); @@ -361,14 +361,14 @@ static void release_stats_buffers(struct ibmvnic_adapter *adapter) static int init_stats_buffers(struct ibmvnic_adapter *adapter) { adapter->tx_stats_buffers = - kcalloc(adapter->req_tx_queues, + kcalloc(IBMVNIC_MAX_QUEUES, sizeof(struct ibmvnic_tx_queue_stats), GFP_KERNEL); if (!adapter->tx_stats_buffers) return -ENOMEM; adapter->rx_stats_buffers = - kcalloc(adapter->req_rx_queues, + kcalloc(IBMVNIC_MAX_QUEUES, sizeof(struct ibmvnic_rx_queue_stats), GFP_KERNEL); if (!adapter->rx_stats_buffers) @@ -509,7 +509,7 @@ static int init_rx_pools(struct net_device *netdev) return -1; } - adapter->num_active_rx_pools = 0; + adapter->num_active_rx_pools = rxadd_subcrqs; for (i = 0; i < rxadd_subcrqs; i++) { rx_pool = &adapter->rx_pool[i]; @@ -554,8 +554,6 @@ static int init_rx_pools(struct net_device *netdev) rx_pool->next_free = 0; } - adapter->num_active_rx_pools = rxadd_subcrqs; - return 0; } @@ -641,7 +639,7 @@ static int init_tx_pools(struct net_device *netdev) if (!adapter->tx_pool) return -1; - adapter->num_active_tx_pools = 0; + adapter->num_active_tx_pools = tx_subcrqs; for (i = 0; i < tx_subcrqs; i++) { tx_pool = &adapter->tx_pool[i]; @@ -690,8 +688,6 @@ static int init_tx_pools(struct net_device *netdev) tx_pool->producer_index = 0; } - adapter->num_active_tx_pools = tx_subcrqs; - return 0; } @@ -740,6 +736,45 @@ static void ibmvnic_napi_disable(struct ibmvnic_adapter *adapter) adapter->napi_enabled = false; } +static int init_napi(struct ibmvnic_adapter *adapter) +{ + int i; + + adapter->napi = kcalloc(adapter->req_rx_queues, + sizeof(struct napi_struct), GFP_KERNEL); + if (!adapter->napi) + return -ENOMEM; + + for (i = 0; i < adapter->req_rx_queues; i++) { + netdev_dbg(adapter->netdev, "Adding napi[%d]\n", i); + netif_napi_add(adapter->netdev, &adapter->napi[i], + ibmvnic_poll, NAPI_POLL_WEIGHT); + } + + adapter->num_active_rx_napi = adapter->req_rx_queues; + return 0; +} + +static void release_napi(struct ibmvnic_adapter *adapter) +{ + int i; + + if (!adapter->napi) + return; + + for (i = 0; i < adapter->num_active_rx_napi; i++) { + if (&adapter->napi[i]) { + netdev_dbg(adapter->netdev, + "Releasing napi[%d]\n", i); + netif_napi_del(&adapter->napi[i]); + } + } + + kfree(adapter->napi); + adapter->napi = NULL; + adapter->num_active_rx_napi = 0; +} + static int ibmvnic_login(struct net_device *netdev) { struct ibmvnic_adapter *adapter = netdev_priv(netdev); @@ -750,7 +785,7 @@ static int ibmvnic_login(struct net_device *netdev) do { if (adapter->renegotiate) { adapter->renegotiate = false; - release_sub_crqs(adapter); + release_sub_crqs(adapter, 1); reinit_completion(&adapter->init_done); send_cap_queries(adapter); @@ -774,8 +809,11 @@ static int ibmvnic_login(struct net_device *netdev) } reinit_completion(&adapter->init_done); - send_login(adapter); - if (!wait_for_completion_timeout(&adapter->init_done, + rc = send_login(adapter); + if (rc) { + dev_err(dev, "Unable to attempt device login\n"); + return rc; + } else if (!wait_for_completion_timeout(&adapter->init_done, timeout)) { dev_err(dev, "Login timeout\n"); return -1; @@ -791,28 +829,28 @@ static int ibmvnic_login(struct net_device *netdev) return 0; } -static void release_resources(struct ibmvnic_adapter *adapter) +static void release_login_buffer(struct ibmvnic_adapter *adapter) { - int i; + kfree(adapter->login_buf); + adapter->login_buf = NULL; +} +static void release_login_rsp_buffer(struct ibmvnic_adapter *adapter) +{ + kfree(adapter->login_rsp_buf); + adapter->login_rsp_buf = NULL; +} + +static void release_resources(struct ibmvnic_adapter *adapter) +{ release_vpd_data(adapter); release_tx_pools(adapter); release_rx_pools(adapter); - release_stats_token(adapter); - release_stats_buffers(adapter); release_error_buffers(adapter); - - if (adapter->napi) { - for (i = 0; i < adapter->req_rx_queues; i++) { - if (&adapter->napi[i]) { - netdev_dbg(adapter->netdev, - "Releasing napi[%d]\n", i); - netif_napi_del(&adapter->napi[i]); - } - } - } + release_napi(adapter); + release_login_rsp_buffer(adapter); } static int set_link_state(struct ibmvnic_adapter *adapter, u8 link_state) @@ -931,20 +969,12 @@ static int ibmvnic_get_vpd(struct ibmvnic_adapter *adapter) static int init_resources(struct ibmvnic_adapter *adapter) { struct net_device *netdev = adapter->netdev; - int i, rc; + int rc; rc = set_real_num_queues(netdev); if (rc) return rc; - rc = init_stats_buffers(adapter); - if (rc) - return rc; - - rc = init_stats_token(adapter); - if (rc) - return rc; - adapter->vpd = kzalloc(sizeof(*adapter->vpd), GFP_KERNEL); if (!adapter->vpd) return -ENOMEM; @@ -957,16 +987,10 @@ static int init_resources(struct ibmvnic_adapter *adapter) } adapter->map_id = 1; - adapter->napi = kcalloc(adapter->req_rx_queues, - sizeof(struct napi_struct), GFP_KERNEL); - if (!adapter->napi) - return -ENOMEM; - for (i = 0; i < adapter->req_rx_queues; i++) { - netdev_dbg(netdev, "Adding napi[%d]\n", i); - netif_napi_add(netdev, &adapter->napi[i], ibmvnic_poll, - NAPI_POLL_WEIGHT); - } + rc = init_napi(adapter); + if (rc) + return rc; send_map_query(adapter); @@ -1057,9 +1081,41 @@ static int ibmvnic_open(struct net_device *netdev) return rc; } +static void clean_rx_pools(struct ibmvnic_adapter *adapter) +{ + struct ibmvnic_rx_pool *rx_pool; + struct ibmvnic_rx_buff *rx_buff; + u64 rx_entries; + int rx_scrqs; + int i, j; + + if (!adapter->rx_pool) + return; + + rx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs); + rx_entries = adapter->req_rx_add_entries_per_subcrq; + + /* Free any remaining skbs in the rx buffer pools */ + for (i = 0; i < rx_scrqs; i++) { + rx_pool = &adapter->rx_pool[i]; + if (!rx_pool || !rx_pool->rx_buff) + continue; + + netdev_dbg(adapter->netdev, "Cleaning rx_pool[%d]\n", i); + for (j = 0; j < rx_entries; j++) { + rx_buff = &rx_pool->rx_buff[j]; + if (rx_buff && rx_buff->skb) { + dev_kfree_skb_any(rx_buff->skb); + rx_buff->skb = NULL; + } + } + } +} + static void clean_tx_pools(struct ibmvnic_adapter *adapter) { struct ibmvnic_tx_pool *tx_pool; + struct ibmvnic_tx_buff *tx_buff; u64 tx_entries; int tx_scrqs; int i, j; @@ -1073,14 +1129,15 @@ static void clean_tx_pools(struct ibmvnic_adapter *adapter) /* Free any remaining skbs in the tx buffer pools */ for (i = 0; i < tx_scrqs; i++) { tx_pool = &adapter->tx_pool[i]; - if (!tx_pool) + if (!tx_pool && !tx_pool->tx_buff) continue; netdev_dbg(adapter->netdev, "Cleaning tx_pool[%d]\n", i); for (j = 0; j < tx_entries; j++) { - if (tx_pool->tx_buff[j].skb) { - dev_kfree_skb_any(tx_pool->tx_buff[j].skb); - tx_pool->tx_buff[j].skb = NULL; + tx_buff = &tx_pool->tx_buff[j]; + if (tx_buff && tx_buff->skb) { + dev_kfree_skb_any(tx_buff->skb); + tx_buff->skb = NULL; } } } @@ -1134,7 +1191,7 @@ static int __ibmvnic_close(struct net_device *netdev) } } } - + clean_rx_pools(adapter); clean_tx_pools(adapter); adapter->state = VNIC_CLOSED; return rc; @@ -1422,6 +1479,7 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) if ((*hdrs >> 7) & 1) { build_hdr_descs_arr(tx_buff, &num_entries, *hdrs); tx_crq.v1.n_crq_elem = num_entries; + tx_buff->num_entries = num_entries; tx_buff->indir_arr[0] = tx_crq; tx_buff->indir_dma = dma_map_single(dev, tx_buff->indir_arr, sizeof(tx_buff->indir_arr), @@ -1440,6 +1498,7 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) (u64)tx_buff->indir_dma, (u64)num_entries); } else { + tx_buff->num_entries = num_entries; lpar_rc = send_subcrq(adapter, handle_array[queue_num], &tx_crq); } @@ -1470,9 +1529,9 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) goto out; } - if (atomic_inc_return(&tx_scrq->used) + if (atomic_add_return(num_entries, &tx_scrq->used) >= adapter->req_tx_entries_per_subcrq) { - netdev_info(netdev, "Stopping queue %d\n", queue_num); + netdev_dbg(netdev, "Stopping queue %d\n", queue_num); netif_stop_subqueue(netdev, queue_num); } @@ -1608,7 +1667,7 @@ static int do_reset(struct ibmvnic_adapter *adapter, if (adapter->reset_reason == VNIC_RESET_CHANGE_PARAM || adapter->wait_for_reset) { release_resources(adapter); - release_sub_crqs(adapter); + release_sub_crqs(adapter, 1); release_crq_queue(adapter); } @@ -1646,6 +1705,9 @@ static int do_reset(struct ibmvnic_adapter *adapter, release_tx_pools(adapter); init_rx_pools(netdev); init_tx_pools(netdev); + + release_napi(adapter); + init_napi(adapter); } else { rc = reset_tx_pools(adapter); if (rc) @@ -1670,8 +1732,6 @@ static int do_reset(struct ibmvnic_adapter *adapter, return 0; } - netif_carrier_on(netdev); - /* kick napi */ for (i = 0; i < adapter->req_rx_queues; i++) napi_schedule(&adapter->napi[i]); @@ -1679,6 +1739,8 @@ static int do_reset(struct ibmvnic_adapter *adapter, if (adapter->reset_reason != VNIC_RESET_FAILOVER) netdev_notify_peers(netdev); + netif_carrier_on(netdev); + return 0; } @@ -1853,6 +1915,12 @@ restart_poll: be16_to_cpu(next->rx_comp.rc)); /* free the entry */ next->rx_comp.first = 0; + dev_kfree_skb_any(rx_buff->skb); + remove_buff_from_pool(adapter, rx_buff); + continue; + } else if (!rx_buff->skb) { + /* free the entry */ + next->rx_comp.first = 0; remove_buff_from_pool(adapter, rx_buff); continue; } @@ -2244,24 +2312,27 @@ static int reset_sub_crq_queues(struct ibmvnic_adapter *adapter) } static void release_sub_crq_queue(struct ibmvnic_adapter *adapter, - struct ibmvnic_sub_crq_queue *scrq) + struct ibmvnic_sub_crq_queue *scrq, + bool do_h_free) { struct device *dev = &adapter->vdev->dev; long rc; netdev_dbg(adapter->netdev, "Releasing sub-CRQ\n"); - /* Close the sub-crqs */ - do { - rc = plpar_hcall_norets(H_FREE_SUB_CRQ, - adapter->vdev->unit_address, - scrq->crq_num); - } while (rc == H_BUSY || H_IS_LONG_BUSY(rc)); + if (do_h_free) { + /* Close the sub-crqs */ + do { + rc = plpar_hcall_norets(H_FREE_SUB_CRQ, + adapter->vdev->unit_address, + scrq->crq_num); + } while (rc == H_BUSY || H_IS_LONG_BUSY(rc)); - if (rc) { - netdev_err(adapter->netdev, - "Failed to release sub-CRQ %16lx, rc = %ld\n", - scrq->crq_num, rc); + if (rc) { + netdev_err(adapter->netdev, + "Failed to release sub-CRQ %16lx, rc = %ld\n", + scrq->crq_num, rc); + } } dma_unmap_single(dev, scrq->msg_token, 4 * PAGE_SIZE, @@ -2329,12 +2400,12 @@ zero_page_failed: return NULL; } -static void release_sub_crqs(struct ibmvnic_adapter *adapter) +static void release_sub_crqs(struct ibmvnic_adapter *adapter, bool do_h_free) { int i; if (adapter->tx_scrq) { - for (i = 0; i < adapter->req_tx_queues; i++) { + for (i = 0; i < adapter->num_active_tx_scrqs; i++) { if (!adapter->tx_scrq[i]) continue; @@ -2347,15 +2418,17 @@ static void release_sub_crqs(struct ibmvnic_adapter *adapter) adapter->tx_scrq[i]->irq = 0; } - release_sub_crq_queue(adapter, adapter->tx_scrq[i]); + release_sub_crq_queue(adapter, adapter->tx_scrq[i], + do_h_free); } kfree(adapter->tx_scrq); adapter->tx_scrq = NULL; + adapter->num_active_tx_scrqs = 0; } if (adapter->rx_scrq) { - for (i = 0; i < adapter->req_rx_queues; i++) { + for (i = 0; i < adapter->num_active_rx_scrqs; i++) { if (!adapter->rx_scrq[i]) continue; @@ -2368,11 +2441,13 @@ static void release_sub_crqs(struct ibmvnic_adapter *adapter) adapter->rx_scrq[i]->irq = 0; } - release_sub_crq_queue(adapter, adapter->rx_scrq[i]); + release_sub_crq_queue(adapter, adapter->rx_scrq[i], + do_h_free); } kfree(adapter->rx_scrq); adapter->rx_scrq = NULL; + adapter->num_active_rx_scrqs = 0; } } @@ -2422,6 +2497,7 @@ static int ibmvnic_complete_tx(struct ibmvnic_adapter *adapter, restart_loop: while (pending_scrq(adapter, scrq)) { unsigned int pool = scrq->pool_index; + int num_entries = 0; next = ibmvnic_next_scrq(adapter, scrq); for (i = 0; i < next->tx_comp.num_comps; i++) { @@ -2452,6 +2528,8 @@ restart_loop: txbuff->skb = NULL; } + num_entries += txbuff->num_entries; + adapter->tx_pool[pool].free_map[adapter->tx_pool[pool]. producer_index] = index; adapter->tx_pool[pool].producer_index = @@ -2461,13 +2539,13 @@ restart_loop: /* remove tx_comp scrq*/ next->tx_comp.first = 0; - if (atomic_sub_return(next->tx_comp.num_comps, &scrq->used) <= + if (atomic_sub_return(num_entries, &scrq->used) <= (adapter->req_tx_entries_per_subcrq / 2) && __netif_subqueue_stopped(adapter->netdev, scrq->pool_index)) { netif_wake_subqueue(adapter->netdev, scrq->pool_index); - netdev_info(adapter->netdev, "Started queue %d\n", - scrq->pool_index); + netdev_dbg(adapter->netdev, "Started queue %d\n", + scrq->pool_index); } } @@ -2539,7 +2617,7 @@ static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter) dev_err(dev, "Couldn't register tx irq 0x%x. rc=%d\n", scrq->irq, rc); irq_dispose_mapping(scrq->irq); - goto req_rx_irq_failed; + goto req_tx_irq_failed; } } @@ -2575,7 +2653,7 @@ req_tx_irq_failed: free_irq(adapter->tx_scrq[j]->irq, adapter->tx_scrq[j]); irq_dispose_mapping(adapter->rx_scrq[j]->irq); } - release_sub_crqs(adapter); + release_sub_crqs(adapter, 1); return rc; } @@ -2637,6 +2715,7 @@ static int init_sub_crqs(struct ibmvnic_adapter *adapter) for (i = 0; i < adapter->req_tx_queues; i++) { adapter->tx_scrq[i] = allqueues[i]; adapter->tx_scrq[i]->pool_index = i; + adapter->num_active_tx_scrqs++; } adapter->rx_scrq = kcalloc(adapter->req_rx_queues, @@ -2647,6 +2726,7 @@ static int init_sub_crqs(struct ibmvnic_adapter *adapter) for (i = 0; i < adapter->req_rx_queues; i++) { adapter->rx_scrq[i] = allqueues[i + adapter->req_tx_queues]; adapter->rx_scrq[i]->scrq_num = i; + adapter->num_active_rx_scrqs++; } kfree(allqueues); @@ -2657,7 +2737,7 @@ rx_failed: adapter->tx_scrq = NULL; tx_failed: for (i = 0; i < registered_queues; i++) - release_sub_crq_queue(adapter, allqueues[i]); + release_sub_crq_queue(adapter, allqueues[i], 1); kfree(allqueues); return -1; } @@ -2997,7 +3077,7 @@ static void vnic_add_client_data(struct ibmvnic_adapter *adapter, strncpy(&vlcd->name, adapter->netdev->name, len); } -static void send_login(struct ibmvnic_adapter *adapter) +static int send_login(struct ibmvnic_adapter *adapter) { struct ibmvnic_login_rsp_buffer *login_rsp_buffer; struct ibmvnic_login_buffer *login_buffer; @@ -3013,6 +3093,13 @@ static void send_login(struct ibmvnic_adapter *adapter) struct vnic_login_client_data *vlcd; int i; + if (!adapter->tx_scrq || !adapter->rx_scrq) { + netdev_err(adapter->netdev, + "RX or TX queues are not allocated, device login failed\n"); + return -1; + } + + release_login_rsp_buffer(adapter); client_data_len = vnic_client_data_len(adapter); buffer_size = @@ -3109,7 +3196,7 @@ static void send_login(struct ibmvnic_adapter *adapter) crq.login.len = cpu_to_be32(buffer_size); ibmvnic_send_crq(adapter, &crq); - return; + return 0; buf_rsp_map_failed: kfree(login_rsp_buffer); @@ -3118,7 +3205,7 @@ buf_rsp_alloc_failed: buf_map_failed: kfree(login_buffer); buf_alloc_failed: - return; + return -1; } static void send_request_map(struct ibmvnic_adapter *adapter, dma_addr_t addr, @@ -3738,6 +3825,7 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq, ibmvnic_remove(adapter->vdev); return -EIO; } + release_login_buffer(adapter); complete(&adapter->init_done); return 0; @@ -4282,6 +4370,7 @@ static int ibmvnic_init(struct ibmvnic_adapter *adapter) { struct device *dev = &adapter->vdev->dev; unsigned long timeout = msecs_to_jiffies(30000); + u64 old_num_rx_queues, old_num_tx_queues; int rc; if (adapter->resetting && !adapter->wait_for_reset) { @@ -4299,6 +4388,9 @@ static int ibmvnic_init(struct ibmvnic_adapter *adapter) adapter->from_passive_init = false; + old_num_rx_queues = adapter->req_rx_queues; + old_num_tx_queues = adapter->req_tx_queues; + init_completion(&adapter->init_done); adapter->init_done_rc = 0; ibmvnic_send_crq_init(adapter); @@ -4318,10 +4410,18 @@ static int ibmvnic_init(struct ibmvnic_adapter *adapter) return -1; } - if (adapter->resetting && !adapter->wait_for_reset) - rc = reset_sub_crq_queues(adapter); - else + if (adapter->resetting && !adapter->wait_for_reset) { + if (adapter->req_rx_queues != old_num_rx_queues || + adapter->req_tx_queues != old_num_tx_queues) { + release_sub_crqs(adapter, 0); + rc = init_sub_crqs(adapter); + } else { + rc = reset_sub_crq_queues(adapter); + } + } else { rc = init_sub_crqs(adapter); + } + if (rc) { dev_err(dev, "Initialization of sub crqs failed\n"); release_crq_queue(adapter); @@ -4334,6 +4434,14 @@ static int ibmvnic_init(struct ibmvnic_adapter *adapter) release_crq_queue(adapter); } + rc = init_stats_buffers(adapter); + if (rc) + return rc; + + rc = init_stats_token(adapter); + if (rc) + return rc; + return rc; } @@ -4421,7 +4529,7 @@ ibmvnic_register_fail: device_remove_file(&dev->dev, &dev_attr_failover); ibmvnic_init_fail: - release_sub_crqs(adapter); + release_sub_crqs(adapter, 1); release_crq_queue(adapter); free_netdev(netdev); @@ -4438,9 +4546,12 @@ static int ibmvnic_remove(struct vio_dev *dev) mutex_lock(&adapter->reset_lock); release_resources(adapter); - release_sub_crqs(adapter); + release_sub_crqs(adapter, 1); release_crq_queue(adapter); + release_stats_token(adapter); + release_stats_buffers(adapter); + adapter->state = VNIC_REMOVED; mutex_unlock(&adapter->reset_lock); diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index fe21a6e2ddae..099c89d49945 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -909,6 +909,7 @@ struct ibmvnic_tx_buff { union sub_crq indir_arr[6]; u8 hdr_data[140]; dma_addr_t indir_dma; + int num_entries; }; struct ibmvnic_tx_pool { @@ -1091,8 +1092,11 @@ struct ibmvnic_adapter { u64 opt_rxba_entries_per_subcrq; __be64 tx_rx_desc_req; u8 map_id; - u64 num_active_rx_pools; - u64 num_active_tx_pools; + u32 num_active_rx_scrqs; + u32 num_active_rx_pools; + u32 num_active_rx_napi; + u32 num_active_tx_scrqs; + u32 num_active_tx_pools; struct tasklet_struct tasklet; enum vnic_state state; diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 46e9f4e0a02c..36d9401a6258 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -507,6 +507,7 @@ struct i40e_pf { #define I40E_HW_STOP_FW_LLDP BIT(16) #define I40E_HW_PORT_ID_VALID BIT(17) #define I40E_HW_RESTART_AUTONEG BIT(18) +#define I40E_HW_STOPPABLE_FW_LLDP BIT(19) u64 flags; #define I40E_FLAG_RX_CSUM_ENABLED BIT_ULL(0) @@ -824,6 +825,7 @@ struct i40e_q_vector { struct i40e_ring_container rx; struct i40e_ring_container tx; + u8 itr_countdown; /* when 0 should adjust adaptive ITR */ u8 num_ringpairs; /* total number of ring pairs in vector */ cpumask_t affinity_mask; @@ -832,8 +834,6 @@ struct i40e_q_vector { struct rcu_head rcu; /* to avoid race with update stats on free */ char name[I40E_INT_NAME_STR_LEN]; bool arm_wb_state; -#define ITR_COUNTDOWN_START 100 - u8 itr_countdown; /* when 0 should adjust ITR */ } ____cacheline_internodealigned_in_smp; /* lan device */ @@ -1109,4 +1109,10 @@ static inline bool i40e_enabled_xdp_vsi(struct i40e_vsi *vsi) int i40e_create_queue_channel(struct i40e_vsi *vsi, struct i40e_channel *ch); int i40e_set_bw_limit(struct i40e_vsi *vsi, u16 seid, u64 max_tx_rate); +int i40e_add_del_cloud_filter(struct i40e_vsi *vsi, + struct i40e_cloud_filter *filter, + bool add); +int i40e_add_del_cloud_filter_big_buf(struct i40e_vsi *vsi, + struct i40e_cloud_filter *filter, + bool add); #endif /* _I40E_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index a852775d3059..0dfc52772c45 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -1914,6 +1914,43 @@ enum i40e_aq_phy_type { I40E_PHY_TYPE_DEFAULT = 0xFF, }; +#define I40E_PHY_TYPES_BITMASK (BIT_ULL(I40E_PHY_TYPE_SGMII) | \ + BIT_ULL(I40E_PHY_TYPE_1000BASE_KX) | \ + BIT_ULL(I40E_PHY_TYPE_10GBASE_KX4) | \ + BIT_ULL(I40E_PHY_TYPE_10GBASE_KR) | \ + BIT_ULL(I40E_PHY_TYPE_40GBASE_KR4) | \ + BIT_ULL(I40E_PHY_TYPE_XAUI) | \ + BIT_ULL(I40E_PHY_TYPE_XFI) | \ + BIT_ULL(I40E_PHY_TYPE_SFI) | \ + BIT_ULL(I40E_PHY_TYPE_XLAUI) | \ + BIT_ULL(I40E_PHY_TYPE_XLPPI) | \ + BIT_ULL(I40E_PHY_TYPE_40GBASE_CR4_CU) | \ + BIT_ULL(I40E_PHY_TYPE_10GBASE_CR1_CU) | \ + BIT_ULL(I40E_PHY_TYPE_10GBASE_AOC) | \ + BIT_ULL(I40E_PHY_TYPE_40GBASE_AOC) | \ + BIT_ULL(I40E_PHY_TYPE_UNRECOGNIZED) | \ + BIT_ULL(I40E_PHY_TYPE_UNSUPPORTED) | \ + BIT_ULL(I40E_PHY_TYPE_100BASE_TX) | \ + BIT_ULL(I40E_PHY_TYPE_1000BASE_T) | \ + BIT_ULL(I40E_PHY_TYPE_10GBASE_T) | \ + BIT_ULL(I40E_PHY_TYPE_10GBASE_SR) | \ + BIT_ULL(I40E_PHY_TYPE_10GBASE_LR) | \ + BIT_ULL(I40E_PHY_TYPE_10GBASE_SFPP_CU) | \ + BIT_ULL(I40E_PHY_TYPE_10GBASE_CR1) | \ + BIT_ULL(I40E_PHY_TYPE_40GBASE_CR4) | \ + BIT_ULL(I40E_PHY_TYPE_40GBASE_SR4) | \ + BIT_ULL(I40E_PHY_TYPE_40GBASE_LR4) | \ + BIT_ULL(I40E_PHY_TYPE_1000BASE_SX) | \ + BIT_ULL(I40E_PHY_TYPE_1000BASE_LX) | \ + BIT_ULL(I40E_PHY_TYPE_1000BASE_T_OPTICAL) | \ + BIT_ULL(I40E_PHY_TYPE_20GBASE_KR2) | \ + BIT_ULL(I40E_PHY_TYPE_25GBASE_KR) | \ + BIT_ULL(I40E_PHY_TYPE_25GBASE_CR) | \ + BIT_ULL(I40E_PHY_TYPE_25GBASE_SR) | \ + BIT_ULL(I40E_PHY_TYPE_25GBASE_LR) | \ + BIT_ULL(I40E_PHY_TYPE_25GBASE_AOC) | \ + BIT_ULL(I40E_PHY_TYPE_25GBASE_ACC)) + #define I40E_LINK_SPEED_100MB_SHIFT 0x1 #define I40E_LINK_SPEED_1000MB_SHIFT 0x2 #define I40E_LINK_SPEED_10GB_SHIFT 0x3 diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index 4c3b4243cf65..b829fd365693 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -155,8 +155,8 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) dev_info(&pf->pdev->dev, " vlan_features = 0x%08lx\n", (unsigned long int)nd->vlan_features); } - dev_info(&pf->pdev->dev, - " vlgrp: & = %p\n", vsi->active_vlans); + dev_info(&pf->pdev->dev, " active_vlans is %s\n", + vsi->active_vlans ? "<valid>" : "<null>"); dev_info(&pf->pdev->dev, " flags = 0x%08lx, netdev_registered = %i, current_netdev_flags = 0x%04x\n", vsi->flags, vsi->netdev_registered, vsi->current_netdev_flags); @@ -270,14 +270,6 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) continue; dev_info(&pf->pdev->dev, - " rx_rings[%i]: desc = %p\n", - i, rx_ring->desc); - dev_info(&pf->pdev->dev, - " rx_rings[%i]: dev = %p, netdev = %p, rx_bi = %p\n", - i, rx_ring->dev, - rx_ring->netdev, - rx_ring->rx_bi); - dev_info(&pf->pdev->dev, " rx_rings[%i]: state = %lu, queue_index = %d, reg_idx = %d\n", i, *rx_ring->state, rx_ring->queue_index, @@ -307,17 +299,12 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) rx_ring->rx_stats.realloc_count, rx_ring->rx_stats.page_reuse_count); dev_info(&pf->pdev->dev, - " rx_rings[%i]: size = %i, dma = 0x%08lx\n", - i, rx_ring->size, - (unsigned long int)rx_ring->dma); - dev_info(&pf->pdev->dev, - " rx_rings[%i]: vsi = %p, q_vector = %p\n", - i, rx_ring->vsi, - rx_ring->q_vector); + " rx_rings[%i]: size = %i\n", + i, rx_ring->size); dev_info(&pf->pdev->dev, - " rx_rings[%i]: rx_itr_setting = %d (%s)\n", - i, rx_ring->rx_itr_setting, - ITR_IS_DYNAMIC(rx_ring->rx_itr_setting) ? "dynamic" : "fixed"); + " rx_rings[%i]: itr_setting = %d (%s)\n", + i, rx_ring->itr_setting, + ITR_IS_DYNAMIC(rx_ring->itr_setting) ? "dynamic" : "fixed"); } for (i = 0; i < vsi->num_queue_pairs; i++) { struct i40e_ring *tx_ring = READ_ONCE(vsi->tx_rings[i]); @@ -326,14 +313,6 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) continue; dev_info(&pf->pdev->dev, - " tx_rings[%i]: desc = %p\n", - i, tx_ring->desc); - dev_info(&pf->pdev->dev, - " tx_rings[%i]: dev = %p, netdev = %p, tx_bi = %p\n", - i, tx_ring->dev, - tx_ring->netdev, - tx_ring->tx_bi); - dev_info(&pf->pdev->dev, " tx_rings[%i]: state = %lu, queue_index = %d, reg_idx = %d\n", i, *tx_ring->state, tx_ring->queue_index, @@ -355,20 +334,15 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) tx_ring->tx_stats.tx_busy, tx_ring->tx_stats.tx_done_old); dev_info(&pf->pdev->dev, - " tx_rings[%i]: size = %i, dma = 0x%08lx\n", - i, tx_ring->size, - (unsigned long int)tx_ring->dma); - dev_info(&pf->pdev->dev, - " tx_rings[%i]: vsi = %p, q_vector = %p\n", - i, tx_ring->vsi, - tx_ring->q_vector); + " tx_rings[%i]: size = %i\n", + i, tx_ring->size); dev_info(&pf->pdev->dev, " tx_rings[%i]: DCB tc = %d\n", i, tx_ring->dcb_tc); dev_info(&pf->pdev->dev, - " tx_rings[%i]: tx_itr_setting = %d (%s)\n", - i, tx_ring->tx_itr_setting, - ITR_IS_DYNAMIC(tx_ring->tx_itr_setting) ? "dynamic" : "fixed"); + " tx_rings[%i]: itr_setting = %d (%s)\n", + i, tx_ring->itr_setting, + ITR_IS_DYNAMIC(tx_ring->itr_setting) ? "dynamic" : "fixed"); } rcu_read_unlock(); dev_info(&pf->pdev->dev, @@ -466,8 +440,6 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) vsi->info.resp_reserved[6], vsi->info.resp_reserved[7], vsi->info.resp_reserved[8], vsi->info.resp_reserved[9], vsi->info.resp_reserved[10], vsi->info.resp_reserved[11]); - if (vsi->back) - dev_info(&pf->pdev->dev, " PF = %p\n", vsi->back); dev_info(&pf->pdev->dev, " idx = %d\n", vsi->idx); dev_info(&pf->pdev->dev, " tc_config: numtc = %d, enabled_tc = 0x%x\n", diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 2f5bee713fef..89807e32a898 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -230,6 +230,8 @@ static const struct i40e_priv_flags i40e_gstrings_priv_flags[] = { I40E_PRIV_FLAG("flow-director-atr", I40E_FLAG_FD_ATR_ENABLED, 0), I40E_PRIV_FLAG("veb-stats", I40E_FLAG_VEB_STATS_ENABLED, 0), I40E_PRIV_FLAG("hw-atr-eviction", I40E_FLAG_HW_ATR_EVICT_ENABLED, 0), + I40E_PRIV_FLAG("link-down-on-close", + I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED, 0), I40E_PRIV_FLAG("legacy-rx", I40E_FLAG_LEGACY_RX, 0), I40E_PRIV_FLAG("disable-source-pruning", I40E_FLAG_SOURCE_PRUNING_DISABLED, 0), @@ -2244,14 +2246,14 @@ static int __i40e_get_coalesce(struct net_device *netdev, rx_ring = vsi->rx_rings[queue]; tx_ring = vsi->tx_rings[queue]; - if (ITR_IS_DYNAMIC(rx_ring->rx_itr_setting)) + if (ITR_IS_DYNAMIC(rx_ring->itr_setting)) ec->use_adaptive_rx_coalesce = 1; - if (ITR_IS_DYNAMIC(tx_ring->tx_itr_setting)) + if (ITR_IS_DYNAMIC(tx_ring->itr_setting)) ec->use_adaptive_tx_coalesce = 1; - ec->rx_coalesce_usecs = rx_ring->rx_itr_setting & ~I40E_ITR_DYNAMIC; - ec->tx_coalesce_usecs = tx_ring->tx_itr_setting & ~I40E_ITR_DYNAMIC; + ec->rx_coalesce_usecs = rx_ring->itr_setting & ~I40E_ITR_DYNAMIC; + ec->tx_coalesce_usecs = tx_ring->itr_setting & ~I40E_ITR_DYNAMIC; /* we use the _usecs_high to store/set the interrupt rate limit * that the hardware supports, that almost but not quite @@ -2311,34 +2313,35 @@ static void i40e_set_itr_per_queue(struct i40e_vsi *vsi, struct i40e_pf *pf = vsi->back; struct i40e_hw *hw = &pf->hw; struct i40e_q_vector *q_vector; - u16 vector, intrl; + u16 intrl; intrl = i40e_intrl_usec_to_reg(vsi->int_rate_limit); - rx_ring->rx_itr_setting = ec->rx_coalesce_usecs; - tx_ring->tx_itr_setting = ec->tx_coalesce_usecs; + rx_ring->itr_setting = ITR_REG_ALIGN(ec->rx_coalesce_usecs); + tx_ring->itr_setting = ITR_REG_ALIGN(ec->tx_coalesce_usecs); if (ec->use_adaptive_rx_coalesce) - rx_ring->rx_itr_setting |= I40E_ITR_DYNAMIC; + rx_ring->itr_setting |= I40E_ITR_DYNAMIC; else - rx_ring->rx_itr_setting &= ~I40E_ITR_DYNAMIC; + rx_ring->itr_setting &= ~I40E_ITR_DYNAMIC; if (ec->use_adaptive_tx_coalesce) - tx_ring->tx_itr_setting |= I40E_ITR_DYNAMIC; + tx_ring->itr_setting |= I40E_ITR_DYNAMIC; else - tx_ring->tx_itr_setting &= ~I40E_ITR_DYNAMIC; + tx_ring->itr_setting &= ~I40E_ITR_DYNAMIC; q_vector = rx_ring->q_vector; - q_vector->rx.itr = ITR_TO_REG(rx_ring->rx_itr_setting); - vector = vsi->base_vector + q_vector->v_idx; - wr32(hw, I40E_PFINT_ITRN(I40E_RX_ITR, vector - 1), q_vector->rx.itr); + q_vector->rx.target_itr = ITR_TO_REG(rx_ring->itr_setting); q_vector = tx_ring->q_vector; - q_vector->tx.itr = ITR_TO_REG(tx_ring->tx_itr_setting); - vector = vsi->base_vector + q_vector->v_idx; - wr32(hw, I40E_PFINT_ITRN(I40E_TX_ITR, vector - 1), q_vector->tx.itr); + q_vector->tx.target_itr = ITR_TO_REG(tx_ring->itr_setting); - wr32(hw, I40E_PFINT_RATEN(vector - 1), intrl); + /* The interrupt handler itself will take care of programming + * the Tx and Rx ITR values based on the values we have entered + * into the q_vector, no need to write the values now. + */ + + wr32(hw, I40E_PFINT_RATEN(q_vector->reg_idx), intrl); i40e_flush(hw); } @@ -2364,11 +2367,11 @@ static int __i40e_set_coalesce(struct net_device *netdev, vsi->work_limit = ec->tx_max_coalesced_frames_irq; if (queue < 0) { - cur_rx_itr = vsi->rx_rings[0]->rx_itr_setting; - cur_tx_itr = vsi->tx_rings[0]->tx_itr_setting; + cur_rx_itr = vsi->rx_rings[0]->itr_setting; + cur_tx_itr = vsi->tx_rings[0]->itr_setting; } else if (queue < vsi->num_queue_pairs) { - cur_rx_itr = vsi->rx_rings[queue]->rx_itr_setting; - cur_tx_itr = vsi->tx_rings[queue]->tx_itr_setting; + cur_rx_itr = vsi->rx_rings[queue]->itr_setting; + cur_tx_itr = vsi->tx_rings[queue]->itr_setting; } else { netif_info(pf, drv, netdev, "Invalid queue value, queue range is 0 - %d\n", vsi->num_queue_pairs - 1); @@ -2396,7 +2399,7 @@ static int __i40e_set_coalesce(struct net_device *netdev, return -EINVAL; } - if (ec->rx_coalesce_usecs > (I40E_MAX_ITR << 1)) { + if (ec->rx_coalesce_usecs > I40E_MAX_ITR) { netif_info(pf, drv, netdev, "Invalid value, rx-usecs range is 0-8160\n"); return -EINVAL; } @@ -2407,16 +2410,16 @@ static int __i40e_set_coalesce(struct net_device *netdev, return -EINVAL; } - if (ec->tx_coalesce_usecs > (I40E_MAX_ITR << 1)) { + if (ec->tx_coalesce_usecs > I40E_MAX_ITR) { netif_info(pf, drv, netdev, "Invalid value, tx-usecs range is 0-8160\n"); return -EINVAL; } if (ec->use_adaptive_rx_coalesce && !cur_rx_itr) - ec->rx_coalesce_usecs = I40E_MIN_ITR << 1; + ec->rx_coalesce_usecs = I40E_MIN_ITR; if (ec->use_adaptive_tx_coalesce && !cur_tx_itr) - ec->tx_coalesce_usecs = I40E_MIN_ITR << 1; + ec->tx_coalesce_usecs = I40E_MIN_ITR; intrl_reg = i40e_intrl_usec_to_reg(ec->rx_coalesce_usecs_high); vsi->int_rate_limit = INTRL_REG_TO_USEC(intrl_reg); @@ -4406,6 +4409,8 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags) } flags_complete: + changed_flags = orig_flags ^ new_flags; + /* Before we finalize any flag changes, we need to perform some * checks to ensure that the changes are supported and safe. */ @@ -4415,21 +4420,17 @@ flags_complete: !(pf->hw_features & I40E_HW_ATR_EVICT_CAPABLE)) return -EOPNOTSUPP; - /* Disable FW LLDP not supported if NPAR active or if FW - * API version < 1.7 + /* If the driver detected FW LLDP was disabled on init, this flag could + * be set, however we do not support _changing_ the flag if NPAR is + * enabled or FW API version < 1.7. There are situations where older + * FW versions/NPAR enabled PFs could disable LLDP, however we _must_ + * not allow the user to enable/disable LLDP with this flag on + * unsupported FW versions. */ - if (new_flags & I40E_FLAG_DISABLE_FW_LLDP) { - if (pf->hw.func_caps.npar_enable) { - dev_warn(&pf->pdev->dev, - "Unable to stop FW LLDP if NPAR active\n"); - return -EOPNOTSUPP; - } - - if (pf->hw.aq.api_maj_ver < 1 || - (pf->hw.aq.api_maj_ver == 1 && - pf->hw.aq.api_min_ver < 7)) { + if (changed_flags & I40E_FLAG_DISABLE_FW_LLDP) { + if (!(pf->hw_features & I40E_HW_STOPPABLE_FW_LLDP)) { dev_warn(&pf->pdev->dev, - "FW ver does not support stopping FW LLDP\n"); + "Device does not support changing FW LLDP\n"); return -EOPNOTSUPP; } } @@ -4439,6 +4440,10 @@ flags_complete: * something else has modified the flags variable since we copied it * originally. We'll just punt with an error and log something in the * message buffer. + * + * This is the point of no return for this function. We need to have + * checked any discrepancies or misconfigurations and returned + * EOPNOTSUPP before updating pf->flags here. */ if (cmpxchg64(&pf->flags, orig_flags, new_flags) != orig_flags) { dev_warn(&pf->pdev->dev, @@ -4446,8 +4451,6 @@ flags_complete: return -EAGAIN; } - changed_flags = orig_flags ^ new_flags; - /* Process any additional changes needed as a result of flag changes. * The changed_flags value reflects the list of bits that were * changed in the code above. @@ -4479,6 +4482,12 @@ flags_complete: } } + if ((changed_flags & pf->flags & + I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED) && + (pf->flags & I40E_FLAG_MFP_ENABLED)) + dev_warn(&pf->pdev->dev, + "Turning on link-down-on-close flag may affect other partitions\n"); + if (changed_flags & I40E_FLAG_DISABLE_FW_LLDP) { if (pf->flags & I40E_FLAG_DISABLE_FW_LLDP) { struct i40e_dcbx_config *dcbcfg; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index e31adbc75f9c..be9a1467a1a1 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -69,12 +69,6 @@ static int i40e_reset(struct i40e_pf *pf); static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired); static void i40e_fdir_sb_setup(struct i40e_pf *pf); static int i40e_veb_get_bw_info(struct i40e_veb *veb); -static int i40e_add_del_cloud_filter(struct i40e_vsi *vsi, - struct i40e_cloud_filter *filter, - bool add); -static int i40e_add_del_cloud_filter_big_buf(struct i40e_vsi *vsi, - struct i40e_cloud_filter *filter, - bool add); static int i40e_get_capabilities(struct i40e_pf *pf, enum i40e_admin_queue_opc list_type); @@ -215,8 +209,8 @@ static int i40e_get_lump(struct i40e_pf *pf, struct i40e_lump_tracking *pile, if (!pile || needed == 0 || id >= I40E_PILE_VALID_BIT) { dev_info(&pf->pdev->dev, - "param err: pile=%p needed=%d id=0x%04x\n", - pile, needed, id); + "param err: pile=%s needed=%d id=0x%04x\n", + pile ? "<valid>" : "<null>", needed, id); return -EINVAL; } @@ -1380,14 +1374,7 @@ struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi, ether_addr_copy(f->macaddr, macaddr); f->vlan = vlan; - /* If we're in overflow promisc mode, set the state directly - * to failed, so we don't bother to try sending the filter - * to the hardware. - */ - if (test_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state)) - f->state = I40E_FILTER_FAILED; - else - f->state = I40E_FILTER_NEW; + f->state = I40E_FILTER_NEW; INIT_HLIST_NODE(&f->hlist); key = i40e_addr_to_hkey(macaddr); @@ -2116,17 +2103,16 @@ void i40e_aqc_del_filters(struct i40e_vsi *vsi, const char *vsi_name, * @list: the list of filters to send to firmware * @add_head: Position in the add hlist * @num_add: the number of filters to add - * @promisc_change: set to true on exit if promiscuous mode was forced on * * Send a request to firmware via AdminQ to add a chunk of filters. Will set - * promisc_changed to true if the firmware has run out of space for more - * filters. + * __I40E_VSI_OVERFLOW_PROMISC bit in vsi->state if the firmware has run out of + * space for more filters. */ static void i40e_aqc_add_filters(struct i40e_vsi *vsi, const char *vsi_name, struct i40e_aqc_add_macvlan_element_data *list, struct i40e_new_mac_filter *add_head, - int num_add, bool *promisc_changed) + int num_add) { struct i40e_hw *hw = &vsi->back->hw; int aq_err, fcnt; @@ -2136,7 +2122,6 @@ void i40e_aqc_add_filters(struct i40e_vsi *vsi, const char *vsi_name, fcnt = i40e_update_filter_state(num_add, list, add_head); if (fcnt != num_add) { - *promisc_changed = true; set_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); dev_warn(&vsi->back->pdev->dev, "Error %s adding RX filters on %s, promiscuous mode forced on\n", @@ -2177,11 +2162,13 @@ i40e_aqc_broadcast_filter(struct i40e_vsi *vsi, const char *vsi_name, NULL); } - if (aq_ret) + if (aq_ret) { + set_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); dev_warn(&vsi->back->pdev->dev, - "Error %s setting broadcast promiscuous mode on %s\n", + "Error %s, forcing overflow promiscuous on %s\n", i40e_aq_str(hw, hw->aq.asq_last_status), vsi_name); + } return aq_ret; } @@ -2267,9 +2254,9 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) struct i40e_mac_filter *f; struct i40e_new_mac_filter *new, *add_head = NULL; struct i40e_hw *hw = &vsi->back->hw; + bool old_overflow, new_overflow; unsigned int failed_filters = 0; unsigned int vlan_filters = 0; - bool promisc_changed = false; char vsi_name[16] = "PF"; int filter_list_len = 0; i40e_status aq_ret = 0; @@ -2291,6 +2278,8 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) usleep_range(1000, 2000); pf = vsi->back; + old_overflow = test_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); + if (vsi->netdev) { changed_flags = vsi->current_netdev_flags ^ vsi->netdev->flags; vsi->current_netdev_flags = vsi->netdev->flags; @@ -2423,12 +2412,6 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) num_add = 0; hlist_for_each_entry_safe(new, h, &tmp_add_list, hlist) { - if (test_bit(__I40E_VSI_OVERFLOW_PROMISC, - vsi->state)) { - new->state = I40E_FILTER_FAILED; - continue; - } - /* handle broadcast filters by updating the broadcast * promiscuous flag instead of adding a MAC filter. */ @@ -2464,15 +2447,14 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) /* flush a full buffer */ if (num_add == filter_list_len) { i40e_aqc_add_filters(vsi, vsi_name, add_list, - add_head, num_add, - &promisc_changed); + add_head, num_add); memset(add_list, 0, list_size); num_add = 0; } } if (num_add) { i40e_aqc_add_filters(vsi, vsi_name, add_list, add_head, - num_add, &promisc_changed); + num_add); } /* Now move all of the filters from the temp add list back to * the VSI's list. @@ -2501,24 +2483,16 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) } spin_unlock_bh(&vsi->mac_filter_hash_lock); - /* If promiscuous mode has changed, we need to calculate a new - * threshold for when we are safe to exit - */ - if (promisc_changed) - vsi->promisc_threshold = (vsi->active_filters * 3) / 4; - /* Check if we are able to exit overflow promiscuous mode. We can * safely exit if we didn't just enter, we no longer have any failed * filters, and we have reduced filters below the threshold value. */ - if (test_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state) && - !promisc_changed && !failed_filters && - (vsi->active_filters < vsi->promisc_threshold)) { + if (old_overflow && !failed_filters && + vsi->active_filters < vsi->promisc_threshold) { dev_info(&pf->pdev->dev, "filter logjam cleared on %s, leaving overflow promiscuous mode\n", vsi_name); clear_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); - promisc_changed = true; vsi->promisc_threshold = 0; } @@ -2528,6 +2502,14 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) goto out; } + new_overflow = test_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); + + /* If we are entering overflow promiscuous, we need to calculate a new + * threshold for when we are safe to exit + */ + if (!old_overflow && new_overflow) + vsi->promisc_threshold = (vsi->active_filters * 3) / 4; + /* check for changes in promiscuous modes */ if (changed_flags & IFF_ALLMULTI) { bool cur_multipromisc; @@ -2548,12 +2530,11 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) } } - if ((changed_flags & IFF_PROMISC) || promisc_changed) { + if ((changed_flags & IFF_PROMISC) || old_overflow != new_overflow) { bool cur_promisc; cur_promisc = (!!(vsi->current_netdev_flags & IFF_PROMISC) || - test_bit(__I40E_VSI_OVERFLOW_PROMISC, - vsi->state)); + new_overflow); aq_ret = i40e_set_promiscuous(pf, cur_promisc); if (aq_ret) { retval = i40e_aq_rc_to_posix(aq_ret, @@ -3449,15 +3430,20 @@ static void i40e_vsi_configure_msix(struct i40e_vsi *vsi) for (i = 0; i < vsi->num_q_vectors; i++, vector++) { struct i40e_q_vector *q_vector = vsi->q_vectors[i]; - q_vector->itr_countdown = ITR_COUNTDOWN_START; - q_vector->rx.itr = ITR_TO_REG(vsi->rx_rings[i]->rx_itr_setting); - q_vector->rx.latency_range = I40E_LOW_LATENCY; + q_vector->rx.next_update = jiffies + 1; + q_vector->rx.target_itr = + ITR_TO_REG(vsi->rx_rings[i]->itr_setting); wr32(hw, I40E_PFINT_ITRN(I40E_RX_ITR, vector - 1), - q_vector->rx.itr); - q_vector->tx.itr = ITR_TO_REG(vsi->tx_rings[i]->tx_itr_setting); - q_vector->tx.latency_range = I40E_LOW_LATENCY; + q_vector->rx.target_itr); + q_vector->rx.current_itr = q_vector->rx.target_itr; + + q_vector->tx.next_update = jiffies + 1; + q_vector->tx.target_itr = + ITR_TO_REG(vsi->tx_rings[i]->itr_setting); wr32(hw, I40E_PFINT_ITRN(I40E_TX_ITR, vector - 1), - q_vector->tx.itr); + q_vector->tx.target_itr); + q_vector->tx.current_itr = q_vector->tx.target_itr; + wr32(hw, I40E_PFINT_RATEN(vector - 1), i40e_intrl_usec_to_reg(vsi->int_rate_limit)); @@ -3558,13 +3544,14 @@ static void i40e_configure_msi_and_legacy(struct i40e_vsi *vsi) u32 val; /* set the ITR configuration */ - q_vector->itr_countdown = ITR_COUNTDOWN_START; - q_vector->rx.itr = ITR_TO_REG(vsi->rx_rings[0]->rx_itr_setting); - q_vector->rx.latency_range = I40E_LOW_LATENCY; - wr32(hw, I40E_PFINT_ITR0(I40E_RX_ITR), q_vector->rx.itr); - q_vector->tx.itr = ITR_TO_REG(vsi->tx_rings[0]->tx_itr_setting); - q_vector->tx.latency_range = I40E_LOW_LATENCY; - wr32(hw, I40E_PFINT_ITR0(I40E_TX_ITR), q_vector->tx.itr); + q_vector->rx.next_update = jiffies + 1; + q_vector->rx.target_itr = ITR_TO_REG(vsi->rx_rings[0]->itr_setting); + wr32(hw, I40E_PFINT_ITR0(I40E_RX_ITR), q_vector->rx.target_itr); + q_vector->rx.current_itr = q_vector->rx.target_itr; + q_vector->tx.next_update = jiffies + 1; + q_vector->tx.target_itr = ITR_TO_REG(vsi->tx_rings[0]->itr_setting); + wr32(hw, I40E_PFINT_ITR0(I40E_TX_ITR), q_vector->tx.target_itr); + q_vector->tx.current_itr = q_vector->tx.target_itr; i40e_enable_misc_int_causes(pf); @@ -5375,7 +5362,7 @@ out: * @vsi: VSI to be configured * **/ -int i40e_get_link_speed(struct i40e_vsi *vsi) +static int i40e_get_link_speed(struct i40e_vsi *vsi) { struct i40e_pf *pf = vsi->back; @@ -6560,6 +6547,75 @@ int i40e_up(struct i40e_vsi *vsi) } /** + * i40e_force_link_state - Force the link status + * @pf: board private structure + * @is_up: whether the link state should be forced up or down + **/ +static i40e_status i40e_force_link_state(struct i40e_pf *pf, bool is_up) +{ + struct i40e_aq_get_phy_abilities_resp abilities; + struct i40e_aq_set_phy_config config = {0}; + struct i40e_hw *hw = &pf->hw; + i40e_status err; + u64 mask; + + /* Get the current phy config */ + err = i40e_aq_get_phy_capabilities(hw, false, false, &abilities, + NULL); + if (err) { + dev_err(&pf->pdev->dev, + "failed to get phy cap., ret = %s last_status = %s\n", + i40e_stat_str(hw, err), + i40e_aq_str(hw, hw->aq.asq_last_status)); + return err; + } + + /* If link needs to go up, but was not forced to go down, + * no need for a flap + */ + if (is_up && abilities.phy_type != 0) + return I40E_SUCCESS; + + /* To force link we need to set bits for all supported PHY types, + * but there are now more than 32, so we need to split the bitmap + * across two fields. + */ + mask = I40E_PHY_TYPES_BITMASK; + config.phy_type = is_up ? cpu_to_le32((u32)(mask & 0xffffffff)) : 0; + config.phy_type_ext = is_up ? (u8)((mask >> 32) & 0xff) : 0; + /* Copy the old settings, except of phy_type */ + config.abilities = abilities.abilities; + config.link_speed = abilities.link_speed; + config.eee_capability = abilities.eee_capability; + config.eeer = abilities.eeer_val; + config.low_power_ctrl = abilities.d3_lpan; + err = i40e_aq_set_phy_config(hw, &config, NULL); + + if (err) { + dev_err(&pf->pdev->dev, + "set phy config ret = %s last_status = %s\n", + i40e_stat_str(&pf->hw, err), + i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); + return err; + } + + /* Update the link info */ + err = i40e_update_link_info(hw); + if (err) { + /* Wait a little bit (on 40G cards it sometimes takes a really + * long time for link to come back from the atomic reset) + * and try once more + */ + msleep(1000); + i40e_update_link_info(hw); + } + + i40e_aq_set_link_restart_an(hw, true, NULL); + + return I40E_SUCCESS; +} + +/** * i40e_down - Shutdown the connection processing * @vsi: the VSI being stopped **/ @@ -6576,6 +6632,9 @@ void i40e_down(struct i40e_vsi *vsi) } i40e_vsi_disable_irq(vsi); i40e_vsi_stop_rings(vsi); + if (vsi->type == I40E_VSI_MAIN && + vsi->back->flags & I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED) + i40e_force_link_state(vsi->back, false); i40e_napi_disable_all(vsi); for (i = 0; i < vsi->num_queue_pairs; i++) { @@ -6848,8 +6907,8 @@ i40e_set_cld_element(struct i40e_cloud_filter *filter, * Add or delete a cloud filter for a specific flow spec. * Returns 0 if the filter were successfully added. **/ -static int i40e_add_del_cloud_filter(struct i40e_vsi *vsi, - struct i40e_cloud_filter *filter, bool add) +int i40e_add_del_cloud_filter(struct i40e_vsi *vsi, + struct i40e_cloud_filter *filter, bool add) { struct i40e_aqc_cloud_filters_element_data cld_filter; struct i40e_pf *pf = vsi->back; @@ -6915,9 +6974,9 @@ static int i40e_add_del_cloud_filter(struct i40e_vsi *vsi, * Add or delete a cloud filter for a specific flow spec using big buffer. * Returns 0 if the filter were successfully added. **/ -static int i40e_add_del_cloud_filter_big_buf(struct i40e_vsi *vsi, - struct i40e_cloud_filter *filter, - bool add) +int i40e_add_del_cloud_filter_big_buf(struct i40e_vsi *vsi, + struct i40e_cloud_filter *filter, + bool add) { struct i40e_aqc_cloud_filters_element_bb cld_filter; struct i40e_pf *pf = vsi->back; @@ -7537,6 +7596,9 @@ int i40e_open(struct net_device *netdev) netif_carrier_off(netdev); + if (i40e_force_link_state(pf, true)) + return -EAGAIN; + err = i40e_vsi_open(vsi); if (err) return err; @@ -9215,6 +9277,17 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) } i40e_get_oem_version(&pf->hw); + if (test_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state) && + ((hw->aq.fw_maj_ver == 4 && hw->aq.fw_min_ver <= 33) || + hw->aq.fw_maj_ver < 4) && hw->mac.type == I40E_MAC_XL710) { + /* The following delay is necessary for 4.33 firmware and older + * to recover after EMP reset. 200 ms should suffice but we + * put here 300 ms to be sure that FW is ready to operate + * after reset. + */ + mdelay(300); + } + /* re-verify the eeprom if we just had an EMP reset */ if (test_and_clear_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state)) i40e_verify_eeprom(pf); @@ -9937,18 +10010,17 @@ static int i40e_vsi_clear(struct i40e_vsi *vsi) mutex_lock(&pf->switch_mutex); if (!pf->vsi[vsi->idx]) { - dev_err(&pf->pdev->dev, "pf->vsi[%d] is NULL, just free vsi[%d](%p,type %d)\n", - vsi->idx, vsi->idx, vsi, vsi->type); + dev_err(&pf->pdev->dev, "pf->vsi[%d] is NULL, just free vsi[%d](type %d)\n", + vsi->idx, vsi->idx, vsi->type); goto unlock_vsi; } if (pf->vsi[vsi->idx] != vsi) { dev_err(&pf->pdev->dev, - "pf->vsi[%d](%p, type %d) != vsi[%d](%p,type %d): no free!\n", + "pf->vsi[%d](type %d) != vsi[%d](type %d): no free!\n", pf->vsi[vsi->idx]->idx, - pf->vsi[vsi->idx], pf->vsi[vsi->idx]->type, - vsi->idx, vsi, vsi->type); + vsi->idx, vsi->type); goto unlock_vsi; } @@ -10018,7 +10090,7 @@ static int i40e_alloc_rings(struct i40e_vsi *vsi) ring->dcb_tc = 0; if (vsi->back->hw_features & I40E_HW_WB_ON_ITR_CAPABLE) ring->flags = I40E_TXR_FLAGS_WB_ON_ITR; - ring->tx_itr_setting = pf->tx_itr_default; + ring->itr_setting = pf->tx_itr_default; vsi->tx_rings[i] = ring++; if (!i40e_enabled_xdp_vsi(vsi)) @@ -10036,7 +10108,7 @@ static int i40e_alloc_rings(struct i40e_vsi *vsi) if (vsi->back->hw_features & I40E_HW_WB_ON_ITR_CAPABLE) ring->flags = I40E_TXR_FLAGS_WB_ON_ITR; set_ring_xdp(ring); - ring->tx_itr_setting = pf->tx_itr_default; + ring->itr_setting = pf->tx_itr_default; vsi->xdp_rings[i] = ring++; setup_rx: @@ -10049,7 +10121,7 @@ setup_rx: ring->count = vsi->num_desc; ring->size = 0; ring->dcb_tc = 0; - ring->rx_itr_setting = pf->rx_itr_default; + ring->itr_setting = pf->rx_itr_default; vsi->rx_rings[i] = ring; } @@ -10328,9 +10400,6 @@ static int i40e_vsi_alloc_q_vector(struct i40e_vsi *vsi, int v_idx, int cpu) netif_napi_add(vsi->netdev, &q_vector->napi, i40e_napi_poll, NAPI_POLL_WEIGHT); - q_vector->rx.latency_range = I40E_LOW_LATENCY; - q_vector->tx.latency_range = I40E_LOW_LATENCY; - /* tie q_vector and vsi together */ vsi->q_vectors[v_idx] = q_vector; @@ -11089,6 +11158,16 @@ static int i40e_sw_init(struct i40e_pf *pf) /* IWARP needs one extra vector for CQP just like MISC.*/ pf->num_iwarp_msix = (int)num_online_cpus() + 1; } + /* Stopping the FW LLDP engine is only supported on the + * XL710 with a FW ver >= 1.7. Also, stopping FW LLDP + * engine is not supported if NPAR is functioning on this + * part + */ + if (pf->hw.mac.type == I40E_MAC_XL710 && + !pf->hw.func_caps.npar_enable && + (pf->hw.aq.api_maj_ver > 1 || + (pf->hw.aq.api_maj_ver == 1 && pf->hw.aq.api_min_ver > 6))) + pf->hw_features |= I40E_HW_STOPPABLE_FW_LLDP; #ifdef CONFIG_PCI_IOV if (pf->hw.func_caps.num_vfs && pf->hw.partition_id == 1) { diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index e554aa6cf070..97cfe944b568 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -708,16 +708,22 @@ void i40e_free_tx_resources(struct i40e_ring *tx_ring) /** * i40e_get_tx_pending - how many tx descriptors not processed * @tx_ring: the ring of descriptors + * @in_sw: use SW variables * * Since there is no access to the ring head register * in XL710, we need to use our local copies **/ -u32 i40e_get_tx_pending(struct i40e_ring *ring) +u32 i40e_get_tx_pending(struct i40e_ring *ring, bool in_sw) { u32 head, tail; - head = i40e_get_head(ring); - tail = readl(ring->tail); + if (!in_sw) { + head = i40e_get_head(ring); + tail = readl(ring->tail); + } else { + head = ring->next_to_clean; + tail = ring->next_to_use; + } if (head != tail) return (head < tail) ? @@ -774,7 +780,7 @@ void i40e_detect_recover_hung(struct i40e_vsi *vsi) */ smp_rmb(); tx_ring->tx_stats.prev_pkt_ctr = - i40e_get_tx_pending(tx_ring) ? packets : -1; + i40e_get_tx_pending(tx_ring, true) ? packets : -1; } } } @@ -898,7 +904,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, * them to be written back in case we stay in NAPI. * In this mode on X722 we do not enable Interrupt. */ - unsigned int j = i40e_get_tx_pending(tx_ring); + unsigned int j = i40e_get_tx_pending(tx_ring, false); if (budget && ((j / WB_STRIDE) == 0) && (j > 0) && @@ -995,99 +1001,241 @@ void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) } } +static inline bool i40e_container_is_rx(struct i40e_q_vector *q_vector, + struct i40e_ring_container *rc) +{ + return &q_vector->rx == rc; +} + +static inline unsigned int i40e_itr_divisor(struct i40e_q_vector *q_vector) +{ + unsigned int divisor; + + switch (q_vector->vsi->back->hw.phy.link_info.link_speed) { + case I40E_LINK_SPEED_40GB: + divisor = I40E_ITR_ADAPTIVE_MIN_INC * 1024; + break; + case I40E_LINK_SPEED_25GB: + case I40E_LINK_SPEED_20GB: + divisor = I40E_ITR_ADAPTIVE_MIN_INC * 512; + break; + default: + case I40E_LINK_SPEED_10GB: + divisor = I40E_ITR_ADAPTIVE_MIN_INC * 256; + break; + case I40E_LINK_SPEED_1GB: + case I40E_LINK_SPEED_100MB: + divisor = I40E_ITR_ADAPTIVE_MIN_INC * 32; + break; + } + + return divisor; +} + /** - * i40e_set_new_dynamic_itr - Find new ITR level + * i40e_update_itr - update the dynamic ITR value based on statistics + * @q_vector: structure containing interrupt and ring information * @rc: structure containing ring performance data * - * Returns true if ITR changed, false if not - * - * Stores a new ITR value based on packets and byte counts during - * the last interrupt. The advantage of per interrupt computation - * is faster updates and more accurate ITR for the current traffic - * pattern. Constants in this function were computed based on - * theoretical maximum wire speed and thresholds were set based on - * testing data as well as attempting to minimize response time + * Stores a new ITR value based on packets and byte + * counts during the last interrupt. The advantage of per interrupt + * computation is faster updates and more accurate ITR for the current + * traffic pattern. Constants in this function were computed + * based on theoretical maximum wire speed and thresholds were set based + * on testing data as well as attempting to minimize response time * while increasing bulk throughput. **/ -static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc) +static void i40e_update_itr(struct i40e_q_vector *q_vector, + struct i40e_ring_container *rc) { - enum i40e_latency_range new_latency_range = rc->latency_range; - u32 new_itr = rc->itr; - int bytes_per_usec; - unsigned int usecs, estimated_usecs; + unsigned int avg_wire_size, packets, bytes, itr; + unsigned long next_update = jiffies; - if (rc->total_packets == 0 || !rc->itr) - return false; + /* If we don't have any rings just leave ourselves set for maximum + * possible latency so we take ourselves out of the equation. + */ + if (!rc->ring || !ITR_IS_DYNAMIC(rc->ring->itr_setting)) + return; + + /* For Rx we want to push the delay up and default to low latency. + * for Tx we want to pull the delay down and default to high latency. + */ + itr = i40e_container_is_rx(q_vector, rc) ? + I40E_ITR_ADAPTIVE_MIN_USECS | I40E_ITR_ADAPTIVE_LATENCY : + I40E_ITR_ADAPTIVE_MAX_USECS | I40E_ITR_ADAPTIVE_LATENCY; + + /* If we didn't update within up to 1 - 2 jiffies we can assume + * that either packets are coming in so slow there hasn't been + * any work, or that there is so much work that NAPI is dealing + * with interrupt moderation and we don't need to do anything. + */ + if (time_after(next_update, rc->next_update)) + goto clear_counts; + + /* If itr_countdown is set it means we programmed an ITR within + * the last 4 interrupt cycles. This has a side effect of us + * potentially firing an early interrupt. In order to work around + * this we need to throw out any data received for a few + * interrupts following the update. + */ + if (q_vector->itr_countdown) { + itr = rc->target_itr; + goto clear_counts; + } + + packets = rc->total_packets; + bytes = rc->total_bytes; - usecs = (rc->itr << 1) * ITR_COUNTDOWN_START; - bytes_per_usec = rc->total_bytes / usecs; + if (i40e_container_is_rx(q_vector, rc)) { + /* If Rx there are 1 to 4 packets and bytes are less than + * 9000 assume insufficient data to use bulk rate limiting + * approach unless Tx is already in bulk rate limiting. We + * are likely latency driven. + */ + if (packets && packets < 4 && bytes < 9000 && + (q_vector->tx.target_itr & I40E_ITR_ADAPTIVE_LATENCY)) { + itr = I40E_ITR_ADAPTIVE_LATENCY; + goto adjust_by_size; + } + } else if (packets < 4) { + /* If we have Tx and Rx ITR maxed and Tx ITR is running in + * bulk mode and we are receiving 4 or fewer packets just + * reset the ITR_ADAPTIVE_LATENCY bit for latency mode so + * that the Rx can relax. + */ + if (rc->target_itr == I40E_ITR_ADAPTIVE_MAX_USECS && + (q_vector->rx.target_itr & I40E_ITR_MASK) == + I40E_ITR_ADAPTIVE_MAX_USECS) + goto clear_counts; + } else if (packets > 32) { + /* If we have processed over 32 packets in a single interrupt + * for Tx assume we need to switch over to "bulk" mode. + */ + rc->target_itr &= ~I40E_ITR_ADAPTIVE_LATENCY; + } - /* The calculations in this algorithm depend on interrupts actually - * firing at the ITR rate. This may not happen if the packet rate is - * really low, or if we've been napi polling. Check to make sure - * that's not the case before we continue. + /* We have no packets to actually measure against. This means + * either one of the other queues on this vector is active or + * we are a Tx queue doing TSO with too high of an interrupt rate. + * + * Between 4 and 56 we can assume that our current interrupt delay + * is only slightly too low. As such we should increase it by a small + * fixed amount. */ - estimated_usecs = jiffies_to_usecs(jiffies - rc->last_itr_update); - if (estimated_usecs > usecs) { - new_latency_range = I40E_LOW_LATENCY; - goto reset_latency; + if (packets < 56) { + itr = rc->target_itr + I40E_ITR_ADAPTIVE_MIN_INC; + if ((itr & I40E_ITR_MASK) > I40E_ITR_ADAPTIVE_MAX_USECS) { + itr &= I40E_ITR_ADAPTIVE_LATENCY; + itr += I40E_ITR_ADAPTIVE_MAX_USECS; + } + goto clear_counts; + } + + if (packets <= 256) { + itr = min(q_vector->tx.current_itr, q_vector->rx.current_itr); + itr &= I40E_ITR_MASK; + + /* Between 56 and 112 is our "goldilocks" zone where we are + * working out "just right". Just report that our current + * ITR is good for us. + */ + if (packets <= 112) + goto clear_counts; + + /* If packet count is 128 or greater we are likely looking + * at a slight overrun of the delay we want. Try halving + * our delay to see if that will cut the number of packets + * in half per interrupt. + */ + itr /= 2; + itr &= I40E_ITR_MASK; + if (itr < I40E_ITR_ADAPTIVE_MIN_USECS) + itr = I40E_ITR_ADAPTIVE_MIN_USECS; + + goto clear_counts; } - /* simple throttlerate management - * 0-10MB/s lowest (50000 ints/s) - * 10-20MB/s low (20000 ints/s) - * 20-1249MB/s bulk (18000 ints/s) + /* The paths below assume we are dealing with a bulk ITR since + * number of packets is greater than 256. We are just going to have + * to compute a value and try to bring the count under control, + * though for smaller packet sizes there isn't much we can do as + * NAPI polling will likely be kicking in sooner rather than later. + */ + itr = I40E_ITR_ADAPTIVE_BULK; + +adjust_by_size: + /* If packet counts are 256 or greater we can assume we have a gross + * overestimation of what the rate should be. Instead of trying to fine + * tune it just use the formula below to try and dial in an exact value + * give the current packet size of the frame. + */ + avg_wire_size = bytes / packets; + + /* The following is a crude approximation of: + * wmem_default / (size + overhead) = desired_pkts_per_int + * rate / bits_per_byte / (size + ethernet overhead) = pkt_rate + * (desired_pkt_rate / pkt_rate) * usecs_per_sec = ITR value + * + * Assuming wmem_default is 212992 and overhead is 640 bytes per + * packet, (256 skb, 64 headroom, 320 shared info), we can reduce the + * formula down to * - * The math works out because the divisor is in 10^(-6) which - * turns the bytes/us input value into MB/s values, but - * make sure to use usecs, as the register values written - * are in 2 usec increments in the ITR registers, and make sure - * to use the smoothed values that the countdown timer gives us. + * (170 * (size + 24)) / (size + 640) = ITR + * + * We first do some math on the packet size and then finally bitshift + * by 8 after rounding up. We also have to account for PCIe link speed + * difference as ITR scales based on this. */ - switch (new_latency_range) { - case I40E_LOWEST_LATENCY: - if (bytes_per_usec > 10) - new_latency_range = I40E_LOW_LATENCY; - break; - case I40E_LOW_LATENCY: - if (bytes_per_usec > 20) - new_latency_range = I40E_BULK_LATENCY; - else if (bytes_per_usec <= 10) - new_latency_range = I40E_LOWEST_LATENCY; - break; - case I40E_BULK_LATENCY: - default: - if (bytes_per_usec <= 20) - new_latency_range = I40E_LOW_LATENCY; - break; + if (avg_wire_size <= 60) { + /* Start at 250k ints/sec */ + avg_wire_size = 4096; + } else if (avg_wire_size <= 380) { + /* 250K ints/sec to 60K ints/sec */ + avg_wire_size *= 40; + avg_wire_size += 1696; + } else if (avg_wire_size <= 1084) { + /* 60K ints/sec to 36K ints/sec */ + avg_wire_size *= 15; + avg_wire_size += 11452; + } else if (avg_wire_size <= 1980) { + /* 36K ints/sec to 30K ints/sec */ + avg_wire_size *= 5; + avg_wire_size += 22420; + } else { + /* plateau at a limit of 30K ints/sec */ + avg_wire_size = 32256; } -reset_latency: - rc->latency_range = new_latency_range; + /* If we are in low latency mode halve our delay which doubles the + * rate to somewhere between 100K to 16K ints/sec + */ + if (itr & I40E_ITR_ADAPTIVE_LATENCY) + avg_wire_size /= 2; - switch (new_latency_range) { - case I40E_LOWEST_LATENCY: - new_itr = I40E_ITR_50K; - break; - case I40E_LOW_LATENCY: - new_itr = I40E_ITR_20K; - break; - case I40E_BULK_LATENCY: - new_itr = I40E_ITR_18K; - break; - default: - break; + /* Resultant value is 256 times larger than it needs to be. This + * gives us room to adjust the value as needed to either increase + * or decrease the value based on link speeds of 10G, 2.5G, 1G, etc. + * + * Use addition as we have already recorded the new latency flag + * for the ITR value. + */ + itr += DIV_ROUND_UP(avg_wire_size, i40e_itr_divisor(q_vector)) * + I40E_ITR_ADAPTIVE_MIN_INC; + + if ((itr & I40E_ITR_MASK) > I40E_ITR_ADAPTIVE_MAX_USECS) { + itr &= I40E_ITR_ADAPTIVE_LATENCY; + itr += I40E_ITR_ADAPTIVE_MAX_USECS; } +clear_counts: + /* write back value */ + rc->target_itr = itr; + + /* next update should occur within next jiffy */ + rc->next_update = next_update + 1; + rc->total_bytes = 0; rc->total_packets = 0; - rc->last_itr_update = jiffies; - - if (new_itr != rc->itr) { - rc->itr = new_itr; - return true; - } - return false; } /** @@ -1991,7 +2139,7 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring, * @rx_buffer: rx buffer to pull data from * * This function will clean up the contents of the rx_buffer. It will - * either recycle the bufer or unmap it and free the associated resources. + * either recycle the buffer or unmap it and free the associated resources. */ static void i40e_put_rx_buffer(struct i40e_ring *rx_ring, struct i40e_rx_buffer *rx_buffer) @@ -2274,29 +2422,45 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) return failure ? budget : (int)total_rx_packets; } -static u32 i40e_buildreg_itr(const int type, const u16 itr) +static inline u32 i40e_buildreg_itr(const int type, u16 itr) { u32 val; + /* We don't bother with setting the CLEARPBA bit as the data sheet + * points out doing so is "meaningless since it was already + * auto-cleared". The auto-clearing happens when the interrupt is + * asserted. + * + * Hardware errata 28 for also indicates that writing to a + * xxINT_DYN_CTLx CSR with INTENA_MSK (bit 31) set to 0 will clear + * an event in the PBA anyway so we need to rely on the automask + * to hold pending events for us until the interrupt is re-enabled + * + * The itr value is reported in microseconds, and the register + * value is recorded in 2 microsecond units. For this reason we + * only need to shift by the interval shift - 1 instead of the + * full value. + */ + itr &= I40E_ITR_MASK; + val = I40E_PFINT_DYN_CTLN_INTENA_MASK | - I40E_PFINT_DYN_CTLN_CLEARPBA_MASK | (type << I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT) | - (itr << I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT); + (itr << (I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT - 1)); return val; } /* a small macro to shorten up some long lines */ #define INTREG I40E_PFINT_DYN_CTLN -static inline int get_rx_itr(struct i40e_vsi *vsi, int idx) -{ - return vsi->rx_rings[idx]->rx_itr_setting; -} -static inline int get_tx_itr(struct i40e_vsi *vsi, int idx) -{ - return vsi->tx_rings[idx]->tx_itr_setting; -} +/* The act of updating the ITR will cause it to immediately trigger. In order + * to prevent this from throwing off adaptive update statistics we defer the + * update so that it can only happen so often. So after either Tx or Rx are + * updated we make the adaptive scheme wait until either the ITR completely + * expires via the next_update expiration or we have been through at least + * 3 interrupts. + */ +#define ITR_COUNTDOWN_START 3 /** * i40e_update_enable_itr - Update itr and re-enable MSIX interrupt @@ -2308,10 +2472,7 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) { struct i40e_hw *hw = &vsi->back->hw; - bool rx = false, tx = false; - u32 rxval, txval; - int idx = q_vector->v_idx; - int rx_itr_setting, tx_itr_setting; + u32 intval; /* If we don't have MSIX, then we only need to re-enable icr0 */ if (!(vsi->back->flags & I40E_FLAG_MSIX_ENABLED)) { @@ -2319,65 +2480,49 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, return; } - /* avoid dynamic calculation if in countdown mode OR if - * all dynamic is disabled - */ - rxval = txval = i40e_buildreg_itr(I40E_ITR_NONE, 0); - - rx_itr_setting = get_rx_itr(vsi, idx); - tx_itr_setting = get_tx_itr(vsi, idx); - - if (q_vector->itr_countdown > 0 || - (!ITR_IS_DYNAMIC(rx_itr_setting) && - !ITR_IS_DYNAMIC(tx_itr_setting))) { - goto enable_int; - } - - if (ITR_IS_DYNAMIC(rx_itr_setting)) { - rx = i40e_set_new_dynamic_itr(&q_vector->rx); - rxval = i40e_buildreg_itr(I40E_RX_ITR, q_vector->rx.itr); - } - - if (ITR_IS_DYNAMIC(tx_itr_setting)) { - tx = i40e_set_new_dynamic_itr(&q_vector->tx); - txval = i40e_buildreg_itr(I40E_TX_ITR, q_vector->tx.itr); - } + /* These will do nothing if dynamic updates are not enabled */ + i40e_update_itr(q_vector, &q_vector->tx); + i40e_update_itr(q_vector, &q_vector->rx); - if (rx || tx) { - /* get the higher of the two ITR adjustments and - * use the same value for both ITR registers - * when in adaptive mode (Rx and/or Tx) - */ - u16 itr = max(q_vector->tx.itr, q_vector->rx.itr); - - q_vector->tx.itr = q_vector->rx.itr = itr; - txval = i40e_buildreg_itr(I40E_TX_ITR, itr); - tx = true; - rxval = i40e_buildreg_itr(I40E_RX_ITR, itr); - rx = true; - } - - /* only need to enable the interrupt once, but need - * to possibly update both ITR values + /* This block of logic allows us to get away with only updating + * one ITR value with each interrupt. The idea is to perform a + * pseudo-lazy update with the following criteria. + * + * 1. Rx is given higher priority than Tx if both are in same state + * 2. If we must reduce an ITR that is given highest priority. + * 3. We then give priority to increasing ITR based on amount. */ - if (rx) { - /* set the INTENA_MSK_MASK so that this first write - * won't actually enable the interrupt, instead just - * updating the ITR (it's bit 31 PF and VF) + if (q_vector->rx.target_itr < q_vector->rx.current_itr) { + /* Rx ITR needs to be reduced, this is highest priority */ + intval = i40e_buildreg_itr(I40E_RX_ITR, + q_vector->rx.target_itr); + q_vector->rx.current_itr = q_vector->rx.target_itr; + q_vector->itr_countdown = ITR_COUNTDOWN_START; + } else if ((q_vector->tx.target_itr < q_vector->tx.current_itr) || + ((q_vector->rx.target_itr - q_vector->rx.current_itr) < + (q_vector->tx.target_itr - q_vector->tx.current_itr))) { + /* Tx ITR needs to be reduced, this is second priority + * Tx ITR needs to be increased more than Rx, fourth priority */ - rxval |= BIT(31); - /* don't check _DOWN because interrupt isn't being enabled */ - wr32(hw, INTREG(q_vector->reg_idx), rxval); + intval = i40e_buildreg_itr(I40E_TX_ITR, + q_vector->tx.target_itr); + q_vector->tx.current_itr = q_vector->tx.target_itr; + q_vector->itr_countdown = ITR_COUNTDOWN_START; + } else if (q_vector->rx.current_itr != q_vector->rx.target_itr) { + /* Rx ITR needs to be increased, third priority */ + intval = i40e_buildreg_itr(I40E_RX_ITR, + q_vector->rx.target_itr); + q_vector->rx.current_itr = q_vector->rx.target_itr; + q_vector->itr_countdown = ITR_COUNTDOWN_START; + } else { + /* No ITR update, lowest priority */ + intval = i40e_buildreg_itr(I40E_ITR_NONE, 0); + if (q_vector->itr_countdown) + q_vector->itr_countdown--; } -enable_int: if (!test_bit(__I40E_VSI_DOWN, vsi->state)) - wr32(hw, INTREG(q_vector->reg_idx), txval); - - if (q_vector->itr_countdown) - q_vector->itr_countdown--; - else - q_vector->itr_countdown = ITR_COUNTDOWN_START; + wr32(hw, INTREG(q_vector->reg_idx), intval); } /** diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index 701b708628b0..3c80ea784389 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -30,32 +30,37 @@ #include <net/xdp.h> /* Interrupt Throttling and Rate Limiting Goodies */ - -#define I40E_MAX_ITR 0x0FF0 /* reg uses 2 usec resolution */ -#define I40E_MIN_ITR 0x0001 /* reg uses 2 usec resolution */ -#define I40E_ITR_100K 0x0005 -#define I40E_ITR_50K 0x000A -#define I40E_ITR_20K 0x0019 -#define I40E_ITR_18K 0x001B -#define I40E_ITR_8K 0x003E -#define I40E_ITR_4K 0x007A -#define I40E_MAX_INTRL 0x3B /* reg uses 4 usec resolution */ -#define I40E_ITR_RX_DEF (ITR_REG_TO_USEC(I40E_ITR_20K) | \ - I40E_ITR_DYNAMIC) -#define I40E_ITR_TX_DEF (ITR_REG_TO_USEC(I40E_ITR_20K) | \ - I40E_ITR_DYNAMIC) -#define I40E_ITR_DYNAMIC 0x8000 /* use top bit as a flag */ -#define I40E_MIN_INT_RATE 250 /* ~= 1000000 / (I40E_MAX_ITR * 2) */ -#define I40E_MAX_INT_RATE 500000 /* == 1000000 / (I40E_MIN_ITR * 2) */ #define I40E_DEFAULT_IRQ_WORK 256 -#define ITR_TO_REG(setting) ((setting & ~I40E_ITR_DYNAMIC) >> 1) -#define ITR_IS_DYNAMIC(setting) (!!(setting & I40E_ITR_DYNAMIC)) -#define ITR_REG_TO_USEC(itr_reg) (itr_reg << 1) + +/* The datasheet for the X710 and XL710 indicate that the maximum value for + * the ITR is 8160usec which is then called out as 0xFF0 with a 2usec + * resolution. 8160 is 0x1FE0 when written out in hex. So instead of storing + * the register value which is divided by 2 lets use the actual values and + * avoid an excessive amount of translation. + */ +#define I40E_ITR_DYNAMIC 0x8000 /* use top bit as a flag */ +#define I40E_ITR_MASK 0x1FFE /* mask for ITR register value */ +#define I40E_MIN_ITR 2 /* reg uses 2 usec resolution */ +#define I40E_ITR_100K 10 /* all values below must be even */ +#define I40E_ITR_50K 20 +#define I40E_ITR_20K 50 +#define I40E_ITR_18K 60 +#define I40E_ITR_8K 122 +#define I40E_MAX_ITR 8160 /* maximum value as per datasheet */ +#define ITR_TO_REG(setting) ((setting) & ~I40E_ITR_DYNAMIC) +#define ITR_REG_ALIGN(setting) __ALIGN_MASK(setting, ~I40E_ITR_MASK) +#define ITR_IS_DYNAMIC(setting) (!!((setting) & I40E_ITR_DYNAMIC)) + +#define I40E_ITR_RX_DEF (I40E_ITR_20K | I40E_ITR_DYNAMIC) +#define I40E_ITR_TX_DEF (I40E_ITR_20K | I40E_ITR_DYNAMIC) + /* 0x40 is the enable bit for interrupt rate limiting, and must be set if * the value of the rate limit is non-zero */ #define INTRL_ENA BIT(6) +#define I40E_MAX_INTRL 0x3B /* reg uses 4 usec resolution */ #define INTRL_REG_TO_USEC(intrl) ((intrl & ~INTRL_ENA) << 2) + /** * i40e_intrl_usec_to_reg - convert interrupt rate limit to register * @intrl: interrupt rate limit to convert @@ -382,8 +387,7 @@ struct i40e_ring { * these values always store the USER setting, and must be converted * before programming to a register. */ - u16 rx_itr_setting; - u16 tx_itr_setting; + u16 itr_setting; u16 count; /* Number of descriptors */ u16 reg_idx; /* HW register index of the ring */ @@ -459,21 +463,21 @@ static inline void set_ring_xdp(struct i40e_ring *ring) ring->flags |= I40E_TXR_FLAGS_XDP; } -enum i40e_latency_range { - I40E_LOWEST_LATENCY = 0, - I40E_LOW_LATENCY = 1, - I40E_BULK_LATENCY = 2, -}; +#define I40E_ITR_ADAPTIVE_MIN_INC 0x0002 +#define I40E_ITR_ADAPTIVE_MIN_USECS 0x0002 +#define I40E_ITR_ADAPTIVE_MAX_USECS 0x007e +#define I40E_ITR_ADAPTIVE_LATENCY 0x8000 +#define I40E_ITR_ADAPTIVE_BULK 0x0000 +#define ITR_IS_BULK(x) (!((x) & I40E_ITR_ADAPTIVE_LATENCY)) struct i40e_ring_container { - /* array of pointers to rings */ - struct i40e_ring *ring; + struct i40e_ring *ring; /* pointer to linked list of ring(s) */ + unsigned long next_update; /* jiffies value of next update */ unsigned int total_bytes; /* total bytes processed this int */ unsigned int total_packets; /* total packets processed this int */ - unsigned long last_itr_update; /* jiffies of last ITR update */ u16 count; - enum i40e_latency_range latency_range; - u16 itr; + u16 target_itr; /* target ITR setting for ring(s) */ + u16 current_itr; /* current ITR setting for ring(s) */ }; /* iterator for handling rings in ring container */ @@ -501,7 +505,7 @@ void i40e_free_tx_resources(struct i40e_ring *tx_ring); void i40e_free_rx_resources(struct i40e_ring *rx_ring); int i40e_napi_poll(struct napi_struct *napi, int budget); void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector); -u32 i40e_get_tx_pending(struct i40e_ring *ring); +u32 i40e_get_tx_pending(struct i40e_ring *ring, bool in_sw); void i40e_detect_recover_hung(struct i40e_vsi *vsi); int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size); bool __i40e_chk_linearize(struct sk_buff *skb); diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h index cd294e6a8587..b0eed8c0b2f2 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_type.h +++ b/drivers/net/ethernet/intel/i40e/i40e_type.h @@ -39,7 +39,7 @@ #define I40E_MASK(mask, shift) ((u32)(mask) << (shift)) #define I40E_MAX_VSI_QP 16 -#define I40E_MAX_VF_VSI 3 +#define I40E_MAX_VF_VSI 4 #define I40E_MAX_CHAINED_RX_BUFFERS 5 #define I40E_MAX_PF_UDP_OFFLOAD_PORTS 16 diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index e9309fb9084b..e23975c67417 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -258,6 +258,38 @@ static u16 i40e_vc_get_pf_queue_id(struct i40e_vf *vf, u16 vsi_id, } /** + * i40e_get_real_pf_qid + * @vf: pointer to the VF info + * @vsi_id: vsi id + * @queue_id: queue number + * + * wrapper function to get pf_queue_id handling ADq code as well + **/ +static u16 i40e_get_real_pf_qid(struct i40e_vf *vf, u16 vsi_id, u16 queue_id) +{ + int i; + + if (vf->adq_enabled) { + /* Although VF considers all the queues(can be 1 to 16) as its + * own but they may actually belong to different VSIs(up to 4). + * We need to find which queues belongs to which VSI. + */ + for (i = 0; i < vf->num_tc; i++) { + if (queue_id < vf->ch[i].num_qps) { + vsi_id = vf->ch[i].vsi_id; + break; + } + /* find right queue id which is relative to a + * given VSI. + */ + queue_id -= vf->ch[i].num_qps; + } + } + + return i40e_vc_get_pf_queue_id(vf, vsi_id, queue_id); +} + +/** * i40e_config_irq_link_list * @vf: pointer to the VF info * @vsi_id: id of VSI as given by the FW @@ -310,7 +342,7 @@ static void i40e_config_irq_link_list(struct i40e_vf *vf, u16 vsi_id, vsi_queue_id = next_q / I40E_VIRTCHNL_SUPPORTED_QTYPES; qtype = next_q % I40E_VIRTCHNL_SUPPORTED_QTYPES; - pf_queue_id = i40e_vc_get_pf_queue_id(vf, vsi_id, vsi_queue_id); + pf_queue_id = i40e_get_real_pf_qid(vf, vsi_id, vsi_queue_id); reg = ((qtype << I40E_VPINT_LNKLSTN_FIRSTQ_TYPE_SHIFT) | pf_queue_id); wr32(hw, reg_idx, reg); @@ -333,8 +365,9 @@ static void i40e_config_irq_link_list(struct i40e_vf *vf, u16 vsi_id, if (next_q < size) { vsi_queue_id = next_q / I40E_VIRTCHNL_SUPPORTED_QTYPES; qtype = next_q % I40E_VIRTCHNL_SUPPORTED_QTYPES; - pf_queue_id = i40e_vc_get_pf_queue_id(vf, vsi_id, - vsi_queue_id); + pf_queue_id = i40e_get_real_pf_qid(vf, + vsi_id, + vsi_queue_id); } else { pf_queue_id = I40E_QUEUE_END_OF_LIST; qtype = 0; @@ -669,18 +702,20 @@ error_param: /** * i40e_alloc_vsi_res * @vf: pointer to the VF info - * @type: type of VSI to allocate + * @idx: VSI index, applies only for ADq mode, zero otherwise * * alloc VF vsi context & resources **/ -static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type) +static int i40e_alloc_vsi_res(struct i40e_vf *vf, u8 idx) { struct i40e_mac_filter *f = NULL; struct i40e_pf *pf = vf->pf; struct i40e_vsi *vsi; + u64 max_tx_rate = 0; int ret = 0; - vsi = i40e_vsi_setup(pf, type, pf->vsi[pf->lan_vsi]->seid, vf->vf_id); + vsi = i40e_vsi_setup(pf, I40E_VSI_SRIOV, pf->vsi[pf->lan_vsi]->seid, + vf->vf_id); if (!vsi) { dev_err(&pf->pdev->dev, @@ -689,7 +724,8 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type) ret = -ENOENT; goto error_alloc_vsi_res; } - if (type == I40E_VSI_SRIOV) { + + if (!idx) { u64 hena = i40e_pf_get_default_rss_hena(pf); u8 broadcast[ETH_ALEN]; @@ -721,17 +757,29 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type) spin_unlock_bh(&vsi->mac_filter_hash_lock); wr32(&pf->hw, I40E_VFQF_HENA1(0, vf->vf_id), (u32)hena); wr32(&pf->hw, I40E_VFQF_HENA1(1, vf->vf_id), (u32)(hena >> 32)); + /* program mac filter only for VF VSI */ + ret = i40e_sync_vsi_filters(vsi); + if (ret) + dev_err(&pf->pdev->dev, "Unable to program ucast filters\n"); } - /* program mac filter */ - ret = i40e_sync_vsi_filters(vsi); - if (ret) - dev_err(&pf->pdev->dev, "Unable to program ucast filters\n"); + /* storing VSI index and id for ADq and don't apply the mac filter */ + if (vf->adq_enabled) { + vf->ch[idx].vsi_idx = vsi->idx; + vf->ch[idx].vsi_id = vsi->id; + } /* Set VF bandwidth if specified */ if (vf->tx_rate) { + max_tx_rate = vf->tx_rate; + } else if (vf->ch[idx].max_tx_rate) { + max_tx_rate = vf->ch[idx].max_tx_rate; + } + + if (max_tx_rate) { + max_tx_rate = div_u64(max_tx_rate, I40E_BW_CREDIT_DIVISOR); ret = i40e_aq_config_vsi_bw_limit(&pf->hw, vsi->seid, - vf->tx_rate / 50, 0, NULL); + max_tx_rate, 0, NULL); if (ret) dev_err(&pf->pdev->dev, "Unable to set tx rate, VF %d, error code %d.\n", vf->vf_id, ret); @@ -742,6 +790,92 @@ error_alloc_vsi_res: } /** + * i40e_map_pf_queues_to_vsi + * @vf: pointer to the VF info + * + * PF maps LQPs to a VF by programming VSILAN_QTABLE & VPLAN_QTABLE. This + * function takes care of first part VSILAN_QTABLE, mapping pf queues to VSI. + **/ +static void i40e_map_pf_queues_to_vsi(struct i40e_vf *vf) +{ + struct i40e_pf *pf = vf->pf; + struct i40e_hw *hw = &pf->hw; + u32 reg, num_tc = 1; /* VF has at least one traffic class */ + u16 vsi_id, qps; + int i, j; + + if (vf->adq_enabled) + num_tc = vf->num_tc; + + for (i = 0; i < num_tc; i++) { + if (vf->adq_enabled) { + qps = vf->ch[i].num_qps; + vsi_id = vf->ch[i].vsi_id; + } else { + qps = pf->vsi[vf->lan_vsi_idx]->alloc_queue_pairs; + vsi_id = vf->lan_vsi_id; + } + + for (j = 0; j < 7; j++) { + if (j * 2 >= qps) { + /* end of list */ + reg = 0x07FF07FF; + } else { + u16 qid = i40e_vc_get_pf_queue_id(vf, + vsi_id, + j * 2); + reg = qid; + qid = i40e_vc_get_pf_queue_id(vf, vsi_id, + (j * 2) + 1); + reg |= qid << 16; + } + i40e_write_rx_ctl(hw, + I40E_VSILAN_QTABLE(j, vsi_id), + reg); + } + } +} + +/** + * i40e_map_pf_to_vf_queues + * @vf: pointer to the VF info + * + * PF maps LQPs to a VF by programming VSILAN_QTABLE & VPLAN_QTABLE. This + * function takes care of the second part VPLAN_QTABLE & completes VF mappings. + **/ +static void i40e_map_pf_to_vf_queues(struct i40e_vf *vf) +{ + struct i40e_pf *pf = vf->pf; + struct i40e_hw *hw = &pf->hw; + u32 reg, total_qps = 0; + u32 qps, num_tc = 1; /* VF has at least one traffic class */ + u16 vsi_id, qid; + int i, j; + + if (vf->adq_enabled) + num_tc = vf->num_tc; + + for (i = 0; i < num_tc; i++) { + if (vf->adq_enabled) { + qps = vf->ch[i].num_qps; + vsi_id = vf->ch[i].vsi_id; + } else { + qps = pf->vsi[vf->lan_vsi_idx]->alloc_queue_pairs; + vsi_id = vf->lan_vsi_id; + } + + for (j = 0; j < qps; j++) { + qid = i40e_vc_get_pf_queue_id(vf, vsi_id, j); + + reg = (qid & I40E_VPLAN_QTABLE_QINDEX_MASK); + wr32(hw, I40E_VPLAN_QTABLE(total_qps, vf->vf_id), + reg); + total_qps++; + } + } +} + +/** * i40e_enable_vf_mappings * @vf: pointer to the VF info * @@ -751,8 +885,7 @@ static void i40e_enable_vf_mappings(struct i40e_vf *vf) { struct i40e_pf *pf = vf->pf; struct i40e_hw *hw = &pf->hw; - u32 reg, total_queue_pairs = 0; - int j; + u32 reg; /* Tell the hardware we're using noncontiguous mapping. HW requires * that VF queues be mapped using this method, even when they are @@ -765,30 +898,8 @@ static void i40e_enable_vf_mappings(struct i40e_vf *vf) reg = I40E_VPLAN_MAPENA_TXRX_ENA_MASK; wr32(hw, I40E_VPLAN_MAPENA(vf->vf_id), reg); - /* map PF queues to VF queues */ - for (j = 0; j < pf->vsi[vf->lan_vsi_idx]->alloc_queue_pairs; j++) { - u16 qid = i40e_vc_get_pf_queue_id(vf, vf->lan_vsi_id, j); - - reg = (qid & I40E_VPLAN_QTABLE_QINDEX_MASK); - wr32(hw, I40E_VPLAN_QTABLE(total_queue_pairs, vf->vf_id), reg); - total_queue_pairs++; - } - - /* map PF queues to VSI */ - for (j = 0; j < 7; j++) { - if (j * 2 >= pf->vsi[vf->lan_vsi_idx]->alloc_queue_pairs) { - reg = 0x07FF07FF; /* unused */ - } else { - u16 qid = i40e_vc_get_pf_queue_id(vf, vf->lan_vsi_id, - j * 2); - reg = qid; - qid = i40e_vc_get_pf_queue_id(vf, vf->lan_vsi_id, - (j * 2) + 1); - reg |= qid << 16; - } - i40e_write_rx_ctl(hw, I40E_VSILAN_QTABLE(j, vf->lan_vsi_id), - reg); - } + i40e_map_pf_to_vf_queues(vf); + i40e_map_pf_queues_to_vsi(vf); i40e_flush(hw); } @@ -824,7 +935,7 @@ static void i40e_free_vf_res(struct i40e_vf *vf) struct i40e_pf *pf = vf->pf; struct i40e_hw *hw = &pf->hw; u32 reg_idx, reg; - int i, msix_vf; + int i, j, msix_vf; /* Start by disabling VF's configuration API to prevent the OS from * accessing the VF's VSI after it's freed / invalidated. @@ -846,6 +957,20 @@ static void i40e_free_vf_res(struct i40e_vf *vf) vf->lan_vsi_id = 0; vf->num_mac = 0; } + + /* do the accounting and remove additional ADq VSI's */ + if (vf->adq_enabled && vf->ch[0].vsi_idx) { + for (j = 0; j < vf->num_tc; j++) { + /* At this point VSI0 is already released so don't + * release it again and only clear their values in + * structure variables + */ + if (j) + i40e_vsi_release(pf->vsi[vf->ch[j].vsi_idx]); + vf->ch[j].vsi_idx = 0; + vf->ch[j].vsi_id = 0; + } + } msix_vf = pf->hw.func_caps.num_msix_vectors_vf; /* disable interrupts so the VF starts in a known state */ @@ -891,7 +1016,7 @@ static int i40e_alloc_vf_res(struct i40e_vf *vf) { struct i40e_pf *pf = vf->pf; int total_queue_pairs = 0; - int ret; + int ret, idx; if (vf->num_req_queues && vf->num_req_queues <= pf->queues_left + I40E_DEFAULT_QUEUES_PER_VF) @@ -900,11 +1025,30 @@ static int i40e_alloc_vf_res(struct i40e_vf *vf) pf->num_vf_qps = I40E_DEFAULT_QUEUES_PER_VF; /* allocate hw vsi context & associated resources */ - ret = i40e_alloc_vsi_res(vf, I40E_VSI_SRIOV); + ret = i40e_alloc_vsi_res(vf, 0); if (ret) goto error_alloc; total_queue_pairs += pf->vsi[vf->lan_vsi_idx]->alloc_queue_pairs; + /* allocate additional VSIs based on tc information for ADq */ + if (vf->adq_enabled) { + if (pf->queues_left >= + (I40E_MAX_VF_QUEUES - I40E_DEFAULT_QUEUES_PER_VF)) { + /* TC 0 always belongs to VF VSI */ + for (idx = 1; idx < vf->num_tc; idx++) { + ret = i40e_alloc_vsi_res(vf, idx); + if (ret) + goto error_alloc; + } + /* send correct number of queues */ + total_queue_pairs = I40E_MAX_VF_QUEUES; + } else { + dev_info(&pf->pdev->dev, "VF %d: Not enough queues to allocate, disabling ADq\n", + vf->vf_id); + vf->adq_enabled = false; + } + } + /* We account for each VF to get a default number of queue pairs. If * the VF has now requested more, we need to account for that to make * certain we never request more queues than we actually have left in @@ -1537,6 +1681,27 @@ static int i40e_vc_get_version_msg(struct i40e_vf *vf, u8 *msg) } /** + * i40e_del_qch - delete all the additional VSIs created as a part of ADq + * @vf: pointer to VF structure + **/ +static void i40e_del_qch(struct i40e_vf *vf) +{ + struct i40e_pf *pf = vf->pf; + int i; + + /* first element in the array belongs to primary VF VSI and we shouldn't + * delete it. We should however delete the rest of the VSIs created + */ + for (i = 1; i < vf->num_tc; i++) { + if (vf->ch[i].vsi_idx) { + i40e_vsi_release(pf->vsi[vf->ch[i].vsi_idx]); + vf->ch[i].vsi_idx = 0; + vf->ch[i].vsi_id = 0; + } + } +} + +/** * i40e_vc_get_vf_resources_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer @@ -1631,6 +1796,9 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg) if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_REQ_QUEUES) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_REQ_QUEUES; + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_ADQ) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_ADQ; + vfres->num_vsis = num_vsis; vfres->num_queue_pairs = vf->num_queue_pairs; vfres->max_vectors = pf->hw.func_caps.num_msix_vectors_vf; @@ -1855,27 +2023,37 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) (struct virtchnl_vsi_queue_config_info *)msg; struct virtchnl_queue_pair_info *qpi; struct i40e_pf *pf = vf->pf; - u16 vsi_id, vsi_queue_id; + u16 vsi_id, vsi_queue_id = 0; i40e_status aq_ret = 0; - int i; + int i, j = 0, idx = 0; + + vsi_id = qci->vsi_id; if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { aq_ret = I40E_ERR_PARAM; goto error_param; } - vsi_id = qci->vsi_id; if (!i40e_vc_isvalid_vsi_id(vf, vsi_id)) { aq_ret = I40E_ERR_PARAM; goto error_param; } + for (i = 0; i < qci->num_queue_pairs; i++) { qpi = &qci->qpair[i]; - vsi_queue_id = qpi->txq.queue_id; - if ((qpi->txq.vsi_id != vsi_id) || - (qpi->rxq.vsi_id != vsi_id) || - (qpi->rxq.queue_id != vsi_queue_id) || - !i40e_vc_isvalid_queue_id(vf, vsi_id, vsi_queue_id)) { + + if (!vf->adq_enabled) { + vsi_queue_id = qpi->txq.queue_id; + + if (qpi->txq.vsi_id != qci->vsi_id || + qpi->rxq.vsi_id != qci->vsi_id || + qpi->rxq.queue_id != vsi_queue_id) { + aq_ret = I40E_ERR_PARAM; + goto error_param; + } + } + + if (!i40e_vc_isvalid_queue_id(vf, vsi_id, vsi_queue_id)) { aq_ret = I40E_ERR_PARAM; goto error_param; } @@ -1887,9 +2065,33 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) aq_ret = I40E_ERR_PARAM; goto error_param; } + + /* For ADq there can be up to 4 VSIs with max 4 queues each. + * VF does not know about these additional VSIs and all + * it cares is about its own queues. PF configures these queues + * to its appropriate VSIs based on TC mapping + **/ + if (vf->adq_enabled) { + if (j == (vf->ch[idx].num_qps - 1)) { + idx++; + j = 0; /* resetting the queue count */ + vsi_queue_id = 0; + } else { + j++; + vsi_queue_id++; + } + vsi_id = vf->ch[idx].vsi_id; + } } /* set vsi num_queue_pairs in use to num configured by VF */ - pf->vsi[vf->lan_vsi_idx]->num_queue_pairs = qci->num_queue_pairs; + if (!vf->adq_enabled) { + pf->vsi[vf->lan_vsi_idx]->num_queue_pairs = + qci->num_queue_pairs; + } else { + for (i = 0; i < vf->num_tc; i++) + pf->vsi[vf->ch[i].vsi_idx]->num_queue_pairs = + vf->ch[i].num_qps; + } error_param: /* send the response to the VF */ @@ -1898,6 +2100,33 @@ error_param: } /** + * i40e_validate_queue_map + * @vsi_id: vsi id + * @queuemap: Tx or Rx queue map + * + * check if Tx or Rx queue map is valid + **/ +static int i40e_validate_queue_map(struct i40e_vf *vf, u16 vsi_id, + unsigned long queuemap) +{ + u16 vsi_queue_id, queue_id; + + for_each_set_bit(vsi_queue_id, &queuemap, I40E_MAX_VSI_QP) { + if (vf->adq_enabled) { + vsi_id = vf->ch[vsi_queue_id / I40E_MAX_VF_VSI].vsi_id; + queue_id = (vsi_queue_id % I40E_DEFAULT_QUEUES_PER_VF); + } else { + queue_id = vsi_queue_id; + } + + if (!i40e_vc_isvalid_queue_id(vf, vsi_id, queue_id)) + return -EINVAL; + } + + return 0; +} + +/** * i40e_vc_config_irq_map_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer @@ -1911,9 +2140,8 @@ static int i40e_vc_config_irq_map_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) struct virtchnl_irq_map_info *irqmap_info = (struct virtchnl_irq_map_info *)msg; struct virtchnl_vector_map *map; - u16 vsi_id, vsi_queue_id, vector_id; + u16 vsi_id, vector_id; i40e_status aq_ret = 0; - unsigned long tempmap; int i; if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { @@ -1923,7 +2151,6 @@ static int i40e_vc_config_irq_map_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) for (i = 0; i < irqmap_info->num_vectors; i++) { map = &irqmap_info->vecmap[i]; - vector_id = map->vector_id; vsi_id = map->vsi_id; /* validate msg params */ @@ -1933,23 +2160,14 @@ static int i40e_vc_config_irq_map_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) goto error_param; } - /* lookout for the invalid queue index */ - tempmap = map->rxq_map; - for_each_set_bit(vsi_queue_id, &tempmap, I40E_MAX_VSI_QP) { - if (!i40e_vc_isvalid_queue_id(vf, vsi_id, - vsi_queue_id)) { - aq_ret = I40E_ERR_PARAM; - goto error_param; - } + if (i40e_validate_queue_map(vf, vsi_id, map->rxq_map)) { + aq_ret = I40E_ERR_PARAM; + goto error_param; } - tempmap = map->txq_map; - for_each_set_bit(vsi_queue_id, &tempmap, I40E_MAX_VSI_QP) { - if (!i40e_vc_isvalid_queue_id(vf, vsi_id, - vsi_queue_id)) { - aq_ret = I40E_ERR_PARAM; - goto error_param; - } + if (i40e_validate_queue_map(vf, vsi_id, map->txq_map)) { + aq_ret = I40E_ERR_PARAM; + goto error_param; } i40e_config_irq_link_list(vf, vsi_id, map); @@ -1975,6 +2193,7 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) struct i40e_pf *pf = vf->pf; u16 vsi_id = vqs->vsi_id; i40e_status aq_ret = 0; + int i; if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { aq_ret = I40E_ERR_PARAM; @@ -1993,6 +2212,16 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) if (i40e_vsi_start_rings(pf->vsi[vf->lan_vsi_idx])) aq_ret = I40E_ERR_TIMEOUT; + + /* need to start the rings for additional ADq VSI's as well */ + if (vf->adq_enabled) { + /* zero belongs to LAN VSI */ + for (i = 1; i < vf->num_tc; i++) { + if (i40e_vsi_start_rings(pf->vsi[vf->ch[i].vsi_idx])) + aq_ret = I40E_ERR_TIMEOUT; + } + } + error_param: /* send the response to the VF */ return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_ENABLE_QUEUES, @@ -2688,6 +2917,618 @@ err: } /** + * i40e_validate_cloud_filter + * @mask: mask for TC filter + * @data: data for TC filter + * + * This function validates cloud filter programmed as TC filter for ADq + **/ +static int i40e_validate_cloud_filter(struct i40e_vf *vf, + struct virtchnl_filter *tc_filter) +{ + struct virtchnl_l4_spec mask = tc_filter->mask.tcp_spec; + struct virtchnl_l4_spec data = tc_filter->data.tcp_spec; + struct i40e_pf *pf = vf->pf; + struct i40e_vsi *vsi = NULL; + struct i40e_mac_filter *f; + struct hlist_node *h; + bool found = false; + int bkt; + + if (!tc_filter->action) { + dev_info(&pf->pdev->dev, + "VF %d: Currently ADq doesn't support Drop Action\n", + vf->vf_id); + goto err; + } + + /* action_meta is TC number here to which the filter is applied */ + if (!tc_filter->action_meta || + tc_filter->action_meta > I40E_MAX_VF_VSI) { + dev_info(&pf->pdev->dev, "VF %d: Invalid TC number %u\n", + vf->vf_id, tc_filter->action_meta); + goto err; + } + + /* Check filter if it's programmed for advanced mode or basic mode. + * There are two ADq modes (for VF only), + * 1. Basic mode: intended to allow as many filter options as possible + * to be added to a VF in Non-trusted mode. Main goal is + * to add filters to its own MAC and VLAN id. + * 2. Advanced mode: is for allowing filters to be applied other than + * its own MAC or VLAN. This mode requires the VF to be + * Trusted. + */ + if (mask.dst_mac[0] && !mask.dst_ip[0]) { + vsi = pf->vsi[vf->lan_vsi_idx]; + f = i40e_find_mac(vsi, data.dst_mac); + + if (!f) { + dev_info(&pf->pdev->dev, + "Destination MAC %pM doesn't belong to VF %d\n", + data.dst_mac, vf->vf_id); + goto err; + } + + if (mask.vlan_id) { + hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, + hlist) { + if (f->vlan == ntohs(data.vlan_id)) { + found = true; + break; + } + } + if (!found) { + dev_info(&pf->pdev->dev, + "VF %d doesn't have any VLAN id %u\n", + vf->vf_id, ntohs(data.vlan_id)); + goto err; + } + } + } else { + /* Check if VF is trusted */ + if (!test_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps)) { + dev_err(&pf->pdev->dev, + "VF %d not trusted, make VF trusted to add advanced mode ADq cloud filters\n", + vf->vf_id); + return I40E_ERR_CONFIG; + } + } + + if (mask.dst_mac[0] & data.dst_mac[0]) { + if (is_broadcast_ether_addr(data.dst_mac) || + is_zero_ether_addr(data.dst_mac)) { + dev_info(&pf->pdev->dev, "VF %d: Invalid Dest MAC addr %pM\n", + vf->vf_id, data.dst_mac); + goto err; + } + } + + if (mask.src_mac[0] & data.src_mac[0]) { + if (is_broadcast_ether_addr(data.src_mac) || + is_zero_ether_addr(data.src_mac)) { + dev_info(&pf->pdev->dev, "VF %d: Invalid Source MAC addr %pM\n", + vf->vf_id, data.src_mac); + goto err; + } + } + + if (mask.dst_port & data.dst_port) { + if (!data.dst_port || be16_to_cpu(data.dst_port) > 0xFFFF) { + dev_info(&pf->pdev->dev, "VF %d: Invalid Dest port\n", + vf->vf_id); + goto err; + } + } + + if (mask.src_port & data.src_port) { + if (!data.src_port || be16_to_cpu(data.src_port) > 0xFFFF) { + dev_info(&pf->pdev->dev, "VF %d: Invalid Source port\n", + vf->vf_id); + goto err; + } + } + + if (tc_filter->flow_type != VIRTCHNL_TCP_V6_FLOW && + tc_filter->flow_type != VIRTCHNL_TCP_V4_FLOW) { + dev_info(&pf->pdev->dev, "VF %d: Invalid Flow type\n", + vf->vf_id); + goto err; + } + + if (mask.vlan_id & data.vlan_id) { + if (ntohs(data.vlan_id) > I40E_MAX_VLANID) { + dev_info(&pf->pdev->dev, "VF %d: invalid VLAN ID\n", + vf->vf_id); + goto err; + } + } + + return I40E_SUCCESS; +err: + return I40E_ERR_CONFIG; +} + +/** + * i40e_find_vsi_from_seid - searches for the vsi with the given seid + * @vf: pointer to the VF info + * @seid - seid of the vsi it is searching for + **/ +static struct i40e_vsi *i40e_find_vsi_from_seid(struct i40e_vf *vf, u16 seid) +{ + struct i40e_pf *pf = vf->pf; + struct i40e_vsi *vsi = NULL; + int i; + + for (i = 0; i < vf->num_tc ; i++) { + vsi = i40e_find_vsi_from_id(pf, vf->ch[i].vsi_id); + if (vsi && vsi->seid == seid) + return vsi; + } + return NULL; +} + +/** + * i40e_del_all_cloud_filters + * @vf: pointer to the VF info + * + * This function deletes all cloud filters + **/ +static void i40e_del_all_cloud_filters(struct i40e_vf *vf) +{ + struct i40e_cloud_filter *cfilter = NULL; + struct i40e_pf *pf = vf->pf; + struct i40e_vsi *vsi = NULL; + struct hlist_node *node; + int ret; + + hlist_for_each_entry_safe(cfilter, node, + &vf->cloud_filter_list, cloud_node) { + vsi = i40e_find_vsi_from_seid(vf, cfilter->seid); + + if (!vsi) { + dev_err(&pf->pdev->dev, "VF %d: no VSI found for matching %u seid, can't delete cloud filter\n", + vf->vf_id, cfilter->seid); + continue; + } + + if (cfilter->dst_port) + ret = i40e_add_del_cloud_filter_big_buf(vsi, cfilter, + false); + else + ret = i40e_add_del_cloud_filter(vsi, cfilter, false); + if (ret) + dev_err(&pf->pdev->dev, + "VF %d: Failed to delete cloud filter, err %s aq_err %s\n", + vf->vf_id, i40e_stat_str(&pf->hw, ret), + i40e_aq_str(&pf->hw, + pf->hw.aq.asq_last_status)); + + hlist_del(&cfilter->cloud_node); + kfree(cfilter); + vf->num_cloud_filters--; + } +} + +/** + * i40e_vc_del_cloud_filter + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * This function deletes a cloud filter programmed as TC filter for ADq + **/ +static int i40e_vc_del_cloud_filter(struct i40e_vf *vf, u8 *msg) +{ + struct virtchnl_filter *vcf = (struct virtchnl_filter *)msg; + struct virtchnl_l4_spec mask = vcf->mask.tcp_spec; + struct virtchnl_l4_spec tcf = vcf->data.tcp_spec; + struct i40e_cloud_filter cfilter, *cf = NULL; + struct i40e_pf *pf = vf->pf; + struct i40e_vsi *vsi = NULL; + struct hlist_node *node; + i40e_status aq_ret = 0; + int i, ret; + + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + aq_ret = I40E_ERR_PARAM; + goto err; + } + + if (!vf->adq_enabled) { + dev_info(&pf->pdev->dev, + "VF %d: ADq not enabled, can't apply cloud filter\n", + vf->vf_id); + aq_ret = I40E_ERR_PARAM; + goto err; + } + + if (i40e_validate_cloud_filter(vf, vcf)) { + dev_info(&pf->pdev->dev, + "VF %d: Invalid input, can't apply cloud filter\n", + vf->vf_id); + aq_ret = I40E_ERR_PARAM; + goto err; + } + + memset(&cfilter, 0, sizeof(cfilter)); + /* parse destination mac address */ + for (i = 0; i < ETH_ALEN; i++) + cfilter.dst_mac[i] = mask.dst_mac[i] & tcf.dst_mac[i]; + + /* parse source mac address */ + for (i = 0; i < ETH_ALEN; i++) + cfilter.src_mac[i] = mask.src_mac[i] & tcf.src_mac[i]; + + cfilter.vlan_id = mask.vlan_id & tcf.vlan_id; + cfilter.dst_port = mask.dst_port & tcf.dst_port; + cfilter.src_port = mask.src_port & tcf.src_port; + + switch (vcf->flow_type) { + case VIRTCHNL_TCP_V4_FLOW: + cfilter.n_proto = ETH_P_IP; + if (mask.dst_ip[0] & tcf.dst_ip[0]) + memcpy(&cfilter.ip.v4.dst_ip, tcf.dst_ip, + ARRAY_SIZE(tcf.dst_ip)); + else if (mask.src_ip[0] & tcf.dst_ip[0]) + memcpy(&cfilter.ip.v4.src_ip, tcf.src_ip, + ARRAY_SIZE(tcf.dst_ip)); + break; + case VIRTCHNL_TCP_V6_FLOW: + cfilter.n_proto = ETH_P_IPV6; + if (mask.dst_ip[3] & tcf.dst_ip[3]) + memcpy(&cfilter.ip.v6.dst_ip6, tcf.dst_ip, + sizeof(cfilter.ip.v6.dst_ip6)); + if (mask.src_ip[3] & tcf.src_ip[3]) + memcpy(&cfilter.ip.v6.src_ip6, tcf.src_ip, + sizeof(cfilter.ip.v6.src_ip6)); + break; + default: + /* TC filter can be configured based on different combinations + * and in this case IP is not a part of filter config + */ + dev_info(&pf->pdev->dev, "VF %d: Flow type not configured\n", + vf->vf_id); + } + + /* get the vsi to which the tc belongs to */ + vsi = pf->vsi[vf->ch[vcf->action_meta].vsi_idx]; + cfilter.seid = vsi->seid; + cfilter.flags = vcf->field_flags; + + /* Deleting TC filter */ + if (tcf.dst_port) + ret = i40e_add_del_cloud_filter_big_buf(vsi, &cfilter, false); + else + ret = i40e_add_del_cloud_filter(vsi, &cfilter, false); + if (ret) { + dev_err(&pf->pdev->dev, + "VF %d: Failed to delete cloud filter, err %s aq_err %s\n", + vf->vf_id, i40e_stat_str(&pf->hw, ret), + i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); + goto err; + } + + hlist_for_each_entry_safe(cf, node, + &vf->cloud_filter_list, cloud_node) { + if (cf->seid != cfilter.seid) + continue; + if (mask.dst_port) + if (cfilter.dst_port != cf->dst_port) + continue; + if (mask.dst_mac[0]) + if (!ether_addr_equal(cf->src_mac, cfilter.src_mac)) + continue; + /* for ipv4 data to be valid, only first byte of mask is set */ + if (cfilter.n_proto == ETH_P_IP && mask.dst_ip[0]) + if (memcmp(&cfilter.ip.v4.dst_ip, &cf->ip.v4.dst_ip, + ARRAY_SIZE(tcf.dst_ip))) + continue; + /* for ipv6, mask is set for all sixteen bytes (4 words) */ + if (cfilter.n_proto == ETH_P_IPV6 && mask.dst_ip[3]) + if (memcmp(&cfilter.ip.v6.dst_ip6, &cf->ip.v6.dst_ip6, + sizeof(cfilter.ip.v6.src_ip6))) + continue; + if (mask.vlan_id) + if (cfilter.vlan_id != cf->vlan_id) + continue; + + hlist_del(&cf->cloud_node); + kfree(cf); + vf->num_cloud_filters--; + } + +err: + return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_DEL_CLOUD_FILTER, + aq_ret); +} + +/** + * i40e_vc_add_cloud_filter + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * This function adds a cloud filter programmed as TC filter for ADq + **/ +static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg) +{ + struct virtchnl_filter *vcf = (struct virtchnl_filter *)msg; + struct virtchnl_l4_spec mask = vcf->mask.tcp_spec; + struct virtchnl_l4_spec tcf = vcf->data.tcp_spec; + struct i40e_cloud_filter *cfilter = NULL; + struct i40e_pf *pf = vf->pf; + struct i40e_vsi *vsi = NULL; + i40e_status aq_ret = 0; + int i, ret; + + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + aq_ret = I40E_ERR_PARAM; + goto err; + } + + if (!vf->adq_enabled) { + dev_info(&pf->pdev->dev, + "VF %d: ADq is not enabled, can't apply cloud filter\n", + vf->vf_id); + aq_ret = I40E_ERR_PARAM; + goto err; + } + + if (i40e_validate_cloud_filter(vf, vcf)) { + dev_info(&pf->pdev->dev, + "VF %d: Invalid input/s, can't apply cloud filter\n", + vf->vf_id); + aq_ret = I40E_ERR_PARAM; + goto err; + } + + cfilter = kzalloc(sizeof(*cfilter), GFP_KERNEL); + if (!cfilter) + return -ENOMEM; + + /* parse destination mac address */ + for (i = 0; i < ETH_ALEN; i++) + cfilter->dst_mac[i] = mask.dst_mac[i] & tcf.dst_mac[i]; + + /* parse source mac address */ + for (i = 0; i < ETH_ALEN; i++) + cfilter->src_mac[i] = mask.src_mac[i] & tcf.src_mac[i]; + + cfilter->vlan_id = mask.vlan_id & tcf.vlan_id; + cfilter->dst_port = mask.dst_port & tcf.dst_port; + cfilter->src_port = mask.src_port & tcf.src_port; + + switch (vcf->flow_type) { + case VIRTCHNL_TCP_V4_FLOW: + cfilter->n_proto = ETH_P_IP; + if (mask.dst_ip[0] & tcf.dst_ip[0]) + memcpy(&cfilter->ip.v4.dst_ip, tcf.dst_ip, + ARRAY_SIZE(tcf.dst_ip)); + else if (mask.src_ip[0] & tcf.dst_ip[0]) + memcpy(&cfilter->ip.v4.src_ip, tcf.src_ip, + ARRAY_SIZE(tcf.dst_ip)); + break; + case VIRTCHNL_TCP_V6_FLOW: + cfilter->n_proto = ETH_P_IPV6; + if (mask.dst_ip[3] & tcf.dst_ip[3]) + memcpy(&cfilter->ip.v6.dst_ip6, tcf.dst_ip, + sizeof(cfilter->ip.v6.dst_ip6)); + if (mask.src_ip[3] & tcf.src_ip[3]) + memcpy(&cfilter->ip.v6.src_ip6, tcf.src_ip, + sizeof(cfilter->ip.v6.src_ip6)); + break; + default: + /* TC filter can be configured based on different combinations + * and in this case IP is not a part of filter config + */ + dev_info(&pf->pdev->dev, "VF %d: Flow type not configured\n", + vf->vf_id); + } + + /* get the VSI to which the TC belongs to */ + vsi = pf->vsi[vf->ch[vcf->action_meta].vsi_idx]; + cfilter->seid = vsi->seid; + cfilter->flags = vcf->field_flags; + + /* Adding cloud filter programmed as TC filter */ + if (tcf.dst_port) + ret = i40e_add_del_cloud_filter_big_buf(vsi, cfilter, true); + else + ret = i40e_add_del_cloud_filter(vsi, cfilter, true); + if (ret) { + dev_err(&pf->pdev->dev, + "VF %d: Failed to add cloud filter, err %s aq_err %s\n", + vf->vf_id, i40e_stat_str(&pf->hw, ret), + i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); + goto err; + } + + INIT_HLIST_NODE(&cfilter->cloud_node); + hlist_add_head(&cfilter->cloud_node, &vf->cloud_filter_list); + vf->num_cloud_filters++; +err: + return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_ADD_CLOUD_FILTER, + aq_ret); +} + +/** + * i40e_vc_add_qch_msg: Add queue channel and enable ADq + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + **/ +static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg) +{ + struct virtchnl_tc_info *tci = + (struct virtchnl_tc_info *)msg; + struct i40e_pf *pf = vf->pf; + struct i40e_link_status *ls = &pf->hw.phy.link_info; + int i, adq_request_qps = 0, speed = 0; + i40e_status aq_ret = 0; + + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + aq_ret = I40E_ERR_PARAM; + goto err; + } + + /* ADq cannot be applied if spoof check is ON */ + if (vf->spoofchk) { + dev_err(&pf->pdev->dev, + "Spoof check is ON, turn it OFF to enable ADq\n"); + aq_ret = I40E_ERR_PARAM; + goto err; + } + + if (!(vf->driver_caps & VIRTCHNL_VF_OFFLOAD_ADQ)) { + dev_err(&pf->pdev->dev, + "VF %d attempting to enable ADq, but hasn't properly negotiated that capability\n", + vf->vf_id); + aq_ret = I40E_ERR_PARAM; + goto err; + } + + /* max number of traffic classes for VF currently capped at 4 */ + if (!tci->num_tc || tci->num_tc > I40E_MAX_VF_VSI) { + dev_err(&pf->pdev->dev, + "VF %d trying to set %u TCs, valid range 1-4 TCs per VF\n", + vf->vf_id, tci->num_tc); + aq_ret = I40E_ERR_PARAM; + goto err; + } + + /* validate queues for each TC */ + for (i = 0; i < tci->num_tc; i++) + if (!tci->list[i].count || + tci->list[i].count > I40E_DEFAULT_QUEUES_PER_VF) { + dev_err(&pf->pdev->dev, + "VF %d: TC %d trying to set %u queues, valid range 1-4 queues per TC\n", + vf->vf_id, i, tci->list[i].count); + aq_ret = I40E_ERR_PARAM; + goto err; + } + + /* need Max VF queues but already have default number of queues */ + adq_request_qps = I40E_MAX_VF_QUEUES - I40E_DEFAULT_QUEUES_PER_VF; + + if (pf->queues_left < adq_request_qps) { + dev_err(&pf->pdev->dev, + "No queues left to allocate to VF %d\n", + vf->vf_id); + aq_ret = I40E_ERR_PARAM; + goto err; + } else { + /* we need to allocate max VF queues to enable ADq so as to + * make sure ADq enabled VF always gets back queues when it + * goes through a reset. + */ + vf->num_queue_pairs = I40E_MAX_VF_QUEUES; + } + + /* get link speed in MB to validate rate limit */ + switch (ls->link_speed) { + case VIRTCHNL_LINK_SPEED_100MB: + speed = SPEED_100; + break; + case VIRTCHNL_LINK_SPEED_1GB: + speed = SPEED_1000; + break; + case VIRTCHNL_LINK_SPEED_10GB: + speed = SPEED_10000; + break; + case VIRTCHNL_LINK_SPEED_20GB: + speed = SPEED_20000; + break; + case VIRTCHNL_LINK_SPEED_25GB: + speed = SPEED_25000; + break; + case VIRTCHNL_LINK_SPEED_40GB: + speed = SPEED_40000; + break; + default: + dev_err(&pf->pdev->dev, + "Cannot detect link speed\n"); + aq_ret = I40E_ERR_PARAM; + goto err; + } + + /* parse data from the queue channel info */ + vf->num_tc = tci->num_tc; + for (i = 0; i < vf->num_tc; i++) { + if (tci->list[i].max_tx_rate) { + if (tci->list[i].max_tx_rate > speed) { + dev_err(&pf->pdev->dev, + "Invalid max tx rate %llu specified for VF %d.", + tci->list[i].max_tx_rate, + vf->vf_id); + aq_ret = I40E_ERR_PARAM; + goto err; + } else { + vf->ch[i].max_tx_rate = + tci->list[i].max_tx_rate; + } + } + vf->ch[i].num_qps = tci->list[i].count; + } + + /* set this flag only after making sure all inputs are sane */ + vf->adq_enabled = true; + /* num_req_queues is set when user changes number of queues via ethtool + * and this causes issue for default VSI(which depends on this variable) + * when ADq is enabled, hence reset it. + */ + vf->num_req_queues = 0; + + /* reset the VF in order to allocate resources */ + i40e_vc_notify_vf_reset(vf); + i40e_reset_vf(vf, false); + + return I40E_SUCCESS; + + /* send the response to the VF */ +err: + return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_ENABLE_CHANNELS, + aq_ret); +} + +/** + * i40e_vc_del_qch_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + **/ +static int i40e_vc_del_qch_msg(struct i40e_vf *vf, u8 *msg) +{ + struct i40e_pf *pf = vf->pf; + i40e_status aq_ret = 0; + + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + aq_ret = I40E_ERR_PARAM; + goto err; + } + + if (vf->adq_enabled) { + i40e_del_all_cloud_filters(vf); + i40e_del_qch(vf); + vf->adq_enabled = false; + vf->num_tc = 0; + dev_info(&pf->pdev->dev, + "Deleting Queue Channels and cloud filters for ADq on VF %d\n", + vf->vf_id); + } else { + dev_info(&pf->pdev->dev, "VF %d trying to delete queue channels but ADq isn't enabled\n", + vf->vf_id); + aq_ret = I40E_ERR_PARAM; + } + + /* reset the VF in order to allocate resources */ + i40e_vc_notify_vf_reset(vf); + i40e_reset_vf(vf, false); + + return I40E_SUCCESS; + +err: + return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_DISABLE_CHANNELS, + aq_ret); +} + +/** * i40e_vc_process_vf_msg * @pf: pointer to the PF structure * @vf_id: source VF id @@ -2816,7 +3657,18 @@ int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode, case VIRTCHNL_OP_REQUEST_QUEUES: ret = i40e_vc_request_queues_msg(vf, msg, msglen); break; - + case VIRTCHNL_OP_ENABLE_CHANNELS: + ret = i40e_vc_add_qch_msg(vf, msg); + break; + case VIRTCHNL_OP_DISABLE_CHANNELS: + ret = i40e_vc_del_qch_msg(vf, msg); + break; + case VIRTCHNL_OP_ADD_CLOUD_FILTER: + ret = i40e_vc_add_cloud_filter(vf, msg); + break; + case VIRTCHNL_OP_DEL_CLOUD_FILTER: + ret = i40e_vc_del_cloud_filter(vf, msg); + break; case VIRTCHNL_OP_UNKNOWN: default: dev_err(&pf->pdev->dev, "Unsupported opcode %d from VF %d\n", @@ -3382,6 +4234,16 @@ int i40e_ndo_set_vf_trust(struct net_device *netdev, int vf_id, bool setting) i40e_vc_disable_vf(vf); dev_info(&pf->pdev->dev, "VF %u is now %strusted\n", vf_id, setting ? "" : "un"); + + if (vf->adq_enabled) { + if (!vf->trusted) { + dev_info(&pf->pdev->dev, + "VF %u no longer Trusted, deleting all cloud filters\n", + vf_id); + i40e_del_all_cloud_filters(vf); + } + } + out: return ret; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index 5efc4f92bb37..6852599b2379 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -69,6 +69,19 @@ enum i40e_vf_capabilities { I40E_VIRTCHNL_VF_CAP_IWARP, }; +/* In ADq, max 4 VSI's can be allocated per VF including primary VF VSI. + * These variables are used to store indices, id's and number of queues + * for each VSI including that of primary VF VSI. Each Traffic class is + * termed as channel and each channel can in-turn have 4 queues which + * means max 16 queues overall per VF. + */ +struct i40evf_channel { + u16 vsi_idx; /* index in PF struct for all channel VSIs */ + u16 vsi_id; /* VSI ID used by firmware */ + u16 num_qps; /* number of queue pairs requested by user */ + u64 max_tx_rate; /* bandwidth rate allocation for VSIs */ +}; + /* VF information structure */ struct i40e_vf { struct i40e_pf *pf; @@ -111,6 +124,13 @@ struct i40e_vf { u16 num_mac; u16 num_vlan; + /* ADq related variables */ + bool adq_enabled; /* flag to enable adq */ + u8 num_tc; + struct i40evf_channel ch[I40E_MAX_VF_VSI]; + struct hlist_head cloud_filter_list; + u16 num_cloud_filters; + /* RDMA Client */ struct virtchnl_iwarp_qvlist_info *qvlist_info; }; diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index 357d6051281f..e088d23eb083 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -196,7 +196,7 @@ void i40evf_detect_recover_hung(struct i40e_vsi *vsi) */ smp_rmb(); tx_ring->tx_stats.prev_pkt_ctr = - i40evf_get_tx_pending(tx_ring, false) ? packets : -1; + i40evf_get_tx_pending(tx_ring, true) ? packets : -1; } } } @@ -392,99 +392,241 @@ void i40evf_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) val); } +static inline bool i40e_container_is_rx(struct i40e_q_vector *q_vector, + struct i40e_ring_container *rc) +{ + return &q_vector->rx == rc; +} + +static inline unsigned int i40e_itr_divisor(struct i40e_q_vector *q_vector) +{ + unsigned int divisor; + + switch (q_vector->adapter->link_speed) { + case I40E_LINK_SPEED_40GB: + divisor = I40E_ITR_ADAPTIVE_MIN_INC * 1024; + break; + case I40E_LINK_SPEED_25GB: + case I40E_LINK_SPEED_20GB: + divisor = I40E_ITR_ADAPTIVE_MIN_INC * 512; + break; + default: + case I40E_LINK_SPEED_10GB: + divisor = I40E_ITR_ADAPTIVE_MIN_INC * 256; + break; + case I40E_LINK_SPEED_1GB: + case I40E_LINK_SPEED_100MB: + divisor = I40E_ITR_ADAPTIVE_MIN_INC * 32; + break; + } + + return divisor; +} + /** - * i40e_set_new_dynamic_itr - Find new ITR level + * i40e_update_itr - update the dynamic ITR value based on statistics + * @q_vector: structure containing interrupt and ring information * @rc: structure containing ring performance data * - * Returns true if ITR changed, false if not - * - * Stores a new ITR value based on packets and byte counts during - * the last interrupt. The advantage of per interrupt computation - * is faster updates and more accurate ITR for the current traffic - * pattern. Constants in this function were computed based on - * theoretical maximum wire speed and thresholds were set based on - * testing data as well as attempting to minimize response time + * Stores a new ITR value based on packets and byte + * counts during the last interrupt. The advantage of per interrupt + * computation is faster updates and more accurate ITR for the current + * traffic pattern. Constants in this function were computed + * based on theoretical maximum wire speed and thresholds were set based + * on testing data as well as attempting to minimize response time * while increasing bulk throughput. **/ -static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc) +static void i40e_update_itr(struct i40e_q_vector *q_vector, + struct i40e_ring_container *rc) { - enum i40e_latency_range new_latency_range = rc->latency_range; - u32 new_itr = rc->itr; - int bytes_per_usec; - unsigned int usecs, estimated_usecs; + unsigned int avg_wire_size, packets, bytes, itr; + unsigned long next_update = jiffies; - if (rc->total_packets == 0 || !rc->itr) - return false; + /* If we don't have any rings just leave ourselves set for maximum + * possible latency so we take ourselves out of the equation. + */ + if (!rc->ring || !ITR_IS_DYNAMIC(rc->ring->itr_setting)) + return; + + /* For Rx we want to push the delay up and default to low latency. + * for Tx we want to pull the delay down and default to high latency. + */ + itr = i40e_container_is_rx(q_vector, rc) ? + I40E_ITR_ADAPTIVE_MIN_USECS | I40E_ITR_ADAPTIVE_LATENCY : + I40E_ITR_ADAPTIVE_MAX_USECS | I40E_ITR_ADAPTIVE_LATENCY; + + /* If we didn't update within up to 1 - 2 jiffies we can assume + * that either packets are coming in so slow there hasn't been + * any work, or that there is so much work that NAPI is dealing + * with interrupt moderation and we don't need to do anything. + */ + if (time_after(next_update, rc->next_update)) + goto clear_counts; + + /* If itr_countdown is set it means we programmed an ITR within + * the last 4 interrupt cycles. This has a side effect of us + * potentially firing an early interrupt. In order to work around + * this we need to throw out any data received for a few + * interrupts following the update. + */ + if (q_vector->itr_countdown) { + itr = rc->target_itr; + goto clear_counts; + } + + packets = rc->total_packets; + bytes = rc->total_bytes; - usecs = (rc->itr << 1) * ITR_COUNTDOWN_START; - bytes_per_usec = rc->total_bytes / usecs; + if (i40e_container_is_rx(q_vector, rc)) { + /* If Rx there are 1 to 4 packets and bytes are less than + * 9000 assume insufficient data to use bulk rate limiting + * approach unless Tx is already in bulk rate limiting. We + * are likely latency driven. + */ + if (packets && packets < 4 && bytes < 9000 && + (q_vector->tx.target_itr & I40E_ITR_ADAPTIVE_LATENCY)) { + itr = I40E_ITR_ADAPTIVE_LATENCY; + goto adjust_by_size; + } + } else if (packets < 4) { + /* If we have Tx and Rx ITR maxed and Tx ITR is running in + * bulk mode and we are receiving 4 or fewer packets just + * reset the ITR_ADAPTIVE_LATENCY bit for latency mode so + * that the Rx can relax. + */ + if (rc->target_itr == I40E_ITR_ADAPTIVE_MAX_USECS && + (q_vector->rx.target_itr & I40E_ITR_MASK) == + I40E_ITR_ADAPTIVE_MAX_USECS) + goto clear_counts; + } else if (packets > 32) { + /* If we have processed over 32 packets in a single interrupt + * for Tx assume we need to switch over to "bulk" mode. + */ + rc->target_itr &= ~I40E_ITR_ADAPTIVE_LATENCY; + } - /* The calculations in this algorithm depend on interrupts actually - * firing at the ITR rate. This may not happen if the packet rate is - * really low, or if we've been napi polling. Check to make sure - * that's not the case before we continue. + /* We have no packets to actually measure against. This means + * either one of the other queues on this vector is active or + * we are a Tx queue doing TSO with too high of an interrupt rate. + * + * Between 4 and 56 we can assume that our current interrupt delay + * is only slightly too low. As such we should increase it by a small + * fixed amount. */ - estimated_usecs = jiffies_to_usecs(jiffies - rc->last_itr_update); - if (estimated_usecs > usecs) { - new_latency_range = I40E_LOW_LATENCY; - goto reset_latency; + if (packets < 56) { + itr = rc->target_itr + I40E_ITR_ADAPTIVE_MIN_INC; + if ((itr & I40E_ITR_MASK) > I40E_ITR_ADAPTIVE_MAX_USECS) { + itr &= I40E_ITR_ADAPTIVE_LATENCY; + itr += I40E_ITR_ADAPTIVE_MAX_USECS; + } + goto clear_counts; + } + + if (packets <= 256) { + itr = min(q_vector->tx.current_itr, q_vector->rx.current_itr); + itr &= I40E_ITR_MASK; + + /* Between 56 and 112 is our "goldilocks" zone where we are + * working out "just right". Just report that our current + * ITR is good for us. + */ + if (packets <= 112) + goto clear_counts; + + /* If packet count is 128 or greater we are likely looking + * at a slight overrun of the delay we want. Try halving + * our delay to see if that will cut the number of packets + * in half per interrupt. + */ + itr /= 2; + itr &= I40E_ITR_MASK; + if (itr < I40E_ITR_ADAPTIVE_MIN_USECS) + itr = I40E_ITR_ADAPTIVE_MIN_USECS; + + goto clear_counts; } - /* simple throttlerate management - * 0-10MB/s lowest (50000 ints/s) - * 10-20MB/s low (20000 ints/s) - * 20-1249MB/s bulk (18000 ints/s) + /* The paths below assume we are dealing with a bulk ITR since + * number of packets is greater than 256. We are just going to have + * to compute a value and try to bring the count under control, + * though for smaller packet sizes there isn't much we can do as + * NAPI polling will likely be kicking in sooner rather than later. + */ + itr = I40E_ITR_ADAPTIVE_BULK; + +adjust_by_size: + /* If packet counts are 256 or greater we can assume we have a gross + * overestimation of what the rate should be. Instead of trying to fine + * tune it just use the formula below to try and dial in an exact value + * give the current packet size of the frame. + */ + avg_wire_size = bytes / packets; + + /* The following is a crude approximation of: + * wmem_default / (size + overhead) = desired_pkts_per_int + * rate / bits_per_byte / (size + ethernet overhead) = pkt_rate + * (desired_pkt_rate / pkt_rate) * usecs_per_sec = ITR value * - * The math works out because the divisor is in 10^(-6) which - * turns the bytes/us input value into MB/s values, but - * make sure to use usecs, as the register values written - * are in 2 usec increments in the ITR registers, and make sure - * to use the smoothed values that the countdown timer gives us. + * Assuming wmem_default is 212992 and overhead is 640 bytes per + * packet, (256 skb, 64 headroom, 320 shared info), we can reduce the + * formula down to + * + * (170 * (size + 24)) / (size + 640) = ITR + * + * We first do some math on the packet size and then finally bitshift + * by 8 after rounding up. We also have to account for PCIe link speed + * difference as ITR scales based on this. */ - switch (new_latency_range) { - case I40E_LOWEST_LATENCY: - if (bytes_per_usec > 10) - new_latency_range = I40E_LOW_LATENCY; - break; - case I40E_LOW_LATENCY: - if (bytes_per_usec > 20) - new_latency_range = I40E_BULK_LATENCY; - else if (bytes_per_usec <= 10) - new_latency_range = I40E_LOWEST_LATENCY; - break; - case I40E_BULK_LATENCY: - default: - if (bytes_per_usec <= 20) - new_latency_range = I40E_LOW_LATENCY; - break; + if (avg_wire_size <= 60) { + /* Start at 250k ints/sec */ + avg_wire_size = 4096; + } else if (avg_wire_size <= 380) { + /* 250K ints/sec to 60K ints/sec */ + avg_wire_size *= 40; + avg_wire_size += 1696; + } else if (avg_wire_size <= 1084) { + /* 60K ints/sec to 36K ints/sec */ + avg_wire_size *= 15; + avg_wire_size += 11452; + } else if (avg_wire_size <= 1980) { + /* 36K ints/sec to 30K ints/sec */ + avg_wire_size *= 5; + avg_wire_size += 22420; + } else { + /* plateau at a limit of 30K ints/sec */ + avg_wire_size = 32256; } -reset_latency: - rc->latency_range = new_latency_range; + /* If we are in low latency mode halve our delay which doubles the + * rate to somewhere between 100K to 16K ints/sec + */ + if (itr & I40E_ITR_ADAPTIVE_LATENCY) + avg_wire_size /= 2; - switch (new_latency_range) { - case I40E_LOWEST_LATENCY: - new_itr = I40E_ITR_50K; - break; - case I40E_LOW_LATENCY: - new_itr = I40E_ITR_20K; - break; - case I40E_BULK_LATENCY: - new_itr = I40E_ITR_18K; - break; - default: - break; + /* Resultant value is 256 times larger than it needs to be. This + * gives us room to adjust the value as needed to either increase + * or decrease the value based on link speeds of 10G, 2.5G, 1G, etc. + * + * Use addition as we have already recorded the new latency flag + * for the ITR value. + */ + itr += DIV_ROUND_UP(avg_wire_size, i40e_itr_divisor(q_vector)) * + I40E_ITR_ADAPTIVE_MIN_INC; + + if ((itr & I40E_ITR_MASK) > I40E_ITR_ADAPTIVE_MAX_USECS) { + itr &= I40E_ITR_ADAPTIVE_LATENCY; + itr += I40E_ITR_ADAPTIVE_MAX_USECS; } +clear_counts: + /* write back value */ + rc->target_itr = itr; + + /* next update should occur within next jiffy */ + rc->next_update = next_update + 1; + rc->total_bytes = 0; rc->total_packets = 0; - rc->last_itr_update = jiffies; - - if (new_itr != rc->itr) { - rc->itr = new_itr; - return true; - } - return false; } /** @@ -1273,7 +1415,7 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring, * @rx_buffer: rx buffer to pull data from * * This function will clean up the contents of the rx_buffer. It will - * either recycle the bufer or unmap it and free the associated resources. + * either recycle the buffer or unmap it and free the associated resources. */ static void i40e_put_rx_buffer(struct i40e_ring *rx_ring, struct i40e_rx_buffer *rx_buffer) @@ -1457,33 +1599,45 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) return failure ? budget : (int)total_rx_packets; } -static u32 i40e_buildreg_itr(const int type, const u16 itr) +static inline u32 i40e_buildreg_itr(const int type, u16 itr) { u32 val; + /* We don't bother with setting the CLEARPBA bit as the data sheet + * points out doing so is "meaningless since it was already + * auto-cleared". The auto-clearing happens when the interrupt is + * asserted. + * + * Hardware errata 28 for also indicates that writing to a + * xxINT_DYN_CTLx CSR with INTENA_MSK (bit 31) set to 0 will clear + * an event in the PBA anyway so we need to rely on the automask + * to hold pending events for us until the interrupt is re-enabled + * + * The itr value is reported in microseconds, and the register + * value is recorded in 2 microsecond units. For this reason we + * only need to shift by the interval shift - 1 instead of the + * full value. + */ + itr &= I40E_ITR_MASK; + val = I40E_VFINT_DYN_CTLN1_INTENA_MASK | - I40E_VFINT_DYN_CTLN1_CLEARPBA_MASK | (type << I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT) | - (itr << I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT); + (itr << (I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT - 1)); return val; } /* a small macro to shorten up some long lines */ #define INTREG I40E_VFINT_DYN_CTLN1 -static inline int get_rx_itr(struct i40e_vsi *vsi, int idx) -{ - struct i40evf_adapter *adapter = vsi->back; - return adapter->rx_rings[idx].rx_itr_setting; -} - -static inline int get_tx_itr(struct i40e_vsi *vsi, int idx) -{ - struct i40evf_adapter *adapter = vsi->back; - - return adapter->tx_rings[idx].tx_itr_setting; -} +/* The act of updating the ITR will cause it to immediately trigger. In order + * to prevent this from throwing off adaptive update statistics we defer the + * update so that it can only happen so often. So after either Tx or Rx are + * updated we make the adaptive scheme wait until either the ITR completely + * expires via the next_update expiration or we have been through at least + * 3 interrupts. + */ +#define ITR_COUNTDOWN_START 3 /** * i40e_update_enable_itr - Update itr and re-enable MSIX interrupt @@ -1495,70 +1649,51 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) { struct i40e_hw *hw = &vsi->back->hw; - bool rx = false, tx = false; - u32 rxval, txval; - int idx = q_vector->v_idx; - int rx_itr_setting, tx_itr_setting; - - /* avoid dynamic calculation if in countdown mode OR if - * all dynamic is disabled - */ - rxval = txval = i40e_buildreg_itr(I40E_ITR_NONE, 0); - - rx_itr_setting = get_rx_itr(vsi, idx); - tx_itr_setting = get_tx_itr(vsi, idx); + u32 intval; - if (q_vector->itr_countdown > 0 || - (!ITR_IS_DYNAMIC(rx_itr_setting) && - !ITR_IS_DYNAMIC(tx_itr_setting))) { - goto enable_int; - } - - if (ITR_IS_DYNAMIC(rx_itr_setting)) { - rx = i40e_set_new_dynamic_itr(&q_vector->rx); - rxval = i40e_buildreg_itr(I40E_RX_ITR, q_vector->rx.itr); - } + /* These will do nothing if dynamic updates are not enabled */ + i40e_update_itr(q_vector, &q_vector->tx); + i40e_update_itr(q_vector, &q_vector->rx); - if (ITR_IS_DYNAMIC(tx_itr_setting)) { - tx = i40e_set_new_dynamic_itr(&q_vector->tx); - txval = i40e_buildreg_itr(I40E_TX_ITR, q_vector->tx.itr); - } - - if (rx || tx) { - /* get the higher of the two ITR adjustments and - * use the same value for both ITR registers - * when in adaptive mode (Rx and/or Tx) - */ - u16 itr = max(q_vector->tx.itr, q_vector->rx.itr); - - q_vector->tx.itr = q_vector->rx.itr = itr; - txval = i40e_buildreg_itr(I40E_TX_ITR, itr); - tx = true; - rxval = i40e_buildreg_itr(I40E_RX_ITR, itr); - rx = true; - } - - /* only need to enable the interrupt once, but need - * to possibly update both ITR values + /* This block of logic allows us to get away with only updating + * one ITR value with each interrupt. The idea is to perform a + * pseudo-lazy update with the following criteria. + * + * 1. Rx is given higher priority than Tx if both are in same state + * 2. If we must reduce an ITR that is given highest priority. + * 3. We then give priority to increasing ITR based on amount. */ - if (rx) { - /* set the INTENA_MSK_MASK so that this first write - * won't actually enable the interrupt, instead just - * updating the ITR (it's bit 31 PF and VF) + if (q_vector->rx.target_itr < q_vector->rx.current_itr) { + /* Rx ITR needs to be reduced, this is highest priority */ + intval = i40e_buildreg_itr(I40E_RX_ITR, + q_vector->rx.target_itr); + q_vector->rx.current_itr = q_vector->rx.target_itr; + q_vector->itr_countdown = ITR_COUNTDOWN_START; + } else if ((q_vector->tx.target_itr < q_vector->tx.current_itr) || + ((q_vector->rx.target_itr - q_vector->rx.current_itr) < + (q_vector->tx.target_itr - q_vector->tx.current_itr))) { + /* Tx ITR needs to be reduced, this is second priority + * Tx ITR needs to be increased more than Rx, fourth priority */ - rxval |= BIT(31); - /* don't check _DOWN because interrupt isn't being enabled */ - wr32(hw, INTREG(q_vector->reg_idx), rxval); + intval = i40e_buildreg_itr(I40E_TX_ITR, + q_vector->tx.target_itr); + q_vector->tx.current_itr = q_vector->tx.target_itr; + q_vector->itr_countdown = ITR_COUNTDOWN_START; + } else if (q_vector->rx.current_itr != q_vector->rx.target_itr) { + /* Rx ITR needs to be increased, third priority */ + intval = i40e_buildreg_itr(I40E_RX_ITR, + q_vector->rx.target_itr); + q_vector->rx.current_itr = q_vector->rx.target_itr; + q_vector->itr_countdown = ITR_COUNTDOWN_START; + } else { + /* No ITR update, lowest priority */ + intval = i40e_buildreg_itr(I40E_ITR_NONE, 0); + if (q_vector->itr_countdown) + q_vector->itr_countdown--; } -enable_int: if (!test_bit(__I40E_VSI_DOWN, vsi->state)) - wr32(hw, INTREG(q_vector->reg_idx), txval); - - if (q_vector->itr_countdown) - q_vector->itr_countdown--; - else - q_vector->itr_countdown = ITR_COUNTDOWN_START; + wr32(hw, INTREG(q_vector->reg_idx), intval); } /** diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h index 7798a6645c3f..9129447d079b 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h @@ -28,31 +28,35 @@ #define _I40E_TXRX_H_ /* Interrupt Throttling and Rate Limiting Goodies */ - -#define I40E_MAX_ITR 0x0FF0 /* reg uses 2 usec resolution */ -#define I40E_MIN_ITR 0x0001 /* reg uses 2 usec resolution */ -#define I40E_ITR_100K 0x0005 -#define I40E_ITR_50K 0x000A -#define I40E_ITR_20K 0x0019 -#define I40E_ITR_18K 0x001B -#define I40E_ITR_8K 0x003E -#define I40E_ITR_4K 0x007A -#define I40E_MAX_INTRL 0x3B /* reg uses 4 usec resolution */ -#define I40E_ITR_RX_DEF (ITR_REG_TO_USEC(I40E_ITR_20K) | \ - I40E_ITR_DYNAMIC) -#define I40E_ITR_TX_DEF (ITR_REG_TO_USEC(I40E_ITR_20K) | \ - I40E_ITR_DYNAMIC) -#define I40E_ITR_DYNAMIC 0x8000 /* use top bit as a flag */ -#define I40E_MIN_INT_RATE 250 /* ~= 1000000 / (I40E_MAX_ITR * 2) */ -#define I40E_MAX_INT_RATE 500000 /* == 1000000 / (I40E_MIN_ITR * 2) */ #define I40E_DEFAULT_IRQ_WORK 256 -#define ITR_TO_REG(setting) ((setting & ~I40E_ITR_DYNAMIC) >> 1) -#define ITR_IS_DYNAMIC(setting) (!!(setting & I40E_ITR_DYNAMIC)) -#define ITR_REG_TO_USEC(itr_reg) (itr_reg << 1) + +/* The datasheet for the X710 and XL710 indicate that the maximum value for + * the ITR is 8160usec which is then called out as 0xFF0 with a 2usec + * resolution. 8160 is 0x1FE0 when written out in hex. So instead of storing + * the register value which is divided by 2 lets use the actual values and + * avoid an excessive amount of translation. + */ +#define I40E_ITR_DYNAMIC 0x8000 /* use top bit as a flag */ +#define I40E_ITR_MASK 0x1FFE /* mask for ITR register value */ +#define I40E_MIN_ITR 2 /* reg uses 2 usec resolution */ +#define I40E_ITR_100K 10 /* all values below must be even */ +#define I40E_ITR_50K 20 +#define I40E_ITR_20K 50 +#define I40E_ITR_18K 60 +#define I40E_ITR_8K 122 +#define I40E_MAX_ITR 8160 /* maximum value as per datasheet */ +#define ITR_TO_REG(setting) ((setting) & ~I40E_ITR_DYNAMIC) +#define ITR_REG_ALIGN(setting) __ALIGN_MASK(setting, ~I40E_ITR_MASK) +#define ITR_IS_DYNAMIC(setting) (!!((setting) & I40E_ITR_DYNAMIC)) + +#define I40E_ITR_RX_DEF (I40E_ITR_20K | I40E_ITR_DYNAMIC) +#define I40E_ITR_TX_DEF (I40E_ITR_20K | I40E_ITR_DYNAMIC) + /* 0x40 is the enable bit for interrupt rate limiting, and must be set if * the value of the rate limit is non-zero */ #define INTRL_ENA BIT(6) +#define I40E_MAX_INTRL 0x3B /* reg uses 4 usec resolution */ #define INTRL_REG_TO_USEC(intrl) ((intrl & ~INTRL_ENA) << 2) #define INTRL_USEC_TO_REG(set) ((set) ? ((set) >> 2) | INTRL_ENA : 0) #define I40E_INTRL_8K 125 /* 8000 ints/sec */ @@ -362,8 +366,7 @@ struct i40e_ring { * these values always store the USER setting, and must be converted * before programming to a register. */ - u16 rx_itr_setting; - u16 tx_itr_setting; + u16 itr_setting; u16 count; /* Number of descriptors */ u16 reg_idx; /* HW register index of the ring */ @@ -425,21 +428,21 @@ static inline void clear_ring_build_skb_enabled(struct i40e_ring *ring) ring->flags &= ~I40E_RXR_FLAGS_BUILD_SKB_ENABLED; } -enum i40e_latency_range { - I40E_LOWEST_LATENCY = 0, - I40E_LOW_LATENCY = 1, - I40E_BULK_LATENCY = 2, -}; +#define I40E_ITR_ADAPTIVE_MIN_INC 0x0002 +#define I40E_ITR_ADAPTIVE_MIN_USECS 0x0002 +#define I40E_ITR_ADAPTIVE_MAX_USECS 0x007e +#define I40E_ITR_ADAPTIVE_LATENCY 0x8000 +#define I40E_ITR_ADAPTIVE_BULK 0x0000 +#define ITR_IS_BULK(x) (!((x) & I40E_ITR_ADAPTIVE_LATENCY)) struct i40e_ring_container { - /* array of pointers to rings */ - struct i40e_ring *ring; + struct i40e_ring *ring; /* pointer to linked list of ring(s) */ + unsigned long next_update; /* jiffies value of next update */ unsigned int total_bytes; /* total bytes processed this int */ unsigned int total_packets; /* total packets processed this int */ - unsigned long last_itr_update; /* jiffies of last ITR update */ u16 count; - enum i40e_latency_range latency_range; - u16 itr; + u16 target_itr; /* target ITR setting for ring(s) */ + u16 current_itr; /* current ITR setting for ring(s) */ }; /* iterator for handling rings in ring container */ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h index 9690c1ea019e..e46555ad7122 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf.h +++ b/drivers/net/ethernet/intel/i40evf/i40evf.h @@ -52,7 +52,10 @@ #include <linux/socket.h> #include <linux/jiffies.h> #include <net/ip6_checksum.h> +#include <net/pkt_cls.h> #include <net/udp.h> +#include <net/tc_act/tc_gact.h> +#include <net/tc_act/tc_mirred.h> #include "i40e_type.h" #include <linux/avf/virtchnl.h> @@ -106,6 +109,7 @@ struct i40e_vsi { #define I40EVF_HKEY_ARRAY_SIZE ((I40E_VFQF_HKEY_MAX_INDEX + 1) * 4) #define I40EVF_HLUT_ARRAY_SIZE ((I40E_VFQF_HLUT_MAX_INDEX + 1) * 4) +#define I40EVF_MBPS_DIVISOR 125000 /* divisor to convert to Mbps */ /* MAX_MSIX_Q_VECTORS of these are allocated, * but we only use one per queue-specific vector. @@ -117,9 +121,8 @@ struct i40e_q_vector { struct i40e_ring_container rx; struct i40e_ring_container tx; u32 ring_mask; + u8 itr_countdown; /* when 0 should adjust adaptive ITR */ u8 num_ringpairs; /* total number of ring pairs in vector */ -#define ITR_COUNTDOWN_START 100 - u8 itr_countdown; /* when 0 or 1 update ITR */ u16 v_idx; /* index in the vsi->q_vector array. */ u16 reg_idx; /* register index of the interrupt */ char name[IFNAMSIZ + 15]; @@ -169,6 +172,28 @@ struct i40evf_vlan_filter { bool add; /* filter needs to be added */ }; +#define I40EVF_MAX_TRAFFIC_CLASS 4 +/* State of traffic class creation */ +enum i40evf_tc_state_t { + __I40EVF_TC_INVALID, /* no traffic class, default state */ + __I40EVF_TC_RUNNING, /* traffic classes have been created */ +}; + +/* channel info */ +struct i40evf_channel_config { + struct virtchnl_channel_info ch_info[I40EVF_MAX_TRAFFIC_CLASS]; + enum i40evf_tc_state_t state; + u8 total_qps; +}; + +/* State of cloud filter */ +enum i40evf_cloud_filter_state_t { + __I40EVF_CF_INVALID, /* cloud filter not added */ + __I40EVF_CF_ADD_PENDING, /* cloud filter pending add by the PF */ + __I40EVF_CF_DEL_PENDING, /* cloud filter pending del by the PF */ + __I40EVF_CF_ACTIVE, /* cloud filter is active */ +}; + /* Driver state. The order of these is important! */ enum i40evf_state_t { __I40EVF_STARTUP, /* driver loaded, probe complete */ @@ -190,6 +215,36 @@ enum i40evf_critical_section_t { __I40EVF_IN_REMOVE_TASK, /* device being removed */ }; +#define I40EVF_CLOUD_FIELD_OMAC 0x01 +#define I40EVF_CLOUD_FIELD_IMAC 0x02 +#define I40EVF_CLOUD_FIELD_IVLAN 0x04 +#define I40EVF_CLOUD_FIELD_TEN_ID 0x08 +#define I40EVF_CLOUD_FIELD_IIP 0x10 + +#define I40EVF_CF_FLAGS_OMAC I40EVF_CLOUD_FIELD_OMAC +#define I40EVF_CF_FLAGS_IMAC I40EVF_CLOUD_FIELD_IMAC +#define I40EVF_CF_FLAGS_IMAC_IVLAN (I40EVF_CLOUD_FIELD_IMAC |\ + I40EVF_CLOUD_FIELD_IVLAN) +#define I40EVF_CF_FLAGS_IMAC_TEN_ID (I40EVF_CLOUD_FIELD_IMAC |\ + I40EVF_CLOUD_FIELD_TEN_ID) +#define I40EVF_CF_FLAGS_OMAC_TEN_ID_IMAC (I40EVF_CLOUD_FIELD_OMAC |\ + I40EVF_CLOUD_FIELD_IMAC |\ + I40EVF_CLOUD_FIELD_TEN_ID) +#define I40EVF_CF_FLAGS_IMAC_IVLAN_TEN_ID (I40EVF_CLOUD_FIELD_IMAC |\ + I40EVF_CLOUD_FIELD_IVLAN |\ + I40EVF_CLOUD_FIELD_TEN_ID) +#define I40EVF_CF_FLAGS_IIP I40E_CLOUD_FIELD_IIP + +/* bookkeeping of cloud filters */ +struct i40evf_cloud_filter { + enum i40evf_cloud_filter_state_t state; + struct list_head list; + struct virtchnl_filter f; + unsigned long cookie; + bool del; /* filter needs to be deleted */ + bool add; /* filter needs to be added */ +}; + /* board specific private data structure */ struct i40evf_adapter { struct timer_list watchdog_timer; @@ -241,6 +296,7 @@ struct i40evf_adapter { #define I40EVF_FLAG_ALLMULTI_ON BIT(14) #define I40EVF_FLAG_LEGACY_RX BIT(15) #define I40EVF_FLAG_REINIT_ITR_NEEDED BIT(16) +#define I40EVF_FLAG_QUEUES_DISABLED BIT(17) /* duplicates for common code */ #define I40E_FLAG_DCB_ENABLED 0 #define I40E_FLAG_RX_CSUM_ENABLED I40EVF_FLAG_RX_CSUM_ENABLED @@ -269,6 +325,10 @@ struct i40evf_adapter { #define I40EVF_FLAG_AQ_RELEASE_ALLMULTI BIT(18) #define I40EVF_FLAG_AQ_ENABLE_VLAN_STRIPPING BIT(19) #define I40EVF_FLAG_AQ_DISABLE_VLAN_STRIPPING BIT(20) +#define I40EVF_FLAG_AQ_ENABLE_CHANNELS BIT(21) +#define I40EVF_FLAG_AQ_DISABLE_CHANNELS BIT(22) +#define I40EVF_FLAG_AQ_ADD_CLOUD_FILTER BIT(23) +#define I40EVF_FLAG_AQ_DEL_CLOUD_FILTER BIT(24) /* OS defined structs */ struct net_device *netdev; @@ -314,6 +374,13 @@ struct i40evf_adapter { u16 rss_lut_size; u8 *rss_key; u8 *rss_lut; + /* ADQ related members */ + struct i40evf_channel_config ch_config; + u8 num_tc; + struct list_head cloud_filter_list; + /* lock to protest access to the cloud filter list */ + spinlock_t cloud_filter_list_lock; + u16 num_cloud_filters; }; @@ -380,4 +447,8 @@ void i40evf_notify_client_message(struct i40e_vsi *vsi, u8 *msg, u16 len); void i40evf_notify_client_l2_params(struct i40e_vsi *vsi); void i40evf_notify_client_open(struct i40e_vsi *vsi); void i40evf_notify_client_close(struct i40e_vsi *vsi, bool reset); +void i40evf_enable_channels(struct i40evf_adapter *adapter); +void i40evf_disable_channels(struct i40evf_adapter *adapter); +void i40evf_add_cloud_filter(struct i40evf_adapter *adapter); +void i40evf_del_cloud_filter(struct i40evf_adapter *adapter); #endif /* _I40EVF_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c index e2d8aa19d205..e6793255de0b 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c @@ -457,14 +457,14 @@ static int __i40evf_get_coalesce(struct net_device *netdev, rx_ring = &adapter->rx_rings[queue]; tx_ring = &adapter->tx_rings[queue]; - if (ITR_IS_DYNAMIC(rx_ring->rx_itr_setting)) + if (ITR_IS_DYNAMIC(rx_ring->itr_setting)) ec->use_adaptive_rx_coalesce = 1; - if (ITR_IS_DYNAMIC(tx_ring->tx_itr_setting)) + if (ITR_IS_DYNAMIC(tx_ring->itr_setting)) ec->use_adaptive_tx_coalesce = 1; - ec->rx_coalesce_usecs = rx_ring->rx_itr_setting & ~I40E_ITR_DYNAMIC; - ec->tx_coalesce_usecs = tx_ring->tx_itr_setting & ~I40E_ITR_DYNAMIC; + ec->rx_coalesce_usecs = rx_ring->itr_setting & ~I40E_ITR_DYNAMIC; + ec->tx_coalesce_usecs = tx_ring->itr_setting & ~I40E_ITR_DYNAMIC; return 0; } @@ -502,7 +502,7 @@ static int i40evf_get_per_queue_coalesce(struct net_device *netdev, /** * i40evf_set_itr_per_queue - set ITR values for specific queue - * @vsi: the VSI to set values for + * @adapter: the VF adapter struct to set values for * @ec: coalesce settings from ethtool * @queue: the queue to modify * @@ -514,33 +514,29 @@ static void i40evf_set_itr_per_queue(struct i40evf_adapter *adapter, { struct i40e_ring *rx_ring = &adapter->rx_rings[queue]; struct i40e_ring *tx_ring = &adapter->tx_rings[queue]; - struct i40e_vsi *vsi = &adapter->vsi; - struct i40e_hw *hw = &adapter->hw; struct i40e_q_vector *q_vector; - u16 vector; - rx_ring->rx_itr_setting = ec->rx_coalesce_usecs; - tx_ring->tx_itr_setting = ec->tx_coalesce_usecs; + rx_ring->itr_setting = ITR_REG_ALIGN(ec->rx_coalesce_usecs); + tx_ring->itr_setting = ITR_REG_ALIGN(ec->tx_coalesce_usecs); - rx_ring->rx_itr_setting |= I40E_ITR_DYNAMIC; + rx_ring->itr_setting |= I40E_ITR_DYNAMIC; if (!ec->use_adaptive_rx_coalesce) - rx_ring->rx_itr_setting ^= I40E_ITR_DYNAMIC; + rx_ring->itr_setting ^= I40E_ITR_DYNAMIC; - tx_ring->tx_itr_setting |= I40E_ITR_DYNAMIC; + tx_ring->itr_setting |= I40E_ITR_DYNAMIC; if (!ec->use_adaptive_tx_coalesce) - tx_ring->tx_itr_setting ^= I40E_ITR_DYNAMIC; + tx_ring->itr_setting ^= I40E_ITR_DYNAMIC; q_vector = rx_ring->q_vector; - q_vector->rx.itr = ITR_TO_REG(rx_ring->rx_itr_setting); - vector = vsi->base_vector + q_vector->v_idx; - wr32(hw, I40E_VFINT_ITRN1(I40E_RX_ITR, vector - 1), q_vector->rx.itr); + q_vector->rx.target_itr = ITR_TO_REG(rx_ring->itr_setting); q_vector = tx_ring->q_vector; - q_vector->tx.itr = ITR_TO_REG(tx_ring->tx_itr_setting); - vector = vsi->base_vector + q_vector->v_idx; - wr32(hw, I40E_VFINT_ITRN1(I40E_TX_ITR, vector - 1), q_vector->tx.itr); + q_vector->tx.target_itr = ITR_TO_REG(tx_ring->itr_setting); - i40e_flush(hw); + /* The interrupt handler itself will take care of programming + * the Tx and Rx ITR values based on the values we have entered + * into the q_vector, no need to write the values now. + */ } /** @@ -565,8 +561,8 @@ static int __i40evf_set_coalesce(struct net_device *netdev, if (ec->rx_coalesce_usecs == 0) { if (ec->use_adaptive_rx_coalesce) netif_info(adapter, drv, netdev, "rx-usecs=0, need to disable adaptive-rx for a complete disable\n"); - } else if ((ec->rx_coalesce_usecs < (I40E_MIN_ITR << 1)) || - (ec->rx_coalesce_usecs > (I40E_MAX_ITR << 1))) { + } else if ((ec->rx_coalesce_usecs < I40E_MIN_ITR) || + (ec->rx_coalesce_usecs > I40E_MAX_ITR)) { netif_info(adapter, drv, netdev, "Invalid value, rx-usecs range is 0-8160\n"); return -EINVAL; } @@ -575,8 +571,8 @@ static int __i40evf_set_coalesce(struct net_device *netdev, if (ec->tx_coalesce_usecs == 0) { if (ec->use_adaptive_tx_coalesce) netif_info(adapter, drv, netdev, "tx-usecs=0, need to disable adaptive-tx for a complete disable\n"); - } else if ((ec->tx_coalesce_usecs < (I40E_MIN_ITR << 1)) || - (ec->tx_coalesce_usecs > (I40E_MAX_ITR << 1))) { + } else if ((ec->tx_coalesce_usecs < I40E_MIN_ITR) || + (ec->tx_coalesce_usecs > I40E_MAX_ITR)) { netif_info(adapter, drv, netdev, "Invalid value, tx-usecs range is 0-8160\n"); return -EINVAL; } @@ -699,6 +695,12 @@ static int i40evf_set_channels(struct net_device *netdev, return -EINVAL; } + if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) && + adapter->num_tc) { + dev_info(&adapter->pdev->dev, "Cannot set channels since ADq is enabled.\n"); + return -EINVAL; + } + /* All of these should have already been checked by ethtool before this * even gets to us, but just to be sure. */ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index 16989ad2ca90..dae121877935 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -353,11 +353,12 @@ i40evf_map_vector_to_rxq(struct i40evf_adapter *adapter, int v_idx, int r_idx) rx_ring->vsi = &adapter->vsi; q_vector->rx.ring = rx_ring; q_vector->rx.count++; - q_vector->rx.latency_range = I40E_LOW_LATENCY; - q_vector->rx.itr = ITR_TO_REG(rx_ring->rx_itr_setting); + q_vector->rx.next_update = jiffies + 1; + q_vector->rx.target_itr = ITR_TO_REG(rx_ring->itr_setting); q_vector->ring_mask |= BIT(r_idx); - q_vector->itr_countdown = ITR_COUNTDOWN_START; - wr32(hw, I40E_VFINT_ITRN1(I40E_RX_ITR, v_idx - 1), q_vector->rx.itr); + wr32(hw, I40E_VFINT_ITRN1(I40E_RX_ITR, q_vector->reg_idx), + q_vector->rx.current_itr); + q_vector->rx.current_itr = q_vector->rx.target_itr; } /** @@ -378,11 +379,12 @@ i40evf_map_vector_to_txq(struct i40evf_adapter *adapter, int v_idx, int t_idx) tx_ring->vsi = &adapter->vsi; q_vector->tx.ring = tx_ring; q_vector->tx.count++; - q_vector->tx.latency_range = I40E_LOW_LATENCY; - q_vector->tx.itr = ITR_TO_REG(tx_ring->tx_itr_setting); - q_vector->itr_countdown = ITR_COUNTDOWN_START; + q_vector->tx.next_update = jiffies + 1; + q_vector->tx.target_itr = ITR_TO_REG(tx_ring->itr_setting); q_vector->num_ringpairs++; - wr32(hw, I40E_VFINT_ITRN1(I40E_TX_ITR, v_idx - 1), q_vector->tx.itr); + wr32(hw, I40E_VFINT_ITRN1(I40E_TX_ITR, q_vector->reg_idx), + q_vector->tx.target_itr); + q_vector->tx.current_itr = q_vector->tx.target_itr; } /** @@ -783,7 +785,7 @@ static int i40evf_vlan_rx_kill_vid(struct net_device *netdev, **/ static struct i40evf_mac_filter *i40evf_find_filter(struct i40evf_adapter *adapter, - u8 *macaddr) + const u8 *macaddr) { struct i40evf_mac_filter *f; @@ -806,20 +808,18 @@ i40evf_mac_filter *i40evf_find_filter(struct i40evf_adapter *adapter, **/ static struct i40evf_mac_filter *i40evf_add_filter(struct i40evf_adapter *adapter, - u8 *macaddr) + const u8 *macaddr) { struct i40evf_mac_filter *f; if (!macaddr) return NULL; - spin_lock_bh(&adapter->mac_vlan_list_lock); - f = i40evf_find_filter(adapter, macaddr); if (!f) { f = kzalloc(sizeof(*f), GFP_ATOMIC); if (!f) - goto clearout; + return f; ether_addr_copy(f->macaddr, macaddr); @@ -830,8 +830,6 @@ i40evf_mac_filter *i40evf_add_filter(struct i40evf_adapter *adapter, f->remove = false; } -clearout: - spin_unlock_bh(&adapter->mac_vlan_list_lock); return f; } @@ -866,9 +864,10 @@ static int i40evf_set_mac(struct net_device *netdev, void *p) adapter->aq_required |= I40EVF_FLAG_AQ_DEL_MAC_FILTER; } + f = i40evf_add_filter(adapter, addr->sa_data); + spin_unlock_bh(&adapter->mac_vlan_list_lock); - f = i40evf_add_filter(adapter, addr->sa_data); if (f) { ether_addr_copy(hw->mac.addr, addr->sa_data); ether_addr_copy(netdev->dev_addr, adapter->hw.mac.addr); @@ -878,50 +877,64 @@ static int i40evf_set_mac(struct net_device *netdev, void *p) } /** - * i40evf_set_rx_mode - NDO callback to set the netdev filters - * @netdev: network interface device structure - **/ -static void i40evf_set_rx_mode(struct net_device *netdev) + * i40evf_addr_sync - Callback for dev_(mc|uc)_sync to add address + * @netdev: the netdevice + * @addr: address to add + * + * Called by __dev_(mc|uc)_sync when an address needs to be added. We call + * __dev_(uc|mc)_sync from .set_rx_mode and guarantee to hold the hash lock. + */ +static int i40evf_addr_sync(struct net_device *netdev, const u8 *addr) { struct i40evf_adapter *adapter = netdev_priv(netdev); - struct i40evf_mac_filter *f, *ftmp; - struct netdev_hw_addr *uca; - struct netdev_hw_addr *mca; - struct netdev_hw_addr *ha; - - /* add addr if not already in the filter list */ - netdev_for_each_uc_addr(uca, netdev) { - i40evf_add_filter(adapter, uca->addr); - } - netdev_for_each_mc_addr(mca, netdev) { - i40evf_add_filter(adapter, mca->addr); - } - spin_lock_bh(&adapter->mac_vlan_list_lock); - - list_for_each_entry_safe(f, ftmp, &adapter->mac_filter_list, list) { - netdev_for_each_mc_addr(mca, netdev) - if (ether_addr_equal(mca->addr, f->macaddr)) - goto bottom_of_search_loop; - - netdev_for_each_uc_addr(uca, netdev) - if (ether_addr_equal(uca->addr, f->macaddr)) - goto bottom_of_search_loop; + if (i40evf_add_filter(adapter, addr)) + return 0; + else + return -ENOMEM; +} - for_each_dev_addr(netdev, ha) - if (ether_addr_equal(ha->addr, f->macaddr)) - goto bottom_of_search_loop; +/** + * i40evf_addr_unsync - Callback for dev_(mc|uc)_sync to remove address + * @netdev: the netdevice + * @addr: address to add + * + * Called by __dev_(mc|uc)_sync when an address needs to be removed. We call + * __dev_(uc|mc)_sync from .set_rx_mode and guarantee to hold the hash lock. + */ +static int i40evf_addr_unsync(struct net_device *netdev, const u8 *addr) +{ + struct i40evf_adapter *adapter = netdev_priv(netdev); + struct i40evf_mac_filter *f; - if (ether_addr_equal(f->macaddr, adapter->hw.mac.addr)) - goto bottom_of_search_loop; + /* Under some circumstances, we might receive a request to delete + * our own device address from our uc list. Because we store the + * device address in the VSI's MAC/VLAN filter list, we need to ignore + * such requests and not delete our device address from this list. + */ + if (ether_addr_equal(addr, netdev->dev_addr)) + return 0; - /* f->macaddr wasn't found in uc, mc, or ha list so delete it */ + f = i40evf_find_filter(adapter, addr); + if (f) { f->remove = true; adapter->aq_required |= I40EVF_FLAG_AQ_DEL_MAC_FILTER; - -bottom_of_search_loop: - continue; } + return 0; +} + +/** + * i40evf_set_rx_mode - NDO callback to set the netdev filters + * @netdev: network interface device structure + **/ +static void i40evf_set_rx_mode(struct net_device *netdev) +{ + struct i40evf_adapter *adapter = netdev_priv(netdev); + + spin_lock_bh(&adapter->mac_vlan_list_lock); + __dev_uc_sync(netdev, i40evf_addr_sync, i40evf_addr_unsync); + __dev_mc_sync(netdev, i40evf_addr_sync, i40evf_addr_unsync); + spin_unlock_bh(&adapter->mac_vlan_list_lock); if (netdev->flags & IFF_PROMISC && !(adapter->flags & I40EVF_FLAG_PROMISC_ON)) @@ -936,8 +949,6 @@ bottom_of_search_loop: else if (!(netdev->flags & IFF_ALLMULTI) && adapter->flags & I40EVF_FLAG_ALLMULTI_ON) adapter->aq_required |= I40EVF_FLAG_AQ_RELEASE_ALLMULTI; - - spin_unlock_bh(&adapter->mac_vlan_list_lock); } /** @@ -1025,7 +1036,9 @@ static void i40evf_up_complete(struct i40evf_adapter *adapter) void i40evf_down(struct i40evf_adapter *adapter) { struct net_device *netdev = adapter->netdev; + struct i40evf_vlan_filter *vlf; struct i40evf_mac_filter *f; + struct i40evf_cloud_filter *cf; if (adapter->state <= __I40EVF_DOWN_PENDING) return; @@ -1038,17 +1051,29 @@ void i40evf_down(struct i40evf_adapter *adapter) spin_lock_bh(&adapter->mac_vlan_list_lock); + /* clear the sync flag on all filters */ + __dev_uc_unsync(adapter->netdev, NULL); + __dev_mc_unsync(adapter->netdev, NULL); + /* remove all MAC filters */ list_for_each_entry(f, &adapter->mac_filter_list, list) { f->remove = true; } + /* remove all VLAN filters */ - list_for_each_entry(f, &adapter->vlan_filter_list, list) { - f->remove = true; + list_for_each_entry(vlf, &adapter->vlan_filter_list, list) { + vlf->remove = true; } spin_unlock_bh(&adapter->mac_vlan_list_lock); + /* remove all cloud filters */ + spin_lock_bh(&adapter->cloud_filter_list_lock); + list_for_each_entry(cf, &adapter->cloud_filter_list, list) { + cf->del = true; + } + spin_unlock_bh(&adapter->cloud_filter_list_lock); + if (!(adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED) && adapter->state != __I40EVF_RESETTING) { /* cancel any current operation */ @@ -1059,6 +1084,7 @@ void i40evf_down(struct i40evf_adapter *adapter) */ adapter->aq_required = I40EVF_FLAG_AQ_DEL_MAC_FILTER; adapter->aq_required |= I40EVF_FLAG_AQ_DEL_VLAN_FILTER; + adapter->aq_required |= I40EVF_FLAG_AQ_DEL_CLOUD_FILTER; adapter->aq_required |= I40EVF_FLAG_AQ_DISABLE_QUEUES; } @@ -1144,6 +1170,9 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter) */ if (adapter->num_req_queues) num_active_queues = adapter->num_req_queues; + else if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) && + adapter->num_tc) + num_active_queues = adapter->ch_config.total_qps; else num_active_queues = min_t(int, adapter->vsi_res->num_queue_pairs, @@ -1169,7 +1198,7 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter) tx_ring->netdev = adapter->netdev; tx_ring->dev = &adapter->pdev->dev; tx_ring->count = adapter->tx_desc_count; - tx_ring->tx_itr_setting = I40E_ITR_TX_DEF; + tx_ring->itr_setting = I40E_ITR_TX_DEF; if (adapter->flags & I40EVF_FLAG_WB_ON_ITR_CAPABLE) tx_ring->flags |= I40E_TXR_FLAGS_WB_ON_ITR; @@ -1178,7 +1207,7 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter) rx_ring->netdev = adapter->netdev; rx_ring->dev = &adapter->pdev->dev; rx_ring->count = adapter->rx_desc_count; - rx_ring->rx_itr_setting = I40E_ITR_RX_DEF; + rx_ring->itr_setting = I40E_ITR_RX_DEF; } adapter->num_active_queues = num_active_queues; @@ -1471,6 +1500,16 @@ int i40evf_init_interrupt_scheme(struct i40evf_adapter *adapter) goto err_alloc_q_vectors; } + /* If we've made it so far while ADq flag being ON, then we haven't + * bailed out anywhere in middle. And ADq isn't just enabled but actual + * resources have been allocated in the reset path. + * Now we can truly claim that ADq is enabled. + */ + if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) && + adapter->num_tc) + dev_info(&adapter->pdev->dev, "ADq Enabled, %u TCs created", + adapter->num_tc); + dev_info(&adapter->pdev->dev, "Multiqueue %s: Queue pair count = %u", (adapter->num_active_queues > 1) ? "Enabled" : "Disabled", adapter->num_active_queues); @@ -1712,6 +1751,27 @@ static void i40evf_watchdog_task(struct work_struct *work) i40evf_set_promiscuous(adapter, 0); goto watchdog_done; } + + if (adapter->aq_required & I40EVF_FLAG_AQ_ENABLE_CHANNELS) { + i40evf_enable_channels(adapter); + goto watchdog_done; + } + + if (adapter->aq_required & I40EVF_FLAG_AQ_DISABLE_CHANNELS) { + i40evf_disable_channels(adapter); + goto watchdog_done; + } + + if (adapter->aq_required & I40EVF_FLAG_AQ_ADD_CLOUD_FILTER) { + i40evf_add_cloud_filter(adapter); + goto watchdog_done; + } + + if (adapter->aq_required & I40EVF_FLAG_AQ_DEL_CLOUD_FILTER) { + i40evf_del_cloud_filter(adapter); + goto watchdog_done; + } + schedule_delayed_work(&adapter->client_task, msecs_to_jiffies(5)); if (adapter->state == __I40EVF_RUNNING) @@ -1735,6 +1795,7 @@ static void i40evf_disable_vf(struct i40evf_adapter *adapter) { struct i40evf_mac_filter *f, *ftmp; struct i40evf_vlan_filter *fv, *fvtmp; + struct i40evf_cloud_filter *cf, *cftmp; adapter->flags |= I40EVF_FLAG_PF_COMMS_FAILED; @@ -1756,7 +1817,7 @@ static void i40evf_disable_vf(struct i40evf_adapter *adapter) spin_lock_bh(&adapter->mac_vlan_list_lock); - /* Delete all of the filters, both MAC and VLAN. */ + /* Delete all of the filters */ list_for_each_entry_safe(f, ftmp, &adapter->mac_filter_list, list) { list_del(&f->list); kfree(f); @@ -1769,6 +1830,14 @@ static void i40evf_disable_vf(struct i40evf_adapter *adapter) spin_unlock_bh(&adapter->mac_vlan_list_lock); + spin_lock_bh(&adapter->cloud_filter_list_lock); + list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list, list) { + list_del(&cf->list); + kfree(cf); + adapter->num_cloud_filters--; + } + spin_unlock_bh(&adapter->cloud_filter_list_lock); + i40evf_free_misc_irq(adapter); i40evf_reset_interrupt_capability(adapter); i40evf_free_queues(adapter); @@ -1798,9 +1867,11 @@ static void i40evf_reset_task(struct work_struct *work) struct i40evf_adapter *adapter = container_of(work, struct i40evf_adapter, reset_task); + struct virtchnl_vf_resource *vfres = adapter->vf_res; struct net_device *netdev = adapter->netdev; struct i40e_hw *hw = &adapter->hw; struct i40evf_vlan_filter *vlf; + struct i40evf_cloud_filter *cf; struct i40evf_mac_filter *f; u32 reg_val; int i = 0, err; @@ -1893,6 +1964,7 @@ continue_reset: i40evf_free_all_rx_resources(adapter); i40evf_free_all_tx_resources(adapter); + adapter->flags |= I40EVF_FLAG_QUEUES_DISABLED; /* kill and reinit the admin queue */ i40evf_shutdown_adminq(hw); adapter->current_op = VIRTCHNL_OP_UNKNOWN; @@ -1924,8 +1996,19 @@ continue_reset: spin_unlock_bh(&adapter->mac_vlan_list_lock); + /* check if TCs are running and re-add all cloud filters */ + spin_lock_bh(&adapter->cloud_filter_list_lock); + if ((vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) && + adapter->num_tc) { + list_for_each_entry(cf, &adapter->cloud_filter_list, list) { + cf->add = true; + } + } + spin_unlock_bh(&adapter->cloud_filter_list_lock); + adapter->aq_required |= I40EVF_FLAG_AQ_ADD_MAC_FILTER; adapter->aq_required |= I40EVF_FLAG_AQ_ADD_VLAN_FILTER; + adapter->aq_required |= I40EVF_FLAG_AQ_ADD_CLOUD_FILTER; i40evf_misc_irq_enable(adapter); mod_timer(&adapter->watchdog_timer, jiffies + 2); @@ -2191,6 +2274,713 @@ void i40evf_free_all_rx_resources(struct i40evf_adapter *adapter) } /** + * i40evf_validate_tx_bandwidth - validate the max Tx bandwidth + * @adapter: board private structure + * @max_tx_rate: max Tx bw for a tc + **/ +static int i40evf_validate_tx_bandwidth(struct i40evf_adapter *adapter, + u64 max_tx_rate) +{ + int speed = 0, ret = 0; + + switch (adapter->link_speed) { + case I40E_LINK_SPEED_40GB: + speed = 40000; + break; + case I40E_LINK_SPEED_25GB: + speed = 25000; + break; + case I40E_LINK_SPEED_20GB: + speed = 20000; + break; + case I40E_LINK_SPEED_10GB: + speed = 10000; + break; + case I40E_LINK_SPEED_1GB: + speed = 1000; + break; + case I40E_LINK_SPEED_100MB: + speed = 100; + break; + default: + break; + } + + if (max_tx_rate > speed) { + dev_err(&adapter->pdev->dev, + "Invalid tx rate specified\n"); + ret = -EINVAL; + } + + return ret; +} + +/** + * i40evf_validate_channel_config - validate queue mapping info + * @adapter: board private structure + * @mqprio_qopt: queue parameters + * + * This function validates if the config provided by the user to + * configure queue channels is valid or not. Returns 0 on a valid + * config. + **/ +static int i40evf_validate_ch_config(struct i40evf_adapter *adapter, + struct tc_mqprio_qopt_offload *mqprio_qopt) +{ + u64 total_max_rate = 0; + int i, num_qps = 0; + u64 tx_rate = 0; + int ret = 0; + + if (mqprio_qopt->qopt.num_tc > I40EVF_MAX_TRAFFIC_CLASS || + mqprio_qopt->qopt.num_tc < 1) + return -EINVAL; + + for (i = 0; i <= mqprio_qopt->qopt.num_tc - 1; i++) { + if (!mqprio_qopt->qopt.count[i] || + mqprio_qopt->qopt.offset[i] != num_qps) + return -EINVAL; + if (mqprio_qopt->min_rate[i]) { + dev_err(&adapter->pdev->dev, + "Invalid min tx rate (greater than 0) specified\n"); + return -EINVAL; + } + /*convert to Mbps */ + tx_rate = div_u64(mqprio_qopt->max_rate[i], + I40EVF_MBPS_DIVISOR); + total_max_rate += tx_rate; + num_qps += mqprio_qopt->qopt.count[i]; + } + if (num_qps > MAX_QUEUES) + return -EINVAL; + + ret = i40evf_validate_tx_bandwidth(adapter, total_max_rate); + return ret; +} + +/** + * i40evf_del_all_cloud_filters - delete all cloud filters + * on the traffic classes + **/ +static void i40evf_del_all_cloud_filters(struct i40evf_adapter *adapter) +{ + struct i40evf_cloud_filter *cf, *cftmp; + + spin_lock_bh(&adapter->cloud_filter_list_lock); + list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list, + list) { + list_del(&cf->list); + kfree(cf); + adapter->num_cloud_filters--; + } + spin_unlock_bh(&adapter->cloud_filter_list_lock); +} + +/** + * __i40evf_setup_tc - configure multiple traffic classes + * @netdev: network interface device structure + * @type_date: tc offload data + * + * This function processes the config information provided by the + * user to configure traffic classes/queue channels and packages the + * information to request the PF to setup traffic classes. + * + * Returns 0 on success. + **/ +static int __i40evf_setup_tc(struct net_device *netdev, void *type_data) +{ + struct tc_mqprio_qopt_offload *mqprio_qopt = type_data; + struct i40evf_adapter *adapter = netdev_priv(netdev); + struct virtchnl_vf_resource *vfres = adapter->vf_res; + u8 num_tc = 0, total_qps = 0; + int ret = 0, netdev_tc = 0; + u64 max_tx_rate; + u16 mode; + int i; + + num_tc = mqprio_qopt->qopt.num_tc; + mode = mqprio_qopt->mode; + + /* delete queue_channel */ + if (!mqprio_qopt->qopt.hw) { + if (adapter->ch_config.state == __I40EVF_TC_RUNNING) { + /* reset the tc configuration */ + netdev_reset_tc(netdev); + adapter->num_tc = 0; + netif_tx_stop_all_queues(netdev); + netif_tx_disable(netdev); + i40evf_del_all_cloud_filters(adapter); + adapter->aq_required = I40EVF_FLAG_AQ_DISABLE_CHANNELS; + goto exit; + } else { + return -EINVAL; + } + } + + /* add queue channel */ + if (mode == TC_MQPRIO_MODE_CHANNEL) { + if (!(vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ)) { + dev_err(&adapter->pdev->dev, "ADq not supported\n"); + return -EOPNOTSUPP; + } + if (adapter->ch_config.state != __I40EVF_TC_INVALID) { + dev_err(&adapter->pdev->dev, "TC configuration already exists\n"); + return -EINVAL; + } + + ret = i40evf_validate_ch_config(adapter, mqprio_qopt); + if (ret) + return ret; + /* Return if same TC config is requested */ + if (adapter->num_tc == num_tc) + return 0; + adapter->num_tc = num_tc; + + for (i = 0; i < I40EVF_MAX_TRAFFIC_CLASS; i++) { + if (i < num_tc) { + adapter->ch_config.ch_info[i].count = + mqprio_qopt->qopt.count[i]; + adapter->ch_config.ch_info[i].offset = + mqprio_qopt->qopt.offset[i]; + total_qps += mqprio_qopt->qopt.count[i]; + max_tx_rate = mqprio_qopt->max_rate[i]; + /* convert to Mbps */ + max_tx_rate = div_u64(max_tx_rate, + I40EVF_MBPS_DIVISOR); + adapter->ch_config.ch_info[i].max_tx_rate = + max_tx_rate; + } else { + adapter->ch_config.ch_info[i].count = 1; + adapter->ch_config.ch_info[i].offset = 0; + } + } + adapter->ch_config.total_qps = total_qps; + netif_tx_stop_all_queues(netdev); + netif_tx_disable(netdev); + adapter->aq_required |= I40EVF_FLAG_AQ_ENABLE_CHANNELS; + netdev_reset_tc(netdev); + /* Report the tc mapping up the stack */ + netdev_set_num_tc(adapter->netdev, num_tc); + for (i = 0; i < I40EVF_MAX_TRAFFIC_CLASS; i++) { + u16 qcount = mqprio_qopt->qopt.count[i]; + u16 qoffset = mqprio_qopt->qopt.offset[i]; + + if (i < num_tc) + netdev_set_tc_queue(netdev, netdev_tc++, qcount, + qoffset); + } + } +exit: + return ret; +} + +/** + * i40evf_parse_cls_flower - Parse tc flower filters provided by kernel + * @adapter: board private structure + * @cls_flower: pointer to struct tc_cls_flower_offload + * @filter: pointer to cloud filter structure + */ +static int i40evf_parse_cls_flower(struct i40evf_adapter *adapter, + struct tc_cls_flower_offload *f, + struct i40evf_cloud_filter *filter) +{ + u16 n_proto_mask = 0; + u16 n_proto_key = 0; + u8 field_flags = 0; + u16 addr_type = 0; + u16 n_proto = 0; + int i = 0; + struct virtchnl_filter *vf = &filter->f; + + if (f->dissector->used_keys & + ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | + BIT(FLOW_DISSECTOR_KEY_BASIC) | + BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_VLAN) | + BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_PORTS) | + BIT(FLOW_DISSECTOR_KEY_ENC_KEYID))) { + dev_err(&adapter->pdev->dev, "Unsupported key used: 0x%x\n", + f->dissector->used_keys); + return -EOPNOTSUPP; + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) { + struct flow_dissector_key_keyid *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ENC_KEYID, + f->mask); + + if (mask->keyid != 0) + field_flags |= I40EVF_CLOUD_FIELD_TEN_ID; + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_dissector_key_basic *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_BASIC, + f->key); + + struct flow_dissector_key_basic *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_BASIC, + f->mask); + n_proto_key = ntohs(key->n_proto); + n_proto_mask = ntohs(mask->n_proto); + + if (n_proto_key == ETH_P_ALL) { + n_proto_key = 0; + n_proto_mask = 0; + } + n_proto = n_proto_key & n_proto_mask; + if (n_proto != ETH_P_IP && n_proto != ETH_P_IPV6) + return -EINVAL; + if (n_proto == ETH_P_IPV6) { + /* specify flow type as TCP IPv6 */ + vf->flow_type = VIRTCHNL_TCP_V6_FLOW; + } + + if (key->ip_proto != IPPROTO_TCP) { + dev_info(&adapter->pdev->dev, "Only TCP transport is supported\n"); + return -EINVAL; + } + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + struct flow_dissector_key_eth_addrs *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ETH_ADDRS, + f->key); + + struct flow_dissector_key_eth_addrs *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ETH_ADDRS, + f->mask); + /* use is_broadcast and is_zero to check for all 0xf or 0 */ + if (!is_zero_ether_addr(mask->dst)) { + if (is_broadcast_ether_addr(mask->dst)) { + field_flags |= I40EVF_CLOUD_FIELD_OMAC; + } else { + dev_err(&adapter->pdev->dev, "Bad ether dest mask %pM\n", + mask->dst); + return I40E_ERR_CONFIG; + } + } + + if (!is_zero_ether_addr(mask->src)) { + if (is_broadcast_ether_addr(mask->src)) { + field_flags |= I40EVF_CLOUD_FIELD_IMAC; + } else { + dev_err(&adapter->pdev->dev, "Bad ether src mask %pM\n", + mask->src); + return I40E_ERR_CONFIG; + } + } + + if (!is_zero_ether_addr(key->dst)) + if (is_valid_ether_addr(key->dst) || + is_multicast_ether_addr(key->dst)) { + /* set the mask if a valid dst_mac address */ + for (i = 0; i < ETH_ALEN; i++) + vf->mask.tcp_spec.dst_mac[i] |= 0xff; + ether_addr_copy(vf->data.tcp_spec.dst_mac, + key->dst); + } + + if (!is_zero_ether_addr(key->src)) + if (is_valid_ether_addr(key->src) || + is_multicast_ether_addr(key->src)) { + /* set the mask if a valid dst_mac address */ + for (i = 0; i < ETH_ALEN; i++) + vf->mask.tcp_spec.src_mac[i] |= 0xff; + ether_addr_copy(vf->data.tcp_spec.src_mac, + key->src); + } + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_dissector_key_vlan *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_VLAN, + f->key); + struct flow_dissector_key_vlan *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_VLAN, + f->mask); + + if (mask->vlan_id) { + if (mask->vlan_id == VLAN_VID_MASK) { + field_flags |= I40EVF_CLOUD_FIELD_IVLAN; + } else { + dev_err(&adapter->pdev->dev, "Bad vlan mask %u\n", + mask->vlan_id); + return I40E_ERR_CONFIG; + } + } + vf->mask.tcp_spec.vlan_id |= cpu_to_be16(0xffff); + vf->data.tcp_spec.vlan_id = cpu_to_be16(key->vlan_id); + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) { + struct flow_dissector_key_control *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_CONTROL, + f->key); + + addr_type = key->addr_type; + } + + if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { + struct flow_dissector_key_ipv4_addrs *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_IPV4_ADDRS, + f->key); + struct flow_dissector_key_ipv4_addrs *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_IPV4_ADDRS, + f->mask); + + if (mask->dst) { + if (mask->dst == cpu_to_be32(0xffffffff)) { + field_flags |= I40EVF_CLOUD_FIELD_IIP; + } else { + dev_err(&adapter->pdev->dev, "Bad ip dst mask 0x%08x\n", + be32_to_cpu(mask->dst)); + return I40E_ERR_CONFIG; + } + } + + if (mask->src) { + if (mask->src == cpu_to_be32(0xffffffff)) { + field_flags |= I40EVF_CLOUD_FIELD_IIP; + } else { + dev_err(&adapter->pdev->dev, "Bad ip src mask 0x%08x\n", + be32_to_cpu(mask->dst)); + return I40E_ERR_CONFIG; + } + } + + if (field_flags & I40EVF_CLOUD_FIELD_TEN_ID) { + dev_info(&adapter->pdev->dev, "Tenant id not allowed for ip filter\n"); + return I40E_ERR_CONFIG; + } + if (key->dst) { + vf->mask.tcp_spec.dst_ip[0] |= cpu_to_be32(0xffffffff); + vf->data.tcp_spec.dst_ip[0] = key->dst; + } + if (key->src) { + vf->mask.tcp_spec.src_ip[0] |= cpu_to_be32(0xffffffff); + vf->data.tcp_spec.src_ip[0] = key->src; + } + } + + if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { + struct flow_dissector_key_ipv6_addrs *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_IPV6_ADDRS, + f->key); + struct flow_dissector_key_ipv6_addrs *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_IPV6_ADDRS, + f->mask); + + /* validate mask, make sure it is not IPV6_ADDR_ANY */ + if (ipv6_addr_any(&mask->dst)) { + dev_err(&adapter->pdev->dev, "Bad ipv6 dst mask 0x%02x\n", + IPV6_ADDR_ANY); + return I40E_ERR_CONFIG; + } + + /* src and dest IPv6 address should not be LOOPBACK + * (0:0:0:0:0:0:0:1) which can be represented as ::1 + */ + if (ipv6_addr_loopback(&key->dst) || + ipv6_addr_loopback(&key->src)) { + dev_err(&adapter->pdev->dev, + "ipv6 addr should not be loopback\n"); + return I40E_ERR_CONFIG; + } + if (!ipv6_addr_any(&mask->dst) || !ipv6_addr_any(&mask->src)) + field_flags |= I40EVF_CLOUD_FIELD_IIP; + + for (i = 0; i < 4; i++) + vf->mask.tcp_spec.dst_ip[i] |= cpu_to_be32(0xffffffff); + memcpy(&vf->data.tcp_spec.dst_ip, &key->dst.s6_addr32, + sizeof(vf->data.tcp_spec.dst_ip)); + for (i = 0; i < 4; i++) + vf->mask.tcp_spec.src_ip[i] |= cpu_to_be32(0xffffffff); + memcpy(&vf->data.tcp_spec.src_ip, &key->src.s6_addr32, + sizeof(vf->data.tcp_spec.src_ip)); + } + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) { + struct flow_dissector_key_ports *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_PORTS, + f->key); + struct flow_dissector_key_ports *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_PORTS, + f->mask); + + if (mask->src) { + if (mask->src == cpu_to_be16(0xffff)) { + field_flags |= I40EVF_CLOUD_FIELD_IIP; + } else { + dev_err(&adapter->pdev->dev, "Bad src port mask %u\n", + be16_to_cpu(mask->src)); + return I40E_ERR_CONFIG; + } + } + + if (mask->dst) { + if (mask->dst == cpu_to_be16(0xffff)) { + field_flags |= I40EVF_CLOUD_FIELD_IIP; + } else { + dev_err(&adapter->pdev->dev, "Bad dst port mask %u\n", + be16_to_cpu(mask->dst)); + return I40E_ERR_CONFIG; + } + } + if (key->dst) { + vf->mask.tcp_spec.dst_port |= cpu_to_be16(0xffff); + vf->data.tcp_spec.dst_port = key->dst; + } + + if (key->src) { + vf->mask.tcp_spec.src_port |= cpu_to_be16(0xffff); + vf->data.tcp_spec.src_port = key->dst; + } + } + vf->field_flags = field_flags; + + return 0; +} + +/** + * i40evf_handle_tclass - Forward to a traffic class on the device + * @adapter: board private structure + * @tc: traffic class index on the device + * @filter: pointer to cloud filter structure + */ +static int i40evf_handle_tclass(struct i40evf_adapter *adapter, u32 tc, + struct i40evf_cloud_filter *filter) +{ + if (tc == 0) + return 0; + if (tc < adapter->num_tc) { + if (!filter->f.data.tcp_spec.dst_port) { + dev_err(&adapter->pdev->dev, + "Specify destination port to redirect to traffic class other than TC0\n"); + return -EINVAL; + } + } + /* redirect to a traffic class on the same device */ + filter->f.action = VIRTCHNL_ACTION_TC_REDIRECT; + filter->f.action_meta = tc; + return 0; +} + +/** + * i40evf_configure_clsflower - Add tc flower filters + * @adapter: board private structure + * @cls_flower: Pointer to struct tc_cls_flower_offload + */ +static int i40evf_configure_clsflower(struct i40evf_adapter *adapter, + struct tc_cls_flower_offload *cls_flower) +{ + int tc = tc_classid_to_hwtc(adapter->netdev, cls_flower->classid); + struct i40evf_cloud_filter *filter = NULL; + int err = 0, count = 50; + + while (test_and_set_bit(__I40EVF_IN_CRITICAL_TASK, + &adapter->crit_section)) { + udelay(1); + if (--count == 0) + return -EINVAL; + } + + if (tc < 0) { + dev_err(&adapter->pdev->dev, "Invalid traffic class\n"); + return -EINVAL; + } + + filter = kzalloc(sizeof(*filter), GFP_KERNEL); + if (!filter) { + err = -ENOMEM; + goto clearout; + } + filter->cookie = cls_flower->cookie; + + /* set the mask to all zeroes to begin with */ + memset(&filter->f.mask.tcp_spec, 0, sizeof(struct virtchnl_l4_spec)); + /* start out with flow type and eth type IPv4 to begin with */ + filter->f.flow_type = VIRTCHNL_TCP_V4_FLOW; + err = i40evf_parse_cls_flower(adapter, cls_flower, filter); + if (err < 0) + goto err; + + err = i40evf_handle_tclass(adapter, tc, filter); + if (err < 0) + goto err; + + /* add filter to the list */ + spin_lock_bh(&adapter->cloud_filter_list_lock); + list_add_tail(&filter->list, &adapter->cloud_filter_list); + adapter->num_cloud_filters++; + filter->add = true; + adapter->aq_required |= I40EVF_FLAG_AQ_ADD_CLOUD_FILTER; + spin_unlock_bh(&adapter->cloud_filter_list_lock); +err: + if (err) + kfree(filter); +clearout: + clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); + return err; +} + +/* i40evf_find_cf - Find the cloud filter in the list + * @adapter: Board private structure + * @cookie: filter specific cookie + * + * Returns ptr to the filter object or NULL. Must be called while holding the + * cloud_filter_list_lock. + */ +static struct i40evf_cloud_filter *i40evf_find_cf(struct i40evf_adapter *adapter, + unsigned long *cookie) +{ + struct i40evf_cloud_filter *filter = NULL; + + if (!cookie) + return NULL; + + list_for_each_entry(filter, &adapter->cloud_filter_list, list) { + if (!memcmp(cookie, &filter->cookie, sizeof(filter->cookie))) + return filter; + } + return NULL; +} + +/** + * i40evf_delete_clsflower - Remove tc flower filters + * @adapter: board private structure + * @cls_flower: Pointer to struct tc_cls_flower_offload + */ +static int i40evf_delete_clsflower(struct i40evf_adapter *adapter, + struct tc_cls_flower_offload *cls_flower) +{ + struct i40evf_cloud_filter *filter = NULL; + int err = 0; + + spin_lock_bh(&adapter->cloud_filter_list_lock); + filter = i40evf_find_cf(adapter, &cls_flower->cookie); + if (filter) { + filter->del = true; + adapter->aq_required |= I40EVF_FLAG_AQ_DEL_CLOUD_FILTER; + } else { + err = -EINVAL; + } + spin_unlock_bh(&adapter->cloud_filter_list_lock); + + return err; +} + +/** + * i40evf_setup_tc_cls_flower - flower classifier offloads + * @netdev: net device to configure + * @type_data: offload data + */ +static int i40evf_setup_tc_cls_flower(struct i40evf_adapter *adapter, + struct tc_cls_flower_offload *cls_flower) +{ + if (cls_flower->common.chain_index) + return -EOPNOTSUPP; + + switch (cls_flower->command) { + case TC_CLSFLOWER_REPLACE: + return i40evf_configure_clsflower(adapter, cls_flower); + case TC_CLSFLOWER_DESTROY: + return i40evf_delete_clsflower(adapter, cls_flower); + case TC_CLSFLOWER_STATS: + return -EOPNOTSUPP; + default: + return -EINVAL; + } +} + +/** + * i40evf_setup_tc_block_cb - block callback for tc + * @type: type of offload + * @type_data: offload data + * @cb_priv: + * + * This function is the block callback for traffic classes + **/ +static int i40evf_setup_tc_block_cb(enum tc_setup_type type, void *type_data, + void *cb_priv) +{ + switch (type) { + case TC_SETUP_CLSFLOWER: + return i40evf_setup_tc_cls_flower(cb_priv, type_data); + default: + return -EOPNOTSUPP; + } +} + +/** + * i40evf_setup_tc_block - register callbacks for tc + * @netdev: network interface device structure + * @f: tc offload data + * + * This function registers block callbacks for tc + * offloads + **/ +static int i40evf_setup_tc_block(struct net_device *dev, + struct tc_block_offload *f) +{ + struct i40evf_adapter *adapter = netdev_priv(dev); + + if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS) + return -EOPNOTSUPP; + + switch (f->command) { + case TC_BLOCK_BIND: + return tcf_block_cb_register(f->block, i40evf_setup_tc_block_cb, + adapter, adapter); + case TC_BLOCK_UNBIND: + tcf_block_cb_unregister(f->block, i40evf_setup_tc_block_cb, + adapter); + return 0; + default: + return -EOPNOTSUPP; + } +} + +/** + * i40evf_setup_tc - configure multiple traffic classes + * @netdev: network interface device structure + * @type: type of offload + * @type_date: tc offload data + * + * This function is the callback to ndo_setup_tc in the + * netdev_ops. + * + * Returns 0 on success + **/ +static int i40evf_setup_tc(struct net_device *netdev, enum tc_setup_type type, + void *type_data) +{ + switch (type) { + case TC_SETUP_QDISC_MQPRIO: + return __i40evf_setup_tc(netdev, type_data); + case TC_SETUP_BLOCK: + return i40evf_setup_tc_block(netdev, type_data); + default: + return -EOPNOTSUPP; + } +} + +/** * i40evf_open - Called when a network interface is made active * @netdev: network interface device structure * @@ -2236,7 +3026,12 @@ static int i40evf_open(struct net_device *netdev) if (err) goto err_req_irq; + spin_lock_bh(&adapter->mac_vlan_list_lock); + i40evf_add_filter(adapter, adapter->hw.mac.addr); + + spin_unlock_bh(&adapter->mac_vlan_list_lock); + i40evf_configure(adapter); i40evf_up_complete(adapter); @@ -2457,6 +3252,7 @@ static const struct net_device_ops i40evf_netdev_ops = { #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = i40evf_netpoll, #endif + .ndo_setup_tc = i40evf_setup_tc, }; /** @@ -2571,6 +3367,9 @@ int i40evf_process_config(struct i40evf_adapter *adapter) if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN) hw_features |= (NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX); + /* Enable cloud filter if ADQ is supported */ + if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) + hw_features |= NETIF_F_HW_TC; netdev->hw_features |= hw_features; @@ -2938,9 +3737,11 @@ static int i40evf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) mutex_init(&hw->aq.arq_mutex); spin_lock_init(&adapter->mac_vlan_list_lock); + spin_lock_init(&adapter->cloud_filter_list_lock); INIT_LIST_HEAD(&adapter->mac_filter_list); INIT_LIST_HEAD(&adapter->vlan_filter_list); + INIT_LIST_HEAD(&adapter->cloud_filter_list); INIT_WORK(&adapter->reset_task, i40evf_reset_task); INIT_WORK(&adapter->adminq_task, i40evf_adminq_task); @@ -3065,7 +3866,9 @@ static void i40evf_remove(struct pci_dev *pdev) { struct net_device *netdev = pci_get_drvdata(pdev); struct i40evf_adapter *adapter = netdev_priv(netdev); + struct i40evf_vlan_filter *vlf, *vlftmp; struct i40evf_mac_filter *f, *ftmp; + struct i40evf_cloud_filter *cf, *cftmp; struct i40e_hw *hw = &adapter->hw; int err; /* Indicate we are in remove and not to run reset_task */ @@ -3087,6 +3890,7 @@ static void i40evf_remove(struct pci_dev *pdev) /* Shut down all the garbage mashers on the detention level */ adapter->state = __I40EVF_REMOVE; adapter->aq_required = 0; + adapter->flags &= ~I40EVF_FLAG_REINIT_ITR_NEEDED; i40evf_request_reset(adapter); msleep(50); /* If the FW isn't responding, kick it once, but only once. */ @@ -3127,13 +3931,21 @@ static void i40evf_remove(struct pci_dev *pdev) list_del(&f->list); kfree(f); } - list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { - list_del(&f->list); - kfree(f); + list_for_each_entry_safe(vlf, vlftmp, &adapter->vlan_filter_list, + list) { + list_del(&vlf->list); + kfree(vlf); } spin_unlock_bh(&adapter->mac_vlan_list_lock); + spin_lock_bh(&adapter->cloud_filter_list_lock); + list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list, list) { + list_del(&cf->list); + kfree(cf); + } + spin_unlock_bh(&adapter->cloud_filter_list_lock); + free_netdev(netdev); pci_disable_pcie_error_reporting(pdev); diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c index 50ce0d6c09ef..3c76c817ca1a 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c @@ -161,7 +161,8 @@ int i40evf_send_vf_config_msg(struct i40evf_adapter *adapter) VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 | VIRTCHNL_VF_OFFLOAD_ENCAP | VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM | - VIRTCHNL_VF_OFFLOAD_REQ_QUEUES; + VIRTCHNL_VF_OFFLOAD_REQ_QUEUES | + VIRTCHNL_VF_OFFLOAD_ADQ; adapter->current_op = VIRTCHNL_OP_GET_VF_RESOURCES; adapter->aq_required &= ~I40EVF_FLAG_AQ_GET_CONFIG; @@ -344,6 +345,7 @@ void i40evf_disable_queues(struct i40evf_adapter *adapter) void i40evf_map_queues(struct i40evf_adapter *adapter) { struct virtchnl_irq_map_info *vimi; + struct virtchnl_vector_map *vecmap; int v_idx, q_vectors, len; struct i40e_q_vector *q_vector; @@ -367,17 +369,22 @@ void i40evf_map_queues(struct i40evf_adapter *adapter) vimi->num_vectors = adapter->num_msix_vectors; /* Queue vectors first */ for (v_idx = 0; v_idx < q_vectors; v_idx++) { - q_vector = adapter->q_vectors + v_idx; - vimi->vecmap[v_idx].vsi_id = adapter->vsi_res->vsi_id; - vimi->vecmap[v_idx].vector_id = v_idx + NONQ_VECS; - vimi->vecmap[v_idx].txq_map = q_vector->ring_mask; - vimi->vecmap[v_idx].rxq_map = q_vector->ring_mask; + q_vector = &adapter->q_vectors[v_idx]; + vecmap = &vimi->vecmap[v_idx]; + + vecmap->vsi_id = adapter->vsi_res->vsi_id; + vecmap->vector_id = v_idx + NONQ_VECS; + vecmap->txq_map = q_vector->ring_mask; + vecmap->rxq_map = q_vector->ring_mask; + vecmap->rxitr_idx = I40E_RX_ITR; + vecmap->txitr_idx = I40E_TX_ITR; } /* Misc vector last - this is only for AdminQ messages */ - vimi->vecmap[v_idx].vsi_id = adapter->vsi_res->vsi_id; - vimi->vecmap[v_idx].vector_id = 0; - vimi->vecmap[v_idx].txq_map = 0; - vimi->vecmap[v_idx].rxq_map = 0; + vecmap = &vimi->vecmap[v_idx]; + vecmap->vsi_id = adapter->vsi_res->vsi_id; + vecmap->vector_id = 0; + vecmap->txq_map = 0; + vecmap->rxq_map = 0; adapter->aq_required &= ~I40EVF_FLAG_AQ_MAP_VECTORS; i40evf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_IRQ_MAP, @@ -459,7 +466,7 @@ void i40evf_add_ether_addrs(struct i40evf_adapter *adapter) more = true; } - veal = kzalloc(len, GFP_KERNEL); + veal = kzalloc(len, GFP_ATOMIC); if (!veal) { spin_unlock_bh(&adapter->mac_vlan_list_lock); return; @@ -532,7 +539,7 @@ void i40evf_del_ether_addrs(struct i40evf_adapter *adapter) (count * sizeof(struct virtchnl_ether_addr)); more = true; } - veal = kzalloc(len, GFP_KERNEL); + veal = kzalloc(len, GFP_ATOMIC); if (!veal) { spin_unlock_bh(&adapter->mac_vlan_list_lock); return; @@ -606,7 +613,7 @@ void i40evf_add_vlans(struct i40evf_adapter *adapter) (count * sizeof(u16)); more = true; } - vvfl = kzalloc(len, GFP_KERNEL); + vvfl = kzalloc(len, GFP_ATOMIC); if (!vvfl) { spin_unlock_bh(&adapter->mac_vlan_list_lock); return; @@ -678,7 +685,7 @@ void i40evf_del_vlans(struct i40evf_adapter *adapter) (count * sizeof(u16)); more = true; } - vvfl = kzalloc(len, GFP_KERNEL); + vvfl = kzalloc(len, GFP_ATOMIC); if (!vvfl) { spin_unlock_bh(&adapter->mac_vlan_list_lock); return; @@ -967,6 +974,205 @@ static void i40evf_print_link_message(struct i40evf_adapter *adapter) } /** + * i40evf_enable_channel + * @adapter: adapter structure + * + * Request that the PF enable channels as specified by + * the user via tc tool. + **/ +void i40evf_enable_channels(struct i40evf_adapter *adapter) +{ + struct virtchnl_tc_info *vti = NULL; + u16 len; + int i; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot configure mqprio, command %d pending\n", + adapter->current_op); + return; + } + + len = (adapter->num_tc * sizeof(struct virtchnl_channel_info)) + + sizeof(struct virtchnl_tc_info); + + vti = kzalloc(len, GFP_KERNEL); + if (!vti) + return; + vti->num_tc = adapter->num_tc; + for (i = 0; i < vti->num_tc; i++) { + vti->list[i].count = adapter->ch_config.ch_info[i].count; + vti->list[i].offset = adapter->ch_config.ch_info[i].offset; + vti->list[i].pad = 0; + vti->list[i].max_tx_rate = + adapter->ch_config.ch_info[i].max_tx_rate; + } + + adapter->ch_config.state = __I40EVF_TC_RUNNING; + adapter->flags |= I40EVF_FLAG_REINIT_ITR_NEEDED; + adapter->current_op = VIRTCHNL_OP_ENABLE_CHANNELS; + adapter->aq_required &= ~I40EVF_FLAG_AQ_ENABLE_CHANNELS; + i40evf_send_pf_msg(adapter, VIRTCHNL_OP_ENABLE_CHANNELS, + (u8 *)vti, len); + kfree(vti); +} + +/** + * i40evf_disable_channel + * @adapter: adapter structure + * + * Request that the PF disable channels that are configured + **/ +void i40evf_disable_channels(struct i40evf_adapter *adapter) +{ + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot configure mqprio, command %d pending\n", + adapter->current_op); + return; + } + + adapter->ch_config.state = __I40EVF_TC_INVALID; + adapter->flags |= I40EVF_FLAG_REINIT_ITR_NEEDED; + adapter->current_op = VIRTCHNL_OP_DISABLE_CHANNELS; + adapter->aq_required &= ~I40EVF_FLAG_AQ_DISABLE_CHANNELS; + i40evf_send_pf_msg(adapter, VIRTCHNL_OP_DISABLE_CHANNELS, + NULL, 0); +} + +/** + * i40evf_print_cloud_filter + * @adapter: adapter structure + * @f: cloud filter to print + * + * Print the cloud filter + **/ +static void i40evf_print_cloud_filter(struct i40evf_adapter *adapter, + struct virtchnl_filter *f) +{ + switch (f->flow_type) { + case VIRTCHNL_TCP_V4_FLOW: + dev_info(&adapter->pdev->dev, "dst_mac: %pM src_mac: %pM vlan_id: %hu dst_ip: %pI4 src_ip %pI4 dst_port %hu src_port %hu\n", + &f->data.tcp_spec.dst_mac, + &f->data.tcp_spec.src_mac, + ntohs(f->data.tcp_spec.vlan_id), + &f->data.tcp_spec.dst_ip[0], + &f->data.tcp_spec.src_ip[0], + ntohs(f->data.tcp_spec.dst_port), + ntohs(f->data.tcp_spec.src_port)); + break; + case VIRTCHNL_TCP_V6_FLOW: + dev_info(&adapter->pdev->dev, "dst_mac: %pM src_mac: %pM vlan_id: %hu dst_ip: %pI6 src_ip %pI6 dst_port %hu src_port %hu\n", + &f->data.tcp_spec.dst_mac, + &f->data.tcp_spec.src_mac, + ntohs(f->data.tcp_spec.vlan_id), + &f->data.tcp_spec.dst_ip, + &f->data.tcp_spec.src_ip, + ntohs(f->data.tcp_spec.dst_port), + ntohs(f->data.tcp_spec.src_port)); + break; + } +} + +/** + * i40evf_add_cloud_filter + * @adapter: adapter structure + * + * Request that the PF add cloud filters as specified + * by the user via tc tool. + **/ +void i40evf_add_cloud_filter(struct i40evf_adapter *adapter) +{ + struct i40evf_cloud_filter *cf; + struct virtchnl_filter *f; + int len = 0, count = 0; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot add cloud filter, command %d pending\n", + adapter->current_op); + return; + } + list_for_each_entry(cf, &adapter->cloud_filter_list, list) { + if (cf->add) { + count++; + break; + } + } + if (!count) { + adapter->aq_required &= ~I40EVF_FLAG_AQ_ADD_CLOUD_FILTER; + return; + } + adapter->current_op = VIRTCHNL_OP_ADD_CLOUD_FILTER; + + len = sizeof(struct virtchnl_filter); + f = kzalloc(len, GFP_KERNEL); + if (!f) + return; + + list_for_each_entry(cf, &adapter->cloud_filter_list, list) { + if (cf->add) { + memcpy(f, &cf->f, sizeof(struct virtchnl_filter)); + cf->add = false; + cf->state = __I40EVF_CF_ADD_PENDING; + i40evf_send_pf_msg(adapter, + VIRTCHNL_OP_ADD_CLOUD_FILTER, + (u8 *)f, len); + } + } + kfree(f); +} + +/** + * i40evf_del_cloud_filter + * @adapter: adapter structure + * + * Request that the PF delete cloud filters as specified + * by the user via tc tool. + **/ +void i40evf_del_cloud_filter(struct i40evf_adapter *adapter) +{ + struct i40evf_cloud_filter *cf, *cftmp; + struct virtchnl_filter *f; + int len = 0, count = 0; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot remove cloud filter, command %d pending\n", + adapter->current_op); + return; + } + list_for_each_entry(cf, &adapter->cloud_filter_list, list) { + if (cf->del) { + count++; + break; + } + } + if (!count) { + adapter->aq_required &= ~I40EVF_FLAG_AQ_DEL_CLOUD_FILTER; + return; + } + adapter->current_op = VIRTCHNL_OP_DEL_CLOUD_FILTER; + + len = sizeof(struct virtchnl_filter); + f = kzalloc(len, GFP_KERNEL); + if (!f) + return; + + list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list, list) { + if (cf->del) { + memcpy(f, &cf->f, sizeof(struct virtchnl_filter)); + cf->del = false; + cf->state = __I40EVF_CF_DEL_PENDING; + i40evf_send_pf_msg(adapter, + VIRTCHNL_OP_DEL_CLOUD_FILTER, + (u8 *)f, len); + } + } + kfree(f); +} + +/** * i40evf_request_reset * @adapter: adapter structure * @@ -1011,14 +1217,25 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, if (adapter->link_up == link_up) break; - /* If we get link up message and start queues before - * our queues are configured it will trigger a TX hang. - * In that case, just ignore the link status message, - * we'll get another one after we enable queues and - * actually prepared to send traffic. - */ - if (link_up && adapter->state != __I40EVF_RUNNING) - break; + if (link_up) { + /* If we get link up message and start queues + * before our queues are configured it will + * trigger a TX hang. In that case, just ignore + * the link status message,we'll get another one + * after we enable queues and actually prepared + * to send traffic. + */ + if (adapter->state != __I40EVF_RUNNING) + break; + + /* For ADq enabled VF, we reconfigure VSIs and + * re-allocate queues. Hence wait till all + * queues are enabled. + */ + if (adapter->flags & + I40EVF_FLAG_QUEUES_DISABLED) + break; + } adapter->link_up = link_up; if (link_up) { @@ -1031,7 +1248,7 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, i40evf_print_link_message(adapter); break; case VIRTCHNL_EVENT_RESET_IMPENDING: - dev_info(&adapter->pdev->dev, "PF reset warning received\n"); + dev_info(&adapter->pdev->dev, "Reset warning received from the PF\n"); if (!(adapter->flags & I40EVF_FLAG_RESET_PENDING)) { adapter->flags |= I40EVF_FLAG_RESET_PENDING; dev_info(&adapter->pdev->dev, "Scheduling reset task\n"); @@ -1063,6 +1280,57 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, dev_err(&adapter->pdev->dev, "Failed to delete MAC filter, error %s\n", i40evf_stat_str(&adapter->hw, v_retval)); break; + case VIRTCHNL_OP_ENABLE_CHANNELS: + dev_err(&adapter->pdev->dev, "Failed to configure queue channels, error %s\n", + i40evf_stat_str(&adapter->hw, v_retval)); + adapter->flags &= ~I40EVF_FLAG_REINIT_ITR_NEEDED; + adapter->ch_config.state = __I40EVF_TC_INVALID; + netdev_reset_tc(netdev); + netif_tx_start_all_queues(netdev); + break; + case VIRTCHNL_OP_DISABLE_CHANNELS: + dev_err(&adapter->pdev->dev, "Failed to disable queue channels, error %s\n", + i40evf_stat_str(&adapter->hw, v_retval)); + adapter->flags &= ~I40EVF_FLAG_REINIT_ITR_NEEDED; + adapter->ch_config.state = __I40EVF_TC_RUNNING; + netif_tx_start_all_queues(netdev); + break; + case VIRTCHNL_OP_ADD_CLOUD_FILTER: { + struct i40evf_cloud_filter *cf, *cftmp; + + list_for_each_entry_safe(cf, cftmp, + &adapter->cloud_filter_list, + list) { + if (cf->state == __I40EVF_CF_ADD_PENDING) { + cf->state = __I40EVF_CF_INVALID; + dev_info(&adapter->pdev->dev, "Failed to add cloud filter, error %s\n", + i40evf_stat_str(&adapter->hw, + v_retval)); + i40evf_print_cloud_filter(adapter, + &cf->f); + list_del(&cf->list); + kfree(cf); + adapter->num_cloud_filters--; + } + } + } + break; + case VIRTCHNL_OP_DEL_CLOUD_FILTER: { + struct i40evf_cloud_filter *cf; + + list_for_each_entry(cf, &adapter->cloud_filter_list, + list) { + if (cf->state == __I40EVF_CF_DEL_PENDING) { + cf->state = __I40EVF_CF_ACTIVE; + dev_info(&adapter->pdev->dev, "Failed to del cloud filter, error %s\n", + i40evf_stat_str(&adapter->hw, + v_retval)); + i40evf_print_cloud_filter(adapter, + &cf->f); + } + } + } + break; default: dev_err(&adapter->pdev->dev, "PF returned error %d (%s) to our request %d\n", v_retval, @@ -1102,6 +1370,7 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, case VIRTCHNL_OP_ENABLE_QUEUES: /* enable transmits */ i40evf_irq_enable(adapter, true); + adapter->flags &= ~I40EVF_FLAG_QUEUES_DISABLED; break; case VIRTCHNL_OP_DISABLE_QUEUES: i40evf_free_all_tx_resources(adapter); @@ -1156,6 +1425,29 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, } } break; + case VIRTCHNL_OP_ADD_CLOUD_FILTER: { + struct i40evf_cloud_filter *cf; + + list_for_each_entry(cf, &adapter->cloud_filter_list, list) { + if (cf->state == __I40EVF_CF_ADD_PENDING) + cf->state = __I40EVF_CF_ACTIVE; + } + } + break; + case VIRTCHNL_OP_DEL_CLOUD_FILTER: { + struct i40evf_cloud_filter *cf, *cftmp; + + list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list, + list) { + if (cf->state == __I40EVF_CF_DEL_PENDING) { + cf->state = __I40EVF_CF_INVALID; + list_del(&cf->list); + kfree(cf); + adapter->num_cloud_filters--; + } + } + } + break; default: if (adapter->current_op && (v_opcode != adapter->current_op)) dev_warn(&adapter->pdev->dev, "Expected response %d from PF, received %d\n", diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 221f15803480..89edb9fae6f0 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -3059,6 +3059,8 @@ static int ixgbe_set_rxfh(struct net_device *netdev, const u32 *indir, for (i = 0; i < reta_entries; i++) adapter->rss_indir_tbl[i] = indir[i]; + + ixgbe_store_reta(adapter); } /* Fill out the rss hash key */ @@ -3067,8 +3069,6 @@ static int ixgbe_set_rxfh(struct net_device *netdev, const u32 *indir, ixgbe_store_key(adapter); } - ixgbe_store_reta(adapter); - return 0; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c index 4242f0213e46..ed4cbe94c355 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c @@ -58,7 +58,6 @@ static bool ixgbe_cache_ring_dcb_sriov(struct ixgbe_adapter *adapter) return false; /* start at VMDq register offset for SR-IOV enabled setups */ - pool = 0; reg_idx = vmdq->offset * __ALIGN_MASK(1, ~vmdq->mask); for (i = 0, pool = 0; i < adapter->num_rx_queues; i++, reg_idx++) { /* If we are greater than indices move to next pool */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 0da5aa2c8aba..b032091022a8 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -7703,7 +7703,8 @@ static void ixgbe_service_task(struct work_struct *work) if (test_bit(__IXGBE_PTP_RUNNING, &adapter->state)) { ixgbe_ptp_overflow_check(adapter); - ixgbe_ptp_rx_hang(adapter); + if (adapter->flags & IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER) + ixgbe_ptp_rx_hang(adapter); ixgbe_ptp_tx_hang(adapter); } diff --git a/drivers/net/ethernet/intel/ixgbevf/ethtool.c b/drivers/net/ethernet/intel/ixgbevf/ethtool.c index 4400e49090b4..e7623fed42da 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ethtool.c +++ b/drivers/net/ethernet/intel/ixgbevf/ethtool.c @@ -94,6 +94,13 @@ static const char ixgbe_gstrings_test[][ETH_GSTRING_LEN] = { #define IXGBEVF_TEST_LEN (sizeof(ixgbe_gstrings_test) / ETH_GSTRING_LEN) +static const char ixgbevf_priv_flags_strings[][ETH_GSTRING_LEN] = { +#define IXGBEVF_PRIV_FLAGS_LEGACY_RX BIT(0) + "legacy-rx", +}; + +#define IXGBEVF_PRIV_FLAGS_STR_LEN ARRAY_SIZE(ixgbevf_priv_flags_strings) + static int ixgbevf_get_link_ksettings(struct net_device *netdev, struct ethtool_link_ksettings *cmd) { @@ -241,6 +248,8 @@ static void ixgbevf_get_drvinfo(struct net_device *netdev, sizeof(drvinfo->version)); strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), sizeof(drvinfo->bus_info)); + + drvinfo->n_priv_flags = IXGBEVF_PRIV_FLAGS_STR_LEN; } static void ixgbevf_get_ringparam(struct net_device *netdev, @@ -392,6 +401,8 @@ static int ixgbevf_get_sset_count(struct net_device *netdev, int stringset) return IXGBEVF_TEST_LEN; case ETH_SS_STATS: return IXGBEVF_STATS_LEN; + case ETH_SS_PRIV_FLAGS: + return IXGBEVF_PRIV_FLAGS_STR_LEN; default: return -EINVAL; } @@ -496,6 +507,10 @@ static void ixgbevf_get_strings(struct net_device *netdev, u32 stringset, p += ETH_GSTRING_LEN; } break; + case ETH_SS_PRIV_FLAGS: + memcpy(data, ixgbevf_priv_flags_strings, + IXGBEVF_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN); + break; } } @@ -888,6 +903,37 @@ static int ixgbevf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, return err; } +static u32 ixgbevf_get_priv_flags(struct net_device *netdev) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + u32 priv_flags = 0; + + if (adapter->flags & IXGBEVF_FLAGS_LEGACY_RX) + priv_flags |= IXGBEVF_PRIV_FLAGS_LEGACY_RX; + + return priv_flags; +} + +static int ixgbevf_set_priv_flags(struct net_device *netdev, u32 priv_flags) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + unsigned int flags = adapter->flags; + + flags &= ~IXGBEVF_FLAGS_LEGACY_RX; + if (priv_flags & IXGBEVF_PRIV_FLAGS_LEGACY_RX) + flags |= IXGBEVF_FLAGS_LEGACY_RX; + + if (flags != adapter->flags) { + adapter->flags = flags; + + /* reset interface to repopulate queues */ + if (netif_running(netdev)) + ixgbevf_reinit_locked(adapter); + } + + return 0; +} + static const struct ethtool_ops ixgbevf_ethtool_ops = { .get_drvinfo = ixgbevf_get_drvinfo, .get_regs_len = ixgbevf_get_regs_len, @@ -909,6 +955,8 @@ static const struct ethtool_ops ixgbevf_ethtool_ops = { .get_rxfh_key_size = ixgbevf_get_rxfh_key_size, .get_rxfh = ixgbevf_get_rxfh, .get_link_ksettings = ixgbevf_get_link_ksettings, + .get_priv_flags = ixgbevf_get_priv_flags, + .set_priv_flags = ixgbevf_set_priv_flags, }; void ixgbevf_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h index f6952425c87d..f65ca156af2d 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h @@ -89,19 +89,15 @@ struct ixgbevf_rx_queue_stats { }; enum ixgbevf_ring_state_t { + __IXGBEVF_RX_3K_BUFFER, + __IXGBEVF_RX_BUILD_SKB_ENABLED, __IXGBEVF_TX_DETECT_HANG, __IXGBEVF_HANG_CHECK_ARMED, }; -#define check_for_tx_hang(ring) \ - test_bit(__IXGBEVF_TX_DETECT_HANG, &(ring)->state) -#define set_check_for_tx_hang(ring) \ - set_bit(__IXGBEVF_TX_DETECT_HANG, &(ring)->state) -#define clear_check_for_tx_hang(ring) \ - clear_bit(__IXGBEVF_TX_DETECT_HANG, &(ring)->state) - struct ixgbevf_ring { struct ixgbevf_ring *next; + struct ixgbevf_q_vector *q_vector; /* backpointer to q_vector */ struct net_device *netdev; struct device *dev; void *desc; /* descriptor ring memory */ @@ -133,7 +129,7 @@ struct ixgbevf_ring { */ u16 reg_idx; int queue_index; /* needed for multiqueue queue management */ -}; +} ____cacheline_internodealigned_in_smp; /* How many Rx Buffers do we bundle into one write to the hardware ? */ #define IXGBEVF_RX_BUFFER_WRITE 16 /* Must be power of 2 */ @@ -156,12 +152,20 @@ struct ixgbevf_ring { /* Supported Rx Buffer Sizes */ #define IXGBEVF_RXBUFFER_256 256 /* Used for packet split */ #define IXGBEVF_RXBUFFER_2048 2048 +#define IXGBEVF_RXBUFFER_3072 3072 #define IXGBEVF_RX_HDR_SIZE IXGBEVF_RXBUFFER_256 -#define IXGBEVF_RX_BUFSZ IXGBEVF_RXBUFFER_2048 #define MAXIMUM_ETHERNET_VLAN_SIZE (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN) +#define IXGBEVF_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) +#if (PAGE_SIZE < 8192) +#define IXGBEVF_MAX_FRAME_BUILD_SKB \ + (SKB_WITH_OVERHEAD(IXGBEVF_RXBUFFER_2048) - IXGBEVF_SKB_PAD) +#else +#define IXGBEVF_MAX_FRAME_BUILD_SKB IXGBEVF_RXBUFFER_2048 +#endif + #define IXGBE_TX_FLAGS_CSUM BIT(0) #define IXGBE_TX_FLAGS_VLAN BIT(1) #define IXGBE_TX_FLAGS_TSO BIT(2) @@ -170,6 +174,50 @@ struct ixgbevf_ring { #define IXGBE_TX_FLAGS_VLAN_PRIO_MASK 0x0000e000 #define IXGBE_TX_FLAGS_VLAN_SHIFT 16 +#define ring_uses_large_buffer(ring) \ + test_bit(__IXGBEVF_RX_3K_BUFFER, &(ring)->state) +#define set_ring_uses_large_buffer(ring) \ + set_bit(__IXGBEVF_RX_3K_BUFFER, &(ring)->state) +#define clear_ring_uses_large_buffer(ring) \ + clear_bit(__IXGBEVF_RX_3K_BUFFER, &(ring)->state) + +#define ring_uses_build_skb(ring) \ + test_bit(__IXGBEVF_RX_BUILD_SKB_ENABLED, &(ring)->state) +#define set_ring_build_skb_enabled(ring) \ + set_bit(__IXGBEVF_RX_BUILD_SKB_ENABLED, &(ring)->state) +#define clear_ring_build_skb_enabled(ring) \ + clear_bit(__IXGBEVF_RX_BUILD_SKB_ENABLED, &(ring)->state) + +static inline unsigned int ixgbevf_rx_bufsz(struct ixgbevf_ring *ring) +{ +#if (PAGE_SIZE < 8192) + if (ring_uses_large_buffer(ring)) + return IXGBEVF_RXBUFFER_3072; + + if (ring_uses_build_skb(ring)) + return IXGBEVF_MAX_FRAME_BUILD_SKB; +#endif + return IXGBEVF_RXBUFFER_2048; +} + +static inline unsigned int ixgbevf_rx_pg_order(struct ixgbevf_ring *ring) +{ +#if (PAGE_SIZE < 8192) + if (ring_uses_large_buffer(ring)) + return 1; +#endif + return 0; +} + +#define ixgbevf_rx_pg_size(_ring) (PAGE_SIZE << ixgbevf_rx_pg_order(_ring)) + +#define check_for_tx_hang(ring) \ + test_bit(__IXGBEVF_TX_DETECT_HANG, &(ring)->state) +#define set_check_for_tx_hang(ring) \ + set_bit(__IXGBEVF_TX_DETECT_HANG, &(ring)->state) +#define clear_check_for_tx_hang(ring) \ + clear_bit(__IXGBEVF_TX_DETECT_HANG, &(ring)->state) + struct ixgbevf_ring_container { struct ixgbevf_ring *ring; /* pointer to linked list of rings */ unsigned int total_bytes; /* total bytes processed this int */ @@ -194,7 +242,11 @@ struct ixgbevf_q_vector { u16 itr; /* Interrupt throttle rate written to EITR */ struct napi_struct napi; struct ixgbevf_ring_container rx, tx; + struct rcu_head rcu; /* to avoid race with update stats on free */ char name[IFNAMSIZ + 9]; + + /* for dynamic allocation of rings associated with this q_vector */ + struct ixgbevf_ring ring[0] ____cacheline_internodealigned_in_smp; #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int state; #define IXGBEVF_QV_STATE_IDLE 0 @@ -331,6 +383,8 @@ struct ixgbevf_adapter { u32 *rss_key; u8 rss_indir_tbl[IXGBEVF_X550_VFRETA_SIZE]; + u32 flags; +#define IXGBEVF_FLAGS_LEGACY_RX BIT(1) }; enum ixbgevf_state_t { diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 9b3d43d28106..f37307131eb6 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -130,6 +130,9 @@ static void ixgbevf_service_event_complete(struct ixgbevf_adapter *adapter) static void ixgbevf_queue_reset_subtask(struct ixgbevf_adapter *adapter); static void ixgbevf_set_itr(struct ixgbevf_q_vector *q_vector); static void ixgbevf_free_all_rx_resources(struct ixgbevf_adapter *adapter); +static bool ixgbevf_can_reuse_rx_page(struct ixgbevf_rx_buffer *rx_buffer); +static void ixgbevf_reuse_rx_page(struct ixgbevf_ring *rx_ring, + struct ixgbevf_rx_buffer *old_buff); static void ixgbevf_remove_adapter(struct ixgbe_hw *hw) { @@ -527,6 +530,49 @@ static void ixgbevf_process_skb_fields(struct ixgbevf_ring *rx_ring, skb->protocol = eth_type_trans(skb, rx_ring->netdev); } +static +struct ixgbevf_rx_buffer *ixgbevf_get_rx_buffer(struct ixgbevf_ring *rx_ring, + const unsigned int size) +{ + struct ixgbevf_rx_buffer *rx_buffer; + + rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; + prefetchw(rx_buffer->page); + + /* we are reusing so sync this buffer for CPU use */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_buffer->dma, + rx_buffer->page_offset, + size, + DMA_FROM_DEVICE); + + rx_buffer->pagecnt_bias--; + + return rx_buffer; +} + +static void ixgbevf_put_rx_buffer(struct ixgbevf_ring *rx_ring, + struct ixgbevf_rx_buffer *rx_buffer) +{ + if (ixgbevf_can_reuse_rx_page(rx_buffer)) { + /* hand second half of page back to the ring */ + ixgbevf_reuse_rx_page(rx_ring, rx_buffer); + } else { + /* We are not reusing the buffer so unmap it and free + * any references we are holding to it + */ + dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, + ixgbevf_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, + IXGBEVF_RX_DMA_ATTR); + __page_frag_cache_drain(rx_buffer->page, + rx_buffer->pagecnt_bias); + } + + /* clear contents of rx_buffer */ + rx_buffer->page = NULL; +} + /** * ixgbevf_is_non_eop - process handling of non-EOP buffers * @rx_ring: Rx ring being processed @@ -554,32 +600,38 @@ static bool ixgbevf_is_non_eop(struct ixgbevf_ring *rx_ring, return true; } +static inline unsigned int ixgbevf_rx_offset(struct ixgbevf_ring *rx_ring) +{ + return ring_uses_build_skb(rx_ring) ? IXGBEVF_SKB_PAD : 0; +} + static bool ixgbevf_alloc_mapped_page(struct ixgbevf_ring *rx_ring, struct ixgbevf_rx_buffer *bi) { struct page *page = bi->page; - dma_addr_t dma = bi->dma; + dma_addr_t dma; /* since we are recycling buffers we should seldom need to alloc */ if (likely(page)) return true; /* alloc new page for storage */ - page = dev_alloc_page(); + page = dev_alloc_pages(ixgbevf_rx_pg_order(rx_ring)); if (unlikely(!page)) { rx_ring->rx_stats.alloc_rx_page_failed++; return false; } /* map page for use */ - dma = dma_map_page_attrs(rx_ring->dev, page, 0, PAGE_SIZE, + dma = dma_map_page_attrs(rx_ring->dev, page, 0, + ixgbevf_rx_pg_size(rx_ring), DMA_FROM_DEVICE, IXGBEVF_RX_DMA_ATTR); /* if mapping failed free memory back to system since * there isn't much point in holding memory we can't use */ if (dma_mapping_error(rx_ring->dev, dma)) { - __free_page(page); + __free_pages(page, ixgbevf_rx_pg_order(rx_ring)); rx_ring->rx_stats.alloc_rx_page_failed++; return false; @@ -587,7 +639,7 @@ static bool ixgbevf_alloc_mapped_page(struct ixgbevf_ring *rx_ring, bi->dma = dma; bi->page = page; - bi->page_offset = 0; + bi->page_offset = ixgbevf_rx_offset(rx_ring); bi->pagecnt_bias = 1; rx_ring->rx_stats.alloc_rx_page++; @@ -621,7 +673,7 @@ static void ixgbevf_alloc_rx_buffers(struct ixgbevf_ring *rx_ring, /* sync the buffer for use by the device */ dma_sync_single_range_for_device(rx_ring->dev, bi->dma, bi->page_offset, - IXGBEVF_RX_BUFSZ, + ixgbevf_rx_bufsz(rx_ring), DMA_FROM_DEVICE); /* Refresh the desc even if pkt_addr didn't change @@ -734,11 +786,10 @@ static inline bool ixgbevf_page_is_reserved(struct page *page) return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page); } -static bool ixgbevf_can_reuse_rx_page(struct ixgbevf_rx_buffer *rx_buffer, - struct page *page, - const unsigned int truesize) +static bool ixgbevf_can_reuse_rx_page(struct ixgbevf_rx_buffer *rx_buffer) { - unsigned int pagecnt_bias = rx_buffer->pagecnt_bias--; + unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; + struct page *page = rx_buffer->page; /* avoid re-using remote pages */ if (unlikely(ixgbevf_page_is_reserved(page))) @@ -746,17 +797,13 @@ static bool ixgbevf_can_reuse_rx_page(struct ixgbevf_rx_buffer *rx_buffer, #if (PAGE_SIZE < 8192) /* if we are only owner of page we can reuse it */ - if (unlikely(page_ref_count(page) != pagecnt_bias)) + if (unlikely((page_ref_count(page) - pagecnt_bias) > 1)) return false; - - /* flip page offset to other buffer */ - rx_buffer->page_offset ^= IXGBEVF_RX_BUFSZ; - #else - /* move offset up to the next cache line */ - rx_buffer->page_offset += truesize; +#define IXGBEVF_LAST_OFFSET \ + (SKB_WITH_OVERHEAD(PAGE_SIZE) - IXGBEVF_RXBUFFER_2048) - if (rx_buffer->page_offset > (PAGE_SIZE - IXGBEVF_RX_BUFSZ)) + if (rx_buffer->page_offset > IXGBEVF_LAST_OFFSET) return false; #endif @@ -765,7 +812,7 @@ static bool ixgbevf_can_reuse_rx_page(struct ixgbevf_rx_buffer *rx_buffer, * the pagecnt_bias and page count so that we fully restock the * number of references the driver holds. */ - if (unlikely(pagecnt_bias == 1)) { + if (unlikely(!pagecnt_bias)) { page_ref_add(page, USHRT_MAX); rx_buffer->pagecnt_bias = USHRT_MAX; } @@ -777,127 +824,81 @@ static bool ixgbevf_can_reuse_rx_page(struct ixgbevf_rx_buffer *rx_buffer, * ixgbevf_add_rx_frag - Add contents of Rx buffer to sk_buff * @rx_ring: rx descriptor ring to transact packets on * @rx_buffer: buffer containing page to add - * @rx_desc: descriptor containing length of buffer written by hardware * @skb: sk_buff to place the data into + * @size: size of buffer to be added * * This function will add the data contained in rx_buffer->page to the skb. - * This is done either through a direct copy if the data in the buffer is - * less than the skb header size, otherwise it will just attach the page as - * a frag to the skb. - * - * The function will then update the page offset if necessary and return - * true if the buffer can be reused by the adapter. **/ -static bool ixgbevf_add_rx_frag(struct ixgbevf_ring *rx_ring, +static void ixgbevf_add_rx_frag(struct ixgbevf_ring *rx_ring, struct ixgbevf_rx_buffer *rx_buffer, - u16 size, - union ixgbe_adv_rx_desc *rx_desc, - struct sk_buff *skb) + struct sk_buff *skb, + unsigned int size) { - struct page *page = rx_buffer->page; - unsigned char *va = page_address(page) + rx_buffer->page_offset; #if (PAGE_SIZE < 8192) - unsigned int truesize = IXGBEVF_RX_BUFSZ; + unsigned int truesize = ixgbevf_rx_pg_size(rx_ring) / 2; #else - unsigned int truesize = ALIGN(size, L1_CACHE_BYTES); + unsigned int truesize = ring_uses_build_skb(rx_ring) ? + SKB_DATA_ALIGN(IXGBEVF_SKB_PAD + size) : + SKB_DATA_ALIGN(size); +#endif + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page, + rx_buffer->page_offset, size, truesize); +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; #endif - unsigned int pull_len; - - if (unlikely(skb_is_nonlinear(skb))) - goto add_tail_frag; - - if (likely(size <= IXGBEVF_RX_HDR_SIZE)) { - memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long))); - - /* page is not reserved, we can reuse buffer as is */ - if (likely(!ixgbevf_page_is_reserved(page))) - return true; - - /* this page cannot be reused so discard it */ - return false; - } - - /* we need the header to contain the greater of either ETH_HLEN or - * 60 bytes if the skb->len is less than 60 for skb_pad. - */ - pull_len = eth_get_headlen(va, IXGBEVF_RX_HDR_SIZE); - - /* align pull length to size of long to optimize memcpy performance */ - memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long))); - - /* update all of the pointers */ - va += pull_len; - size -= pull_len; - -add_tail_frag: - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, - (unsigned long)va & ~PAGE_MASK, size, truesize); - - return ixgbevf_can_reuse_rx_page(rx_buffer, page, truesize); } -static struct sk_buff *ixgbevf_fetch_rx_buffer(struct ixgbevf_ring *rx_ring, - union ixgbe_adv_rx_desc *rx_desc, - struct sk_buff *skb) +static +struct sk_buff *ixgbevf_construct_skb(struct ixgbevf_ring *rx_ring, + struct ixgbevf_rx_buffer *rx_buffer, + union ixgbe_adv_rx_desc *rx_desc, + unsigned int size) { - struct ixgbevf_rx_buffer *rx_buffer; - struct page *page; - u16 size = le16_to_cpu(rx_desc->wb.upper.length); - - rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; - page = rx_buffer->page; - prefetchw(page); - - /* we are reusing so sync this buffer for CPU use */ - dma_sync_single_range_for_cpu(rx_ring->dev, - rx_buffer->dma, - rx_buffer->page_offset, - size, - DMA_FROM_DEVICE); - - if (likely(!skb)) { - void *page_addr = page_address(page) + - rx_buffer->page_offset; + void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; +#if (PAGE_SIZE < 8192) + unsigned int truesize = ixgbevf_rx_pg_size(rx_ring) / 2; +#else + unsigned int truesize = SKB_DATA_ALIGN(size); +#endif + unsigned int headlen; + struct sk_buff *skb; - /* prefetch first cache line of first page */ - prefetch(page_addr); + /* prefetch first cache line of first page */ + prefetch(va); #if L1_CACHE_BYTES < 128 - prefetch(page_addr + L1_CACHE_BYTES); + prefetch(va + L1_CACHE_BYTES); #endif - /* allocate a skb to store the frags */ - skb = netdev_alloc_skb_ip_align(rx_ring->netdev, - IXGBEVF_RX_HDR_SIZE); - if (unlikely(!skb)) { - rx_ring->rx_stats.alloc_rx_buff_failed++; - return NULL; - } + /* allocate a skb to store the frags */ + skb = napi_alloc_skb(&rx_ring->q_vector->napi, IXGBEVF_RX_HDR_SIZE); + if (unlikely(!skb)) + return NULL; - /* we will be copying header into skb->data in - * pskb_may_pull so it is in our interest to prefetch - * it now to avoid a possible cache miss - */ - prefetchw(skb->data); - } + /* Determine available headroom for copy */ + headlen = size; + if (headlen > IXGBEVF_RX_HDR_SIZE) + headlen = eth_get_headlen(va, IXGBEVF_RX_HDR_SIZE); - /* pull page into skb */ - if (ixgbevf_add_rx_frag(rx_ring, rx_buffer, size, rx_desc, skb)) { - /* hand second half of page back to the ring */ - ixgbevf_reuse_rx_page(rx_ring, rx_buffer); + /* align pull length to size of long to optimize memcpy performance */ + memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long))); + + /* update all of the pointers */ + size -= headlen; + if (size) { + skb_add_rx_frag(skb, 0, rx_buffer->page, + (va + headlen) - page_address(rx_buffer->page), + size, truesize); +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif } else { - /* We are not reusing the buffer so unmap it and free - * any references we are holding to it - */ - dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, - PAGE_SIZE, DMA_FROM_DEVICE, - IXGBEVF_RX_DMA_ATTR); - __page_frag_cache_drain(page, rx_buffer->pagecnt_bias); + rx_buffer->pagecnt_bias++; } - /* clear contents of buffer_info */ - rx_buffer->dma = 0; - rx_buffer->page = NULL; - return skb; } @@ -909,6 +910,44 @@ static inline void ixgbevf_irq_enable_queues(struct ixgbevf_adapter *adapter, IXGBE_WRITE_REG(hw, IXGBE_VTEIMS, qmask); } +static struct sk_buff *ixgbevf_build_skb(struct ixgbevf_ring *rx_ring, + struct ixgbevf_rx_buffer *rx_buffer, + union ixgbe_adv_rx_desc *rx_desc, + unsigned int size) +{ + void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; +#if (PAGE_SIZE < 8192) + unsigned int truesize = ixgbevf_rx_pg_size(rx_ring) / 2; +#else + unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) + + SKB_DATA_ALIGN(IXGBEVF_SKB_PAD + size); +#endif + struct sk_buff *skb; + + /* prefetch first cache line of first page */ + prefetch(va); +#if L1_CACHE_BYTES < 128 + prefetch(va + L1_CACHE_BYTES); +#endif + + /* build an skb to around the page buffer */ + skb = build_skb(va - IXGBEVF_SKB_PAD, truesize); + if (unlikely(!skb)) + return NULL; + + /* update pointers within the skb to store the data */ + skb_reserve(skb, IXGBEVF_SKB_PAD); + __skb_put(skb, size); + + /* update buffer offset */ +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif + + return skb; +} static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, struct ixgbevf_ring *rx_ring, int budget) @@ -919,6 +958,8 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, while (likely(total_rx_packets < budget)) { union ixgbe_adv_rx_desc *rx_desc; + struct ixgbevf_rx_buffer *rx_buffer; + unsigned int size; /* return some buffers to hardware, one at a time is too slow */ if (cleaned_count >= IXGBEVF_RX_BUFFER_WRITE) { @@ -927,8 +968,8 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, } rx_desc = IXGBEVF_RX_DESC(rx_ring, rx_ring->next_to_clean); - - if (!rx_desc->wb.upper.length) + size = le16_to_cpu(rx_desc->wb.upper.length); + if (!size) break; /* This memory barrier is needed to keep us from reading @@ -937,15 +978,26 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, */ rmb(); + rx_buffer = ixgbevf_get_rx_buffer(rx_ring, size); + /* retrieve a buffer from the ring */ - skb = ixgbevf_fetch_rx_buffer(rx_ring, rx_desc, skb); + if (skb) + ixgbevf_add_rx_frag(rx_ring, rx_buffer, skb, size); + else if (ring_uses_build_skb(rx_ring)) + skb = ixgbevf_build_skb(rx_ring, rx_buffer, + rx_desc, size); + else + skb = ixgbevf_construct_skb(rx_ring, rx_buffer, + rx_desc, size); /* exit if we failed to retrieve a buffer */ if (!skb) { rx_ring->rx_stats.alloc_rx_buff_failed++; + rx_buffer->pagecnt_bias++; break; } + ixgbevf_put_rx_buffer(rx_ring, rx_buffer); cleaned_count++; /* fetch next buffer in frame if non-eop */ @@ -1260,85 +1312,6 @@ static irqreturn_t ixgbevf_msix_clean_rings(int irq, void *data) return IRQ_HANDLED; } -static inline void map_vector_to_rxq(struct ixgbevf_adapter *a, int v_idx, - int r_idx) -{ - struct ixgbevf_q_vector *q_vector = a->q_vector[v_idx]; - - a->rx_ring[r_idx]->next = q_vector->rx.ring; - q_vector->rx.ring = a->rx_ring[r_idx]; - q_vector->rx.count++; -} - -static inline void map_vector_to_txq(struct ixgbevf_adapter *a, int v_idx, - int t_idx) -{ - struct ixgbevf_q_vector *q_vector = a->q_vector[v_idx]; - - a->tx_ring[t_idx]->next = q_vector->tx.ring; - q_vector->tx.ring = a->tx_ring[t_idx]; - q_vector->tx.count++; -} - -/** - * ixgbevf_map_rings_to_vectors - Maps descriptor rings to vectors - * @adapter: board private structure to initialize - * - * This function maps descriptor rings to the queue-specific vectors - * we were allotted through the MSI-X enabling code. Ideally, we'd have - * one vector per ring/queue, but on a constrained vector budget, we - * group the rings as "efficiently" as possible. You would add new - * mapping configurations in here. - **/ -static int ixgbevf_map_rings_to_vectors(struct ixgbevf_adapter *adapter) -{ - int q_vectors; - int v_start = 0; - int rxr_idx = 0, txr_idx = 0; - int rxr_remaining = adapter->num_rx_queues; - int txr_remaining = adapter->num_tx_queues; - int i, j; - int rqpv, tqpv; - - q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; - - /* The ideal configuration... - * We have enough vectors to map one per queue. - */ - if (q_vectors == adapter->num_rx_queues + adapter->num_tx_queues) { - for (; rxr_idx < rxr_remaining; v_start++, rxr_idx++) - map_vector_to_rxq(adapter, v_start, rxr_idx); - - for (; txr_idx < txr_remaining; v_start++, txr_idx++) - map_vector_to_txq(adapter, v_start, txr_idx); - return 0; - } - - /* If we don't have enough vectors for a 1-to-1 - * mapping, we'll have to group them so there are - * multiple queues per vector. - */ - /* Re-adjusting *qpv takes care of the remainder. */ - for (i = v_start; i < q_vectors; i++) { - rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors - i); - for (j = 0; j < rqpv; j++) { - map_vector_to_rxq(adapter, i, rxr_idx); - rxr_idx++; - rxr_remaining--; - } - } - for (i = v_start; i < q_vectors; i++) { - tqpv = DIV_ROUND_UP(txr_remaining, q_vectors - i); - for (j = 0; j < tqpv; j++) { - map_vector_to_txq(adapter, i, txr_idx); - txr_idx++; - txr_remaining--; - } - } - - return 0; -} - /** * ixgbevf_request_msix_irqs - Initialize MSI-X interrupts * @adapter: board private structure @@ -1411,20 +1384,6 @@ free_queue_irqs: return err; } -static inline void ixgbevf_reset_q_vectors(struct ixgbevf_adapter *adapter) -{ - int i, q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; - - for (i = 0; i < q_vectors; i++) { - struct ixgbevf_q_vector *q_vector = adapter->q_vector[i]; - - q_vector->rx.ring = NULL; - q_vector->tx.ring = NULL; - q_vector->rx.count = 0; - q_vector->tx.count = 0; - } -} - /** * ixgbevf_request_irq - initialize interrupts * @adapter: board private structure @@ -1464,8 +1423,6 @@ static void ixgbevf_free_irq(struct ixgbevf_adapter *adapter) free_irq(adapter->msix_entries[i].vector, adapter->q_vector[i]); } - - ixgbevf_reset_q_vectors(adapter); } /** @@ -1587,7 +1544,8 @@ static void ixgbevf_configure_tx(struct ixgbevf_adapter *adapter) #define IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT 2 -static void ixgbevf_configure_srrctl(struct ixgbevf_adapter *adapter, int index) +static void ixgbevf_configure_srrctl(struct ixgbevf_adapter *adapter, + struct ixgbevf_ring *ring, int index) { struct ixgbe_hw *hw = &adapter->hw; u32 srrctl; @@ -1595,7 +1553,10 @@ static void ixgbevf_configure_srrctl(struct ixgbevf_adapter *adapter, int index) srrctl = IXGBE_SRRCTL_DROP_EN; srrctl |= IXGBEVF_RX_HDR_SIZE << IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT; - srrctl |= IXGBEVF_RX_BUFSZ >> IXGBE_SRRCTL_BSIZEPKT_SHIFT; + if (ring_uses_large_buffer(ring)) + srrctl |= IXGBEVF_RXBUFFER_3072 >> IXGBE_SRRCTL_BSIZEPKT_SHIFT; + else + srrctl |= IXGBEVF_RXBUFFER_2048 >> IXGBE_SRRCTL_BSIZEPKT_SHIFT; srrctl |= IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF; IXGBE_WRITE_REG(hw, IXGBE_VFSRRCTL(index), srrctl); @@ -1767,10 +1728,21 @@ static void ixgbevf_configure_rx_ring(struct ixgbevf_adapter *adapter, ring->next_to_use = 0; ring->next_to_alloc = 0; - ixgbevf_configure_srrctl(adapter, reg_idx); + ixgbevf_configure_srrctl(adapter, ring, reg_idx); + + /* RXDCTL.RLPML does not work on 82599 */ + if (adapter->hw.mac.type != ixgbe_mac_82599_vf) { + rxdctl &= ~(IXGBE_RXDCTL_RLPMLMASK | + IXGBE_RXDCTL_RLPML_EN); - /* allow any size packet since we can handle overflow */ - rxdctl &= ~IXGBE_RXDCTL_RLPML_EN; +#if (PAGE_SIZE < 8192) + /* Limit the maximum frame size so we don't overrun the skb */ + if (ring_uses_build_skb(ring) && + !ring_uses_large_buffer(ring)) + rxdctl |= IXGBEVF_MAX_FRAME_BUILD_SKB | + IXGBE_RXDCTL_RLPML_EN; +#endif + } rxdctl |= IXGBE_RXDCTL_ENABLE | IXGBE_RXDCTL_VME; IXGBE_WRITE_REG(hw, IXGBE_VFRXDCTL(reg_idx), rxdctl); @@ -1779,6 +1751,29 @@ static void ixgbevf_configure_rx_ring(struct ixgbevf_adapter *adapter, ixgbevf_alloc_rx_buffers(ring, ixgbevf_desc_unused(ring)); } +static void ixgbevf_set_rx_buffer_len(struct ixgbevf_adapter *adapter, + struct ixgbevf_ring *rx_ring) +{ + struct net_device *netdev = adapter->netdev; + unsigned int max_frame = netdev->mtu + ETH_HLEN + ETH_FCS_LEN; + + /* set build_skb and buffer size flags */ + clear_ring_build_skb_enabled(rx_ring); + clear_ring_uses_large_buffer(rx_ring); + + if (adapter->flags & IXGBEVF_FLAGS_LEGACY_RX) + return; + + set_ring_build_skb_enabled(rx_ring); + +#if (PAGE_SIZE < 8192) + if (max_frame <= IXGBEVF_MAX_FRAME_BUILD_SKB) + return; + + set_ring_uses_large_buffer(rx_ring); +#endif +} + /** * ixgbevf_configure_rx - Configure 82599 VF Receive Unit after Reset * @adapter: board private structure @@ -1806,8 +1801,12 @@ static void ixgbevf_configure_rx(struct ixgbevf_adapter *adapter) /* Setup the HW Rx Head and Tail Descriptor Pointers and * the Base and Length of the Rx Descriptor Ring */ - for (i = 0; i < adapter->num_rx_queues; i++) - ixgbevf_configure_rx_ring(adapter, adapter->rx_ring[i]); + for (i = 0; i < adapter->num_rx_queues; i++) { + struct ixgbevf_ring *rx_ring = adapter->rx_ring[i]; + + ixgbevf_set_rx_buffer_len(adapter, rx_ring); + ixgbevf_configure_rx_ring(adapter, rx_ring); + } } static int ixgbevf_vlan_rx_add_vid(struct net_device *netdev, @@ -2136,13 +2135,13 @@ static void ixgbevf_clean_rx_ring(struct ixgbevf_ring *rx_ring) dma_sync_single_range_for_cpu(rx_ring->dev, rx_buffer->dma, rx_buffer->page_offset, - IXGBEVF_RX_BUFSZ, + ixgbevf_rx_bufsz(rx_ring), DMA_FROM_DEVICE); /* free resources associated with mapping */ dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, - PAGE_SIZE, + ixgbevf_rx_pg_size(rx_ring), DMA_FROM_DEVICE, IXGBEVF_RX_DMA_ATTR); @@ -2405,105 +2404,171 @@ static void ixgbevf_set_num_queues(struct ixgbevf_adapter *adapter) } /** - * ixgbevf_alloc_queues - Allocate memory for all rings + * ixgbevf_set_interrupt_capability - set MSI-X or FAIL if not supported + * @adapter: board private structure to initialize + * + * Attempt to configure the interrupts using the best available + * capabilities of the hardware and the kernel. + **/ +static int ixgbevf_set_interrupt_capability(struct ixgbevf_adapter *adapter) +{ + int vector, v_budget; + + /* It's easy to be greedy for MSI-X vectors, but it really + * doesn't do us much good if we have a lot more vectors + * than CPU's. So let's be conservative and only ask for + * (roughly) the same number of vectors as there are CPU's. + * The default is to use pairs of vectors. + */ + v_budget = max(adapter->num_rx_queues, adapter->num_tx_queues); + v_budget = min_t(int, v_budget, num_online_cpus()); + v_budget += NON_Q_VECTORS; + + adapter->msix_entries = kcalloc(v_budget, + sizeof(struct msix_entry), GFP_KERNEL); + if (!adapter->msix_entries) + return -ENOMEM; + + for (vector = 0; vector < v_budget; vector++) + adapter->msix_entries[vector].entry = vector; + + /* A failure in MSI-X entry allocation isn't fatal, but the VF driver + * does not support any other modes, so we will simply fail here. Note + * that we clean up the msix_entries pointer else-where. + */ + return ixgbevf_acquire_msix_vectors(adapter, v_budget); +} + +static void ixgbevf_add_ring(struct ixgbevf_ring *ring, + struct ixgbevf_ring_container *head) +{ + ring->next = head->ring; + head->ring = ring; + head->count++; +} + +/** + * ixgbevf_alloc_q_vector - Allocate memory for a single interrupt vector * @adapter: board private structure to initialize + * @v_idx: index of vector in adapter struct + * @txr_count: number of Tx rings for q vector + * @txr_idx: index of first Tx ring to assign + * @rxr_count: number of Rx rings for q vector + * @rxr_idx: index of first Rx ring to assign * - * We allocate one ring per queue at run-time since we don't know the - * number of queues at compile-time. The polling_netdev array is - * intended for Multiqueue, but should work fine with a single queue. + * We allocate one q_vector. If allocation fails we return -ENOMEM. **/ -static int ixgbevf_alloc_queues(struct ixgbevf_adapter *adapter) +static int ixgbevf_alloc_q_vector(struct ixgbevf_adapter *adapter, int v_idx, + int txr_count, int txr_idx, + int rxr_count, int rxr_idx) { + struct ixgbevf_q_vector *q_vector; struct ixgbevf_ring *ring; - int rx = 0, tx = 0; + int ring_count, size; + + ring_count = txr_count + rxr_count; + size = sizeof(*q_vector) + (sizeof(*ring) * ring_count); + + /* allocate q_vector and rings */ + q_vector = kzalloc(size, GFP_KERNEL); + if (!q_vector) + return -ENOMEM; + + /* initialize NAPI */ + netif_napi_add(adapter->netdev, &q_vector->napi, ixgbevf_poll, 64); + + /* tie q_vector and adapter together */ + adapter->q_vector[v_idx] = q_vector; + q_vector->adapter = adapter; + q_vector->v_idx = v_idx; - for (; tx < adapter->num_tx_queues; tx++) { - ring = kzalloc(sizeof(*ring), GFP_KERNEL); - if (!ring) - goto err_allocation; + /* initialize pointer to rings */ + ring = q_vector->ring; + while (txr_count) { + /* assign generic ring traits */ ring->dev = &adapter->pdev->dev; ring->netdev = adapter->netdev; + + /* configure backlink on ring */ + ring->q_vector = q_vector; + + /* update q_vector Tx values */ + ixgbevf_add_ring(ring, &q_vector->tx); + + /* apply Tx specific ring traits */ ring->count = adapter->tx_ring_count; - ring->queue_index = tx; - ring->reg_idx = tx; + ring->queue_index = txr_idx; + ring->reg_idx = txr_idx; - adapter->tx_ring[tx] = ring; - } + /* assign ring to adapter */ + adapter->tx_ring[txr_idx] = ring; + + /* update count and index */ + txr_count--; + txr_idx++; - for (; rx < adapter->num_rx_queues; rx++) { - ring = kzalloc(sizeof(*ring), GFP_KERNEL); - if (!ring) - goto err_allocation; + /* push pointer to next ring */ + ring++; + } + while (rxr_count) { + /* assign generic ring traits */ ring->dev = &adapter->pdev->dev; ring->netdev = adapter->netdev; + /* configure backlink on ring */ + ring->q_vector = q_vector; + + /* update q_vector Rx values */ + ixgbevf_add_ring(ring, &q_vector->rx); + + /* apply Rx specific ring traits */ ring->count = adapter->rx_ring_count; - ring->queue_index = rx; - ring->reg_idx = rx; + ring->queue_index = rxr_idx; + ring->reg_idx = rxr_idx; - adapter->rx_ring[rx] = ring; - } + /* assign ring to adapter */ + adapter->rx_ring[rxr_idx] = ring; - return 0; + /* update count and index */ + rxr_count--; + rxr_idx++; -err_allocation: - while (tx) { - kfree(adapter->tx_ring[--tx]); - adapter->tx_ring[tx] = NULL; + /* push pointer to next ring */ + ring++; } - while (rx) { - kfree(adapter->rx_ring[--rx]); - adapter->rx_ring[rx] = NULL; - } - return -ENOMEM; + return 0; } /** - * ixgbevf_set_interrupt_capability - set MSI-X or FAIL if not supported + * ixgbevf_free_q_vector - Free memory allocated for specific interrupt vector * @adapter: board private structure to initialize + * @v_idx: index of vector in adapter struct * - * Attempt to configure the interrupts using the best available - * capabilities of the hardware and the kernel. + * This function frees the memory allocated to the q_vector. In addition if + * NAPI is enabled it will delete any references to the NAPI struct prior + * to freeing the q_vector. **/ -static int ixgbevf_set_interrupt_capability(struct ixgbevf_adapter *adapter) +static void ixgbevf_free_q_vector(struct ixgbevf_adapter *adapter, int v_idx) { - struct net_device *netdev = adapter->netdev; - int err; - int vector, v_budget; - - /* It's easy to be greedy for MSI-X vectors, but it really - * doesn't do us much good if we have a lot more vectors - * than CPU's. So let's be conservative and only ask for - * (roughly) the same number of vectors as there are CPU's. - * The default is to use pairs of vectors. - */ - v_budget = max(adapter->num_rx_queues, adapter->num_tx_queues); - v_budget = min_t(int, v_budget, num_online_cpus()); - v_budget += NON_Q_VECTORS; - - /* A failure in MSI-X entry allocation isn't fatal, but it does - * mean we disable MSI-X capabilities of the adapter. - */ - adapter->msix_entries = kcalloc(v_budget, - sizeof(struct msix_entry), GFP_KERNEL); - if (!adapter->msix_entries) - return -ENOMEM; + struct ixgbevf_q_vector *q_vector = adapter->q_vector[v_idx]; + struct ixgbevf_ring *ring; - for (vector = 0; vector < v_budget; vector++) - adapter->msix_entries[vector].entry = vector; + ixgbevf_for_each_ring(ring, q_vector->tx) + adapter->tx_ring[ring->queue_index] = NULL; - err = ixgbevf_acquire_msix_vectors(adapter, v_budget); - if (err) - return err; + ixgbevf_for_each_ring(ring, q_vector->rx) + adapter->rx_ring[ring->queue_index] = NULL; - err = netif_set_real_num_tx_queues(netdev, adapter->num_tx_queues); - if (err) - return err; + adapter->q_vector[v_idx] = NULL; + netif_napi_del(&q_vector->napi); - return netif_set_real_num_rx_queues(netdev, adapter->num_rx_queues); + /* ixgbevf_get_stats() might access the rings on this vector, + * we must wait a grace period before freeing it. + */ + kfree_rcu(q_vector, rcu); } /** @@ -2515,35 +2580,53 @@ static int ixgbevf_set_interrupt_capability(struct ixgbevf_adapter *adapter) **/ static int ixgbevf_alloc_q_vectors(struct ixgbevf_adapter *adapter) { - int q_idx, num_q_vectors; - struct ixgbevf_q_vector *q_vector; + int q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; + int rxr_remaining = adapter->num_rx_queues; + int txr_remaining = adapter->num_tx_queues; + int rxr_idx = 0, txr_idx = 0, v_idx = 0; + int err; + + if (q_vectors >= (rxr_remaining + txr_remaining)) { + for (; rxr_remaining; v_idx++, q_vectors--) { + int rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors); + + err = ixgbevf_alloc_q_vector(adapter, v_idx, + 0, 0, rqpv, rxr_idx); + if (err) + goto err_out; - num_q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; + /* update counts and index */ + rxr_remaining -= rqpv; + rxr_idx += rqpv; + } + } + + for (; q_vectors; v_idx++, q_vectors--) { + int rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors); + int tqpv = DIV_ROUND_UP(txr_remaining, q_vectors); - for (q_idx = 0; q_idx < num_q_vectors; q_idx++) { - q_vector = kzalloc(sizeof(struct ixgbevf_q_vector), GFP_KERNEL); - if (!q_vector) + err = ixgbevf_alloc_q_vector(adapter, v_idx, + tqpv, txr_idx, + rqpv, rxr_idx); + + if (err) goto err_out; - q_vector->adapter = adapter; - q_vector->v_idx = q_idx; - netif_napi_add(adapter->netdev, &q_vector->napi, - ixgbevf_poll, 64); - adapter->q_vector[q_idx] = q_vector; + + /* update counts and index */ + rxr_remaining -= rqpv; + rxr_idx += rqpv; + txr_remaining -= tqpv; + txr_idx += tqpv; } return 0; err_out: - while (q_idx) { - q_idx--; - q_vector = adapter->q_vector[q_idx]; -#ifdef CONFIG_NET_RX_BUSY_POLL - napi_hash_del(&q_vector->napi); -#endif - netif_napi_del(&q_vector->napi); - kfree(q_vector); - adapter->q_vector[q_idx] = NULL; + while (v_idx) { + v_idx--; + ixgbevf_free_q_vector(adapter, v_idx); } + return -ENOMEM; } @@ -2557,17 +2640,11 @@ err_out: **/ static void ixgbevf_free_q_vectors(struct ixgbevf_adapter *adapter) { - int q_idx, num_q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; - - for (q_idx = 0; q_idx < num_q_vectors; q_idx++) { - struct ixgbevf_q_vector *q_vector = adapter->q_vector[q_idx]; + int q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; - adapter->q_vector[q_idx] = NULL; -#ifdef CONFIG_NET_RX_BUSY_POLL - napi_hash_del(&q_vector->napi); -#endif - netif_napi_del(&q_vector->napi); - kfree(q_vector); + while (q_vectors) { + q_vectors--; + ixgbevf_free_q_vector(adapter, q_vectors); } } @@ -2611,12 +2688,6 @@ static int ixgbevf_init_interrupt_scheme(struct ixgbevf_adapter *adapter) goto err_alloc_q_vectors; } - err = ixgbevf_alloc_queues(adapter); - if (err) { - pr_err("Unable to allocate memory for queues\n"); - goto err_alloc_queues; - } - hw_dbg(&adapter->hw, "Multiqueue %s: Rx Queue count = %u, Tx Queue count = %u\n", (adapter->num_rx_queues > 1) ? "Enabled" : "Disabled", adapter->num_rx_queues, adapter->num_tx_queues); @@ -2624,8 +2695,6 @@ static int ixgbevf_init_interrupt_scheme(struct ixgbevf_adapter *adapter) set_bit(__IXGBEVF_DOWN, &adapter->state); return 0; -err_alloc_queues: - ixgbevf_free_q_vectors(adapter); err_alloc_q_vectors: ixgbevf_reset_interrupt_capability(adapter); err_set_interrupt: @@ -2641,17 +2710,6 @@ err_set_interrupt: **/ static void ixgbevf_clear_interrupt_scheme(struct ixgbevf_adapter *adapter) { - int i; - - for (i = 0; i < adapter->num_tx_queues; i++) { - kfree(adapter->tx_ring[i]); - adapter->tx_ring[i] = NULL; - } - for (i = 0; i < adapter->num_rx_queues; i++) { - kfree(adapter->rx_ring[i]); - adapter->rx_ring[i] = NULL; - } - adapter->num_tx_queues = 0; adapter->num_rx_queues = 0; @@ -3088,9 +3146,14 @@ static int ixgbevf_setup_all_tx_resources(struct ixgbevf_adapter *adapter) if (!err) continue; hw_dbg(&adapter->hw, "Allocation for Tx Queue %u failed\n", i); - break; + goto err_setup_tx; } + return 0; +err_setup_tx: + /* rewind the index freeing the rings as we go */ + while (i--) + ixgbevf_free_tx_resources(adapter->tx_ring[i]); return err; } @@ -3148,8 +3211,14 @@ static int ixgbevf_setup_all_rx_resources(struct ixgbevf_adapter *adapter) if (!err) continue; hw_dbg(&adapter->hw, "Allocation for Rx Queue %u failed\n", i); - break; + goto err_setup_rx; } + + return 0; +err_setup_rx: + /* rewind the index freeing the rings as we go */ + while (i--) + ixgbevf_free_rx_resources(adapter->rx_ring[i]); return err; } @@ -3244,28 +3313,31 @@ int ixgbevf_open(struct net_device *netdev) ixgbevf_configure(adapter); - /* Map the Tx/Rx rings to the vectors we were allotted. - * if request_irq will be called in this function map_rings - * must be called *before* up_complete - */ - ixgbevf_map_rings_to_vectors(adapter); - err = ixgbevf_request_irq(adapter); if (err) goto err_req_irq; + /* Notify the stack of the actual queue counts. */ + err = netif_set_real_num_tx_queues(netdev, adapter->num_tx_queues); + if (err) + goto err_set_queues; + + err = netif_set_real_num_rx_queues(netdev, adapter->num_rx_queues); + if (err) + goto err_set_queues; + ixgbevf_up_complete(adapter); return 0; +err_set_queues: + ixgbevf_free_irq(adapter); err_req_irq: - ixgbevf_down(adapter); -err_setup_rx: ixgbevf_free_all_rx_resources(adapter); -err_setup_tx: +err_setup_rx: ixgbevf_free_all_tx_resources(adapter); +err_setup_tx: ixgbevf_reset(adapter); - err_setup_reset: return err; @@ -3707,11 +3779,10 @@ static int ixgbevf_maybe_stop_tx(struct ixgbevf_ring *tx_ring, int size) return __ixgbevf_maybe_stop_tx(tx_ring, size); } -static int ixgbevf_xmit_frame(struct sk_buff *skb, struct net_device *netdev) +static int ixgbevf_xmit_frame_ring(struct sk_buff *skb, + struct ixgbevf_ring *tx_ring) { - struct ixgbevf_adapter *adapter = netdev_priv(netdev); struct ixgbevf_tx_buffer *first; - struct ixgbevf_ring *tx_ring; int tso; u32 tx_flags = 0; u16 count = TXD_USE_COUNT(skb_headlen(skb)); @@ -3726,8 +3797,6 @@ static int ixgbevf_xmit_frame(struct sk_buff *skb, struct net_device *netdev) return NETDEV_TX_OK; } - tx_ring = adapter->tx_ring[skb->queue_mapping]; - /* need: 1 descriptor per page * PAGE_SIZE/IXGBE_MAX_DATA_PER_TXD, * + 1 desc for skb_headlen/IXGBE_MAX_DATA_PER_TXD, * + 2 desc gap to keep tail from touching head, @@ -3780,6 +3849,29 @@ out_drop: return NETDEV_TX_OK; } +static int ixgbevf_xmit_frame(struct sk_buff *skb, struct net_device *netdev) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + struct ixgbevf_ring *tx_ring; + + if (skb->len <= 0) { + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; + } + + /* The minimum packet size for olinfo paylen is 17 so pad the skb + * in order to meet this minimum size requirement. + */ + if (skb->len < 17) { + if (skb_padto(skb, 17)) + return NETDEV_TX_OK; + skb->len = 17; + } + + tx_ring = adapter->tx_ring[skb->queue_mapping]; + return ixgbevf_xmit_frame_ring(skb, tx_ring); +} + /** * ixgbevf_set_mac - Change the Ethernet Address of the NIC * @netdev: network interface device structure @@ -3839,6 +3931,9 @@ static int ixgbevf_change_mtu(struct net_device *netdev, int new_mtu) /* must set new MTU before calling down or up */ netdev->mtu = new_mtu; + if (netif_running(netdev)) + ixgbevf_reinit_locked(adapter); + return 0; } @@ -3917,17 +4012,11 @@ static int ixgbevf_resume(struct pci_dev *pdev) rtnl_lock(); err = ixgbevf_init_interrupt_scheme(adapter); + if (!err && netif_running(netdev)) + err = ixgbevf_open(netdev); rtnl_unlock(); - if (err) { - dev_err(&pdev->dev, "Cannot initialize interrupts\n"); + if (err) return err; - } - - if (netif_running(netdev)) { - err = ixgbevf_open(netdev); - if (err) - return err; - } netif_device_attach(netdev); @@ -3953,6 +4042,7 @@ static void ixgbevf_get_stats(struct net_device *netdev, stats->multicast = adapter->stats.vfmprc - adapter->stats.base_vfmprc; + rcu_read_lock(); for (i = 0; i < adapter->num_rx_queues; i++) { ring = adapter->rx_ring[i]; do { @@ -3974,6 +4064,7 @@ static void ixgbevf_get_stats(struct net_device *netdev, stats->tx_bytes += bytes; stats->tx_packets += packets; } + rcu_read_unlock(); } #define IXGBEVF_MAX_MAC_HDR_LEN 127 diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index a1d7b88cf083..5a1668cdb461 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -7137,6 +7137,7 @@ static void mvpp2_set_rx_mode(struct net_device *dev) int id = port->id; bool allmulti = dev->flags & IFF_ALLMULTI; +retry: mvpp2_prs_mac_promisc_set(priv, id, dev->flags & IFF_PROMISC); mvpp2_prs_mac_multi_set(priv, id, MVPP2_PE_MAC_MC_ALL, allmulti); mvpp2_prs_mac_multi_set(priv, id, MVPP2_PE_MAC_MC_IP6, allmulti); @@ -7144,9 +7145,13 @@ static void mvpp2_set_rx_mode(struct net_device *dev) /* Remove all port->id's mcast enries */ mvpp2_prs_mcast_del_all(priv, id); - if (allmulti && !netdev_mc_empty(dev)) { - netdev_for_each_mc_addr(ha, dev) - mvpp2_prs_mac_da_accept(priv, id, ha->addr, true); + if (!allmulti) { + netdev_for_each_mc_addr(ha, dev) { + if (mvpp2_prs_mac_da_accept(priv, id, ha->addr, true)) { + allmulti = true; + goto retry; + } + } } } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index ebc1f566a4d9..9a7a2f05ab35 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -199,6 +199,10 @@ static const char main_strings[][ETH_GSTRING_LEN] = { "rx_xdp_drop", "rx_xdp_tx", "rx_xdp_tx_full", + + /* phy statistics */ + "rx_packets_phy", "rx_bytes_phy", + "tx_packets_phy", "tx_bytes_phy", }; static const char mlx4_en_test_names[][ETH_GSTRING_LEN]= { @@ -411,6 +415,10 @@ static void mlx4_en_get_ethtool_stats(struct net_device *dev, if (bitmap_iterator_test(&it)) data[index++] = ((unsigned long *)&priv->xdp_stats)[i]; + for (i = 0; i < NUM_PHY_STATS; i++, bitmap_iterator_inc(&it)) + if (bitmap_iterator_test(&it)) + data[index++] = ((unsigned long *)&priv->phy_stats)[i]; + for (i = 0; i < priv->tx_ring_num[TX]; i++) { data[index++] = priv->tx_ring[TX][i]->packets; data[index++] = priv->tx_ring[TX][i]->bytes; @@ -490,6 +498,12 @@ static void mlx4_en_get_strings(struct net_device *dev, strcpy(data + (index++) * ETH_GSTRING_LEN, main_strings[strings]); + for (i = 0; i < NUM_PHY_STATS; i++, strings++, + bitmap_iterator_inc(&it)) + if (bitmap_iterator_test(&it)) + strcpy(data + (index++) * ETH_GSTRING_LEN, + main_strings[strings]); + for (i = 0; i < priv->tx_ring_num[TX]; i++) { sprintf(data + (index++) * ETH_GSTRING_LEN, "tx%d_packets", i); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 8fc51bc29003..e0adac4a9a19 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -3256,6 +3256,10 @@ void mlx4_en_set_stats_bitmap(struct mlx4_dev *dev, bitmap_set(stats_bitmap->bitmap, last_i, NUM_XDP_STATS); last_i += NUM_XDP_STATS; + + if (!mlx4_is_slave(dev)) + bitmap_set(stats_bitmap->bitmap, last_i, NUM_PHY_STATS); + last_i += NUM_PHY_STATS; } int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, @@ -3630,10 +3634,6 @@ int mlx4_en_reset_config(struct net_device *dev, mlx4_en_stop_port(dev, 1); } - en_warn(priv, "Changing device configuration rx filter(%x) rx vlan(%x)\n", - ts_config.rx_filter, - !!(features & NETIF_F_HW_VLAN_CTAG_RX)); - mlx4_en_safe_replace_resources(priv, tmp); if (DEV_FEATURE_CHANGED(dev, features, NETIF_F_HW_VLAN_CTAG_RX)) { diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c index 1fa4849a6f56..0158b88bea5b 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_port.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c @@ -275,19 +275,31 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) priv->port_stats.xmit_more += READ_ONCE(ring->xmit_more); } - if (mlx4_is_master(mdev->dev)) { - stats->rx_packets = en_stats_adder(&mlx4_en_stats->RTOT_prio_0, - &mlx4_en_stats->RTOT_prio_1, - NUM_PRIORITIES); - stats->tx_packets = en_stats_adder(&mlx4_en_stats->TTOT_prio_0, - &mlx4_en_stats->TTOT_prio_1, - NUM_PRIORITIES); - stats->rx_bytes = en_stats_adder(&mlx4_en_stats->ROCT_prio_0, - &mlx4_en_stats->ROCT_prio_1, - NUM_PRIORITIES); - stats->tx_bytes = en_stats_adder(&mlx4_en_stats->TOCT_prio_0, - &mlx4_en_stats->TOCT_prio_1, - NUM_PRIORITIES); + if (!mlx4_is_slave(mdev->dev)) { + struct mlx4_en_phy_stats *p_stats = &priv->phy_stats; + + p_stats->rx_packets_phy = + en_stats_adder(&mlx4_en_stats->RTOT_prio_0, + &mlx4_en_stats->RTOT_prio_1, + NUM_PRIORITIES); + p_stats->tx_packets_phy = + en_stats_adder(&mlx4_en_stats->TTOT_prio_0, + &mlx4_en_stats->TTOT_prio_1, + NUM_PRIORITIES); + p_stats->rx_bytes_phy = + en_stats_adder(&mlx4_en_stats->ROCT_prio_0, + &mlx4_en_stats->ROCT_prio_1, + NUM_PRIORITIES); + p_stats->tx_bytes_phy = + en_stats_adder(&mlx4_en_stats->TOCT_prio_0, + &mlx4_en_stats->TOCT_prio_1, + NUM_PRIORITIES); + if (mlx4_is_master(mdev->dev)) { + stats->rx_packets = p_stats->rx_packets_phy; + stats->tx_packets = p_stats->tx_packets_phy; + stats->rx_bytes = p_stats->rx_bytes_phy; + stats->tx_bytes = p_stats->tx_bytes_phy; + } } /* net device stats */ diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index b4d144e67514..c2c6bd7578fd 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -649,6 +649,12 @@ static int check_csum(struct mlx4_cqe *cqe, struct sk_buff *skb, void *va, return get_fixed_ipv4_csum(hw_checksum, skb, hdr); } +#if IS_ENABLED(CONFIG_IPV6) +#define MLX4_CQE_STATUS_IP_ANY (MLX4_CQE_STATUS_IPV4 | MLX4_CQE_STATUS_IPV6) +#else +#define MLX4_CQE_STATUS_IP_ANY (MLX4_CQE_STATUS_IPV4) +#endif + int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int budget) { struct mlx4_en_priv *priv = netdev_priv(dev); @@ -662,12 +668,9 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud int polled = 0; int index; - if (unlikely(!priv->port_up)) + if (unlikely(!priv->port_up || budget <= 0)) return 0; - if (unlikely(budget <= 0)) - return polled; - ring = priv->rx_ring[cq_ring]; /* Protect accesses to: ring->xdp_prog, priv->mac_hash list */ @@ -838,12 +841,7 @@ xdp_drop_no_cnt: ring->csum_ok++; } else { if (!(priv->flags & MLX4_EN_FLAG_RX_CSUM_NON_TCP_UDP && - (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV4 | -#if IS_ENABLED(CONFIG_IPV6) - MLX4_CQE_STATUS_IPV6)))) -#else - 0)))) -#endif + (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IP_ANY)))) goto csum_none; if (check_csum(cqe, skb, va, dev->features)) goto csum_none; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index f470ae37d937..f7c81133594f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -608,6 +608,7 @@ struct mlx4_en_priv { struct mlx4_en_flow_stats_tx tx_flowstats; struct mlx4_en_port_stats port_stats; struct mlx4_en_xdp_stats xdp_stats; + struct mlx4_en_phy_stats phy_stats; struct mlx4_en_stats_bitmap stats_bitmap; struct list_head mc_list; struct list_head curr_list; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h index aab28eb27a30..86b6051da8ec 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h @@ -63,6 +63,14 @@ struct mlx4_en_xdp_stats { #define NUM_XDP_STATS 3 }; +struct mlx4_en_phy_stats { + unsigned long rx_packets_phy; + unsigned long rx_bytes_phy; + unsigned long tx_packets_phy; + unsigned long tx_bytes_phy; +#define NUM_PHY_STATS 4 +}; + #define NUM_MAIN_STATS 21 #define MLX4_NUM_PRIORITIES 8 @@ -116,7 +124,7 @@ enum { #define NUM_ALL_STATS (NUM_MAIN_STATS + NUM_PORT_STATS + NUM_PKT_STATS + \ NUM_FLOW_STATS + NUM_PERF_STATS + NUM_PF_STATS + \ - NUM_XDP_STATS) + NUM_XDP_STATS + NUM_PHY_STATS) #define MLX4_FIND_NETDEV_STAT(n) (offsetof(struct net_device_stats, n) / \ sizeof(((struct net_device_stats *)0)->n)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c index 0be4575b58a2..fd509160c8f6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c @@ -96,10 +96,10 @@ static void print_lyr_2_4_hdrs(struct trace_seq *p, "%pI4"); } else if (ethertype.v == ETH_P_IPV6) { static const struct in6_addr full_ones = { - .in6_u.u6_addr32 = {htonl(0xffffffff), - htonl(0xffffffff), - htonl(0xffffffff), - htonl(0xffffffff)}, + .in6_u.u6_addr32 = {__constant_htonl(0xffffffff), + __constant_htonl(0xffffffff), + __constant_htonl(0xffffffff), + __constant_htonl(0xffffffff)}, }; DECLARE_MASK_VAL(struct in6_addr, src_ipv6); DECLARE_MASK_VAL(struct in6_addr, dst_ipv6); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 47bab842c5ee..da94c8cba5ee 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1768,13 +1768,16 @@ static void mlx5e_build_rq_param(struct mlx5e_priv *priv, param->wq.linear = 1; } -static void mlx5e_build_drop_rq_param(struct mlx5e_rq_param *param) +static void mlx5e_build_drop_rq_param(struct mlx5_core_dev *mdev, + struct mlx5e_rq_param *param) { void *rqc = param->rqc; void *wq = MLX5_ADDR_OF(rqc, rqc, wq); MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_LINKED_LIST); MLX5_SET(wq, wq, log_wq_stride, ilog2(sizeof(struct mlx5e_rx_wqe))); + + param->wq.buf_numa_node = dev_to_node(&mdev->pdev->dev); } static void mlx5e_build_sq_param_common(struct mlx5e_priv *priv, @@ -2634,6 +2637,9 @@ static int mlx5e_alloc_drop_cq(struct mlx5_core_dev *mdev, struct mlx5e_cq *cq, struct mlx5e_cq_param *param) { + param->wq.buf_numa_node = dev_to_node(&mdev->pdev->dev); + param->wq.db_numa_node = dev_to_node(&mdev->pdev->dev); + return mlx5e_alloc_cq_common(mdev, param, cq); } @@ -2645,7 +2651,7 @@ static int mlx5e_open_drop_rq(struct mlx5_core_dev *mdev, struct mlx5e_cq *cq = &drop_rq->cq; int err; - mlx5e_build_drop_rq_param(&rq_param); + mlx5e_build_drop_rq_param(mdev, &rq_param); err = mlx5e_alloc_drop_cq(mdev, cq, &cq_param); if (err) @@ -2994,8 +3000,8 @@ static int mlx5e_setup_tc_block(struct net_device *dev, } #endif -int mlx5e_setup_tc(struct net_device *dev, enum tc_setup_type type, - void *type_data) +static int mlx5e_setup_tc(struct net_device *dev, enum tc_setup_type type, + void *type_data) { switch (type) { #ifdef CONFIG_MLX5_ESWITCH diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 80b84f6af2a1..8cce90dc461d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -36,6 +36,7 @@ #include <linux/tcp.h> #include <linux/bpf_trace.h> #include <net/busy_poll.h> +#include <net/ip6_checksum.h> #include "en.h" #include "en_tc.h" #include "eswitch.h" @@ -547,20 +548,33 @@ bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq) return true; } +static void mlx5e_lro_update_tcp_hdr(struct mlx5_cqe64 *cqe, struct tcphdr *tcp) +{ + u8 l4_hdr_type = get_cqe_l4_hdr_type(cqe); + u8 tcp_ack = (l4_hdr_type == CQE_L4_HDR_TYPE_TCP_ACK_NO_DATA) || + (l4_hdr_type == CQE_L4_HDR_TYPE_TCP_ACK_AND_DATA); + + tcp->check = 0; + tcp->psh = get_cqe_lro_tcppsh(cqe); + + if (tcp_ack) { + tcp->ack = 1; + tcp->ack_seq = cqe->lro_ack_seq_num; + tcp->window = cqe->lro_tcp_win; + } +} + static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe, u32 cqe_bcnt) { struct ethhdr *eth = (struct ethhdr *)(skb->data); struct tcphdr *tcp; int network_depth = 0; + __wsum check; __be16 proto; u16 tot_len; void *ip_p; - u8 l4_hdr_type = get_cqe_l4_hdr_type(cqe); - u8 tcp_ack = (l4_hdr_type == CQE_L4_HDR_TYPE_TCP_ACK_NO_DATA) || - (l4_hdr_type == CQE_L4_HDR_TYPE_TCP_ACK_AND_DATA); - proto = __vlan_get_protocol(skb, eth->h_proto, &network_depth); tot_len = cqe_bcnt - network_depth; @@ -577,23 +591,30 @@ static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe, ipv4->check = 0; ipv4->check = ip_fast_csum((unsigned char *)ipv4, ipv4->ihl); + + mlx5e_lro_update_tcp_hdr(cqe, tcp); + check = csum_partial(tcp, tcp->doff * 4, + csum_unfold((__force __sum16)cqe->check_sum)); + /* Almost done, don't forget the pseudo header */ + tcp->check = csum_tcpudp_magic(ipv4->saddr, ipv4->daddr, + tot_len - sizeof(struct iphdr), + IPPROTO_TCP, check); } else { + u16 payload_len = tot_len - sizeof(struct ipv6hdr); struct ipv6hdr *ipv6 = ip_p; tcp = ip_p + sizeof(struct ipv6hdr); skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; ipv6->hop_limit = cqe->lro_min_ttl; - ipv6->payload_len = cpu_to_be16(tot_len - - sizeof(struct ipv6hdr)); - } - - tcp->psh = get_cqe_lro_tcppsh(cqe); - - if (tcp_ack) { - tcp->ack = 1; - tcp->ack_seq = cqe->lro_ack_seq_num; - tcp->window = cqe->lro_tcp_win; + ipv6->payload_len = cpu_to_be16(payload_len); + + mlx5e_lro_update_tcp_hdr(cqe, tcp); + check = csum_partial(tcp, tcp->doff * 4, + csum_unfold((__force __sum16)cqe->check_sum)); + /* Almost done, don't forget the pseudo header */ + tcp->check = csum_ipv6_magic(&ipv6->saddr, &ipv6->daddr, payload_len, + IPPROTO_TCP, check); } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c index 5a4608281f38..707976482c09 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c @@ -216,7 +216,8 @@ mlx5e_test_loopback_validate(struct sk_buff *skb, if (iph->protocol != IPPROTO_UDP) goto out; - udph = udp_hdr(skb); + /* Don't assume skb_transport_header() was set */ + udph = (struct udphdr *)((u8 *)iph + 4 * iph->ihl); if (udph->dest != htons(9)) goto out; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index fd98b0dc610f..fa86a1466718 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -2529,7 +2529,8 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, if (tcf_vlan_action(a) == TCA_VLAN_ACT_POP) { attr->action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP; } else if (tcf_vlan_action(a) == TCA_VLAN_ACT_PUSH) { - if (tcf_vlan_push_proto(a) != htons(ETH_P_8021Q)) + if (tcf_vlan_push_proto(a) != htons(ETH_P_8021Q) || + tcf_vlan_push_prio(a)) return -EOPNOTSUPP; attr->action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 569b42a01026..11b4f1089d1c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -176,7 +176,7 @@ static inline u16 mlx5e_calc_min_inline(enum mlx5_inline_modes mode, default: hlen = mlx5e_skb_l2_header_offset(skb); } - return min_t(u16, hlen, skb->len); + return min_t(u16, hlen, skb_headlen(skb)); } static inline void mlx5e_tx_skb_pull_inline(unsigned char **skb_data, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 964cd8c4fdcc..77b7272eaaa8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1529,6 +1529,10 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num, esw_debug(esw->dev, "Enabling VPORT(%d)\n", vport_num); + /* Create steering drop counters for ingress and egress ACLs */ + if (vport_num && esw->mode == SRIOV_LEGACY) + esw_vport_create_drop_counters(vport); + /* Restore old vport configuration */ esw_apply_vport_conf(esw, vport); @@ -1545,10 +1549,6 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num, if (!vport_num) vport->info.trusted = true; - /* create steering drop counters for ingress and egress ACLs */ - if (vport_num && esw->mode == SRIOV_LEGACY) - esw_vport_create_drop_counters(vport); - esw_vport_change_handle_locked(vport); esw->enabled_vports++; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index c025c98700e4..31fc2cfac3b3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1429,7 +1429,8 @@ static bool check_conflicting_actions(u32 action1, u32 action2) if (xored_actions & (MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_ENCAP | - MLX5_FLOW_CONTEXT_ACTION_DECAP)) + MLX5_FLOW_CONTEXT_ACTION_DECAP | + MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)) return true; return false; @@ -1758,8 +1759,11 @@ search_again_locked: /* Collect all fgs which has a matching match_criteria */ err = build_match_list(&match_head, ft, spec); - if (err) + if (err) { + if (take_write) + up_write_ref_node(&ft->node); return ERR_PTR(err); + } if (!take_write) up_read_ref_node(&ft->node); @@ -1768,8 +1772,11 @@ search_again_locked: dest_num, version); free_match_list(&match_head); if (!IS_ERR(rule) || - (PTR_ERR(rule) != -ENOENT && PTR_ERR(rule) != -EAGAIN)) + (PTR_ERR(rule) != -ENOENT && PTR_ERR(rule) != -EAGAIN)) { + if (take_write) + up_write_ref_node(&ft->node); return rule; + } if (!take_write) { nested_down_write_ref_node(&ft->node, FS_LOCK_GRANDPARENT); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index e159243e0fcf..857035583ccd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -34,6 +34,7 @@ #include <linux/highmem.h> #include <rdma/mlx5-abi.h> #include "en.h" +#include "clock.h" enum { MLX5_CYCLES_SHIFT = 23 diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 8cc22bf80c87..7142c90d4669 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -551,7 +551,7 @@ static int handle_hca_cap(struct mlx5_core_dev *dev) MLX5_SET(cmd_hca_cap, set_hca_cap, cache_line_128byte, - cache_line_size() == 128 ? 1 : 0); + cache_line_size() >= 128 ? 1 : 0); if (MLX5_CAP_GEN_MAX(dev, dct)) MLX5_SET(cmd_hca_cap, set_hca_cap, dct, 1); diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig index d56eea310509..93d97b4676eb 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig +++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig @@ -78,6 +78,10 @@ config MLXSW_SPECTRUM depends on IPV6 || IPV6=n select PARMAN select MLXFW + depends on NET_IPGRE + depends on !(MLXSW_CORE=y && NET_IPGRE=m) + depends on IPV6_GRE + depends on !(MLXSW_CORE=y && IPV6_GRE=m) default m ---help--- This driver supports Mellanox Technologies Spectrum Ethernet diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile index 9463c3fa254f..0cadcabfe86f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Makefile +++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile @@ -20,7 +20,7 @@ mlxsw_spectrum-objs := spectrum.o spectrum_buffers.o \ spectrum_cnt.o spectrum_fid.o \ spectrum_ipip.o spectrum_acl_flex_actions.o \ spectrum_mr.o spectrum_mr_tcam.o \ - spectrum_qdisc.o + spectrum_qdisc.o spectrum_span.o mlxsw_spectrum-$(CONFIG_MLXSW_SPECTRUM_DCB) += spectrum_dcb.o mlxsw_spectrum-$(CONFIG_NET_DEVLINK) += spectrum_dpipe.o obj-$(CONFIG_MLXSW_MINIMAL) += mlxsw_minimal.o diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c index b698fb481b2e..ba338428ffd1 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c @@ -1,6 +1,6 @@ /* * drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c - * Copyright (c) 2017 Mellanox Technologies. All rights reserved. + * Copyright (c) 2017, 2018 Mellanox Technologies. All rights reserved. * Copyright (c) 2017 Jiri Pirko <jiri@mellanox.com> * * Redistribution and use in source and binary forms, with or without @@ -838,7 +838,6 @@ struct mlxsw_afa_mirror { struct mlxsw_afa_resource resource; int span_id; u8 local_in_port; - u8 local_out_port; bool ingress; }; @@ -848,7 +847,7 @@ mlxsw_afa_mirror_destroy(struct mlxsw_afa_block *block, { block->afa->ops->mirror_del(block->afa->ops_priv, mirror->local_in_port, - mirror->local_out_port, + mirror->span_id, mirror->ingress); kfree(mirror); } @@ -864,9 +863,8 @@ mlxsw_afa_mirror_destructor(struct mlxsw_afa_block *block, } static struct mlxsw_afa_mirror * -mlxsw_afa_mirror_create(struct mlxsw_afa_block *block, - u8 local_in_port, u8 local_out_port, - bool ingress) +mlxsw_afa_mirror_create(struct mlxsw_afa_block *block, u8 local_in_port, + const struct net_device *out_dev, bool ingress) { struct mlxsw_afa_mirror *mirror; int err; @@ -876,13 +874,12 @@ mlxsw_afa_mirror_create(struct mlxsw_afa_block *block, return ERR_PTR(-ENOMEM); err = block->afa->ops->mirror_add(block->afa->ops_priv, - local_in_port, local_out_port, + local_in_port, out_dev, ingress, &mirror->span_id); if (err) goto err_mirror_add; mirror->ingress = ingress; - mirror->local_out_port = local_out_port; mirror->local_in_port = local_in_port; mirror->resource.destructor = mlxsw_afa_mirror_destructor; mlxsw_afa_resource_add(block, &mirror->resource); @@ -909,13 +906,13 @@ mlxsw_afa_block_append_allocated_mirror(struct mlxsw_afa_block *block, } int -mlxsw_afa_block_append_mirror(struct mlxsw_afa_block *block, - u8 local_in_port, u8 local_out_port, bool ingress) +mlxsw_afa_block_append_mirror(struct mlxsw_afa_block *block, u8 local_in_port, + const struct net_device *out_dev, bool ingress) { struct mlxsw_afa_mirror *mirror; int err; - mirror = mlxsw_afa_mirror_create(block, local_in_port, local_out_port, + mirror = mlxsw_afa_mirror_create(block, local_in_port, out_dev, ingress); if (IS_ERR(mirror)) return PTR_ERR(mirror); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h index 43132293475c..6dd601703c99 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h @@ -36,6 +36,7 @@ #define _MLXSW_CORE_ACL_FLEX_ACTIONS_H #include <linux/types.h> +#include <linux/netdevice.h> struct mlxsw_afa; struct mlxsw_afa_block; @@ -48,9 +49,10 @@ struct mlxsw_afa_ops { void (*kvdl_fwd_entry_del)(void *priv, u32 kvdl_index); int (*counter_index_get)(void *priv, unsigned int *p_counter_index); void (*counter_index_put)(void *priv, unsigned int counter_index); - int (*mirror_add)(void *priv, u8 locol_in_port, u8 local_out_port, + int (*mirror_add)(void *priv, u8 local_in_port, + const struct net_device *out_dev, bool ingress, int *p_span_id); - void (*mirror_del)(void *priv, u8 locol_in_port, u8 local_out_port, + void (*mirror_del)(void *priv, u8 local_in_port, int span_id, bool ingress); }; @@ -70,7 +72,8 @@ int mlxsw_afa_block_append_trap(struct mlxsw_afa_block *block, u16 trap_id); int mlxsw_afa_block_append_trap_and_forward(struct mlxsw_afa_block *block, u16 trap_id); int mlxsw_afa_block_append_mirror(struct mlxsw_afa_block *block, - u8 local_in_port, u8 local_out_port, + u8 local_in_port, + const struct net_device *out_dev, bool ingress); int mlxsw_afa_block_append_fwd(struct mlxsw_afa_block *block, u8 local_port, bool in_port); diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 0e08be41c8e0..cb5f77f09f8e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -1,11 +1,11 @@ /* * drivers/net/ethernet/mellanox/mlxsw/reg.h - * Copyright (c) 2015-2017 Mellanox Technologies. All rights reserved. + * Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved. * Copyright (c) 2015-2016 Ido Schimmel <idosch@mellanox.com> * Copyright (c) 2015 Elad Raz <eladr@mellanox.com> * Copyright (c) 2015-2017 Jiri Pirko <jiri@mellanox.com> * Copyright (c) 2016 Yotam Gigi <yotamg@mellanox.com> - * Copyright (c) 2017 Petr Machata <petrm@mellanox.com> + * Copyright (c) 2017-2018 Petr Machata <petrm@mellanox.com> * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -6772,8 +6772,104 @@ MLXSW_ITEM32(reg, mpat, qos, 0x04, 26, 1); */ MLXSW_ITEM32(reg, mpat, be, 0x04, 25, 1); +enum mlxsw_reg_mpat_span_type { + /* Local SPAN Ethernet. + * The original packet is not encapsulated. + */ + MLXSW_REG_MPAT_SPAN_TYPE_LOCAL_ETH = 0x0, + + /* Encapsulated Remote SPAN Ethernet L3 GRE. + * The packet is encapsulated with GRE header. + */ + MLXSW_REG_MPAT_SPAN_TYPE_REMOTE_ETH_L3 = 0x3, +}; + +/* reg_mpat_span_type + * SPAN type. + * Access: RW + */ +MLXSW_ITEM32(reg, mpat, span_type, 0x04, 0, 4); + +/* Remote SPAN - Ethernet VLAN + * - - - - - - - - - - - - - - + */ + +/* reg_mpat_eth_rspan_vid + * Encapsulation header VLAN ID. + * Access: RW + */ +MLXSW_ITEM32(reg, mpat, eth_rspan_vid, 0x18, 0, 12); + +/* Encapsulated Remote SPAN - Ethernet L2 + * - - - - - - - - - - - - - - - - - - - + */ + +enum mlxsw_reg_mpat_eth_rspan_version { + MLXSW_REG_MPAT_ETH_RSPAN_VERSION_NO_HEADER = 15, +}; + +/* reg_mpat_eth_rspan_version + * RSPAN mirror header version. + * Access: RW + */ +MLXSW_ITEM32(reg, mpat, eth_rspan_version, 0x10, 18, 4); + +/* reg_mpat_eth_rspan_mac + * Destination MAC address. + * Access: RW + */ +MLXSW_ITEM_BUF(reg, mpat, eth_rspan_mac, 0x12, 6); + +/* reg_mpat_eth_rspan_tp + * Tag Packet. Indicates whether the mirroring header should be VLAN tagged. + * Access: RW + */ +MLXSW_ITEM32(reg, mpat, eth_rspan_tp, 0x18, 16, 1); + +/* Encapsulated Remote SPAN - Ethernet L3 + * - - - - - - - - - - - - - - - - - - - + */ + +enum mlxsw_reg_mpat_eth_rspan_protocol { + MLXSW_REG_MPAT_ETH_RSPAN_PROTOCOL_IPV4, + MLXSW_REG_MPAT_ETH_RSPAN_PROTOCOL_IPV6, +}; + +/* reg_mpat_eth_rspan_protocol + * SPAN encapsulation protocol. + * Access: RW + */ +MLXSW_ITEM32(reg, mpat, eth_rspan_protocol, 0x18, 24, 4); + +/* reg_mpat_eth_rspan_ttl + * Encapsulation header Time-to-Live/HopLimit. + * Access: RW + */ +MLXSW_ITEM32(reg, mpat, eth_rspan_ttl, 0x1C, 4, 8); + +/* reg_mpat_eth_rspan_smac + * Source MAC address + * Access: RW + */ +MLXSW_ITEM_BUF(reg, mpat, eth_rspan_smac, 0x22, 6); + +/* reg_mpat_eth_rspan_dip* + * Destination IP address. The IP version is configured by protocol. + * Access: RW + */ +MLXSW_ITEM32(reg, mpat, eth_rspan_dip4, 0x4C, 0, 32); +MLXSW_ITEM_BUF(reg, mpat, eth_rspan_dip6, 0x40, 16); + +/* reg_mpat_eth_rspan_sip* + * Source IP address. The IP version is configured by protocol. + * Access: RW + */ +MLXSW_ITEM32(reg, mpat, eth_rspan_sip4, 0x5C, 0, 32); +MLXSW_ITEM_BUF(reg, mpat, eth_rspan_sip6, 0x50, 16); + static inline void mlxsw_reg_mpat_pack(char *payload, u8 pa_id, - u16 system_port, bool e) + u16 system_port, bool e, + enum mlxsw_reg_mpat_span_type span_type) { MLXSW_REG_ZERO(mpat, payload); mlxsw_reg_mpat_pa_id_set(payload, pa_id); @@ -6781,6 +6877,49 @@ static inline void mlxsw_reg_mpat_pack(char *payload, u8 pa_id, mlxsw_reg_mpat_e_set(payload, e); mlxsw_reg_mpat_qos_set(payload, 1); mlxsw_reg_mpat_be_set(payload, 1); + mlxsw_reg_mpat_span_type_set(payload, span_type); +} + +static inline void mlxsw_reg_mpat_eth_rspan_pack(char *payload, u16 vid) +{ + mlxsw_reg_mpat_eth_rspan_vid_set(payload, vid); +} + +static inline void +mlxsw_reg_mpat_eth_rspan_l2_pack(char *payload, + enum mlxsw_reg_mpat_eth_rspan_version version, + const char *mac, + bool tp) +{ + mlxsw_reg_mpat_eth_rspan_version_set(payload, version); + mlxsw_reg_mpat_eth_rspan_mac_memcpy_to(payload, mac); + mlxsw_reg_mpat_eth_rspan_tp_set(payload, tp); +} + +static inline void +mlxsw_reg_mpat_eth_rspan_l3_ipv4_pack(char *payload, u8 ttl, + const char *smac, + u32 sip, u32 dip) +{ + mlxsw_reg_mpat_eth_rspan_ttl_set(payload, ttl); + mlxsw_reg_mpat_eth_rspan_smac_memcpy_to(payload, smac); + mlxsw_reg_mpat_eth_rspan_protocol_set(payload, + MLXSW_REG_MPAT_ETH_RSPAN_PROTOCOL_IPV4); + mlxsw_reg_mpat_eth_rspan_sip4_set(payload, sip); + mlxsw_reg_mpat_eth_rspan_dip4_set(payload, dip); +} + +static inline void +mlxsw_reg_mpat_eth_rspan_l3_ipv6_pack(char *payload, u8 ttl, + const char *smac, + struct in6_addr sip, struct in6_addr dip) +{ + mlxsw_reg_mpat_eth_rspan_ttl_set(payload, ttl); + mlxsw_reg_mpat_eth_rspan_smac_memcpy_to(payload, smac); + mlxsw_reg_mpat_eth_rspan_protocol_set(payload, + MLXSW_REG_MPAT_ETH_RSPAN_PROTOCOL_IPV6); + mlxsw_reg_mpat_eth_rspan_sip6_memcpy_to(payload, (void *)&sip); + mlxsw_reg_mpat_eth_rspan_dip6_memcpy_to(payload, (void *)&dip); } /* MPAR - Monitoring Port Analyzer Register diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 3dcc58d61506..8d2d140d7910 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -1,6 +1,6 @@ /* * drivers/net/ethernet/mellanox/mlxsw/spectrum.c - * Copyright (c) 2015-2017 Mellanox Technologies. All rights reserved. + * Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved. * Copyright (c) 2015-2017 Jiri Pirko <jiri@mellanox.com> * Copyright (c) 2015 Ido Schimmel <idosch@mellanox.com> * Copyright (c) 2015 Elad Raz <eladr@mellanox.com> @@ -71,6 +71,7 @@ #include "spectrum_cnt.h" #include "spectrum_dpipe.h" #include "spectrum_acl_flex_actions.h" +#include "spectrum_span.h" #include "../mlxfw/mlxfw.h" #define MLXSW_FWREV_MAJOR 13 @@ -487,327 +488,6 @@ static int mlxsw_sp_base_mac_get(struct mlxsw_sp *mlxsw_sp) return 0; } -static int mlxsw_sp_span_init(struct mlxsw_sp *mlxsw_sp) -{ - int i; - - if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_SPAN)) - return -EIO; - - mlxsw_sp->span.entries_count = MLXSW_CORE_RES_GET(mlxsw_sp->core, - MAX_SPAN); - mlxsw_sp->span.entries = kcalloc(mlxsw_sp->span.entries_count, - sizeof(struct mlxsw_sp_span_entry), - GFP_KERNEL); - if (!mlxsw_sp->span.entries) - return -ENOMEM; - - for (i = 0; i < mlxsw_sp->span.entries_count; i++) - INIT_LIST_HEAD(&mlxsw_sp->span.entries[i].bound_ports_list); - - return 0; -} - -static void mlxsw_sp_span_fini(struct mlxsw_sp *mlxsw_sp) -{ - int i; - - for (i = 0; i < mlxsw_sp->span.entries_count; i++) { - struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i]; - - WARN_ON_ONCE(!list_empty(&curr->bound_ports_list)); - } - kfree(mlxsw_sp->span.entries); -} - -static struct mlxsw_sp_span_entry * -mlxsw_sp_span_entry_create(struct mlxsw_sp_port *port) -{ - struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; - struct mlxsw_sp_span_entry *span_entry; - char mpat_pl[MLXSW_REG_MPAT_LEN]; - u8 local_port = port->local_port; - int index; - int i; - int err; - - /* find a free entry to use */ - index = -1; - for (i = 0; i < mlxsw_sp->span.entries_count; i++) { - if (!mlxsw_sp->span.entries[i].used) { - index = i; - span_entry = &mlxsw_sp->span.entries[i]; - break; - } - } - if (index < 0) - return NULL; - - /* create a new port analayzer entry for local_port */ - mlxsw_reg_mpat_pack(mpat_pl, index, local_port, true); - err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mpat), mpat_pl); - if (err) - return NULL; - - span_entry->used = true; - span_entry->id = index; - span_entry->ref_count = 1; - span_entry->local_port = local_port; - return span_entry; -} - -static void mlxsw_sp_span_entry_destroy(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_span_entry *span_entry) -{ - u8 local_port = span_entry->local_port; - char mpat_pl[MLXSW_REG_MPAT_LEN]; - int pa_id = span_entry->id; - - mlxsw_reg_mpat_pack(mpat_pl, pa_id, local_port, false); - mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mpat), mpat_pl); - span_entry->used = false; -} - -struct mlxsw_sp_span_entry * -mlxsw_sp_span_entry_find(struct mlxsw_sp *mlxsw_sp, u8 local_port) -{ - int i; - - for (i = 0; i < mlxsw_sp->span.entries_count; i++) { - struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i]; - - if (curr->used && curr->local_port == local_port) - return curr; - } - return NULL; -} - -static struct mlxsw_sp_span_entry -*mlxsw_sp_span_entry_get(struct mlxsw_sp_port *port) -{ - struct mlxsw_sp_span_entry *span_entry; - - span_entry = mlxsw_sp_span_entry_find(port->mlxsw_sp, - port->local_port); - if (span_entry) { - /* Already exists, just take a reference */ - span_entry->ref_count++; - return span_entry; - } - - return mlxsw_sp_span_entry_create(port); -} - -static int mlxsw_sp_span_entry_put(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_span_entry *span_entry) -{ - WARN_ON(!span_entry->ref_count); - if (--span_entry->ref_count == 0) - mlxsw_sp_span_entry_destroy(mlxsw_sp, span_entry); - return 0; -} - -static bool mlxsw_sp_span_is_egress_mirror(struct mlxsw_sp_port *port) -{ - struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; - struct mlxsw_sp_span_inspected_port *p; - int i; - - for (i = 0; i < mlxsw_sp->span.entries_count; i++) { - struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i]; - - list_for_each_entry(p, &curr->bound_ports_list, list) - if (p->local_port == port->local_port && - p->type == MLXSW_SP_SPAN_EGRESS) - return true; - } - - return false; -} - -static int mlxsw_sp_span_mtu_to_buffsize(const struct mlxsw_sp *mlxsw_sp, - int mtu) -{ - return mlxsw_sp_bytes_cells(mlxsw_sp, mtu * 5 / 2) + 1; -} - -static int mlxsw_sp_span_port_mtu_update(struct mlxsw_sp_port *port, u16 mtu) -{ - struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; - char sbib_pl[MLXSW_REG_SBIB_LEN]; - int err; - - /* If port is egress mirrored, the shared buffer size should be - * updated according to the mtu value - */ - if (mlxsw_sp_span_is_egress_mirror(port)) { - u32 buffsize = mlxsw_sp_span_mtu_to_buffsize(mlxsw_sp, mtu); - - mlxsw_reg_sbib_pack(sbib_pl, port->local_port, buffsize); - err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl); - if (err) { - netdev_err(port->dev, "Could not update shared buffer for mirroring\n"); - return err; - } - } - - return 0; -} - -static struct mlxsw_sp_span_inspected_port * -mlxsw_sp_span_entry_bound_port_find(struct mlxsw_sp_port *port, - struct mlxsw_sp_span_entry *span_entry) -{ - struct mlxsw_sp_span_inspected_port *p; - - list_for_each_entry(p, &span_entry->bound_ports_list, list) - if (port->local_port == p->local_port) - return p; - return NULL; -} - -static int -mlxsw_sp_span_inspected_port_bind(struct mlxsw_sp_port *port, - struct mlxsw_sp_span_entry *span_entry, - enum mlxsw_sp_span_type type, - bool bind) -{ - struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; - char mpar_pl[MLXSW_REG_MPAR_LEN]; - int pa_id = span_entry->id; - - /* bind the port to the SPAN entry */ - mlxsw_reg_mpar_pack(mpar_pl, port->local_port, - (enum mlxsw_reg_mpar_i_e) type, bind, pa_id); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mpar), mpar_pl); -} - -static int -mlxsw_sp_span_inspected_port_add(struct mlxsw_sp_port *port, - struct mlxsw_sp_span_entry *span_entry, - enum mlxsw_sp_span_type type, - bool bind) -{ - struct mlxsw_sp_span_inspected_port *inspected_port; - struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; - char sbib_pl[MLXSW_REG_SBIB_LEN]; - int err; - - /* if it is an egress SPAN, bind a shared buffer to it */ - if (type == MLXSW_SP_SPAN_EGRESS) { - u32 buffsize = mlxsw_sp_span_mtu_to_buffsize(mlxsw_sp, - port->dev->mtu); - - mlxsw_reg_sbib_pack(sbib_pl, port->local_port, buffsize); - err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl); - if (err) { - netdev_err(port->dev, "Could not create shared buffer for mirroring\n"); - return err; - } - } - - if (bind) { - err = mlxsw_sp_span_inspected_port_bind(port, span_entry, type, - true); - if (err) - goto err_port_bind; - } - - inspected_port = kzalloc(sizeof(*inspected_port), GFP_KERNEL); - if (!inspected_port) { - err = -ENOMEM; - goto err_inspected_port_alloc; - } - inspected_port->local_port = port->local_port; - inspected_port->type = type; - list_add_tail(&inspected_port->list, &span_entry->bound_ports_list); - - return 0; - -err_inspected_port_alloc: - if (bind) - mlxsw_sp_span_inspected_port_bind(port, span_entry, type, - false); -err_port_bind: - if (type == MLXSW_SP_SPAN_EGRESS) { - mlxsw_reg_sbib_pack(sbib_pl, port->local_port, 0); - mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl); - } - return err; -} - -static void -mlxsw_sp_span_inspected_port_del(struct mlxsw_sp_port *port, - struct mlxsw_sp_span_entry *span_entry, - enum mlxsw_sp_span_type type, - bool bind) -{ - struct mlxsw_sp_span_inspected_port *inspected_port; - struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; - char sbib_pl[MLXSW_REG_SBIB_LEN]; - - inspected_port = mlxsw_sp_span_entry_bound_port_find(port, span_entry); - if (!inspected_port) - return; - - if (bind) - mlxsw_sp_span_inspected_port_bind(port, span_entry, type, - false); - /* remove the SBIB buffer if it was egress SPAN */ - if (type == MLXSW_SP_SPAN_EGRESS) { - mlxsw_reg_sbib_pack(sbib_pl, port->local_port, 0); - mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl); - } - - mlxsw_sp_span_entry_put(mlxsw_sp, span_entry); - - list_del(&inspected_port->list); - kfree(inspected_port); -} - -int mlxsw_sp_span_mirror_add(struct mlxsw_sp_port *from, - struct mlxsw_sp_port *to, - enum mlxsw_sp_span_type type, bool bind) -{ - struct mlxsw_sp *mlxsw_sp = from->mlxsw_sp; - struct mlxsw_sp_span_entry *span_entry; - int err; - - span_entry = mlxsw_sp_span_entry_get(to); - if (!span_entry) - return -ENOENT; - - netdev_dbg(from->dev, "Adding inspected port to SPAN entry %d\n", - span_entry->id); - - err = mlxsw_sp_span_inspected_port_add(from, span_entry, type, bind); - if (err) - goto err_port_bind; - - return 0; - -err_port_bind: - mlxsw_sp_span_entry_put(mlxsw_sp, span_entry); - return err; -} - -void mlxsw_sp_span_mirror_del(struct mlxsw_sp_port *from, u8 destination_port, - enum mlxsw_sp_span_type type, bool bind) -{ - struct mlxsw_sp_span_entry *span_entry; - - span_entry = mlxsw_sp_span_entry_find(from->mlxsw_sp, - destination_port); - if (!span_entry) { - netdev_err(from->dev, "no span entry found\n"); - return; - } - - netdev_dbg(from->dev, "removing inspected port from SPAN entry %d\n", - span_entry->id); - mlxsw_sp_span_inspected_port_del(from, span_entry, type, bind); -} - static int mlxsw_sp_port_sample_set(struct mlxsw_sp_port *mlxsw_sp_port, bool enable, u32 rate) { @@ -1578,7 +1258,6 @@ mlxsw_sp_port_add_cls_matchall_mirror(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress) { enum mlxsw_sp_span_type span_type; - struct mlxsw_sp_port *to_port; struct net_device *to_dev; to_dev = tcf_mirred_dev(a); @@ -1587,17 +1266,10 @@ mlxsw_sp_port_add_cls_matchall_mirror(struct mlxsw_sp_port *mlxsw_sp_port, return -EINVAL; } - if (!mlxsw_sp_port_dev_check(to_dev)) { - netdev_err(mlxsw_sp_port->dev, "Cannot mirror to a non-spectrum port"); - return -EOPNOTSUPP; - } - to_port = netdev_priv(to_dev); - - mirror->to_local_port = to_port->local_port; mirror->ingress = ingress; span_type = ingress ? MLXSW_SP_SPAN_INGRESS : MLXSW_SP_SPAN_EGRESS; - return mlxsw_sp_span_mirror_add(mlxsw_sp_port, to_port, span_type, - true); + return mlxsw_sp_span_mirror_add(mlxsw_sp_port, to_dev, span_type, + true, &mirror->span_id); } static void @@ -1608,7 +1280,7 @@ mlxsw_sp_port_del_cls_matchall_mirror(struct mlxsw_sp_port *mlxsw_sp_port, span_type = mirror->ingress ? MLXSW_SP_SPAN_INGRESS : MLXSW_SP_SPAN_EGRESS; - mlxsw_sp_span_mirror_del(mlxsw_sp_port, mirror->to_local_port, + mlxsw_sp_span_mirror_del(mlxsw_sp_port, mirror->span_id, span_type, true); } @@ -3995,14 +3667,24 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, goto err_afa_init; } + err = mlxsw_sp_span_init(mlxsw_sp); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Failed to init span system\n"); + goto err_span_init; + } + + /* Initialize router after SPAN is initialized, so that the FIB and + * neighbor event handlers can issue SPAN respin. + */ err = mlxsw_sp_router_init(mlxsw_sp); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize router\n"); goto err_router_init; } - /* Initialize netdevice notifier after router is initialized, so that - * the event handler can use router structures. + /* Initialize netdevice notifier after router and SPAN is initialized, + * so that the event handler can use router structures and call SPAN + * respin. */ mlxsw_sp->netdevice_nb.notifier_call = mlxsw_sp_netdevice_event; err = register_netdevice_notifier(&mlxsw_sp->netdevice_nb); @@ -4011,12 +3693,6 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, goto err_netdev_notifier; } - err = mlxsw_sp_span_init(mlxsw_sp); - if (err) { - dev_err(mlxsw_sp->bus_info->dev, "Failed to init span system\n"); - goto err_span_init; - } - err = mlxsw_sp_acl_init(mlxsw_sp); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize ACL\n"); @@ -4042,12 +3718,12 @@ err_ports_create: err_dpipe_init: mlxsw_sp_acl_fini(mlxsw_sp); err_acl_init: - mlxsw_sp_span_fini(mlxsw_sp); -err_span_init: unregister_netdevice_notifier(&mlxsw_sp->netdevice_nb); err_netdev_notifier: mlxsw_sp_router_fini(mlxsw_sp); err_router_init: + mlxsw_sp_span_fini(mlxsw_sp); +err_span_init: mlxsw_sp_afa_fini(mlxsw_sp); err_afa_init: mlxsw_sp_counter_pool_fini(mlxsw_sp); @@ -4073,9 +3749,9 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core) mlxsw_sp_ports_remove(mlxsw_sp); mlxsw_sp_dpipe_fini(mlxsw_sp); mlxsw_sp_acl_fini(mlxsw_sp); - mlxsw_sp_span_fini(mlxsw_sp); unregister_netdevice_notifier(&mlxsw_sp->netdevice_nb); mlxsw_sp_router_fini(mlxsw_sp); + mlxsw_sp_span_fini(mlxsw_sp); mlxsw_sp_afa_fini(mlxsw_sp); mlxsw_sp_counter_pool_fini(mlxsw_sp); mlxsw_sp_switchdev_fini(mlxsw_sp); @@ -4118,70 +3794,6 @@ static const struct mlxsw_config_profile mlxsw_sp_config_profile = { .resource_query_enable = 1, }; -static bool -mlxsw_sp_resource_kvd_granularity_validate(struct netlink_ext_ack *extack, - u64 size) -{ - const struct mlxsw_config_profile *profile; - - profile = &mlxsw_sp_config_profile; - if (size % profile->kvd_hash_granularity) { - NL_SET_ERR_MSG_MOD(extack, "resource set with wrong granularity"); - return false; - } - return true; -} - -static int -mlxsw_sp_resource_kvd_size_validate(struct devlink *devlink, u64 size, - struct netlink_ext_ack *extack) -{ - NL_SET_ERR_MSG_MOD(extack, "kvd size cannot be changed"); - return -EINVAL; -} - -static int -mlxsw_sp_resource_kvd_linear_size_validate(struct devlink *devlink, u64 size, - struct netlink_ext_ack *extack) -{ - if (!mlxsw_sp_resource_kvd_granularity_validate(extack, size)) - return -EINVAL; - - return 0; -} - -static int -mlxsw_sp_resource_kvd_hash_single_size_validate(struct devlink *devlink, u64 size, - struct netlink_ext_ack *extack) -{ - struct mlxsw_core *mlxsw_core = devlink_priv(devlink); - - if (!mlxsw_sp_resource_kvd_granularity_validate(extack, size)) - return -EINVAL; - - if (size < MLXSW_CORE_RES_GET(mlxsw_core, KVD_SINGLE_MIN_SIZE)) { - NL_SET_ERR_MSG_MOD(extack, "hash single size is smaller than minimum"); - return -EINVAL; - } - return 0; -} - -static int -mlxsw_sp_resource_kvd_hash_double_size_validate(struct devlink *devlink, u64 size, - struct netlink_ext_ack *extack) -{ - struct mlxsw_core *mlxsw_core = devlink_priv(devlink); - - if (!mlxsw_sp_resource_kvd_granularity_validate(extack, size)) - return -EINVAL; - - if (size < MLXSW_CORE_RES_GET(mlxsw_core, KVD_DOUBLE_MIN_SIZE)) { - NL_SET_ERR_MSG_MOD(extack, "hash double size is smaller than minimum"); - return -EINVAL; - } - return 0; -} - static u64 mlxsw_sp_resource_kvd_linear_occ_get(struct devlink *devlink) { struct mlxsw_core *mlxsw_core = devlink_priv(devlink); @@ -4190,23 +3802,10 @@ static u64 mlxsw_sp_resource_kvd_linear_occ_get(struct devlink *devlink) return mlxsw_sp_kvdl_occ_get(mlxsw_sp); } -static struct devlink_resource_ops mlxsw_sp_resource_kvd_ops = { - .size_validate = mlxsw_sp_resource_kvd_size_validate, -}; - static struct devlink_resource_ops mlxsw_sp_resource_kvd_linear_ops = { - .size_validate = mlxsw_sp_resource_kvd_linear_size_validate, .occ_get = mlxsw_sp_resource_kvd_linear_occ_get, }; -static struct devlink_resource_ops mlxsw_sp_resource_kvd_hash_single_ops = { - .size_validate = mlxsw_sp_resource_kvd_hash_single_size_validate, -}; - -static struct devlink_resource_ops mlxsw_sp_resource_kvd_hash_double_ops = { - .size_validate = mlxsw_sp_resource_kvd_hash_double_size_validate, -}; - static struct devlink_resource_size_params mlxsw_sp_kvd_size_params; static struct devlink_resource_size_params mlxsw_sp_linear_size_params; static struct devlink_resource_size_params mlxsw_sp_hash_single_size_params; @@ -4268,7 +3867,7 @@ static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core) MLXSW_SP_RESOURCE_KVD, DEVLINK_RESOURCE_ID_PARENT_TOP, &mlxsw_sp_kvd_size_params, - &mlxsw_sp_resource_kvd_ops); + NULL); if (err) return err; @@ -4282,6 +3881,10 @@ static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core) if (err) return err; + err = mlxsw_sp_kvdl_resources_register(devlink); + if (err) + return err; + double_size = kvd_size - linear_size; double_size *= profile->kvd_hash_double_parts; double_size /= profile->kvd_hash_double_parts + @@ -4292,7 +3895,7 @@ static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core) MLXSW_SP_RESOURCE_KVD_HASH_DOUBLE, MLXSW_SP_RESOURCE_KVD, &mlxsw_sp_hash_double_size_params, - &mlxsw_sp_resource_kvd_hash_double_ops); + NULL); if (err) return err; @@ -4302,7 +3905,7 @@ static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core) MLXSW_SP_RESOURCE_KVD_HASH_SINGLE, MLXSW_SP_RESOURCE_KVD, &mlxsw_sp_hash_single_size_params, - &mlxsw_sp_resource_kvd_hash_single_ops); + NULL); if (err) return err; @@ -4556,13 +4159,11 @@ mlxsw_sp_master_lag_check(struct mlxsw_sp *mlxsw_sp, u16 lag_id; if (mlxsw_sp_lag_index_get(mlxsw_sp, lag_dev, &lag_id) != 0) { - NL_SET_ERR_MSG(extack, - "spectrum: Exceeded number of supported LAG devices"); + NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported LAG devices"); return false; } if (lag_upper_info->tx_type != NETDEV_LAG_TX_TYPE_HASH) { - NL_SET_ERR_MSG(extack, - "spectrum: LAG device using unsupported Tx type"); + NL_SET_ERR_MSG_MOD(extack, "LAG device using unsupported Tx type"); return false; } return true; @@ -4804,8 +4405,7 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev, !netif_is_lag_master(upper_dev) && !netif_is_bridge_master(upper_dev) && !netif_is_ovs_master(upper_dev)) { - NL_SET_ERR_MSG(extack, - "spectrum: Unknown upper device type"); + NL_SET_ERR_MSG_MOD(extack, "Unknown upper device type"); return -EINVAL; } if (!info->linking) @@ -4814,8 +4414,7 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev, (!netif_is_bridge_master(upper_dev) || !mlxsw_sp_bridge_device_is_offloaded(mlxsw_sp, upper_dev))) { - NL_SET_ERR_MSG(extack, - "spectrum: Enslaving a port to a device that already has an upper device is not supported"); + NL_SET_ERR_MSG_MOD(extack, "Enslaving a port to a device that already has an upper device is not supported"); return -EINVAL; } if (netif_is_lag_master(upper_dev) && @@ -4823,24 +4422,20 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev, info->upper_info, extack)) return -EINVAL; if (netif_is_lag_master(upper_dev) && vlan_uses_dev(dev)) { - NL_SET_ERR_MSG(extack, - "spectrum: Master device is a LAG master and this device has a VLAN"); + NL_SET_ERR_MSG_MOD(extack, "Master device is a LAG master and this device has a VLAN"); return -EINVAL; } if (netif_is_lag_port(dev) && is_vlan_dev(upper_dev) && !netif_is_lag_master(vlan_dev_real_dev(upper_dev))) { - NL_SET_ERR_MSG(extack, - "spectrum: Can not put a VLAN on a LAG port"); + NL_SET_ERR_MSG_MOD(extack, "Can not put a VLAN on a LAG port"); return -EINVAL; } if (netif_is_ovs_master(upper_dev) && vlan_uses_dev(dev)) { - NL_SET_ERR_MSG(extack, - "spectrum: Master device is an OVS master and this device has a VLAN"); + NL_SET_ERR_MSG_MOD(extack, "Master device is an OVS master and this device has a VLAN"); return -EINVAL; } if (netif_is_ovs_port(dev) && is_vlan_dev(upper_dev)) { - NL_SET_ERR_MSG(extack, - "spectrum: Can not put a VLAN on an OVS port"); + NL_SET_ERR_MSG_MOD(extack, "Can not put a VLAN on an OVS port"); return -EINVAL; } break; @@ -4953,7 +4548,7 @@ static int mlxsw_sp_netdevice_port_vlan_event(struct net_device *vlan_dev, case NETDEV_PRECHANGEUPPER: upper_dev = info->upper_dev; if (!netif_is_bridge_master(upper_dev)) { - NL_SET_ERR_MSG(extack, "spectrum: VLAN devices only support bridge and VRF uppers"); + NL_SET_ERR_MSG_MOD(extack, "VLAN devices only support bridge and VRF uppers"); return -EINVAL; } if (!info->linking) @@ -4962,7 +4557,7 @@ static int mlxsw_sp_netdevice_port_vlan_event(struct net_device *vlan_dev, (!netif_is_bridge_master(upper_dev) || !mlxsw_sp_bridge_device_is_offloaded(mlxsw_sp, upper_dev))) { - NL_SET_ERR_MSG(extack, "spectrum: Enslaving a port to a device that already has an upper device is not supported"); + NL_SET_ERR_MSG_MOD(extack, "Enslaving a port to a device that already has an upper device is not supported"); return -EINVAL; } break; @@ -5040,10 +4635,18 @@ static int mlxsw_sp_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct mlxsw_sp_span_entry *span_entry; struct mlxsw_sp *mlxsw_sp; int err = 0; mlxsw_sp = container_of(nb, struct mlxsw_sp, netdevice_nb); + if (event == NETDEV_UNREGISTER) { + span_entry = mlxsw_sp_span_entry_find_by_port(mlxsw_sp, dev); + if (span_entry) + mlxsw_sp_span_entry_invalidate(mlxsw_sp, span_entry); + } + mlxsw_sp_span_respin(mlxsw_sp); + if (mlxsw_sp_netdev_is_ipip_ol(mlxsw_sp, dev)) err = mlxsw_sp_netdevice_ipip_ol_event(mlxsw_sp, dev, event, ptr); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index bdd8f94a452c..2673310f92da 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -70,16 +70,23 @@ #define MLXSW_SP_RESOURCE_NAME_KVD_LINEAR "linear" #define MLXSW_SP_RESOURCE_NAME_KVD_HASH_SINGLE "hash_single" #define MLXSW_SP_RESOURCE_NAME_KVD_HASH_DOUBLE "hash_double" +#define MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_SINGLES "singles" +#define MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_CHUNKS "chunks" +#define MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_LARGE_CHUNKS "large_chunks" enum mlxsw_sp_resource_id { MLXSW_SP_RESOURCE_KVD, MLXSW_SP_RESOURCE_KVD_LINEAR, MLXSW_SP_RESOURCE_KVD_HASH_SINGLE, MLXSW_SP_RESOURCE_KVD_HASH_DOUBLE, + MLXSW_SP_RESOURCE_KVD_LINEAR_SINGLE, + MLXSW_SP_RESOURCE_KVD_LINEAR_CHUNKS, + MLXSW_SP_RESOURCE_KVD_LINEAR_LARGE_CHUNKS, }; struct mlxsw_sp_port; struct mlxsw_sp_rif; +struct mlxsw_sp_span_entry; struct mlxsw_sp_upper { struct net_device *dev; @@ -111,32 +118,13 @@ struct mlxsw_sp_mid { unsigned long *ports_in_mid; /* bits array */ }; -enum mlxsw_sp_span_type { - MLXSW_SP_SPAN_EGRESS, - MLXSW_SP_SPAN_INGRESS -}; - -struct mlxsw_sp_span_inspected_port { - struct list_head list; - enum mlxsw_sp_span_type type; - u8 local_port; -}; - -struct mlxsw_sp_span_entry { - u8 local_port; - bool used; - struct list_head bound_ports_list; - int ref_count; - int id; -}; - enum mlxsw_sp_port_mall_action_type { MLXSW_SP_PORT_MALL_MIRROR, MLXSW_SP_PORT_MALL_SAMPLE, }; struct mlxsw_sp_port_mall_mirror_tc_entry { - u8 to_local_port; + int span_id; bool ingress; }; @@ -396,16 +384,6 @@ struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find(struct net_device *dev); struct mlxsw_sp_port *mlxsw_sp_port_lower_dev_hold(struct net_device *dev); void mlxsw_sp_port_dev_put(struct mlxsw_sp_port *mlxsw_sp_port); struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find_rcu(struct net_device *dev); -int mlxsw_sp_span_mirror_add(struct mlxsw_sp_port *from, - struct mlxsw_sp_port *to, - enum mlxsw_sp_span_type type, - bool bind); -void mlxsw_sp_span_mirror_del(struct mlxsw_sp_port *from, - u8 destination_port, - enum mlxsw_sp_span_type type, - bool bind); -struct mlxsw_sp_span_entry * -mlxsw_sp_span_entry_find(struct mlxsw_sp *mlxsw_sp, u8 local_port); /* spectrum_dcb.c */ #ifdef CONFIG_MLXSW_SPECTRUM_DCB @@ -461,6 +439,7 @@ int mlxsw_sp_kvdl_alloc_size_query(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count, unsigned int *p_alloc_size); u64 mlxsw_sp_kvdl_occ_get(const struct mlxsw_sp *mlxsw_sp); +int mlxsw_sp_kvdl_resources_register(struct devlink *devlink); struct mlxsw_sp_acl_rule_info { unsigned int priority; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c index 0897a5435cc2..21ed27ae51e3 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c @@ -572,7 +572,6 @@ int mlxsw_sp_acl_rulei_act_mirror(struct mlxsw_sp *mlxsw_sp, struct net_device *out_dev) { struct mlxsw_sp_acl_block_binding *binding; - struct mlxsw_sp_port *out_port; struct mlxsw_sp_port *in_port; if (!list_is_singular(&block->binding_list)) @@ -581,16 +580,10 @@ int mlxsw_sp_acl_rulei_act_mirror(struct mlxsw_sp *mlxsw_sp, binding = list_first_entry(&block->binding_list, struct mlxsw_sp_acl_block_binding, list); in_port = binding->mlxsw_sp_port; - if (!mlxsw_sp_port_dev_check(out_dev)) - return -EINVAL; - - out_port = netdev_priv(out_dev); - if (out_port->mlxsw_sp != mlxsw_sp) - return -EINVAL; return mlxsw_afa_block_append_mirror(rulei->act_block, in_port->local_port, - out_port->local_port, + out_dev, binding->ingress); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c index 6ca6894125f0..510ce48d87f7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c @@ -1,6 +1,6 @@ /* * drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c - * Copyright (c) 2017 Mellanox Technologies. All rights reserved. + * Copyright (c) 2017, 2018 Mellanox Technologies. All rights reserved. * Copyright (c) 2017 Jiri Pirko <jiri@mellanox.com> * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com> * @@ -35,6 +35,7 @@ #include "spectrum_acl_flex_actions.h" #include "core_acl_flex_actions.h" +#include "spectrum_span.h" #define MLXSW_SP_KVDL_ACT_EXT_SIZE 1 @@ -125,40 +126,23 @@ mlxsw_sp_act_counter_index_put(void *priv, unsigned int counter_index) } static int -mlxsw_sp_act_mirror_add(void *priv, u8 local_in_port, u8 local_out_port, +mlxsw_sp_act_mirror_add(void *priv, u8 local_in_port, + const struct net_device *out_dev, bool ingress, int *p_span_id) { - struct mlxsw_sp_port *in_port, *out_port; - struct mlxsw_sp_span_entry *span_entry; + struct mlxsw_sp_port *in_port; struct mlxsw_sp *mlxsw_sp = priv; enum mlxsw_sp_span_type type; - int err; type = ingress ? MLXSW_SP_SPAN_INGRESS : MLXSW_SP_SPAN_EGRESS; - out_port = mlxsw_sp->ports[local_out_port]; in_port = mlxsw_sp->ports[local_in_port]; - err = mlxsw_sp_span_mirror_add(in_port, out_port, type, false); - if (err) - return err; - - span_entry = mlxsw_sp_span_entry_find(mlxsw_sp, local_out_port); - if (!span_entry) { - err = -ENOENT; - goto err_span_entry_find; - } - - *p_span_id = span_entry->id; - return 0; - -err_span_entry_find: - mlxsw_sp_span_mirror_del(in_port, local_out_port, type, false); - return err; + return mlxsw_sp_span_mirror_add(in_port, out_dev, type, + false, p_span_id); } static void -mlxsw_sp_act_mirror_del(void *priv, u8 local_in_port, u8 local_out_port, - bool ingress) +mlxsw_sp_act_mirror_del(void *priv, u8 local_in_port, int span_id, bool ingress) { struct mlxsw_sp *mlxsw_sp = priv; struct mlxsw_sp_port *in_port; @@ -167,7 +151,7 @@ mlxsw_sp_act_mirror_del(void *priv, u8 local_in_port, u8 local_out_port, type = ingress ? MLXSW_SP_SPAN_INGRESS : MLXSW_SP_SPAN_EGRESS; in_port = mlxsw_sp->ports[local_in_port]; - mlxsw_sp_span_mirror_del(in_port, local_out_port, type, false); + mlxsw_sp_span_mirror_del(in_port, span_id, type, false); } static const struct mlxsw_afa_ops mlxsw_sp_act_afa_ops = { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c index 7502e53447bd..98d896c14b87 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c @@ -1,7 +1,7 @@ /* * drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c - * Copyright (c) 2017 Mellanox Technologies. All rights reserved. - * Copyright (c) 2017 Petr Machata <petrm@mellanox.com> + * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved. + * Copyright (c) 2017-2018 Petr Machata <petrm@mellanox.com> * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -33,126 +33,125 @@ */ #include <net/ip_tunnels.h> +#include <net/ip6_tunnel.h> #include "spectrum_ipip.h" struct ip_tunnel_parm -mlxsw_sp_ipip_netdev_parms(const struct net_device *ol_dev) +mlxsw_sp_ipip_netdev_parms4(const struct net_device *ol_dev) { struct ip_tunnel *tun = netdev_priv(ol_dev); return tun->parms; } -static bool mlxsw_sp_ipip_parms_has_ikey(struct ip_tunnel_parm parms) +struct __ip6_tnl_parm +mlxsw_sp_ipip_netdev_parms6(const struct net_device *ol_dev) +{ + struct ip6_tnl *tun = netdev_priv(ol_dev); + + return tun->parms; +} + +static bool mlxsw_sp_ipip_parms4_has_ikey(struct ip_tunnel_parm parms) { return !!(parms.i_flags & TUNNEL_KEY); } -static bool mlxsw_sp_ipip_parms_has_okey(struct ip_tunnel_parm parms) +static bool mlxsw_sp_ipip_parms4_has_okey(struct ip_tunnel_parm parms) { return !!(parms.o_flags & TUNNEL_KEY); } -static u32 mlxsw_sp_ipip_parms_ikey(struct ip_tunnel_parm parms) +static u32 mlxsw_sp_ipip_parms4_ikey(struct ip_tunnel_parm parms) { - return mlxsw_sp_ipip_parms_has_ikey(parms) ? + return mlxsw_sp_ipip_parms4_has_ikey(parms) ? be32_to_cpu(parms.i_key) : 0; } -static u32 mlxsw_sp_ipip_parms_okey(struct ip_tunnel_parm parms) +static u32 mlxsw_sp_ipip_parms4_okey(struct ip_tunnel_parm parms) { - return mlxsw_sp_ipip_parms_has_okey(parms) ? + return mlxsw_sp_ipip_parms4_has_okey(parms) ? be32_to_cpu(parms.o_key) : 0; } -static __be32 mlxsw_sp_ipip_parms_saddr4(struct ip_tunnel_parm parms) +static union mlxsw_sp_l3addr +mlxsw_sp_ipip_parms4_saddr(struct ip_tunnel_parm parms) { - return parms.iph.saddr; + return (union mlxsw_sp_l3addr) { .addr4 = parms.iph.saddr }; } static union mlxsw_sp_l3addr -mlxsw_sp_ipip_parms_saddr(enum mlxsw_sp_l3proto proto, - struct ip_tunnel_parm parms) +mlxsw_sp_ipip_parms6_saddr(struct __ip6_tnl_parm parms) { - switch (proto) { - case MLXSW_SP_L3_PROTO_IPV4: - return (union mlxsw_sp_l3addr) { - .addr4 = mlxsw_sp_ipip_parms_saddr4(parms), - }; - case MLXSW_SP_L3_PROTO_IPV6: - break; - } - - WARN_ON(1); - return (union mlxsw_sp_l3addr) { - .addr4 = 0, - }; + return (union mlxsw_sp_l3addr) { .addr6 = parms.laddr }; } -static __be32 mlxsw_sp_ipip_parms_daddr4(struct ip_tunnel_parm parms) +static union mlxsw_sp_l3addr +mlxsw_sp_ipip_parms4_daddr(struct ip_tunnel_parm parms) { - return parms.iph.daddr; + return (union mlxsw_sp_l3addr) { .addr4 = parms.iph.daddr }; } static union mlxsw_sp_l3addr -mlxsw_sp_ipip_parms_daddr(enum mlxsw_sp_l3proto proto, - struct ip_tunnel_parm parms) +mlxsw_sp_ipip_parms6_daddr(struct __ip6_tnl_parm parms) +{ + return (union mlxsw_sp_l3addr) { .addr6 = parms.raddr }; +} + +union mlxsw_sp_l3addr +mlxsw_sp_ipip_netdev_saddr(enum mlxsw_sp_l3proto proto, + const struct net_device *ol_dev) { + struct ip_tunnel_parm parms4; + struct __ip6_tnl_parm parms6; + switch (proto) { case MLXSW_SP_L3_PROTO_IPV4: - return (union mlxsw_sp_l3addr) { - .addr4 = mlxsw_sp_ipip_parms_daddr4(parms), - }; + parms4 = mlxsw_sp_ipip_netdev_parms4(ol_dev); + return mlxsw_sp_ipip_parms4_saddr(parms4); case MLXSW_SP_L3_PROTO_IPV6: - break; + parms6 = mlxsw_sp_ipip_netdev_parms6(ol_dev); + return mlxsw_sp_ipip_parms6_saddr(parms6); } WARN_ON(1); - return (union mlxsw_sp_l3addr) { - .addr4 = 0, - }; -} - -static bool mlxsw_sp_ipip_netdev_has_ikey(const struct net_device *ol_dev) -{ - return mlxsw_sp_ipip_parms_has_ikey(mlxsw_sp_ipip_netdev_parms(ol_dev)); + return (union mlxsw_sp_l3addr) {0}; } -static bool mlxsw_sp_ipip_netdev_has_okey(const struct net_device *ol_dev) +static __be32 mlxsw_sp_ipip_netdev_daddr4(const struct net_device *ol_dev) { - return mlxsw_sp_ipip_parms_has_okey(mlxsw_sp_ipip_netdev_parms(ol_dev)); -} -static u32 mlxsw_sp_ipip_netdev_ikey(const struct net_device *ol_dev) -{ - return mlxsw_sp_ipip_parms_ikey(mlxsw_sp_ipip_netdev_parms(ol_dev)); -} + struct ip_tunnel_parm parms4 = mlxsw_sp_ipip_netdev_parms4(ol_dev); -static u32 mlxsw_sp_ipip_netdev_okey(const struct net_device *ol_dev) -{ - return mlxsw_sp_ipip_parms_okey(mlxsw_sp_ipip_netdev_parms(ol_dev)); + return mlxsw_sp_ipip_parms4_daddr(parms4).addr4; } -union mlxsw_sp_l3addr -mlxsw_sp_ipip_netdev_saddr(enum mlxsw_sp_l3proto proto, +static union mlxsw_sp_l3addr +mlxsw_sp_ipip_netdev_daddr(enum mlxsw_sp_l3proto proto, const struct net_device *ol_dev) { - return mlxsw_sp_ipip_parms_saddr(proto, - mlxsw_sp_ipip_netdev_parms(ol_dev)); -} + struct ip_tunnel_parm parms4; + struct __ip6_tnl_parm parms6; -static __be32 mlxsw_sp_ipip_netdev_daddr4(const struct net_device *ol_dev) -{ - return mlxsw_sp_ipip_parms_daddr4(mlxsw_sp_ipip_netdev_parms(ol_dev)); + switch (proto) { + case MLXSW_SP_L3_PROTO_IPV4: + parms4 = mlxsw_sp_ipip_netdev_parms4(ol_dev); + return mlxsw_sp_ipip_parms4_daddr(parms4); + case MLXSW_SP_L3_PROTO_IPV6: + parms6 = mlxsw_sp_ipip_netdev_parms6(ol_dev); + return mlxsw_sp_ipip_parms6_daddr(parms6); + } + + WARN_ON(1); + return (union mlxsw_sp_l3addr) {0}; } -static union mlxsw_sp_l3addr -mlxsw_sp_ipip_netdev_daddr(enum mlxsw_sp_l3proto proto, - const struct net_device *ol_dev) +bool mlxsw_sp_l3addr_is_zero(union mlxsw_sp_l3addr addr) { - return mlxsw_sp_ipip_parms_daddr(proto, - mlxsw_sp_ipip_netdev_parms(ol_dev)); + union mlxsw_sp_l3addr naddr = {0}; + + return !memcmp(&addr, &naddr, sizeof(naddr)); } static int @@ -176,12 +175,17 @@ mlxsw_sp_ipip_fib_entry_op_gre4_rtdp(struct mlxsw_sp *mlxsw_sp, u32 tunnel_index, struct mlxsw_sp_ipip_entry *ipip_entry) { - bool has_ikey = mlxsw_sp_ipip_netdev_has_ikey(ipip_entry->ol_dev); u16 rif_index = mlxsw_sp_ipip_lb_rif_index(ipip_entry->ol_lb); - u32 ikey = mlxsw_sp_ipip_netdev_ikey(ipip_entry->ol_dev); char rtdp_pl[MLXSW_REG_RTDP_LEN]; + struct ip_tunnel_parm parms; unsigned int type_check; + bool has_ikey; u32 daddr4; + u32 ikey; + + parms = mlxsw_sp_ipip_netdev_parms4(ipip_entry->ol_dev); + has_ikey = mlxsw_sp_ipip_parms4_has_ikey(parms); + ikey = mlxsw_sp_ipip_parms4_ikey(parms); mlxsw_reg_rtdp_pack(rtdp_pl, MLXSW_REG_RTDP_TYPE_IPIP, tunnel_index); @@ -243,15 +247,14 @@ static bool mlxsw_sp_ipip_tunnel_complete(enum mlxsw_sp_l3proto proto, { union mlxsw_sp_l3addr saddr = mlxsw_sp_ipip_netdev_saddr(proto, ol_dev); union mlxsw_sp_l3addr daddr = mlxsw_sp_ipip_netdev_daddr(proto, ol_dev); - union mlxsw_sp_l3addr naddr = {0}; /* Tunnels with unset local or remote address are valid in Linux and * used for lightweight tunnels (LWT) and Non-Broadcast Multi-Access * (NBMA) tunnels. In principle these can be offloaded, but the driver * currently doesn't support this. So punt. */ - return memcmp(&saddr, &naddr, sizeof(naddr)) && - memcmp(&daddr, &naddr, sizeof(naddr)); + return !mlxsw_sp_l3addr_is_zero(saddr) && + !mlxsw_sp_l3addr_is_zero(daddr); } static bool mlxsw_sp_ipip_can_offload_gre4(const struct mlxsw_sp *mlxsw_sp, @@ -273,14 +276,15 @@ static struct mlxsw_sp_rif_ipip_lb_config mlxsw_sp_ipip_ol_loopback_config_gre4(struct mlxsw_sp *mlxsw_sp, const struct net_device *ol_dev) { + struct ip_tunnel_parm parms = mlxsw_sp_ipip_netdev_parms4(ol_dev); enum mlxsw_reg_ritr_loopback_ipip_type lb_ipipt; - lb_ipipt = mlxsw_sp_ipip_netdev_has_okey(ol_dev) ? + lb_ipipt = mlxsw_sp_ipip_parms4_has_okey(parms) ? MLXSW_REG_RITR_LOOPBACK_IPIP_TYPE_IP_IN_GRE_KEY_IN_IP : MLXSW_REG_RITR_LOOPBACK_IPIP_TYPE_IP_IN_GRE_IN_IP; return (struct mlxsw_sp_rif_ipip_lb_config){ .lb_ipipt = lb_ipipt, - .okey = mlxsw_sp_ipip_netdev_okey(ol_dev), + .okey = mlxsw_sp_ipip_parms4_okey(parms), .ul_protocol = MLXSW_SP_L3_PROTO_IPV4, .saddr = mlxsw_sp_ipip_netdev_saddr(MLXSW_SP_L3_PROTO_IPV4, ol_dev), @@ -300,16 +304,12 @@ mlxsw_sp_ipip_ol_netdev_change_gre4(struct mlxsw_sp *mlxsw_sp, bool update_nhs = false; int err = 0; - new_parms = mlxsw_sp_ipip_netdev_parms(ipip_entry->ol_dev); + new_parms = mlxsw_sp_ipip_netdev_parms4(ipip_entry->ol_dev); - new_saddr = mlxsw_sp_ipip_parms_saddr(MLXSW_SP_L3_PROTO_IPV4, - new_parms); - old_saddr = mlxsw_sp_ipip_parms_saddr(MLXSW_SP_L3_PROTO_IPV4, - ipip_entry->parms); - new_daddr = mlxsw_sp_ipip_parms_daddr(MLXSW_SP_L3_PROTO_IPV4, - new_parms); - old_daddr = mlxsw_sp_ipip_parms_daddr(MLXSW_SP_L3_PROTO_IPV4, - ipip_entry->parms); + new_saddr = mlxsw_sp_ipip_parms4_saddr(new_parms); + old_saddr = mlxsw_sp_ipip_parms4_saddr(ipip_entry->parms4); + new_daddr = mlxsw_sp_ipip_parms4_daddr(new_parms); + old_daddr = mlxsw_sp_ipip_parms4_daddr(ipip_entry->parms4); if (!mlxsw_sp_l3addr_eq(&new_saddr, &old_saddr)) { u16 ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(ipip_entry->ol_dev); @@ -326,14 +326,14 @@ mlxsw_sp_ipip_ol_netdev_change_gre4(struct mlxsw_sp *mlxsw_sp, } update_tunnel = true; - } else if ((mlxsw_sp_ipip_parms_okey(ipip_entry->parms) != - mlxsw_sp_ipip_parms_okey(new_parms)) || - ipip_entry->parms.link != new_parms.link) { + } else if ((mlxsw_sp_ipip_parms4_okey(ipip_entry->parms4) != + mlxsw_sp_ipip_parms4_okey(new_parms)) || + ipip_entry->parms4.link != new_parms.link) { update_tunnel = true; } else if (!mlxsw_sp_l3addr_eq(&new_daddr, &old_daddr)) { update_nhs = true; - } else if (mlxsw_sp_ipip_parms_ikey(ipip_entry->parms) != - mlxsw_sp_ipip_parms_ikey(new_parms)) { + } else if (mlxsw_sp_ipip_parms4_ikey(ipip_entry->parms4) != + mlxsw_sp_ipip_parms4_ikey(new_parms)) { update_decap = true; } @@ -350,7 +350,7 @@ mlxsw_sp_ipip_ol_netdev_change_gre4(struct mlxsw_sp *mlxsw_sp, false, false, false, extack); - ipip_entry->parms = new_parms; + ipip_entry->parms4 = new_parms; return err; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h index 04b08d9d76e9..6909d867bb59 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h @@ -1,7 +1,7 @@ /* * drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h - * Copyright (c) 2017 Mellanox Technologies. All rights reserved. - * Copyright (c) 2017 Petr Machata <petrm@mellanox.com> + * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved. + * Copyright (c) 2017-2018 Petr Machata <petrm@mellanox.com> * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -37,14 +37,19 @@ #include "spectrum_router.h" #include <net/ip_fib.h> +#include <linux/if_tunnel.h> struct ip_tunnel_parm -mlxsw_sp_ipip_netdev_parms(const struct net_device *ol_dev); +mlxsw_sp_ipip_netdev_parms4(const struct net_device *ol_dev); +struct __ip6_tnl_parm +mlxsw_sp_ipip_netdev_parms6(const struct net_device *ol_dev); union mlxsw_sp_l3addr mlxsw_sp_ipip_netdev_saddr(enum mlxsw_sp_l3proto proto, const struct net_device *ol_dev); +bool mlxsw_sp_l3addr_is_zero(union mlxsw_sp_l3addr addr); + enum mlxsw_sp_ipip_type { MLXSW_SP_IPIP_TYPE_GRE4, MLXSW_SP_IPIP_TYPE_MAX, @@ -56,7 +61,9 @@ struct mlxsw_sp_ipip_entry { struct mlxsw_sp_rif_ipip_lb *ol_lb; struct mlxsw_sp_fib_entry *decap_fib_entry; struct list_head ipip_list_node; - struct ip_tunnel_parm parms; + union { + struct ip_tunnel_parm parms4; + }; }; struct mlxsw_sp_ipip_ops { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c index 55f9d2d70f9e..059eb3214328 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c @@ -67,7 +67,7 @@ struct mlxsw_sp_kvdl_part_info { struct mlxsw_sp_kvdl_part { struct list_head list; - const struct mlxsw_sp_kvdl_part_info *info; + struct mlxsw_sp_kvdl_part_info *info; unsigned long usage[0]; /* Entries */ }; @@ -188,21 +188,27 @@ int mlxsw_sp_kvdl_alloc_size_query(struct mlxsw_sp *mlxsw_sp, return 0; } +enum mlxsw_sp_kvdl_part_id { + MLXSW_SP_KVDL_PART_SINGLE, + MLXSW_SP_KVDL_PART_CHUNKS, + MLXSW_SP_KVDL_PART_LARGE_CHUNKS, +}; + static const struct mlxsw_sp_kvdl_part_info kvdl_parts_info[] = { { - .part_index = 0, + .part_index = MLXSW_SP_KVDL_PART_SINGLE, .start_index = MLXSW_SP_KVDL_SINGLE_BASE, .end_index = MLXSW_SP_KVDL_SINGLE_END, .alloc_size = 1, }, { - .part_index = 1, + .part_index = MLXSW_SP_KVDL_PART_CHUNKS, .start_index = MLXSW_SP_KVDL_CHUNKS_BASE, .end_index = MLXSW_SP_KVDL_CHUNKS_END, .alloc_size = MLXSW_SP_CHUNK_MAX, }, { - .part_index = 2, + .part_index = MLXSW_SP_KVDL_PART_LARGE_CHUNKS, .start_index = MLXSW_SP_KVDL_LARGE_CHUNKS_BASE, .end_index = MLXSW_SP_KVDL_LARGE_CHUNKS_END, .alloc_size = MLXSW_SP_LARGE_CHUNK_MAX, @@ -222,27 +228,76 @@ mlxsw_sp_kvdl_part_find(struct mlxsw_sp *mlxsw_sp, unsigned int part_index) return NULL; } +static void +mlxsw_sp_kvdl_part_update(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_kvdl_part *part, unsigned int size) +{ + struct mlxsw_sp_kvdl_part_info *info = part->info; + + if (list_is_last(&part->list, &mlxsw_sp->kvdl->parts_list)) { + info->end_index = size - 1; + } else { + struct mlxsw_sp_kvdl_part *last_part; + + last_part = list_next_entry(part, list); + info->start_index = last_part->info->end_index + 1; + info->end_index = info->start_index + size - 1; + } +} + static int mlxsw_sp_kvdl_part_init(struct mlxsw_sp *mlxsw_sp, unsigned int part_index) { + struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); const struct mlxsw_sp_kvdl_part_info *info; + enum mlxsw_sp_resource_id resource_id; struct mlxsw_sp_kvdl_part *part; + bool need_update = true; unsigned int nr_entries; size_t usage_size; + u64 resource_size; + int err; info = &kvdl_parts_info[part_index]; - nr_entries = (info->end_index - info->start_index + 1) / - info->alloc_size; + switch (part_index) { + case MLXSW_SP_KVDL_PART_SINGLE: + resource_id = MLXSW_SP_RESOURCE_KVD_LINEAR_SINGLE; + break; + case MLXSW_SP_KVDL_PART_CHUNKS: + resource_id = MLXSW_SP_RESOURCE_KVD_LINEAR_CHUNKS; + break; + case MLXSW_SP_KVDL_PART_LARGE_CHUNKS: + resource_id = MLXSW_SP_RESOURCE_KVD_LINEAR_LARGE_CHUNKS; + break; + default: + return -EINVAL; + } + + err = devlink_resource_size_get(devlink, resource_id, &resource_size); + if (err) { + need_update = false; + resource_size = info->end_index - info->start_index + 1; + } + + nr_entries = div_u64(resource_size, info->alloc_size); usage_size = BITS_TO_LONGS(nr_entries) * sizeof(unsigned long); part = kzalloc(sizeof(*part) + usage_size, GFP_KERNEL); if (!part) return -ENOMEM; - part->info = info; - list_add(&part->list, &mlxsw_sp->kvdl->parts_list); + part->info = kmemdup(info, sizeof(*part->info), GFP_KERNEL); + if (!part->info) + goto err_part_info_alloc; + list_add(&part->list, &mlxsw_sp->kvdl->parts_list); + if (need_update) + mlxsw_sp_kvdl_part_update(mlxsw_sp, part, resource_size); return 0; + +err_part_info_alloc: + kfree(part); + return -ENOMEM; } static void mlxsw_sp_kvdl_part_fini(struct mlxsw_sp *mlxsw_sp, @@ -255,6 +310,7 @@ static void mlxsw_sp_kvdl_part_fini(struct mlxsw_sp *mlxsw_sp, return; list_del(&part->list); + kfree(part->info); kfree(part); } @@ -312,6 +368,123 @@ u64 mlxsw_sp_kvdl_occ_get(const struct mlxsw_sp *mlxsw_sp) return occ; } +u64 mlxsw_sp_kvdl_single_occ_get(struct devlink *devlink) +{ + struct mlxsw_core *mlxsw_core = devlink_priv(devlink); + struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); + struct mlxsw_sp_kvdl_part *part; + + part = mlxsw_sp_kvdl_part_find(mlxsw_sp, MLXSW_SP_KVDL_PART_SINGLE); + if (!part) + return -EINVAL; + + return mlxsw_sp_kvdl_part_occ(part); +} + +u64 mlxsw_sp_kvdl_chunks_occ_get(struct devlink *devlink) +{ + struct mlxsw_core *mlxsw_core = devlink_priv(devlink); + struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); + struct mlxsw_sp_kvdl_part *part; + + part = mlxsw_sp_kvdl_part_find(mlxsw_sp, MLXSW_SP_KVDL_PART_CHUNKS); + if (!part) + return -EINVAL; + + return mlxsw_sp_kvdl_part_occ(part); +} + +u64 mlxsw_sp_kvdl_large_chunks_occ_get(struct devlink *devlink) +{ + struct mlxsw_core *mlxsw_core = devlink_priv(devlink); + struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); + struct mlxsw_sp_kvdl_part *part; + + part = mlxsw_sp_kvdl_part_find(mlxsw_sp, + MLXSW_SP_KVDL_PART_LARGE_CHUNKS); + if (!part) + return -EINVAL; + + return mlxsw_sp_kvdl_part_occ(part); +} + +static struct devlink_resource_ops mlxsw_sp_kvdl_single_ops = { + .occ_get = mlxsw_sp_kvdl_single_occ_get, +}; + +static struct devlink_resource_ops mlxsw_sp_kvdl_chunks_ops = { + .occ_get = mlxsw_sp_kvdl_chunks_occ_get, +}; + +static struct devlink_resource_ops mlxsw_sp_kvdl_chunks_large_ops = { + .occ_get = mlxsw_sp_kvdl_large_chunks_occ_get, +}; + +static struct devlink_resource_size_params mlxsw_sp_kvdl_single_size_params = { + .size_min = 0, + .size_granularity = 1, + .unit = DEVLINK_RESOURCE_UNIT_ENTRY, +}; + +static struct devlink_resource_size_params mlxsw_sp_kvdl_chunks_size_params = { + .size_min = 0, + .size_granularity = MLXSW_SP_CHUNK_MAX, + .unit = DEVLINK_RESOURCE_UNIT_ENTRY, +}; + +static struct devlink_resource_size_params mlxsw_sp_kvdl_large_chunks_size_params = { + .size_min = 0, + .size_granularity = MLXSW_SP_LARGE_CHUNK_MAX, + .unit = DEVLINK_RESOURCE_UNIT_ENTRY, +}; + +static void +mlxsw_sp_kvdl_resource_size_params_prepare(struct devlink *devlink) +{ + struct mlxsw_core *mlxsw_core = devlink_priv(devlink); + u32 kvdl_max_size; + + kvdl_max_size = MLXSW_CORE_RES_GET(mlxsw_core, KVD_SIZE) - + MLXSW_CORE_RES_GET(mlxsw_core, KVD_SINGLE_MIN_SIZE) - + MLXSW_CORE_RES_GET(mlxsw_core, KVD_DOUBLE_MIN_SIZE); + + mlxsw_sp_kvdl_single_size_params.size_max = kvdl_max_size; + mlxsw_sp_kvdl_chunks_size_params.size_max = kvdl_max_size; + mlxsw_sp_kvdl_large_chunks_size_params.size_max = kvdl_max_size; +} + +int mlxsw_sp_kvdl_resources_register(struct devlink *devlink) +{ + int err; + + mlxsw_sp_kvdl_resource_size_params_prepare(devlink); + err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_SINGLES, + false, MLXSW_SP_KVDL_SINGLE_SIZE, + MLXSW_SP_RESOURCE_KVD_LINEAR_SINGLE, + MLXSW_SP_RESOURCE_KVD_LINEAR, + &mlxsw_sp_kvdl_single_size_params, + &mlxsw_sp_kvdl_single_ops); + if (err) + return err; + + err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_CHUNKS, + false, MLXSW_SP_KVDL_CHUNKS_SIZE, + MLXSW_SP_RESOURCE_KVD_LINEAR_CHUNKS, + MLXSW_SP_RESOURCE_KVD_LINEAR, + &mlxsw_sp_kvdl_chunks_size_params, + &mlxsw_sp_kvdl_chunks_ops); + if (err) + return err; + + err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_LARGE_CHUNKS, + false, MLXSW_SP_KVDL_LARGE_CHUNKS_SIZE, + MLXSW_SP_RESOURCE_KVD_LINEAR_LARGE_CHUNKS, + MLXSW_SP_RESOURCE_KVD_LINEAR, + &mlxsw_sp_kvdl_large_chunks_size_params, + &mlxsw_sp_kvdl_chunks_large_ops); + return err; +} + int mlxsw_sp_kvdl_init(struct mlxsw_sp *mlxsw_sp) { struct mlxsw_sp_kvdl *kvdl; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index f0b25baba09a..69f16c605b9d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -1,10 +1,10 @@ /* * drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c - * Copyright (c) 2016-2017 Mellanox Technologies. All rights reserved. + * Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved. * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com> * Copyright (c) 2016 Ido Schimmel <idosch@mellanox.com> * Copyright (c) 2016 Yotam Gigi <yotamg@mellanox.com> - * Copyright (c) 2017 Petr Machata <petrm@mellanox.com> + * Copyright (c) 2017-2018 Petr Machata <petrm@mellanox.com> * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -70,6 +70,7 @@ #include "spectrum_mr.h" #include "spectrum_mr_tcam.h" #include "spectrum_router.h" +#include "spectrum_span.h" struct mlxsw_sp_fib; struct mlxsw_sp_vr; @@ -788,37 +789,41 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_create(struct mlxsw_sp *mlxsw_sp, u32 tb_id, struct netlink_ext_ack *extack) { + struct mlxsw_sp_mr_table *mr4_table; + struct mlxsw_sp_fib *fib4; + struct mlxsw_sp_fib *fib6; struct mlxsw_sp_vr *vr; int err; vr = mlxsw_sp_vr_find_unused(mlxsw_sp); if (!vr) { - NL_SET_ERR_MSG(extack, "spectrum: Exceeded number of supported virtual routers"); + NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported virtual routers"); return ERR_PTR(-EBUSY); } - vr->fib4 = mlxsw_sp_fib_create(mlxsw_sp, vr, MLXSW_SP_L3_PROTO_IPV4); - if (IS_ERR(vr->fib4)) - return ERR_CAST(vr->fib4); - vr->fib6 = mlxsw_sp_fib_create(mlxsw_sp, vr, MLXSW_SP_L3_PROTO_IPV6); - if (IS_ERR(vr->fib6)) { - err = PTR_ERR(vr->fib6); + fib4 = mlxsw_sp_fib_create(mlxsw_sp, vr, MLXSW_SP_L3_PROTO_IPV4); + if (IS_ERR(fib4)) + return ERR_CAST(fib4); + fib6 = mlxsw_sp_fib_create(mlxsw_sp, vr, MLXSW_SP_L3_PROTO_IPV6); + if (IS_ERR(fib6)) { + err = PTR_ERR(fib6); goto err_fib6_create; } - vr->mr4_table = mlxsw_sp_mr_table_create(mlxsw_sp, vr->id, - MLXSW_SP_L3_PROTO_IPV4); - if (IS_ERR(vr->mr4_table)) { - err = PTR_ERR(vr->mr4_table); + mr4_table = mlxsw_sp_mr_table_create(mlxsw_sp, vr->id, + MLXSW_SP_L3_PROTO_IPV4); + if (IS_ERR(mr4_table)) { + err = PTR_ERR(mr4_table); goto err_mr_table_create; } + vr->fib4 = fib4; + vr->fib6 = fib6; + vr->mr4_table = mr4_table; vr->tb_id = tb_id; return vr; err_mr_table_create: - mlxsw_sp_fib_destroy(mlxsw_sp, vr->fib6); - vr->fib6 = NULL; + mlxsw_sp_fib_destroy(mlxsw_sp, fib6); err_fib6_create: - mlxsw_sp_fib_destroy(mlxsw_sp, vr->fib4); - vr->fib4 = NULL; + mlxsw_sp_fib_destroy(mlxsw_sp, fib4); return ERR_PTR(err); } @@ -1020,9 +1025,11 @@ mlxsw_sp_ipip_entry_alloc(struct mlxsw_sp *mlxsw_sp, enum mlxsw_sp_ipip_type ipipt, struct net_device *ol_dev) { + const struct mlxsw_sp_ipip_ops *ipip_ops; struct mlxsw_sp_ipip_entry *ipip_entry; struct mlxsw_sp_ipip_entry *ret = NULL; + ipip_ops = mlxsw_sp->router->ipip_ops_arr[ipipt]; ipip_entry = kzalloc(sizeof(*ipip_entry), GFP_KERNEL); if (!ipip_entry) return ERR_PTR(-ENOMEM); @@ -1036,7 +1043,15 @@ mlxsw_sp_ipip_entry_alloc(struct mlxsw_sp *mlxsw_sp, ipip_entry->ipipt = ipipt; ipip_entry->ol_dev = ol_dev; - ipip_entry->parms = mlxsw_sp_ipip_netdev_parms(ol_dev); + + switch (ipip_ops->ul_proto) { + case MLXSW_SP_L3_PROTO_IPV4: + ipip_entry->parms4 = mlxsw_sp_ipip_netdev_parms4(ol_dev); + break; + case MLXSW_SP_L3_PROTO_IPV6: + WARN_ON(1); + break; + } return ipip_entry; @@ -2316,6 +2331,8 @@ static void mlxsw_sp_router_neigh_event_work(struct work_struct *work) read_unlock_bh(&n->lock); rtnl_lock(); + mlxsw_sp_span_respin(mlxsw_sp); + entry_connected = nud_state & NUD_VALID && !dead; neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, n); if (!entry_connected && !neigh_entry) @@ -3790,6 +3807,9 @@ mlxsw_sp_fib4_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry) struct mlxsw_sp_nexthop_group *nh_grp = fib_entry->nh_group; int i; + if (!list_is_singular(&nh_grp->fib_list)) + return; + for (i = 0; i < nh_grp->count; i++) { struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i]; @@ -5572,6 +5592,8 @@ static void mlxsw_sp_router_fib4_event_work(struct work_struct *work) /* Protect internal structures from changes */ rtnl_lock(); + mlxsw_sp_span_respin(mlxsw_sp); + switch (fib_work->event) { case FIB_EVENT_ENTRY_REPLACE: /* fall through */ case FIB_EVENT_ENTRY_APPEND: /* fall through */ @@ -5614,6 +5636,8 @@ static void mlxsw_sp_router_fib6_event_work(struct work_struct *work) int err; rtnl_lock(); + mlxsw_sp_span_respin(mlxsw_sp); + switch (fib_work->event) { case FIB_EVENT_ENTRY_REPLACE: /* fall through */ case FIB_EVENT_ENTRY_ADD: @@ -5786,7 +5810,7 @@ static int mlxsw_sp_router_fib_rule_event(unsigned long event, } if (err < 0) - NL_SET_ERR_MSG(extack, "spectrum: FIB rules not supported. Aborting offload"); + NL_SET_ERR_MSG_MOD(extack, "FIB rules not supported. Aborting offload"); return err; } @@ -6025,7 +6049,7 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp, err = mlxsw_sp_rif_index_alloc(mlxsw_sp, &rif_index); if (err) { - NL_SET_ERR_MSG(extack, "spectrum: Exceeded number of supported router interfaces"); + NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported router interfaces"); goto err_rif_index_alloc; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c new file mode 100644 index 000000000000..f537e1de11d9 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c @@ -0,0 +1,796 @@ +/* + * drivers/net/ethernet/mellanox/mlxsw/mlxsw_span.c + * Copyright (c) 2018 Mellanox Technologies. All rights reserved. + * Copyright (c) 2018 Petr Machata <petrm@mellanox.com> + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include <linux/list.h> +#include <net/arp.h> +#include <net/gre.h> +#include <net/ndisc.h> +#include <net/ip6_tunnel.h> + +#include "spectrum.h" +#include "spectrum_span.h" +#include "spectrum_ipip.h" + +int mlxsw_sp_span_init(struct mlxsw_sp *mlxsw_sp) +{ + int i; + + if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_SPAN)) + return -EIO; + + mlxsw_sp->span.entries_count = MLXSW_CORE_RES_GET(mlxsw_sp->core, + MAX_SPAN); + mlxsw_sp->span.entries = kcalloc(mlxsw_sp->span.entries_count, + sizeof(struct mlxsw_sp_span_entry), + GFP_KERNEL); + if (!mlxsw_sp->span.entries) + return -ENOMEM; + + for (i = 0; i < mlxsw_sp->span.entries_count; i++) { + struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i]; + + INIT_LIST_HEAD(&curr->bound_ports_list); + curr->id = i; + } + + return 0; +} + +void mlxsw_sp_span_fini(struct mlxsw_sp *mlxsw_sp) +{ + int i; + + for (i = 0; i < mlxsw_sp->span.entries_count; i++) { + struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i]; + + WARN_ON_ONCE(!list_empty(&curr->bound_ports_list)); + } + kfree(mlxsw_sp->span.entries); +} + +static int +mlxsw_sp_span_entry_phys_parms(const struct net_device *to_dev, + struct mlxsw_sp_span_parms *sparmsp) +{ + sparmsp->dest_port = netdev_priv(to_dev); + return 0; +} + +static int +mlxsw_sp_span_entry_phys_configure(struct mlxsw_sp_span_entry *span_entry, + struct mlxsw_sp_span_parms sparms) +{ + struct mlxsw_sp_port *dest_port = sparms.dest_port; + struct mlxsw_sp *mlxsw_sp = dest_port->mlxsw_sp; + u8 local_port = dest_port->local_port; + char mpat_pl[MLXSW_REG_MPAT_LEN]; + int pa_id = span_entry->id; + + /* Create a new port analayzer entry for local_port. */ + mlxsw_reg_mpat_pack(mpat_pl, pa_id, local_port, true, + MLXSW_REG_MPAT_SPAN_TYPE_LOCAL_ETH); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mpat), mpat_pl); +} + +static void +mlxsw_sp_span_entry_deconfigure_common(struct mlxsw_sp_span_entry *span_entry, + enum mlxsw_reg_mpat_span_type span_type) +{ + struct mlxsw_sp_port *dest_port = span_entry->parms.dest_port; + struct mlxsw_sp *mlxsw_sp = dest_port->mlxsw_sp; + u8 local_port = dest_port->local_port; + char mpat_pl[MLXSW_REG_MPAT_LEN]; + int pa_id = span_entry->id; + + mlxsw_reg_mpat_pack(mpat_pl, pa_id, local_port, false, span_type); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mpat), mpat_pl); +} + +static void +mlxsw_sp_span_entry_phys_deconfigure(struct mlxsw_sp_span_entry *span_entry) +{ + mlxsw_sp_span_entry_deconfigure_common(span_entry, + MLXSW_REG_MPAT_SPAN_TYPE_LOCAL_ETH); +} + +static const +struct mlxsw_sp_span_entry_ops mlxsw_sp_span_entry_ops_phys = { + .can_handle = mlxsw_sp_port_dev_check, + .parms = mlxsw_sp_span_entry_phys_parms, + .configure = mlxsw_sp_span_entry_phys_configure, + .deconfigure = mlxsw_sp_span_entry_phys_deconfigure, +}; + +static struct net_device * +mlxsw_sp_span_gretap4_route(const struct net_device *to_dev, + __be32 *saddrp, __be32 *daddrp) +{ + struct ip_tunnel *tun = netdev_priv(to_dev); + struct net_device *dev = NULL; + struct ip_tunnel_parm parms; + struct rtable *rt = NULL; + struct flowi4 fl4; + + /* We assume "dev" stays valid after rt is put. */ + ASSERT_RTNL(); + + parms = mlxsw_sp_ipip_netdev_parms4(to_dev); + ip_tunnel_init_flow(&fl4, parms.iph.protocol, *daddrp, *saddrp, + 0, 0, parms.link, tun->fwmark); + + rt = ip_route_output_key(tun->net, &fl4); + if (IS_ERR(rt)) + return NULL; + + if (rt->rt_type != RTN_UNICAST) + goto out; + + dev = rt->dst.dev; + *saddrp = fl4.saddr; + *daddrp = rt->rt_gateway; + +out: + ip_rt_put(rt); + return dev; +} + +static int mlxsw_sp_span_dmac(struct neigh_table *tbl, + const void *pkey, + struct net_device *l3edev, + unsigned char dmac[ETH_ALEN]) +{ + struct neighbour *neigh = neigh_lookup(tbl, pkey, l3edev); + int err = 0; + + if (!neigh) { + neigh = neigh_create(tbl, pkey, l3edev); + if (IS_ERR(neigh)) + return PTR_ERR(neigh); + } + + neigh_event_send(neigh, NULL); + + read_lock_bh(&neigh->lock); + if ((neigh->nud_state & NUD_VALID) && !neigh->dead) + memcpy(dmac, neigh->ha, ETH_ALEN); + else + err = -ENOENT; + read_unlock_bh(&neigh->lock); + + neigh_release(neigh); + return err; +} + +static int +mlxsw_sp_span_entry_unoffloadable(struct mlxsw_sp_span_parms *sparmsp) +{ + sparmsp->dest_port = NULL; + return 0; +} + +static int +mlxsw_sp_span_entry_tunnel_parms_common(struct net_device *l3edev, + union mlxsw_sp_l3addr saddr, + union mlxsw_sp_l3addr daddr, + union mlxsw_sp_l3addr gw, + __u8 ttl, + struct neigh_table *tbl, + struct mlxsw_sp_span_parms *sparmsp) +{ + unsigned char dmac[ETH_ALEN]; + + if (mlxsw_sp_l3addr_is_zero(gw)) + gw = daddr; + + if (!l3edev || !mlxsw_sp_port_dev_check(l3edev) || + mlxsw_sp_span_dmac(tbl, &gw, l3edev, dmac)) + return mlxsw_sp_span_entry_unoffloadable(sparmsp); + + sparmsp->dest_port = netdev_priv(l3edev); + sparmsp->ttl = ttl; + memcpy(sparmsp->dmac, dmac, ETH_ALEN); + memcpy(sparmsp->smac, l3edev->dev_addr, ETH_ALEN); + sparmsp->saddr = saddr; + sparmsp->daddr = daddr; + return 0; +} + +static int +mlxsw_sp_span_entry_gretap4_parms(const struct net_device *to_dev, + struct mlxsw_sp_span_parms *sparmsp) +{ + struct ip_tunnel_parm tparm = mlxsw_sp_ipip_netdev_parms4(to_dev); + union mlxsw_sp_l3addr saddr = { .addr4 = tparm.iph.saddr }; + union mlxsw_sp_l3addr daddr = { .addr4 = tparm.iph.daddr }; + bool inherit_tos = tparm.iph.tos & 0x1; + bool inherit_ttl = !tparm.iph.ttl; + union mlxsw_sp_l3addr gw = daddr; + struct net_device *l3edev; + + if (!(to_dev->flags & IFF_UP) || + /* Reject tunnels with GRE keys, checksums, etc. */ + tparm.i_flags || tparm.o_flags || + /* Require a fixed TTL and a TOS copied from the mirrored packet. */ + inherit_ttl || !inherit_tos || + /* A destination address may not be "any". */ + mlxsw_sp_l3addr_is_zero(daddr)) + return mlxsw_sp_span_entry_unoffloadable(sparmsp); + + l3edev = mlxsw_sp_span_gretap4_route(to_dev, &saddr.addr4, &gw.addr4); + return mlxsw_sp_span_entry_tunnel_parms_common(l3edev, saddr, daddr, gw, + tparm.iph.ttl, + &arp_tbl, sparmsp); +} + +static int +mlxsw_sp_span_entry_gretap4_configure(struct mlxsw_sp_span_entry *span_entry, + struct mlxsw_sp_span_parms sparms) +{ + struct mlxsw_sp_port *dest_port = sparms.dest_port; + struct mlxsw_sp *mlxsw_sp = dest_port->mlxsw_sp; + u8 local_port = dest_port->local_port; + char mpat_pl[MLXSW_REG_MPAT_LEN]; + int pa_id = span_entry->id; + + /* Create a new port analayzer entry for local_port. */ + mlxsw_reg_mpat_pack(mpat_pl, pa_id, local_port, true, + MLXSW_REG_MPAT_SPAN_TYPE_REMOTE_ETH_L3); + mlxsw_reg_mpat_eth_rspan_l2_pack(mpat_pl, + MLXSW_REG_MPAT_ETH_RSPAN_VERSION_NO_HEADER, + sparms.dmac, false); + mlxsw_reg_mpat_eth_rspan_l3_ipv4_pack(mpat_pl, + sparms.ttl, sparms.smac, + be32_to_cpu(sparms.saddr.addr4), + be32_to_cpu(sparms.daddr.addr4)); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mpat), mpat_pl); +} + +static void +mlxsw_sp_span_entry_gretap4_deconfigure(struct mlxsw_sp_span_entry *span_entry) +{ + mlxsw_sp_span_entry_deconfigure_common(span_entry, + MLXSW_REG_MPAT_SPAN_TYPE_REMOTE_ETH_L3); +} + +static const struct mlxsw_sp_span_entry_ops mlxsw_sp_span_entry_ops_gretap4 = { + .can_handle = is_gretap_dev, + .parms = mlxsw_sp_span_entry_gretap4_parms, + .configure = mlxsw_sp_span_entry_gretap4_configure, + .deconfigure = mlxsw_sp_span_entry_gretap4_deconfigure, +}; + +static struct net_device * +mlxsw_sp_span_gretap6_route(const struct net_device *to_dev, + struct in6_addr *saddrp, + struct in6_addr *daddrp) +{ + struct ip6_tnl *t = netdev_priv(to_dev); + struct flowi6 fl6 = t->fl.u.ip6; + struct net_device *dev = NULL; + struct dst_entry *dst; + struct rt6_info *rt6; + + /* We assume "dev" stays valid after dst is released. */ + ASSERT_RTNL(); + + fl6.flowi6_mark = t->parms.fwmark; + if (!ip6_tnl_xmit_ctl(t, &fl6.saddr, &fl6.daddr)) + return NULL; + + dst = ip6_route_output(t->net, NULL, &fl6); + if (!dst || dst->error) + goto out; + + rt6 = container_of(dst, struct rt6_info, dst); + + dev = dst->dev; + *saddrp = fl6.saddr; + *daddrp = rt6->rt6i_gateway; + +out: + dst_release(dst); + return dev; +} + +static int +mlxsw_sp_span_entry_gretap6_parms(const struct net_device *to_dev, + struct mlxsw_sp_span_parms *sparmsp) +{ + struct __ip6_tnl_parm tparm = mlxsw_sp_ipip_netdev_parms6(to_dev); + bool inherit_tos = tparm.flags & IP6_TNL_F_USE_ORIG_TCLASS; + union mlxsw_sp_l3addr saddr = { .addr6 = tparm.laddr }; + union mlxsw_sp_l3addr daddr = { .addr6 = tparm.raddr }; + bool inherit_ttl = !tparm.hop_limit; + union mlxsw_sp_l3addr gw = daddr; + struct net_device *l3edev; + + if (!(to_dev->flags & IFF_UP) || + /* Reject tunnels with GRE keys, checksums, etc. */ + tparm.i_flags || tparm.o_flags || + /* Require a fixed TTL and a TOS copied from the mirrored packet. */ + inherit_ttl || !inherit_tos || + /* A destination address may not be "any". */ + mlxsw_sp_l3addr_is_zero(daddr)) + return mlxsw_sp_span_entry_unoffloadable(sparmsp); + + l3edev = mlxsw_sp_span_gretap6_route(to_dev, &saddr.addr6, &gw.addr6); + return mlxsw_sp_span_entry_tunnel_parms_common(l3edev, saddr, daddr, gw, + tparm.hop_limit, + &nd_tbl, sparmsp); +} + +static int +mlxsw_sp_span_entry_gretap6_configure(struct mlxsw_sp_span_entry *span_entry, + struct mlxsw_sp_span_parms sparms) +{ + struct mlxsw_sp_port *dest_port = sparms.dest_port; + struct mlxsw_sp *mlxsw_sp = dest_port->mlxsw_sp; + u8 local_port = dest_port->local_port; + char mpat_pl[MLXSW_REG_MPAT_LEN]; + int pa_id = span_entry->id; + + /* Create a new port analayzer entry for local_port. */ + mlxsw_reg_mpat_pack(mpat_pl, pa_id, local_port, true, + MLXSW_REG_MPAT_SPAN_TYPE_REMOTE_ETH_L3); + mlxsw_reg_mpat_eth_rspan_l2_pack(mpat_pl, + MLXSW_REG_MPAT_ETH_RSPAN_VERSION_NO_HEADER, + sparms.dmac, false); + mlxsw_reg_mpat_eth_rspan_l3_ipv6_pack(mpat_pl, sparms.ttl, sparms.smac, + sparms.saddr.addr6, + sparms.daddr.addr6); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mpat), mpat_pl); +} + +static void +mlxsw_sp_span_entry_gretap6_deconfigure(struct mlxsw_sp_span_entry *span_entry) +{ + mlxsw_sp_span_entry_deconfigure_common(span_entry, + MLXSW_REG_MPAT_SPAN_TYPE_REMOTE_ETH_L3); +} + +static const +struct mlxsw_sp_span_entry_ops mlxsw_sp_span_entry_ops_gretap6 = { + .can_handle = is_ip6gretap_dev, + .parms = mlxsw_sp_span_entry_gretap6_parms, + .configure = mlxsw_sp_span_entry_gretap6_configure, + .deconfigure = mlxsw_sp_span_entry_gretap6_deconfigure, +}; + +static const +struct mlxsw_sp_span_entry_ops *const mlxsw_sp_span_entry_types[] = { + &mlxsw_sp_span_entry_ops_phys, + &mlxsw_sp_span_entry_ops_gretap4, + &mlxsw_sp_span_entry_ops_gretap6, +}; + +static int +mlxsw_sp_span_entry_nop_parms(const struct net_device *to_dev, + struct mlxsw_sp_span_parms *sparmsp) +{ + return mlxsw_sp_span_entry_unoffloadable(sparmsp); +} + +static int +mlxsw_sp_span_entry_nop_configure(struct mlxsw_sp_span_entry *span_entry, + struct mlxsw_sp_span_parms sparms) +{ + return 0; +} + +static void +mlxsw_sp_span_entry_nop_deconfigure(struct mlxsw_sp_span_entry *span_entry) +{ +} + +static const struct mlxsw_sp_span_entry_ops mlxsw_sp_span_entry_ops_nop = { + .parms = mlxsw_sp_span_entry_nop_parms, + .configure = mlxsw_sp_span_entry_nop_configure, + .deconfigure = mlxsw_sp_span_entry_nop_deconfigure, +}; + +static void +mlxsw_sp_span_entry_configure(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_span_entry *span_entry, + struct mlxsw_sp_span_parms sparms) +{ + if (sparms.dest_port) { + if (sparms.dest_port->mlxsw_sp != mlxsw_sp) { + netdev_err(span_entry->to_dev, "Cannot mirror to %s, which belongs to a different mlxsw instance", + sparms.dest_port->dev->name); + sparms.dest_port = NULL; + } else if (span_entry->ops->configure(span_entry, sparms)) { + netdev_err(span_entry->to_dev, "Failed to offload mirror to %s", + sparms.dest_port->dev->name); + sparms.dest_port = NULL; + } + } + + span_entry->parms = sparms; +} + +static void +mlxsw_sp_span_entry_deconfigure(struct mlxsw_sp_span_entry *span_entry) +{ + if (span_entry->parms.dest_port) + span_entry->ops->deconfigure(span_entry); +} + +static struct mlxsw_sp_span_entry * +mlxsw_sp_span_entry_create(struct mlxsw_sp *mlxsw_sp, + const struct net_device *to_dev, + const struct mlxsw_sp_span_entry_ops *ops, + struct mlxsw_sp_span_parms sparms) +{ + struct mlxsw_sp_span_entry *span_entry = NULL; + int i; + + /* find a free entry to use */ + for (i = 0; i < mlxsw_sp->span.entries_count; i++) { + if (!mlxsw_sp->span.entries[i].ref_count) { + span_entry = &mlxsw_sp->span.entries[i]; + break; + } + } + if (!span_entry) + return NULL; + + span_entry->ops = ops; + span_entry->ref_count = 1; + span_entry->to_dev = to_dev; + mlxsw_sp_span_entry_configure(mlxsw_sp, span_entry, sparms); + + return span_entry; +} + +static void mlxsw_sp_span_entry_destroy(struct mlxsw_sp_span_entry *span_entry) +{ + mlxsw_sp_span_entry_deconfigure(span_entry); +} + +struct mlxsw_sp_span_entry * +mlxsw_sp_span_entry_find_by_port(struct mlxsw_sp *mlxsw_sp, + const struct net_device *to_dev) +{ + int i; + + for (i = 0; i < mlxsw_sp->span.entries_count; i++) { + struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i]; + + if (curr->ref_count && curr->to_dev == to_dev) + return curr; + } + return NULL; +} + +void mlxsw_sp_span_entry_invalidate(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_span_entry *span_entry) +{ + mlxsw_sp_span_entry_deconfigure(span_entry); + span_entry->ops = &mlxsw_sp_span_entry_ops_nop; +} + +static struct mlxsw_sp_span_entry * +mlxsw_sp_span_entry_find_by_id(struct mlxsw_sp *mlxsw_sp, int span_id) +{ + int i; + + for (i = 0; i < mlxsw_sp->span.entries_count; i++) { + struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i]; + + if (curr->ref_count && curr->id == span_id) + return curr; + } + return NULL; +} + +static struct mlxsw_sp_span_entry * +mlxsw_sp_span_entry_get(struct mlxsw_sp *mlxsw_sp, + const struct net_device *to_dev, + const struct mlxsw_sp_span_entry_ops *ops, + struct mlxsw_sp_span_parms sparms) +{ + struct mlxsw_sp_span_entry *span_entry; + + span_entry = mlxsw_sp_span_entry_find_by_port(mlxsw_sp, to_dev); + if (span_entry) { + /* Already exists, just take a reference */ + span_entry->ref_count++; + return span_entry; + } + + return mlxsw_sp_span_entry_create(mlxsw_sp, to_dev, ops, sparms); +} + +static int mlxsw_sp_span_entry_put(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_span_entry *span_entry) +{ + WARN_ON(!span_entry->ref_count); + if (--span_entry->ref_count == 0) + mlxsw_sp_span_entry_destroy(span_entry); + return 0; +} + +static bool mlxsw_sp_span_is_egress_mirror(struct mlxsw_sp_port *port) +{ + struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; + struct mlxsw_sp_span_inspected_port *p; + int i; + + for (i = 0; i < mlxsw_sp->span.entries_count; i++) { + struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i]; + + list_for_each_entry(p, &curr->bound_ports_list, list) + if (p->local_port == port->local_port && + p->type == MLXSW_SP_SPAN_EGRESS) + return true; + } + + return false; +} + +static int mlxsw_sp_span_mtu_to_buffsize(const struct mlxsw_sp *mlxsw_sp, + int mtu) +{ + return mlxsw_sp_bytes_cells(mlxsw_sp, mtu * 5 / 2) + 1; +} + +int mlxsw_sp_span_port_mtu_update(struct mlxsw_sp_port *port, u16 mtu) +{ + struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; + char sbib_pl[MLXSW_REG_SBIB_LEN]; + int err; + + /* If port is egress mirrored, the shared buffer size should be + * updated according to the mtu value + */ + if (mlxsw_sp_span_is_egress_mirror(port)) { + u32 buffsize = mlxsw_sp_span_mtu_to_buffsize(mlxsw_sp, mtu); + + mlxsw_reg_sbib_pack(sbib_pl, port->local_port, buffsize); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl); + if (err) { + netdev_err(port->dev, "Could not update shared buffer for mirroring\n"); + return err; + } + } + + return 0; +} + +static struct mlxsw_sp_span_inspected_port * +mlxsw_sp_span_entry_bound_port_find(struct mlxsw_sp_port *port, + struct mlxsw_sp_span_entry *span_entry) +{ + struct mlxsw_sp_span_inspected_port *p; + + list_for_each_entry(p, &span_entry->bound_ports_list, list) + if (port->local_port == p->local_port) + return p; + return NULL; +} + +static int +mlxsw_sp_span_inspected_port_bind(struct mlxsw_sp_port *port, + struct mlxsw_sp_span_entry *span_entry, + enum mlxsw_sp_span_type type, + bool bind) +{ + struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; + char mpar_pl[MLXSW_REG_MPAR_LEN]; + int pa_id = span_entry->id; + + /* bind the port to the SPAN entry */ + mlxsw_reg_mpar_pack(mpar_pl, port->local_port, + (enum mlxsw_reg_mpar_i_e)type, bind, pa_id); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mpar), mpar_pl); +} + +static int +mlxsw_sp_span_inspected_port_add(struct mlxsw_sp_port *port, + struct mlxsw_sp_span_entry *span_entry, + enum mlxsw_sp_span_type type, + bool bind) +{ + struct mlxsw_sp_span_inspected_port *inspected_port; + struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; + char sbib_pl[MLXSW_REG_SBIB_LEN]; + int err; + + /* if it is an egress SPAN, bind a shared buffer to it */ + if (type == MLXSW_SP_SPAN_EGRESS) { + u32 buffsize = mlxsw_sp_span_mtu_to_buffsize(mlxsw_sp, + port->dev->mtu); + + mlxsw_reg_sbib_pack(sbib_pl, port->local_port, buffsize); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl); + if (err) { + netdev_err(port->dev, "Could not create shared buffer for mirroring\n"); + return err; + } + } + + if (bind) { + err = mlxsw_sp_span_inspected_port_bind(port, span_entry, type, + true); + if (err) + goto err_port_bind; + } + + inspected_port = kzalloc(sizeof(*inspected_port), GFP_KERNEL); + if (!inspected_port) { + err = -ENOMEM; + goto err_inspected_port_alloc; + } + inspected_port->local_port = port->local_port; + inspected_port->type = type; + list_add_tail(&inspected_port->list, &span_entry->bound_ports_list); + + return 0; + +err_inspected_port_alloc: + if (bind) + mlxsw_sp_span_inspected_port_bind(port, span_entry, type, + false); +err_port_bind: + if (type == MLXSW_SP_SPAN_EGRESS) { + mlxsw_reg_sbib_pack(sbib_pl, port->local_port, 0); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl); + } + return err; +} + +static void +mlxsw_sp_span_inspected_port_del(struct mlxsw_sp_port *port, + struct mlxsw_sp_span_entry *span_entry, + enum mlxsw_sp_span_type type, + bool bind) +{ + struct mlxsw_sp_span_inspected_port *inspected_port; + struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; + char sbib_pl[MLXSW_REG_SBIB_LEN]; + + inspected_port = mlxsw_sp_span_entry_bound_port_find(port, span_entry); + if (!inspected_port) + return; + + if (bind) + mlxsw_sp_span_inspected_port_bind(port, span_entry, type, + false); + /* remove the SBIB buffer if it was egress SPAN */ + if (type == MLXSW_SP_SPAN_EGRESS) { + mlxsw_reg_sbib_pack(sbib_pl, port->local_port, 0); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl); + } + + mlxsw_sp_span_entry_put(mlxsw_sp, span_entry); + + list_del(&inspected_port->list); + kfree(inspected_port); +} + +static const struct mlxsw_sp_span_entry_ops * +mlxsw_sp_span_entry_ops(struct mlxsw_sp *mlxsw_sp, + const struct net_device *to_dev) +{ + size_t i; + + for (i = 0; i < ARRAY_SIZE(mlxsw_sp_span_entry_types); ++i) + if (mlxsw_sp_span_entry_types[i]->can_handle(to_dev)) + return mlxsw_sp_span_entry_types[i]; + + return NULL; +} + +int mlxsw_sp_span_mirror_add(struct mlxsw_sp_port *from, + const struct net_device *to_dev, + enum mlxsw_sp_span_type type, bool bind, + int *p_span_id) +{ + struct mlxsw_sp *mlxsw_sp = from->mlxsw_sp; + const struct mlxsw_sp_span_entry_ops *ops; + struct mlxsw_sp_span_parms sparms = {0}; + struct mlxsw_sp_span_entry *span_entry; + int err; + + ops = mlxsw_sp_span_entry_ops(mlxsw_sp, to_dev); + if (!ops) { + netdev_err(to_dev, "Cannot mirror to %s", to_dev->name); + return -EOPNOTSUPP; + } + + err = ops->parms(to_dev, &sparms); + if (err) + return err; + + span_entry = mlxsw_sp_span_entry_get(mlxsw_sp, to_dev, ops, sparms); + if (!span_entry) + return -ENOENT; + + netdev_dbg(from->dev, "Adding inspected port to SPAN entry %d\n", + span_entry->id); + + err = mlxsw_sp_span_inspected_port_add(from, span_entry, type, bind); + if (err) + goto err_port_bind; + + *p_span_id = span_entry->id; + return 0; + +err_port_bind: + mlxsw_sp_span_entry_put(mlxsw_sp, span_entry); + return err; +} + +void mlxsw_sp_span_mirror_del(struct mlxsw_sp_port *from, int span_id, + enum mlxsw_sp_span_type type, bool bind) +{ + struct mlxsw_sp_span_entry *span_entry; + + span_entry = mlxsw_sp_span_entry_find_by_id(from->mlxsw_sp, span_id); + if (!span_entry) { + netdev_err(from->dev, "no span entry found\n"); + return; + } + + netdev_dbg(from->dev, "removing inspected port from SPAN entry %d\n", + span_entry->id); + mlxsw_sp_span_inspected_port_del(from, span_entry, type, bind); +} + +void mlxsw_sp_span_respin(struct mlxsw_sp *mlxsw_sp) +{ + int i; + int err; + + ASSERT_RTNL(); + for (i = 0; i < mlxsw_sp->span.entries_count; i++) { + struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i]; + struct mlxsw_sp_span_parms sparms = {0}; + + if (!curr->ref_count) + continue; + + err = curr->ops->parms(curr->to_dev, &sparms); + if (err) + continue; + + if (memcmp(&sparms, &curr->parms, sizeof(sparms))) { + mlxsw_sp_span_entry_deconfigure(curr); + mlxsw_sp_span_entry_configure(mlxsw_sp, curr, sparms); + } + } +} diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h new file mode 100644 index 000000000000..948aceb512c5 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h @@ -0,0 +1,104 @@ +/* + * drivers/net/ethernet/mellanox/mlxsw/mlxsw_span.h + * Copyright (c) 2018 Mellanox Technologies. All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _MLXSW_SPECTRUM_SPAN_H +#define _MLXSW_SPECTRUM_SPAN_H + +#include <linux/types.h> +#include <linux/if_ether.h> + +#include "spectrum_router.h" + +struct mlxsw_sp; +struct mlxsw_sp_port; + +enum mlxsw_sp_span_type { + MLXSW_SP_SPAN_EGRESS, + MLXSW_SP_SPAN_INGRESS +}; + +struct mlxsw_sp_span_inspected_port { + struct list_head list; + enum mlxsw_sp_span_type type; + u8 local_port; +}; + +struct mlxsw_sp_span_parms { + struct mlxsw_sp_port *dest_port; /* NULL for unoffloaded SPAN. */ + unsigned int ttl; + unsigned char dmac[ETH_ALEN]; + unsigned char smac[ETH_ALEN]; + union mlxsw_sp_l3addr daddr; + union mlxsw_sp_l3addr saddr; +}; + +struct mlxsw_sp_span_entry_ops; + +struct mlxsw_sp_span_entry { + const struct net_device *to_dev; + const struct mlxsw_sp_span_entry_ops *ops; + struct mlxsw_sp_span_parms parms; + struct list_head bound_ports_list; + int ref_count; + int id; +}; + +struct mlxsw_sp_span_entry_ops { + bool (*can_handle)(const struct net_device *to_dev); + int (*parms)(const struct net_device *to_dev, + struct mlxsw_sp_span_parms *sparmsp); + int (*configure)(struct mlxsw_sp_span_entry *span_entry, + struct mlxsw_sp_span_parms sparms); + void (*deconfigure)(struct mlxsw_sp_span_entry *span_entry); +}; + +int mlxsw_sp_span_init(struct mlxsw_sp *mlxsw_sp); +void mlxsw_sp_span_fini(struct mlxsw_sp *mlxsw_sp); +void mlxsw_sp_span_respin(struct mlxsw_sp *mlxsw_sp); + +int mlxsw_sp_span_mirror_add(struct mlxsw_sp_port *from, + const struct net_device *to_dev, + enum mlxsw_sp_span_type type, + bool bind, int *p_span_id); +void mlxsw_sp_span_mirror_del(struct mlxsw_sp_port *from, int span_id, + enum mlxsw_sp_span_type type, bool bind); +struct mlxsw_sp_span_entry * +mlxsw_sp_span_entry_find_by_port(struct mlxsw_sp *mlxsw_sp, + const struct net_device *to_dev); + +void mlxsw_sp_span_entry_invalidate(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_span_entry *span_entry); + +int mlxsw_sp_span_port_mtu_update(struct mlxsw_sp_port *port, u16 mtu); + +#endif diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 593ad31be749..917663adf925 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -1819,7 +1819,7 @@ mlxsw_sp_bridge_8021q_port_join(struct mlxsw_sp_bridge_device *bridge_device, struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan; if (is_vlan_dev(bridge_port->dev)) { - NL_SET_ERR_MSG(extack, "spectrum: Can not enslave a VLAN device to a VLAN-aware bridge"); + NL_SET_ERR_MSG_MOD(extack, "Can not enslave a VLAN device to a VLAN-aware bridge"); return -EINVAL; } @@ -1882,20 +1882,16 @@ mlxsw_sp_bridge_8021d_port_join(struct mlxsw_sp_bridge_device *bridge_device, struct netlink_ext_ack *extack) { struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan; + struct net_device *dev = bridge_port->dev; u16 vid; - if (!is_vlan_dev(bridge_port->dev)) { - NL_SET_ERR_MSG(extack, "spectrum: Only VLAN devices can be enslaved to a VLAN-unaware bridge"); - return -EINVAL; - } - vid = vlan_dev_vlan_id(bridge_port->dev); - + vid = is_vlan_dev(dev) ? vlan_dev_vlan_id(dev) : 1; mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid); if (WARN_ON(!mlxsw_sp_port_vlan)) return -EINVAL; if (mlxsw_sp_port_is_br_member(mlxsw_sp_port, bridge_device->dev)) { - NL_SET_ERR_MSG(extack, "spectrum: Can not bridge VLAN uppers of the same port"); + NL_SET_ERR_MSG_MOD(extack, "Can not bridge VLAN uppers of the same port"); return -EINVAL; } @@ -1912,8 +1908,10 @@ mlxsw_sp_bridge_8021d_port_leave(struct mlxsw_sp_bridge_device *bridge_device, struct mlxsw_sp_port *mlxsw_sp_port) { struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan; - u16 vid = vlan_dev_vlan_id(bridge_port->dev); + struct net_device *dev = bridge_port->dev; + u16 vid; + vid = is_vlan_dev(dev) ? vlan_dev_vlan_id(dev) : 1; mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid); if (WARN_ON(!mlxsw_sp_port_vlan)) return; diff --git a/drivers/net/ethernet/natsemi/jazzsonic.c b/drivers/net/ethernet/natsemi/jazzsonic.c index d5b28884e21e..51fa82b429a3 100644 --- a/drivers/net/ethernet/natsemi/jazzsonic.c +++ b/drivers/net/ethernet/natsemi/jazzsonic.c @@ -60,14 +60,6 @@ do { \ *((volatile unsigned int *)dev->base_addr+(reg)) = (val); \ } while (0) - -/* use 0 for production, 1 for verification, >1 for debug */ -#ifdef SONIC_DEBUG -static unsigned int sonic_debug = SONIC_DEBUG; -#else -static unsigned int sonic_debug = 1; -#endif - /* * We cannot use station (ethernet) address prefixes to detect the * sonic controller since these are board manufacturer depended. @@ -117,7 +109,6 @@ static const struct net_device_ops sonic_netdev_ops = { static int sonic_probe1(struct net_device *dev) { - static unsigned version_printed; unsigned int silicon_revision; unsigned int val; struct sonic_local *lp = netdev_priv(dev); @@ -133,26 +124,17 @@ static int sonic_probe1(struct net_device *dev) * the expected location. */ silicon_revision = SONIC_READ(SONIC_SR); - if (sonic_debug > 1) - printk("SONIC Silicon Revision = 0x%04x\n",silicon_revision); - i = 0; while (known_revisions[i] != 0xffff && known_revisions[i] != silicon_revision) i++; if (known_revisions[i] == 0xffff) { - printk("SONIC ethernet controller not found (0x%4x)\n", - silicon_revision); + pr_info("SONIC ethernet controller not found (0x%4x)\n", + silicon_revision); goto out; } - if (sonic_debug && version_printed++ == 0) - printk(version); - - printk(KERN_INFO "%s: Sonic ethernet found at 0x%08lx, ", - dev_name(lp->device), dev->base_addr); - /* * Put the sonic into software reset, then * retrieve and print the ethernet address. @@ -245,12 +227,16 @@ static int jazz_sonic_probe(struct platform_device *pdev) err = sonic_probe1(dev); if (err) goto out; + + pr_info("SONIC ethernet @%08lx, MAC %pM, IRQ %d\n", + dev->base_addr, dev->dev_addr, dev->irq); + + sonic_msg_init(dev); + err = register_netdev(dev); if (err) goto out1; - printk("%s: MAC %pM IRQ %d\n", dev->name, dev->dev_addr, dev->irq); - return 0; out1: @@ -262,8 +248,6 @@ out: } MODULE_DESCRIPTION("Jazz SONIC ethernet driver"); -module_param(sonic_debug, int, 0); -MODULE_PARM_DESC(sonic_debug, "jazzsonic debug level (1-4)"); MODULE_ALIAS("platform:jazzsonic"); #include "sonic.c" diff --git a/drivers/net/ethernet/natsemi/macsonic.c b/drivers/net/ethernet/natsemi/macsonic.c index b922ab5cedea..0937fc2a928e 100644 --- a/drivers/net/ethernet/natsemi/macsonic.c +++ b/drivers/net/ethernet/natsemi/macsonic.c @@ -60,8 +60,6 @@ #include <asm/macints.h> #include <asm/mac_via.h> -static char mac_sonic_string[] = "macsonic"; - #include "sonic.h" /* These should basically be bus-size and endian independent (since @@ -72,15 +70,6 @@ static char mac_sonic_string[] = "macsonic"; #define SONIC_WRITE(reg,val) (nubus_writew(val, dev->base_addr + (reg * 4) \ + lp->reg_offset)) -/* use 0 for production, 1 for verification, >1 for debug */ -#ifdef SONIC_DEBUG -static unsigned int sonic_debug = SONIC_DEBUG; -#else -static unsigned int sonic_debug = 1; -#endif - -static int sonic_version_printed; - /* For onboard SONIC */ #define ONBOARD_SONIC_REGISTERS 0x50F0A000 #define ONBOARD_SONIC_PROM_BASE 0x50f08000 @@ -313,11 +302,6 @@ static int mac_onboard_sonic_probe(struct net_device *dev) int sr; bool commslot = macintosh_config->expansion_type == MAC_EXP_PDS_COMM; - if (!MACH_IS_MAC) - return -ENODEV; - - printk(KERN_INFO "Checking for internal Macintosh ethernet (SONIC).. "); - /* Bogus probing, on the models which may or may not have Ethernet (BTW, the Ethernet *is* always at the same address, and nothing else lives there, at least if Apple's @@ -327,13 +311,11 @@ static int mac_onboard_sonic_probe(struct net_device *dev) card_present = hwreg_present((void*)ONBOARD_SONIC_REGISTERS); if (!card_present) { - printk("none.\n"); + pr_info("Onboard/comm-slot SONIC not found\n"); return -ENODEV; } } - printk("yes\n"); - /* Danger! My arms are flailing wildly! You *must* set lp->reg_offset * and dev->base_addr before using SONIC_READ() or SONIC_WRITE() */ dev->base_addr = ONBOARD_SONIC_REGISTERS; @@ -342,18 +324,10 @@ static int mac_onboard_sonic_probe(struct net_device *dev) else dev->irq = IRQ_NUBUS_9; - if (!sonic_version_printed) { - printk(KERN_INFO "%s", version); - sonic_version_printed = 1; - } - printk(KERN_INFO "%s: onboard / comm-slot SONIC at 0x%08lx\n", - dev_name(lp->device), dev->base_addr); - /* The PowerBook's SONIC is 16 bit always. */ if (macintosh_config->ident == MAC_MODEL_PB520) { lp->reg_offset = 0; lp->dma_bitmode = SONIC_BITMODE16; - sr = SONIC_READ(SONIC_SR); } else if (commslot) { /* Some of the comm-slot cards are 16 bit. But some of them are not. The 32-bit cards use offset 2 and @@ -370,22 +344,21 @@ static int mac_onboard_sonic_probe(struct net_device *dev) else { lp->dma_bitmode = SONIC_BITMODE16; lp->reg_offset = 0; - sr = SONIC_READ(SONIC_SR); } } else { /* All onboard cards are at offset 2 with 32 bit DMA. */ lp->reg_offset = 2; lp->dma_bitmode = SONIC_BITMODE32; - sr = SONIC_READ(SONIC_SR); } - printk(KERN_INFO - "%s: revision 0x%04x, using %d bit DMA and register offset %d\n", - dev_name(lp->device), sr, lp->dma_bitmode?32:16, lp->reg_offset); -#if 0 /* This is sometimes useful to find out how MacOS configured the card. */ - printk(KERN_INFO "%s: DCR: 0x%04x, DCR2: 0x%04x\n", dev_name(lp->device), - SONIC_READ(SONIC_DCR) & 0xffff, SONIC_READ(SONIC_DCR2) & 0xffff); -#endif + pr_info("Onboard/comm-slot SONIC, revision 0x%04x, %d bit DMA, register offset %d\n", + SONIC_READ(SONIC_SR), lp->dma_bitmode ? 32 : 16, + lp->reg_offset); + + /* This is sometimes useful to find out how MacOS configured the card */ + pr_debug("%s: DCR=0x%04x, DCR2=0x%04x\n", __func__, + SONIC_READ(SONIC_DCR) & 0xffff, + SONIC_READ(SONIC_DCR2) & 0xffff); /* Software reset, then initialize control registers. */ SONIC_WRITE(SONIC_CMD, SONIC_CR_RST); @@ -406,11 +379,14 @@ static int mac_onboard_sonic_probe(struct net_device *dev) /* Now look for the MAC address. */ mac_onboard_sonic_ethernet_addr(dev); + pr_info("SONIC ethernet @%08lx, MAC %pM, IRQ %d\n", + dev->base_addr, dev->dev_addr, dev->irq); + /* Shared init code */ return macsonic_init(dev); } -static int mac_nubus_sonic_ethernet_addr(struct net_device *dev, +static int mac_sonic_nubus_ethernet_addr(struct net_device *dev, unsigned long prom_addr, int id) { int i; @@ -449,70 +425,49 @@ static int macsonic_ident(struct nubus_rsrc *fres) return -1; } -static int mac_nubus_sonic_probe(struct net_device *dev) +static int mac_sonic_nubus_probe_board(struct nubus_board *board, int id, + struct net_device *dev) { - static int slots; - struct nubus_rsrc *ndev = NULL; struct sonic_local* lp = netdev_priv(dev); unsigned long base_addr, prom_addr; u16 sonic_dcr; - int id = -1; int reg_offset, dma_bitmode; - /* Find the first SONIC that hasn't been initialized already */ - for_each_func_rsrc(ndev) { - if (ndev->category != NUBUS_CAT_NETWORK || - ndev->type != NUBUS_TYPE_ETHERNET) - continue; - - /* Have we seen it already? */ - if (slots & (1<<ndev->board->slot)) - continue; - slots |= 1<<ndev->board->slot; - - /* Is it one of ours? */ - if ((id = macsonic_ident(ndev)) != -1) - break; - } - - if (ndev == NULL) - return -ENODEV; - switch (id) { case MACSONIC_DUODOCK: - base_addr = ndev->board->slot_addr + DUODOCK_SONIC_REGISTERS; - prom_addr = ndev->board->slot_addr + DUODOCK_SONIC_PROM_BASE; + base_addr = board->slot_addr + DUODOCK_SONIC_REGISTERS; + prom_addr = board->slot_addr + DUODOCK_SONIC_PROM_BASE; sonic_dcr = SONIC_DCR_EXBUS | SONIC_DCR_RFT0 | SONIC_DCR_RFT1 | SONIC_DCR_TFT0; reg_offset = 2; dma_bitmode = SONIC_BITMODE32; break; case MACSONIC_APPLE: - base_addr = ndev->board->slot_addr + APPLE_SONIC_REGISTERS; - prom_addr = ndev->board->slot_addr + APPLE_SONIC_PROM_BASE; + base_addr = board->slot_addr + APPLE_SONIC_REGISTERS; + prom_addr = board->slot_addr + APPLE_SONIC_PROM_BASE; sonic_dcr = SONIC_DCR_BMS | SONIC_DCR_RFT1 | SONIC_DCR_TFT0; reg_offset = 0; dma_bitmode = SONIC_BITMODE32; break; case MACSONIC_APPLE16: - base_addr = ndev->board->slot_addr + APPLE_SONIC_REGISTERS; - prom_addr = ndev->board->slot_addr + APPLE_SONIC_PROM_BASE; + base_addr = board->slot_addr + APPLE_SONIC_REGISTERS; + prom_addr = board->slot_addr + APPLE_SONIC_PROM_BASE; sonic_dcr = SONIC_DCR_EXBUS | SONIC_DCR_RFT1 | SONIC_DCR_TFT0 | SONIC_DCR_PO1 | SONIC_DCR_BMS; reg_offset = 0; dma_bitmode = SONIC_BITMODE16; break; case MACSONIC_DAYNALINK: - base_addr = ndev->board->slot_addr + APPLE_SONIC_REGISTERS; - prom_addr = ndev->board->slot_addr + DAYNALINK_PROM_BASE; + base_addr = board->slot_addr + APPLE_SONIC_REGISTERS; + prom_addr = board->slot_addr + DAYNALINK_PROM_BASE; sonic_dcr = SONIC_DCR_RFT1 | SONIC_DCR_TFT0 | SONIC_DCR_PO1 | SONIC_DCR_BMS; reg_offset = 0; dma_bitmode = SONIC_BITMODE16; break; case MACSONIC_DAYNA: - base_addr = ndev->board->slot_addr + DAYNA_SONIC_REGISTERS; - prom_addr = ndev->board->slot_addr + DAYNA_SONIC_MAC_ADDR; + base_addr = board->slot_addr + DAYNA_SONIC_REGISTERS; + prom_addr = board->slot_addr + DAYNA_SONIC_MAC_ADDR; sonic_dcr = SONIC_DCR_BMS | SONIC_DCR_RFT1 | SONIC_DCR_TFT0 | SONIC_DCR_PO1; reg_offset = 0; @@ -528,21 +483,16 @@ static int mac_nubus_sonic_probe(struct net_device *dev) dev->base_addr = base_addr; lp->reg_offset = reg_offset; lp->dma_bitmode = dma_bitmode; - dev->irq = SLOT2IRQ(ndev->board->slot); + dev->irq = SLOT2IRQ(board->slot); - if (!sonic_version_printed) { - printk(KERN_INFO "%s", version); - sonic_version_printed = 1; - } - printk(KERN_INFO "%s: %s in slot %X\n", - dev_name(lp->device), ndev->board->name, ndev->board->slot); - printk(KERN_INFO "%s: revision 0x%04x, using %d bit DMA and register offset %d\n", - dev_name(lp->device), SONIC_READ(SONIC_SR), dma_bitmode?32:16, reg_offset); + dev_info(&board->dev, "%s, revision 0x%04x, %d bit DMA, register offset %d\n", + board->name, SONIC_READ(SONIC_SR), + lp->dma_bitmode ? 32 : 16, lp->reg_offset); -#if 0 /* This is sometimes useful to find out how MacOS configured the card. */ - printk(KERN_INFO "%s: DCR: 0x%04x, DCR2: 0x%04x\n", dev_name(lp->device), - SONIC_READ(SONIC_DCR) & 0xffff, SONIC_READ(SONIC_DCR2) & 0xffff); -#endif + /* This is sometimes useful to find out how MacOS configured the card */ + dev_dbg(&board->dev, "%s: DCR=0x%04x, DCR2=0x%04x\n", __func__, + SONIC_READ(SONIC_DCR) & 0xffff, + SONIC_READ(SONIC_DCR2) & 0xffff); /* Software reset, then initialize control registers. */ SONIC_WRITE(SONIC_CMD, SONIC_CR_RST); @@ -557,14 +507,17 @@ static int mac_nubus_sonic_probe(struct net_device *dev) SONIC_WRITE(SONIC_ISR, 0x7fff); /* Now look for the MAC address. */ - if (mac_nubus_sonic_ethernet_addr(dev, prom_addr, id) != 0) + if (mac_sonic_nubus_ethernet_addr(dev, prom_addr, id) != 0) return -ENODEV; + dev_info(&board->dev, "SONIC ethernet @%08lx, MAC %pM, IRQ %d\n", + dev->base_addr, dev->dev_addr, dev->irq); + /* Shared init code */ return macsonic_init(dev); } -static int mac_sonic_probe(struct platform_device *pdev) +static int mac_sonic_platform_probe(struct platform_device *pdev) { struct net_device *dev; struct sonic_local *lp; @@ -579,22 +532,16 @@ static int mac_sonic_probe(struct platform_device *pdev) SET_NETDEV_DEV(dev, &pdev->dev); platform_set_drvdata(pdev, dev); - /* This will catch fatal stuff like -ENOMEM as well as success */ err = mac_onboard_sonic_probe(dev); - if (err == 0) - goto found; - if (err != -ENODEV) - goto out; - err = mac_nubus_sonic_probe(dev); if (err) goto out; -found: + + sonic_msg_init(dev); + err = register_netdev(dev); if (err) goto out; - printk("%s: MAC %pM IRQ %d\n", dev->name, dev->dev_addr, dev->irq); - return 0; out: @@ -604,13 +551,11 @@ out: } MODULE_DESCRIPTION("Macintosh SONIC ethernet driver"); -module_param(sonic_debug, int, 0); -MODULE_PARM_DESC(sonic_debug, "macsonic debug level (1-4)"); MODULE_ALIAS("platform:macsonic"); #include "sonic.c" -static int mac_sonic_device_remove(struct platform_device *pdev) +static int mac_sonic_platform_remove(struct platform_device *pdev) { struct net_device *dev = platform_get_drvdata(pdev); struct sonic_local* lp = netdev_priv(dev); @@ -623,12 +568,105 @@ static int mac_sonic_device_remove(struct platform_device *pdev) return 0; } -static struct platform_driver mac_sonic_driver = { - .probe = mac_sonic_probe, - .remove = mac_sonic_device_remove, - .driver = { - .name = mac_sonic_string, +static struct platform_driver mac_sonic_platform_driver = { + .probe = mac_sonic_platform_probe, + .remove = mac_sonic_platform_remove, + .driver = { + .name = "macsonic", + }, +}; + +static int mac_sonic_nubus_probe(struct nubus_board *board) +{ + struct net_device *ndev; + struct sonic_local *lp; + struct nubus_rsrc *fres; + int id = -1; + int err; + + /* The platform driver will handle a PDS or Comm Slot card (even if + * it has a pseudoslot declaration ROM). + */ + if (macintosh_config->expansion_type == MAC_EXP_PDS_COMM) + return -ENODEV; + + for_each_board_func_rsrc(board, fres) { + if (fres->category != NUBUS_CAT_NETWORK || + fres->type != NUBUS_TYPE_ETHERNET) + continue; + + id = macsonic_ident(fres); + if (id != -1) + break; + } + if (!fres) + return -ENODEV; + + ndev = alloc_etherdev(sizeof(struct sonic_local)); + if (!ndev) + return -ENOMEM; + + lp = netdev_priv(ndev); + lp->device = &board->dev; + SET_NETDEV_DEV(ndev, &board->dev); + + err = mac_sonic_nubus_probe_board(board, id, ndev); + if (err) + goto out; + + sonic_msg_init(ndev); + + err = register_netdev(ndev); + if (err) + goto out; + + nubus_set_drvdata(board, ndev); + + return 0; + +out: + free_netdev(ndev); + return err; +} + +static int mac_sonic_nubus_remove(struct nubus_board *board) +{ + struct net_device *ndev = nubus_get_drvdata(board); + struct sonic_local *lp = netdev_priv(ndev); + + unregister_netdev(ndev); + dma_free_coherent(lp->device, + SIZEOF_SONIC_DESC * SONIC_BUS_SCALE(lp->dma_bitmode), + lp->descriptors, lp->descriptors_laddr); + free_netdev(ndev); + + return 0; +} + +static struct nubus_driver mac_sonic_nubus_driver = { + .probe = mac_sonic_nubus_probe, + .remove = mac_sonic_nubus_remove, + .driver = { + .name = "macsonic-nubus", + .owner = THIS_MODULE, }, }; -module_platform_driver(mac_sonic_driver); +static int perr, nerr; + +static int __init mac_sonic_init(void) +{ + perr = platform_driver_register(&mac_sonic_platform_driver); + nerr = nubus_driver_register(&mac_sonic_nubus_driver); + return 0; +} +module_init(mac_sonic_init); + +static void __exit mac_sonic_exit(void) +{ + if (!perr) + platform_driver_unregister(&mac_sonic_platform_driver); + if (!nerr) + nubus_driver_unregister(&mac_sonic_nubus_driver); +} +module_exit(mac_sonic_exit); diff --git a/drivers/net/ethernet/natsemi/sonic.c b/drivers/net/ethernet/natsemi/sonic.c index 612c7a44b26c..7ed08486ae23 100644 --- a/drivers/net/ethernet/natsemi/sonic.c +++ b/drivers/net/ethernet/natsemi/sonic.c @@ -33,7 +33,21 @@ * the NetBSD file "sys/arch/mac68k/dev/if_sn.c". */ +static unsigned int version_printed; +static int sonic_debug = -1; +module_param(sonic_debug, int, 0); +MODULE_PARM_DESC(sonic_debug, "debug message level"); + +static void sonic_msg_init(struct net_device *dev) +{ + struct sonic_local *lp = netdev_priv(dev); + + lp->msg_enable = netif_msg_init(sonic_debug, 0); + + if (version_printed++ == 0) + netif_dbg(lp, drv, dev, "%s", version); +} /* * Open/initialize the SONIC controller. @@ -47,8 +61,7 @@ static int sonic_open(struct net_device *dev) struct sonic_local *lp = netdev_priv(dev); int i; - if (sonic_debug > 2) - printk("sonic_open: initializing sonic driver.\n"); + netif_dbg(lp, ifup, dev, "%s: initializing sonic driver\n", __func__); for (i = 0; i < SONIC_NUM_RRS; i++) { struct sk_buff *skb = netdev_alloc_skb(dev, SONIC_RBSIZE + 2); @@ -95,8 +108,7 @@ static int sonic_open(struct net_device *dev) netif_start_queue(dev); - if (sonic_debug > 2) - printk("sonic_open: Initialization done.\n"); + netif_dbg(lp, ifup, dev, "%s: Initialization done\n", __func__); return 0; } @@ -110,8 +122,7 @@ static int sonic_close(struct net_device *dev) struct sonic_local *lp = netdev_priv(dev); int i; - if (sonic_debug > 2) - printk("sonic_close\n"); + netif_dbg(lp, ifdown, dev, "%s\n", __func__); netif_stop_queue(dev); @@ -205,8 +216,7 @@ static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev) int length; int entry = lp->next_tx; - if (sonic_debug > 2) - printk("sonic_send_packet: skb=%p, dev=%p\n", skb, dev); + netif_dbg(lp, tx_queued, dev, "%s: skb=%p\n", __func__, skb); length = skb->len; if (length < ETH_ZLEN) { @@ -252,14 +262,12 @@ static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev) lp->next_tx = (entry + 1) & SONIC_TDS_MASK; if (lp->tx_skb[lp->next_tx] != NULL) { /* The ring is full, the ISR has yet to process the next TD. */ - if (sonic_debug > 3) - printk("%s: stopping queue\n", dev->name); + netif_dbg(lp, tx_queued, dev, "%s: stopping queue\n", __func__); netif_stop_queue(dev); /* after this packet, wait for ISR to free up some TDAs */ } else netif_start_queue(dev); - if (sonic_debug > 2) - printk("sonic_send_packet: issuing Tx command\n"); + netif_dbg(lp, tx_queued, dev, "%s: issuing Tx command\n", __func__); SONIC_WRITE(SONIC_CMD, SONIC_CR_TXP); @@ -281,8 +289,7 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id) do { if (status & SONIC_INT_PKTRX) { - if (sonic_debug > 2) - printk("%s: packet rx\n", dev->name); + netif_dbg(lp, intr, dev, "%s: packet rx\n", __func__); sonic_rx(dev); /* got packet(s) */ SONIC_WRITE(SONIC_ISR, SONIC_INT_PKTRX); /* clear the interrupt */ } @@ -299,8 +306,7 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id) * still being allocated by sonic_send_packet (status clear & tx_skb[entry] clear) */ - if (sonic_debug > 2) - printk("%s: tx done\n", dev->name); + netif_dbg(lp, intr, dev, "%s: tx done\n", __func__); while (lp->tx_skb[entry] != NULL) { if ((td_status = sonic_tda_get(dev, entry, SONIC_TD_STATUS)) == 0) @@ -346,20 +352,20 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id) * check error conditions */ if (status & SONIC_INT_RFO) { - if (sonic_debug > 1) - printk("%s: rx fifo overrun\n", dev->name); + netif_dbg(lp, rx_err, dev, "%s: rx fifo overrun\n", + __func__); lp->stats.rx_fifo_errors++; SONIC_WRITE(SONIC_ISR, SONIC_INT_RFO); /* clear the interrupt */ } if (status & SONIC_INT_RDE) { - if (sonic_debug > 1) - printk("%s: rx descriptors exhausted\n", dev->name); + netif_dbg(lp, rx_err, dev, "%s: rx descriptors exhausted\n", + __func__); lp->stats.rx_dropped++; SONIC_WRITE(SONIC_ISR, SONIC_INT_RDE); /* clear the interrupt */ } if (status & SONIC_INT_RBAE) { - if (sonic_debug > 1) - printk("%s: rx buffer area exceeded\n", dev->name); + netif_dbg(lp, rx_err, dev, "%s: rx buffer area exceeded\n", + __func__); lp->stats.rx_dropped++; SONIC_WRITE(SONIC_ISR, SONIC_INT_RBAE); /* clear the interrupt */ } @@ -380,8 +386,9 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id) /* transmit error */ if (status & SONIC_INT_TXER) { - if ((SONIC_READ(SONIC_TCR) & SONIC_TCR_FU) && (sonic_debug > 2)) - printk(KERN_ERR "%s: tx fifo underrun\n", dev->name); + if (SONIC_READ(SONIC_TCR) & SONIC_TCR_FU) + netif_dbg(lp, tx_err, dev, "%s: tx fifo underrun\n", + __func__); SONIC_WRITE(SONIC_ISR, SONIC_INT_TXER); /* clear the interrupt */ } @@ -475,8 +482,8 @@ static void sonic_rx(struct net_device *dev) if (lp->cur_rwp >= lp->rra_end) lp->cur_rwp = lp->rra_laddr & 0xffff; SONIC_WRITE(SONIC_RWP, lp->cur_rwp); if (SONIC_READ(SONIC_ISR) & SONIC_INT_RBE) { - if (sonic_debug > 2) - printk("%s: rx buffer exhausted\n", dev->name); + netif_dbg(lp, rx_err, dev, "%s: rx buffer exhausted\n", + __func__); SONIC_WRITE(SONIC_ISR, SONIC_INT_RBE); /* clear the flag */ } } else @@ -542,9 +549,8 @@ static void sonic_multicast_list(struct net_device *dev) (netdev_mc_count(dev) > 15)) { rcr |= SONIC_RCR_AMC; } else { - if (sonic_debug > 2) - printk("sonic_multicast_list: mc_count %d\n", - netdev_mc_count(dev)); + netif_dbg(lp, ifup, dev, "%s: mc_count %d\n", __func__, + netdev_mc_count(dev)); sonic_set_cam_enable(dev, 1); /* always enable our own address */ i = 1; netdev_for_each_mc_addr(ha, dev) { @@ -562,8 +568,7 @@ static void sonic_multicast_list(struct net_device *dev) } } - if (sonic_debug > 2) - printk("sonic_multicast_list: setting RCR=%x\n", rcr); + netif_dbg(lp, ifup, dev, "%s: setting RCR=%x\n", __func__, rcr); SONIC_WRITE(SONIC_RCR, rcr); } @@ -596,8 +601,8 @@ static int sonic_init(struct net_device *dev) /* * initialize the receive resource area */ - if (sonic_debug > 2) - printk("sonic_init: initialize receive resource area\n"); + netif_dbg(lp, ifup, dev, "%s: initialize receive resource area\n", + __func__); for (i = 0; i < SONIC_NUM_RRS; i++) { u16 bufadr_l = (unsigned long)lp->rx_laddr[i] & 0xffff; @@ -622,8 +627,7 @@ static int sonic_init(struct net_device *dev) SONIC_WRITE(SONIC_EOBC, (SONIC_RBSIZE >> 1) - (lp->dma_bitmode ? 2 : 1)); /* load the resource pointers */ - if (sonic_debug > 3) - printk("sonic_init: issuing RRRA command\n"); + netif_dbg(lp, ifup, dev, "%s: issuing RRRA command\n", __func__); SONIC_WRITE(SONIC_CMD, SONIC_CR_RRRA); i = 0; @@ -632,16 +636,17 @@ static int sonic_init(struct net_device *dev) break; } - if (sonic_debug > 2) - printk("sonic_init: status=%x i=%d\n", SONIC_READ(SONIC_CMD), i); + netif_dbg(lp, ifup, dev, "%s: status=%x, i=%d\n", __func__, + SONIC_READ(SONIC_CMD), i); /* * Initialize the receive descriptors so that they * become a circular linked list, ie. let the last * descriptor point to the first again. */ - if (sonic_debug > 2) - printk("sonic_init: initialize receive descriptors\n"); + netif_dbg(lp, ifup, dev, "%s: initialize receive descriptors\n", + __func__); + for (i=0; i<SONIC_NUM_RDS; i++) { sonic_rda_put(dev, i, SONIC_RD_STATUS, 0); sonic_rda_put(dev, i, SONIC_RD_PKTLEN, 0); @@ -664,8 +669,9 @@ static int sonic_init(struct net_device *dev) /* * initialize transmit descriptors */ - if (sonic_debug > 2) - printk("sonic_init: initialize transmit descriptors\n"); + netif_dbg(lp, ifup, dev, "%s: initialize transmit descriptors\n", + __func__); + for (i = 0; i < SONIC_NUM_TDS; i++) { sonic_tda_put(dev, i, SONIC_TD_STATUS, 0); sonic_tda_put(dev, i, SONIC_TD_CONFIG, 0); @@ -712,10 +718,8 @@ static int sonic_init(struct net_device *dev) if (SONIC_READ(SONIC_ISR) & SONIC_INT_LCD) break; } - if (sonic_debug > 2) { - printk("sonic_init: CMD=%x, ISR=%x\n, i=%d", - SONIC_READ(SONIC_CMD), SONIC_READ(SONIC_ISR), i); - } + netif_dbg(lp, ifup, dev, "%s: CMD=%x, ISR=%x, i=%d\n", __func__, + SONIC_READ(SONIC_CMD), SONIC_READ(SONIC_ISR), i); /* * enable receiver, disable loopback @@ -731,9 +735,8 @@ static int sonic_init(struct net_device *dev) if ((cmd & SONIC_CR_RXEN) == 0 || (cmd & SONIC_CR_STP) == 0) printk(KERN_ERR "sonic_init: failed, status=%x\n", cmd); - if (sonic_debug > 2) - printk("sonic_init: new status=%x\n", - SONIC_READ(SONIC_CMD)); + netif_dbg(lp, ifup, dev, "%s: new status=%x\n", __func__, + SONIC_READ(SONIC_CMD)); return 0; } diff --git a/drivers/net/ethernet/natsemi/sonic.h b/drivers/net/ethernet/natsemi/sonic.h index 421b1a283fed..2b27f7049acb 100644 --- a/drivers/net/ethernet/natsemi/sonic.h +++ b/drivers/net/ethernet/natsemi/sonic.h @@ -319,6 +319,7 @@ struct sonic_local { unsigned int eol_rx; unsigned int eol_tx; /* last unacked transmit packet */ unsigned int next_tx; /* next free TD */ + int msg_enable; struct device *device; /* generic device */ struct net_device_stats stats; }; @@ -336,6 +337,7 @@ static struct net_device_stats *sonic_get_stats(struct net_device *dev); static void sonic_multicast_list(struct net_device *dev); static int sonic_init(struct net_device *dev); static void sonic_tx_timeout(struct net_device *dev); +static void sonic_msg_init(struct net_device *dev); /* Internal inlines for reading/writing DMA buffers. Note that bus size and endianness matter here, whereas they don't for registers, diff --git a/drivers/net/ethernet/natsemi/xtsonic.c b/drivers/net/ethernet/natsemi/xtsonic.c index 1817deea98a4..e1b886e87a76 100644 --- a/drivers/net/ethernet/natsemi/xtsonic.c +++ b/drivers/net/ethernet/natsemi/xtsonic.c @@ -73,14 +73,6 @@ extern void xtboard_get_ether_addr(unsigned char *buf); #define SONIC_WRITE(reg,val) \ *((volatile unsigned int *)dev->base_addr+reg) = val - -/* Use 0 for production, 1 for verification, and >2 for debug */ -#ifdef SONIC_DEBUG -static unsigned int sonic_debug = SONIC_DEBUG; -#else -static unsigned int sonic_debug = 1; -#endif - /* * We cannot use station (ethernet) address prefixes to detect the * sonic controller since these are board manufacturer depended. @@ -130,7 +122,6 @@ static const struct net_device_ops xtsonic_netdev_ops = { static int __init sonic_probe1(struct net_device *dev) { - static unsigned version_printed = 0; unsigned int silicon_revision; struct sonic_local *lp = netdev_priv(dev); unsigned int base_addr = dev->base_addr; @@ -146,23 +137,17 @@ static int __init sonic_probe1(struct net_device *dev) * the expected location. */ silicon_revision = SONIC_READ(SONIC_SR); - if (sonic_debug > 1) - printk("SONIC Silicon Revision = 0x%04x\n",silicon_revision); - i = 0; while ((known_revisions[i] != 0xffff) && (known_revisions[i] != silicon_revision)) i++; if (known_revisions[i] == 0xffff) { - printk("SONIC ethernet controller not found (0x%4x)\n", - silicon_revision); + pr_info("SONIC ethernet controller not found (0x%4x)\n", + silicon_revision); return -ENODEV; } - if (sonic_debug && version_printed++ == 0) - printk(version); - /* * Put the sonic into software reset, then retrieve ethernet address. * Note: we are assuming that the boot-loader has initialized the cam. @@ -273,12 +258,15 @@ int xtsonic_probe(struct platform_device *pdev) if ((err = sonic_probe1(dev))) goto out; + + pr_info("SONIC ethernet @%08lx, MAC %pM, IRQ %d\n", + dev->base_addr, dev->dev_addr, dev->irq); + + sonic_msg_init(dev); + if ((err = register_netdev(dev))) goto out1; - printk("%s: SONIC ethernet @%08lx, MAC %pM, IRQ %d\n", dev->name, - dev->base_addr, dev->dev_addr, dev->irq); - return 0; out1: @@ -290,8 +278,6 @@ out: } MODULE_DESCRIPTION("Xtensa XT2000 SONIC ethernet driver"); -module_param(sonic_debug, int, 0); -MODULE_PARM_DESC(sonic_debug, "xtsonic debug level (1-4)"); #include "sonic.c" diff --git a/drivers/net/ethernet/netronome/nfp/bpf/Makefile b/drivers/net/ethernet/netronome/nfp/bpf/Makefile new file mode 100644 index 000000000000..805fa28f391a --- /dev/null +++ b/drivers/net/ethernet/netronome/nfp/bpf/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +# kbuild requires Makefile in a directory to build individual objects diff --git a/drivers/net/ethernet/netronome/nfp/flower/Makefile b/drivers/net/ethernet/netronome/nfp/flower/Makefile new file mode 100644 index 000000000000..805fa28f391a --- /dev/null +++ b/drivers/net/ethernet/netronome/nfp/flower/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +# kbuild requires Makefile in a directory to build individual objects diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h index adfe474c2cf0..28c1cd5b823b 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h @@ -61,6 +61,13 @@ #define NFP_FLOWER_MASK_MPLS_BOS BIT(8) #define NFP_FLOWER_MASK_MPLS_Q BIT(0) +/* Compressed HW representation of TCP Flags */ +#define NFP_FL_TCP_FLAG_URG BIT(4) +#define NFP_FL_TCP_FLAG_PSH BIT(3) +#define NFP_FL_TCP_FLAG_RST BIT(2) +#define NFP_FL_TCP_FLAG_SYN BIT(1) +#define NFP_FL_TCP_FLAG_FIN BIT(0) + #define NFP_FL_SC_ACT_DROP 0x80000000 #define NFP_FL_SC_ACT_USER 0x7D000000 #define NFP_FL_SC_ACT_POPV 0x6A000000 @@ -257,7 +264,7 @@ struct nfp_flower_tp_ports { * 3 2 1 * 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - * | DSCP |ECN| protocol | reserved | + * | DSCP |ECN| protocol | ttl | flags | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | ipv4_addr_src | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ @@ -268,7 +275,7 @@ struct nfp_flower_ipv4 { u8 tos; u8 proto; u8 ttl; - u8 reserved; + u8 flags; __be32 ipv4_src; __be32 ipv4_dst; }; diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h index 332ff0fdc038..c5cebf6fb1d3 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.h +++ b/drivers/net/ethernet/netronome/nfp/flower/main.h @@ -41,6 +41,7 @@ #include <linux/time64.h> #include <linux/types.h> #include <net/pkt_cls.h> +#include <net/tcp.h> #include <linux/workqueue.h> struct net_device; diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c index 37c2ecae2a7a..b3bc8279d4fb 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/match.c +++ b/drivers/net/ethernet/netronome/nfp/flower/match.c @@ -181,6 +181,26 @@ nfp_flower_compile_ipv4(struct nfp_flower_ipv4 *frame, frame->tos = flow_ip->tos; frame->ttl = flow_ip->ttl; } + + if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_TCP)) { + struct flow_dissector_key_tcp *tcp; + u32 tcp_flags; + + tcp = skb_flow_dissector_target(flow->dissector, + FLOW_DISSECTOR_KEY_TCP, target); + tcp_flags = be16_to_cpu(tcp->flags); + + if (tcp_flags & TCPHDR_FIN) + frame->flags |= NFP_FL_TCP_FLAG_FIN; + if (tcp_flags & TCPHDR_SYN) + frame->flags |= NFP_FL_TCP_FLAG_SYN; + if (tcp_flags & TCPHDR_RST) + frame->flags |= NFP_FL_TCP_FLAG_RST; + if (tcp_flags & TCPHDR_PSH) + frame->flags |= NFP_FL_TCP_FLAG_PSH; + if (tcp_flags & TCPHDR_URG) + frame->flags |= NFP_FL_TCP_FLAG_URG; + } } static void diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index eb5c13dea8f5..f3586c519805 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -44,11 +44,16 @@ #include "../nfp_net.h" #include "../nfp_port.h" +#define NFP_FLOWER_SUPPORTED_TCPFLAGS \ + (TCPHDR_FIN | TCPHDR_SYN | TCPHDR_RST | \ + TCPHDR_PSH | TCPHDR_URG) + #define NFP_FLOWER_WHITELIST_DISSECTOR \ (BIT(FLOW_DISSECTOR_KEY_CONTROL) | \ BIT(FLOW_DISSECTOR_KEY_BASIC) | \ BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | \ BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | \ + BIT(FLOW_DISSECTOR_KEY_TCP) | \ BIT(FLOW_DISSECTOR_KEY_PORTS) | \ BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | \ BIT(FLOW_DISSECTOR_KEY_VLAN) | \ @@ -288,6 +293,35 @@ nfp_flower_calculate_key_layers(struct nfp_app *app, } } + if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_TCP)) { + struct flow_dissector_key_tcp *tcp; + u32 tcp_flags; + + tcp = skb_flow_dissector_target(flow->dissector, + FLOW_DISSECTOR_KEY_TCP, + flow->key); + tcp_flags = be16_to_cpu(tcp->flags); + + if (tcp_flags & ~NFP_FLOWER_SUPPORTED_TCPFLAGS) + return -EOPNOTSUPP; + + /* We only support PSH and URG flags when either + * FIN, SYN or RST is present as well. + */ + if ((tcp_flags & (TCPHDR_PSH | TCPHDR_URG)) && + !(tcp_flags & (TCPHDR_FIN | TCPHDR_SYN | TCPHDR_RST))) + return -EOPNOTSUPP; + + /* We need to store TCP flags in the IPv4 key space, thus + * we need to ensure we include a IPv4 key layer if we have + * not done so already. + */ + if (!(key_layer & NFP_FLOWER_LAYER_IPV4)) { + key_layer |= NFP_FLOWER_LAYER_IPV4; + key_size += sizeof(struct nfp_flower_ipv4); + } + } + ret_key_ls->key_layer = key_layer; ret_key_ls->key_layer_two = key_layer_two; ret_key_ls->key_size = key_size; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.c b/drivers/net/ethernet/netronome/nfp/nfp_main.c index ab301d56430b..c4b1f344b4da 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_main.c @@ -645,6 +645,7 @@ MODULE_FIRMWARE("netronome/nic_AMDA0097-0001_4x10_1x40.nffw"); MODULE_FIRMWARE("netronome/nic_AMDA0097-0001_8x10.nffw"); MODULE_FIRMWARE("netronome/nic_AMDA0099-0001_2x10.nffw"); MODULE_FIRMWARE("netronome/nic_AMDA0099-0001_2x25.nffw"); +MODULE_FIRMWARE("netronome/nic_AMDA0099-0001_1x10_1x25.nffw"); MODULE_AUTHOR("Netronome Systems <oss-drivers@netronome.com>"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h index 4499a7333078..bb63c115537d 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2015-2017 Netronome Systems, Inc. + * Copyright (C) 2015-2018 Netronome Systems, Inc. * * This software is dual licensed under the GNU General License Version 2, * June 1991 as shown in the file COPYING in the top-level directory of this @@ -51,12 +51,12 @@ * The configuration BAR is 8K in size, but due to * THB-350, 32k needs to be reserved. */ -#define NFP_NET_CFG_BAR_SZ (32 * 1024) +#define NFP_NET_CFG_BAR_SZ (32 * 1024) /** * Offset in Freelist buffer where packet starts on RX */ -#define NFP_NET_RX_OFFSET 32 +#define NFP_NET_RX_OFFSET 32 /** * LSO parameters @@ -75,65 +75,65 @@ #define NFP_NET_META_PORTID 5 #define NFP_NET_META_CSUM 6 /* checksum complete type */ -#define NFP_META_PORT_ID_CTRL ~0U +#define NFP_META_PORT_ID_CTRL ~0U /** * Hash type pre-pended when a RSS hash was computed */ -#define NFP_NET_RSS_NONE 0 -#define NFP_NET_RSS_IPV4 1 -#define NFP_NET_RSS_IPV6 2 -#define NFP_NET_RSS_IPV6_EX 3 -#define NFP_NET_RSS_IPV4_TCP 4 -#define NFP_NET_RSS_IPV6_TCP 5 -#define NFP_NET_RSS_IPV6_EX_TCP 6 -#define NFP_NET_RSS_IPV4_UDP 7 -#define NFP_NET_RSS_IPV6_UDP 8 -#define NFP_NET_RSS_IPV6_EX_UDP 9 +#define NFP_NET_RSS_NONE 0 +#define NFP_NET_RSS_IPV4 1 +#define NFP_NET_RSS_IPV6 2 +#define NFP_NET_RSS_IPV6_EX 3 +#define NFP_NET_RSS_IPV4_TCP 4 +#define NFP_NET_RSS_IPV6_TCP 5 +#define NFP_NET_RSS_IPV6_EX_TCP 6 +#define NFP_NET_RSS_IPV4_UDP 7 +#define NFP_NET_RSS_IPV6_UDP 8 +#define NFP_NET_RSS_IPV6_EX_UDP 9 /** * Ring counts - * %NFP_NET_TXR_MAX: Maximum number of TX rings - * %NFP_NET_RXR_MAX: Maximum number of RX rings + * %NFP_NET_TXR_MAX: Maximum number of TX rings + * %NFP_NET_RXR_MAX: Maximum number of RX rings */ -#define NFP_NET_TXR_MAX 64 -#define NFP_NET_RXR_MAX 64 +#define NFP_NET_TXR_MAX 64 +#define NFP_NET_RXR_MAX 64 /** * Read/Write config words (0x0000 - 0x002c) - * %NFP_NET_CFG_CTRL: Global control + * %NFP_NET_CFG_CTRL: Global control * %NFP_NET_CFG_UPDATE: Indicate which fields are updated * %NFP_NET_CFG_TXRS_ENABLE: Bitmask of enabled TX rings * %NFP_NET_CFG_RXRS_ENABLE: Bitmask of enabled RX rings - * %NFP_NET_CFG_MTU: Set MTU size + * %NFP_NET_CFG_MTU: Set MTU size * %NFP_NET_CFG_FLBUFSZ: Set freelist buffer size (must be larger than MTU) - * %NFP_NET_CFG_EXN: MSI-X table entry for exceptions - * %NFP_NET_CFG_LSC: MSI-X table entry for link state changes + * %NFP_NET_CFG_EXN: MSI-X table entry for exceptions + * %NFP_NET_CFG_LSC: MSI-X table entry for link state changes * %NFP_NET_CFG_MACADDR: MAC address * * TODO: * - define Error details in UPDATE */ -#define NFP_NET_CFG_CTRL 0x0000 -#define NFP_NET_CFG_CTRL_ENABLE (0x1 << 0) /* Global enable */ -#define NFP_NET_CFG_CTRL_PROMISC (0x1 << 1) /* Enable Promisc mode */ -#define NFP_NET_CFG_CTRL_L2BC (0x1 << 2) /* Allow L2 Broadcast */ -#define NFP_NET_CFG_CTRL_L2MC (0x1 << 3) /* Allow L2 Multicast */ -#define NFP_NET_CFG_CTRL_RXCSUM (0x1 << 4) /* Enable RX Checksum */ -#define NFP_NET_CFG_CTRL_TXCSUM (0x1 << 5) /* Enable TX Checksum */ -#define NFP_NET_CFG_CTRL_RXVLAN (0x1 << 6) /* Enable VLAN strip */ -#define NFP_NET_CFG_CTRL_TXVLAN (0x1 << 7) /* Enable VLAN insert */ -#define NFP_NET_CFG_CTRL_SCATTER (0x1 << 8) /* Scatter DMA */ -#define NFP_NET_CFG_CTRL_GATHER (0x1 << 9) /* Gather DMA */ -#define NFP_NET_CFG_CTRL_LSO (0x1 << 10) /* LSO/TSO (version 1) */ +#define NFP_NET_CFG_CTRL 0x0000 +#define NFP_NET_CFG_CTRL_ENABLE (0x1 << 0) /* Global enable */ +#define NFP_NET_CFG_CTRL_PROMISC (0x1 << 1) /* Enable Promisc mode */ +#define NFP_NET_CFG_CTRL_L2BC (0x1 << 2) /* Allow L2 Broadcast */ +#define NFP_NET_CFG_CTRL_L2MC (0x1 << 3) /* Allow L2 Multicast */ +#define NFP_NET_CFG_CTRL_RXCSUM (0x1 << 4) /* Enable RX Checksum */ +#define NFP_NET_CFG_CTRL_TXCSUM (0x1 << 5) /* Enable TX Checksum */ +#define NFP_NET_CFG_CTRL_RXVLAN (0x1 << 6) /* Enable VLAN strip */ +#define NFP_NET_CFG_CTRL_TXVLAN (0x1 << 7) /* Enable VLAN insert */ +#define NFP_NET_CFG_CTRL_SCATTER (0x1 << 8) /* Scatter DMA */ +#define NFP_NET_CFG_CTRL_GATHER (0x1 << 9) /* Gather DMA */ +#define NFP_NET_CFG_CTRL_LSO (0x1 << 10) /* LSO/TSO (version 1) */ #define NFP_NET_CFG_CTRL_CTAG_FILTER (0x1 << 11) /* VLAN CTAG filtering */ -#define NFP_NET_CFG_CTRL_RINGCFG (0x1 << 16) /* Ring runtime changes */ +#define NFP_NET_CFG_CTRL_RINGCFG (0x1 << 16) /* Ring runtime changes */ #define NFP_NET_CFG_CTRL_RSS (0x1 << 17) /* RSS (version 1) */ -#define NFP_NET_CFG_CTRL_IRQMOD (0x1 << 18) /* Interrupt moderation */ -#define NFP_NET_CFG_CTRL_RINGPRIO (0x1 << 19) /* Ring priorities */ -#define NFP_NET_CFG_CTRL_MSIXAUTO (0x1 << 20) /* MSI-X auto-masking */ -#define NFP_NET_CFG_CTRL_TXRWB (0x1 << 21) /* Write-back of TX ring*/ -#define NFP_NET_CFG_CTRL_L2SWITCH (0x1 << 22) /* L2 Switch */ +#define NFP_NET_CFG_CTRL_IRQMOD (0x1 << 18) /* Interrupt moderation */ +#define NFP_NET_CFG_CTRL_RINGPRIO (0x1 << 19) /* Ring priorities */ +#define NFP_NET_CFG_CTRL_MSIXAUTO (0x1 << 20) /* MSI-X auto-masking */ +#define NFP_NET_CFG_CTRL_TXRWB (0x1 << 21) /* Write-back of TX ring*/ +#define NFP_NET_CFG_CTRL_L2SWITCH (0x1 << 22) /* L2 Switch */ #define NFP_NET_CFG_CTRL_L2SWITCH_LOCAL (0x1 << 23) /* Switch to local */ #define NFP_NET_CFG_CTRL_VXLAN (0x1 << 24) /* VXLAN tunnel support */ #define NFP_NET_CFG_CTRL_NVGRE (0x1 << 25) /* NVGRE tunnel support */ @@ -152,35 +152,35 @@ #define NFP_NET_CFG_CTRL_CHAIN_META (NFP_NET_CFG_CTRL_RSS2 | \ NFP_NET_CFG_CTRL_CSUM_COMPLETE) -#define NFP_NET_CFG_UPDATE 0x0004 -#define NFP_NET_CFG_UPDATE_GEN (0x1 << 0) /* General update */ -#define NFP_NET_CFG_UPDATE_RING (0x1 << 1) /* Ring config change */ -#define NFP_NET_CFG_UPDATE_RSS (0x1 << 2) /* RSS config change */ -#define NFP_NET_CFG_UPDATE_TXRPRIO (0x1 << 3) /* TX Ring prio change */ -#define NFP_NET_CFG_UPDATE_RXRPRIO (0x1 << 4) /* RX Ring prio change */ -#define NFP_NET_CFG_UPDATE_MSIX (0x1 << 5) /* MSI-X change */ -#define NFP_NET_CFG_UPDATE_L2SWITCH (0x1 << 6) /* Switch changes */ -#define NFP_NET_CFG_UPDATE_RESET (0x1 << 7) /* Update due to FLR */ -#define NFP_NET_CFG_UPDATE_IRQMOD (0x1 << 8) /* IRQ mod change */ +#define NFP_NET_CFG_UPDATE 0x0004 +#define NFP_NET_CFG_UPDATE_GEN (0x1 << 0) /* General update */ +#define NFP_NET_CFG_UPDATE_RING (0x1 << 1) /* Ring config change */ +#define NFP_NET_CFG_UPDATE_RSS (0x1 << 2) /* RSS config change */ +#define NFP_NET_CFG_UPDATE_TXRPRIO (0x1 << 3) /* TX Ring prio change */ +#define NFP_NET_CFG_UPDATE_RXRPRIO (0x1 << 4) /* RX Ring prio change */ +#define NFP_NET_CFG_UPDATE_MSIX (0x1 << 5) /* MSI-X change */ +#define NFP_NET_CFG_UPDATE_L2SWITCH (0x1 << 6) /* Switch changes */ +#define NFP_NET_CFG_UPDATE_RESET (0x1 << 7) /* Update due to FLR */ +#define NFP_NET_CFG_UPDATE_IRQMOD (0x1 << 8) /* IRQ mod change */ #define NFP_NET_CFG_UPDATE_VXLAN (0x1 << 9) /* VXLAN port change */ #define NFP_NET_CFG_UPDATE_BPF (0x1 << 10) /* BPF program load */ #define NFP_NET_CFG_UPDATE_MACADDR (0x1 << 11) /* MAC address change */ #define NFP_NET_CFG_UPDATE_MBOX (0x1 << 12) /* Mailbox update */ #define NFP_NET_CFG_UPDATE_VF (0x1 << 13) /* VF settings change */ -#define NFP_NET_CFG_UPDATE_ERR (0x1 << 31) /* A error occurred */ -#define NFP_NET_CFG_TXRS_ENABLE 0x0008 -#define NFP_NET_CFG_RXRS_ENABLE 0x0010 -#define NFP_NET_CFG_MTU 0x0018 -#define NFP_NET_CFG_FLBUFSZ 0x001c -#define NFP_NET_CFG_EXN 0x001f -#define NFP_NET_CFG_LSC 0x0020 -#define NFP_NET_CFG_MACADDR 0x0024 +#define NFP_NET_CFG_UPDATE_ERR (0x1 << 31) /* A error occurred */ +#define NFP_NET_CFG_TXRS_ENABLE 0x0008 +#define NFP_NET_CFG_RXRS_ENABLE 0x0010 +#define NFP_NET_CFG_MTU 0x0018 +#define NFP_NET_CFG_FLBUFSZ 0x001c +#define NFP_NET_CFG_EXN 0x001f +#define NFP_NET_CFG_LSC 0x0020 +#define NFP_NET_CFG_MACADDR 0x0024 /** * Read-only words (0x0030 - 0x0050): * %NFP_NET_CFG_VERSION: Firmware version number - * %NFP_NET_CFG_STS: Status - * %NFP_NET_CFG_CAP: Capabilities (same bits as %NFP_NET_CFG_CTRL) + * %NFP_NET_CFG_STS: Status + * %NFP_NET_CFG_CAP: Capabilities (same bits as %NFP_NET_CFG_CTRL) * %NFP_NET_CFG_MAX_TXRINGS: Maximum number of TX rings * %NFP_NET_CFG_MAX_RXRINGS: Maximum number of RX rings * %NFP_NET_CFG_MAX_MTU: Maximum support MTU @@ -190,37 +190,37 @@ * TODO: * - define more STS bits */ -#define NFP_NET_CFG_VERSION 0x0030 +#define NFP_NET_CFG_VERSION 0x0030 #define NFP_NET_CFG_VERSION_RESERVED_MASK (0xff << 24) #define NFP_NET_CFG_VERSION_CLASS_MASK (0xff << 16) -#define NFP_NET_CFG_VERSION_CLASS(x) (((x) & 0xff) << 16) +#define NFP_NET_CFG_VERSION_CLASS(x) (((x) & 0xff) << 16) #define NFP_NET_CFG_VERSION_CLASS_GENERIC 0 #define NFP_NET_CFG_VERSION_MAJOR_MASK (0xff << 8) -#define NFP_NET_CFG_VERSION_MAJOR(x) (((x) & 0xff) << 8) +#define NFP_NET_CFG_VERSION_MAJOR(x) (((x) & 0xff) << 8) #define NFP_NET_CFG_VERSION_MINOR_MASK (0xff << 0) -#define NFP_NET_CFG_VERSION_MINOR(x) (((x) & 0xff) << 0) -#define NFP_NET_CFG_STS 0x0034 -#define NFP_NET_CFG_STS_LINK (0x1 << 0) /* Link up or down */ +#define NFP_NET_CFG_VERSION_MINOR(x) (((x) & 0xff) << 0) +#define NFP_NET_CFG_STS 0x0034 +#define NFP_NET_CFG_STS_LINK (0x1 << 0) /* Link up or down */ /* Link rate */ #define NFP_NET_CFG_STS_LINK_RATE_SHIFT 1 #define NFP_NET_CFG_STS_LINK_RATE_MASK 0xF -#define NFP_NET_CFG_STS_LINK_RATE \ +#define NFP_NET_CFG_STS_LINK_RATE \ (NFP_NET_CFG_STS_LINK_RATE_MASK << NFP_NET_CFG_STS_LINK_RATE_SHIFT) #define NFP_NET_CFG_STS_LINK_RATE_UNSUPPORTED 0 -#define NFP_NET_CFG_STS_LINK_RATE_UNKNOWN 1 -#define NFP_NET_CFG_STS_LINK_RATE_1G 2 -#define NFP_NET_CFG_STS_LINK_RATE_10G 3 -#define NFP_NET_CFG_STS_LINK_RATE_25G 4 -#define NFP_NET_CFG_STS_LINK_RATE_40G 5 -#define NFP_NET_CFG_STS_LINK_RATE_50G 6 -#define NFP_NET_CFG_STS_LINK_RATE_100G 7 -#define NFP_NET_CFG_CAP 0x0038 -#define NFP_NET_CFG_MAX_TXRINGS 0x003c -#define NFP_NET_CFG_MAX_RXRINGS 0x0040 -#define NFP_NET_CFG_MAX_MTU 0x0044 +#define NFP_NET_CFG_STS_LINK_RATE_UNKNOWN 1 +#define NFP_NET_CFG_STS_LINK_RATE_1G 2 +#define NFP_NET_CFG_STS_LINK_RATE_10G 3 +#define NFP_NET_CFG_STS_LINK_RATE_25G 4 +#define NFP_NET_CFG_STS_LINK_RATE_40G 5 +#define NFP_NET_CFG_STS_LINK_RATE_50G 6 +#define NFP_NET_CFG_STS_LINK_RATE_100G 7 +#define NFP_NET_CFG_CAP 0x0038 +#define NFP_NET_CFG_MAX_TXRINGS 0x003c +#define NFP_NET_CFG_MAX_RXRINGS 0x0040 +#define NFP_NET_CFG_MAX_MTU 0x0044 /* Next two words are being used by VFs for solving THB350 issue */ -#define NFP_NET_CFG_START_TXQ 0x0048 -#define NFP_NET_CFG_START_RXQ 0x004c +#define NFP_NET_CFG_START_TXQ 0x0048 +#define NFP_NET_CFG_START_RXQ 0x004c /** * Prepend configuration @@ -280,8 +280,8 @@ /** * 40B reserved for future use (0x0098 - 0x00c0) */ -#define NFP_NET_CFG_RESERVED 0x0098 -#define NFP_NET_CFG_RESERVED_SZ 0x0028 +#define NFP_NET_CFG_RESERVED 0x0098 +#define NFP_NET_CFG_RESERVED_SZ 0x0028 /** * RSS configuration (0x0100 - 0x01ac): @@ -290,26 +290,26 @@ * %NFP_NET_CFG_RSS_KEY: RSS "secret" key * %NFP_NET_CFG_RSS_ITBL: RSS indirection table */ -#define NFP_NET_CFG_RSS_BASE 0x0100 -#define NFP_NET_CFG_RSS_CTRL NFP_NET_CFG_RSS_BASE -#define NFP_NET_CFG_RSS_MASK (0x7f) -#define NFP_NET_CFG_RSS_MASK_of(_x) ((_x) & 0x7f) -#define NFP_NET_CFG_RSS_IPV4 (1 << 8) /* RSS for IPv4 */ -#define NFP_NET_CFG_RSS_IPV6 (1 << 9) /* RSS for IPv6 */ -#define NFP_NET_CFG_RSS_IPV4_TCP (1 << 10) /* RSS for IPv4/TCP */ -#define NFP_NET_CFG_RSS_IPV4_UDP (1 << 11) /* RSS for IPv4/UDP */ -#define NFP_NET_CFG_RSS_IPV6_TCP (1 << 12) /* RSS for IPv6/TCP */ -#define NFP_NET_CFG_RSS_IPV6_UDP (1 << 13) /* RSS for IPv6/UDP */ +#define NFP_NET_CFG_RSS_BASE 0x0100 +#define NFP_NET_CFG_RSS_CTRL NFP_NET_CFG_RSS_BASE +#define NFP_NET_CFG_RSS_MASK (0x7f) +#define NFP_NET_CFG_RSS_MASK_of(_x) ((_x) & 0x7f) +#define NFP_NET_CFG_RSS_IPV4 (1 << 8) /* RSS for IPv4 */ +#define NFP_NET_CFG_RSS_IPV6 (1 << 9) /* RSS for IPv6 */ +#define NFP_NET_CFG_RSS_IPV4_TCP (1 << 10) /* RSS for IPv4/TCP */ +#define NFP_NET_CFG_RSS_IPV4_UDP (1 << 11) /* RSS for IPv4/UDP */ +#define NFP_NET_CFG_RSS_IPV6_TCP (1 << 12) /* RSS for IPv6/TCP */ +#define NFP_NET_CFG_RSS_IPV6_UDP (1 << 13) /* RSS for IPv6/UDP */ #define NFP_NET_CFG_RSS_HFUNC 0xff000000 -#define NFP_NET_CFG_RSS_TOEPLITZ (1 << 24) /* Use Toeplitz hash */ +#define NFP_NET_CFG_RSS_TOEPLITZ (1 << 24) /* Use Toeplitz hash */ #define NFP_NET_CFG_RSS_XOR (1 << 25) /* Use XOR as hash */ #define NFP_NET_CFG_RSS_CRC32 (1 << 26) /* Use CRC32 as hash */ #define NFP_NET_CFG_RSS_HFUNCS 3 -#define NFP_NET_CFG_RSS_KEY (NFP_NET_CFG_RSS_BASE + 0x4) -#define NFP_NET_CFG_RSS_KEY_SZ 0x28 -#define NFP_NET_CFG_RSS_ITBL (NFP_NET_CFG_RSS_BASE + 0x4 + \ +#define NFP_NET_CFG_RSS_KEY (NFP_NET_CFG_RSS_BASE + 0x4) +#define NFP_NET_CFG_RSS_KEY_SZ 0x28 +#define NFP_NET_CFG_RSS_ITBL (NFP_NET_CFG_RSS_BASE + 0x4 + \ NFP_NET_CFG_RSS_KEY_SZ) -#define NFP_NET_CFG_RSS_ITBL_SZ 0x80 +#define NFP_NET_CFG_RSS_ITBL_SZ 0x80 /** * TX ring configuration (0x200 - 0x800) @@ -321,13 +321,13 @@ * %NFP_NET_CFG_TXR_PRIO: Per TX ring priority (1B entries) * %NFP_NET_CFG_TXR_IRQ_MOD: Per TX ring interrupt moderation packet */ -#define NFP_NET_CFG_TXR_BASE 0x0200 -#define NFP_NET_CFG_TXR_ADDR(_x) (NFP_NET_CFG_TXR_BASE + ((_x) * 0x8)) -#define NFP_NET_CFG_TXR_WB_ADDR(_x) (NFP_NET_CFG_TXR_BASE + 0x200 + \ +#define NFP_NET_CFG_TXR_BASE 0x0200 +#define NFP_NET_CFG_TXR_ADDR(_x) (NFP_NET_CFG_TXR_BASE + ((_x) * 0x8)) +#define NFP_NET_CFG_TXR_WB_ADDR(_x) (NFP_NET_CFG_TXR_BASE + 0x200 + \ ((_x) * 0x8)) -#define NFP_NET_CFG_TXR_SZ(_x) (NFP_NET_CFG_TXR_BASE + 0x400 + (_x)) -#define NFP_NET_CFG_TXR_VEC(_x) (NFP_NET_CFG_TXR_BASE + 0x440 + (_x)) -#define NFP_NET_CFG_TXR_PRIO(_x) (NFP_NET_CFG_TXR_BASE + 0x480 + (_x)) +#define NFP_NET_CFG_TXR_SZ(_x) (NFP_NET_CFG_TXR_BASE + 0x400 + (_x)) +#define NFP_NET_CFG_TXR_VEC(_x) (NFP_NET_CFG_TXR_BASE + 0x440 + (_x)) +#define NFP_NET_CFG_TXR_PRIO(_x) (NFP_NET_CFG_TXR_BASE + 0x480 + (_x)) #define NFP_NET_CFG_TXR_IRQ_MOD(_x) (NFP_NET_CFG_TXR_BASE + 0x500 + \ ((_x) * 0x4)) @@ -340,11 +340,11 @@ * %NFP_NET_CFG_RXR_PRIO: Per RX ring priority (1B entries) * %NFP_NET_CFG_RXR_IRQ_MOD: Per RX ring interrupt moderation (4B entries) */ -#define NFP_NET_CFG_RXR_BASE 0x0800 -#define NFP_NET_CFG_RXR_ADDR(_x) (NFP_NET_CFG_RXR_BASE + ((_x) * 0x8)) -#define NFP_NET_CFG_RXR_SZ(_x) (NFP_NET_CFG_RXR_BASE + 0x200 + (_x)) -#define NFP_NET_CFG_RXR_VEC(_x) (NFP_NET_CFG_RXR_BASE + 0x240 + (_x)) -#define NFP_NET_CFG_RXR_PRIO(_x) (NFP_NET_CFG_RXR_BASE + 0x280 + (_x)) +#define NFP_NET_CFG_RXR_BASE 0x0800 +#define NFP_NET_CFG_RXR_ADDR(_x) (NFP_NET_CFG_RXR_BASE + ((_x) * 0x8)) +#define NFP_NET_CFG_RXR_SZ(_x) (NFP_NET_CFG_RXR_BASE + 0x200 + (_x)) +#define NFP_NET_CFG_RXR_VEC(_x) (NFP_NET_CFG_RXR_BASE + 0x240 + (_x)) +#define NFP_NET_CFG_RXR_PRIO(_x) (NFP_NET_CFG_RXR_BASE + 0x280 + (_x)) #define NFP_NET_CFG_RXR_IRQ_MOD(_x) (NFP_NET_CFG_RXR_BASE + 0x300 + \ ((_x) * 0x4)) @@ -358,36 +358,36 @@ * the MSI-X entry and the host driver must clear the register to * re-enable the interrupt. */ -#define NFP_NET_CFG_ICR_BASE 0x0c00 -#define NFP_NET_CFG_ICR(_x) (NFP_NET_CFG_ICR_BASE + (_x)) -#define NFP_NET_CFG_ICR_UNMASKED 0x0 -#define NFP_NET_CFG_ICR_RXTX 0x1 -#define NFP_NET_CFG_ICR_LSC 0x2 +#define NFP_NET_CFG_ICR_BASE 0x0c00 +#define NFP_NET_CFG_ICR(_x) (NFP_NET_CFG_ICR_BASE + (_x)) +#define NFP_NET_CFG_ICR_UNMASKED 0x0 +#define NFP_NET_CFG_ICR_RXTX 0x1 +#define NFP_NET_CFG_ICR_LSC 0x2 /** * General device stats (0x0d00 - 0x0d90) * all counters are 64bit. */ -#define NFP_NET_CFG_STATS_BASE 0x0d00 -#define NFP_NET_CFG_STATS_RX_DISCARDS (NFP_NET_CFG_STATS_BASE + 0x00) -#define NFP_NET_CFG_STATS_RX_ERRORS (NFP_NET_CFG_STATS_BASE + 0x08) -#define NFP_NET_CFG_STATS_RX_OCTETS (NFP_NET_CFG_STATS_BASE + 0x10) -#define NFP_NET_CFG_STATS_RX_UC_OCTETS (NFP_NET_CFG_STATS_BASE + 0x18) -#define NFP_NET_CFG_STATS_RX_MC_OCTETS (NFP_NET_CFG_STATS_BASE + 0x20) -#define NFP_NET_CFG_STATS_RX_BC_OCTETS (NFP_NET_CFG_STATS_BASE + 0x28) -#define NFP_NET_CFG_STATS_RX_FRAMES (NFP_NET_CFG_STATS_BASE + 0x30) -#define NFP_NET_CFG_STATS_RX_MC_FRAMES (NFP_NET_CFG_STATS_BASE + 0x38) -#define NFP_NET_CFG_STATS_RX_BC_FRAMES (NFP_NET_CFG_STATS_BASE + 0x40) - -#define NFP_NET_CFG_STATS_TX_DISCARDS (NFP_NET_CFG_STATS_BASE + 0x48) -#define NFP_NET_CFG_STATS_TX_ERRORS (NFP_NET_CFG_STATS_BASE + 0x50) -#define NFP_NET_CFG_STATS_TX_OCTETS (NFP_NET_CFG_STATS_BASE + 0x58) -#define NFP_NET_CFG_STATS_TX_UC_OCTETS (NFP_NET_CFG_STATS_BASE + 0x60) -#define NFP_NET_CFG_STATS_TX_MC_OCTETS (NFP_NET_CFG_STATS_BASE + 0x68) -#define NFP_NET_CFG_STATS_TX_BC_OCTETS (NFP_NET_CFG_STATS_BASE + 0x70) -#define NFP_NET_CFG_STATS_TX_FRAMES (NFP_NET_CFG_STATS_BASE + 0x78) -#define NFP_NET_CFG_STATS_TX_MC_FRAMES (NFP_NET_CFG_STATS_BASE + 0x80) -#define NFP_NET_CFG_STATS_TX_BC_FRAMES (NFP_NET_CFG_STATS_BASE + 0x88) +#define NFP_NET_CFG_STATS_BASE 0x0d00 +#define NFP_NET_CFG_STATS_RX_DISCARDS (NFP_NET_CFG_STATS_BASE + 0x00) +#define NFP_NET_CFG_STATS_RX_ERRORS (NFP_NET_CFG_STATS_BASE + 0x08) +#define NFP_NET_CFG_STATS_RX_OCTETS (NFP_NET_CFG_STATS_BASE + 0x10) +#define NFP_NET_CFG_STATS_RX_UC_OCTETS (NFP_NET_CFG_STATS_BASE + 0x18) +#define NFP_NET_CFG_STATS_RX_MC_OCTETS (NFP_NET_CFG_STATS_BASE + 0x20) +#define NFP_NET_CFG_STATS_RX_BC_OCTETS (NFP_NET_CFG_STATS_BASE + 0x28) +#define NFP_NET_CFG_STATS_RX_FRAMES (NFP_NET_CFG_STATS_BASE + 0x30) +#define NFP_NET_CFG_STATS_RX_MC_FRAMES (NFP_NET_CFG_STATS_BASE + 0x38) +#define NFP_NET_CFG_STATS_RX_BC_FRAMES (NFP_NET_CFG_STATS_BASE + 0x40) + +#define NFP_NET_CFG_STATS_TX_DISCARDS (NFP_NET_CFG_STATS_BASE + 0x48) +#define NFP_NET_CFG_STATS_TX_ERRORS (NFP_NET_CFG_STATS_BASE + 0x50) +#define NFP_NET_CFG_STATS_TX_OCTETS (NFP_NET_CFG_STATS_BASE + 0x58) +#define NFP_NET_CFG_STATS_TX_UC_OCTETS (NFP_NET_CFG_STATS_BASE + 0x60) +#define NFP_NET_CFG_STATS_TX_MC_OCTETS (NFP_NET_CFG_STATS_BASE + 0x68) +#define NFP_NET_CFG_STATS_TX_BC_OCTETS (NFP_NET_CFG_STATS_BASE + 0x70) +#define NFP_NET_CFG_STATS_TX_FRAMES (NFP_NET_CFG_STATS_BASE + 0x78) +#define NFP_NET_CFG_STATS_TX_MC_FRAMES (NFP_NET_CFG_STATS_BASE + 0x80) +#define NFP_NET_CFG_STATS_TX_BC_FRAMES (NFP_NET_CFG_STATS_BASE + 0x88) #define NFP_NET_CFG_STATS_APP0_FRAMES (NFP_NET_CFG_STATS_BASE + 0x90) #define NFP_NET_CFG_STATS_APP0_BYTES (NFP_NET_CFG_STATS_BASE + 0x98) @@ -404,11 +404,11 @@ * %NFP_NET_CFG_TXR_STATS: TX ring statistics (Packet and Byte count) * %NFP_NET_CFG_RXR_STATS: RX ring statistics (Packet and Byte count) */ -#define NFP_NET_CFG_TXR_STATS_BASE 0x1000 -#define NFP_NET_CFG_TXR_STATS(_x) (NFP_NET_CFG_TXR_STATS_BASE + \ +#define NFP_NET_CFG_TXR_STATS_BASE 0x1000 +#define NFP_NET_CFG_TXR_STATS(_x) (NFP_NET_CFG_TXR_STATS_BASE + \ ((_x) * 0x10)) -#define NFP_NET_CFG_RXR_STATS_BASE 0x1400 -#define NFP_NET_CFG_RXR_STATS(_x) (NFP_NET_CFG_RXR_STATS_BASE + \ +#define NFP_NET_CFG_RXR_STATS_BASE 0x1400 +#define NFP_NET_CFG_RXR_STATS(_x) (NFP_NET_CFG_RXR_STATS_BASE + \ ((_x) * 0x10)) /** @@ -444,7 +444,7 @@ * %NFP_NET_CFG_TLV_TYPE: Offset of type within the TLV * %NFP_NET_CFG_TLV_TYPE_REQUIRED: Driver must be able to parse the TLV * %NFP_NET_CFG_TLV_LENGTH: Offset of length within the TLV - * %NFP_NET_CFG_TLV_LENGTH_INC: TLV length increments + * %NFP_NET_CFG_TLV_LENGTH_INC: TLV length increments * %NFP_NET_CFG_TLV_VALUE: Offset of value with the TLV * * List of simple TLV structures, first one starts at %NFP_NET_CFG_TLV_BASE. @@ -457,12 +457,12 @@ * Note that the 4 byte TLV header is not counted in %NFP_NET_CFG_TLV_LENGTH. */ #define NFP_NET_CFG_TLV_TYPE 0x00 -#define NFP_NET_CFG_TLV_TYPE_REQUIRED 0x8000 +#define NFP_NET_CFG_TLV_TYPE_REQUIRED 0x8000 #define NFP_NET_CFG_TLV_LENGTH 0x02 #define NFP_NET_CFG_TLV_LENGTH_INC 4 #define NFP_NET_CFG_TLV_VALUE 0x04 -#define NFP_NET_CFG_TLV_HEADER_REQUIRED 0x80000000 +#define NFP_NET_CFG_TLV_HEADER_REQUIRED 0x80000000 #define NFP_NET_CFG_TLV_HEADER_TYPE 0x7fff0000 #define NFP_NET_CFG_TLV_HEADER_LENGTH 0x0000ffff diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/Makefile b/drivers/net/ethernet/netronome/nfp/nfpcore/Makefile new file mode 100644 index 000000000000..805fa28f391a --- /dev/null +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +# kbuild requires Makefile in a directory to build individual objects diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000/Makefile b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000/Makefile new file mode 100644 index 000000000000..805fa28f391a --- /dev/null +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +# kbuild requires Makefile in a directory to build individual objects diff --git a/drivers/net/ethernet/netronome/nfp/nic/Makefile b/drivers/net/ethernet/netronome/nfp/nic/Makefile new file mode 100644 index 000000000000..805fa28f391a --- /dev/null +++ b/drivers/net/ethernet/netronome/nfp/nic/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +# kbuild requires Makefile in a directory to build individual objects diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c index 7e7704daf5f1..c4949183eef3 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c @@ -43,12 +43,6 @@ /* Local Definitions and Declarations */ -struct rmnet_walk_data { - struct net_device *real_dev; - struct list_head *head; - struct rmnet_port *port; -}; - static int rmnet_is_real_dev_registered(const struct net_device *real_dev) { return rcu_access_pointer(real_dev->rx_handler) == rmnet_rx_handler; @@ -112,17 +106,14 @@ static int rmnet_register_real_device(struct net_device *real_dev) static void rmnet_unregister_bridge(struct net_device *dev, struct rmnet_port *port) { - struct net_device *rmnet_dev, *bridge_dev; struct rmnet_port *bridge_port; + struct net_device *bridge_dev; if (port->rmnet_mode != RMNET_EPMODE_BRIDGE) return; /* bridge slave handling */ if (!port->nr_rmnet_devs) { - rmnet_dev = netdev_master_upper_dev_get_rcu(dev); - netdev_upper_dev_unlink(dev, rmnet_dev); - bridge_dev = port->bridge_ep; bridge_port = rmnet_get_port_rtnl(bridge_dev); @@ -132,9 +123,6 @@ static void rmnet_unregister_bridge(struct net_device *dev, bridge_dev = port->bridge_ep; bridge_port = rmnet_get_port_rtnl(bridge_dev); - rmnet_dev = netdev_master_upper_dev_get_rcu(bridge_dev); - netdev_upper_dev_unlink(bridge_dev, rmnet_dev); - rmnet_unregister_real_device(bridge_dev, bridge_port); } } @@ -173,10 +161,6 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev, if (err) goto err1; - err = netdev_master_upper_dev_link(dev, real_dev, NULL, NULL, extack); - if (err) - goto err2; - port->rmnet_mode = mode; hlist_add_head_rcu(&ep->hlnode, &port->muxed_ep[mux_id]); @@ -193,8 +177,6 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev, return 0; -err2: - rmnet_vnd_dellink(mux_id, port, ep); err1: rmnet_unregister_real_device(real_dev, port); err0: @@ -204,14 +186,13 @@ err0: static void rmnet_dellink(struct net_device *dev, struct list_head *head) { + struct rmnet_priv *priv = netdev_priv(dev); struct net_device *real_dev; struct rmnet_endpoint *ep; struct rmnet_port *port; u8 mux_id; - rcu_read_lock(); - real_dev = netdev_master_upper_dev_get_rcu(dev); - rcu_read_unlock(); + real_dev = priv->real_dev; if (!real_dev || !rmnet_is_real_dev_registered(real_dev)) return; @@ -219,7 +200,6 @@ static void rmnet_dellink(struct net_device *dev, struct list_head *head) port = rmnet_get_port_rtnl(real_dev); mux_id = rmnet_vnd_get_mux(dev); - netdev_upper_dev_unlink(dev, real_dev); ep = rmnet_get_endpoint(port, mux_id); if (ep) { @@ -233,30 +213,13 @@ static void rmnet_dellink(struct net_device *dev, struct list_head *head) unregister_netdevice_queue(dev, head); } -static int rmnet_dev_walk_unreg(struct net_device *rmnet_dev, void *data) -{ - struct rmnet_walk_data *d = data; - struct rmnet_endpoint *ep; - u8 mux_id; - - mux_id = rmnet_vnd_get_mux(rmnet_dev); - ep = rmnet_get_endpoint(d->port, mux_id); - if (ep) { - hlist_del_init_rcu(&ep->hlnode); - rmnet_vnd_dellink(mux_id, d->port, ep); - kfree(ep); - } - netdev_upper_dev_unlink(rmnet_dev, d->real_dev); - unregister_netdevice_queue(rmnet_dev, d->head); - - return 0; -} - static void rmnet_force_unassociate_device(struct net_device *dev) { struct net_device *real_dev = dev; - struct rmnet_walk_data d; + struct hlist_node *tmp_ep; + struct rmnet_endpoint *ep; struct rmnet_port *port; + unsigned long bkt_ep; LIST_HEAD(list); if (!rmnet_is_real_dev_registered(real_dev)) @@ -264,16 +227,19 @@ static void rmnet_force_unassociate_device(struct net_device *dev) ASSERT_RTNL(); - d.real_dev = real_dev; - d.head = &list; - port = rmnet_get_port_rtnl(dev); - d.port = port; rcu_read_lock(); rmnet_unregister_bridge(dev, port); - netdev_walk_all_lower_dev_rcu(real_dev, rmnet_dev_walk_unreg, &d); + hash_for_each_safe(port->muxed_ep, bkt_ep, tmp_ep, ep, hlnode) { + unregister_netdevice_queue(ep->egress_dev, &list); + rmnet_vnd_dellink(ep->mux_id, port, ep); + + hlist_del_init_rcu(&ep->hlnode); + kfree(ep); + } + rcu_read_unlock(); unregister_netdevice_many(&list); @@ -422,11 +388,6 @@ int rmnet_add_bridge(struct net_device *rmnet_dev, if (err) return -EBUSY; - err = netdev_master_upper_dev_link(slave_dev, rmnet_dev, NULL, NULL, - extack); - if (err) - return -EINVAL; - slave_port = rmnet_get_port(slave_dev); slave_port->rmnet_mode = RMNET_EPMODE_BRIDGE; slave_port->bridge_ep = real_dev; @@ -449,7 +410,6 @@ int rmnet_del_bridge(struct net_device *rmnet_dev, port->rmnet_mode = RMNET_EPMODE_VND; port->bridge_ep = NULL; - netdev_upper_dev_unlink(slave_dev, rmnet_dev); slave_port = rmnet_get_port(slave_dev); rmnet_unregister_real_device(slave_dev, slave_port); diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c index 6bc328fb88e1..b0dbca070c00 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c @@ -38,6 +38,11 @@ static u8 rmnet_map_do_flow_control(struct sk_buff *skb, } ep = rmnet_get_endpoint(port, mux_id); + if (!ep) { + kfree_skb(skb); + return RX_HANDLER_CONSUMED; + } + vnd = ep->egress_dev; ip_family = cmd->flow_control.ip_family; diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c index 570a227acdd8..346d310914df 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c @@ -121,7 +121,7 @@ static void rmnet_get_stats64(struct net_device *dev, memset(&total_stats, 0, sizeof(struct rmnet_vnd_stats)); for_each_possible_cpu(cpu) { - pcpu_ptr = this_cpu_ptr(priv->pcpu_stats); + pcpu_ptr = per_cpu_ptr(priv->pcpu_stats, cpu); do { start = u64_stats_fetch_begin_irq(&pcpu_ptr->syncp); diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 0bf7d1759250..cc51286ee51f 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -736,9 +736,7 @@ struct ring_info { }; enum features { - RTL_FEATURE_WOL = (1 << 0), - RTL_FEATURE_MSI = (1 << 1), - RTL_FEATURE_GMII = (1 << 2), + RTL_FEATURE_GMII = (1 << 0), }; struct rtl8169_counters { @@ -1473,19 +1471,19 @@ static void rtl8168_driver_stop(struct rtl8169_private *tp) } } -static int r8168dp_check_dash(struct rtl8169_private *tp) +static bool r8168dp_check_dash(struct rtl8169_private *tp) { u16 reg = rtl8168_get_ocp_reg(tp); - return (ocp_read(tp, 0x0f, reg) & 0x00008000) ? 1 : 0; + return !!(ocp_read(tp, 0x0f, reg) & 0x00008000); } -static int r8168ep_check_dash(struct rtl8169_private *tp) +static bool r8168ep_check_dash(struct rtl8169_private *tp) { - return (ocp_read(tp, 0x0f, 0x128) & 0x00000001) ? 1 : 0; + return !!(ocp_read(tp, 0x0f, 0x128) & 0x00000001); } -static int r8168_check_dash(struct rtl8169_private *tp) +static bool r8168_check_dash(struct rtl8169_private *tp) { switch (tp->mac_version) { case RTL_GIGA_MAC_VER_27: @@ -1497,7 +1495,7 @@ static int r8168_check_dash(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_51: return r8168ep_check_dash(tp); default: - return 0; + return false; } } @@ -1859,10 +1857,6 @@ static int rtl8169_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) rtl_lock_work(tp); - if (wol->wolopts) - tp->features |= RTL_FEATURE_WOL; - else - tp->features &= ~RTL_FEATURE_WOL; if (pm_runtime_active(d)) __rtl8169_set_wol(tp, wol->wolopts); else @@ -3805,8 +3799,6 @@ static void rtl8168e_2_hw_phy_config(struct rtl8169_private *tp) rtl_writephy(tp, 0x1f, 0x0005); rtl_w0w1_phy(tp, 0x01, 0x0100, 0x0000); rtl_writephy(tp, 0x1f, 0x0000); - /* soft-reset phy */ - rtl_writephy(tp, MII_BMCR, BMCR_RESET | BMCR_ANENABLE | BMCR_ANRESTART); /* Broken BIOS workaround: feed GigaMAC registers with MAC address. */ rtl_rar_exgmac_set(tp, tp->dev->dev_addr); @@ -4989,15 +4981,8 @@ static void r8168_pll_power_down(struct rtl8169_private *tp) { void __iomem *ioaddr = tp->mmio_addr; - if ((tp->mac_version == RTL_GIGA_MAC_VER_27 || - tp->mac_version == RTL_GIGA_MAC_VER_28 || - tp->mac_version == RTL_GIGA_MAC_VER_31 || - tp->mac_version == RTL_GIGA_MAC_VER_49 || - tp->mac_version == RTL_GIGA_MAC_VER_50 || - tp->mac_version == RTL_GIGA_MAC_VER_51) && - r8168_check_dash(tp)) { + if (r8168_check_dash(tp)) return; - } if ((tp->mac_version == RTL_GIGA_MAC_VER_23 || tp->mac_version == RTL_GIGA_MAC_VER_24) && @@ -7861,7 +7846,7 @@ static int rtl8169_close(struct net_device *dev) cancel_work_sync(&tp->wk.work); - free_irq(pdev->irq, dev); + pci_free_irq(pdev, 0, dev); dma_free_coherent(&pdev->dev, R8169_RX_RING_BYTES, tp->RxDescArray, tp->RxPhyAddr); @@ -7917,9 +7902,8 @@ static int rtl_open(struct net_device *dev) rtl_request_firmware(tp); - retval = request_irq(pdev->irq, rtl8169_interrupt, - (tp->features & RTL_FEATURE_MSI) ? 0 : IRQF_SHARED, - dev->name, dev); + retval = pci_request_irq(pdev, 0, rtl8169_interrupt, NULL, dev, + dev->name); if (retval < 0) goto err_release_fw_2; @@ -8209,15 +8193,8 @@ static void rtl_remove_one(struct pci_dev *pdev) struct net_device *dev = pci_get_drvdata(pdev); struct rtl8169_private *tp = netdev_priv(dev); - if ((tp->mac_version == RTL_GIGA_MAC_VER_27 || - tp->mac_version == RTL_GIGA_MAC_VER_28 || - tp->mac_version == RTL_GIGA_MAC_VER_31 || - tp->mac_version == RTL_GIGA_MAC_VER_49 || - tp->mac_version == RTL_GIGA_MAC_VER_50 || - tp->mac_version == RTL_GIGA_MAC_VER_51) && - r8168_check_dash(tp)) { + if (r8168_check_dash(tp)) rtl8168_driver_stop(tp); - } netif_napi_del(&tp->napi); @@ -8274,7 +8251,7 @@ static const struct rtl_cfg_info { .region = 2, .align = 8, .event_slow = SYSErr | LinkChg | RxOverflow, - .features = RTL_FEATURE_GMII | RTL_FEATURE_MSI, + .features = RTL_FEATURE_GMII, .coalesce_info = rtl_coalesce_info_8168_8136, .default_ver = RTL_GIGA_MAC_VER_11, }, @@ -8284,32 +8261,26 @@ static const struct rtl_cfg_info { .align = 8, .event_slow = SYSErr | LinkChg | RxOverflow | RxFIFOOver | PCSTimeout, - .features = RTL_FEATURE_MSI, .coalesce_info = rtl_coalesce_info_8168_8136, .default_ver = RTL_GIGA_MAC_VER_13, } }; -/* Cfg9346_Unlock assumed. */ -static unsigned rtl_try_msi(struct rtl8169_private *tp, - const struct rtl_cfg_info *cfg) +static int rtl_alloc_irq(struct rtl8169_private *tp) { void __iomem *ioaddr = tp->mmio_addr; - unsigned msi = 0; - u8 cfg2; + unsigned int flags; - cfg2 = RTL_R8(Config2) & ~MSIEnable; - if (cfg->features & RTL_FEATURE_MSI) { - if (pci_enable_msi(tp->pci_dev)) { - netif_info(tp, hw, tp->dev, "no MSI. Back to INTx.\n"); - } else { - cfg2 |= MSIEnable; - msi = RTL_FEATURE_MSI; - } + if (tp->mac_version <= RTL_GIGA_MAC_VER_06) { + RTL_W8(Cfg9346, Cfg9346_Unlock); + RTL_W8(Config2, RTL_R8(Config2) & ~MSIEnable); + RTL_W8(Cfg9346, Cfg9346_Lock); + flags = PCI_IRQ_LEGACY; + } else { + flags = PCI_IRQ_ALL_TYPES; } - if (tp->mac_version <= RTL_GIGA_MAC_VER_06) - RTL_W8(Config2, cfg2); - return msi; + + return pci_alloc_irq_vectors(tp->pci_dev, 1, 1, flags); } DECLARE_RTL_COND(rtl_link_list_ready_cond) @@ -8518,41 +8489,14 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) chipset = tp->mac_version; tp->txd_version = rtl_chip_infos[chipset].txd_version; - RTL_W8(Cfg9346, Cfg9346_Unlock); - RTL_W8(Config1, RTL_R8(Config1) | PMEnable); - RTL_W8(Config5, RTL_R8(Config5) & (BWF | MWF | UWF | LanWake | PMEStatus)); - switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_34: - case RTL_GIGA_MAC_VER_35: - case RTL_GIGA_MAC_VER_36: - case RTL_GIGA_MAC_VER_37: - case RTL_GIGA_MAC_VER_38: - case RTL_GIGA_MAC_VER_40: - case RTL_GIGA_MAC_VER_41: - case RTL_GIGA_MAC_VER_42: - case RTL_GIGA_MAC_VER_43: - case RTL_GIGA_MAC_VER_44: - case RTL_GIGA_MAC_VER_45: - case RTL_GIGA_MAC_VER_46: - case RTL_GIGA_MAC_VER_47: - case RTL_GIGA_MAC_VER_48: - case RTL_GIGA_MAC_VER_49: - case RTL_GIGA_MAC_VER_50: - case RTL_GIGA_MAC_VER_51: - if (rtl_eri_read(tp, 0xdc, ERIAR_EXGMAC) & MagicPacket_v2) - tp->features |= RTL_FEATURE_WOL; - if ((RTL_R8(Config3) & LinkUp) != 0) - tp->features |= RTL_FEATURE_WOL; - break; - default: - if ((RTL_R8(Config3) & (LinkUp | MagicPacket)) != 0) - tp->features |= RTL_FEATURE_WOL; - break; + rc = rtl_alloc_irq(tp); + if (rc < 0) { + netif_err(tp, probe, dev, "Can't allocate interrupt\n"); + return rc; } - if ((RTL_R8(Config5) & (UWF | BWF | MWF)) != 0) - tp->features |= RTL_FEATURE_WOL; - tp->features |= rtl_try_msi(tp, cfg); - RTL_W8(Cfg9346, Cfg9346_Lock); + + /* override BIOS settings, use userspace tools to enable WOL */ + __rtl8169_set_wol(tp, 0); if (rtl_tbi_enabled(tp)) { tp->set_speed = rtl8169_set_speed_tbi; @@ -8676,15 +8620,8 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) rtl_chip_infos[chipset].jumbo_tx_csum ? "ok" : "ko"); } - if ((tp->mac_version == RTL_GIGA_MAC_VER_27 || - tp->mac_version == RTL_GIGA_MAC_VER_28 || - tp->mac_version == RTL_GIGA_MAC_VER_31 || - tp->mac_version == RTL_GIGA_MAC_VER_49 || - tp->mac_version == RTL_GIGA_MAC_VER_50 || - tp->mac_version == RTL_GIGA_MAC_VER_51) && - r8168_check_dash(tp)) { + if (r8168_check_dash(tp)) rtl8168_driver_start(tp); - } netif_carrier_off(dev); diff --git a/drivers/net/ethernet/renesas/ravb.h b/drivers/net/ethernet/renesas/ravb.h index 96a27b00c90e..b81f4faf7b10 100644 --- a/drivers/net/ethernet/renesas/ravb.h +++ b/drivers/net/ethernet/renesas/ravb.h @@ -1018,6 +1018,7 @@ struct ravb_private { u32 dirty_rx[NUM_RX_QUEUE]; /* Producer ring indices */ u32 cur_tx[NUM_TX_QUEUE]; u32 dirty_tx[NUM_TX_QUEUE]; + u32 rx_buf_sz; /* Based on MTU+slack. */ struct napi_struct napi[NUM_RX_QUEUE]; struct work_struct work; /* MII transceiver section. */ diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index c87f57ca4437..54a6265da7a0 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -238,7 +238,7 @@ static void ravb_ring_free(struct net_device *ndev, int q) le32_to_cpu(desc->dptr))) dma_unmap_single(ndev->dev.parent, le32_to_cpu(desc->dptr), - PKT_BUF_SZ, + priv->rx_buf_sz, DMA_FROM_DEVICE); } ring_size = sizeof(struct ravb_ex_rx_desc) * @@ -300,9 +300,9 @@ static void ravb_ring_format(struct net_device *ndev, int q) for (i = 0; i < priv->num_rx_ring[q]; i++) { /* RX descriptor */ rx_desc = &priv->rx_ring[q][i]; - rx_desc->ds_cc = cpu_to_le16(PKT_BUF_SZ); + rx_desc->ds_cc = cpu_to_le16(priv->rx_buf_sz); dma_addr = dma_map_single(ndev->dev.parent, priv->rx_skb[q][i]->data, - PKT_BUF_SZ, + priv->rx_buf_sz, DMA_FROM_DEVICE); /* We just set the data size to 0 for a failed mapping which * should prevent DMA from happening... @@ -346,6 +346,10 @@ static int ravb_ring_init(struct net_device *ndev, int q) int ring_size; int i; + /* +16 gets room from the status from the card. */ + priv->rx_buf_sz = (ndev->mtu <= 1492 ? PKT_BUF_SZ : ndev->mtu) + + ETH_HLEN + VLAN_HLEN; + /* Allocate RX and TX skb rings */ priv->rx_skb[q] = kcalloc(priv->num_rx_ring[q], sizeof(*priv->rx_skb[q]), GFP_KERNEL); @@ -355,7 +359,7 @@ static int ravb_ring_init(struct net_device *ndev, int q) goto error; for (i = 0; i < priv->num_rx_ring[q]; i++) { - skb = netdev_alloc_skb(ndev, PKT_BUF_SZ + RAVB_ALIGN - 1); + skb = netdev_alloc_skb(ndev, priv->rx_buf_sz + RAVB_ALIGN - 1); if (!skb) goto error; ravb_set_buffer_align(skb); @@ -586,7 +590,7 @@ static bool ravb_rx(struct net_device *ndev, int *quota, int q) skb = priv->rx_skb[q][entry]; priv->rx_skb[q][entry] = NULL; dma_unmap_single(ndev->dev.parent, le32_to_cpu(desc->dptr), - PKT_BUF_SZ, + priv->rx_buf_sz, DMA_FROM_DEVICE); get_ts &= (q == RAVB_NC) ? RAVB_RXTSTAMP_TYPE_V2_L2_EVENT : @@ -619,11 +623,12 @@ static bool ravb_rx(struct net_device *ndev, int *quota, int q) for (; priv->cur_rx[q] - priv->dirty_rx[q] > 0; priv->dirty_rx[q]++) { entry = priv->dirty_rx[q] % priv->num_rx_ring[q]; desc = &priv->rx_ring[q][entry]; - desc->ds_cc = cpu_to_le16(PKT_BUF_SZ); + desc->ds_cc = cpu_to_le16(priv->rx_buf_sz); if (!priv->rx_skb[q][entry]) { skb = netdev_alloc_skb(ndev, - PKT_BUF_SZ + RAVB_ALIGN - 1); + priv->rx_buf_sz + + RAVB_ALIGN - 1); if (!skb) break; /* Better luck next round. */ ravb_set_buffer_align(skb); @@ -1854,6 +1859,17 @@ static int ravb_do_ioctl(struct net_device *ndev, struct ifreq *req, int cmd) return phy_mii_ioctl(phydev, req, cmd); } +static int ravb_change_mtu(struct net_device *ndev, int new_mtu) +{ + if (netif_running(ndev)) + return -EBUSY; + + ndev->mtu = new_mtu; + netdev_update_features(ndev); + + return 0; +} + static void ravb_set_rx_csum(struct net_device *ndev, bool enable) { struct ravb_private *priv = netdev_priv(ndev); @@ -1895,6 +1911,7 @@ static const struct net_device_ops ravb_netdev_ops = { .ndo_set_rx_mode = ravb_set_rx_mode, .ndo_tx_timeout = ravb_tx_timeout, .ndo_do_ioctl = ravb_do_ioctl, + .ndo_change_mtu = ravb_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, .ndo_set_features = ravb_set_features, @@ -2117,6 +2134,9 @@ static int ravb_probe(struct platform_device *pdev) goto out_release; } + ndev->max_mtu = 2048 - (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN); + ndev->min_mtu = ETH_MIN_MTU; + /* Set function */ ndev->netdev_ops = &ravb_netdev_ops; ndev->ethtool_ops = &ravb_ethtool_ops; @@ -2255,9 +2275,6 @@ static int ravb_wol_setup(struct net_device *ndev) /* Enable MagicPacket */ ravb_modify(ndev, ECMR, ECMR_MPDE, ECMR_MPDE); - /* Increased clock usage so device won't be suspended */ - clk_enable(priv->clk); - return enable_irq_wake(priv->emac_irq); } @@ -2276,9 +2293,6 @@ static int ravb_wol_restore(struct net_device *ndev) if (ret < 0) return ret; - /* Restore clock usage count */ - clk_disable(priv->clk); - return disable_irq_wake(priv->emac_irq); } diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index a197e11f3a56..d3e1bc05ca9c 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -40,7 +40,6 @@ #include <linux/slab.h> #include <linux/ethtool.h> #include <linux/if_vlan.h> -#include <linux/clk.h> #include <linux/sh_eth.h> #include <linux/of_mdio.h> @@ -124,8 +123,8 @@ static const u16 sh_eth_offset_gigabit[SH_ETH_MAX_REGISTER_OFFSET] = { [TSU_FWSL0] = 0x0030, [TSU_FWSL1] = 0x0034, [TSU_FWSLC] = 0x0038, - [TSU_QTAG0] = 0x0040, - [TSU_QTAG1] = 0x0044, + [TSU_QTAGM0] = 0x0040, + [TSU_QTAGM1] = 0x0044, [TSU_FWSR] = 0x0050, [TSU_FWINMK] = 0x0054, [TSU_ADQT0] = 0x0048, @@ -753,6 +752,7 @@ static struct sh_eth_cpu_data sh7757_data = { .rpadir = 1, .rpadir_value = 2 << 16, .rtrate = 1, + .dual_port = 1, }; #define SH_GIGA_ETH_BASE 0xfee00000UL @@ -831,6 +831,7 @@ static struct sh_eth_cpu_data sh7757_data_giga = { .no_trimd = 1, .no_ade = 1, .tsu = 1, + .dual_port = 1, }; /* SH7734 */ @@ -901,6 +902,7 @@ static struct sh_eth_cpu_data sh7763_data = { .tsu = 1, .irq_flags = IRQF_SHARED, .magic = 1, + .dual_port = 1, }; static struct sh_eth_cpu_data sh7619_data = { @@ -933,6 +935,7 @@ static struct sh_eth_cpu_data sh771x_data = { EESIPR_RRFIP | EESIPR_RTLFIP | EESIPR_RTSFIP | EESIPR_PREIP | EESIPR_CERFIP, .tsu = 1, + .dual_port = 1, }; static void sh_eth_set_default_cpu_data(struct sh_eth_cpu_data *cd) @@ -962,20 +965,16 @@ static void sh_eth_set_default_cpu_data(struct sh_eth_cpu_data *cd) static int sh_eth_check_reset(struct net_device *ndev) { - int ret = 0; - int cnt = 100; + int cnt; - while (cnt > 0) { + for (cnt = 100; cnt > 0; cnt--) { if (!(sh_eth_read(ndev, EDMR) & EDMR_SRST_GETHER)) - break; + return 0; mdelay(1); - cnt--; } - if (cnt <= 0) { - netdev_err(ndev, "Device reset failed\n"); - ret = -ETIMEDOUT; - } - return ret; + + netdev_err(ndev, "Device reset failed\n"); + return -ETIMEDOUT; } static int sh_eth_reset(struct net_device *ndev) @@ -2102,8 +2101,6 @@ static size_t __sh_eth_get_regs(struct net_device *ndev, u32 *buf) add_tsu_reg(TSU_FWSL0); add_tsu_reg(TSU_FWSL1); add_tsu_reg(TSU_FWSLC); - add_tsu_reg(TSU_QTAG0); - add_tsu_reg(TSU_QTAG1); add_tsu_reg(TSU_QTAGM0); add_tsu_reg(TSU_QTAGM1); add_tsu_reg(TSU_FWSR); @@ -2304,7 +2301,7 @@ static void sh_eth_get_wol(struct net_device *ndev, struct ethtool_wolinfo *wol) wol->supported = 0; wol->wolopts = 0; - if (mdp->cd->magic && mdp->clk) { + if (mdp->cd->magic) { wol->supported = WAKE_MAGIC; wol->wolopts = mdp->wol_enabled ? WAKE_MAGIC : 0; } @@ -2314,7 +2311,7 @@ static int sh_eth_set_wol(struct net_device *ndev, struct ethtool_wolinfo *wol) { struct sh_eth_private *mdp = netdev_priv(ndev); - if (!mdp->cd->magic || !mdp->clk || wol->wolopts & ~WAKE_MAGIC) + if (!mdp->cd->magic || wol->wolopts & ~WAKE_MAGIC) return -EOPNOTSUPP; mdp->wol_enabled = !!(wol->wolopts & WAKE_MAGIC); @@ -2922,7 +2919,7 @@ static int sh_eth_vlan_rx_kill_vid(struct net_device *ndev, /* SuperH's TSU register init function */ static void sh_eth_tsu_init(struct sh_eth_private *mdp) { - if (sh_eth_is_rz_fast_ether(mdp)) { + if (!mdp->cd->dual_port) { sh_eth_tsu_write(mdp, 0, TSU_TEN); /* Disable all CAM entry */ sh_eth_tsu_write(mdp, TSU_FWSLC_POSTENU | TSU_FWSLC_POSTENL, TSU_FWSLC); /* Enable POST registers */ @@ -2939,13 +2936,8 @@ static void sh_eth_tsu_init(struct sh_eth_private *mdp) sh_eth_tsu_write(mdp, 0, TSU_FWSL0); sh_eth_tsu_write(mdp, 0, TSU_FWSL1); sh_eth_tsu_write(mdp, TSU_FWSLC_POSTENU | TSU_FWSLC_POSTENL, TSU_FWSLC); - if (sh_eth_is_gether(mdp)) { - sh_eth_tsu_write(mdp, 0, TSU_QTAG0); /* Disable QTAG(0->1) */ - sh_eth_tsu_write(mdp, 0, TSU_QTAG1); /* Disable QTAG(1->0) */ - } else { - sh_eth_tsu_write(mdp, 0, TSU_QTAGM0); /* Disable QTAG(0->1) */ - sh_eth_tsu_write(mdp, 0, TSU_QTAGM1); /* Disable QTAG(1->0) */ - } + sh_eth_tsu_write(mdp, 0, TSU_QTAGM0); /* Disable QTAG(0->1) */ + sh_eth_tsu_write(mdp, 0, TSU_QTAGM1); /* Disable QTAG(1->0) */ sh_eth_tsu_write(mdp, 0, TSU_FWSR); /* all interrupt status clear */ sh_eth_tsu_write(mdp, 0, TSU_FWINMK); /* Disable all interrupt */ sh_eth_tsu_write(mdp, 0, TSU_TEN); /* Disable all CAM entry */ @@ -3153,11 +3145,6 @@ static int sh_eth_drv_probe(struct platform_device *pdev) goto out_release; } - /* Get clock, if not found that's OK but Wake-On-Lan is unavailable */ - mdp->clk = devm_clk_get(&pdev->dev, NULL); - if (IS_ERR(mdp->clk)) - mdp->clk = NULL; - ndev->base_addr = res->start; spin_lock_init(&mdp->lock); @@ -3278,7 +3265,7 @@ static int sh_eth_drv_probe(struct platform_device *pdev) if (ret) goto out_napi_del; - if (mdp->cd->magic && mdp->clk) + if (mdp->cd->magic) device_set_wakeup_capable(&pdev->dev, 1); /* print device information */ @@ -3331,9 +3318,6 @@ static int sh_eth_wol_setup(struct net_device *ndev) /* Enable MagicPacket */ sh_eth_modify(ndev, ECMR, ECMR_MPDE, ECMR_MPDE); - /* Increased clock usage so device won't be suspended */ - clk_enable(mdp->clk); - return enable_irq_wake(ndev->irq); } @@ -3359,9 +3343,6 @@ static int sh_eth_wol_restore(struct net_device *ndev) if (ret < 0) return ret; - /* Restore clock usage count */ - clk_disable(mdp->clk); - return disable_irq_wake(ndev->irq); } diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h index a6753ccba711..5bbaf9e56e92 100644 --- a/drivers/net/ethernet/renesas/sh_eth.h +++ b/drivers/net/ethernet/renesas/sh_eth.h @@ -118,8 +118,8 @@ enum { TSU_FWSL0, TSU_FWSL1, TSU_FWSLC, - TSU_QTAG0, - TSU_QTAG1, + TSU_QTAG0, /* Same as TSU_QTAGM0 */ + TSU_QTAG1, /* Same as TSU_QTAGM1 */ TSU_QTAGM0, TSU_QTAGM1, TSU_FWSR, @@ -509,6 +509,7 @@ struct sh_eth_cpu_data { unsigned rmiimode:1; /* EtherC has RMIIMODE register */ unsigned rtrate:1; /* EtherC has RTRATE register */ unsigned magic:1; /* EtherC has ECMR.MPDE and ECSR.MPD */ + unsigned dual_port:1; /* Dual EtherC/E-DMAC */ }; struct sh_eth_private { diff --git a/drivers/net/ethernet/sfc/falcon/enum.h b/drivers/net/ethernet/sfc/falcon/enum.h index 30a1136fc909..4824fcf5c3d4 100644 --- a/drivers/net/ethernet/sfc/falcon/enum.h +++ b/drivers/net/ethernet/sfc/falcon/enum.h @@ -81,7 +81,6 @@ enum ef4_loopback_mode { (1 << LOOPBACK_XAUI) | \ (1 << LOOPBACK_GMII) | \ (1 << LOOPBACK_SGMII) | \ - (1 << LOOPBACK_SGMII) | \ (1 << LOOPBACK_XGBR) | \ (1 << LOOPBACK_XFI) | \ (1 << LOOPBACK_XAUI_FAR) | \ diff --git a/drivers/net/ethernet/smsc/Kconfig b/drivers/net/ethernet/smsc/Kconfig index 63aca9f847e1..4c2f612e4414 100644 --- a/drivers/net/ethernet/smsc/Kconfig +++ b/drivers/net/ethernet/smsc/Kconfig @@ -20,7 +20,7 @@ if NET_VENDOR_SMSC config SMC9194 tristate "SMC 9194 support" - depends on (ISA || MAC && BROKEN) + depends on ISA select CRC32 ---help--- This is support for the SMC9xxx based Ethernet cards. Choose this diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c index 5270d26f0bc6..2d5d4aea3bcb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c @@ -48,26 +48,18 @@ #define MUX_CLK_NUM_PARENTS 2 struct meson8b_dwmac { - struct platform_device *pdev; - + struct device *dev; void __iomem *regs; - phy_interface_t phy_mode; + struct clk *rgmii_tx_clk; + u32 tx_delay_ns; +}; +struct meson8b_dwmac_clk_configs { struct clk_mux m250_mux; - struct clk *m250_mux_clk; - struct clk *m250_mux_parent[MUX_CLK_NUM_PARENTS]; - struct clk_divider m250_div; - struct clk *m250_div_clk; - struct clk_fixed_factor fixed_div2; - struct clk *fixed_div2_clk; - struct clk_gate rgmii_tx_en; - struct clk *rgmii_tx_en_clk; - - u32 tx_delay_ns; }; static void meson8b_dwmac_mask_bits(struct meson8b_dwmac *dwmac, u32 reg, @@ -82,106 +74,99 @@ static void meson8b_dwmac_mask_bits(struct meson8b_dwmac *dwmac, u32 reg, writel(data, dwmac->regs + reg); } -static int meson8b_init_rgmii_tx_clk(struct meson8b_dwmac *dwmac) +static struct clk *meson8b_dwmac_register_clk(struct meson8b_dwmac *dwmac, + const char *name_suffix, + const char **parent_names, + int num_parents, + const struct clk_ops *ops, + struct clk_hw *hw) { struct clk_init_data init; - int i, ret; - struct device *dev = &dwmac->pdev->dev; char clk_name[32]; - const char *clk_div_parents[1]; - const char *mux_parent_names[MUX_CLK_NUM_PARENTS]; + + snprintf(clk_name, sizeof(clk_name), "%s#%s", dev_name(dwmac->dev), + name_suffix); + + init.name = clk_name; + init.ops = ops; + init.flags = CLK_SET_RATE_PARENT; + init.parent_names = parent_names; + init.num_parents = num_parents; + + hw->init = &init; + + return devm_clk_register(dwmac->dev, hw); +} + +static int meson8b_init_rgmii_tx_clk(struct meson8b_dwmac *dwmac) +{ + int i, ret; + struct clk *clk; + struct device *dev = dwmac->dev; + const char *parent_name, *mux_parent_names[MUX_CLK_NUM_PARENTS]; + struct meson8b_dwmac_clk_configs *clk_configs; + + clk_configs = devm_kzalloc(dev, sizeof(*clk_configs), GFP_KERNEL); + if (!clk_configs) + return -ENOMEM; /* get the mux parents from DT */ for (i = 0; i < MUX_CLK_NUM_PARENTS; i++) { char name[16]; snprintf(name, sizeof(name), "clkin%d", i); - dwmac->m250_mux_parent[i] = devm_clk_get(dev, name); - if (IS_ERR(dwmac->m250_mux_parent[i])) { - ret = PTR_ERR(dwmac->m250_mux_parent[i]); + clk = devm_clk_get(dev, name); + if (IS_ERR(clk)) { + ret = PTR_ERR(clk); if (ret != -EPROBE_DEFER) dev_err(dev, "Missing clock %s\n", name); return ret; } - mux_parent_names[i] = - __clk_get_name(dwmac->m250_mux_parent[i]); + mux_parent_names[i] = __clk_get_name(clk); } - /* create the m250_mux */ - snprintf(clk_name, sizeof(clk_name), "%s#m250_sel", dev_name(dev)); - init.name = clk_name; - init.ops = &clk_mux_ops; - init.flags = CLK_SET_RATE_PARENT; - init.parent_names = mux_parent_names; - init.num_parents = MUX_CLK_NUM_PARENTS; - - dwmac->m250_mux.reg = dwmac->regs + PRG_ETH0; - dwmac->m250_mux.shift = PRG_ETH0_CLK_M250_SEL_SHIFT; - dwmac->m250_mux.mask = PRG_ETH0_CLK_M250_SEL_MASK; - dwmac->m250_mux.flags = 0; - dwmac->m250_mux.table = NULL; - dwmac->m250_mux.hw.init = &init; - - dwmac->m250_mux_clk = devm_clk_register(dev, &dwmac->m250_mux.hw); - if (WARN_ON(IS_ERR(dwmac->m250_mux_clk))) - return PTR_ERR(dwmac->m250_mux_clk); - - /* create the m250_div */ - snprintf(clk_name, sizeof(clk_name), "%s#m250_div", dev_name(dev)); - init.name = devm_kstrdup(dev, clk_name, GFP_KERNEL); - init.ops = &clk_divider_ops; - init.flags = CLK_SET_RATE_PARENT; - clk_div_parents[0] = __clk_get_name(dwmac->m250_mux_clk); - init.parent_names = clk_div_parents; - init.num_parents = ARRAY_SIZE(clk_div_parents); - - dwmac->m250_div.reg = dwmac->regs + PRG_ETH0; - dwmac->m250_div.shift = PRG_ETH0_CLK_M250_DIV_SHIFT; - dwmac->m250_div.width = PRG_ETH0_CLK_M250_DIV_WIDTH; - dwmac->m250_div.hw.init = &init; - dwmac->m250_div.flags = CLK_DIVIDER_ONE_BASED | + clk_configs->m250_mux.reg = dwmac->regs + PRG_ETH0; + clk_configs->m250_mux.shift = PRG_ETH0_CLK_M250_SEL_SHIFT; + clk_configs->m250_mux.mask = PRG_ETH0_CLK_M250_SEL_MASK; + clk = meson8b_dwmac_register_clk(dwmac, "m250_sel", mux_parent_names, + MUX_CLK_NUM_PARENTS, &clk_mux_ops, + &clk_configs->m250_mux.hw); + if (WARN_ON(IS_ERR(clk))) + return PTR_ERR(clk); + + parent_name = __clk_get_name(clk); + clk_configs->m250_div.reg = dwmac->regs + PRG_ETH0; + clk_configs->m250_div.shift = PRG_ETH0_CLK_M250_DIV_SHIFT; + clk_configs->m250_div.width = PRG_ETH0_CLK_M250_DIV_WIDTH; + clk_configs->m250_div.flags = CLK_DIVIDER_ONE_BASED | CLK_DIVIDER_ALLOW_ZERO | CLK_DIVIDER_ROUND_CLOSEST; - - dwmac->m250_div_clk = devm_clk_register(dev, &dwmac->m250_div.hw); - if (WARN_ON(IS_ERR(dwmac->m250_div_clk))) - return PTR_ERR(dwmac->m250_div_clk); - - /* create the fixed_div2 */ - snprintf(clk_name, sizeof(clk_name), "%s#fixed_div2", dev_name(dev)); - init.name = devm_kstrdup(dev, clk_name, GFP_KERNEL); - init.ops = &clk_fixed_factor_ops; - init.flags = CLK_SET_RATE_PARENT; - clk_div_parents[0] = __clk_get_name(dwmac->m250_div_clk); - init.parent_names = clk_div_parents; - init.num_parents = ARRAY_SIZE(clk_div_parents); - - dwmac->fixed_div2.mult = 1; - dwmac->fixed_div2.div = 2; - dwmac->fixed_div2.hw.init = &init; - - dwmac->fixed_div2_clk = devm_clk_register(dev, &dwmac->fixed_div2.hw); - if (WARN_ON(IS_ERR(dwmac->fixed_div2_clk))) - return PTR_ERR(dwmac->fixed_div2_clk); - - /* create the rgmii_tx_en */ - init.name = devm_kasprintf(dev, GFP_KERNEL, "%s#rgmii_tx_en", - dev_name(dev)); - init.ops = &clk_gate_ops; - init.flags = CLK_SET_RATE_PARENT; - clk_div_parents[0] = __clk_get_name(dwmac->fixed_div2_clk); - init.parent_names = clk_div_parents; - init.num_parents = ARRAY_SIZE(clk_div_parents); - - dwmac->rgmii_tx_en.reg = dwmac->regs + PRG_ETH0; - dwmac->rgmii_tx_en.bit_idx = PRG_ETH0_RGMII_TX_CLK_EN; - dwmac->rgmii_tx_en.hw.init = &init; - - dwmac->rgmii_tx_en_clk = devm_clk_register(dev, - &dwmac->rgmii_tx_en.hw); - if (WARN_ON(IS_ERR(dwmac->rgmii_tx_en_clk))) - return PTR_ERR(dwmac->rgmii_tx_en_clk); + clk = meson8b_dwmac_register_clk(dwmac, "m250_div", &parent_name, 1, + &clk_divider_ops, + &clk_configs->m250_div.hw); + if (WARN_ON(IS_ERR(clk))) + return PTR_ERR(clk); + + parent_name = __clk_get_name(clk); + clk_configs->fixed_div2.mult = 1; + clk_configs->fixed_div2.div = 2; + clk = meson8b_dwmac_register_clk(dwmac, "fixed_div2", &parent_name, 1, + &clk_fixed_factor_ops, + &clk_configs->fixed_div2.hw); + if (WARN_ON(IS_ERR(clk))) + return PTR_ERR(clk); + + parent_name = __clk_get_name(clk); + clk_configs->rgmii_tx_en.reg = dwmac->regs + PRG_ETH0; + clk_configs->rgmii_tx_en.bit_idx = PRG_ETH0_RGMII_TX_CLK_EN; + clk = meson8b_dwmac_register_clk(dwmac, "rgmii_tx_en", &parent_name, 1, + &clk_gate_ops, + &clk_configs->rgmii_tx_en.hw); + if (WARN_ON(IS_ERR(clk))) + return PTR_ERR(clk); + + dwmac->rgmii_tx_clk = clk; return 0; } @@ -219,19 +204,23 @@ static int meson8b_init_prg_eth(struct meson8b_dwmac *dwmac) * a register) based on the line-speed (125MHz for Gbit speeds, * 25MHz for 100Mbit/s and 2.5MHz for 10Mbit/s). */ - ret = clk_set_rate(dwmac->rgmii_tx_en_clk, 125 * 1000 * 1000); + ret = clk_set_rate(dwmac->rgmii_tx_clk, 125 * 1000 * 1000); if (ret) { - dev_err(&dwmac->pdev->dev, + dev_err(dwmac->dev, "failed to set RGMII TX clock\n"); return ret; } - ret = clk_prepare_enable(dwmac->rgmii_tx_en_clk); + ret = clk_prepare_enable(dwmac->rgmii_tx_clk); if (ret) { - dev_err(&dwmac->pdev->dev, + dev_err(dwmac->dev, "failed to enable the RGMII TX clock\n"); return ret; } + + devm_add_action_or_reset(dwmac->dev, + (void(*)(void *))clk_disable_unprepare, + dwmac->rgmii_tx_clk); break; case PHY_INTERFACE_MODE_RMII: @@ -251,7 +240,7 @@ static int meson8b_init_prg_eth(struct meson8b_dwmac *dwmac) break; default: - dev_err(&dwmac->pdev->dev, "unsupported phy-mode %s\n", + dev_err(dwmac->dev, "unsupported phy-mode %s\n", phy_modes(dwmac->phy_mode)); return -EINVAL; } @@ -292,7 +281,7 @@ static int meson8b_dwmac_probe(struct platform_device *pdev) goto err_remove_config_dt; } - dwmac->pdev = pdev; + dwmac->dev = &pdev->dev; dwmac->phy_mode = of_get_phy_mode(pdev->dev.of_node); if (dwmac->phy_mode < 0) { dev_err(&pdev->dev, "missing phy-mode property\n"); @@ -317,29 +306,16 @@ static int meson8b_dwmac_probe(struct platform_device *pdev) ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); if (ret) - goto err_clk_disable; + goto err_remove_config_dt; return 0; -err_clk_disable: - if (phy_interface_mode_is_rgmii(dwmac->phy_mode)) - clk_disable_unprepare(dwmac->rgmii_tx_en_clk); err_remove_config_dt: stmmac_remove_config_dt(pdev, plat_dat); return ret; } -static int meson8b_dwmac_remove(struct platform_device *pdev) -{ - struct meson8b_dwmac *dwmac = get_stmmac_bsp_priv(&pdev->dev); - - if (phy_interface_mode_is_rgmii(dwmac->phy_mode)) - clk_disable_unprepare(dwmac->rgmii_tx_en_clk); - - return stmmac_pltfr_remove(pdev); -} - static const struct of_device_id meson8b_dwmac_match[] = { { .compatible = "amlogic,meson8b-dwmac" }, { .compatible = "amlogic,meson-gxbb-dwmac" }, @@ -349,7 +325,7 @@ MODULE_DEVICE_TABLE(of, meson8b_dwmac_match); static struct platform_driver meson8b_dwmac_driver = { .probe = meson8b_dwmac_probe, - .remove = meson8b_dwmac_remove, + .remove = stmmac_pltfr_remove, .driver = { .name = "meson8b-dwmac", .pm = &stmmac_pltfr_pm_ops, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index 63795ecafc8d..46b9ae20ff6c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -120,7 +120,7 @@ static void dwmac4_tx_queue_priority(struct mac_device_info *hw, writel(value, ioaddr + base_register); } -static void dwmac4_tx_queue_routing(struct mac_device_info *hw, +static void dwmac4_rx_queue_routing(struct mac_device_info *hw, u8 packet, u32 queue) { void __iomem *ioaddr = hw->pcsr; @@ -713,7 +713,7 @@ static const struct stmmac_ops dwmac4_ops = { .rx_queue_enable = dwmac4_rx_queue_enable, .rx_queue_prio = dwmac4_rx_queue_priority, .tx_queue_prio = dwmac4_tx_queue_priority, - .rx_queue_routing = dwmac4_tx_queue_routing, + .rx_queue_routing = dwmac4_rx_queue_routing, .prog_mtl_rx_algorithms = dwmac4_prog_mtl_rx_algorithms, .prog_mtl_tx_algorithms = dwmac4_prog_mtl_tx_algorithms, .set_mtl_tx_queue_weight = dwmac4_set_mtl_tx_queue_weight, @@ -744,7 +744,7 @@ static const struct stmmac_ops dwmac410_ops = { .rx_queue_enable = dwmac4_rx_queue_enable, .rx_queue_prio = dwmac4_rx_queue_priority, .tx_queue_prio = dwmac4_tx_queue_priority, - .rx_queue_routing = dwmac4_tx_queue_routing, + .rx_queue_routing = dwmac4_rx_queue_routing, .prog_mtl_rx_algorithms = dwmac4_prog_mtl_rx_algorithms, .prog_mtl_tx_algorithms = dwmac4_prog_mtl_tx_algorithms, .set_mtl_tx_queue_weight = dwmac4_set_mtl_tx_queue_weight, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c index c728ffa095de..2a6521d33e43 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c @@ -389,6 +389,8 @@ static void dwmac4_rd_prepare_tso_tx_desc(struct dma_desc *p, int is_fs, static void dwmac4_release_tx_desc(struct dma_desc *p, int mode) { + p->des0 = 0; + p->des1 = 0; p->des2 = 0; p->des3 = 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index a916e13624eb..75161e1b7e55 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -58,6 +58,7 @@ struct stmmac_tx_queue { unsigned int dirty_tx; dma_addr_t dma_tx_phy; u32 tx_tail_addr; + u32 mss; }; struct stmmac_rx_queue { @@ -138,7 +139,6 @@ struct stmmac_priv { spinlock_t ptp_lock; void __iomem *mmcaddr; void __iomem *ptpaddr; - u32 mss; #ifdef CONFIG_DEBUG_FS struct dentry *dbgfs_dir; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 7ad841434ec8..a9856a8bf8ad 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1355,6 +1355,7 @@ static int init_dma_tx_desc_rings(struct net_device *dev) tx_q->dirty_tx = 0; tx_q->cur_tx = 0; + tx_q->mss = 0; netdev_tx_reset_queue(netdev_get_tx_queue(priv->dev, queue)); } @@ -1843,6 +1844,11 @@ static void stmmac_tx_clean(struct stmmac_priv *priv, u32 queue) if (unlikely(status & tx_dma_own)) break; + /* Make sure descriptor fields are read after reading + * the own bit. + */ + dma_rmb(); + /* Just consider the last segment and ...*/ if (likely(!(status & tx_not_ls))) { /* ... verify the status error condition */ @@ -1946,6 +1952,7 @@ static void stmmac_tx_err(struct stmmac_priv *priv, u32 chan) (i == DMA_TX_SIZE - 1)); tx_q->dirty_tx = 0; tx_q->cur_tx = 0; + tx_q->mss = 0; netdev_tx_reset_queue(netdev_get_tx_queue(priv->dev, chan)); stmmac_start_tx_dma(priv, chan); @@ -2430,7 +2437,7 @@ static void stmmac_mac_config_rx_queues_routing(struct stmmac_priv *priv) continue; packet = priv->plat->rx_queues_cfg[queue].pkt_route; - priv->hw->mac->rx_queue_prio(priv->hw, packet, queue); + priv->hw->mac->rx_queue_routing(priv->hw, packet, queue); } } @@ -2632,7 +2639,6 @@ static int stmmac_open(struct net_device *dev) priv->dma_buf_sz = STMMAC_ALIGN(buf_sz); priv->rx_copybreak = STMMAC_RX_COPYBREAK; - priv->mss = 0; ret = alloc_dma_desc_resources(priv); if (ret < 0) { @@ -2793,6 +2799,7 @@ static void stmmac_tso_allocator(struct stmmac_priv *priv, unsigned int des, while (tmp_len > 0) { tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, DMA_TX_SIZE); + WARN_ON(tx_q->tx_skbuff[tx_q->cur_tx]); desc = tx_q->dma_tx + tx_q->cur_tx; desc->des0 = cpu_to_le32(des + (total_len - tmp_len)); @@ -2872,11 +2879,12 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) mss = skb_shinfo(skb)->gso_size; /* set new MSS value if needed */ - if (mss != priv->mss) { + if (mss != tx_q->mss) { mss_desc = tx_q->dma_tx + tx_q->cur_tx; priv->hw->desc->set_mss(mss_desc, mss); - priv->mss = mss; + tx_q->mss = mss; tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, DMA_TX_SIZE); + WARN_ON(tx_q->tx_skbuff[tx_q->cur_tx]); } if (netif_msg_tx_queued(priv)) { @@ -2887,6 +2895,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) } first_entry = tx_q->cur_tx; + WARN_ON(tx_q->tx_skbuff[first_entry]); desc = tx_q->dma_tx + first_entry; first = desc; @@ -2926,7 +2935,6 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) tx_q->tx_skbuff_dma[tx_q->cur_tx].buf = des; tx_q->tx_skbuff_dma[tx_q->cur_tx].len = skb_frag_size(frag); - tx_q->tx_skbuff[tx_q->cur_tx] = NULL; tx_q->tx_skbuff_dma[tx_q->cur_tx].map_as_page = true; } @@ -2980,14 +2988,21 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) tcp_hdrlen(skb) / 4, (skb->len - proto_hdr_len)); /* If context desc is used to change MSS */ - if (mss_desc) + if (mss_desc) { + /* Make sure that first descriptor has been completely + * written, including its own bit. This is because MSS is + * actually before first descriptor, so we need to make + * sure that MSS's own bit is the last thing written. + */ + dma_wmb(); priv->hw->desc->set_tx_owner(mss_desc); + } /* The own bit must be the latest setting done when prepare the * descriptor and then barrier is needed to make sure that * all is coherent before granting the DMA engine. */ - dma_wmb(); + wmb(); if (netif_msg_pktdata(priv)) { pr_info("%s: curr=%d dirty=%d f=%d, e=%d, f_p=%p, nfrags %d\n", @@ -3062,6 +3077,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) entry = tx_q->cur_tx; first_entry = entry; + WARN_ON(tx_q->tx_skbuff[first_entry]); csum_insertion = (skb->ip_summed == CHECKSUM_PARTIAL); @@ -3090,6 +3106,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) bool last_segment = (i == (nfrags - 1)); entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE); + WARN_ON(tx_q->tx_skbuff[entry]); if (likely(priv->extend_desc)) desc = (struct dma_desc *)(tx_q->dma_etx + entry); @@ -3101,8 +3118,6 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) if (dma_mapping_error(priv->device, des)) goto dma_map_err; /* should reuse desc w/o issues */ - tx_q->tx_skbuff[entry] = NULL; - tx_q->tx_skbuff_dma[entry].buf = des; if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00)) desc->des0 = cpu_to_le32(des); @@ -3211,7 +3226,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) * descriptor and then barrier is needed to make sure that * all is coherent before granting the DMA engine. */ - dma_wmb(); + wmb(); } netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len); @@ -4436,6 +4451,7 @@ static void stmmac_reset_queues_param(struct stmmac_priv *priv) tx_q->cur_tx = 0; tx_q->dirty_tx = 0; + tx_q->mss = 0; } } @@ -4481,11 +4497,6 @@ int stmmac_resume(struct device *dev) stmmac_reset_queues_param(priv); - /* reset private mss value to force mss context settings at - * next tso xmit (only used for gmac4). - */ - priv->mss = 0; - stmmac_clear_descriptors(priv); stmmac_hw_setup(ndev, false); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 05f122b8424a..ebd3e5ffa73c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -135,13 +135,14 @@ static struct stmmac_axi *stmmac_axi_setup(struct platform_device *pdev) * stmmac_mtl_setup - parse DT parameters for multiple queues configuration * @pdev: platform device */ -static void stmmac_mtl_setup(struct platform_device *pdev, - struct plat_stmmacenet_data *plat) +static int stmmac_mtl_setup(struct platform_device *pdev, + struct plat_stmmacenet_data *plat) { struct device_node *q_node; struct device_node *rx_node; struct device_node *tx_node; u8 queue = 0; + int ret = 0; /* For backwards-compatibility with device trees that don't have any * snps,mtl-rx-config or snps,mtl-tx-config properties, we fall back @@ -159,12 +160,12 @@ static void stmmac_mtl_setup(struct platform_device *pdev, rx_node = of_parse_phandle(pdev->dev.of_node, "snps,mtl-rx-config", 0); if (!rx_node) - return; + return ret; tx_node = of_parse_phandle(pdev->dev.of_node, "snps,mtl-tx-config", 0); if (!tx_node) { of_node_put(rx_node); - return; + return ret; } /* Processing RX queues common config */ @@ -220,6 +221,11 @@ static void stmmac_mtl_setup(struct platform_device *pdev, queue++; } + if (queue != plat->rx_queues_to_use) { + ret = -EINVAL; + dev_err(&pdev->dev, "Not all RX queues were configured\n"); + goto out; + } /* Processing TX queues common config */ if (of_property_read_u32(tx_node, "snps,tx-queues-to-use", @@ -281,10 +287,18 @@ static void stmmac_mtl_setup(struct platform_device *pdev, queue++; } + if (queue != plat->tx_queues_to_use) { + ret = -EINVAL; + dev_err(&pdev->dev, "Not all TX queues were configured\n"); + goto out; + } +out: of_node_put(rx_node); of_node_put(tx_node); of_node_put(q_node); + + return ret; } /** @@ -376,6 +390,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) struct device_node *np = pdev->dev.of_node; struct plat_stmmacenet_data *plat; struct stmmac_dma_cfg *dma_cfg; + int rc; plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL); if (!plat) @@ -402,8 +417,9 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) dev_warn(&pdev->dev, "snps,phy-addr property is deprecated\n"); /* To Configure PHY by using all device-tree supported properties */ - if (stmmac_dt_phy(plat, np, &pdev->dev)) - return ERR_PTR(-ENODEV); + rc = stmmac_dt_phy(plat, np, &pdev->dev); + if (rc) + return ERR_PTR(rc); of_property_read_u32(np, "tx-fifo-depth", &plat->tx_fifo_size); @@ -499,7 +515,11 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) plat->axi = stmmac_axi_setup(pdev); - stmmac_mtl_setup(pdev, plat); + rc = stmmac_mtl_setup(pdev, plat); + if (rc) { + stmmac_remove_config_dt(pdev, plat); + return ERR_PTR(rc); + } /* clock setup */ plat->stmmac_clk = devm_clk_get(&pdev->dev, diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index b919e89a9b93..516dd59249d7 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1694,6 +1694,7 @@ static struct pernet_operations geneve_net_ops = { .exit_batch = geneve_exit_batch_net, .id = &geneve_net_id, .size = sizeof(struct geneve_net), + .async = true, }; static int __init geneve_init_module(void) diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index f38e32a7ec9c..127edd23018f 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -1325,6 +1325,7 @@ static struct pernet_operations gtp_net_ops = { .exit = gtp_net_exit, .id = >p_net_id, .size = sizeof(struct gtp_net), + .async = true, }; static int __init gtp_init(void) diff --git a/drivers/net/ieee802154/Kconfig b/drivers/net/ieee802154/Kconfig index 303ba4133920..8782f5655e3f 100644 --- a/drivers/net/ieee802154/Kconfig +++ b/drivers/net/ieee802154/Kconfig @@ -104,3 +104,14 @@ config IEEE802154_CA8210_DEBUGFS exposes a debugfs node for each CA8210 instance which allows direct use of the Cascoda API, exposing the 802.15.4 MAC management entities. + +config IEEE802154_MCR20A + tristate "MCR20A transceiver driver" + depends on IEEE802154_DRIVERS && MAC802154 + depends on SPI + ---help--- + Say Y here to enable the MCR20A SPI 802.15.4 wireless + controller. + + This driver can also be built as a module. To do so, say M here. + the module will be called 'mcr20a'. diff --git a/drivers/net/ieee802154/Makefile b/drivers/net/ieee802154/Makefile index bea1de5e726c..104744d5a668 100644 --- a/drivers/net/ieee802154/Makefile +++ b/drivers/net/ieee802154/Makefile @@ -6,3 +6,4 @@ obj-$(CONFIG_IEEE802154_CC2520) += cc2520.o obj-$(CONFIG_IEEE802154_ATUSB) += atusb.o obj-$(CONFIG_IEEE802154_ADF7242) += adf7242.o obj-$(CONFIG_IEEE802154_CA8210) += ca8210.o +obj-$(CONFIG_IEEE802154_MCR20A) += mcr20a.o diff --git a/drivers/net/ieee802154/mcr20a.c b/drivers/net/ieee802154/mcr20a.c new file mode 100644 index 000000000000..d9eb22a52551 --- /dev/null +++ b/drivers/net/ieee802154/mcr20a.c @@ -0,0 +1,1413 @@ +/* + * Driver for NXP MCR20A 802.15.4 Wireless-PAN Networking controller + * + * Copyright (C) 2018 Xue Liu <liuxuenetmail@gmail.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/gpio.h> +#include <linux/spi/spi.h> +#include <linux/workqueue.h> +#include <linux/interrupt.h> +#include <linux/skbuff.h> +#include <linux/of_gpio.h> +#include <linux/regmap.h> +#include <linux/ieee802154.h> +#include <linux/debugfs.h> + +#include <net/mac802154.h> +#include <net/cfg802154.h> + +#include <linux/device.h> + +#include "mcr20a.h" + +#define SPI_COMMAND_BUFFER 3 + +#define REGISTER_READ BIT(7) +#define REGISTER_WRITE (0 << 7) +#define REGISTER_ACCESS (0 << 6) +#define PACKET_BUFF_BURST_ACCESS BIT(6) +#define PACKET_BUFF_BYTE_ACCESS BIT(5) + +#define MCR20A_WRITE_REG(x) (x) +#define MCR20A_READ_REG(x) (REGISTER_READ | (x)) +#define MCR20A_BURST_READ_PACKET_BUF (0xC0) +#define MCR20A_BURST_WRITE_PACKET_BUF (0x40) + +#define MCR20A_CMD_REG 0x80 +#define MCR20A_CMD_REG_MASK 0x3f +#define MCR20A_CMD_WRITE 0x40 +#define MCR20A_CMD_FB 0x20 + +/* Number of Interrupt Request Status Register */ +#define MCR20A_IRQSTS_NUM 2 /* only IRQ_STS1 and IRQ_STS2 */ + +/* MCR20A CCA Type */ +enum { + MCR20A_CCA_ED, // energy detect - CCA bit not active, + // not to be used for T and CCCA sequences + MCR20A_CCA_MODE1, // energy detect - CCA bit ACTIVE + MCR20A_CCA_MODE2, // 802.15.4 compliant signal detect - CCA bit ACTIVE + MCR20A_CCA_MODE3 +}; + +enum { + MCR20A_XCVSEQ_IDLE = 0x00, + MCR20A_XCVSEQ_RX = 0x01, + MCR20A_XCVSEQ_TX = 0x02, + MCR20A_XCVSEQ_CCA = 0x03, + MCR20A_XCVSEQ_TR = 0x04, + MCR20A_XCVSEQ_CCCA = 0x05, +}; + +/* IEEE-802.15.4 defined constants (2.4 GHz logical channels) */ +#define MCR20A_MIN_CHANNEL (11) +#define MCR20A_MAX_CHANNEL (26) +#define MCR20A_CHANNEL_SPACING (5) + +/* MCR20A CCA Threshold constans */ +#define MCR20A_MIN_CCA_THRESHOLD (0x6EU) +#define MCR20A_MAX_CCA_THRESHOLD (0x00U) + +/* version 0C */ +#define MCR20A_OVERWRITE_VERSION (0x0C) + +/* MCR20A PLL configurations */ +static const u8 PLL_INT[16] = { + /* 2405 */ 0x0B, /* 2410 */ 0x0B, /* 2415 */ 0x0B, + /* 2420 */ 0x0B, /* 2425 */ 0x0B, /* 2430 */ 0x0B, + /* 2435 */ 0x0C, /* 2440 */ 0x0C, /* 2445 */ 0x0C, + /* 2450 */ 0x0C, /* 2455 */ 0x0C, /* 2460 */ 0x0C, + /* 2465 */ 0x0D, /* 2470 */ 0x0D, /* 2475 */ 0x0D, + /* 2480 */ 0x0D +}; + +static const u8 PLL_FRAC[16] = { + /* 2405 */ 0x28, /* 2410 */ 0x50, /* 2415 */ 0x78, + /* 2420 */ 0xA0, /* 2425 */ 0xC8, /* 2430 */ 0xF0, + /* 2435 */ 0x18, /* 2440 */ 0x40, /* 2445 */ 0x68, + /* 2450 */ 0x90, /* 2455 */ 0xB8, /* 2460 */ 0xE0, + /* 2465 */ 0x08, /* 2470 */ 0x30, /* 2475 */ 0x58, + /* 2480 */ 0x80 +}; + +static const struct reg_sequence mar20a_iar_overwrites[] = { + { IAR_MISC_PAD_CTRL, 0x02 }, + { IAR_VCO_CTRL1, 0xB3 }, + { IAR_VCO_CTRL2, 0x07 }, + { IAR_PA_TUNING, 0x71 }, + { IAR_CHF_IBUF, 0x2F }, + { IAR_CHF_QBUF, 0x2F }, + { IAR_CHF_IRIN, 0x24 }, + { IAR_CHF_QRIN, 0x24 }, + { IAR_CHF_IL, 0x24 }, + { IAR_CHF_QL, 0x24 }, + { IAR_CHF_CC1, 0x32 }, + { IAR_CHF_CCL, 0x1D }, + { IAR_CHF_CC2, 0x2D }, + { IAR_CHF_IROUT, 0x24 }, + { IAR_CHF_QROUT, 0x24 }, + { IAR_PA_CAL, 0x28 }, + { IAR_AGC_THR1, 0x55 }, + { IAR_AGC_THR2, 0x2D }, + { IAR_ATT_RSSI1, 0x5F }, + { IAR_ATT_RSSI2, 0x8F }, + { IAR_RSSI_OFFSET, 0x61 }, + { IAR_CHF_PMA_GAIN, 0x03 }, + { IAR_CCA1_THRESH, 0x50 }, + { IAR_CORR_NVAL, 0x13 }, + { IAR_ACKDELAY, 0x3D }, +}; + +#define MCR20A_VALID_CHANNELS (0x07FFF800) + +struct mcr20a_platform_data { + int rst_gpio; +}; + +#define MCR20A_MAX_BUF (127) + +#define printdev(X) (&X->spi->dev) + +/* regmap information for Direct Access Register (DAR) access */ +#define MCR20A_DAR_WRITE 0x01 +#define MCR20A_DAR_READ 0x00 +#define MCR20A_DAR_NUMREGS 0x3F + +/* regmap information for Indirect Access Register (IAR) access */ +#define MCR20A_IAR_ACCESS 0x80 +#define MCR20A_IAR_NUMREGS 0xBEFF + +/* Read/Write SPI Commands for DAR and IAR registers. */ +#define MCR20A_READSHORT(reg) ((reg) << 1) +#define MCR20A_WRITESHORT(reg) ((reg) << 1 | 1) +#define MCR20A_READLONG(reg) (1 << 15 | (reg) << 5) +#define MCR20A_WRITELONG(reg) (1 << 15 | (reg) << 5 | 1 << 4) + +/* Type definitions for link configuration of instantiable layers */ +#define MCR20A_PHY_INDIRECT_QUEUE_SIZE (12) + +static bool +mcr20a_dar_writeable(struct device *dev, unsigned int reg) +{ + switch (reg) { + case DAR_IRQ_STS1: + case DAR_IRQ_STS2: + case DAR_IRQ_STS3: + case DAR_PHY_CTRL1: + case DAR_PHY_CTRL2: + case DAR_PHY_CTRL3: + case DAR_PHY_CTRL4: + case DAR_SRC_CTRL: + case DAR_SRC_ADDRS_SUM_LSB: + case DAR_SRC_ADDRS_SUM_MSB: + case DAR_T3CMP_LSB: + case DAR_T3CMP_MSB: + case DAR_T3CMP_USB: + case DAR_T2PRIMECMP_LSB: + case DAR_T2PRIMECMP_MSB: + case DAR_T1CMP_LSB: + case DAR_T1CMP_MSB: + case DAR_T1CMP_USB: + case DAR_T2CMP_LSB: + case DAR_T2CMP_MSB: + case DAR_T2CMP_USB: + case DAR_T4CMP_LSB: + case DAR_T4CMP_MSB: + case DAR_T4CMP_USB: + case DAR_PLL_INT0: + case DAR_PLL_FRAC0_LSB: + case DAR_PLL_FRAC0_MSB: + case DAR_PA_PWR: + /* no DAR_ACM */ + case DAR_OVERWRITE_VER: + case DAR_CLK_OUT_CTRL: + case DAR_PWR_MODES: + return true; + default: + return false; + } +} + +static bool +mcr20a_dar_readable(struct device *dev, unsigned int reg) +{ + bool rc; + + /* all writeable are also readable */ + rc = mcr20a_dar_writeable(dev, reg); + if (rc) + return rc; + + /* readonly regs */ + switch (reg) { + case DAR_RX_FRM_LEN: + case DAR_CCA1_ED_FNL: + case DAR_EVENT_TMR_LSB: + case DAR_EVENT_TMR_MSB: + case DAR_EVENT_TMR_USB: + case DAR_TIMESTAMP_LSB: + case DAR_TIMESTAMP_MSB: + case DAR_TIMESTAMP_USB: + case DAR_SEQ_STATE: + case DAR_LQI_VALUE: + case DAR_RSSI_CCA_CONT: + return true; + default: + return false; + } +} + +static bool +mcr20a_dar_volatile(struct device *dev, unsigned int reg) +{ + /* can be changed during runtime */ + switch (reg) { + case DAR_IRQ_STS1: + case DAR_IRQ_STS2: + case DAR_IRQ_STS3: + /* use them in spi_async and regmap so it's volatile */ + return true; + default: + return false; + } +} + +static bool +mcr20a_dar_precious(struct device *dev, unsigned int reg) +{ + /* don't clear irq line on read */ + switch (reg) { + case DAR_IRQ_STS1: + case DAR_IRQ_STS2: + case DAR_IRQ_STS3: + return true; + default: + return false; + } +} + +static const struct regmap_config mcr20a_dar_regmap = { + .name = "mcr20a_dar", + .reg_bits = 8, + .val_bits = 8, + .write_flag_mask = REGISTER_ACCESS | REGISTER_WRITE, + .read_flag_mask = REGISTER_ACCESS | REGISTER_READ, + .cache_type = REGCACHE_RBTREE, + .writeable_reg = mcr20a_dar_writeable, + .readable_reg = mcr20a_dar_readable, + .volatile_reg = mcr20a_dar_volatile, + .precious_reg = mcr20a_dar_precious, + .fast_io = true, + .can_multi_write = true, +}; + +static bool +mcr20a_iar_writeable(struct device *dev, unsigned int reg) +{ + switch (reg) { + case IAR_XTAL_TRIM: + case IAR_PMC_LP_TRIM: + case IAR_MACPANID0_LSB: + case IAR_MACPANID0_MSB: + case IAR_MACSHORTADDRS0_LSB: + case IAR_MACSHORTADDRS0_MSB: + case IAR_MACLONGADDRS0_0: + case IAR_MACLONGADDRS0_8: + case IAR_MACLONGADDRS0_16: + case IAR_MACLONGADDRS0_24: + case IAR_MACLONGADDRS0_32: + case IAR_MACLONGADDRS0_40: + case IAR_MACLONGADDRS0_48: + case IAR_MACLONGADDRS0_56: + case IAR_RX_FRAME_FILTER: + case IAR_PLL_INT1: + case IAR_PLL_FRAC1_LSB: + case IAR_PLL_FRAC1_MSB: + case IAR_MACPANID1_LSB: + case IAR_MACPANID1_MSB: + case IAR_MACSHORTADDRS1_LSB: + case IAR_MACSHORTADDRS1_MSB: + case IAR_MACLONGADDRS1_0: + case IAR_MACLONGADDRS1_8: + case IAR_MACLONGADDRS1_16: + case IAR_MACLONGADDRS1_24: + case IAR_MACLONGADDRS1_32: + case IAR_MACLONGADDRS1_40: + case IAR_MACLONGADDRS1_48: + case IAR_MACLONGADDRS1_56: + case IAR_DUAL_PAN_CTRL: + case IAR_DUAL_PAN_DWELL: + case IAR_CCA1_THRESH: + case IAR_CCA1_ED_OFFSET_COMP: + case IAR_LQI_OFFSET_COMP: + case IAR_CCA_CTRL: + case IAR_CCA2_CORR_PEAKS: + case IAR_CCA2_CORR_THRESH: + case IAR_TMR_PRESCALE: + case IAR_ANT_PAD_CTRL: + case IAR_MISC_PAD_CTRL: + case IAR_BSM_CTRL: + case IAR_RNG: + case IAR_RX_WTR_MARK: + case IAR_SOFT_RESET: + case IAR_TXDELAY: + case IAR_ACKDELAY: + case IAR_CORR_NVAL: + case IAR_ANT_AGC_CTRL: + case IAR_AGC_THR1: + case IAR_AGC_THR2: + case IAR_PA_CAL: + case IAR_ATT_RSSI1: + case IAR_ATT_RSSI2: + case IAR_RSSI_OFFSET: + case IAR_XTAL_CTRL: + case IAR_CHF_PMA_GAIN: + case IAR_CHF_IBUF: + case IAR_CHF_QBUF: + case IAR_CHF_IRIN: + case IAR_CHF_QRIN: + case IAR_CHF_IL: + case IAR_CHF_QL: + case IAR_CHF_CC1: + case IAR_CHF_CCL: + case IAR_CHF_CC2: + case IAR_CHF_IROUT: + case IAR_CHF_QROUT: + case IAR_PA_TUNING: + case IAR_VCO_CTRL1: + case IAR_VCO_CTRL2: + return true; + default: + return false; + } +} + +static bool +mcr20a_iar_readable(struct device *dev, unsigned int reg) +{ + bool rc; + + /* all writeable are also readable */ + rc = mcr20a_iar_writeable(dev, reg); + if (rc) + return rc; + + /* readonly regs */ + switch (reg) { + case IAR_PART_ID: + case IAR_DUAL_PAN_STS: + case IAR_RX_BYTE_COUNT: + case IAR_FILTERFAIL_CODE1: + case IAR_FILTERFAIL_CODE2: + case IAR_RSSI: + return true; + default: + return false; + } +} + +static bool +mcr20a_iar_volatile(struct device *dev, unsigned int reg) +{ +/* can be changed during runtime */ + switch (reg) { + case IAR_DUAL_PAN_STS: + case IAR_RX_BYTE_COUNT: + case IAR_FILTERFAIL_CODE1: + case IAR_FILTERFAIL_CODE2: + case IAR_RSSI: + return true; + default: + return false; + } +} + +static const struct regmap_config mcr20a_iar_regmap = { + .name = "mcr20a_iar", + .reg_bits = 16, + .val_bits = 8, + .write_flag_mask = REGISTER_ACCESS | REGISTER_WRITE | IAR_INDEX, + .read_flag_mask = REGISTER_ACCESS | REGISTER_READ | IAR_INDEX, + .cache_type = REGCACHE_RBTREE, + .writeable_reg = mcr20a_iar_writeable, + .readable_reg = mcr20a_iar_readable, + .volatile_reg = mcr20a_iar_volatile, + .fast_io = true, +}; + +struct mcr20a_local { + struct spi_device *spi; + + struct ieee802154_hw *hw; + struct mcr20a_platform_data *pdata; + struct regmap *regmap_dar; + struct regmap *regmap_iar; + + u8 *buf; + + bool is_tx; + + /* for writing tx buffer */ + struct spi_message tx_buf_msg; + u8 tx_header[1]; + /* burst buffer write command */ + struct spi_transfer tx_xfer_header; + u8 tx_len[1]; + /* len of tx packet */ + struct spi_transfer tx_xfer_len; + /* data of tx packet */ + struct spi_transfer tx_xfer_buf; + struct sk_buff *tx_skb; + + /* for read length rxfifo */ + struct spi_message reg_msg; + u8 reg_cmd[1]; + u8 reg_data[MCR20A_IRQSTS_NUM]; + struct spi_transfer reg_xfer_cmd; + struct spi_transfer reg_xfer_data; + + /* receive handling */ + struct spi_message rx_buf_msg; + u8 rx_header[1]; + struct spi_transfer rx_xfer_header; + u8 rx_lqi[1]; + struct spi_transfer rx_xfer_lqi; + u8 rx_buf[MCR20A_MAX_BUF]; + struct spi_transfer rx_xfer_buf; + + /* isr handling for reading intstat */ + struct spi_message irq_msg; + u8 irq_header[1]; + u8 irq_data[MCR20A_IRQSTS_NUM]; + struct spi_transfer irq_xfer_data; + struct spi_transfer irq_xfer_header; +}; + +static void +mcr20a_write_tx_buf_complete(void *context) +{ + struct mcr20a_local *lp = context; + int ret; + + dev_dbg(printdev(lp), "%s\n", __func__); + + lp->reg_msg.complete = NULL; + lp->reg_cmd[0] = MCR20A_WRITE_REG(DAR_PHY_CTRL1); + lp->reg_data[0] = MCR20A_XCVSEQ_TX; + lp->reg_xfer_data.len = 1; + + ret = spi_async(lp->spi, &lp->reg_msg); + if (ret) + dev_err(printdev(lp), "failed to set SEQ TX\n"); +} + +static int +mcr20a_xmit(struct ieee802154_hw *hw, struct sk_buff *skb) +{ + struct mcr20a_local *lp = hw->priv; + + dev_dbg(printdev(lp), "%s\n", __func__); + + lp->tx_skb = skb; + + print_hex_dump_debug("mcr20a tx: ", DUMP_PREFIX_OFFSET, 16, 1, + skb->data, skb->len, 0); + + lp->is_tx = 1; + + lp->reg_msg.complete = NULL; + lp->reg_cmd[0] = MCR20A_WRITE_REG(DAR_PHY_CTRL1); + lp->reg_data[0] = MCR20A_XCVSEQ_IDLE; + lp->reg_xfer_data.len = 1; + + return spi_async(lp->spi, &lp->reg_msg); +} + +static int +mcr20a_ed(struct ieee802154_hw *hw, u8 *level) +{ + WARN_ON(!level); + *level = 0xbe; + return 0; +} + +static int +mcr20a_set_channel(struct ieee802154_hw *hw, u8 page, u8 channel) +{ + struct mcr20a_local *lp = hw->priv; + int ret; + + dev_dbg(printdev(lp), "%s\n", __func__); + + /* freqency = ((PLL_INT+64) + (PLL_FRAC/65536)) * 32 MHz */ + ret = regmap_write(lp->regmap_dar, DAR_PLL_INT0, PLL_INT[channel - 11]); + if (ret) + return ret; + ret = regmap_write(lp->regmap_dar, DAR_PLL_FRAC0_LSB, 0x00); + if (ret) + return ret; + ret = regmap_write(lp->regmap_dar, DAR_PLL_FRAC0_MSB, + PLL_FRAC[channel - 11]); + if (ret) + return ret; + + return 0; +} + +static int +mcr20a_start(struct ieee802154_hw *hw) +{ + struct mcr20a_local *lp = hw->priv; + int ret; + + dev_dbg(printdev(lp), "%s\n", __func__); + + /* No slotted operation */ + dev_dbg(printdev(lp), "no slotted operation\n"); + ret = regmap_update_bits(lp->regmap_dar, DAR_PHY_CTRL1, + DAR_PHY_CTRL1_SLOTTED, 0x0); + + /* enable irq */ + enable_irq(lp->spi->irq); + + /* Unmask SEQ interrupt */ + ret = regmap_update_bits(lp->regmap_dar, DAR_PHY_CTRL2, + DAR_PHY_CTRL2_SEQMSK, 0x0); + + /* Start the RX sequence */ + dev_dbg(printdev(lp), "start the RX sequence\n"); + ret = regmap_update_bits(lp->regmap_dar, DAR_PHY_CTRL1, + DAR_PHY_CTRL1_XCVSEQ_MASK, MCR20A_XCVSEQ_RX); + + return 0; +} + +static void +mcr20a_stop(struct ieee802154_hw *hw) +{ + struct mcr20a_local *lp = hw->priv; + + dev_dbg(printdev(lp), "%s\n", __func__); + + /* stop all running sequence */ + regmap_update_bits(lp->regmap_dar, DAR_PHY_CTRL1, + DAR_PHY_CTRL1_XCVSEQ_MASK, MCR20A_XCVSEQ_IDLE); + + /* disable irq */ + disable_irq(lp->spi->irq); +} + +static int +mcr20a_set_hw_addr_filt(struct ieee802154_hw *hw, + struct ieee802154_hw_addr_filt *filt, + unsigned long changed) +{ + struct mcr20a_local *lp = hw->priv; + + dev_dbg(printdev(lp), "%s\n", __func__); + + if (changed & IEEE802154_AFILT_SADDR_CHANGED) { + u16 addr = le16_to_cpu(filt->short_addr); + + regmap_write(lp->regmap_iar, IAR_MACSHORTADDRS0_LSB, addr); + regmap_write(lp->regmap_iar, IAR_MACSHORTADDRS0_MSB, addr >> 8); + } + + if (changed & IEEE802154_AFILT_PANID_CHANGED) { + u16 pan = le16_to_cpu(filt->pan_id); + + regmap_write(lp->regmap_iar, IAR_MACPANID0_LSB, pan); + regmap_write(lp->regmap_iar, IAR_MACPANID0_MSB, pan >> 8); + } + + if (changed & IEEE802154_AFILT_IEEEADDR_CHANGED) { + u8 addr[8], i; + + memcpy(addr, &filt->ieee_addr, 8); + for (i = 0; i < 8; i++) + regmap_write(lp->regmap_iar, + IAR_MACLONGADDRS0_0 + i, addr[i]); + } + + if (changed & IEEE802154_AFILT_PANC_CHANGED) { + if (filt->pan_coord) { + regmap_update_bits(lp->regmap_dar, DAR_PHY_CTRL4, + DAR_PHY_CTRL4_PANCORDNTR0, 0x10); + } else { + regmap_update_bits(lp->regmap_dar, DAR_PHY_CTRL4, + DAR_PHY_CTRL4_PANCORDNTR0, 0x00); + } + } + + return 0; +} + +/* -30 dBm to 10 dBm */ +#define MCR20A_MAX_TX_POWERS 0x14 +static const s32 mcr20a_powers[MCR20A_MAX_TX_POWERS + 1] = { + -3000, -2800, -2600, -2400, -2200, -2000, -1800, -1600, -1400, + -1200, -1000, -800, -600, -400, -200, 0, 200, 400, 600, 800, 1000 +}; + +static int +mcr20a_set_txpower(struct ieee802154_hw *hw, s32 mbm) +{ + struct mcr20a_local *lp = hw->priv; + u32 i; + + dev_dbg(printdev(lp), "%s(%d)\n", __func__, mbm); + + for (i = 0; i < lp->hw->phy->supported.tx_powers_size; i++) { + if (lp->hw->phy->supported.tx_powers[i] == mbm) + return regmap_write(lp->regmap_dar, DAR_PA_PWR, + ((i + 8) & 0x1F)); + } + + return -EINVAL; +} + +#define MCR20A_MAX_ED_LEVELS MCR20A_MIN_CCA_THRESHOLD +static s32 mcr20a_ed_levels[MCR20A_MAX_ED_LEVELS + 1]; + +static int +mcr20a_set_cca_mode(struct ieee802154_hw *hw, + const struct wpan_phy_cca *cca) +{ + struct mcr20a_local *lp = hw->priv; + unsigned int cca_mode = 0xff; + bool cca_mode_and = false; + int ret; + + dev_dbg(printdev(lp), "%s\n", __func__); + + /* mapping 802.15.4 to driver spec */ + switch (cca->mode) { + case NL802154_CCA_ENERGY: + cca_mode = MCR20A_CCA_MODE1; + break; + case NL802154_CCA_CARRIER: + cca_mode = MCR20A_CCA_MODE2; + break; + case NL802154_CCA_ENERGY_CARRIER: + switch (cca->opt) { + case NL802154_CCA_OPT_ENERGY_CARRIER_AND: + cca_mode = MCR20A_CCA_MODE3; + cca_mode_and = true; + break; + case NL802154_CCA_OPT_ENERGY_CARRIER_OR: + cca_mode = MCR20A_CCA_MODE3; + cca_mode_and = false; + break; + default: + return -EINVAL; + } + break; + default: + return -EINVAL; + } + ret = regmap_update_bits(lp->regmap_dar, DAR_PHY_CTRL4, + DAR_PHY_CTRL4_CCATYPE_MASK, + cca_mode << DAR_PHY_CTRL4_CCATYPE_SHIFT); + if (ret < 0) + return ret; + + if (cca_mode == MCR20A_CCA_MODE3) { + if (cca_mode_and) { + ret = regmap_update_bits(lp->regmap_iar, IAR_CCA_CTRL, + IAR_CCA_CTRL_CCA3_AND_NOT_OR, + 0x08); + } else { + ret = regmap_update_bits(lp->regmap_iar, + IAR_CCA_CTRL, + IAR_CCA_CTRL_CCA3_AND_NOT_OR, + 0x00); + } + if (ret < 0) + return ret; + } + + return ret; +} + +static int +mcr20a_set_cca_ed_level(struct ieee802154_hw *hw, s32 mbm) +{ + struct mcr20a_local *lp = hw->priv; + u32 i; + + dev_dbg(printdev(lp), "%s\n", __func__); + + for (i = 0; i < hw->phy->supported.cca_ed_levels_size; i++) { + if (hw->phy->supported.cca_ed_levels[i] == mbm) + return regmap_write(lp->regmap_iar, IAR_CCA1_THRESH, i); + } + + return 0; +} + +static int +mcr20a_set_promiscuous_mode(struct ieee802154_hw *hw, const bool on) +{ + struct mcr20a_local *lp = hw->priv; + int ret; + u8 rx_frame_filter_reg = 0x0; + u8 val; + + dev_dbg(printdev(lp), "%s(%d)\n", __func__, on); + + if (on) { + /* All frame types accepted*/ + val |= DAR_PHY_CTRL4_PROMISCUOUS; + rx_frame_filter_reg &= ~(IAR_RX_FRAME_FLT_FRM_VER); + rx_frame_filter_reg |= (IAR_RX_FRAME_FLT_ACK_FT | + IAR_RX_FRAME_FLT_NS_FT); + + ret = regmap_update_bits(lp->regmap_dar, DAR_PHY_CTRL4, + DAR_PHY_CTRL4_PROMISCUOUS, + DAR_PHY_CTRL4_PROMISCUOUS); + if (ret < 0) + return ret; + + ret = regmap_write(lp->regmap_iar, IAR_RX_FRAME_FILTER, + rx_frame_filter_reg); + if (ret < 0) + return ret; + } else { + ret = regmap_update_bits(lp->regmap_dar, DAR_PHY_CTRL4, + DAR_PHY_CTRL4_PROMISCUOUS, 0x0); + if (ret < 0) + return ret; + + ret = regmap_write(lp->regmap_iar, IAR_RX_FRAME_FILTER, + IAR_RX_FRAME_FLT_FRM_VER | + IAR_RX_FRAME_FLT_BEACON_FT | + IAR_RX_FRAME_FLT_DATA_FT | + IAR_RX_FRAME_FLT_CMD_FT); + if (ret < 0) + return ret; + } + + return 0; +} + +static const struct ieee802154_ops mcr20a_hw_ops = { + .owner = THIS_MODULE, + .xmit_async = mcr20a_xmit, + .ed = mcr20a_ed, + .set_channel = mcr20a_set_channel, + .start = mcr20a_start, + .stop = mcr20a_stop, + .set_hw_addr_filt = mcr20a_set_hw_addr_filt, + .set_txpower = mcr20a_set_txpower, + .set_cca_mode = mcr20a_set_cca_mode, + .set_cca_ed_level = mcr20a_set_cca_ed_level, + .set_promiscuous_mode = mcr20a_set_promiscuous_mode, +}; + +static int +mcr20a_request_rx(struct mcr20a_local *lp) +{ + dev_dbg(printdev(lp), "%s\n", __func__); + + /* Start the RX sequence */ + regmap_update_bits_async(lp->regmap_dar, DAR_PHY_CTRL1, + DAR_PHY_CTRL1_XCVSEQ_MASK, MCR20A_XCVSEQ_RX); + + return 0; +} + +static void +mcr20a_handle_rx_read_buf_complete(void *context) +{ + struct mcr20a_local *lp = context; + u8 len = lp->reg_data[0] & DAR_RX_FRAME_LENGTH_MASK; + struct sk_buff *skb; + + dev_dbg(printdev(lp), "%s\n", __func__); + + dev_dbg(printdev(lp), "RX is done\n"); + + if (!ieee802154_is_valid_psdu_len(len)) { + dev_vdbg(&lp->spi->dev, "corrupted frame received\n"); + len = IEEE802154_MTU; + } + + len = len - 2; /* get rid of frame check field */ + + skb = dev_alloc_skb(len); + if (!skb) + return; + + memcpy(skb_put(skb, len), lp->rx_buf, len); + ieee802154_rx_irqsafe(lp->hw, skb, lp->rx_lqi[0]); + + print_hex_dump_debug("mcr20a rx: ", DUMP_PREFIX_OFFSET, 16, 1, + lp->rx_buf, len, 0); + pr_debug("mcr20a rx: lqi: %02hhx\n", lp->rx_lqi[0]); + + /* start RX sequence */ + mcr20a_request_rx(lp); +} + +static void +mcr20a_handle_rx_read_len_complete(void *context) +{ + struct mcr20a_local *lp = context; + u8 len; + int ret; + + dev_dbg(printdev(lp), "%s\n", __func__); + + /* get the length of received frame */ + len = lp->reg_data[0] & DAR_RX_FRAME_LENGTH_MASK; + dev_dbg(printdev(lp), "frame len : %d\n", len); + + /* prepare to read the rx buf */ + lp->rx_buf_msg.complete = mcr20a_handle_rx_read_buf_complete; + lp->rx_header[0] = MCR20A_BURST_READ_PACKET_BUF; + lp->rx_xfer_buf.len = len; + + ret = spi_async(lp->spi, &lp->rx_buf_msg); + if (ret) + dev_err(printdev(lp), "failed to read rx buffer length\n"); +} + +static int +mcr20a_handle_rx(struct mcr20a_local *lp) +{ + dev_dbg(printdev(lp), "%s\n", __func__); + lp->reg_msg.complete = mcr20a_handle_rx_read_len_complete; + lp->reg_cmd[0] = MCR20A_READ_REG(DAR_RX_FRM_LEN); + lp->reg_xfer_data.len = 1; + + return spi_async(lp->spi, &lp->reg_msg); +} + +static int +mcr20a_handle_tx_complete(struct mcr20a_local *lp) +{ + dev_dbg(printdev(lp), "%s\n", __func__); + + ieee802154_xmit_complete(lp->hw, lp->tx_skb, false); + + return mcr20a_request_rx(lp); +} + +static int +mcr20a_handle_tx(struct mcr20a_local *lp) +{ + int ret; + + dev_dbg(printdev(lp), "%s\n", __func__); + + /* write tx buffer */ + lp->tx_header[0] = MCR20A_BURST_WRITE_PACKET_BUF; + /* add 2 bytes of FCS */ + lp->tx_len[0] = lp->tx_skb->len + 2; + lp->tx_xfer_buf.tx_buf = lp->tx_skb->data; + /* add 1 byte psduLength */ + lp->tx_xfer_buf.len = lp->tx_skb->len + 1; + + ret = spi_async(lp->spi, &lp->tx_buf_msg); + if (ret) { + dev_err(printdev(lp), "SPI write Failed for TX buf\n"); + return ret; + } + + return 0; +} + +static void +mcr20a_irq_clean_complete(void *context) +{ + struct mcr20a_local *lp = context; + u8 seq_state = lp->irq_data[DAR_IRQ_STS1] & DAR_PHY_CTRL1_XCVSEQ_MASK; + + dev_dbg(printdev(lp), "%s\n", __func__); + + enable_irq(lp->spi->irq); + + dev_dbg(printdev(lp), "IRQ STA1 (%02x) STA2 (%02x)\n", + lp->irq_data[DAR_IRQ_STS1], lp->irq_data[DAR_IRQ_STS2]); + + switch (seq_state) { + /* TX IRQ, RX IRQ and SEQ IRQ */ + case (0x03): + if (lp->is_tx) { + lp->is_tx = 0; + dev_dbg(printdev(lp), "TX is done. No ACK\n"); + mcr20a_handle_tx_complete(lp); + } + break; + case (0x05): + /* rx is starting */ + dev_dbg(printdev(lp), "RX is starting\n"); + mcr20a_handle_rx(lp); + break; + case (0x07): + if (lp->is_tx) { + /* tx is done */ + lp->is_tx = 0; + dev_dbg(printdev(lp), "TX is done. Get ACK\n"); + mcr20a_handle_tx_complete(lp); + } else { + /* rx is starting */ + dev_dbg(printdev(lp), "RX is starting\n"); + mcr20a_handle_rx(lp); + } + break; + case (0x01): + if (lp->is_tx) { + dev_dbg(printdev(lp), "TX is starting\n"); + mcr20a_handle_tx(lp); + } else { + dev_dbg(printdev(lp), "MCR20A is stop\n"); + } + break; + } +} + +static void mcr20a_irq_status_complete(void *context) +{ + int ret; + struct mcr20a_local *lp = context; + + dev_dbg(printdev(lp), "%s\n", __func__); + regmap_update_bits_async(lp->regmap_dar, DAR_PHY_CTRL1, + DAR_PHY_CTRL1_XCVSEQ_MASK, MCR20A_XCVSEQ_IDLE); + + lp->reg_msg.complete = mcr20a_irq_clean_complete; + lp->reg_cmd[0] = MCR20A_WRITE_REG(DAR_IRQ_STS1); + memcpy(lp->reg_data, lp->irq_data, MCR20A_IRQSTS_NUM); + lp->reg_xfer_data.len = MCR20A_IRQSTS_NUM; + + ret = spi_async(lp->spi, &lp->reg_msg); + + if (ret) + dev_err(printdev(lp), "failed to clean irq status\n"); +} + +static irqreturn_t mcr20a_irq_isr(int irq, void *data) +{ + struct mcr20a_local *lp = data; + int ret; + + disable_irq_nosync(irq); + + lp->irq_header[0] = MCR20A_READ_REG(DAR_IRQ_STS1); + /* read IRQSTSx */ + ret = spi_async(lp->spi, &lp->irq_msg); + if (ret) { + enable_irq(irq); + return IRQ_NONE; + } + + return IRQ_HANDLED; +} + +static int mcr20a_get_platform_data(struct spi_device *spi, + struct mcr20a_platform_data *pdata) +{ + int ret = 0; + + if (!spi->dev.of_node) + return -EINVAL; + + pdata->rst_gpio = of_get_named_gpio(spi->dev.of_node, "rst_b-gpio", 0); + dev_dbg(&spi->dev, "rst_b-gpio: %d\n", pdata->rst_gpio); + + return ret; +} + +static void mcr20a_hw_setup(struct mcr20a_local *lp) +{ + u8 i; + struct ieee802154_hw *hw = lp->hw; + struct wpan_phy *phy = lp->hw->phy; + + dev_dbg(printdev(lp), "%s\n", __func__); + + phy->symbol_duration = 16; + phy->lifs_period = 40; + phy->sifs_period = 12; + + hw->flags = IEEE802154_HW_TX_OMIT_CKSUM | + IEEE802154_HW_AFILT | + IEEE802154_HW_PROMISCUOUS; + + phy->flags = WPAN_PHY_FLAG_TXPOWER | WPAN_PHY_FLAG_CCA_ED_LEVEL | + WPAN_PHY_FLAG_CCA_MODE; + + phy->supported.cca_modes = BIT(NL802154_CCA_ENERGY) | + BIT(NL802154_CCA_CARRIER) | BIT(NL802154_CCA_ENERGY_CARRIER); + phy->supported.cca_opts = BIT(NL802154_CCA_OPT_ENERGY_CARRIER_AND) | + BIT(NL802154_CCA_OPT_ENERGY_CARRIER_OR); + + /* initiating cca_ed_levels */ + for (i = MCR20A_MAX_CCA_THRESHOLD; i < MCR20A_MIN_CCA_THRESHOLD + 1; + ++i) { + mcr20a_ed_levels[i] = -i * 100; + } + + phy->supported.cca_ed_levels = mcr20a_ed_levels; + phy->supported.cca_ed_levels_size = ARRAY_SIZE(mcr20a_ed_levels); + + phy->cca.mode = NL802154_CCA_ENERGY; + + phy->supported.channels[0] = MCR20A_VALID_CHANNELS; + phy->current_page = 0; + /* MCR20A default reset value */ + phy->current_channel = 20; + phy->symbol_duration = 16; + phy->supported.tx_powers = mcr20a_powers; + phy->supported.tx_powers_size = ARRAY_SIZE(mcr20a_powers); + phy->cca_ed_level = phy->supported.cca_ed_levels[75]; + phy->transmit_power = phy->supported.tx_powers[0x0F]; +} + +static void +mcr20a_setup_tx_spi_messages(struct mcr20a_local *lp) +{ + spi_message_init(&lp->tx_buf_msg); + lp->tx_buf_msg.context = lp; + lp->tx_buf_msg.complete = mcr20a_write_tx_buf_complete; + + lp->tx_xfer_header.len = 1; + lp->tx_xfer_header.tx_buf = lp->tx_header; + + lp->tx_xfer_len.len = 1; + lp->tx_xfer_len.tx_buf = lp->tx_len; + + spi_message_add_tail(&lp->tx_xfer_header, &lp->tx_buf_msg); + spi_message_add_tail(&lp->tx_xfer_len, &lp->tx_buf_msg); + spi_message_add_tail(&lp->tx_xfer_buf, &lp->tx_buf_msg); +} + +static void +mcr20a_setup_rx_spi_messages(struct mcr20a_local *lp) +{ + spi_message_init(&lp->reg_msg); + lp->reg_msg.context = lp; + + lp->reg_xfer_cmd.len = 1; + lp->reg_xfer_cmd.tx_buf = lp->reg_cmd; + lp->reg_xfer_cmd.rx_buf = lp->reg_cmd; + + lp->reg_xfer_data.rx_buf = lp->reg_data; + lp->reg_xfer_data.tx_buf = lp->reg_data; + + spi_message_add_tail(&lp->reg_xfer_cmd, &lp->reg_msg); + spi_message_add_tail(&lp->reg_xfer_data, &lp->reg_msg); + + spi_message_init(&lp->rx_buf_msg); + lp->rx_buf_msg.context = lp; + lp->rx_buf_msg.complete = mcr20a_handle_rx_read_buf_complete; + lp->rx_xfer_header.len = 1; + lp->rx_xfer_header.tx_buf = lp->rx_header; + lp->rx_xfer_header.rx_buf = lp->rx_header; + + lp->rx_xfer_buf.rx_buf = lp->rx_buf; + + lp->rx_xfer_lqi.len = 1; + lp->rx_xfer_lqi.rx_buf = lp->rx_lqi; + + spi_message_add_tail(&lp->rx_xfer_header, &lp->rx_buf_msg); + spi_message_add_tail(&lp->rx_xfer_buf, &lp->rx_buf_msg); + spi_message_add_tail(&lp->rx_xfer_lqi, &lp->rx_buf_msg); +} + +static void +mcr20a_setup_irq_spi_messages(struct mcr20a_local *lp) +{ + spi_message_init(&lp->irq_msg); + lp->irq_msg.context = lp; + lp->irq_msg.complete = mcr20a_irq_status_complete; + lp->irq_xfer_header.len = 1; + lp->irq_xfer_header.tx_buf = lp->irq_header; + lp->irq_xfer_header.rx_buf = lp->irq_header; + + lp->irq_xfer_data.len = MCR20A_IRQSTS_NUM; + lp->irq_xfer_data.rx_buf = lp->irq_data; + + spi_message_add_tail(&lp->irq_xfer_header, &lp->irq_msg); + spi_message_add_tail(&lp->irq_xfer_data, &lp->irq_msg); +} + +static int +mcr20a_phy_init(struct mcr20a_local *lp) +{ + u8 index; + unsigned int phy_reg = 0; + int ret; + + dev_dbg(printdev(lp), "%s\n", __func__); + + /* Disable Tristate on COCO MISO for SPI reads */ + ret = regmap_write(lp->regmap_iar, IAR_MISC_PAD_CTRL, 0x02); + if (ret) + goto err_ret; + + /* Clear all PP IRQ bits in IRQSTS1 to avoid unexpected interrupts + * immediately after init + */ + ret = regmap_write(lp->regmap_dar, DAR_IRQ_STS1, 0xEF); + if (ret) + goto err_ret; + + /* Clear all PP IRQ bits in IRQSTS2 */ + ret = regmap_write(lp->regmap_dar, DAR_IRQ_STS2, + DAR_IRQSTS2_ASM_IRQ | DAR_IRQSTS2_PB_ERR_IRQ | + DAR_IRQSTS2_WAKE_IRQ); + if (ret) + goto err_ret; + + /* Disable all timer interrupts */ + ret = regmap_write(lp->regmap_dar, DAR_IRQ_STS3, 0xFF); + if (ret) + goto err_ret; + + /* PHY_CTRL1 : default HW settings + AUTOACK enabled */ + ret = regmap_update_bits(lp->regmap_dar, DAR_PHY_CTRL1, + DAR_PHY_CTRL1_AUTOACK, DAR_PHY_CTRL1_AUTOACK); + + /* PHY_CTRL2 : disable all interrupts */ + ret = regmap_write(lp->regmap_dar, DAR_PHY_CTRL2, 0xFF); + if (ret) + goto err_ret; + + /* PHY_CTRL3 : disable all timers and remaining interrupts */ + ret = regmap_write(lp->regmap_dar, DAR_PHY_CTRL3, + DAR_PHY_CTRL3_ASM_MSK | DAR_PHY_CTRL3_PB_ERR_MSK | + DAR_PHY_CTRL3_WAKE_MSK); + if (ret) + goto err_ret; + + /* SRC_CTRL : enable Acknowledge Frame Pending and + * Source Address Matching Enable + */ + ret = regmap_write(lp->regmap_dar, DAR_SRC_CTRL, + DAR_SRC_CTRL_ACK_FRM_PND | + (DAR_SRC_CTRL_INDEX << DAR_SRC_CTRL_INDEX_SHIFT)); + if (ret) + goto err_ret; + + /* RX_FRAME_FILTER */ + /* FRM_VER[1:0] = b11. Accept FrameVersion 0 and 1 packets */ + ret = regmap_write(lp->regmap_iar, IAR_RX_FRAME_FILTER, + IAR_RX_FRAME_FLT_FRM_VER | + IAR_RX_FRAME_FLT_BEACON_FT | + IAR_RX_FRAME_FLT_DATA_FT | + IAR_RX_FRAME_FLT_CMD_FT); + if (ret) + goto err_ret; + + dev_info(printdev(lp), "MCR20A DAR overwrites version: 0x%02x\n", + MCR20A_OVERWRITE_VERSION); + + /* Overwrites direct registers */ + ret = regmap_write(lp->regmap_dar, DAR_OVERWRITE_VER, + MCR20A_OVERWRITE_VERSION); + if (ret) + goto err_ret; + + /* Overwrites indirect registers */ + ret = regmap_multi_reg_write(lp->regmap_iar, mar20a_iar_overwrites, + ARRAY_SIZE(mar20a_iar_overwrites)); + if (ret) + goto err_ret; + + /* Clear HW indirect queue */ + dev_dbg(printdev(lp), "clear HW indirect queue\n"); + for (index = 0; index < MCR20A_PHY_INDIRECT_QUEUE_SIZE; index++) { + phy_reg = (u8)(((index & DAR_SRC_CTRL_INDEX) << + DAR_SRC_CTRL_INDEX_SHIFT) + | (DAR_SRC_CTRL_SRCADDR_EN) + | (DAR_SRC_CTRL_INDEX_DISABLE)); + ret = regmap_write(lp->regmap_dar, DAR_SRC_CTRL, phy_reg); + if (ret) + goto err_ret; + phy_reg = 0; + } + + /* Assign HW Indirect hash table to PAN0 */ + ret = regmap_read(lp->regmap_iar, IAR_DUAL_PAN_CTRL, &phy_reg); + if (ret) + goto err_ret; + + /* Clear current lvl */ + phy_reg &= ~IAR_DUAL_PAN_CTRL_DUAL_PAN_SAM_LVL_MSK; + + /* Set new lvl */ + phy_reg |= MCR20A_PHY_INDIRECT_QUEUE_SIZE << + IAR_DUAL_PAN_CTRL_DUAL_PAN_SAM_LVL_SHIFT; + ret = regmap_write(lp->regmap_iar, IAR_DUAL_PAN_CTRL, phy_reg); + if (ret) + goto err_ret; + + /* Set CCA threshold to -75 dBm */ + ret = regmap_write(lp->regmap_iar, IAR_CCA1_THRESH, 0x4B); + if (ret) + goto err_ret; + + /* Set prescaller to obtain 1 symbol (16us) timebase */ + ret = regmap_write(lp->regmap_iar, IAR_TMR_PRESCALE, 0x05); + if (ret) + goto err_ret; + + /* Enable autodoze mode. */ + ret = regmap_update_bits(lp->regmap_dar, DAR_PWR_MODES, + DAR_PWR_MODES_AUTODOZE, + DAR_PWR_MODES_AUTODOZE); + if (ret) + goto err_ret; + + /* Disable clk_out */ + ret = regmap_update_bits(lp->regmap_dar, DAR_CLK_OUT_CTRL, + DAR_CLK_OUT_CTRL_EN, 0x0); + if (ret) + goto err_ret; + + return 0; + +err_ret: + return ret; +} + +static int +mcr20a_probe(struct spi_device *spi) +{ + struct ieee802154_hw *hw; + struct mcr20a_local *lp; + struct mcr20a_platform_data *pdata; + int irq_type; + int ret = -ENOMEM; + + dev_dbg(&spi->dev, "%s\n", __func__); + + if (!spi->irq) { + dev_err(&spi->dev, "no IRQ specified\n"); + return -EINVAL; + } + + pdata = kmalloc(sizeof(*pdata), GFP_KERNEL); + if (!pdata) + return -ENOMEM; + + /* set mcr20a platform data */ + ret = mcr20a_get_platform_data(spi, pdata); + if (ret < 0) { + dev_crit(&spi->dev, "mcr20a_get_platform_data failed.\n"); + return ret; + } + + /* init reset gpio */ + if (gpio_is_valid(pdata->rst_gpio)) { + ret = devm_gpio_request_one(&spi->dev, pdata->rst_gpio, + GPIOF_OUT_INIT_HIGH, "reset"); + if (ret) + return ret; + } + + /* reset mcr20a */ + if (gpio_is_valid(pdata->rst_gpio)) { + usleep_range(10, 20); + gpio_set_value_cansleep(pdata->rst_gpio, 0); + usleep_range(10, 20); + gpio_set_value_cansleep(pdata->rst_gpio, 1); + usleep_range(120, 240); + } + + /* allocate ieee802154_hw and private data */ + hw = ieee802154_alloc_hw(sizeof(*lp), &mcr20a_hw_ops); + if (!hw) { + dev_crit(&spi->dev, "ieee802154_alloc_hw failed\n"); + return -ENOMEM; + } + + /* init mcr20a local data */ + lp = hw->priv; + lp->hw = hw; + lp->spi = spi; + lp->spi->dev.platform_data = pdata; + lp->pdata = pdata; + + /* init ieee802154_hw */ + hw->parent = &spi->dev; + ieee802154_random_extended_addr(&hw->phy->perm_extended_addr); + + /* init buf */ + lp->buf = devm_kzalloc(&spi->dev, SPI_COMMAND_BUFFER, GFP_KERNEL); + + if (!lp->buf) + return -ENOMEM; + + mcr20a_setup_tx_spi_messages(lp); + mcr20a_setup_rx_spi_messages(lp); + mcr20a_setup_irq_spi_messages(lp); + + /* setup regmap */ + lp->regmap_dar = devm_regmap_init_spi(spi, &mcr20a_dar_regmap); + if (IS_ERR(lp->regmap_dar)) { + ret = PTR_ERR(lp->regmap_dar); + dev_err(&spi->dev, "Failed to allocate dar map: %d\n", + ret); + goto free_dev; + } + + lp->regmap_iar = devm_regmap_init_spi(spi, &mcr20a_iar_regmap); + if (IS_ERR(lp->regmap_iar)) { + ret = PTR_ERR(lp->regmap_iar); + dev_err(&spi->dev, "Failed to allocate iar map: %d\n", ret); + goto free_dev; + } + + mcr20a_hw_setup(lp); + + spi_set_drvdata(spi, lp); + + ret = mcr20a_phy_init(lp); + if (ret < 0) { + dev_crit(&spi->dev, "mcr20a_phy_init failed\n"); + goto free_dev; + } + + irq_type = irq_get_trigger_type(spi->irq); + if (!irq_type) + irq_type = IRQF_TRIGGER_FALLING; + + ret = devm_request_irq(&spi->dev, spi->irq, mcr20a_irq_isr, + irq_type, dev_name(&spi->dev), lp); + if (ret) { + dev_err(&spi->dev, "could not request_irq for mcr20a\n"); + ret = -ENODEV; + goto free_dev; + } + + /* disable_irq by default and wait for starting hardware */ + disable_irq(spi->irq); + + ret = ieee802154_register_hw(hw); + if (ret) { + dev_crit(&spi->dev, "ieee802154_register_hw failed\n"); + goto free_dev; + } + + return ret; + +free_dev: + ieee802154_free_hw(lp->hw); + + return ret; +} + +static int mcr20a_remove(struct spi_device *spi) +{ + struct mcr20a_local *lp = spi_get_drvdata(spi); + + dev_dbg(&spi->dev, "%s\n", __func__); + + ieee802154_unregister_hw(lp->hw); + ieee802154_free_hw(lp->hw); + + return 0; +} + +static const struct of_device_id mcr20a_of_match[] = { + { .compatible = "nxp,mcr20a", }, + { }, +}; +MODULE_DEVICE_TABLE(of, mcr20a_of_match); + +static const struct spi_device_id mcr20a_device_id[] = { + { .name = "mcr20a", }, + { }, +}; +MODULE_DEVICE_TABLE(spi, mcr20a_device_id); + +static struct spi_driver mcr20a_driver = { + .id_table = mcr20a_device_id, + .driver = { + .of_match_table = of_match_ptr(mcr20a_of_match), + .name = "mcr20a", + }, + .probe = mcr20a_probe, + .remove = mcr20a_remove, +}; + +module_spi_driver(mcr20a_driver); + +MODULE_DESCRIPTION("MCR20A Transceiver Driver"); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Xue Liu <liuxuenetmail@gmail>"); diff --git a/drivers/net/ieee802154/mcr20a.h b/drivers/net/ieee802154/mcr20a.h new file mode 100644 index 000000000000..6da4fd00b3c5 --- /dev/null +++ b/drivers/net/ieee802154/mcr20a.h @@ -0,0 +1,498 @@ +/* + * Driver for NXP MCR20A 802.15.4 Wireless-PAN Networking controller + * + * Copyright (C) 2018 Xue Liu <liuxuenetmail@gmail.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ +#ifndef _MCR20A_H +#define _MCR20A_H + +/* Direct Accress Register */ +#define DAR_IRQ_STS1 0x00 +#define DAR_IRQ_STS2 0x01 +#define DAR_IRQ_STS3 0x02 +#define DAR_PHY_CTRL1 0x03 +#define DAR_PHY_CTRL2 0x04 +#define DAR_PHY_CTRL3 0x05 +#define DAR_RX_FRM_LEN 0x06 +#define DAR_PHY_CTRL4 0x07 +#define DAR_SRC_CTRL 0x08 +#define DAR_SRC_ADDRS_SUM_LSB 0x09 +#define DAR_SRC_ADDRS_SUM_MSB 0x0A +#define DAR_CCA1_ED_FNL 0x0B +#define DAR_EVENT_TMR_LSB 0x0C +#define DAR_EVENT_TMR_MSB 0x0D +#define DAR_EVENT_TMR_USB 0x0E +#define DAR_TIMESTAMP_LSB 0x0F +#define DAR_TIMESTAMP_MSB 0x10 +#define DAR_TIMESTAMP_USB 0x11 +#define DAR_T3CMP_LSB 0x12 +#define DAR_T3CMP_MSB 0x13 +#define DAR_T3CMP_USB 0x14 +#define DAR_T2PRIMECMP_LSB 0x15 +#define DAR_T2PRIMECMP_MSB 0x16 +#define DAR_T1CMP_LSB 0x17 +#define DAR_T1CMP_MSB 0x18 +#define DAR_T1CMP_USB 0x19 +#define DAR_T2CMP_LSB 0x1A +#define DAR_T2CMP_MSB 0x1B +#define DAR_T2CMP_USB 0x1C +#define DAR_T4CMP_LSB 0x1D +#define DAR_T4CMP_MSB 0x1E +#define DAR_T4CMP_USB 0x1F +#define DAR_PLL_INT0 0x20 +#define DAR_PLL_FRAC0_LSB 0x21 +#define DAR_PLL_FRAC0_MSB 0x22 +#define DAR_PA_PWR 0x23 +#define DAR_SEQ_STATE 0x24 +#define DAR_LQI_VALUE 0x25 +#define DAR_RSSI_CCA_CONT 0x26 +/*------------------ 0x27 */ +#define DAR_ASM_CTRL1 0x28 +#define DAR_ASM_CTRL2 0x29 +#define DAR_ASM_DATA_0 0x2A +#define DAR_ASM_DATA_1 0x2B +#define DAR_ASM_DATA_2 0x2C +#define DAR_ASM_DATA_3 0x2D +#define DAR_ASM_DATA_4 0x2E +#define DAR_ASM_DATA_5 0x2F +#define DAR_ASM_DATA_6 0x30 +#define DAR_ASM_DATA_7 0x31 +#define DAR_ASM_DATA_8 0x32 +#define DAR_ASM_DATA_9 0x33 +#define DAR_ASM_DATA_A 0x34 +#define DAR_ASM_DATA_B 0x35 +#define DAR_ASM_DATA_C 0x36 +#define DAR_ASM_DATA_D 0x37 +#define DAR_ASM_DATA_E 0x38 +#define DAR_ASM_DATA_F 0x39 +/*----------------------- 0x3A */ +#define DAR_OVERWRITE_VER 0x3B +#define DAR_CLK_OUT_CTRL 0x3C +#define DAR_PWR_MODES 0x3D +#define IAR_INDEX 0x3E +#define IAR_DATA 0x3F + +/* Indirect Resgister Memory */ +#define IAR_PART_ID 0x00 +#define IAR_XTAL_TRIM 0x01 +#define IAR_PMC_LP_TRIM 0x02 +#define IAR_MACPANID0_LSB 0x03 +#define IAR_MACPANID0_MSB 0x04 +#define IAR_MACSHORTADDRS0_LSB 0x05 +#define IAR_MACSHORTADDRS0_MSB 0x06 +#define IAR_MACLONGADDRS0_0 0x07 +#define IAR_MACLONGADDRS0_8 0x08 +#define IAR_MACLONGADDRS0_16 0x09 +#define IAR_MACLONGADDRS0_24 0x0A +#define IAR_MACLONGADDRS0_32 0x0B +#define IAR_MACLONGADDRS0_40 0x0C +#define IAR_MACLONGADDRS0_48 0x0D +#define IAR_MACLONGADDRS0_56 0x0E +#define IAR_RX_FRAME_FILTER 0x0F +#define IAR_PLL_INT1 0x10 +#define IAR_PLL_FRAC1_LSB 0x11 +#define IAR_PLL_FRAC1_MSB 0x12 +#define IAR_MACPANID1_LSB 0x13 +#define IAR_MACPANID1_MSB 0x14 +#define IAR_MACSHORTADDRS1_LSB 0x15 +#define IAR_MACSHORTADDRS1_MSB 0x16 +#define IAR_MACLONGADDRS1_0 0x17 +#define IAR_MACLONGADDRS1_8 0x18 +#define IAR_MACLONGADDRS1_16 0x19 +#define IAR_MACLONGADDRS1_24 0x1A +#define IAR_MACLONGADDRS1_32 0x1B +#define IAR_MACLONGADDRS1_40 0x1C +#define IAR_MACLONGADDRS1_48 0x1D +#define IAR_MACLONGADDRS1_56 0x1E +#define IAR_DUAL_PAN_CTRL 0x1F +#define IAR_DUAL_PAN_DWELL 0x20 +#define IAR_DUAL_PAN_STS 0x21 +#define IAR_CCA1_THRESH 0x22 +#define IAR_CCA1_ED_OFFSET_COMP 0x23 +#define IAR_LQI_OFFSET_COMP 0x24 +#define IAR_CCA_CTRL 0x25 +#define IAR_CCA2_CORR_PEAKS 0x26 +#define IAR_CCA2_CORR_THRESH 0x27 +#define IAR_TMR_PRESCALE 0x28 +/*-------------------- 0x29 */ +#define IAR_GPIO_DATA 0x2A +#define IAR_GPIO_DIR 0x2B +#define IAR_GPIO_PUL_EN 0x2C +#define IAR_GPIO_PUL_SEL 0x2D +#define IAR_GPIO_DS 0x2E +/*------------------ 0x2F */ +#define IAR_ANT_PAD_CTRL 0x30 +#define IAR_MISC_PAD_CTRL 0x31 +#define IAR_BSM_CTRL 0x32 +/*------------------- 0x33 */ +#define IAR_RNG 0x34 +#define IAR_RX_BYTE_COUNT 0x35 +#define IAR_RX_WTR_MARK 0x36 +#define IAR_SOFT_RESET 0x37 +#define IAR_TXDELAY 0x38 +#define IAR_ACKDELAY 0x39 +#define IAR_SEQ_MGR_CTRL 0x3A +#define IAR_SEQ_MGR_STS 0x3B +#define IAR_SEQ_T_STS 0x3C +#define IAR_ABORT_STS 0x3D +#define IAR_CCCA_BUSY_CNT 0x3E +#define IAR_SRC_ADDR_CHECKSUM1 0x3F +#define IAR_SRC_ADDR_CHECKSUM2 0x40 +#define IAR_SRC_TBL_VALID1 0x41 +#define IAR_SRC_TBL_VALID2 0x42 +#define IAR_FILTERFAIL_CODE1 0x43 +#define IAR_FILTERFAIL_CODE2 0x44 +#define IAR_SLOT_PRELOAD 0x45 +/*-------------------- 0x46 */ +#define IAR_CORR_VT 0x47 +#define IAR_SYNC_CTRL 0x48 +#define IAR_PN_LSB_0 0x49 +#define IAR_PN_LSB_1 0x4A +#define IAR_PN_MSB_0 0x4B +#define IAR_PN_MSB_1 0x4C +#define IAR_CORR_NVAL 0x4D +#define IAR_TX_MODE_CTRL 0x4E +#define IAR_SNF_THR 0x4F +#define IAR_FAD_THR 0x50 +#define IAR_ANT_AGC_CTRL 0x51 +#define IAR_AGC_THR1 0x52 +#define IAR_AGC_THR2 0x53 +#define IAR_AGC_HYS 0x54 +#define IAR_AFC 0x55 +/*------------------- 0x56 */ +/*------------------- 0x57 */ +#define IAR_PHY_STS 0x58 +#define IAR_RX_MAX_CORR 0x59 +#define IAR_RX_MAX_PREAMBLE 0x5A +#define IAR_RSSI 0x5B +/*------------------- 0x5C */ +/*------------------- 0x5D */ +#define IAR_PLL_DIG_CTRL 0x5E +#define IAR_VCO_CAL 0x5F +#define IAR_VCO_BEST_DIFF 0x60 +#define IAR_VCO_BIAS 0x61 +#define IAR_KMOD_CTRL 0x62 +#define IAR_KMOD_CAL 0x63 +#define IAR_PA_CAL 0x64 +#define IAR_PA_PWRCAL 0x65 +#define IAR_ATT_RSSI1 0x66 +#define IAR_ATT_RSSI2 0x67 +#define IAR_RSSI_OFFSET 0x68 +#define IAR_RSSI_SLOPE 0x69 +#define IAR_RSSI_CAL1 0x6A +#define IAR_RSSI_CAL2 0x6B +/*------------------- 0x6C */ +/*------------------- 0x6D */ +#define IAR_XTAL_CTRL 0x6E +#define IAR_XTAL_COMP_MIN 0x6F +#define IAR_XTAL_COMP_MAX 0x70 +#define IAR_XTAL_GM 0x71 +/*------------------- 0x72 */ +/*------------------- 0x73 */ +#define IAR_LNA_TUNE 0x74 +#define IAR_LNA_AGCGAIN 0x75 +/*------------------- 0x76 */ +/*------------------- 0x77 */ +#define IAR_CHF_PMA_GAIN 0x78 +#define IAR_CHF_IBUF 0x79 +#define IAR_CHF_QBUF 0x7A +#define IAR_CHF_IRIN 0x7B +#define IAR_CHF_QRIN 0x7C +#define IAR_CHF_IL 0x7D +#define IAR_CHF_QL 0x7E +#define IAR_CHF_CC1 0x7F +#define IAR_CHF_CCL 0x80 +#define IAR_CHF_CC2 0x81 +#define IAR_CHF_IROUT 0x82 +#define IAR_CHF_QROUT 0x83 +/*------------------- 0x84 */ +/*------------------- 0x85 */ +#define IAR_RSSI_CTRL 0x86 +/*------------------- 0x87 */ +/*------------------- 0x88 */ +#define IAR_PA_BIAS 0x89 +#define IAR_PA_TUNING 0x8A +/*------------------- 0x8B */ +/*------------------- 0x8C */ +#define IAR_PMC_HP_TRIM 0x8D +#define IAR_VREGA_TRIM 0x8E +/*------------------- 0x8F */ +/*------------------- 0x90 */ +#define IAR_VCO_CTRL1 0x91 +#define IAR_VCO_CTRL2 0x92 +/*------------------- 0x93 */ +/*------------------- 0x94 */ +#define IAR_ANA_SPARE_OUT1 0x95 +#define IAR_ANA_SPARE_OUT2 0x96 +#define IAR_ANA_SPARE_IN 0x97 +#define IAR_MISCELLANEOUS 0x98 +/*------------------- 0x99 */ +#define IAR_SEQ_MGR_OVRD0 0x9A +#define IAR_SEQ_MGR_OVRD1 0x9B +#define IAR_SEQ_MGR_OVRD2 0x9C +#define IAR_SEQ_MGR_OVRD3 0x9D +#define IAR_SEQ_MGR_OVRD4 0x9E +#define IAR_SEQ_MGR_OVRD5 0x9F +#define IAR_SEQ_MGR_OVRD6 0xA0 +#define IAR_SEQ_MGR_OVRD7 0xA1 +/*------------------- 0xA2 */ +#define IAR_TESTMODE_CTRL 0xA3 +#define IAR_DTM_CTRL1 0xA4 +#define IAR_DTM_CTRL2 0xA5 +#define IAR_ATM_CTRL1 0xA6 +#define IAR_ATM_CTRL2 0xA7 +#define IAR_ATM_CTRL3 0xA8 +/*------------------- 0xA9 */ +#define IAR_LIM_FE_TEST_CTRL 0xAA +#define IAR_CHF_TEST_CTRL 0xAB +#define IAR_VCO_TEST_CTRL 0xAC +#define IAR_PLL_TEST_CTRL 0xAD +#define IAR_PA_TEST_CTRL 0xAE +#define IAR_PMC_TEST_CTRL 0xAF +#define IAR_SCAN_DTM_PROTECT_1 0xFE +#define IAR_SCAN_DTM_PROTECT_0 0xFF + +/* IRQSTS1 bits */ +#define DAR_IRQSTS1_RX_FRM_PEND BIT(7) +#define DAR_IRQSTS1_PLL_UNLOCK_IRQ BIT(6) +#define DAR_IRQSTS1_FILTERFAIL_IRQ BIT(5) +#define DAR_IRQSTS1_RXWTRMRKIRQ BIT(4) +#define DAR_IRQSTS1_CCAIRQ BIT(3) +#define DAR_IRQSTS1_RXIRQ BIT(2) +#define DAR_IRQSTS1_TXIRQ BIT(1) +#define DAR_IRQSTS1_SEQIRQ BIT(0) + +/* IRQSTS2 bits */ +#define DAR_IRQSTS2_CRCVALID BIT(7) +#define DAR_IRQSTS2_CCA BIT(6) +#define DAR_IRQSTS2_SRCADDR BIT(5) +#define DAR_IRQSTS2_PI BIT(4) +#define DAR_IRQSTS2_TMRSTATUS BIT(3) +#define DAR_IRQSTS2_ASM_IRQ BIT(2) +#define DAR_IRQSTS2_PB_ERR_IRQ BIT(1) +#define DAR_IRQSTS2_WAKE_IRQ BIT(0) + +/* IRQSTS3 bits */ +#define DAR_IRQSTS3_TMR4MSK BIT(7) +#define DAR_IRQSTS3_TMR3MSK BIT(6) +#define DAR_IRQSTS3_TMR2MSK BIT(5) +#define DAR_IRQSTS3_TMR1MSK BIT(4) +#define DAR_IRQSTS3_TMR4IRQ BIT(3) +#define DAR_IRQSTS3_TMR3IRQ BIT(2) +#define DAR_IRQSTS3_TMR2IRQ BIT(1) +#define DAR_IRQSTS3_TMR1IRQ BIT(0) + +/* PHY_CTRL1 bits */ +#define DAR_PHY_CTRL1_TMRTRIGEN BIT(7) +#define DAR_PHY_CTRL1_SLOTTED BIT(6) +#define DAR_PHY_CTRL1_CCABFRTX BIT(5) +#define DAR_PHY_CTRL1_CCABFRTX_SHIFT 5 +#define DAR_PHY_CTRL1_RXACKRQD BIT(4) +#define DAR_PHY_CTRL1_AUTOACK BIT(3) +#define DAR_PHY_CTRL1_XCVSEQ_MASK 0x07 + +/* PHY_CTRL2 bits */ +#define DAR_PHY_CTRL2_CRC_MSK BIT(7) +#define DAR_PHY_CTRL2_PLL_UNLOCK_MSK BIT(6) +#define DAR_PHY_CTRL2_FILTERFAIL_MSK BIT(5) +#define DAR_PHY_CTRL2_RX_WMRK_MSK BIT(4) +#define DAR_PHY_CTRL2_CCAMSK BIT(3) +#define DAR_PHY_CTRL2_RXMSK BIT(2) +#define DAR_PHY_CTRL2_TXMSK BIT(1) +#define DAR_PHY_CTRL2_SEQMSK BIT(0) + +/* PHY_CTRL3 bits */ +#define DAR_PHY_CTRL3_TMR4CMP_EN BIT(7) +#define DAR_PHY_CTRL3_TMR3CMP_EN BIT(6) +#define DAR_PHY_CTRL3_TMR2CMP_EN BIT(5) +#define DAR_PHY_CTRL3_TMR1CMP_EN BIT(4) +#define DAR_PHY_CTRL3_ASM_MSK BIT(2) +#define DAR_PHY_CTRL3_PB_ERR_MSK BIT(1) +#define DAR_PHY_CTRL3_WAKE_MSK BIT(0) + +/* RX_FRM_LEN bits */ +#define DAR_RX_FRAME_LENGTH_MASK (0x7F) + +/* PHY_CTRL4 bits */ +#define DAR_PHY_CTRL4_TRCV_MSK BIT(7) +#define DAR_PHY_CTRL4_TC3TMOUT BIT(6) +#define DAR_PHY_CTRL4_PANCORDNTR0 BIT(5) +#define DAR_PHY_CTRL4_CCATYPE (3) +#define DAR_PHY_CTRL4_CCATYPE_SHIFT (3) +#define DAR_PHY_CTRL4_CCATYPE_MASK (0x18) +#define DAR_PHY_CTRL4_TMRLOAD BIT(2) +#define DAR_PHY_CTRL4_PROMISCUOUS BIT(1) +#define DAR_PHY_CTRL4_TC2PRIME_EN BIT(0) + +/* SRC_CTRL bits */ +#define DAR_SRC_CTRL_INDEX (0x0F) +#define DAR_SRC_CTRL_INDEX_SHIFT (4) +#define DAR_SRC_CTRL_ACK_FRM_PND BIT(3) +#define DAR_SRC_CTRL_SRCADDR_EN BIT(2) +#define DAR_SRC_CTRL_INDEX_EN BIT(1) +#define DAR_SRC_CTRL_INDEX_DISABLE BIT(0) + +/* DAR_ASM_CTRL1 bits */ +#define DAR_ASM_CTRL1_CLEAR BIT(7) +#define DAR_ASM_CTRL1_START BIT(6) +#define DAR_ASM_CTRL1_SELFTST BIT(5) +#define DAR_ASM_CTRL1_CTR BIT(4) +#define DAR_ASM_CTRL1_CBC BIT(3) +#define DAR_ASM_CTRL1_AES BIT(2) +#define DAR_ASM_CTRL1_LOAD_MAC BIT(1) + +/* DAR_ASM_CTRL2 bits */ +#define DAR_ASM_CTRL2_DATA_REG_TYPE_SEL (7) +#define DAR_ASM_CTRL2_DATA_REG_TYPE_SEL_SHIFT (5) +#define DAR_ASM_CTRL2_TSTPAS BIT(1) + +/* DAR_CLK_OUT_CTRL bits */ +#define DAR_CLK_OUT_CTRL_EXTEND BIT(7) +#define DAR_CLK_OUT_CTRL_HIZ BIT(6) +#define DAR_CLK_OUT_CTRL_SR BIT(5) +#define DAR_CLK_OUT_CTRL_DS BIT(4) +#define DAR_CLK_OUT_CTRL_EN BIT(3) +#define DAR_CLK_OUT_CTRL_DIV (7) + +/* DAR_PWR_MODES bits */ +#define DAR_PWR_MODES_XTAL_READY BIT(5) +#define DAR_PWR_MODES_XTALEN BIT(4) +#define DAR_PWR_MODES_ASM_CLK_EN BIT(3) +#define DAR_PWR_MODES_AUTODOZE BIT(1) +#define DAR_PWR_MODES_PMC_MODE BIT(0) + +/* RX_FRAME_FILTER bits */ +#define IAR_RX_FRAME_FLT_FRM_VER (0xC0) +#define IAR_RX_FRAME_FLT_FRM_VER_SHIFT (6) +#define IAR_RX_FRAME_FLT_ACTIVE_PROMISCUOUS BIT(5) +#define IAR_RX_FRAME_FLT_NS_FT BIT(4) +#define IAR_RX_FRAME_FLT_CMD_FT BIT(3) +#define IAR_RX_FRAME_FLT_ACK_FT BIT(2) +#define IAR_RX_FRAME_FLT_DATA_FT BIT(1) +#define IAR_RX_FRAME_FLT_BEACON_FT BIT(0) + +/* DUAL_PAN_CTRL bits */ +#define IAR_DUAL_PAN_CTRL_DUAL_PAN_SAM_LVL_MSK (0xF0) +#define IAR_DUAL_PAN_CTRL_DUAL_PAN_SAM_LVL_SHIFT (4) +#define IAR_DUAL_PAN_CTRL_CURRENT_NETWORK BIT(3) +#define IAR_DUAL_PAN_CTRL_PANCORDNTR1 BIT(2) +#define IAR_DUAL_PAN_CTRL_DUAL_PAN_AUTO BIT(1) +#define IAR_DUAL_PAN_CTRL_ACTIVE_NETWORK BIT(0) + +/* DUAL_PAN_STS bits */ +#define IAR_DUAL_PAN_STS_RECD_ON_PAN1 BIT(7) +#define IAR_DUAL_PAN_STS_RECD_ON_PAN0 BIT(6) +#define IAR_DUAL_PAN_STS_DUAL_PAN_REMAIN (0x3F) + +/* CCA_CTRL bits */ +#define IAR_CCA_CTRL_AGC_FRZ_EN BIT(6) +#define IAR_CCA_CTRL_CONT_RSSI_EN BIT(5) +#define IAR_CCA_CTRL_LQI_RSSI_NOT_CORR BIT(4) +#define IAR_CCA_CTRL_CCA3_AND_NOT_OR BIT(3) +#define IAR_CCA_CTRL_POWER_COMP_EN_LQI BIT(2) +#define IAR_CCA_CTRL_POWER_COMP_EN_ED BIT(1) +#define IAR_CCA_CTRL_POWER_COMP_EN_CCA1 BIT(0) + +/* ANT_PAD_CTRL bits */ +#define IAR_ANT_PAD_CTRL_ANTX_POL (0x0F) +#define IAR_ANT_PAD_CTRL_ANTX_POL_SHIFT (4) +#define IAR_ANT_PAD_CTRL_ANTX_CTRLMODE BIT(3) +#define IAR_ANT_PAD_CTRL_ANTX_HZ BIT(2) +#define IAR_ANT_PAD_CTRL_ANTX_EN (3) + +/* MISC_PAD_CTRL bits */ +#define IAR_MISC_PAD_CTRL_MISO_HIZ_EN BIT(3) +#define IAR_MISC_PAD_CTRL_IRQ_B_OD BIT(2) +#define IAR_MISC_PAD_CTRL_NON_GPIO_DS BIT(1) +#define IAR_MISC_PAD_CTRL_ANTX_CURR (1) + +/* ANT_AGC_CTRL bits */ +#define IAR_ANT_AGC_CTRL_FAD_EN_SHIFT (0) +#define IAR_ANT_AGC_CTRL_FAD_EN_MASK (1) +#define IAR_ANT_AGC_CTRL_ANTX_SHIFT (1) +#define IAR_ANT_AGC_CTRL_ANTX_MASK BIT(AR_ANT_AGC_CTRL_ANTX_SHIFT) + +/* BSM_CTRL bits */ +#define BSM_CTRL_BSM_EN (1) + +/* SOFT_RESET bits */ +#define IAR_SOFT_RESET_SOG_RST BIT(7) +#define IAR_SOFT_RESET_REGS_RST BIT(4) +#define IAR_SOFT_RESET_PLL_RST BIT(3) +#define IAR_SOFT_RESET_TX_RST BIT(2) +#define IAR_SOFT_RESET_RX_RST BIT(1) +#define IAR_SOFT_RESET_SEQ_MGR_RST BIT(0) + +/* SEQ_MGR_CTRL bits */ +#define IAR_SEQ_MGR_CTRL_SEQ_STATE_CTRL (3) +#define IAR_SEQ_MGR_CTRL_SEQ_STATE_CTRL_SHIFT (6) +#define IAR_SEQ_MGR_CTRL_NO_RX_RECYCLE BIT(5) +#define IAR_SEQ_MGR_CTRL_LATCH_PREAMBLE BIT(4) +#define IAR_SEQ_MGR_CTRL_EVENT_TMR_DO_NOT_LATCH BIT(3) +#define IAR_SEQ_MGR_CTRL_CLR_NEW_SEQ_INHIBIT BIT(2) +#define IAR_SEQ_MGR_CTRL_PSM_LOCK_DIS BIT(1) +#define IAR_SEQ_MGR_CTRL_PLL_ABORT_OVRD BIT(0) + +/* SEQ_MGR_STS bits */ +#define IAR_SEQ_MGR_STS_TMR2_SEQ_TRIG_ARMED BIT(7) +#define IAR_SEQ_MGR_STS_RX_MODE BIT(6) +#define IAR_SEQ_MGR_STS_RX_TIMEOUT_PENDING BIT(5) +#define IAR_SEQ_MGR_STS_NEW_SEQ_INHIBIT BIT(4) +#define IAR_SEQ_MGR_STS_SEQ_IDLE BIT(3) +#define IAR_SEQ_MGR_STS_XCVSEQ_ACTUAL (7) + +/* ABORT_STS bits */ +#define IAR_ABORT_STS_PLL_ABORTED BIT(2) +#define IAR_ABORT_STS_TC3_ABORTED BIT(1) +#define IAR_ABORT_STS_SW_ABORTED BIT(0) + +/* IAR_FILTERFAIL_CODE2 bits */ +#define IAR_FILTERFAIL_CODE2_PAN_SEL BIT(7) +#define IAR_FILTERFAIL_CODE2_9_8 (3) + +/* PHY_STS bits */ +#define IAR_PHY_STS_PLL_UNLOCK BIT(7) +#define IAR_PHY_STS_PLL_LOCK_ERR BIT(6) +#define IAR_PHY_STS_PLL_LOCK BIT(5) +#define IAR_PHY_STS_CRCVALID BIT(3) +#define IAR_PHY_STS_FILTERFAIL_FLAG_SEL BIT(2) +#define IAR_PHY_STS_SFD_DET BIT(1) +#define IAR_PHY_STS_PREAMBLE_DET BIT(0) + +/* TESTMODE_CTRL bits */ +#define IAR_TEST_MODE_CTRL_HOT_ANT BIT(4) +#define IAR_TEST_MODE_CTRL_IDEAL_RSSI_EN BIT(3) +#define IAR_TEST_MODE_CTRL_IDEAL_PFC_EN BIT(2) +#define IAR_TEST_MODE_CTRL_CONTINUOUS_EN BIT(1) +#define IAR_TEST_MODE_CTRL_FPGA_EN BIT(0) + +/* DTM_CTRL1 bits */ +#define IAR_DTM_CTRL1_ATM_LOCKED BIT(7) +#define IAR_DTM_CTRL1_DTM_EN BIT(6) +#define IAR_DTM_CTRL1_PAGE5 BIT(5) +#define IAR_DTM_CTRL1_PAGE4 BIT(4) +#define IAR_DTM_CTRL1_PAGE3 BIT(3) +#define IAR_DTM_CTRL1_PAGE2 BIT(2) +#define IAR_DTM_CTRL1_PAGE1 BIT(1) +#define IAR_DTM_CTRL1_PAGE0 BIT(0) + +/* TX_MODE_CTRL */ +#define IAR_TX_MODE_CTRL_TX_INV BIT(4) +#define IAR_TX_MODE_CTRL_BT_EN BIT(3) +#define IAR_TX_MODE_CTRL_DTS2 BIT(2) +#define IAR_TX_MODE_CTRL_DTS1 BIT(1) +#define IAR_TX_MODE_CTRL_DTS0 BIT(0) + +#define TX_MODE_CTRL_DTS_MASK (7) + +#endif /* _MCR20A_H */ diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index c1f008fe4e1d..1b5dc200b573 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -35,6 +35,7 @@ void ipvlan_count_rx(const struct ipvl_dev *ipvlan, } EXPORT_SYMBOL_GPL(ipvlan_count_rx); +#if IS_ENABLED(CONFIG_IPV6) static u8 ipvlan_get_v6_hash(const void *iaddr) { const struct in6_addr *ip6_addr = iaddr; @@ -42,6 +43,12 @@ static u8 ipvlan_get_v6_hash(const void *iaddr) return __ipv6_addr_jhash(ip6_addr, ipvlan_jhash_secret) & IPVLAN_HASH_MASK; } +#else +static u8 ipvlan_get_v6_hash(const void *iaddr) +{ + return 0; +} +#endif static u8 ipvlan_get_v4_hash(const void *iaddr) { @@ -51,6 +58,23 @@ static u8 ipvlan_get_v4_hash(const void *iaddr) IPVLAN_HASH_MASK; } +static bool addr_equal(bool is_v6, struct ipvl_addr *addr, const void *iaddr) +{ + if (!is_v6 && addr->atype == IPVL_IPV4) { + struct in_addr *i4addr = (struct in_addr *)iaddr; + + return addr->ip4addr.s_addr == i4addr->s_addr; +#if IS_ENABLED(CONFIG_IPV6) + } else if (is_v6 && addr->atype == IPVL_IPV6) { + struct in6_addr *i6addr = (struct in6_addr *)iaddr; + + return ipv6_addr_equal(&addr->ip6addr, i6addr); +#endif + } + + return false; +} + static struct ipvl_addr *ipvlan_ht_addr_lookup(const struct ipvl_port *port, const void *iaddr, bool is_v6) { @@ -59,15 +83,9 @@ static struct ipvl_addr *ipvlan_ht_addr_lookup(const struct ipvl_port *port, hash = is_v6 ? ipvlan_get_v6_hash(iaddr) : ipvlan_get_v4_hash(iaddr); - hlist_for_each_entry_rcu(addr, &port->hlhead[hash], hlnode) { - if (is_v6 && addr->atype == IPVL_IPV6 && - ipv6_addr_equal(&addr->ip6addr, iaddr)) - return addr; - else if (!is_v6 && addr->atype == IPVL_IPV4 && - addr->ip4addr.s_addr == - ((struct in_addr *)iaddr)->s_addr) + hlist_for_each_entry_rcu(addr, &port->hlhead[hash], hlnode) + if (addr_equal(is_v6, addr, iaddr)) return addr; - } return NULL; } @@ -93,13 +111,9 @@ struct ipvl_addr *ipvlan_find_addr(const struct ipvl_dev *ipvlan, { struct ipvl_addr *addr; - list_for_each_entry(addr, &ipvlan->addrs, anode) { - if ((is_v6 && addr->atype == IPVL_IPV6 && - ipv6_addr_equal(&addr->ip6addr, iaddr)) || - (!is_v6 && addr->atype == IPVL_IPV4 && - addr->ip4addr.s_addr == ((struct in_addr *)iaddr)->s_addr)) + list_for_each_entry(addr, &ipvlan->addrs, anode) + if (addr_equal(is_v6, addr, iaddr)) return addr; - } return NULL; } @@ -150,6 +164,7 @@ static void *ipvlan_get_L3_hdr(struct ipvl_port *port, struct sk_buff *skb, int lyr3h = ip4h; break; } +#if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): { struct ipv6hdr *ip6h; @@ -188,6 +203,7 @@ static void *ipvlan_get_L3_hdr(struct ipvl_port *port, struct sk_buff *skb, int } break; } +#endif default: return NULL; } @@ -337,14 +353,18 @@ static struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, { struct ipvl_addr *addr = NULL; - if (addr_type == IPVL_IPV6) { + switch (addr_type) { +#if IS_ENABLED(CONFIG_IPV6) + case IPVL_IPV6: { struct ipv6hdr *ip6h; struct in6_addr *i6addr; ip6h = (struct ipv6hdr *)lyr3h; i6addr = use_dest ? &ip6h->daddr : &ip6h->saddr; addr = ipvlan_ht_addr_lookup(port, i6addr, true); - } else if (addr_type == IPVL_ICMPV6) { + break; + } + case IPVL_ICMPV6: { struct nd_msg *ndmh; struct in6_addr *i6addr; @@ -356,14 +376,19 @@ static struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, i6addr = &ndmh->target; addr = ipvlan_ht_addr_lookup(port, i6addr, true); } - } else if (addr_type == IPVL_IPV4) { + break; + } +#endif + case IPVL_IPV4: { struct iphdr *ip4h; __be32 *i4addr; ip4h = (struct iphdr *)lyr3h; i4addr = use_dest ? &ip4h->daddr : &ip4h->saddr; addr = ipvlan_ht_addr_lookup(port, i4addr, false); - } else if (addr_type == IPVL_ARP) { + break; + } + case IPVL_ARP: { struct arphdr *arph; unsigned char *arp_ptr; __be32 dip; @@ -377,6 +402,8 @@ static struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, memcpy(&dip, arp_ptr, 4); addr = ipvlan_ht_addr_lookup(port, &dip, false); + break; + } } return addr; @@ -420,6 +447,7 @@ out: return ret; } +#if IS_ENABLED(CONFIG_IPV6) static int ipvlan_process_v6_outbound(struct sk_buff *skb) { const struct ipv6hdr *ip6h = ipv6_hdr(skb); @@ -456,6 +484,12 @@ err: out: return ret; } +#else +static int ipvlan_process_v6_outbound(struct sk_buff *skb) +{ + return NET_XMIT_DROP; +} +#endif static int ipvlan_process_outbound(struct sk_buff *skb) { @@ -759,6 +793,7 @@ struct sk_buff *ipvlan_l3_rcv(struct net_device *dev, struct sk_buff *skb, goto out; break; } +#if IS_ENABLED(CONFIG_IPV6) case AF_INET6: { struct dst_entry *dst; @@ -778,6 +813,7 @@ struct sk_buff *ipvlan_l3_rcv(struct net_device *dev, struct sk_buff *skb, skb_dst_set(skb, dst); break; } +#endif default: break; } diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 2469df118fbf..d05b902c925b 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -22,12 +22,14 @@ static const struct nf_hook_ops ipvl_nfops[] = { .hooknum = NF_INET_LOCAL_IN, .priority = INT_MAX, }, +#if IS_ENABLED(CONFIG_IPV6) { .hook = ipvlan_nf_input, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = INT_MAX, }, +#endif }; static const struct l3mdev_ops ipvl_l3mdev_ops = { @@ -800,12 +802,14 @@ static int ipvlan_add_addr(struct ipvl_dev *ipvlan, void *iaddr, bool is_v6) return -ENOMEM; addr->master = ipvlan; - if (is_v6) { - memcpy(&addr->ip6addr, iaddr, sizeof(struct in6_addr)); - addr->atype = IPVL_IPV6; - } else { + if (!is_v6) { memcpy(&addr->ip4addr, iaddr, sizeof(struct in_addr)); addr->atype = IPVL_IPV4; +#if IS_ENABLED(CONFIG_IPV6) + } else { + memcpy(&addr->ip6addr, iaddr, sizeof(struct in6_addr)); + addr->atype = IPVL_IPV6; +#endif } list_add_tail(&addr->anode, &ipvlan->addrs); @@ -833,6 +837,20 @@ static void ipvlan_del_addr(struct ipvl_dev *ipvlan, void *iaddr, bool is_v6) return; } +static bool ipvlan_is_valid_dev(const struct net_device *dev) +{ + struct ipvl_dev *ipvlan = netdev_priv(dev); + + if (!netif_is_ipvlan(dev)) + return false; + + if (!ipvlan || !ipvlan->port) + return false; + + return true; +} + +#if IS_ENABLED(CONFIG_IPV6) static int ipvlan_add_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr) { if (ipvlan_addr_busy(ipvlan->port, ip6_addr, true)) { @@ -850,19 +868,6 @@ static void ipvlan_del_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr) return ipvlan_del_addr(ipvlan, ip6_addr, true); } -static bool ipvlan_is_valid_dev(const struct net_device *dev) -{ - struct ipvl_dev *ipvlan = netdev_priv(dev); - - if (!netif_is_ipvlan(dev)) - return false; - - if (!ipvlan || !ipvlan->port) - return false; - - return true; -} - static int ipvlan_addr6_event(struct notifier_block *unused, unsigned long event, void *ptr) { @@ -913,6 +918,7 @@ static int ipvlan_addr6_validator_event(struct notifier_block *unused, return NOTIFY_OK; } +#endif static int ipvlan_add_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr) { @@ -993,6 +999,7 @@ static struct notifier_block ipvlan_notifier_block __read_mostly = { .notifier_call = ipvlan_device_event, }; +#if IS_ENABLED(CONFIG_IPV6) static struct notifier_block ipvlan_addr6_notifier_block __read_mostly = { .notifier_call = ipvlan_addr6_event, }; @@ -1000,6 +1007,7 @@ static struct notifier_block ipvlan_addr6_notifier_block __read_mostly = { static struct notifier_block ipvlan_addr6_vtor_notifier_block __read_mostly = { .notifier_call = ipvlan_addr6_validator_event, }; +#endif static void ipvlan_ns_exit(struct net *net) { @@ -1016,6 +1024,7 @@ static struct pernet_operations ipvlan_net_ops = { .id = &ipvlan_netid, .size = sizeof(struct ipvlan_netns), .exit = ipvlan_ns_exit, + .async = true, }; static int __init ipvlan_init_module(void) @@ -1024,9 +1033,11 @@ static int __init ipvlan_init_module(void) ipvlan_init_secret(); register_netdevice_notifier(&ipvlan_notifier_block); +#if IS_ENABLED(CONFIG_IPV6) register_inet6addr_notifier(&ipvlan_addr6_notifier_block); register_inet6addr_validator_notifier( &ipvlan_addr6_vtor_notifier_block); +#endif register_inetaddr_notifier(&ipvlan_addr4_notifier_block); register_inetaddr_validator_notifier(&ipvlan_addr4_vtor_notifier_block); @@ -1045,9 +1056,11 @@ error: unregister_inetaddr_notifier(&ipvlan_addr4_notifier_block); unregister_inetaddr_validator_notifier( &ipvlan_addr4_vtor_notifier_block); +#if IS_ENABLED(CONFIG_IPV6) unregister_inet6addr_notifier(&ipvlan_addr6_notifier_block); unregister_inet6addr_validator_notifier( &ipvlan_addr6_vtor_notifier_block); +#endif unregister_netdevice_notifier(&ipvlan_notifier_block); return err; } @@ -1060,9 +1073,11 @@ static void __exit ipvlan_cleanup_module(void) unregister_inetaddr_notifier(&ipvlan_addr4_notifier_block); unregister_inetaddr_validator_notifier( &ipvlan_addr4_vtor_notifier_block); +#if IS_ENABLED(CONFIG_IPV6) unregister_inet6addr_notifier(&ipvlan_addr6_notifier_block); unregister_inet6addr_validator_notifier( &ipvlan_addr6_vtor_notifier_block); +#endif } module_init(ipvlan_init_module); diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index 30612497643c..b97a907ea5aa 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -230,4 +230,5 @@ out: /* Registered in net/core/dev.c */ struct pernet_operations __net_initdata loopback_net_ops = { .init = loopback_net_init, + .async = true, }; diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index a0f2be81d52e..8fc02d9db3d0 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -1451,7 +1451,7 @@ destroy_macvlan_port: /* the macvlan port may be freed by macvlan_uninit when fail to register. * so we destroy the macvlan port only when it's valid. */ - if (create && macvlan_port_get_rtnl(dev)) + if (create && macvlan_port_get_rtnl(lowerdev)) macvlan_port_destroy(port->dev); return err; } diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index ab58224f897f..b3935778b19f 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -75,6 +75,8 @@ #define DP83867_IO_MUX_CFG_IO_IMPEDANCE_MAX 0x0 #define DP83867_IO_MUX_CFG_IO_IMPEDANCE_MIN 0x1f +#define DP83867_IO_MUX_CFG_CLK_O_SEL_MASK (0x1f << 8) +#define DP83867_IO_MUX_CFG_CLK_O_SEL_SHIFT 8 /* CFG4 bits */ #define DP83867_CFG4_PORT_MIRROR_EN BIT(0) @@ -92,6 +94,7 @@ struct dp83867_private { int io_impedance; int port_mirroring; bool rxctrl_strap_quirk; + int clk_output_sel; }; static int dp83867_ack_interrupt(struct phy_device *phydev) @@ -160,6 +163,14 @@ static int dp83867_of_init(struct phy_device *phydev) dp83867->io_impedance = -EINVAL; /* Optional configuration */ + ret = of_property_read_u32(of_node, "ti,clk-output-sel", + &dp83867->clk_output_sel); + if (ret || dp83867->clk_output_sel > DP83867_CLK_O_SEL_REF_CLK) + /* Keep the default value if ti,clk-output-sel is not set + * or too high + */ + dp83867->clk_output_sel = DP83867_CLK_O_SEL_REF_CLK; + if (of_property_read_bool(of_node, "ti,max-output-impedance")) dp83867->io_impedance = DP83867_IO_MUX_CFG_IO_IMPEDANCE_MAX; else if (of_property_read_bool(of_node, "ti,min-output-impedance")) @@ -295,6 +306,14 @@ static int dp83867_config_init(struct phy_device *phydev) if (dp83867->port_mirroring != DP83867_PORT_MIRROING_KEEP) dp83867_config_port_mirroring(phydev); + /* Clock output selection if muxing property is set */ + if (dp83867->clk_output_sel != DP83867_CLK_O_SEL_REF_CLK) { + val = phy_read_mmd(phydev, DP83867_DEVADDR, DP83867_IO_MUX_CFG); + val &= ~DP83867_IO_MUX_CFG_CLK_O_SEL_MASK; + val |= (dp83867->clk_output_sel << DP83867_IO_MUX_CFG_CLK_O_SEL_SHIFT); + phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_IO_MUX_CFG, val); + } + return 0; } diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index b13eed21c87d..d39ae77707ef 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1382,7 +1382,7 @@ int genphy_setup_forced(struct phy_device *phydev) ctl |= BMCR_FULLDPLX; return phy_modify(phydev, MII_BMCR, - BMCR_LOOPBACK | BMCR_ISOLATE | BMCR_PDOWN, ctl); + ~(BMCR_LOOPBACK | BMCR_ISOLATE | BMCR_PDOWN), ctl); } EXPORT_SYMBOL(genphy_setup_forced); diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 255a5def56e9..a393c1dff7dc 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -971,6 +971,7 @@ static struct pernet_operations ppp_net_ops = { .exit = ppp_exit_net, .id = &ppp_net_id, .size = sizeof(struct ppp_net), + .async = true, }; static int ppp_unit_register(struct ppp *ppp, int unit, bool ifname_is_set) diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index 5aa59f41bf8c..c10e6181a2f0 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -714,7 +714,7 @@ err_put: } static int pppoe_getname(struct socket *sock, struct sockaddr *uaddr, - int *usockaddr_len, int peer) + int peer) { int len = sizeof(struct sockaddr_pppox); struct sockaddr_pppox sp; @@ -726,9 +726,7 @@ static int pppoe_getname(struct socket *sock, struct sockaddr *uaddr, memcpy(uaddr, &sp, len); - *usockaddr_len = len; - - return 0; + return len; } static int pppoe_ioctl(struct socket *sock, unsigned int cmd, @@ -1163,6 +1161,7 @@ static struct pernet_operations pppoe_net_ops = { .exit = pppoe_exit_net, .id = &pppoe_net_id, .size = sizeof(struct pppoe_net), + .async = true, }; static int __init pppoe_init(void) diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c index 6dde9a0cfe76..8249d46a7844 100644 --- a/drivers/net/ppp/pptp.c +++ b/drivers/net/ppp/pptp.c @@ -483,7 +483,7 @@ static int pptp_connect(struct socket *sock, struct sockaddr *uservaddr, } static int pptp_getname(struct socket *sock, struct sockaddr *uaddr, - int *usockaddr_len, int peer) + int peer) { int len = sizeof(struct sockaddr_pppox); struct sockaddr_pppox sp; @@ -496,9 +496,7 @@ static int pptp_getname(struct socket *sock, struct sockaddr *uaddr, memcpy(uaddr, &sp, len); - *usockaddr_len = len; - - return 0; + return len; } static int pptp_release(struct socket *sock) diff --git a/drivers/net/thunderbolt.c b/drivers/net/thunderbolt.c index ca5e375de27c..e0d6760f3219 100644 --- a/drivers/net/thunderbolt.c +++ b/drivers/net/thunderbolt.c @@ -166,6 +166,8 @@ struct tbnet_ring { * @connected_work: Worker that finalizes the ThunderboltIP connection * setup and enables DMA paths for high speed data * transfers + * @disconnect_work: Worker that handles tearing down the ThunderboltIP + * connection * @rx_hdr: Copy of the currently processed Rx frame. Used when a * network packet consists of multiple Thunderbolt frames. * In host byte order. @@ -190,6 +192,7 @@ struct tbnet { int login_retries; struct delayed_work login_work; struct work_struct connected_work; + struct work_struct disconnect_work; struct thunderbolt_ip_frame_header rx_hdr; struct tbnet_ring rx_ring; atomic_t frame_id; @@ -445,7 +448,7 @@ static int tbnet_handle_packet(const void *buf, size_t size, void *data) case TBIP_LOGOUT: ret = tbnet_logout_response(net, route, sequence, command_id); if (!ret) - tbnet_tear_down(net, false); + queue_work(system_long_wq, &net->disconnect_work); break; default: @@ -659,6 +662,13 @@ static void tbnet_login_work(struct work_struct *work) } } +static void tbnet_disconnect_work(struct work_struct *work) +{ + struct tbnet *net = container_of(work, typeof(*net), disconnect_work); + + tbnet_tear_down(net, false); +} + static bool tbnet_check_frame(struct tbnet *net, const struct tbnet_frame *tf, const struct thunderbolt_ip_frame_header *hdr) { @@ -881,6 +891,7 @@ static int tbnet_stop(struct net_device *dev) napi_disable(&net->napi); + cancel_work_sync(&net->disconnect_work); tbnet_tear_down(net, true); tb_ring_free(net->rx_ring.ring); @@ -1195,6 +1206,7 @@ static int tbnet_probe(struct tb_service *svc, const struct tb_service_id *id) net = netdev_priv(dev); INIT_DELAYED_WORK(&net->login_work, tbnet_login_work); INIT_WORK(&net->connected_work, tbnet_connected_work); + INIT_WORK(&net->disconnect_work, tbnet_disconnect_work); mutex_init(&net->connection_lock); atomic_set(&net->command_id, 0); atomic_set(&net->frame_id, 0); @@ -1270,10 +1282,7 @@ static int __maybe_unused tbnet_suspend(struct device *dev) stop_login(net); if (netif_running(net->dev)) { netif_device_detach(net->dev); - tb_ring_stop(net->rx_ring.ring); - tb_ring_stop(net->tx_ring.ring); - tbnet_free_buffers(&net->rx_ring); - tbnet_free_buffers(&net->tx_ring); + tbnet_tear_down(net, true); } return 0; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 81e6cc951e7f..d531954512c7 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -78,6 +78,7 @@ #include <linux/mutex.h> #include <linux/uaccess.h> +#include <linux/proc_fs.h> /* Uncomment to enable debugging */ /* #define TUN_DEBUG 1 */ @@ -1489,27 +1490,23 @@ static struct sk_buff *tun_napi_alloc_frags(struct tun_file *tfile, skb->truesize += skb->data_len; for (i = 1; i < it->nr_segs; i++) { + struct page_frag *pfrag = ¤t->task_frag; size_t fragsz = it->iov[i].iov_len; - unsigned long offset; - struct page *page; - void *data; if (fragsz == 0 || fragsz > PAGE_SIZE) { err = -EINVAL; goto free; } - local_bh_disable(); - data = napi_alloc_frag(fragsz); - local_bh_enable(); - if (!data) { + if (!skb_page_frag_refill(fragsz, pfrag, GFP_KERNEL)) { err = -ENOMEM; goto free; } - page = virt_to_head_page(data); - offset = data - page_address(page); - skb_fill_page_desc(skb, i - 1, page, offset, fragsz); + skb_fill_page_desc(skb, i - 1, pfrag->page, + pfrag->offset, fragsz); + page_ref_inc(pfrag->page); + pfrag->offset += fragsz; } return skb; @@ -2290,11 +2287,67 @@ static int tun_validate(struct nlattr *tb[], struct nlattr *data[], return -EINVAL; } +static size_t tun_get_size(const struct net_device *dev) +{ + BUILD_BUG_ON(sizeof(u32) != sizeof(uid_t)); + BUILD_BUG_ON(sizeof(u32) != sizeof(gid_t)); + + return nla_total_size(sizeof(uid_t)) + /* OWNER */ + nla_total_size(sizeof(gid_t)) + /* GROUP */ + nla_total_size(sizeof(u8)) + /* TYPE */ + nla_total_size(sizeof(u8)) + /* PI */ + nla_total_size(sizeof(u8)) + /* VNET_HDR */ + nla_total_size(sizeof(u8)) + /* PERSIST */ + nla_total_size(sizeof(u8)) + /* MULTI_QUEUE */ + nla_total_size(sizeof(u32)) + /* NUM_QUEUES */ + nla_total_size(sizeof(u32)) + /* NUM_DISABLED_QUEUES */ + 0; +} + +static int tun_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct tun_struct *tun = netdev_priv(dev); + + if (nla_put_u8(skb, IFLA_TUN_TYPE, tun->flags & TUN_TYPE_MASK)) + goto nla_put_failure; + if (uid_valid(tun->owner) && + nla_put_u32(skb, IFLA_TUN_OWNER, + from_kuid_munged(current_user_ns(), tun->owner))) + goto nla_put_failure; + if (gid_valid(tun->group) && + nla_put_u32(skb, IFLA_TUN_GROUP, + from_kgid_munged(current_user_ns(), tun->group))) + goto nla_put_failure; + if (nla_put_u8(skb, IFLA_TUN_PI, !(tun->flags & IFF_NO_PI))) + goto nla_put_failure; + if (nla_put_u8(skb, IFLA_TUN_VNET_HDR, !!(tun->flags & IFF_VNET_HDR))) + goto nla_put_failure; + if (nla_put_u8(skb, IFLA_TUN_PERSIST, !!(tun->flags & IFF_PERSIST))) + goto nla_put_failure; + if (nla_put_u8(skb, IFLA_TUN_MULTI_QUEUE, + !!(tun->flags & IFF_MULTI_QUEUE))) + goto nla_put_failure; + if (tun->flags & IFF_MULTI_QUEUE) { + if (nla_put_u32(skb, IFLA_TUN_NUM_QUEUES, tun->numqueues)) + goto nla_put_failure; + if (nla_put_u32(skb, IFLA_TUN_NUM_DISABLED_QUEUES, + tun->numdisabled)) + goto nla_put_failure; + } + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + static struct rtnl_link_ops tun_link_ops __read_mostly = { .kind = DRV_NAME, .priv_size = sizeof(struct tun_struct), .setup = tun_setup, .validate = tun_validate, + .get_size = tun_get_size, + .fill_info = tun_fill_info, }; static void tun_sock_write_space(struct sock *sk) @@ -2793,6 +2846,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, struct tun_struct *tun; void __user* argp = (void __user*)arg; struct ifreq ifr; + struct net *net; kuid_t owner; kgid_t group; int sndbuf; @@ -2801,7 +2855,8 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, int le; int ret; - if (cmd == TUNSETIFF || cmd == TUNSETQUEUE || _IOC_TYPE(cmd) == SOCK_IOC_TYPE) { + if (cmd == TUNSETIFF || cmd == TUNSETQUEUE || + (_IOC_TYPE(cmd) == SOCK_IOC_TYPE && cmd != SIOCGSKNS)) { if (copy_from_user(&ifr, argp, ifreq_len)) return -EFAULT; } else { @@ -2821,6 +2876,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, rtnl_lock(); tun = tun_get(tfile); + net = sock_net(&tfile->sk); if (cmd == TUNSETIFF) { ret = -EEXIST; if (tun) @@ -2828,7 +2884,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, ifr.ifr_name[IFNAMSIZ-1] = '\0'; - ret = tun_set_iff(sock_net(&tfile->sk), file, &ifr); + ret = tun_set_iff(net, file, &ifr); if (ret) goto unlock; @@ -2850,6 +2906,14 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, tfile->ifindex = ifindex; goto unlock; } + if (cmd == SIOCGSKNS) { + ret = -EPERM; + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + goto unlock; + + ret = open_related_ns(&net->ns, get_net_ns); + goto unlock; + } ret = -EBADFD; if (!tun) diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c index d0a113743195..7a6a1fe79309 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -954,10 +954,11 @@ static int smsc75xx_set_features(struct net_device *netdev, /* it's racing here! */ ret = smsc75xx_write_reg(dev, RFE_CTL, pdata->rfe_ctl); - if (ret < 0) + if (ret < 0) { netdev_warn(dev->net, "Error writing RFE_CTL\n"); - - return ret; + return ret; + } + return 0; } static int smsc75xx_wait_ready(struct usbnet *dev, int in_pm) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 626c27352ae2..9bb9e562b893 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -443,12 +443,8 @@ static bool __virtnet_xdp_xmit(struct virtnet_info *vi, sg_init_one(sq->sg, xdp->data, xdp->data_end - xdp->data); err = virtqueue_add_outbuf(sq->vq, sq->sg, 1, xdp->data, GFP_ATOMIC); - if (unlikely(err)) { - struct page *page = virt_to_head_page(xdp->data); - - put_page(page); - return false; - } + if (unlikely(err)) + return false; /* Caller handle free/refcnt */ return true; } @@ -456,8 +452,18 @@ static bool __virtnet_xdp_xmit(struct virtnet_info *vi, static int virtnet_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp) { struct virtnet_info *vi = netdev_priv(dev); - bool sent = __virtnet_xdp_xmit(vi, xdp); + struct receive_queue *rq = vi->rq; + struct bpf_prog *xdp_prog; + bool sent; + /* Only allow ndo_xdp_xmit if XDP is loaded on dev, as this + * indicate XDP resources have been successfully allocated. + */ + xdp_prog = rcu_dereference(rq->xdp_prog); + if (!xdp_prog) + return -ENXIO; + + sent = __virtnet_xdp_xmit(vi, xdp); if (!sent) return -ENOSPC; return 0; @@ -546,8 +552,11 @@ static struct sk_buff *receive_small(struct net_device *dev, unsigned int buflen = SKB_DATA_ALIGN(GOOD_PACKET_LEN + headroom) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); struct page *page = virt_to_head_page(buf); - unsigned int delta = 0, err; + unsigned int delta = 0; struct page *xdp_page; + bool sent; + int err; + len -= vi->hdr_len; rcu_read_lock(); @@ -558,7 +567,7 @@ static struct sk_buff *receive_small(struct net_device *dev, void *orig_data; u32 act; - if (unlikely(hdr->hdr.gso_type || hdr->hdr.flags)) + if (unlikely(hdr->hdr.gso_type)) goto err_xdp; if (unlikely(xdp_headroom < virtnet_get_headroom(vi))) { @@ -596,16 +605,19 @@ static struct sk_buff *receive_small(struct net_device *dev, delta = orig_data - xdp.data; break; case XDP_TX: - if (unlikely(!__virtnet_xdp_xmit(vi, &xdp))) + sent = __virtnet_xdp_xmit(vi, &xdp); + if (unlikely(!sent)) { trace_xdp_exception(vi->dev, xdp_prog, act); - else - *xdp_xmit = true; + goto err_xdp; + } + *xdp_xmit = true; rcu_read_unlock(); goto xdp_xmit; case XDP_REDIRECT: err = xdp_do_redirect(dev, &xdp, xdp_prog); - if (!err) - *xdp_xmit = true; + if (err) + goto err_xdp; + *xdp_xmit = true; rcu_read_unlock(); goto xdp_xmit; default: @@ -677,7 +689,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, struct bpf_prog *xdp_prog; unsigned int truesize; unsigned int headroom = mergeable_ctx_to_headroom(ctx); - int err; + bool sent; head_skb = NULL; @@ -746,20 +758,18 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, } break; case XDP_TX: - if (unlikely(!__virtnet_xdp_xmit(vi, &xdp))) + sent = __virtnet_xdp_xmit(vi, &xdp); + if (unlikely(!sent)) { trace_xdp_exception(vi->dev, xdp_prog, act); - else - *xdp_xmit = true; + if (unlikely(xdp_page != page)) + put_page(xdp_page); + goto err_xdp; + } + *xdp_xmit = true; if (unlikely(xdp_page != page)) goto err_xdp; rcu_read_unlock(); goto xdp_xmit; - case XDP_REDIRECT: - err = xdp_do_redirect(dev, &xdp, xdp_prog); - if (!err) - *xdp_xmit = true; - rcu_read_unlock(); - goto xdp_xmit; default: bpf_warn_invalid_xdp_action(act); case XDP_ABORTED: diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 139c61c8244a..e459e601c57f 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -736,7 +736,6 @@ static int vrf_rtable_create(struct net_device *dev) return -ENOMEM; rth->dst.output = vrf_output; - rth->rt_table_id = vrf->tb_id; rcu_assign_pointer(vrf->rth, rth); @@ -1146,6 +1145,7 @@ static inline size_t vrf_fib_rule_nl_size(void) sz = NLMSG_ALIGN(sizeof(struct fib_rule_hdr)); sz += nla_total_size(sizeof(u8)); /* FRA_L3MDEV */ sz += nla_total_size(sizeof(u32)); /* FRA_PRIORITY */ + sz += nla_total_size(sizeof(u8)); /* FRA_PROTOCOL */ return sz; } @@ -1176,6 +1176,9 @@ static int vrf_fib_rule(const struct net_device *dev, __u8 family, bool add_it) frh->family = family; frh->action = FR_ACT_TO_TBL; + if (nla_put_u8(skb, FRA_PROTOCOL, RTPROT_KERNEL)) + goto nla_put_failure; + if (nla_put_u8(skb, FRA_L3MDEV, 1)) goto nla_put_failure; @@ -1431,6 +1434,7 @@ static struct pernet_operations vrf_net_ops __net_initdata = { .init = vrf_netns_init, .id = &vrf_net_id, .size = sizeof(bool), + .async = true, }; static int __init vrf_init_module(void) diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index fab7a4db249e..aa5f034d6ad1 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -3752,6 +3752,7 @@ static struct pernet_operations vxlan_net_ops = { .exit_batch = vxlan_exit_batch_net, .id = &vxlan_net_id, .size = sizeof(struct vxlan_net), + .async = true, }; static int __init vxlan_init_module(void) diff --git a/drivers/net/wireless/ath/wil6210/cfg80211.c b/drivers/net/wireless/ath/wil6210/cfg80211.c index 768f63f38341..b799a5384abb 100644 --- a/drivers/net/wireless/ath/wil6210/cfg80211.c +++ b/drivers/net/wireless/ath/wil6210/cfg80211.c @@ -1599,7 +1599,8 @@ static void wil_probe_client_handle(struct wil6210_priv *wil, */ bool alive = (sta->status == wil_sta_connected); - cfg80211_probe_status(ndev, sta->addr, req->cookie, alive, GFP_KERNEL); + cfg80211_probe_status(ndev, sta->addr, req->cookie, alive, + 0, false, GFP_KERNEL); } static struct list_head *next_probe_client(struct wil6210_priv *wil) diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 1cf22e62e3dd..3c64afa161bf 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -493,6 +493,7 @@ static LIST_HEAD(hwsim_radios); static struct workqueue_struct *hwsim_wq; static struct rhashtable hwsim_radios_rht; static int hwsim_radio_idx; +static int hwsim_radios_generation = 1; static struct platform_driver mac80211_hwsim_driver = { .driver = { @@ -637,6 +638,7 @@ static const struct nla_policy hwsim_genl_policy[HWSIM_ATTR_MAX + 1] = { [HWSIM_ATTR_RADIO_NAME] = { .type = NLA_STRING }, [HWSIM_ATTR_NO_VIF] = { .type = NLA_FLAG }, [HWSIM_ATTR_FREQ] = { .type = NLA_U32 }, + [HWSIM_ATTR_PERM_ADDR] = { .type = NLA_UNSPEC, .len = ETH_ALEN }, }; static void mac80211_hwsim_tx_frame(struct ieee80211_hw *hw, @@ -2408,6 +2410,7 @@ struct hwsim_new_radio_params { bool destroy_on_close; const char *hwname; bool no_vif; + const u8 *perm_addr; }; static void hwsim_mcast_config_msg(struct sk_buff *mcast_skb, @@ -2572,15 +2575,25 @@ static int mac80211_hwsim_new_radio(struct genl_info *info, skb_queue_head_init(&data->pending); SET_IEEE80211_DEV(hw, data->dev); - eth_zero_addr(addr); - addr[0] = 0x02; - addr[3] = idx >> 8; - addr[4] = idx; - memcpy(data->addresses[0].addr, addr, ETH_ALEN); - memcpy(data->addresses[1].addr, addr, ETH_ALEN); - data->addresses[1].addr[0] |= 0x40; - hw->wiphy->n_addresses = 2; - hw->wiphy->addresses = data->addresses; + if (!param->perm_addr) { + eth_zero_addr(addr); + addr[0] = 0x02; + addr[3] = idx >> 8; + addr[4] = idx; + memcpy(data->addresses[0].addr, addr, ETH_ALEN); + /* Why need here second address ? */ + data->addresses[1].addr[0] |= 0x40; + memcpy(data->addresses[1].addr, addr, ETH_ALEN); + hw->wiphy->n_addresses = 2; + hw->wiphy->addresses = data->addresses; + /* possible address clash is checked at hash table insertion */ + } else { + memcpy(data->addresses[0].addr, param->perm_addr, ETH_ALEN); + /* compatibility with automatically generated mac addr */ + memcpy(data->addresses[1].addr, param->perm_addr, ETH_ALEN); + hw->wiphy->n_addresses = 2; + hw->wiphy->addresses = data->addresses; + } data->channels = param->channels; data->use_chanctx = param->use_chanctx; @@ -2785,13 +2798,17 @@ static int mac80211_hwsim_new_radio(struct genl_info *info, err = rhashtable_insert_fast(&hwsim_radios_rht, &data->rht, hwsim_rht_params); if (err < 0) { - pr_debug("mac80211_hwsim: radio index %d already present\n", - idx); + if (info) { + GENL_SET_ERR_MSG(info, "perm addr already present"); + NL_SET_BAD_ATTR(info->extack, + info->attrs[HWSIM_ATTR_PERM_ADDR]); + } spin_unlock_bh(&hwsim_radio_lock); goto failed_final_insert; } list_add_tail(&data->list, &hwsim_radios); + hwsim_radios_generation++; spin_unlock_bh(&hwsim_radio_lock); if (idx > 0) @@ -3210,6 +3227,19 @@ static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info) param.regd = hwsim_world_regdom_custom[idx]; } + if (info->attrs[HWSIM_ATTR_PERM_ADDR]) { + if (!is_valid_ether_addr( + nla_data(info->attrs[HWSIM_ATTR_PERM_ADDR]))) { + GENL_SET_ERR_MSG(info,"MAC is no valid source addr"); + NL_SET_BAD_ATTR(info->extack, + info->attrs[HWSIM_ATTR_PERM_ADDR]); + return -EINVAL; + } + + + param.perm_addr = nla_data(info->attrs[HWSIM_ATTR_PERM_ADDR]); + } + ret = mac80211_hwsim_new_radio(info, ¶m); kfree(hwname); return ret; @@ -3249,6 +3279,7 @@ static int hwsim_del_radio_nl(struct sk_buff *msg, struct genl_info *info) list_del(&data->list); rhashtable_remove_fast(&hwsim_radios_rht, &data->rht, hwsim_rht_params); + hwsim_radios_generation++; spin_unlock_bh(&hwsim_radio_lock); mac80211_hwsim_del_radio(data, wiphy_name(data->hw->wiphy), info); @@ -3305,17 +3336,19 @@ out_err: static int hwsim_dump_radio_nl(struct sk_buff *skb, struct netlink_callback *cb) { - int idx = cb->args[0]; + int last_idx = cb->args[0]; struct mac80211_hwsim_data *data = NULL; - int res; + int res = 0; + void *hdr; spin_lock_bh(&hwsim_radio_lock); + cb->seq = hwsim_radios_generation; - if (idx == hwsim_radio_idx) + if (last_idx >= hwsim_radio_idx-1) goto done; list_for_each_entry(data, &hwsim_radios, list) { - if (data->idx < idx) + if (data->idx <= last_idx) continue; if (!net_eq(wiphy_net(data->hw->wiphy), sock_net(skb->sk))) @@ -3328,14 +3361,25 @@ static int hwsim_dump_radio_nl(struct sk_buff *skb, if (res < 0) break; - idx = data->idx + 1; + last_idx = data->idx; } - cb->args[0] = idx; + cb->args[0] = last_idx; + + /* list changed, but no new element sent, set interrupted flag */ + if (skb->len == 0 && cb->prev_seq && cb->seq != cb->prev_seq) { + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, &hwsim_genl_family, + NLM_F_MULTI, HWSIM_CMD_GET_RADIO); + if (!hdr) + res = -EMSGSIZE; + genl_dump_check_consistent(cb, hdr); + genlmsg_end(skb, hdr); + } done: spin_unlock_bh(&hwsim_radio_lock); - return skb->len; + return res ?: skb->len; } /* Generic Netlink operations array */ @@ -3393,6 +3437,7 @@ static void destroy_radio(struct work_struct *work) struct mac80211_hwsim_data *data = container_of(work, struct mac80211_hwsim_data, destroy_work); + hwsim_radios_generation++; mac80211_hwsim_del_radio(data, wiphy_name(data->hw->wiphy), NULL); } @@ -3516,7 +3561,7 @@ static int __init init_mac80211_hwsim(void) spin_lock_init(&hwsim_radio_lock); - hwsim_wq = alloc_workqueue("hwsim_wq",WQ_MEM_RECLAIM,0); + hwsim_wq = alloc_workqueue("hwsim_wq", 0, 0); if (!hwsim_wq) return -ENOMEM; rhashtable_init(&hwsim_radios_rht, &hwsim_rht_params); diff --git a/drivers/net/wireless/mac80211_hwsim.h b/drivers/net/wireless/mac80211_hwsim.h index a96a79c1eff5..0fe3199f8c72 100644 --- a/drivers/net/wireless/mac80211_hwsim.h +++ b/drivers/net/wireless/mac80211_hwsim.h @@ -68,7 +68,12 @@ enum hwsim_tx_control_flags { * %HWSIM_ATTR_SIGNAL, %HWSIM_ATTR_COOKIE * @HWSIM_CMD_NEW_RADIO: create a new radio with the given parameters, * returns the radio ID (>= 0) or negative on errors, if successful - * then multicast the result + * then multicast the result, uses optional parameter: + * %HWSIM_ATTR_REG_STRICT_REG, %HWSIM_ATTR_SUPPORT_P2P_DEVICE, + * %HWSIM_ATTR_DESTROY_RADIO_ON_CLOSE, %HWSIM_ATTR_CHANNELS, + * %HWSIM_ATTR_NO_VIF, %HWSIM_ATTR_RADIO_NAME, %HWSIM_ATTR_USE_CHANCTX, + * %HWSIM_ATTR_REG_HINT_ALPHA2, %HWSIM_ATTR_REG_CUSTOM_REG, + * %HWSIM_ATTR_PERM_ADDR * @HWSIM_CMD_DEL_RADIO: destroy a radio, reply is multicasted * @HWSIM_CMD_GET_RADIO: fetch information about existing radios, uses: * %HWSIM_ATTR_RADIO_ID @@ -126,6 +131,7 @@ enum { * @HWSIM_ATTR_FREQ: Frequency at which packet is transmitted or received. * @HWSIM_ATTR_TX_INFO_FLAGS: additional flags for corresponding * rates of %HWSIM_ATTR_TX_INFO + * @HWSIM_ATTR_PERM_ADDR: permanent mac address of new radio * @__HWSIM_ATTR_MAX: enum limit */ @@ -153,6 +159,7 @@ enum { HWSIM_ATTR_FREQ, HWSIM_ATTR_PAD, HWSIM_ATTR_TX_INFO_FLAGS, + HWSIM_ATTR_PERM_ADDR, __HWSIM_ATTR_MAX, }; #define HWSIM_ATTR_MAX (__HWSIM_ATTR_MAX - 1) diff --git a/drivers/net/xen-netback/rx.c b/drivers/net/xen-netback/rx.c index b1cf7c6f407a..ef5887037b22 100644 --- a/drivers/net/xen-netback/rx.c +++ b/drivers/net/xen-netback/rx.c @@ -419,7 +419,7 @@ static void xenvif_rx_extra_slot(struct xenvif_queue *queue, BUG(); } -void xenvif_rx_skb(struct xenvif_queue *queue) +static void xenvif_rx_skb(struct xenvif_queue *queue) { struct xenvif_pkt_state pkt; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index f431c32774f3..0fe7ea35c221 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -120,8 +120,12 @@ int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl) int ret; ret = nvme_reset_ctrl(ctrl); - if (!ret) + if (!ret) { flush_work(&ctrl->reset_work); + if (ctrl->state != NVME_CTRL_LIVE) + ret = -ENETRESET; + } + return ret; } EXPORT_SYMBOL_GPL(nvme_reset_ctrl_sync); @@ -265,7 +269,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, switch (new_state) { case NVME_CTRL_ADMIN_ONLY: switch (old_state) { - case NVME_CTRL_RECONNECTING: + case NVME_CTRL_CONNECTING: changed = true; /* FALLTHRU */ default: @@ -276,7 +280,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, switch (old_state) { case NVME_CTRL_NEW: case NVME_CTRL_RESETTING: - case NVME_CTRL_RECONNECTING: + case NVME_CTRL_CONNECTING: changed = true; /* FALLTHRU */ default: @@ -294,9 +298,9 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, break; } break; - case NVME_CTRL_RECONNECTING: + case NVME_CTRL_CONNECTING: switch (old_state) { - case NVME_CTRL_LIVE: + case NVME_CTRL_NEW: case NVME_CTRL_RESETTING: changed = true; /* FALLTHRU */ @@ -309,7 +313,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, case NVME_CTRL_LIVE: case NVME_CTRL_ADMIN_ONLY: case NVME_CTRL_RESETTING: - case NVME_CTRL_RECONNECTING: + case NVME_CTRL_CONNECTING: changed = true; /* FALLTHRU */ default: @@ -518,9 +522,11 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req, u64 slba = nvme_block_nr(ns, bio->bi_iter.bi_sector); u32 nlb = bio->bi_iter.bi_size >> ns->lba_shift; - range[n].cattr = cpu_to_le32(0); - range[n].nlb = cpu_to_le32(nlb); - range[n].slba = cpu_to_le64(slba); + if (n < segments) { + range[n].cattr = cpu_to_le32(0); + range[n].nlb = cpu_to_le32(nlb); + range[n].slba = cpu_to_le64(slba); + } n++; } @@ -794,13 +800,9 @@ static void nvme_keep_alive_end_io(struct request *rq, blk_status_t status) static int nvme_keep_alive(struct nvme_ctrl *ctrl) { - struct nvme_command c; struct request *rq; - memset(&c, 0, sizeof(c)); - c.common.opcode = nvme_admin_keep_alive; - - rq = nvme_alloc_request(ctrl->admin_q, &c, BLK_MQ_REQ_RESERVED, + rq = nvme_alloc_request(ctrl->admin_q, &ctrl->ka_cmd, BLK_MQ_REQ_RESERVED, NVME_QID_ANY); if (IS_ERR(rq)) return PTR_ERR(rq); @@ -832,6 +834,8 @@ void nvme_start_keep_alive(struct nvme_ctrl *ctrl) return; INIT_DELAYED_WORK(&ctrl->ka_work, nvme_keep_alive_work); + memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd)); + ctrl->ka_cmd.common.opcode = nvme_admin_keep_alive; schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ); } EXPORT_SYMBOL_GPL(nvme_start_keep_alive); @@ -1117,14 +1121,19 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns, static void nvme_update_formats(struct nvme_ctrl *ctrl) { - struct nvme_ns *ns; + struct nvme_ns *ns, *next; + LIST_HEAD(rm_list); mutex_lock(&ctrl->namespaces_mutex); list_for_each_entry(ns, &ctrl->namespaces, list) { - if (ns->disk && nvme_revalidate_disk(ns->disk)) - nvme_ns_remove(ns); + if (ns->disk && nvme_revalidate_disk(ns->disk)) { + list_move_tail(&ns->list, &rm_list); + } } mutex_unlock(&ctrl->namespaces_mutex); + + list_for_each_entry_safe(ns, next, &rm_list, list) + nvme_ns_remove(ns); } static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects) @@ -2687,7 +2696,7 @@ static ssize_t nvme_sysfs_show_state(struct device *dev, [NVME_CTRL_LIVE] = "live", [NVME_CTRL_ADMIN_ONLY] = "only-admin", [NVME_CTRL_RESETTING] = "resetting", - [NVME_CTRL_RECONNECTING]= "reconnecting", + [NVME_CTRL_CONNECTING] = "connecting", [NVME_CTRL_DELETING] = "deleting", [NVME_CTRL_DEAD] = "dead", }; diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index 25b19f722f5b..a3145d90c1d2 100644 --- a/drivers/nvme/host/fabrics.h +++ b/drivers/nvme/host/fabrics.h @@ -171,13 +171,14 @@ static inline blk_status_t nvmf_check_init_req(struct nvme_ctrl *ctrl, cmd->common.opcode != nvme_fabrics_command || cmd->fabrics.fctype != nvme_fabrics_type_connect) { /* - * Reconnecting state means transport disruption, which can take - * a long time and even might fail permanently, fail fast to - * give upper layers a chance to failover. + * Connecting state means transport disruption or initial + * establishment, which can take a long time and even might + * fail permanently, fail fast to give upper layers a chance + * to failover. * Deleting state means that the ctrl will never accept commands * again, fail it permanently. */ - if (ctrl->state == NVME_CTRL_RECONNECTING || + if (ctrl->state == NVME_CTRL_CONNECTING || ctrl->state == NVME_CTRL_DELETING) { nvme_req(rq)->status = NVME_SC_ABORT_REQ; return BLK_STS_IOERR; diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index b856d7c919d2..7f51f8414b97 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -55,9 +55,7 @@ struct nvme_fc_queue { enum nvme_fcop_flags { FCOP_FLAGS_TERMIO = (1 << 0), - FCOP_FLAGS_RELEASED = (1 << 1), - FCOP_FLAGS_COMPLETE = (1 << 2), - FCOP_FLAGS_AEN = (1 << 3), + FCOP_FLAGS_AEN = (1 << 1), }; struct nvmefc_ls_req_op { @@ -532,7 +530,7 @@ nvme_fc_resume_controller(struct nvme_fc_ctrl *ctrl) { switch (ctrl->ctrl.state) { case NVME_CTRL_NEW: - case NVME_CTRL_RECONNECTING: + case NVME_CTRL_CONNECTING: /* * As all reconnects were suppressed, schedule a * connect. @@ -777,7 +775,7 @@ nvme_fc_ctrl_connectivity_loss(struct nvme_fc_ctrl *ctrl) } break; - case NVME_CTRL_RECONNECTING: + case NVME_CTRL_CONNECTING: /* * The association has already been terminated and the * controller is attempting reconnects. No need to do anything @@ -1470,7 +1468,6 @@ nvme_fc_xmt_disconnect_assoc(struct nvme_fc_ctrl *ctrl) /* *********************** NVME Ctrl Routines **************************** */ -static void __nvme_fc_final_op_cleanup(struct request *rq); static void nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg); static int @@ -1512,13 +1509,19 @@ nvme_fc_exit_request(struct blk_mq_tag_set *set, struct request *rq, static int __nvme_fc_abort_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_fcp_op *op) { - int state; + unsigned long flags; + int opstate; + + spin_lock_irqsave(&ctrl->lock, flags); + opstate = atomic_xchg(&op->state, FCPOP_STATE_ABORTED); + if (opstate != FCPOP_STATE_ACTIVE) + atomic_set(&op->state, opstate); + else if (ctrl->flags & FCCTRL_TERMIO) + ctrl->iocnt++; + spin_unlock_irqrestore(&ctrl->lock, flags); - state = atomic_xchg(&op->state, FCPOP_STATE_ABORTED); - if (state != FCPOP_STATE_ACTIVE) { - atomic_set(&op->state, state); + if (opstate != FCPOP_STATE_ACTIVE) return -ECANCELED; - } ctrl->lport->ops->fcp_abort(&ctrl->lport->localport, &ctrl->rport->remoteport, @@ -1532,60 +1535,26 @@ static void nvme_fc_abort_aen_ops(struct nvme_fc_ctrl *ctrl) { struct nvme_fc_fcp_op *aen_op = ctrl->aen_ops; - unsigned long flags; - int i, ret; - - for (i = 0; i < NVME_NR_AEN_COMMANDS; i++, aen_op++) { - if (atomic_read(&aen_op->state) != FCPOP_STATE_ACTIVE) - continue; - - spin_lock_irqsave(&ctrl->lock, flags); - if (ctrl->flags & FCCTRL_TERMIO) { - ctrl->iocnt++; - aen_op->flags |= FCOP_FLAGS_TERMIO; - } - spin_unlock_irqrestore(&ctrl->lock, flags); - - ret = __nvme_fc_abort_op(ctrl, aen_op); - if (ret) { - /* - * if __nvme_fc_abort_op failed the io wasn't - * active. Thus this call path is running in - * parallel to the io complete. Treat as non-error. - */ + int i; - /* back out the flags/counters */ - spin_lock_irqsave(&ctrl->lock, flags); - if (ctrl->flags & FCCTRL_TERMIO) - ctrl->iocnt--; - aen_op->flags &= ~FCOP_FLAGS_TERMIO; - spin_unlock_irqrestore(&ctrl->lock, flags); - return; - } - } + for (i = 0; i < NVME_NR_AEN_COMMANDS; i++, aen_op++) + __nvme_fc_abort_op(ctrl, aen_op); } -static inline int +static inline void __nvme_fc_fcpop_chk_teardowns(struct nvme_fc_ctrl *ctrl, - struct nvme_fc_fcp_op *op) + struct nvme_fc_fcp_op *op, int opstate) { unsigned long flags; - bool complete_rq = false; - spin_lock_irqsave(&ctrl->lock, flags); - if (unlikely(op->flags & FCOP_FLAGS_TERMIO)) { + if (opstate == FCPOP_STATE_ABORTED) { + spin_lock_irqsave(&ctrl->lock, flags); if (ctrl->flags & FCCTRL_TERMIO) { if (!--ctrl->iocnt) wake_up(&ctrl->ioabort_wait); } + spin_unlock_irqrestore(&ctrl->lock, flags); } - if (op->flags & FCOP_FLAGS_RELEASED) - complete_rq = true; - else - op->flags |= FCOP_FLAGS_COMPLETE; - spin_unlock_irqrestore(&ctrl->lock, flags); - - return complete_rq; } static void @@ -1601,6 +1570,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) __le16 status = cpu_to_le16(NVME_SC_SUCCESS << 1); union nvme_result result; bool terminate_assoc = true; + int opstate; /* * WARNING: @@ -1639,11 +1609,12 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) * association to be terminated. */ + opstate = atomic_xchg(&op->state, FCPOP_STATE_COMPLETE); + fc_dma_sync_single_for_cpu(ctrl->lport->dev, op->fcp_req.rspdma, sizeof(op->rsp_iu), DMA_FROM_DEVICE); - if (atomic_read(&op->state) == FCPOP_STATE_ABORTED || - op->flags & FCOP_FLAGS_TERMIO) + if (opstate == FCPOP_STATE_ABORTED) status = cpu_to_le16(NVME_SC_ABORT_REQ << 1); else if (freq->status) status = cpu_to_le16(NVME_SC_INTERNAL << 1); @@ -1708,7 +1679,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) done: if (op->flags & FCOP_FLAGS_AEN) { nvme_complete_async_event(&queue->ctrl->ctrl, status, &result); - __nvme_fc_fcpop_chk_teardowns(ctrl, op); + __nvme_fc_fcpop_chk_teardowns(ctrl, op, opstate); atomic_set(&op->state, FCPOP_STATE_IDLE); op->flags = FCOP_FLAGS_AEN; /* clear other flags */ nvme_fc_ctrl_put(ctrl); @@ -1722,13 +1693,11 @@ done: if (status && (blk_queue_dying(rq->q) || ctrl->ctrl.state == NVME_CTRL_NEW || - ctrl->ctrl.state == NVME_CTRL_RECONNECTING)) + ctrl->ctrl.state == NVME_CTRL_CONNECTING)) status |= cpu_to_le16(NVME_SC_DNR << 1); - if (__nvme_fc_fcpop_chk_teardowns(ctrl, op)) - __nvme_fc_final_op_cleanup(rq); - else - nvme_end_request(rq, status, result); + __nvme_fc_fcpop_chk_teardowns(ctrl, op, opstate); + nvme_end_request(rq, status, result); check_error: if (terminate_assoc) @@ -2415,46 +2384,16 @@ nvme_fc_submit_async_event(struct nvme_ctrl *arg) } static void -__nvme_fc_final_op_cleanup(struct request *rq) +nvme_fc_complete_rq(struct request *rq) { struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(rq); struct nvme_fc_ctrl *ctrl = op->ctrl; atomic_set(&op->state, FCPOP_STATE_IDLE); - op->flags &= ~(FCOP_FLAGS_TERMIO | FCOP_FLAGS_RELEASED | - FCOP_FLAGS_COMPLETE); nvme_fc_unmap_data(ctrl, rq, op); nvme_complete_rq(rq); nvme_fc_ctrl_put(ctrl); - -} - -static void -nvme_fc_complete_rq(struct request *rq) -{ - struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(rq); - struct nvme_fc_ctrl *ctrl = op->ctrl; - unsigned long flags; - bool completed = false; - - /* - * the core layer, on controller resets after calling - * nvme_shutdown_ctrl(), calls complete_rq without our - * calling blk_mq_complete_request(), thus there may still - * be live i/o outstanding with the LLDD. Means transport has - * to track complete calls vs fcpio_done calls to know what - * path to take on completes and dones. - */ - spin_lock_irqsave(&ctrl->lock, flags); - if (op->flags & FCOP_FLAGS_COMPLETE) - completed = true; - else - op->flags |= FCOP_FLAGS_RELEASED; - spin_unlock_irqrestore(&ctrl->lock, flags); - - if (completed) - __nvme_fc_final_op_cleanup(rq); } /* @@ -2476,35 +2415,11 @@ nvme_fc_terminate_exchange(struct request *req, void *data, bool reserved) struct nvme_ctrl *nctrl = data; struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl); struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(req); - unsigned long flags; - int status; if (!blk_mq_request_started(req)) return; - spin_lock_irqsave(&ctrl->lock, flags); - if (ctrl->flags & FCCTRL_TERMIO) { - ctrl->iocnt++; - op->flags |= FCOP_FLAGS_TERMIO; - } - spin_unlock_irqrestore(&ctrl->lock, flags); - - status = __nvme_fc_abort_op(ctrl, op); - if (status) { - /* - * if __nvme_fc_abort_op failed the io wasn't - * active. Thus this call path is running in - * parallel to the io complete. Treat as non-error. - */ - - /* back out the flags/counters */ - spin_lock_irqsave(&ctrl->lock, flags); - if (ctrl->flags & FCCTRL_TERMIO) - ctrl->iocnt--; - op->flags &= ~FCOP_FLAGS_TERMIO; - spin_unlock_irqrestore(&ctrl->lock, flags); - return; - } + __nvme_fc_abort_op(ctrl, op); } @@ -2943,7 +2858,7 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status) unsigned long recon_delay = ctrl->ctrl.opts->reconnect_delay * HZ; bool recon = true; - if (ctrl->ctrl.state != NVME_CTRL_RECONNECTING) + if (ctrl->ctrl.state != NVME_CTRL_CONNECTING) return; if (portptr->port_state == FC_OBJSTATE_ONLINE) @@ -2991,10 +2906,10 @@ nvme_fc_reset_ctrl_work(struct work_struct *work) /* will block will waiting for io to terminate */ nvme_fc_delete_association(ctrl); - if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RECONNECTING)) { + if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) { dev_err(ctrl->ctrl.device, "NVME-FC{%d}: error_recovery: Couldn't change state " - "to RECONNECTING\n", ctrl->cnum); + "to CONNECTING\n", ctrl->cnum); return; } @@ -3195,7 +3110,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, * transport errors (frame drop, LS failure) inherently must kill * the association. The transport is coded so that any command used * to create the association (prior to a LIVE state transition - * while NEW or RECONNECTING) will fail if it completes in error or + * while NEW or CONNECTING) will fail if it completes in error or * times out. * * As such: as the connect request was mostly likely due to a diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 8e4550fa08f8..0521e4707d1c 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -123,7 +123,7 @@ enum nvme_ctrl_state { NVME_CTRL_LIVE, NVME_CTRL_ADMIN_ONLY, /* Only admin queue live */ NVME_CTRL_RESETTING, - NVME_CTRL_RECONNECTING, + NVME_CTRL_CONNECTING, NVME_CTRL_DELETING, NVME_CTRL_DEAD, }; @@ -183,6 +183,7 @@ struct nvme_ctrl { struct work_struct scan_work; struct work_struct async_event_work; struct delayed_work ka_work; + struct nvme_command ka_cmd; struct work_struct fw_act_work; /* Power saving configuration */ diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 6fe7af00a1f4..73036d2fbbd5 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1141,7 +1141,7 @@ static bool nvme_should_reset(struct nvme_dev *dev, u32 csts) /* If there is a reset/reinit ongoing, we shouldn't reset again. */ switch (dev->ctrl.state) { case NVME_CTRL_RESETTING: - case NVME_CTRL_RECONNECTING: + case NVME_CTRL_CONNECTING: return false; default: break; @@ -1215,13 +1215,17 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved) * cancellation error. All outstanding requests are completed on * shutdown, so we return BLK_EH_HANDLED. */ - if (dev->ctrl.state == NVME_CTRL_RESETTING) { + switch (dev->ctrl.state) { + case NVME_CTRL_CONNECTING: + case NVME_CTRL_RESETTING: dev_warn(dev->ctrl.device, "I/O %d QID %d timeout, disable controller\n", req->tag, nvmeq->qid); nvme_dev_disable(dev, false); nvme_req(req)->flags |= NVME_REQ_CANCELLED; return BLK_EH_HANDLED; + default: + break; } /* @@ -1364,18 +1368,14 @@ static int nvme_cmb_qdepth(struct nvme_dev *dev, int nr_io_queues, static int nvme_alloc_sq_cmds(struct nvme_dev *dev, struct nvme_queue *nvmeq, int qid, int depth) { - if (qid && dev->cmb && use_cmb_sqes && (dev->cmbsz & NVME_CMBSZ_SQS)) { - unsigned offset = (qid - 1) * roundup(SQ_SIZE(depth), - dev->ctrl.page_size); - nvmeq->sq_dma_addr = dev->cmb_bus_addr + offset; - nvmeq->sq_cmds_io = dev->cmb + offset; - } else { - nvmeq->sq_cmds = dma_alloc_coherent(dev->dev, SQ_SIZE(depth), - &nvmeq->sq_dma_addr, GFP_KERNEL); - if (!nvmeq->sq_cmds) - return -ENOMEM; - } + /* CMB SQEs will be mapped before creation */ + if (qid && dev->cmb && use_cmb_sqes && (dev->cmbsz & NVME_CMBSZ_SQS)) + return 0; + nvmeq->sq_cmds = dma_alloc_coherent(dev->dev, SQ_SIZE(depth), + &nvmeq->sq_dma_addr, GFP_KERNEL); + if (!nvmeq->sq_cmds) + return -ENOMEM; return 0; } @@ -1449,6 +1449,13 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid) struct nvme_dev *dev = nvmeq->dev; int result; + if (dev->cmb && use_cmb_sqes && (dev->cmbsz & NVME_CMBSZ_SQS)) { + unsigned offset = (qid - 1) * roundup(SQ_SIZE(nvmeq->q_depth), + dev->ctrl.page_size); + nvmeq->sq_dma_addr = dev->cmb_bus_addr + offset; + nvmeq->sq_cmds_io = dev->cmb + offset; + } + nvmeq->cq_vector = qid - 1; result = adapter_alloc_cq(dev, qid, nvmeq); if (result < 0) @@ -2288,12 +2295,12 @@ static void nvme_reset_work(struct work_struct *work) nvme_dev_disable(dev, false); /* - * Introduce RECONNECTING state from nvme-fc/rdma transports to mark the + * Introduce CONNECTING state from nvme-fc/rdma transports to mark the * initializing procedure here. */ - if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RECONNECTING)) { + if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_CONNECTING)) { dev_warn(dev->ctrl.device, - "failed to mark controller RECONNECTING\n"); + "failed to mark controller CONNECTING\n"); goto out; } diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 2bc059f7d73c..3a51ed50eff2 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -887,7 +887,7 @@ free_ctrl: static void nvme_rdma_reconnect_or_remove(struct nvme_rdma_ctrl *ctrl) { /* If we are resetting/deleting then do nothing */ - if (ctrl->ctrl.state != NVME_CTRL_RECONNECTING) { + if (ctrl->ctrl.state != NVME_CTRL_CONNECTING) { WARN_ON_ONCE(ctrl->ctrl.state == NVME_CTRL_NEW || ctrl->ctrl.state == NVME_CTRL_LIVE); return; @@ -973,7 +973,7 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work) blk_mq_unquiesce_queue(ctrl->ctrl.admin_q); nvme_start_queues(&ctrl->ctrl); - if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RECONNECTING)) { + if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) { /* state change failure should never happen */ WARN_ON_ONCE(1); return; @@ -1756,7 +1756,7 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work) nvme_stop_ctrl(&ctrl->ctrl); nvme_rdma_shutdown_ctrl(ctrl, false); - if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RECONNECTING)) { + if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) { /* state change failure should never happen */ WARN_ON_ONCE(1); return; @@ -1784,11 +1784,8 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work) return; out_fail: - dev_warn(ctrl->ctrl.device, "Removing after reset failure\n"); - nvme_remove_namespaces(&ctrl->ctrl); - nvme_rdma_shutdown_ctrl(ctrl, true); - nvme_uninit_ctrl(&ctrl->ctrl); - nvme_put_ctrl(&ctrl->ctrl); + ++ctrl->ctrl.nr_reconnects; + nvme_rdma_reconnect_or_remove(ctrl); } static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = { @@ -1942,6 +1939,9 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev, if (!ctrl->queues) goto out_uninit_ctrl; + changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING); + WARN_ON_ONCE(!changed); + ret = nvme_rdma_configure_admin_queue(ctrl, true); if (ret) goto out_kfree_queues; diff --git a/drivers/nvme/target/io-cmd.c b/drivers/nvme/target/io-cmd.c index 0a4372a016f2..28bbdff4a88b 100644 --- a/drivers/nvme/target/io-cmd.c +++ b/drivers/nvme/target/io-cmd.c @@ -105,10 +105,13 @@ static void nvmet_execute_flush(struct nvmet_req *req) static u16 nvmet_discard_range(struct nvmet_ns *ns, struct nvme_dsm_range *range, struct bio **bio) { - if (__blkdev_issue_discard(ns->bdev, + int ret; + + ret = __blkdev_issue_discard(ns->bdev, le64_to_cpu(range->slba) << (ns->blksize_shift - 9), le32_to_cpu(range->nlb) << (ns->blksize_shift - 9), - GFP_KERNEL, 0, bio)) + GFP_KERNEL, 0, bio); + if (ret && ret != -EOPNOTSUPP) return NVME_SC_INTERNAL | NVME_SC_DNR; return 0; } diff --git a/drivers/of/property.c b/drivers/of/property.c index 36ed84e26d9c..f46828e3b082 100644 --- a/drivers/of/property.c +++ b/drivers/of/property.c @@ -977,11 +977,11 @@ static int of_fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode, return 0; } -static void * +static const void * of_fwnode_device_get_match_data(const struct fwnode_handle *fwnode, const struct device *dev) { - return (void *)of_device_get_match_data(dev); + return of_device_get_match_data(dev); } const struct fwnode_operations of_fwnode_ops = { diff --git a/drivers/opp/cpu.c b/drivers/opp/cpu.c index 2d87bc1adf38..0c0910709435 100644 --- a/drivers/opp/cpu.c +++ b/drivers/opp/cpu.c @@ -55,7 +55,7 @@ int dev_pm_opp_init_cpufreq_table(struct device *dev, if (max_opps <= 0) return max_opps ? max_opps : -ENODATA; - freq_table = kcalloc((max_opps + 1), sizeof(*freq_table), GFP_ATOMIC); + freq_table = kcalloc((max_opps + 1), sizeof(*freq_table), GFP_KERNEL); if (!freq_table) return -ENOMEM; diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index fc734014206f..8b14bd326d4a 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -3419,22 +3419,29 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_PORT_RIDGE, static void quirk_chelsio_extend_vpd(struct pci_dev *dev) { - pci_set_vpd_size(dev, 8192); -} - -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_CHELSIO, 0x20, quirk_chelsio_extend_vpd); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_CHELSIO, 0x21, quirk_chelsio_extend_vpd); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_CHELSIO, 0x22, quirk_chelsio_extend_vpd); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_CHELSIO, 0x23, quirk_chelsio_extend_vpd); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_CHELSIO, 0x24, quirk_chelsio_extend_vpd); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_CHELSIO, 0x25, quirk_chelsio_extend_vpd); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_CHELSIO, 0x26, quirk_chelsio_extend_vpd); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_CHELSIO, 0x30, quirk_chelsio_extend_vpd); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_CHELSIO, 0x31, quirk_chelsio_extend_vpd); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_CHELSIO, 0x32, quirk_chelsio_extend_vpd); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_CHELSIO, 0x35, quirk_chelsio_extend_vpd); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_CHELSIO, 0x36, quirk_chelsio_extend_vpd); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_CHELSIO, 0x37, quirk_chelsio_extend_vpd); + int chip = (dev->device & 0xf000) >> 12; + int func = (dev->device & 0x0f00) >> 8; + int prod = (dev->device & 0x00ff) >> 0; + + /* + * If this is a T3-based adapter, there's a 1KB VPD area at offset + * 0xc00 which contains the preferred VPD values. If this is a T4 or + * later based adapter, the special VPD is at offset 0x400 for the + * Physical Functions (the SR-IOV Virtual Functions have no VPD + * Capabilities). The PCI VPD Access core routines will normally + * compute the size of the VPD by parsing the VPD Data Structure at + * offset 0x000. This will result in silent failures when attempting + * to accesses these other VPD areas which are beyond those computed + * limits. + */ + if (chip == 0x0 && prod >= 0x20) + pci_set_vpd_size(dev, 8192); + else if (chip >= 0x4 && func < 0x8) + pci_set_vpd_size(dev, 2048); +} + +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_CHELSIO, PCI_ANY_ID, + quirk_chelsio_extend_vpd); #ifdef CONFIG_ACPI /* diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c index 7bc5eee96b31..0c2ed11c0603 100644 --- a/drivers/perf/arm_pmu.c +++ b/drivers/perf/arm_pmu.c @@ -17,7 +17,6 @@ #include <linux/export.h> #include <linux/kernel.h> #include <linux/perf/arm_pmu.h> -#include <linux/platform_device.h> #include <linux/slab.h> #include <linux/sched/clock.h> #include <linux/spinlock.h> @@ -26,6 +25,9 @@ #include <asm/irq_regs.h> +static DEFINE_PER_CPU(struct arm_pmu *, cpu_armpmu); +static DEFINE_PER_CPU(int, cpu_irq); + static int armpmu_map_cache_event(const unsigned (*cache_map) [PERF_COUNT_HW_CACHE_MAX] @@ -320,17 +322,9 @@ validate_group(struct perf_event *event) return 0; } -static struct arm_pmu_platdata *armpmu_get_platdata(struct arm_pmu *armpmu) -{ - struct platform_device *pdev = armpmu->plat_device; - - return pdev ? dev_get_platdata(&pdev->dev) : NULL; -} - static irqreturn_t armpmu_dispatch_irq(int irq, void *dev) { struct arm_pmu *armpmu; - struct arm_pmu_platdata *plat; int ret; u64 start_clock, finish_clock; @@ -341,14 +335,11 @@ static irqreturn_t armpmu_dispatch_irq(int irq, void *dev) * dereference. */ armpmu = *(void **)dev; - - plat = armpmu_get_platdata(armpmu); + if (WARN_ON_ONCE(!armpmu)) + return IRQ_NONE; start_clock = sched_clock(); - if (plat && plat->handle_irq) - ret = plat->handle_irq(irq, armpmu, armpmu->handle_irq); - else - ret = armpmu->handle_irq(irq, armpmu); + ret = armpmu->handle_irq(irq, armpmu); finish_clock = sched_clock(); perf_sample_event_took(finish_clock - start_clock); @@ -531,54 +522,41 @@ int perf_num_counters(void) } EXPORT_SYMBOL_GPL(perf_num_counters); -void armpmu_free_irq(struct arm_pmu *armpmu, int cpu) +static int armpmu_count_irq_users(const int irq) { - struct pmu_hw_events __percpu *hw_events = armpmu->hw_events; - int irq = per_cpu(hw_events->irq, cpu); + int cpu, count = 0; - if (!cpumask_test_and_clear_cpu(cpu, &armpmu->active_irqs)) - return; - - if (irq_is_percpu_devid(irq)) { - free_percpu_irq(irq, &hw_events->percpu_pmu); - cpumask_clear(&armpmu->active_irqs); - return; + for_each_possible_cpu(cpu) { + if (per_cpu(cpu_irq, cpu) == irq) + count++; } - free_irq(irq, per_cpu_ptr(&hw_events->percpu_pmu, cpu)); + return count; } -void armpmu_free_irqs(struct arm_pmu *armpmu) +void armpmu_free_irq(int irq, int cpu) { - int cpu; + if (per_cpu(cpu_irq, cpu) == 0) + return; + if (WARN_ON(irq != per_cpu(cpu_irq, cpu))) + return; + + if (!irq_is_percpu_devid(irq)) + free_irq(irq, per_cpu_ptr(&cpu_armpmu, cpu)); + else if (armpmu_count_irq_users(irq) == 1) + free_percpu_irq(irq, &cpu_armpmu); - for_each_cpu(cpu, &armpmu->supported_cpus) - armpmu_free_irq(armpmu, cpu); + per_cpu(cpu_irq, cpu) = 0; } -int armpmu_request_irq(struct arm_pmu *armpmu, int cpu) +int armpmu_request_irq(int irq, int cpu) { int err = 0; - struct pmu_hw_events __percpu *hw_events = armpmu->hw_events; const irq_handler_t handler = armpmu_dispatch_irq; - int irq = per_cpu(hw_events->irq, cpu); if (!irq) return 0; - if (irq_is_percpu_devid(irq) && cpumask_empty(&armpmu->active_irqs)) { - err = request_percpu_irq(irq, handler, "arm-pmu", - &hw_events->percpu_pmu); - } else if (irq_is_percpu_devid(irq)) { - int other_cpu = cpumask_first(&armpmu->active_irqs); - int other_irq = per_cpu(hw_events->irq, other_cpu); - - if (irq != other_irq) { - pr_warn("mismatched PPIs detected.\n"); - err = -EINVAL; - goto err_out; - } - } else { - struct arm_pmu_platdata *platdata = armpmu_get_platdata(armpmu); + if (!irq_is_percpu_devid(irq)) { unsigned long irq_flags; err = irq_force_affinity(irq, cpumask_of(cpu)); @@ -589,22 +567,22 @@ int armpmu_request_irq(struct arm_pmu *armpmu, int cpu) goto err_out; } - if (platdata && platdata->irq_flags) { - irq_flags = platdata->irq_flags; - } else { - irq_flags = IRQF_PERCPU | - IRQF_NOBALANCING | - IRQF_NO_THREAD; - } + irq_flags = IRQF_PERCPU | + IRQF_NOBALANCING | + IRQF_NO_THREAD; + irq_set_status_flags(irq, IRQ_NOAUTOEN); err = request_irq(irq, handler, irq_flags, "arm-pmu", - per_cpu_ptr(&hw_events->percpu_pmu, cpu)); + per_cpu_ptr(&cpu_armpmu, cpu)); + } else if (armpmu_count_irq_users(irq) == 0) { + err = request_percpu_irq(irq, handler, "arm-pmu", + &cpu_armpmu); } if (err) goto err_out; - cpumask_set_cpu(cpu, &armpmu->active_irqs); + per_cpu(cpu_irq, cpu) = irq; return 0; err_out: @@ -612,19 +590,6 @@ err_out: return err; } -int armpmu_request_irqs(struct arm_pmu *armpmu) -{ - int cpu, err; - - for_each_cpu(cpu, &armpmu->supported_cpus) { - err = armpmu_request_irq(armpmu, cpu); - if (err) - break; - } - - return err; -} - static int armpmu_get_cpu_irq(struct arm_pmu *pmu, int cpu) { struct pmu_hw_events __percpu *hw_events = pmu->hw_events; @@ -647,12 +612,14 @@ static int arm_perf_starting_cpu(unsigned int cpu, struct hlist_node *node) if (pmu->reset) pmu->reset(pmu); + per_cpu(cpu_armpmu, cpu) = pmu; + irq = armpmu_get_cpu_irq(pmu, cpu); if (irq) { - if (irq_is_percpu_devid(irq)) { + if (irq_is_percpu_devid(irq)) enable_percpu_irq(irq, IRQ_TYPE_NONE); - return 0; - } + else + enable_irq(irq); } return 0; @@ -667,8 +634,14 @@ static int arm_perf_teardown_cpu(unsigned int cpu, struct hlist_node *node) return 0; irq = armpmu_get_cpu_irq(pmu, cpu); - if (irq && irq_is_percpu_devid(irq)) - disable_percpu_irq(irq); + if (irq) { + if (irq_is_percpu_devid(irq)) + disable_percpu_irq(irq); + else + disable_irq(irq); + } + + per_cpu(cpu_armpmu, cpu) = NULL; return 0; } @@ -800,18 +773,18 @@ static void cpu_pmu_destroy(struct arm_pmu *cpu_pmu) &cpu_pmu->node); } -struct arm_pmu *armpmu_alloc(void) +static struct arm_pmu *__armpmu_alloc(gfp_t flags) { struct arm_pmu *pmu; int cpu; - pmu = kzalloc(sizeof(*pmu), GFP_KERNEL); + pmu = kzalloc(sizeof(*pmu), flags); if (!pmu) { pr_info("failed to allocate PMU device!\n"); goto out; } - pmu->hw_events = alloc_percpu(struct pmu_hw_events); + pmu->hw_events = alloc_percpu_gfp(struct pmu_hw_events, flags); if (!pmu->hw_events) { pr_info("failed to allocate per-cpu PMU data.\n"); goto out_free_pmu; @@ -857,6 +830,17 @@ out: return NULL; } +struct arm_pmu *armpmu_alloc(void) +{ + return __armpmu_alloc(GFP_KERNEL); +} + +struct arm_pmu *armpmu_alloc_atomic(void) +{ + return __armpmu_alloc(GFP_ATOMIC); +} + + void armpmu_free(struct arm_pmu *pmu) { free_percpu(pmu->hw_events); diff --git a/drivers/perf/arm_pmu_acpi.c b/drivers/perf/arm_pmu_acpi.c index 705f1a390e31..0f197516d708 100644 --- a/drivers/perf/arm_pmu_acpi.c +++ b/drivers/perf/arm_pmu_acpi.c @@ -11,6 +11,8 @@ #include <linux/acpi.h> #include <linux/cpumask.h> #include <linux/init.h> +#include <linux/irq.h> +#include <linux/irqdesc.h> #include <linux/percpu.h> #include <linux/perf/arm_pmu.h> @@ -87,7 +89,13 @@ static int arm_pmu_acpi_parse_irqs(void) pr_warn("No ACPI PMU IRQ for CPU%d\n", cpu); } + /* + * Log and request the IRQ so the core arm_pmu code can manage + * it. We'll have to sanity-check IRQs later when we associate + * them with their PMUs. + */ per_cpu(pmu_irqs, cpu) = irq; + armpmu_request_irq(irq, cpu); } return 0; @@ -127,7 +135,7 @@ static struct arm_pmu *arm_pmu_acpi_find_alloc_pmu(void) return pmu; } - pmu = armpmu_alloc(); + pmu = armpmu_alloc_atomic(); if (!pmu) { pr_warn("Unable to allocate PMU for CPU%d\n", smp_processor_id()); @@ -140,6 +148,35 @@ static struct arm_pmu *arm_pmu_acpi_find_alloc_pmu(void) } /* + * Check whether the new IRQ is compatible with those already associated with + * the PMU (e.g. we don't have mismatched PPIs). + */ +static bool pmu_irq_matches(struct arm_pmu *pmu, int irq) +{ + struct pmu_hw_events __percpu *hw_events = pmu->hw_events; + int cpu; + + if (!irq) + return true; + + for_each_cpu(cpu, &pmu->supported_cpus) { + int other_irq = per_cpu(hw_events->irq, cpu); + if (!other_irq) + continue; + + if (irq == other_irq) + continue; + if (!irq_is_percpu_devid(irq) && !irq_is_percpu_devid(other_irq)) + continue; + + pr_warn("mismatched PPIs detected\n"); + return false; + } + + return true; +} + +/* * This must run before the common arm_pmu hotplug logic, so that we can * associate a CPU and its interrupt before the common code tries to manage the * affinity and so on. @@ -164,19 +201,14 @@ static int arm_pmu_acpi_cpu_starting(unsigned int cpu) if (!pmu) return -ENOMEM; - cpumask_set_cpu(cpu, &pmu->supported_cpus); - per_cpu(probed_pmus, cpu) = pmu; - /* - * Log and request the IRQ so the core arm_pmu code can manage it. In - * some situations (e.g. mismatched PPIs), we may fail to request the - * IRQ. However, it may be too late for us to do anything about it. - * The common ARM PMU code will log a warning in this case. - */ - hw_events = pmu->hw_events; - per_cpu(hw_events->irq, cpu) = irq; - armpmu_request_irq(pmu, cpu); + if (pmu_irq_matches(pmu, irq)) { + hw_events = pmu->hw_events; + per_cpu(hw_events->irq, cpu) = irq; + } + + cpumask_set_cpu(cpu, &pmu->supported_cpus); /* * Ideally, we'd probe the PMU here when we find the first matching @@ -247,11 +279,6 @@ static int arm_pmu_acpi_init(void) if (acpi_disabled) return 0; - /* - * We can't request IRQs yet, since we don't know the cookie value - * until we know which CPUs share the same logical PMU. We'll handle - * that in arm_pmu_acpi_cpu_starting(). - */ ret = arm_pmu_acpi_parse_irqs(); if (ret) return ret; diff --git a/drivers/perf/arm_pmu_platform.c b/drivers/perf/arm_pmu_platform.c index 46501cc79fd7..7729eda5909d 100644 --- a/drivers/perf/arm_pmu_platform.c +++ b/drivers/perf/arm_pmu_platform.c @@ -127,13 +127,6 @@ static int pmu_parse_irqs(struct arm_pmu *pmu) pdev->dev.of_node); } - /* - * Some platforms have all PMU IRQs OR'd into a single IRQ, with a - * special platdata function that attempts to demux them. - */ - if (dev_get_platdata(&pdev->dev)) - cpumask_setall(&pmu->supported_cpus); - for (i = 0; i < num_irqs; i++) { int cpu, irq; @@ -164,6 +157,36 @@ static int pmu_parse_irqs(struct arm_pmu *pmu) return 0; } +static int armpmu_request_irqs(struct arm_pmu *armpmu) +{ + struct pmu_hw_events __percpu *hw_events = armpmu->hw_events; + int cpu, err; + + for_each_cpu(cpu, &armpmu->supported_cpus) { + int irq = per_cpu(hw_events->irq, cpu); + if (!irq) + continue; + + err = armpmu_request_irq(irq, cpu); + if (err) + break; + } + + return err; +} + +static void armpmu_free_irqs(struct arm_pmu *armpmu) +{ + int cpu; + struct pmu_hw_events __percpu *hw_events = armpmu->hw_events; + + for_each_cpu(cpu, &armpmu->supported_cpus) { + int irq = per_cpu(hw_events->irq, cpu); + + armpmu_free_irq(irq, cpu); + } +} + int arm_pmu_device_probe(struct platform_device *pdev, const struct of_device_id *of_table, const struct pmu_probe_info *probe_table) diff --git a/drivers/platform/x86/dell-laptop.c b/drivers/platform/x86/dell-laptop.c index 2a68f59d2228..c52c6723374b 100644 --- a/drivers/platform/x86/dell-laptop.c +++ b/drivers/platform/x86/dell-laptop.c @@ -127,24 +127,6 @@ static const struct dmi_system_id dell_device_table[] __initconst = { }, }, { - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_CHASSIS_TYPE, "30"), /*Tablet*/ - }, - }, - { - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_CHASSIS_TYPE, "31"), /*Convertible*/ - }, - }, - { - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_CHASSIS_TYPE, "32"), /*Detachable*/ - }, - }, - { .ident = "Dell Computer Corporation", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"), @@ -1279,7 +1261,7 @@ static int kbd_get_state(struct kbd_state *state) struct calling_interface_buffer buffer; int ret; - dell_fill_request(&buffer, 0, 0, 0, 0); + dell_fill_request(&buffer, 0x1, 0, 0, 0); ret = dell_send_request(&buffer, CLASS_KBD_BACKLIGHT, SELECT_KBD_BACKLIGHT); if (ret) diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index 5b6f18b18801..535199c9e6bc 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -113,7 +113,7 @@ MODULE_PARM_DESC(no_bt_rfkill, "No rfkill for bluetooth."); /* * ACPI Helpers */ -#define IDEAPAD_EC_TIMEOUT (100) /* in ms */ +#define IDEAPAD_EC_TIMEOUT (200) /* in ms */ static int read_method_int(acpi_handle handle, const char *method, int *val) { diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c index daa68acbc900..c0c8945603cb 100644 --- a/drivers/platform/x86/wmi.c +++ b/drivers/platform/x86/wmi.c @@ -933,7 +933,7 @@ static int wmi_dev_probe(struct device *dev) goto probe_failure; } - buf = kmalloc(strlen(wdriver->driver.name) + 4, GFP_KERNEL); + buf = kmalloc(strlen(wdriver->driver.name) + 5, GFP_KERNEL); if (!buf) { ret = -ENOMEM; goto probe_string_failure; diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c index ba2e0856d22c..8f5c1d7f751a 100644 --- a/drivers/s390/virtio/virtio_ccw.c +++ b/drivers/s390/virtio/virtio_ccw.c @@ -1297,6 +1297,9 @@ static int virtio_ccw_cio_notify(struct ccw_device *cdev, int event) vcdev->device_lost = true; rc = NOTIFY_DONE; break; + case CIO_OPER: + rc = NOTIFY_OK; + break; default: rc = NOTIFY_DONE; break; @@ -1309,6 +1312,27 @@ static struct ccw_device_id virtio_ids[] = { {}, }; +#ifdef CONFIG_PM_SLEEP +static int virtio_ccw_freeze(struct ccw_device *cdev) +{ + struct virtio_ccw_device *vcdev = dev_get_drvdata(&cdev->dev); + + return virtio_device_freeze(&vcdev->vdev); +} + +static int virtio_ccw_restore(struct ccw_device *cdev) +{ + struct virtio_ccw_device *vcdev = dev_get_drvdata(&cdev->dev); + int ret; + + ret = virtio_ccw_set_transport_rev(vcdev); + if (ret) + return ret; + + return virtio_device_restore(&vcdev->vdev); +} +#endif + static struct ccw_driver virtio_ccw_driver = { .driver = { .owner = THIS_MODULE, @@ -1321,6 +1345,11 @@ static struct ccw_driver virtio_ccw_driver = { .set_online = virtio_ccw_online, .notify = virtio_ccw_cio_notify, .int_class = IRQIO_VIR, +#ifdef CONFIG_PM_SLEEP + .freeze = virtio_ccw_freeze, + .thaw = virtio_ccw_restore, + .restore = virtio_ccw_restore, +#endif }; static int __init pure_hex(char **cp, unsigned int *val, int min_digit, diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile index fcfd28d2884c..de1b3fce936d 100644 --- a/drivers/scsi/Makefile +++ b/drivers/scsi/Makefile @@ -185,7 +185,6 @@ ncr53c8xx-flags-$(CONFIG_SCSI_ZALON) \ CFLAGS_ncr53c8xx.o := $(ncr53c8xx-flags-y) $(ncr53c8xx-flags-m) zalon7xx-objs := zalon.o ncr53c8xx.o NCR_Q720_mod-objs := NCR_Q720.o ncr53c8xx.o -oktagon_esp_mod-objs := oktagon_esp.o oktagon_io.o # Files generated that shall be removed upon make clean clean-files := 53c700_d.h 53c700_u.h diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c index b3b931ab77eb..2664ea0df35f 100644 --- a/drivers/scsi/aacraid/linit.c +++ b/drivers/scsi/aacraid/linit.c @@ -1693,8 +1693,10 @@ static int aac_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) * Map in the registers from the adapter. */ aac->base_size = AAC_MIN_FOOTPRINT_SIZE; - if ((*aac_drivers[index].init)(aac)) + if ((*aac_drivers[index].init)(aac)) { + error = -ENODEV; goto out_unmap; + } if (aac->sync_mode) { if (aac_sync_mode) diff --git a/drivers/scsi/aic7xxx/aiclib.c b/drivers/scsi/aic7xxx/aiclib.c deleted file mode 100644 index 828ae3d9a510..000000000000 --- a/drivers/scsi/aic7xxx/aiclib.c +++ /dev/null @@ -1,34 +0,0 @@ -/* - * Implementation of Utility functions for all SCSI device types. - * - * Copyright (c) 1997, 1998, 1999 Justin T. Gibbs. - * Copyright (c) 1997, 1998 Kenneth D. Merry. - * All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions, and the following disclaimer, - * without modification, immediately at the beginning of the file. - * 2. The name of the author may not be used to endorse or promote products - * derived from this software without specific prior written permission. - * - * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND - * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE - * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE - * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE FOR - * ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL - * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS - * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) - * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT - * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY - * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF - * SUCH DAMAGE. - * - * $FreeBSD: src/sys/cam/scsi/scsi_all.c,v 1.38 2002/09/23 04:56:35 mjacob Exp $ - * $Id$ - */ - -#include "aiclib.h" - diff --git a/drivers/scsi/bnx2fc/bnx2fc_io.c b/drivers/scsi/bnx2fc/bnx2fc_io.c index 8e2f767147cb..5a645b8b9af1 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_io.c +++ b/drivers/scsi/bnx2fc/bnx2fc_io.c @@ -1889,6 +1889,7 @@ void bnx2fc_process_scsi_cmd_compl(struct bnx2fc_cmd *io_req, /* we will not receive ABTS response for this IO */ BNX2FC_IO_DBG(io_req, "Timer context finished processing " "this scsi cmd\n"); + return; } /* Cancel the timeout_work, as we received IO completion */ diff --git a/drivers/scsi/csiostor/csio_lnode.c b/drivers/scsi/csiostor/csio_lnode.c index be5ee2d37815..7dbbbb81a1e7 100644 --- a/drivers/scsi/csiostor/csio_lnode.c +++ b/drivers/scsi/csiostor/csio_lnode.c @@ -114,7 +114,7 @@ static enum csio_ln_ev fwevt_to_lnevt[] = { static struct csio_lnode * csio_ln_lookup_by_portid(struct csio_hw *hw, uint8_t portid) { - struct csio_lnode *ln = hw->rln; + struct csio_lnode *ln; struct list_head *tmp; /* Match siblings lnode with portid */ diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c index 022e421c2185..4b44325d1a82 100644 --- a/drivers/scsi/device_handler/scsi_dh_alua.c +++ b/drivers/scsi/device_handler/scsi_dh_alua.c @@ -876,6 +876,11 @@ static void alua_rtpg_work(struct work_struct *work) /** * alua_rtpg_queue() - cause RTPG to be submitted asynchronously + * @pg: ALUA port group associated with @sdev. + * @sdev: SCSI device for which to submit an RTPG. + * @qdata: Information about the callback to invoke after the RTPG. + * @force: Whether or not to submit an RTPG if a work item that will submit an + * RTPG already has been scheduled. * * Returns true if and only if alua_rtpg_work() will be called asynchronously. * That function is responsible for calling @qdata->fn(). diff --git a/drivers/scsi/ibmvscsi/ibmvfc.h b/drivers/scsi/ibmvscsi/ibmvfc.h index 9a0696f68f37..b81a53c4a9a8 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.h +++ b/drivers/scsi/ibmvscsi/ibmvfc.h @@ -367,7 +367,7 @@ enum ibmvfc_fcp_rsp_info_codes { }; struct ibmvfc_fcp_rsp_info { - __be16 reserved; + u8 reserved[3]; u8 rsp_code; u8 reserved2[4]; }__attribute__((packed, aligned (2))); diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c index 6198559abbd8..0ad00dbf912d 100644 --- a/drivers/scsi/iscsi_tcp.c +++ b/drivers/scsi/iscsi_tcp.c @@ -732,7 +732,7 @@ static int iscsi_sw_tcp_conn_get_param(struct iscsi_cls_conn *cls_conn, struct iscsi_tcp_conn *tcp_conn = conn->dd_data; struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data; struct sockaddr_in6 addr; - int rc, len; + int rc; switch(param) { case ISCSI_PARAM_CONN_PORT: @@ -745,12 +745,12 @@ static int iscsi_sw_tcp_conn_get_param(struct iscsi_cls_conn *cls_conn, } if (param == ISCSI_PARAM_LOCAL_PORT) rc = kernel_getsockname(tcp_sw_conn->sock, - (struct sockaddr *)&addr, &len); + (struct sockaddr *)&addr); else rc = kernel_getpeername(tcp_sw_conn->sock, - (struct sockaddr *)&addr, &len); + (struct sockaddr *)&addr); spin_unlock_bh(&conn->session->frwd_lock); - if (rc) + if (rc < 0) return rc; return iscsi_conn_get_addr_param((struct sockaddr_storage *) @@ -771,7 +771,7 @@ static int iscsi_sw_tcp_host_get_param(struct Scsi_Host *shost, struct iscsi_tcp_conn *tcp_conn; struct iscsi_sw_tcp_conn *tcp_sw_conn; struct sockaddr_in6 addr; - int rc, len; + int rc; switch (param) { case ISCSI_HOST_PARAM_IPADDRESS: @@ -793,9 +793,9 @@ static int iscsi_sw_tcp_host_get_param(struct Scsi_Host *shost, } rc = kernel_getsockname(tcp_sw_conn->sock, - (struct sockaddr *)&addr, &len); + (struct sockaddr *)&addr); spin_unlock_bh(&session->frwd_lock); - if (rc) + if (rc < 0) return rc; return iscsi_conn_get_addr_param((struct sockaddr_storage *) diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 13d6e4ec3022..59a87ca328d3 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -2410,8 +2410,11 @@ _base_assign_reply_queues(struct MPT3SAS_ADAPTER *ioc) continue; } - for_each_cpu(cpu, mask) + for_each_cpu_and(cpu, mask, cpu_online_mask) { + if (cpu >= ioc->cpu_msix_table_sz) + break; ioc->cpu_msix_table[cpu] = reply_q->msix_index; + } } return; } diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index 029e2e69b29f..f57a94b4f0d9 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -1724,7 +1724,6 @@ static ssize_t qedi_show_boot_eth_info(void *data, int type, char *buf) { struct qedi_ctx *qedi = data; struct nvm_iscsi_initiator *initiator; - char *str = buf; int rc = 1; u32 ipv6_en, dhcp_en, ip_len; struct nvm_iscsi_block *block; @@ -1758,32 +1757,32 @@ static ssize_t qedi_show_boot_eth_info(void *data, int type, char *buf) switch (type) { case ISCSI_BOOT_ETH_IP_ADDR: - rc = snprintf(str, ip_len, fmt, ip); + rc = snprintf(buf, ip_len, fmt, ip); break; case ISCSI_BOOT_ETH_SUBNET_MASK: - rc = snprintf(str, ip_len, fmt, sub); + rc = snprintf(buf, ip_len, fmt, sub); break; case ISCSI_BOOT_ETH_GATEWAY: - rc = snprintf(str, ip_len, fmt, gw); + rc = snprintf(buf, ip_len, fmt, gw); break; case ISCSI_BOOT_ETH_FLAGS: - rc = snprintf(str, 3, "%hhd\n", + rc = snprintf(buf, 3, "%hhd\n", SYSFS_FLAG_FW_SEL_BOOT); break; case ISCSI_BOOT_ETH_INDEX: - rc = snprintf(str, 3, "0\n"); + rc = snprintf(buf, 3, "0\n"); break; case ISCSI_BOOT_ETH_MAC: - rc = sysfs_format_mac(str, qedi->mac, ETH_ALEN); + rc = sysfs_format_mac(buf, qedi->mac, ETH_ALEN); break; case ISCSI_BOOT_ETH_VLAN: - rc = snprintf(str, 12, "%d\n", + rc = snprintf(buf, 12, "%d\n", GET_FIELD2(initiator->generic_cont0, NVM_ISCSI_CFG_INITIATOR_VLAN)); break; case ISCSI_BOOT_ETH_ORIGIN: if (dhcp_en) - rc = snprintf(str, 3, "3\n"); + rc = snprintf(buf, 3, "3\n"); break; default: rc = 0; @@ -1819,7 +1818,6 @@ static ssize_t qedi_show_boot_ini_info(void *data, int type, char *buf) { struct qedi_ctx *qedi = data; struct nvm_iscsi_initiator *initiator; - char *str = buf; int rc; struct nvm_iscsi_block *block; @@ -1831,8 +1829,8 @@ static ssize_t qedi_show_boot_ini_info(void *data, int type, char *buf) switch (type) { case ISCSI_BOOT_INI_INITIATOR_NAME: - rc = snprintf(str, NVM_ISCSI_CFG_ISCSI_NAME_MAX_LEN, "%s\n", - initiator->initiator_name.byte); + rc = sprintf(buf, "%.*s\n", NVM_ISCSI_CFG_ISCSI_NAME_MAX_LEN, + initiator->initiator_name.byte); break; default: rc = 0; @@ -1860,7 +1858,6 @@ static ssize_t qedi_show_boot_tgt_info(struct qedi_ctx *qedi, int type, char *buf, enum qedi_nvm_tgts idx) { - char *str = buf; int rc = 1; u32 ctrl_flags, ipv6_en, chap_en, mchap_en, ip_len; struct nvm_iscsi_block *block; @@ -1899,48 +1896,48 @@ qedi_show_boot_tgt_info(struct qedi_ctx *qedi, int type, switch (type) { case ISCSI_BOOT_TGT_NAME: - rc = snprintf(str, NVM_ISCSI_CFG_ISCSI_NAME_MAX_LEN, "%s\n", - block->target[idx].target_name.byte); + rc = sprintf(buf, "%.*s\n", NVM_ISCSI_CFG_ISCSI_NAME_MAX_LEN, + block->target[idx].target_name.byte); break; case ISCSI_BOOT_TGT_IP_ADDR: if (ipv6_en) - rc = snprintf(str, ip_len, "%pI6\n", + rc = snprintf(buf, ip_len, "%pI6\n", block->target[idx].ipv6_addr.byte); else - rc = snprintf(str, ip_len, "%pI4\n", + rc = snprintf(buf, ip_len, "%pI4\n", block->target[idx].ipv4_addr.byte); break; case ISCSI_BOOT_TGT_PORT: - rc = snprintf(str, 12, "%d\n", + rc = snprintf(buf, 12, "%d\n", GET_FIELD2(block->target[idx].generic_cont0, NVM_ISCSI_CFG_TARGET_TCP_PORT)); break; case ISCSI_BOOT_TGT_LUN: - rc = snprintf(str, 22, "%.*d\n", + rc = snprintf(buf, 22, "%.*d\n", block->target[idx].lun.value[1], block->target[idx].lun.value[0]); break; case ISCSI_BOOT_TGT_CHAP_NAME: - rc = snprintf(str, NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN, "%s\n", - chap_name); + rc = sprintf(buf, "%.*s\n", NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN, + chap_name); break; case ISCSI_BOOT_TGT_CHAP_SECRET: - rc = snprintf(str, NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN, "%s\n", - chap_secret); + rc = sprintf(buf, "%.*s\n", NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN, + chap_secret); break; case ISCSI_BOOT_TGT_REV_CHAP_NAME: - rc = snprintf(str, NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN, "%s\n", - mchap_name); + rc = sprintf(buf, "%.*s\n", NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN, + mchap_name); break; case ISCSI_BOOT_TGT_REV_CHAP_SECRET: - rc = snprintf(str, NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN, "%s\n", - mchap_secret); + rc = sprintf(buf, "%.*s\n", NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN, + mchap_secret); break; case ISCSI_BOOT_TGT_FLAGS: - rc = snprintf(str, 3, "%hhd\n", SYSFS_FLAG_FW_SEL_BOOT); + rc = snprintf(buf, 3, "%hhd\n", SYSFS_FLAG_FW_SEL_BOOT); break; case ISCSI_BOOT_TGT_NIC_ASSOC: - rc = snprintf(str, 3, "0\n"); + rc = snprintf(buf, 3, "0\n"); break; default: rc = 0; diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index aececf664654..2dea1129d396 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -59,8 +59,6 @@ qla2x00_sp_timeout(struct timer_list *t) req->outstanding_cmds[sp->handle] = NULL; iocb = &sp->u.iocb_cmd; iocb->timeout(sp); - if (sp->type != SRB_ELS_DCMD) - sp->free(sp); spin_unlock_irqrestore(&vha->hw->hardware_lock, flags); } @@ -102,7 +100,6 @@ qla2x00_async_iocb_timeout(void *data) srb_t *sp = data; fc_port_t *fcport = sp->fcport; struct srb_iocb *lio = &sp->u.iocb_cmd; - struct event_arg ea; if (fcport) { ql_dbg(ql_dbg_disc, fcport->vha, 0x2071, @@ -117,25 +114,13 @@ qla2x00_async_iocb_timeout(void *data) switch (sp->type) { case SRB_LOGIN_CMD: - if (!fcport) - break; /* Retry as needed. */ lio->u.logio.data[0] = MBS_COMMAND_ERROR; lio->u.logio.data[1] = lio->u.logio.flags & SRB_LOGIN_RETRIED ? QLA_LOGIO_LOGIN_RETRIED : 0; - memset(&ea, 0, sizeof(ea)); - ea.event = FCME_PLOGI_DONE; - ea.fcport = sp->fcport; - ea.data[0] = lio->u.logio.data[0]; - ea.data[1] = lio->u.logio.data[1]; - ea.sp = sp; - qla24xx_handle_plogi_done_event(fcport->vha, &ea); + sp->done(sp, QLA_FUNCTION_TIMEOUT); break; case SRB_LOGOUT_CMD: - if (!fcport) - break; - qlt_logo_completion_handler(fcport, QLA_FUNCTION_TIMEOUT); - break; case SRB_CT_PTHRU_CMD: case SRB_MB_IOCB: case SRB_NACK_PLOGI: @@ -235,12 +220,10 @@ static void qla2x00_async_logout_sp_done(void *ptr, int res) { srb_t *sp = ptr; - struct srb_iocb *lio = &sp->u.iocb_cmd; sp->fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE); - if (!test_bit(UNLOADING, &sp->vha->dpc_flags)) - qla2x00_post_async_logout_done_work(sp->vha, sp->fcport, - lio->u.logio.data); + sp->fcport->login_gen++; + qlt_logo_completion_handler(sp->fcport, res); sp->free(sp); } diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c index 1b62e943ec49..8d00d559bd26 100644 --- a/drivers/scsi/qla2xxx/qla_iocb.c +++ b/drivers/scsi/qla2xxx/qla_iocb.c @@ -3275,12 +3275,11 @@ qla24xx_abort_iocb(srb_t *sp, struct abort_entry_24xx *abt_iocb) memset(abt_iocb, 0, sizeof(struct abort_entry_24xx)); abt_iocb->entry_type = ABORT_IOCB_TYPE; abt_iocb->entry_count = 1; - abt_iocb->handle = - cpu_to_le32(MAKE_HANDLE(aio->u.abt.req_que_no, - aio->u.abt.cmd_hndl)); + abt_iocb->handle = cpu_to_le32(MAKE_HANDLE(req->id, sp->handle)); abt_iocb->nport_handle = cpu_to_le16(sp->fcport->loop_id); abt_iocb->handle_to_abort = - cpu_to_le32(MAKE_HANDLE(req->id, aio->u.abt.cmd_hndl)); + cpu_to_le32(MAKE_HANDLE(aio->u.abt.req_que_no, + aio->u.abt.cmd_hndl)); abt_iocb->port_id[0] = sp->fcport->d_id.b.al_pa; abt_iocb->port_id[1] = sp->fcport->d_id.b.area; abt_iocb->port_id[2] = sp->fcport->d_id.b.domain; diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index 14109d86c3f6..89f93ebd819d 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -272,7 +272,8 @@ qla2x00_mbx_completion(scsi_qla_host_t *vha, uint16_t mb0) struct device_reg_2xxx __iomem *reg = &ha->iobase->isp; /* Read all mbox registers? */ - mboxes = (1 << ha->mbx_count) - 1; + WARN_ON_ONCE(ha->mbx_count > 32); + mboxes = (1ULL << ha->mbx_count) - 1; if (!ha->mcp) ql_dbg(ql_dbg_async, vha, 0x5001, "MBX pointer ERROR.\n"); else @@ -2880,7 +2881,8 @@ qla24xx_mbx_completion(scsi_qla_host_t *vha, uint16_t mb0) struct device_reg_24xx __iomem *reg = &ha->iobase->isp24; /* Read all mbox registers? */ - mboxes = (1 << ha->mbx_count) - 1; + WARN_ON_ONCE(ha->mbx_count > 32); + mboxes = (1ULL << ha->mbx_count) - 1; if (!ha->mcp) ql_dbg(ql_dbg_async, vha, 0x504e, "MBX pointer ERROR.\n"); else diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 12ee6e02d146..afcb5567998a 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -3625,6 +3625,8 @@ qla2x00_remove_one(struct pci_dev *pdev) } qla2x00_wait_for_hba_ready(base_vha); + qla2x00_wait_for_sess_deletion(base_vha); + /* * if UNLOAD flag is already set, then continue unload, * where it was set first. diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index fc89af8fe256..896b2d8bd803 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -4871,8 +4871,6 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha, sess); qlt_send_term_imm_notif(vha, iocb, 1); res = 0; - spin_lock_irqsave(&tgt->ha->tgt.sess_lock, - flags); break; } diff --git a/drivers/scsi/qla4xxx/ql4_def.h b/drivers/scsi/qla4xxx/ql4_def.h index fc233717355f..817f312023a9 100644 --- a/drivers/scsi/qla4xxx/ql4_def.h +++ b/drivers/scsi/qla4xxx/ql4_def.h @@ -168,6 +168,8 @@ #define DEV_DB_NON_PERSISTENT 0 #define DEV_DB_PERSISTENT 1 +#define QL4_ISP_REG_DISCONNECT 0xffffffffU + #define COPY_ISID(dst_isid, src_isid) { \ int i, j; \ for (i = 0, j = ISID_SIZE - 1; i < ISID_SIZE;) \ diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c index 82e889bbe0ed..fc2c97d9a0d6 100644 --- a/drivers/scsi/qla4xxx/ql4_os.c +++ b/drivers/scsi/qla4xxx/ql4_os.c @@ -262,6 +262,24 @@ static struct iscsi_transport qla4xxx_iscsi_transport = { static struct scsi_transport_template *qla4xxx_scsi_transport; +static int qla4xxx_isp_check_reg(struct scsi_qla_host *ha) +{ + u32 reg_val = 0; + int rval = QLA_SUCCESS; + + if (is_qla8022(ha)) + reg_val = readl(&ha->qla4_82xx_reg->host_status); + else if (is_qla8032(ha) || is_qla8042(ha)) + reg_val = qla4_8xxx_rd_direct(ha, QLA8XXX_PEG_ALIVE_COUNTER); + else + reg_val = readw(&ha->reg->ctrl_status); + + if (reg_val == QL4_ISP_REG_DISCONNECT) + rval = QLA_ERROR; + + return rval; +} + static int qla4xxx_send_ping(struct Scsi_Host *shost, uint32_t iface_num, uint32_t iface_type, uint32_t payload_size, uint32_t pid, struct sockaddr *dst_addr) @@ -9186,10 +9204,17 @@ static int qla4xxx_eh_abort(struct scsi_cmnd *cmd) struct srb *srb = NULL; int ret = SUCCESS; int wait = 0; + int rval; ql4_printk(KERN_INFO, ha, "scsi%ld:%d:%llu: Abort command issued cmd=%p, cdb=0x%x\n", ha->host_no, id, lun, cmd, cmd->cmnd[0]); + rval = qla4xxx_isp_check_reg(ha); + if (rval != QLA_SUCCESS) { + ql4_printk(KERN_INFO, ha, "PCI/Register disconnect, exiting.\n"); + return FAILED; + } + spin_lock_irqsave(&ha->hardware_lock, flags); srb = (struct srb *) CMD_SP(cmd); if (!srb) { @@ -9241,6 +9266,7 @@ static int qla4xxx_eh_device_reset(struct scsi_cmnd *cmd) struct scsi_qla_host *ha = to_qla_host(cmd->device->host); struct ddb_entry *ddb_entry = cmd->device->hostdata; int ret = FAILED, stat; + int rval; if (!ddb_entry) return ret; @@ -9260,6 +9286,12 @@ static int qla4xxx_eh_device_reset(struct scsi_cmnd *cmd) cmd, jiffies, cmd->request->timeout / HZ, ha->dpc_flags, cmd->result, cmd->allowed)); + rval = qla4xxx_isp_check_reg(ha); + if (rval != QLA_SUCCESS) { + ql4_printk(KERN_INFO, ha, "PCI/Register disconnect, exiting.\n"); + return FAILED; + } + /* FIXME: wait for hba to go online */ stat = qla4xxx_reset_lun(ha, ddb_entry, cmd->device->lun); if (stat != QLA_SUCCESS) { @@ -9303,6 +9335,7 @@ static int qla4xxx_eh_target_reset(struct scsi_cmnd *cmd) struct scsi_qla_host *ha = to_qla_host(cmd->device->host); struct ddb_entry *ddb_entry = cmd->device->hostdata; int stat, ret; + int rval; if (!ddb_entry) return FAILED; @@ -9320,6 +9353,12 @@ static int qla4xxx_eh_target_reset(struct scsi_cmnd *cmd) ha->host_no, cmd, jiffies, cmd->request->timeout / HZ, ha->dpc_flags, cmd->result, cmd->allowed)); + rval = qla4xxx_isp_check_reg(ha); + if (rval != QLA_SUCCESS) { + ql4_printk(KERN_INFO, ha, "PCI/Register disconnect, exiting.\n"); + return FAILED; + } + stat = qla4xxx_reset_target(ha, ddb_entry); if (stat != QLA_SUCCESS) { starget_printk(KERN_INFO, scsi_target(cmd->device), @@ -9374,9 +9413,16 @@ static int qla4xxx_eh_host_reset(struct scsi_cmnd *cmd) { int return_status = FAILED; struct scsi_qla_host *ha; + int rval; ha = to_qla_host(cmd->device->host); + rval = qla4xxx_isp_check_reg(ha); + if (rval != QLA_SUCCESS) { + ql4_printk(KERN_INFO, ha, "PCI/Register disconnect, exiting.\n"); + return FAILED; + } + if ((is_qla8032(ha) || is_qla8042(ha)) && ql4xdontresethba) qla4_83xx_set_idc_dontreset(ha); diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 40fc7a590e81..6be5ab32c94f 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1657,7 +1657,7 @@ static struct scsi_host_template scsi_driver = { .eh_timed_out = storvsc_eh_timed_out, .slave_alloc = storvsc_device_alloc, .slave_configure = storvsc_device_configure, - .cmd_per_lun = 255, + .cmd_per_lun = 2048, .this_id = -1, .use_clustering = ENABLE_CLUSTERING, /* Make sure we dont get a sg segment crosses a page boundary */ diff --git a/drivers/scsi/sym53c8xx_2/sym_hipd.c b/drivers/scsi/sym53c8xx_2/sym_hipd.c index ca360daa6a25..378af306fda1 100644 --- a/drivers/scsi/sym53c8xx_2/sym_hipd.c +++ b/drivers/scsi/sym53c8xx_2/sym_hipd.c @@ -536,7 +536,7 @@ sym_getsync(struct sym_hcb *np, u_char dt, u_char sfac, u_char *divp, u_char *fa * Look for the greatest clock divisor that allows an * input speed faster than the period. */ - while (div-- > 0) + while (--div > 0) if (kpc >= (div_10M[div] << 2)) break; /* diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index a355d989b414..c7da2c185990 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -4352,6 +4352,8 @@ static int ufshcd_slave_alloc(struct scsi_device *sdev) /* REPORT SUPPORTED OPERATION CODES is not supported */ sdev->no_report_opcodes = 1; + /* WRITE_SAME command is not supported */ + sdev->no_write_same = 1; ufshcd_set_queue_depth(sdev); diff --git a/drivers/soc/qcom/qmi_interface.c b/drivers/soc/qcom/qmi_interface.c index 877611d5c42b..321982277697 100644 --- a/drivers/soc/qcom/qmi_interface.c +++ b/drivers/soc/qcom/qmi_interface.c @@ -586,7 +586,6 @@ static struct socket *qmi_sock_create(struct qmi_handle *qmi, struct sockaddr_qrtr *sq) { struct socket *sock; - int sl = sizeof(*sq); int ret; ret = sock_create_kern(&init_net, AF_QIPCRTR, SOCK_DGRAM, @@ -594,7 +593,7 @@ static struct socket *qmi_sock_create(struct qmi_handle *qmi, if (ret < 0) return ERR_PTR(ret); - ret = kernel_getsockname(sock, (struct sockaddr *)sq, &sl); + ret = kernel_getsockname(sock, (struct sockaddr *)sq); if (ret < 0) { sock_release(sock); return ERR_PTR(ret); diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c index bbdc53b686dd..6dbba5aff191 100644 --- a/drivers/staging/android/ashmem.c +++ b/drivers/staging/android/ashmem.c @@ -702,30 +702,32 @@ static int ashmem_pin_unpin(struct ashmem_area *asma, unsigned long cmd, size_t pgstart, pgend; int ret = -EINVAL; + mutex_lock(&ashmem_mutex); + if (unlikely(!asma->file)) - return -EINVAL; + goto out_unlock; - if (unlikely(copy_from_user(&pin, p, sizeof(pin)))) - return -EFAULT; + if (unlikely(copy_from_user(&pin, p, sizeof(pin)))) { + ret = -EFAULT; + goto out_unlock; + } /* per custom, you can pass zero for len to mean "everything onward" */ if (!pin.len) pin.len = PAGE_ALIGN(asma->size) - pin.offset; if (unlikely((pin.offset | pin.len) & ~PAGE_MASK)) - return -EINVAL; + goto out_unlock; if (unlikely(((__u32)-1) - pin.offset < pin.len)) - return -EINVAL; + goto out_unlock; if (unlikely(PAGE_ALIGN(asma->size) < pin.offset + pin.len)) - return -EINVAL; + goto out_unlock; pgstart = pin.offset / PAGE_SIZE; pgend = pgstart + (pin.len / PAGE_SIZE) - 1; - mutex_lock(&ashmem_mutex); - switch (cmd) { case ASHMEM_PIN: ret = ashmem_pin(asma, pgstart, pgend); @@ -738,6 +740,7 @@ static int ashmem_pin_unpin(struct ashmem_area *asma, unsigned long cmd, break; } +out_unlock: mutex_unlock(&ashmem_mutex); return ret; diff --git a/drivers/staging/android/ion/ion_cma_heap.c b/drivers/staging/android/ion/ion_cma_heap.c index 94e06925c712..49718c96bf9e 100644 --- a/drivers/staging/android/ion/ion_cma_heap.c +++ b/drivers/staging/android/ion/ion_cma_heap.c @@ -12,6 +12,7 @@ #include <linux/err.h> #include <linux/cma.h> #include <linux/scatterlist.h> +#include <linux/highmem.h> #include "ion.h" @@ -42,6 +43,22 @@ static int ion_cma_allocate(struct ion_heap *heap, struct ion_buffer *buffer, if (!pages) return -ENOMEM; + if (PageHighMem(pages)) { + unsigned long nr_clear_pages = nr_pages; + struct page *page = pages; + + while (nr_clear_pages > 0) { + void *vaddr = kmap_atomic(page); + + memset(vaddr, 0, PAGE_SIZE); + kunmap_atomic(vaddr); + page++; + nr_clear_pages--; + } + } else { + memset(page_address(pages), 0, size); + } + table = kmalloc(sizeof(*table), GFP_KERNEL); if (!table) goto err; diff --git a/drivers/staging/fsl-mc/bus/Kconfig b/drivers/staging/fsl-mc/bus/Kconfig index 1f9100049176..b35ef7ee6901 100644 --- a/drivers/staging/fsl-mc/bus/Kconfig +++ b/drivers/staging/fsl-mc/bus/Kconfig @@ -7,7 +7,7 @@ config FSL_MC_BUS bool "QorIQ DPAA2 fsl-mc bus driver" - depends on OF && (ARCH_LAYERSCAPE || (COMPILE_TEST && (ARM || ARM64 || X86 || PPC))) + depends on OF && (ARCH_LAYERSCAPE || (COMPILE_TEST && (ARM || ARM64 || X86_LOCAL_APIC || PPC))) select GENERIC_MSI_IRQ_DOMAIN help Driver to enable the bus infrastructure for the QorIQ DPAA2 diff --git a/drivers/staging/fsl-mc/bus/irq-gic-v3-its-fsl-mc-msi.c b/drivers/staging/fsl-mc/bus/irq-gic-v3-its-fsl-mc-msi.c index 5064d5ddf581..fc2013aade51 100644 --- a/drivers/staging/fsl-mc/bus/irq-gic-v3-its-fsl-mc-msi.c +++ b/drivers/staging/fsl-mc/bus/irq-gic-v3-its-fsl-mc-msi.c @@ -73,6 +73,8 @@ static int __init its_fsl_mc_msi_init(void) for (np = of_find_matching_node(NULL, its_device_id); np; np = of_find_matching_node(np, its_device_id)) { + if (!of_device_is_available(np)) + continue; if (!of_property_read_bool(np, "msi-controller")) continue; diff --git a/drivers/staging/iio/adc/ad7192.c b/drivers/staging/iio/adc/ad7192.c index f01595593ce2..425e8b82533b 100644 --- a/drivers/staging/iio/adc/ad7192.c +++ b/drivers/staging/iio/adc/ad7192.c @@ -141,6 +141,8 @@ #define AD7192_GPOCON_P1DAT BIT(1) /* P1 state */ #define AD7192_GPOCON_P0DAT BIT(0) /* P0 state */ +#define AD7192_EXT_FREQ_MHZ_MIN 2457600 +#define AD7192_EXT_FREQ_MHZ_MAX 5120000 #define AD7192_INT_FREQ_MHZ 4915200 /* NOTE: @@ -218,6 +220,12 @@ static int ad7192_calibrate_all(struct ad7192_state *st) ARRAY_SIZE(ad7192_calib_arr)); } +static inline bool ad7192_valid_external_frequency(u32 freq) +{ + return (freq >= AD7192_EXT_FREQ_MHZ_MIN && + freq <= AD7192_EXT_FREQ_MHZ_MAX); +} + static int ad7192_setup(struct ad7192_state *st, const struct ad7192_platform_data *pdata) { @@ -243,17 +251,20 @@ static int ad7192_setup(struct ad7192_state *st, id); switch (pdata->clock_source_sel) { - case AD7192_CLK_EXT_MCLK1_2: - case AD7192_CLK_EXT_MCLK2: - st->mclk = AD7192_INT_FREQ_MHZ; - break; case AD7192_CLK_INT: case AD7192_CLK_INT_CO: - if (pdata->ext_clk_hz) - st->mclk = pdata->ext_clk_hz; - else - st->mclk = AD7192_INT_FREQ_MHZ; + st->mclk = AD7192_INT_FREQ_MHZ; break; + case AD7192_CLK_EXT_MCLK1_2: + case AD7192_CLK_EXT_MCLK2: + if (ad7192_valid_external_frequency(pdata->ext_clk_hz)) { + st->mclk = pdata->ext_clk_hz; + break; + } + dev_err(&st->sd.spi->dev, "Invalid frequency setting %u\n", + pdata->ext_clk_hz); + ret = -EINVAL; + goto out; default: ret = -EINVAL; goto out; diff --git a/drivers/staging/iio/impedance-analyzer/ad5933.c b/drivers/staging/iio/impedance-analyzer/ad5933.c index 2b28fb9c0048..3bcf49466361 100644 --- a/drivers/staging/iio/impedance-analyzer/ad5933.c +++ b/drivers/staging/iio/impedance-analyzer/ad5933.c @@ -648,8 +648,6 @@ static int ad5933_register_ring_funcs_and_init(struct iio_dev *indio_dev) /* Ring buffer functions - here trigger setup related */ indio_dev->setup_ops = &ad5933_ring_setup_ops; - indio_dev->modes |= INDIO_BUFFER_HARDWARE; - return 0; } @@ -762,7 +760,7 @@ static int ad5933_probe(struct i2c_client *client, indio_dev->dev.parent = &client->dev; indio_dev->info = &ad5933_info; indio_dev->name = id->name; - indio_dev->modes = INDIO_DIRECT_MODE; + indio_dev->modes = (INDIO_BUFFER_SOFTWARE | INDIO_DIRECT_MODE); indio_dev->channels = ad5933_channels; indio_dev->num_channels = ARRAY_SIZE(ad5933_channels); diff --git a/drivers/staging/ipx/af_ipx.c b/drivers/staging/ipx/af_ipx.c index d21a9d128d3e..5703dd176787 100644 --- a/drivers/staging/ipx/af_ipx.c +++ b/drivers/staging/ipx/af_ipx.c @@ -1577,7 +1577,7 @@ out: static int ipx_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { struct ipx_address *addr; struct sockaddr_ipx sipx; @@ -1585,8 +1585,6 @@ static int ipx_getname(struct socket *sock, struct sockaddr *uaddr, struct ipx_sock *ipxs = ipx_sk(sk); int rc; - *uaddr_len = sizeof(struct sockaddr_ipx); - lock_sock(sk); if (peer) { rc = -ENOTCONN; @@ -1620,7 +1618,7 @@ static int ipx_getname(struct socket *sock, struct sockaddr *uaddr, sipx.sipx_zero = 0; memcpy(uaddr, &sipx, sizeof(sipx)); - rc = 0; + rc = sizeof(struct sockaddr_ipx); out: release_sock(sk); return rc; diff --git a/drivers/staging/irda/net/af_irda.c b/drivers/staging/irda/net/af_irda.c index 2f1e9ab3d6d0..c13553a9ee11 100644 --- a/drivers/staging/irda/net/af_irda.c +++ b/drivers/staging/irda/net/af_irda.c @@ -697,7 +697,7 @@ static int irda_discover_daddr_and_lsap_sel(struct irda_sock *self, char *name) * */ static int irda_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { struct sockaddr_irda saddr; struct sock *sk = sock->sk; @@ -720,11 +720,9 @@ static int irda_getname(struct socket *sock, struct sockaddr *uaddr, pr_debug("%s(), tsap_sel = %#x\n", __func__, saddr.sir_lsap_sel); pr_debug("%s(), addr = %08x\n", __func__, saddr.sir_addr); - /* uaddr_len come to us uninitialised */ - *uaddr_len = sizeof (struct sockaddr_irda); - memcpy(uaddr, &saddr, *uaddr_len); + memcpy(uaddr, &saddr, sizeof (struct sockaddr_irda)); - return 0; + return sizeof (struct sockaddr_irda); } /* diff --git a/drivers/staging/lustre/lnet/lnet/lib-socket.c b/drivers/staging/lustre/lnet/lnet/lib-socket.c index ce93806eefca..1bee667802b0 100644 --- a/drivers/staging/lustre/lnet/lnet/lib-socket.c +++ b/drivers/staging/lustre/lnet/lnet/lib-socket.c @@ -448,14 +448,13 @@ int lnet_sock_getaddr(struct socket *sock, bool remote, __u32 *ip, int *port) { struct sockaddr_in sin; - int len = sizeof(sin); int rc; if (remote) - rc = kernel_getpeername(sock, (struct sockaddr *)&sin, &len); + rc = kernel_getpeername(sock, (struct sockaddr *)&sin); else - rc = kernel_getsockname(sock, (struct sockaddr *)&sin, &len); - if (rc) { + rc = kernel_getsockname(sock, (struct sockaddr *)&sin); + if (rc < 0) { CERROR("Error %d getting sock %s IP/port\n", rc, remote ? "peer" : "local"); return rc; diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index 64c5a57b92e4..99501785cdc1 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -1020,7 +1020,7 @@ int iscsit_accept_np(struct iscsi_np *np, struct iscsi_conn *conn) struct socket *new_sock, *sock = np->np_socket; struct sockaddr_in sock_in; struct sockaddr_in6 sock_in6; - int rc, err; + int rc; rc = kernel_accept(sock, &new_sock, 0); if (rc < 0) @@ -1033,8 +1033,8 @@ int iscsit_accept_np(struct iscsi_np *np, struct iscsi_conn *conn) memset(&sock_in6, 0, sizeof(struct sockaddr_in6)); rc = conn->sock->ops->getname(conn->sock, - (struct sockaddr *)&sock_in6, &err, 1); - if (!rc) { + (struct sockaddr *)&sock_in6, 1); + if (rc >= 0) { if (!ipv6_addr_v4mapped(&sock_in6.sin6_addr)) { memcpy(&conn->login_sockaddr, &sock_in6, sizeof(sock_in6)); } else { @@ -1047,8 +1047,8 @@ int iscsit_accept_np(struct iscsi_np *np, struct iscsi_conn *conn) } rc = conn->sock->ops->getname(conn->sock, - (struct sockaddr *)&sock_in6, &err, 0); - if (!rc) { + (struct sockaddr *)&sock_in6, 0); + if (rc >= 0) { if (!ipv6_addr_v4mapped(&sock_in6.sin6_addr)) { memcpy(&conn->local_sockaddr, &sock_in6, sizeof(sock_in6)); } else { @@ -1063,13 +1063,13 @@ int iscsit_accept_np(struct iscsi_np *np, struct iscsi_conn *conn) memset(&sock_in, 0, sizeof(struct sockaddr_in)); rc = conn->sock->ops->getname(conn->sock, - (struct sockaddr *)&sock_in, &err, 1); - if (!rc) + (struct sockaddr *)&sock_in, 1); + if (rc >= 0) memcpy(&conn->login_sockaddr, &sock_in, sizeof(sock_in)); rc = conn->sock->ops->getname(conn->sock, - (struct sockaddr *)&sock_in, &err, 0); - if (!rc) + (struct sockaddr *)&sock_in, 0); + if (rc >= 0) memcpy(&conn->local_sockaddr, &sock_in, sizeof(sock_in)); } diff --git a/drivers/usb/Kconfig b/drivers/usb/Kconfig index f699abab1787..148f3ee70286 100644 --- a/drivers/usb/Kconfig +++ b/drivers/usb/Kconfig @@ -19,6 +19,12 @@ config USB_EHCI_BIG_ENDIAN_MMIO config USB_EHCI_BIG_ENDIAN_DESC bool +config USB_UHCI_BIG_ENDIAN_MMIO + bool + +config USB_UHCI_BIG_ENDIAN_DESC + bool + menuconfig USB_SUPPORT bool "USB support" depends on HAS_IOMEM diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 06b3b54a0e68..7b366a6c0b49 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -174,6 +174,7 @@ static int acm_wb_alloc(struct acm *acm) wb = &acm->wb[wbn]; if (!wb->use) { wb->use = 1; + wb->len = 0; return wbn; } wbn = (wbn + 1) % ACM_NW; @@ -805,16 +806,18 @@ static int acm_tty_write(struct tty_struct *tty, static void acm_tty_flush_chars(struct tty_struct *tty) { struct acm *acm = tty->driver_data; - struct acm_wb *cur = acm->putbuffer; + struct acm_wb *cur; int err; unsigned long flags; + spin_lock_irqsave(&acm->write_lock, flags); + + cur = acm->putbuffer; if (!cur) /* nothing to do */ - return; + goto out; acm->putbuffer = NULL; err = usb_autopm_get_interface_async(acm->control); - spin_lock_irqsave(&acm->write_lock, flags); if (err < 0) { cur->use = 0; acm->putbuffer = cur; diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 4024926c1d68..f4a548471f0f 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -226,6 +226,9 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x1a0a, 0x0200), .driver_info = USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL }, + /* Corsair K70 RGB */ + { USB_DEVICE(0x1b1c, 0x1b13), .driver_info = USB_QUIRK_DELAY_INIT }, + /* Corsair Strafe RGB */ { USB_DEVICE(0x1b1c, 0x1b20), .driver_info = USB_QUIRK_DELAY_INIT }, diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c index e4c3ce0de5de..5bcad1d869b5 100644 --- a/drivers/usb/dwc2/gadget.c +++ b/drivers/usb/dwc2/gadget.c @@ -1917,7 +1917,9 @@ static void dwc2_hsotg_program_zlp(struct dwc2_hsotg *hsotg, /* Not specific buffer needed for ep0 ZLP */ dma_addr_t dma = hs_ep->desc_list_dma; - dwc2_gadget_set_ep0_desc_chain(hsotg, hs_ep); + if (!index) + dwc2_gadget_set_ep0_desc_chain(hsotg, hs_ep); + dwc2_gadget_config_nonisoc_xfer_ddma(hs_ep, dma, 0); } else { dwc2_writel(DXEPTSIZ_MC(1) | DXEPTSIZ_PKTCNT(1) | @@ -2974,9 +2976,13 @@ static void dwc2_hsotg_epint(struct dwc2_hsotg *hsotg, unsigned int idx, if (ints & DXEPINT_STSPHSERCVD) { dev_dbg(hsotg->dev, "%s: StsPhseRcvd\n", __func__); - /* Move to STATUS IN for DDMA */ - if (using_desc_dma(hsotg)) - dwc2_hsotg_ep0_zlp(hsotg, true); + /* Safety check EP0 state when STSPHSERCVD asserted */ + if (hsotg->ep0_state == DWC2_EP0_DATA_OUT) { + /* Move to STATUS IN for DDMA */ + if (using_desc_dma(hsotg)) + dwc2_hsotg_ep0_zlp(hsotg, true); + } + } if (ints & DXEPINT_BACK2BACKSETUP) @@ -3375,12 +3381,6 @@ void dwc2_hsotg_core_init_disconnected(struct dwc2_hsotg *hsotg, dwc2_writel(dwc2_hsotg_ep0_mps(hsotg->eps_out[0]->ep.maxpacket) | DXEPCTL_USBACTEP, hsotg->regs + DIEPCTL0); - dwc2_hsotg_enqueue_setup(hsotg); - - dev_dbg(hsotg->dev, "EP0: DIEPCTL0=0x%08x, DOEPCTL0=0x%08x\n", - dwc2_readl(hsotg->regs + DIEPCTL0), - dwc2_readl(hsotg->regs + DOEPCTL0)); - /* clear global NAKs */ val = DCTL_CGOUTNAK | DCTL_CGNPINNAK; if (!is_usb_reset) @@ -3391,6 +3391,12 @@ void dwc2_hsotg_core_init_disconnected(struct dwc2_hsotg *hsotg, mdelay(3); hsotg->lx_state = DWC2_L0; + + dwc2_hsotg_enqueue_setup(hsotg); + + dev_dbg(hsotg->dev, "EP0: DIEPCTL0=0x%08x, DOEPCTL0=0x%08x\n", + dwc2_readl(hsotg->regs + DIEPCTL0), + dwc2_readl(hsotg->regs + DOEPCTL0)); } static void dwc2_hsotg_core_disconnect(struct dwc2_hsotg *hsotg) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index ade2ab00d37a..f1d838a4acd6 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -100,6 +100,8 @@ static void dwc3_set_prtcap(struct dwc3 *dwc, u32 mode) reg &= ~(DWC3_GCTL_PRTCAPDIR(DWC3_GCTL_PRTCAP_OTG)); reg |= DWC3_GCTL_PRTCAPDIR(mode); dwc3_writel(dwc->regs, DWC3_GCTL, reg); + + dwc->current_dr_role = mode; } static void __dwc3_set_mode(struct work_struct *work) @@ -133,8 +135,6 @@ static void __dwc3_set_mode(struct work_struct *work) dwc3_set_prtcap(dwc, dwc->desired_dr_role); - dwc->current_dr_role = dwc->desired_dr_role; - spin_unlock_irqrestore(&dwc->lock, flags); switch (dwc->desired_dr_role) { @@ -219,7 +219,7 @@ static int dwc3_core_soft_reset(struct dwc3 *dwc) * XHCI driver will reset the host block. If dwc3 was configured for * host-only mode, then we can return early. */ - if (dwc->dr_mode == USB_DR_MODE_HOST) + if (dwc->current_dr_role == DWC3_GCTL_PRTCAP_HOST) return 0; reg = dwc3_readl(dwc->regs, DWC3_DCTL); @@ -234,6 +234,9 @@ static int dwc3_core_soft_reset(struct dwc3 *dwc) udelay(1); } while (--retries); + phy_exit(dwc->usb3_generic_phy); + phy_exit(dwc->usb2_generic_phy); + return -ETIMEDOUT; } @@ -483,6 +486,22 @@ static void dwc3_cache_hwparams(struct dwc3 *dwc) parms->hwparams8 = dwc3_readl(dwc->regs, DWC3_GHWPARAMS8); } +static int dwc3_core_ulpi_init(struct dwc3 *dwc) +{ + int intf; + int ret = 0; + + intf = DWC3_GHWPARAMS3_HSPHY_IFC(dwc->hwparams.hwparams3); + + if (intf == DWC3_GHWPARAMS3_HSPHY_IFC_ULPI || + (intf == DWC3_GHWPARAMS3_HSPHY_IFC_UTMI_ULPI && + dwc->hsphy_interface && + !strncmp(dwc->hsphy_interface, "ulpi", 4))) + ret = dwc3_ulpi_init(dwc); + + return ret; +} + /** * dwc3_phy_setup - Configure USB PHY Interface of DWC3 Core * @dwc: Pointer to our controller context structure @@ -494,7 +513,6 @@ static void dwc3_cache_hwparams(struct dwc3 *dwc) static int dwc3_phy_setup(struct dwc3 *dwc) { u32 reg; - int ret; reg = dwc3_readl(dwc->regs, DWC3_GUSB3PIPECTL(0)); @@ -565,9 +583,6 @@ static int dwc3_phy_setup(struct dwc3 *dwc) } /* FALLTHROUGH */ case DWC3_GHWPARAMS3_HSPHY_IFC_ULPI: - ret = dwc3_ulpi_init(dwc); - if (ret) - return ret; /* FALLTHROUGH */ default: break; @@ -724,6 +739,7 @@ static void dwc3_core_setup_global_control(struct dwc3 *dwc) } static int dwc3_core_get_phy(struct dwc3 *dwc); +static int dwc3_core_ulpi_init(struct dwc3 *dwc); /** * dwc3_core_init - Low-level initialization of DWC3 Core @@ -755,17 +771,27 @@ static int dwc3_core_init(struct dwc3 *dwc) dwc->maximum_speed = USB_SPEED_HIGH; } - ret = dwc3_core_get_phy(dwc); + ret = dwc3_phy_setup(dwc); if (ret) goto err0; - ret = dwc3_core_soft_reset(dwc); - if (ret) - goto err0; + if (!dwc->ulpi_ready) { + ret = dwc3_core_ulpi_init(dwc); + if (ret) + goto err0; + dwc->ulpi_ready = true; + } - ret = dwc3_phy_setup(dwc); + if (!dwc->phys_ready) { + ret = dwc3_core_get_phy(dwc); + if (ret) + goto err0a; + dwc->phys_ready = true; + } + + ret = dwc3_core_soft_reset(dwc); if (ret) - goto err0; + goto err0a; dwc3_core_setup_global_control(dwc); dwc3_core_num_eps(dwc); @@ -838,6 +864,9 @@ err1: phy_exit(dwc->usb2_generic_phy); phy_exit(dwc->usb3_generic_phy); +err0a: + dwc3_ulpi_exit(dwc); + err0: return ret; } @@ -916,7 +945,6 @@ static int dwc3_core_init_mode(struct dwc3 *dwc) switch (dwc->dr_mode) { case USB_DR_MODE_PERIPHERAL: - dwc->current_dr_role = DWC3_GCTL_PRTCAP_DEVICE; dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_DEVICE); if (dwc->usb2_phy) @@ -932,7 +960,6 @@ static int dwc3_core_init_mode(struct dwc3 *dwc) } break; case USB_DR_MODE_HOST: - dwc->current_dr_role = DWC3_GCTL_PRTCAP_HOST; dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_HOST); if (dwc->usb2_phy) @@ -1234,7 +1261,6 @@ err4: err3: dwc3_free_event_buffers(dwc); - dwc3_ulpi_exit(dwc); err2: pm_runtime_allow(&pdev->dev); @@ -1284,7 +1310,7 @@ static int dwc3_remove(struct platform_device *pdev) } #ifdef CONFIG_PM -static int dwc3_suspend_common(struct dwc3 *dwc) +static int dwc3_suspend_common(struct dwc3 *dwc, pm_message_t msg) { unsigned long flags; @@ -1296,6 +1322,10 @@ static int dwc3_suspend_common(struct dwc3 *dwc) dwc3_core_exit(dwc); break; case DWC3_GCTL_PRTCAP_HOST: + /* do nothing during host runtime_suspend */ + if (!PMSG_IS_AUTO(msg)) + dwc3_core_exit(dwc); + break; default: /* do nothing */ break; @@ -1304,7 +1334,7 @@ static int dwc3_suspend_common(struct dwc3 *dwc) return 0; } -static int dwc3_resume_common(struct dwc3 *dwc) +static int dwc3_resume_common(struct dwc3 *dwc, pm_message_t msg) { unsigned long flags; int ret; @@ -1320,6 +1350,13 @@ static int dwc3_resume_common(struct dwc3 *dwc) spin_unlock_irqrestore(&dwc->lock, flags); break; case DWC3_GCTL_PRTCAP_HOST: + /* nothing to do on host runtime_resume */ + if (!PMSG_IS_AUTO(msg)) { + ret = dwc3_core_init(dwc); + if (ret) + return ret; + } + break; default: /* do nothing */ break; @@ -1331,12 +1368,11 @@ static int dwc3_resume_common(struct dwc3 *dwc) static int dwc3_runtime_checks(struct dwc3 *dwc) { switch (dwc->current_dr_role) { - case USB_DR_MODE_PERIPHERAL: - case USB_DR_MODE_OTG: + case DWC3_GCTL_PRTCAP_DEVICE: if (dwc->connected) return -EBUSY; break; - case USB_DR_MODE_HOST: + case DWC3_GCTL_PRTCAP_HOST: default: /* do nothing */ break; @@ -1353,7 +1389,7 @@ static int dwc3_runtime_suspend(struct device *dev) if (dwc3_runtime_checks(dwc)) return -EBUSY; - ret = dwc3_suspend_common(dwc); + ret = dwc3_suspend_common(dwc, PMSG_AUTO_SUSPEND); if (ret) return ret; @@ -1369,7 +1405,7 @@ static int dwc3_runtime_resume(struct device *dev) device_init_wakeup(dev, false); - ret = dwc3_resume_common(dwc); + ret = dwc3_resume_common(dwc, PMSG_AUTO_RESUME); if (ret) return ret; @@ -1416,7 +1452,7 @@ static int dwc3_suspend(struct device *dev) struct dwc3 *dwc = dev_get_drvdata(dev); int ret; - ret = dwc3_suspend_common(dwc); + ret = dwc3_suspend_common(dwc, PMSG_SUSPEND); if (ret) return ret; @@ -1432,7 +1468,7 @@ static int dwc3_resume(struct device *dev) pinctrl_pm_select_default_state(dev); - ret = dwc3_resume_common(dwc); + ret = dwc3_resume_common(dwc, PMSG_RESUME); if (ret) return ret; diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index 03c7aaaac926..860d2bc184d1 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -158,13 +158,15 @@ #define DWC3_GDBGFIFOSPACE_TYPE(n) (((n) << 5) & 0x1e0) #define DWC3_GDBGFIFOSPACE_SPACE_AVAILABLE(n) (((n) >> 16) & 0xffff) -#define DWC3_TXFIFOQ 1 -#define DWC3_RXFIFOQ 3 -#define DWC3_TXREQQ 5 -#define DWC3_RXREQQ 7 -#define DWC3_RXINFOQ 9 -#define DWC3_DESCFETCHQ 13 -#define DWC3_EVENTQ 15 +#define DWC3_TXFIFOQ 0 +#define DWC3_RXFIFOQ 1 +#define DWC3_TXREQQ 2 +#define DWC3_RXREQQ 3 +#define DWC3_RXINFOQ 4 +#define DWC3_PSTATQ 5 +#define DWC3_DESCFETCHQ 6 +#define DWC3_EVENTQ 7 +#define DWC3_AUXEVENTQ 8 /* Global RX Threshold Configuration Register */ #define DWC3_GRXTHRCFG_MAXRXBURSTSIZE(n) (((n) & 0x1f) << 19) @@ -795,7 +797,9 @@ struct dwc3_scratchpad_array { * @usb3_phy: pointer to USB3 PHY * @usb2_generic_phy: pointer to USB2 PHY * @usb3_generic_phy: pointer to USB3 PHY + * @phys_ready: flag to indicate that PHYs are ready * @ulpi: pointer to ulpi interface + * @ulpi_ready: flag to indicate that ULPI is initialized * @u2sel: parameter from Set SEL request. * @u2pel: parameter from Set SEL request. * @u1sel: parameter from Set SEL request. @@ -893,7 +897,10 @@ struct dwc3 { struct phy *usb2_generic_phy; struct phy *usb3_generic_phy; + bool phys_ready; + struct ulpi *ulpi; + bool ulpi_ready; void __iomem *regs; size_t regs_size; diff --git a/drivers/usb/dwc3/dwc3-of-simple.c b/drivers/usb/dwc3/dwc3-of-simple.c index 7ae0eefc7cc7..e54c3622eb28 100644 --- a/drivers/usb/dwc3/dwc3-of-simple.c +++ b/drivers/usb/dwc3/dwc3-of-simple.c @@ -143,6 +143,7 @@ static int dwc3_of_simple_remove(struct platform_device *pdev) clk_disable_unprepare(simple->clks[i]); clk_put(simple->clks[i]); } + simple->num_clocks = 0; reset_control_assert(simple->resets); reset_control_put(simple->resets); diff --git a/drivers/usb/dwc3/dwc3-omap.c b/drivers/usb/dwc3/dwc3-omap.c index a4719e853b85..ed8b86517675 100644 --- a/drivers/usb/dwc3/dwc3-omap.c +++ b/drivers/usb/dwc3/dwc3-omap.c @@ -582,9 +582,25 @@ static int dwc3_omap_resume(struct device *dev) return 0; } +static void dwc3_omap_complete(struct device *dev) +{ + struct dwc3_omap *omap = dev_get_drvdata(dev); + + if (extcon_get_state(omap->edev, EXTCON_USB)) + dwc3_omap_set_mailbox(omap, OMAP_DWC3_VBUS_VALID); + else + dwc3_omap_set_mailbox(omap, OMAP_DWC3_VBUS_OFF); + + if (extcon_get_state(omap->edev, EXTCON_USB_HOST)) + dwc3_omap_set_mailbox(omap, OMAP_DWC3_ID_GROUND); + else + dwc3_omap_set_mailbox(omap, OMAP_DWC3_ID_FLOAT); +} + static const struct dev_pm_ops dwc3_omap_dev_pm_ops = { SET_SYSTEM_SLEEP_PM_OPS(dwc3_omap_suspend, dwc3_omap_resume) + .complete = dwc3_omap_complete, }; #define DEV_PM_OPS (&dwc3_omap_dev_pm_ops) diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c index 9c2e4a17918e..18be31d5743a 100644 --- a/drivers/usb/dwc3/ep0.c +++ b/drivers/usb/dwc3/ep0.c @@ -854,7 +854,12 @@ static void dwc3_ep0_complete_data(struct dwc3 *dwc, trb++; trb->ctrl &= ~DWC3_TRB_CTRL_HWO; trace_dwc3_complete_trb(ep0, trb); - ep0->trb_enqueue = 0; + + if (r->direction) + dwc->eps[1]->trb_enqueue = 0; + else + dwc->eps[0]->trb_enqueue = 0; + dwc->ep0_bounced = false; } diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 616ef49ccb49..2bda4eb1e9ac 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -2745,6 +2745,8 @@ static void dwc3_gadget_conndone_interrupt(struct dwc3 *dwc) break; } + dwc->eps[1]->endpoint.maxpacket = dwc->gadget.ep0->maxpacket; + /* Enable USB2 LPM Capability */ if ((dwc->revision > DWC3_REVISION_194A) && diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 8f2cf3baa19c..c2592d883f67 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -1855,44 +1855,20 @@ static int ffs_func_eps_enable(struct ffs_function *func) spin_lock_irqsave(&func->ffs->eps_lock, flags); while(count--) { - struct usb_endpoint_descriptor *ds; - struct usb_ss_ep_comp_descriptor *comp_desc = NULL; - int needs_comp_desc = false; - int desc_idx; - - if (ffs->gadget->speed == USB_SPEED_SUPER) { - desc_idx = 2; - needs_comp_desc = true; - } else if (ffs->gadget->speed == USB_SPEED_HIGH) - desc_idx = 1; - else - desc_idx = 0; - - /* fall-back to lower speed if desc missing for current speed */ - do { - ds = ep->descs[desc_idx]; - } while (!ds && --desc_idx >= 0); - - if (!ds) { - ret = -EINVAL; - break; - } - ep->ep->driver_data = ep; - ep->ep->desc = ds; - if (needs_comp_desc) { - comp_desc = (struct usb_ss_ep_comp_descriptor *)(ds + - USB_DT_ENDPOINT_SIZE); - ep->ep->maxburst = comp_desc->bMaxBurst + 1; - ep->ep->comp_desc = comp_desc; + ret = config_ep_by_speed(func->gadget, &func->function, ep->ep); + if (ret) { + pr_err("%s: config_ep_by_speed(%s) returned %d\n", + __func__, ep->ep->name, ret); + break; } ret = usb_ep_enable(ep->ep); if (likely(!ret)) { epfile->ep = ep; - epfile->in = usb_endpoint_dir_in(ds); - epfile->isoc = usb_endpoint_xfer_isoc(ds); + epfile->in = usb_endpoint_dir_in(ep->ep->desc); + epfile->isoc = usb_endpoint_xfer_isoc(ep->ep->desc); } else { break; } @@ -2979,10 +2955,8 @@ static int _ffs_func_bind(struct usb_configuration *c, struct ffs_data *ffs = func->ffs; const int full = !!func->ffs->fs_descs_count; - const int high = gadget_is_dualspeed(func->gadget) && - func->ffs->hs_descs_count; - const int super = gadget_is_superspeed(func->gadget) && - func->ffs->ss_descs_count; + const int high = !!func->ffs->hs_descs_count; + const int super = !!func->ffs->ss_descs_count; int fs_len, hs_len, ss_len, ret, i; struct ffs_ep *eps_ptr; diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c index 11fe788b4308..d2dc1f00180b 100644 --- a/drivers/usb/gadget/function/f_uac2.c +++ b/drivers/usb/gadget/function/f_uac2.c @@ -524,6 +524,8 @@ afunc_bind(struct usb_configuration *cfg, struct usb_function *fn) dev_err(dev, "%s:%d Error!\n", __func__, __LINE__); return ret; } + iad_desc.bFirstInterface = ret; + std_ac_if_desc.bInterfaceNumber = ret; uac2->ac_intf = ret; uac2->ac_alt = 0; diff --git a/drivers/usb/gadget/udc/Kconfig b/drivers/usb/gadget/udc/Kconfig index 1e9567091d86..0875d38476ee 100644 --- a/drivers/usb/gadget/udc/Kconfig +++ b/drivers/usb/gadget/udc/Kconfig @@ -274,7 +274,6 @@ config USB_SNP_UDC_PLAT tristate "Synopsys USB 2.0 Device controller" depends on USB_GADGET && OF && HAS_DMA depends on EXTCON || EXTCON=n - select USB_GADGET_DUALSPEED select USB_SNP_CORE default ARCH_BCM_IPROC help diff --git a/drivers/usb/gadget/udc/bdc/bdc_pci.c b/drivers/usb/gadget/udc/bdc/bdc_pci.c index 1e940f054cb8..6dbc489513cd 100644 --- a/drivers/usb/gadget/udc/bdc/bdc_pci.c +++ b/drivers/usb/gadget/udc/bdc/bdc_pci.c @@ -77,6 +77,7 @@ static int bdc_pci_probe(struct pci_dev *pci, const struct pci_device_id *id) if (ret) { dev_err(&pci->dev, "couldn't add resources to bdc device\n"); + platform_device_put(bdc); return ret; } diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index 859d5b11ba4c..1f8b19d9cf97 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -180,8 +180,8 @@ EXPORT_SYMBOL_GPL(usb_ep_alloc_request); void usb_ep_free_request(struct usb_ep *ep, struct usb_request *req) { - ep->ops->free_request(ep, req); trace_usb_ep_free_request(ep, req, 0); + ep->ops->free_request(ep, req); } EXPORT_SYMBOL_GPL(usb_ep_free_request); diff --git a/drivers/usb/gadget/udc/fsl_udc_core.c b/drivers/usb/gadget/udc/fsl_udc_core.c index e5b4ee96c4bf..56b517a38865 100644 --- a/drivers/usb/gadget/udc/fsl_udc_core.c +++ b/drivers/usb/gadget/udc/fsl_udc_core.c @@ -1305,7 +1305,7 @@ static void udc_reset_ep_queue(struct fsl_udc *udc, u8 pipe) { struct fsl_ep *ep = get_ep_by_pipe(udc, pipe); - if (ep->name) + if (ep->ep.name) nuke(ep, -ESHUTDOWN); } @@ -1693,7 +1693,7 @@ static void dtd_complete_irq(struct fsl_udc *udc) curr_ep = get_ep_by_pipe(udc, i); /* If the ep is configured */ - if (curr_ep->name == NULL) { + if (!curr_ep->ep.name) { WARNING("Invalid EP?"); continue; } diff --git a/drivers/usb/gadget/udc/renesas_usb3.c b/drivers/usb/gadget/udc/renesas_usb3.c index 6e87af248367..409cde4e6a51 100644 --- a/drivers/usb/gadget/udc/renesas_usb3.c +++ b/drivers/usb/gadget/udc/renesas_usb3.c @@ -2410,7 +2410,7 @@ static int renesas_usb3_remove(struct platform_device *pdev) __renesas_usb3_ep_free_request(usb3->ep0_req); if (usb3->phy) phy_put(usb3->phy); - pm_runtime_disable(usb3_to_dev(usb3)); + pm_runtime_disable(&pdev->dev); return 0; } diff --git a/drivers/usb/host/Kconfig b/drivers/usb/host/Kconfig index 6150bed7cfa8..4fcfb3084b36 100644 --- a/drivers/usb/host/Kconfig +++ b/drivers/usb/host/Kconfig @@ -633,14 +633,6 @@ config USB_UHCI_ASPEED bool default y if ARCH_ASPEED -config USB_UHCI_BIG_ENDIAN_MMIO - bool - default y if SPARC_LEON - -config USB_UHCI_BIG_ENDIAN_DESC - bool - default y if SPARC_LEON - config USB_FHCI_HCD tristate "Freescale QE USB Host Controller support" depends on OF_GPIO && QE_GPIO && QUICC_ENGINE diff --git a/drivers/usb/host/ehci-hub.c b/drivers/usb/host/ehci-hub.c index facafdf8fb95..d7641cbdee43 100644 --- a/drivers/usb/host/ehci-hub.c +++ b/drivers/usb/host/ehci-hub.c @@ -774,12 +774,12 @@ static struct urb *request_single_step_set_feature_urb( atomic_inc(&urb->use_count); atomic_inc(&urb->dev->urbnum); urb->setup_dma = dma_map_single( - hcd->self.controller, + hcd->self.sysdev, urb->setup_packet, sizeof(struct usb_ctrlrequest), DMA_TO_DEVICE); urb->transfer_dma = dma_map_single( - hcd->self.controller, + hcd->self.sysdev, urb->transfer_buffer, urb->transfer_buffer_length, DMA_FROM_DEVICE); diff --git a/drivers/usb/host/ehci-q.c b/drivers/usb/host/ehci-q.c index 88158324dcae..327630405695 100644 --- a/drivers/usb/host/ehci-q.c +++ b/drivers/usb/host/ehci-q.c @@ -1188,10 +1188,10 @@ static int submit_single_step_set_feature( * 15 secs after the setup */ if (is_setup) { - /* SETUP pid */ + /* SETUP pid, and interrupt after SETUP completion */ qtd_fill(ehci, qtd, urb->setup_dma, sizeof(struct usb_ctrlrequest), - token | (2 /* "setup" */ << 8), 8); + QTD_IOC | token | (2 /* "setup" */ << 8), 8); submit_async(ehci, urb, &qtd_list, GFP_ATOMIC); return 0; /*Return now; we shall come back after 15 seconds*/ @@ -1228,12 +1228,8 @@ static int submit_single_step_set_feature( qtd_prev->hw_next = QTD_NEXT(ehci, qtd->qtd_dma); list_add_tail(&qtd->qtd_list, head); - /* dont fill any data in such packets */ - qtd_fill(ehci, qtd, 0, 0, token, 0); - - /* by default, enable interrupt on urb completion */ - if (likely(!(urb->transfer_flags & URB_NO_INTERRUPT))) - qtd->hw_token |= cpu_to_hc32(ehci, QTD_IOC); + /* Interrupt after STATUS completion */ + qtd_fill(ehci, qtd, 0, 0, token | QTD_IOC, 0); submit_async(ehci, urb, &qtd_list, GFP_KERNEL); diff --git a/drivers/usb/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c index ee9676349333..84f88fa411cd 100644 --- a/drivers/usb/host/ohci-hcd.c +++ b/drivers/usb/host/ohci-hcd.c @@ -74,6 +74,7 @@ static const char hcd_name [] = "ohci_hcd"; #define STATECHANGE_DELAY msecs_to_jiffies(300) #define IO_WATCHDOG_DELAY msecs_to_jiffies(275) +#define IO_WATCHDOG_OFF 0xffffff00 #include "ohci.h" #include "pci-quirks.h" @@ -231,7 +232,7 @@ static int ohci_urb_enqueue ( } /* Start up the I/O watchdog timer, if it's not running */ - if (!timer_pending(&ohci->io_watchdog) && + if (ohci->prev_frame_no == IO_WATCHDOG_OFF && list_empty(&ohci->eds_in_use) && !(ohci->flags & OHCI_QUIRK_QEMU)) { ohci->prev_frame_no = ohci_frame_no(ohci); @@ -501,6 +502,7 @@ static int ohci_init (struct ohci_hcd *ohci) return 0; timer_setup(&ohci->io_watchdog, io_watchdog_func, 0); + ohci->prev_frame_no = IO_WATCHDOG_OFF; ohci->hcca = dma_alloc_coherent (hcd->self.controller, sizeof(*ohci->hcca), &ohci->hcca_dma, GFP_KERNEL); @@ -730,7 +732,7 @@ static void io_watchdog_func(struct timer_list *t) u32 head; struct ed *ed; struct td *td, *td_start, *td_next; - unsigned frame_no; + unsigned frame_no, prev_frame_no = IO_WATCHDOG_OFF; unsigned long flags; spin_lock_irqsave(&ohci->lock, flags); @@ -835,7 +837,7 @@ static void io_watchdog_func(struct timer_list *t) } } if (!list_empty(&ohci->eds_in_use)) { - ohci->prev_frame_no = frame_no; + prev_frame_no = frame_no; ohci->prev_wdh_cnt = ohci->wdh_cnt; ohci->prev_donehead = ohci_readl(ohci, &ohci->regs->donehead); @@ -845,6 +847,7 @@ static void io_watchdog_func(struct timer_list *t) } done: + ohci->prev_frame_no = prev_frame_no; spin_unlock_irqrestore(&ohci->lock, flags); } @@ -973,6 +976,7 @@ static void ohci_stop (struct usb_hcd *hcd) if (quirk_nec(ohci)) flush_work(&ohci->nec_work); del_timer_sync(&ohci->io_watchdog); + ohci->prev_frame_no = IO_WATCHDOG_OFF; ohci_writel (ohci, OHCI_INTR_MIE, &ohci->regs->intrdisable); ohci_usb_reset(ohci); diff --git a/drivers/usb/host/ohci-hub.c b/drivers/usb/host/ohci-hub.c index fb7aaa3b9d06..634f3c7bf774 100644 --- a/drivers/usb/host/ohci-hub.c +++ b/drivers/usb/host/ohci-hub.c @@ -311,8 +311,10 @@ static int ohci_bus_suspend (struct usb_hcd *hcd) rc = ohci_rh_suspend (ohci, 0); spin_unlock_irq (&ohci->lock); - if (rc == 0) + if (rc == 0) { del_timer_sync(&ohci->io_watchdog); + ohci->prev_frame_no = IO_WATCHDOG_OFF; + } return rc; } diff --git a/drivers/usb/host/ohci-q.c b/drivers/usb/host/ohci-q.c index b2ec8c399363..4ccb85a67bb3 100644 --- a/drivers/usb/host/ohci-q.c +++ b/drivers/usb/host/ohci-q.c @@ -1019,6 +1019,8 @@ skip_ed: * have modified this list. normally it's just prepending * entries (which we'd ignore), but paranoia won't hurt. */ + *last = ed->ed_next; + ed->ed_next = NULL; modified = 0; /* unlink urbs as requested, but rescan the list after @@ -1077,21 +1079,22 @@ rescan_this: goto rescan_this; /* - * If no TDs are queued, take ED off the ed_rm_list. + * If no TDs are queued, ED is now idle. * Otherwise, if the HC is running, reschedule. - * If not, leave it on the list for further dequeues. + * If the HC isn't running, add ED back to the + * start of the list for later processing. */ if (list_empty(&ed->td_list)) { - *last = ed->ed_next; - ed->ed_next = NULL; ed->state = ED_IDLE; list_del(&ed->in_use_list); } else if (ohci->rh_state == OHCI_RH_RUNNING) { - *last = ed->ed_next; - ed->ed_next = NULL; ed_schedule(ohci, ed); } else { - last = &ed->ed_next; + ed->ed_next = ohci->ed_rm_list; + ohci->ed_rm_list = ed; + /* Don't loop on the same ED */ + if (last == &ohci->ed_rm_list) + last = &ed->ed_next; } if (modified) diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c index 161536717025..67ad4bb6919a 100644 --- a/drivers/usb/host/pci-quirks.c +++ b/drivers/usb/host/pci-quirks.c @@ -66,6 +66,23 @@ #define AX_INDXC 0x30 #define AX_DATAC 0x34 +#define PT_ADDR_INDX 0xE8 +#define PT_READ_INDX 0xE4 +#define PT_SIG_1_ADDR 0xA520 +#define PT_SIG_2_ADDR 0xA521 +#define PT_SIG_3_ADDR 0xA522 +#define PT_SIG_4_ADDR 0xA523 +#define PT_SIG_1_DATA 0x78 +#define PT_SIG_2_DATA 0x56 +#define PT_SIG_3_DATA 0x34 +#define PT_SIG_4_DATA 0x12 +#define PT4_P1_REG 0xB521 +#define PT4_P2_REG 0xB522 +#define PT2_P1_REG 0xD520 +#define PT2_P2_REG 0xD521 +#define PT1_P1_REG 0xD522 +#define PT1_P2_REG 0xD523 + #define NB_PCIE_INDX_ADDR 0xe0 #define NB_PCIE_INDX_DATA 0xe4 #define PCIE_P_CNTL 0x10040 @@ -513,6 +530,98 @@ void usb_amd_dev_put(void) EXPORT_SYMBOL_GPL(usb_amd_dev_put); /* + * Check if port is disabled in BIOS on AMD Promontory host. + * BIOS Disabled ports may wake on connect/disconnect and need + * driver workaround to keep them disabled. + * Returns true if port is marked disabled. + */ +bool usb_amd_pt_check_port(struct device *device, int port) +{ + unsigned char value, port_shift; + struct pci_dev *pdev; + u16 reg; + + pdev = to_pci_dev(device); + pci_write_config_word(pdev, PT_ADDR_INDX, PT_SIG_1_ADDR); + + pci_read_config_byte(pdev, PT_READ_INDX, &value); + if (value != PT_SIG_1_DATA) + return false; + + pci_write_config_word(pdev, PT_ADDR_INDX, PT_SIG_2_ADDR); + + pci_read_config_byte(pdev, PT_READ_INDX, &value); + if (value != PT_SIG_2_DATA) + return false; + + pci_write_config_word(pdev, PT_ADDR_INDX, PT_SIG_3_ADDR); + + pci_read_config_byte(pdev, PT_READ_INDX, &value); + if (value != PT_SIG_3_DATA) + return false; + + pci_write_config_word(pdev, PT_ADDR_INDX, PT_SIG_4_ADDR); + + pci_read_config_byte(pdev, PT_READ_INDX, &value); + if (value != PT_SIG_4_DATA) + return false; + + /* Check disabled port setting, if bit is set port is enabled */ + switch (pdev->device) { + case 0x43b9: + case 0x43ba: + /* + * device is AMD_PROMONTORYA_4(0x43b9) or PROMONTORYA_3(0x43ba) + * PT4_P1_REG bits[7..1] represents USB2.0 ports 6 to 0 + * PT4_P2_REG bits[6..0] represents ports 13 to 7 + */ + if (port > 6) { + reg = PT4_P2_REG; + port_shift = port - 7; + } else { + reg = PT4_P1_REG; + port_shift = port + 1; + } + break; + case 0x43bb: + /* + * device is AMD_PROMONTORYA_2(0x43bb) + * PT2_P1_REG bits[7..5] represents USB2.0 ports 2 to 0 + * PT2_P2_REG bits[5..0] represents ports 9 to 3 + */ + if (port > 2) { + reg = PT2_P2_REG; + port_shift = port - 3; + } else { + reg = PT2_P1_REG; + port_shift = port + 5; + } + break; + case 0x43bc: + /* + * device is AMD_PROMONTORYA_1(0x43bc) + * PT1_P1_REG[7..4] represents USB2.0 ports 3 to 0 + * PT1_P2_REG[5..0] represents ports 9 to 4 + */ + if (port > 3) { + reg = PT1_P2_REG; + port_shift = port - 4; + } else { + reg = PT1_P1_REG; + port_shift = port + 4; + } + break; + default: + return false; + } + pci_write_config_word(pdev, PT_ADDR_INDX, reg); + pci_read_config_byte(pdev, PT_READ_INDX, &value); + + return !(value & BIT(port_shift)); +} +EXPORT_SYMBOL_GPL(usb_amd_pt_check_port); + +/* * Make sure the controller is completely inactive, unable to * generate interrupts or do DMA. */ diff --git a/drivers/usb/host/pci-quirks.h b/drivers/usb/host/pci-quirks.h index b68dcb5dd0fd..4ca0d9b7e463 100644 --- a/drivers/usb/host/pci-quirks.h +++ b/drivers/usb/host/pci-quirks.h @@ -17,6 +17,7 @@ void usb_enable_intel_xhci_ports(struct pci_dev *xhci_pdev); void usb_disable_xhci_ports(struct pci_dev *xhci_pdev); void sb800_prefetch(struct device *dev, int on); bool usb_xhci_needs_pci_reset(struct pci_dev *pdev); +bool usb_amd_pt_check_port(struct device *device, int port); #else struct pci_dev; static inline void usb_amd_quirk_pll_disable(void) {} @@ -25,6 +26,10 @@ static inline void usb_asmedia_modifyflowcontrol(struct pci_dev *pdev) {} static inline void usb_amd_dev_put(void) {} static inline void usb_disable_xhci_ports(struct pci_dev *xhci_pdev) {} static inline void sb800_prefetch(struct device *dev, int on) {} +static inline bool usb_amd_pt_check_port(struct device *device, int port) +{ + return false; +} #endif /* CONFIG_USB_PCI */ #endif /* __LINUX_USB_PCI_QUIRKS_H */ diff --git a/drivers/usb/host/xhci-debugfs.c b/drivers/usb/host/xhci-debugfs.c index e26e685d8a57..5851052d4668 100644 --- a/drivers/usb/host/xhci-debugfs.c +++ b/drivers/usb/host/xhci-debugfs.c @@ -211,7 +211,7 @@ static void xhci_ring_dump_segment(struct seq_file *s, static int xhci_ring_trb_show(struct seq_file *s, void *unused) { int i; - struct xhci_ring *ring = s->private; + struct xhci_ring *ring = *(struct xhci_ring **)s->private; struct xhci_segment *seg = ring->first_seg; for (i = 0; i < ring->num_segs; i++) { @@ -387,7 +387,7 @@ void xhci_debugfs_create_endpoint(struct xhci_hcd *xhci, snprintf(epriv->name, sizeof(epriv->name), "ep%02d", ep_index); epriv->root = xhci_debugfs_create_ring_dir(xhci, - &dev->eps[ep_index].new_ring, + &dev->eps[ep_index].ring, epriv->name, spriv->root); spriv->eps[ep_index] = epriv; diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index 46d5e08f05f1..72ebbc908e19 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -1224,17 +1224,17 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, temp = readl(port_array[wIndex]); break; } - - /* Software should not attempt to set - * port link state above '3' (U3) and the port - * must be enabled. - */ - if ((temp & PORT_PE) == 0 || - (link_state > USB_SS_PORT_LS_U3)) { - xhci_warn(xhci, "Cannot set link state.\n"); + /* Port must be enabled */ + if (!(temp & PORT_PE)) { + retval = -ENODEV; + break; + } + /* Can't set port link state above '3' (U3) */ + if (link_state > USB_SS_PORT_LS_U3) { + xhci_warn(xhci, "Cannot set port %d link state %d\n", + wIndex, link_state); goto error; } - if (link_state == USB_SS_PORT_LS_U3) { slot_id = xhci_find_slot_id_by_port(hcd, xhci, wIndex + 1); @@ -1522,6 +1522,13 @@ int xhci_bus_suspend(struct usb_hcd *hcd) t2 |= PORT_WKOC_E | PORT_WKCONN_E; t2 &= ~PORT_WKDISC_E; } + + if ((xhci->quirks & XHCI_U2_DISABLE_WAKE) && + (hcd->speed < HCD_USB3)) { + if (usb_amd_pt_check_port(hcd->self.controller, + port_index)) + t2 &= ~PORT_WAKE_BITS; + } } else t2 &= ~PORT_WAKE_BITS; diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 6c79037876db..5262fa571a5d 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -42,6 +42,10 @@ #define PCI_DEVICE_ID_INTEL_APL_XHCI 0x5aa8 #define PCI_DEVICE_ID_INTEL_DNV_XHCI 0x19d0 +#define PCI_DEVICE_ID_AMD_PROMONTORYA_4 0x43b9 +#define PCI_DEVICE_ID_AMD_PROMONTORYA_3 0x43ba +#define PCI_DEVICE_ID_AMD_PROMONTORYA_2 0x43bb +#define PCI_DEVICE_ID_AMD_PROMONTORYA_1 0x43bc #define PCI_DEVICE_ID_ASMEDIA_1042A_XHCI 0x1142 static const char hcd_name[] = "xhci_hcd"; @@ -125,6 +129,13 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) if (pdev->vendor == PCI_VENDOR_ID_AMD) xhci->quirks |= XHCI_TRUST_TX_LENGTH; + if ((pdev->vendor == PCI_VENDOR_ID_AMD) && + ((pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_4) || + (pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_3) || + (pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_2) || + (pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_1))) + xhci->quirks |= XHCI_U2_DISABLE_WAKE; + if (pdev->vendor == PCI_VENDOR_ID_INTEL) { xhci->quirks |= XHCI_LPM_SUPPORT; xhci->quirks |= XHCI_INTEL_HOST; diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 1eeb3396300f..25d4b748a56f 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -646,8 +646,6 @@ static void xhci_stop(struct usb_hcd *hcd) return; } - xhci_debugfs_exit(xhci); - xhci_dbc_exit(xhci); spin_lock_irq(&xhci->lock); @@ -680,6 +678,7 @@ static void xhci_stop(struct usb_hcd *hcd) xhci_dbg_trace(xhci, trace_xhci_dbg_init, "cleaning up memory"); xhci_mem_cleanup(xhci); + xhci_debugfs_exit(xhci); xhci_dbg_trace(xhci, trace_xhci_dbg_init, "xhci_stop completed - status = %x", readl(&xhci->op_regs->status)); @@ -1014,6 +1013,7 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated) xhci_dbg(xhci, "cleaning up memory\n"); xhci_mem_cleanup(xhci); + xhci_debugfs_exit(xhci); xhci_dbg(xhci, "xhci_stop completed - status = %x\n", readl(&xhci->op_regs->status)); @@ -3544,12 +3544,10 @@ static void xhci_free_dev(struct usb_hcd *hcd, struct usb_device *udev) virt_dev->eps[i].ep_state &= ~EP_STOP_CMD_PENDING; del_timer_sync(&virt_dev->eps[i].stop_cmd_timer); } - + xhci_debugfs_remove_slot(xhci, udev->slot_id); ret = xhci_disable_slot(xhci, udev->slot_id); - if (ret) { - xhci_debugfs_remove_slot(xhci, udev->slot_id); + if (ret) xhci_free_virt_device(xhci, udev->slot_id); - } } int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id) diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 96099a245c69..e4d7d3d06a75 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1822,7 +1822,7 @@ struct xhci_hcd { /* For controller with a broken Port Disable implementation */ #define XHCI_BROKEN_PORT_PED (1 << 25) #define XHCI_LIMIT_ENDPOINT_INTERVAL_7 (1 << 26) -/* Reserved. It was XHCI_U2_DISABLE_WAKE */ +#define XHCI_U2_DISABLE_WAKE (1 << 27) #define XHCI_ASMEDIA_MODIFY_FLOWCONTROL (1 << 28) #define XHCI_HW_LPM_DISABLE (1 << 29) diff --git a/drivers/usb/misc/ldusb.c b/drivers/usb/misc/ldusb.c index 63b9e85dc0e9..236a60f53099 100644 --- a/drivers/usb/misc/ldusb.c +++ b/drivers/usb/misc/ldusb.c @@ -42,6 +42,9 @@ #define USB_DEVICE_ID_LD_MICROCASSYTIME 0x1033 /* USB Product ID of Micro-CASSY Time (reserved) */ #define USB_DEVICE_ID_LD_MICROCASSYTEMPERATURE 0x1035 /* USB Product ID of Micro-CASSY Temperature */ #define USB_DEVICE_ID_LD_MICROCASSYPH 0x1038 /* USB Product ID of Micro-CASSY pH */ +#define USB_DEVICE_ID_LD_POWERANALYSERCASSY 0x1040 /* USB Product ID of Power Analyser CASSY */ +#define USB_DEVICE_ID_LD_CONVERTERCONTROLLERCASSY 0x1042 /* USB Product ID of Converter Controller CASSY */ +#define USB_DEVICE_ID_LD_MACHINETESTCASSY 0x1043 /* USB Product ID of Machine Test CASSY */ #define USB_DEVICE_ID_LD_JWM 0x1080 /* USB Product ID of Joule and Wattmeter */ #define USB_DEVICE_ID_LD_DMMP 0x1081 /* USB Product ID of Digital Multimeter P (reserved) */ #define USB_DEVICE_ID_LD_UMIP 0x1090 /* USB Product ID of UMI P */ @@ -84,6 +87,9 @@ static const struct usb_device_id ld_usb_table[] = { { USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_MICROCASSYTIME) }, { USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_MICROCASSYTEMPERATURE) }, { USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_MICROCASSYPH) }, + { USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_POWERANALYSERCASSY) }, + { USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_CONVERTERCONTROLLERCASSY) }, + { USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_MACHINETESTCASSY) }, { USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_JWM) }, { USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_DMMP) }, { USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_UMIP) }, diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c index 968bf1e8b0fe..eef4ad578b31 100644 --- a/drivers/usb/musb/musb_core.c +++ b/drivers/usb/musb/musb_core.c @@ -2708,7 +2708,8 @@ static int musb_resume(struct device *dev) if ((devctl & mask) != (musb->context.devctl & mask)) musb->port1_status = 0; - musb_start(musb); + musb_enable_interrupts(musb); + musb_platform_enable(musb); spin_lock_irqsave(&musb->lock, flags); error = musb_run_resume_work(musb); diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c index 394b4ac86161..45ed32c2cba9 100644 --- a/drivers/usb/musb/musb_host.c +++ b/drivers/usb/musb/musb_host.c @@ -391,13 +391,7 @@ static void musb_advance_schedule(struct musb *musb, struct urb *urb, } } - /* - * The pipe must be broken if current urb->status is set, so don't - * start next urb. - * TODO: to minimize the risk of regression, only check urb->status - * for RX, until we have a test case to understand the behavior of TX. - */ - if ((!status || !is_in) && qh && qh->is_ready) { + if (qh != NULL && qh->is_ready) { musb_dbg(musb, "... next ep%d %cX urb %p", hw_ep->epnum, is_in ? 'R' : 'T', next_urb(qh)); musb_start_urb(musb, is_in, qh); diff --git a/drivers/usb/phy/phy-mxs-usb.c b/drivers/usb/phy/phy-mxs-usb.c index da031c45395a..fbec863350f6 100644 --- a/drivers/usb/phy/phy-mxs-usb.c +++ b/drivers/usb/phy/phy-mxs-usb.c @@ -602,6 +602,9 @@ static enum usb_charger_type mxs_phy_charger_detect(struct usb_phy *phy) void __iomem *base = phy->io_priv; enum usb_charger_type chgr_type = UNKNOWN_TYPE; + if (!regmap) + return UNKNOWN_TYPE; + if (mxs_charger_data_contact_detect(mxs_phy)) return chgr_type; diff --git a/drivers/usb/renesas_usbhs/fifo.c b/drivers/usb/renesas_usbhs/fifo.c index 5925d111bd47..39fa2fc1b8b7 100644 --- a/drivers/usb/renesas_usbhs/fifo.c +++ b/drivers/usb/renesas_usbhs/fifo.c @@ -982,6 +982,10 @@ static int usbhsf_dma_prepare_pop_with_usb_dmac(struct usbhs_pkt *pkt, if ((uintptr_t)pkt->buf & (USBHS_USB_DMAC_XFER_SIZE - 1)) goto usbhsf_pio_prepare_pop; + /* return at this time if the pipe is running */ + if (usbhs_pipe_is_running(pipe)) + return 0; + usbhs_pipe_config_change_bfre(pipe, 1); ret = usbhsf_fifo_select(pipe, fifo, 0); @@ -1172,6 +1176,7 @@ static int usbhsf_dma_pop_done_with_usb_dmac(struct usbhs_pkt *pkt, usbhsf_fifo_clear(pipe, fifo); pkt->actual = usbhs_dma_calc_received_size(pkt, chan, rcv_len); + usbhs_pipe_running(pipe, 0); usbhsf_dma_stop(pipe, fifo); usbhsf_dma_unmap(pkt); usbhsf_fifo_unselect(pipe, pipe->fifo); diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 5db8ed517e0e..2d8d9150da0c 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -241,6 +241,7 @@ static void option_instat_callback(struct urb *urb); #define QUECTEL_PRODUCT_EC21 0x0121 #define QUECTEL_PRODUCT_EC25 0x0125 #define QUECTEL_PRODUCT_BG96 0x0296 +#define QUECTEL_PRODUCT_EP06 0x0306 #define CMOTECH_VENDOR_ID 0x16d8 #define CMOTECH_PRODUCT_6001 0x6001 @@ -689,6 +690,10 @@ static const struct option_blacklist_info yuga_clm920_nc5_blacklist = { .reserved = BIT(1) | BIT(4), }; +static const struct option_blacklist_info quectel_ep06_blacklist = { + .reserved = BIT(4) | BIT(5), +}; + static const struct usb_device_id option_ids[] = { { USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_COLT) }, { USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_RICOLA) }, @@ -1203,6 +1208,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, { USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_BG96), .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, + { USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06), + .driver_info = (kernel_ulong_t)&quectel_ep06_blacklist }, { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) }, { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_300) }, { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6003), diff --git a/drivers/usb/usbip/stub_dev.c b/drivers/usb/usbip/stub_dev.c index 49e552472c3f..dd8ef36ab10e 100644 --- a/drivers/usb/usbip/stub_dev.c +++ b/drivers/usb/usbip/stub_dev.c @@ -73,6 +73,7 @@ static ssize_t usbip_sockfd_store(struct device *dev, struct device_attribute *a goto err; sdev->ud.tcp_socket = socket; + sdev->ud.sockfd = sockfd; spin_unlock_irq(&sdev->ud.lock); @@ -172,6 +173,7 @@ static void stub_shutdown_connection(struct usbip_device *ud) if (ud->tcp_socket) { sockfd_put(ud->tcp_socket); ud->tcp_socket = NULL; + ud->sockfd = -1; } /* 3. free used data */ @@ -266,6 +268,7 @@ static struct stub_device *stub_device_alloc(struct usb_device *udev) sdev->ud.status = SDEV_ST_AVAILABLE; spin_lock_init(&sdev->ud.lock); sdev->ud.tcp_socket = NULL; + sdev->ud.sockfd = -1; INIT_LIST_HEAD(&sdev->priv_init); INIT_LIST_HEAD(&sdev->priv_tx); diff --git a/drivers/usb/usbip/vhci_hcd.c b/drivers/usb/usbip/vhci_hcd.c index c3e1008aa491..20e3d4609583 100644 --- a/drivers/usb/usbip/vhci_hcd.c +++ b/drivers/usb/usbip/vhci_hcd.c @@ -984,6 +984,7 @@ static void vhci_shutdown_connection(struct usbip_device *ud) if (vdev->ud.tcp_socket) { sockfd_put(vdev->ud.tcp_socket); vdev->ud.tcp_socket = NULL; + vdev->ud.sockfd = -1; } pr_info("release socket\n"); @@ -1030,6 +1031,7 @@ static void vhci_device_reset(struct usbip_device *ud) if (ud->tcp_socket) { sockfd_put(ud->tcp_socket); ud->tcp_socket = NULL; + ud->sockfd = -1; } ud->status = VDEV_ST_NULL; diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 610cba276d47..b5fb56b822fd 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1038,7 +1038,7 @@ static struct socket *get_raw_socket(int fd) struct sockaddr_ll sa; char buf[MAX_ADDR_LEN]; } uaddr; - int uaddr_len = sizeof uaddr, r; + int r; struct socket *sock = sockfd_lookup(fd, &r); if (!sock) @@ -1050,9 +1050,8 @@ static struct socket *get_raw_socket(int fd) goto err; } - r = sock->ops->getname(sock, (struct sockaddr *)&uaddr.sa, - &uaddr_len, 0); - if (r) + r = sock->ops->getname(sock, (struct sockaddr *)&uaddr.sa, 0); + if (r < 0) goto err; if (uaddr.sa.sll_family != AF_PACKET) { diff --git a/drivers/video/fbdev/geode/video_gx.c b/drivers/video/fbdev/geode/video_gx.c index 6082f653c68a..67773e8bbb95 100644 --- a/drivers/video/fbdev/geode/video_gx.c +++ b/drivers/video/fbdev/geode/video_gx.c @@ -127,7 +127,7 @@ void gx_set_dclk_frequency(struct fb_info *info) int timeout = 1000; /* Rev. 1 Geode GXs use a 14 MHz reference clock instead of 48 MHz. */ - if (cpu_data(0).x86_mask == 1) { + if (cpu_data(0).x86_stepping == 1) { pll_table = gx_pll_table_14MHz; pll_table_len = ARRAY_SIZE(gx_pll_table_14MHz); } else { diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c index 753d9cb437d0..aedbee3b2838 100644 --- a/drivers/xen/pvcalls-front.c +++ b/drivers/xen/pvcalls-front.c @@ -60,6 +60,7 @@ struct sock_mapping { bool active_socket; struct list_head list; struct socket *sock; + atomic_t refcount; union { struct { int irq; @@ -93,6 +94,32 @@ struct sock_mapping { }; }; +static inline struct sock_mapping *pvcalls_enter_sock(struct socket *sock) +{ + struct sock_mapping *map; + + if (!pvcalls_front_dev || + dev_get_drvdata(&pvcalls_front_dev->dev) == NULL) + return ERR_PTR(-ENOTCONN); + + map = (struct sock_mapping *)sock->sk->sk_send_head; + if (map == NULL) + return ERR_PTR(-ENOTSOCK); + + pvcalls_enter(); + atomic_inc(&map->refcount); + return map; +} + +static inline void pvcalls_exit_sock(struct socket *sock) +{ + struct sock_mapping *map; + + map = (struct sock_mapping *)sock->sk->sk_send_head; + atomic_dec(&map->refcount); + pvcalls_exit(); +} + static inline int get_request(struct pvcalls_bedata *bedata, int *req_id) { *req_id = bedata->ring.req_prod_pvt & (RING_SIZE(&bedata->ring) - 1); @@ -369,31 +396,23 @@ int pvcalls_front_connect(struct socket *sock, struct sockaddr *addr, if (addr->sa_family != AF_INET || sock->type != SOCK_STREAM) return -EOPNOTSUPP; - pvcalls_enter(); - if (!pvcalls_front_dev) { - pvcalls_exit(); - return -ENOTCONN; - } + map = pvcalls_enter_sock(sock); + if (IS_ERR(map)) + return PTR_ERR(map); bedata = dev_get_drvdata(&pvcalls_front_dev->dev); - map = (struct sock_mapping *)sock->sk->sk_send_head; - if (!map) { - pvcalls_exit(); - return -ENOTSOCK; - } - spin_lock(&bedata->socket_lock); ret = get_request(bedata, &req_id); if (ret < 0) { spin_unlock(&bedata->socket_lock); - pvcalls_exit(); + pvcalls_exit_sock(sock); return ret; } ret = create_active(map, &evtchn); if (ret < 0) { spin_unlock(&bedata->socket_lock); - pvcalls_exit(); + pvcalls_exit_sock(sock); return ret; } @@ -423,7 +442,7 @@ int pvcalls_front_connect(struct socket *sock, struct sockaddr *addr, smp_rmb(); ret = bedata->rsp[req_id].ret; bedata->rsp[req_id].req_id = PVCALLS_INVALID_ID; - pvcalls_exit(); + pvcalls_exit_sock(sock); return ret; } @@ -488,23 +507,15 @@ int pvcalls_front_sendmsg(struct socket *sock, struct msghdr *msg, if (flags & (MSG_CONFIRM|MSG_DONTROUTE|MSG_EOR|MSG_OOB)) return -EOPNOTSUPP; - pvcalls_enter(); - if (!pvcalls_front_dev) { - pvcalls_exit(); - return -ENOTCONN; - } + map = pvcalls_enter_sock(sock); + if (IS_ERR(map)) + return PTR_ERR(map); bedata = dev_get_drvdata(&pvcalls_front_dev->dev); - map = (struct sock_mapping *) sock->sk->sk_send_head; - if (!map) { - pvcalls_exit(); - return -ENOTSOCK; - } - mutex_lock(&map->active.out_mutex); if ((flags & MSG_DONTWAIT) && !pvcalls_front_write_todo(map)) { mutex_unlock(&map->active.out_mutex); - pvcalls_exit(); + pvcalls_exit_sock(sock); return -EAGAIN; } if (len > INT_MAX) @@ -526,7 +537,7 @@ again: tot_sent = sent; mutex_unlock(&map->active.out_mutex); - pvcalls_exit(); + pvcalls_exit_sock(sock); return tot_sent; } @@ -591,19 +602,11 @@ int pvcalls_front_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, if (flags & (MSG_CMSG_CLOEXEC|MSG_ERRQUEUE|MSG_OOB|MSG_TRUNC)) return -EOPNOTSUPP; - pvcalls_enter(); - if (!pvcalls_front_dev) { - pvcalls_exit(); - return -ENOTCONN; - } + map = pvcalls_enter_sock(sock); + if (IS_ERR(map)) + return PTR_ERR(map); bedata = dev_get_drvdata(&pvcalls_front_dev->dev); - map = (struct sock_mapping *) sock->sk->sk_send_head; - if (!map) { - pvcalls_exit(); - return -ENOTSOCK; - } - mutex_lock(&map->active.in_mutex); if (len > XEN_FLEX_RING_SIZE(PVCALLS_RING_ORDER)) len = XEN_FLEX_RING_SIZE(PVCALLS_RING_ORDER); @@ -623,7 +626,7 @@ int pvcalls_front_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, ret = 0; mutex_unlock(&map->active.in_mutex); - pvcalls_exit(); + pvcalls_exit_sock(sock); return ret; } @@ -637,24 +640,16 @@ int pvcalls_front_bind(struct socket *sock, struct sockaddr *addr, int addr_len) if (addr->sa_family != AF_INET || sock->type != SOCK_STREAM) return -EOPNOTSUPP; - pvcalls_enter(); - if (!pvcalls_front_dev) { - pvcalls_exit(); - return -ENOTCONN; - } + map = pvcalls_enter_sock(sock); + if (IS_ERR(map)) + return PTR_ERR(map); bedata = dev_get_drvdata(&pvcalls_front_dev->dev); - map = (struct sock_mapping *) sock->sk->sk_send_head; - if (map == NULL) { - pvcalls_exit(); - return -ENOTSOCK; - } - spin_lock(&bedata->socket_lock); ret = get_request(bedata, &req_id); if (ret < 0) { spin_unlock(&bedata->socket_lock); - pvcalls_exit(); + pvcalls_exit_sock(sock); return ret; } req = RING_GET_REQUEST(&bedata->ring, req_id); @@ -684,7 +679,7 @@ int pvcalls_front_bind(struct socket *sock, struct sockaddr *addr, int addr_len) bedata->rsp[req_id].req_id = PVCALLS_INVALID_ID; map->passive.status = PVCALLS_STATUS_BIND; - pvcalls_exit(); + pvcalls_exit_sock(sock); return 0; } @@ -695,21 +690,13 @@ int pvcalls_front_listen(struct socket *sock, int backlog) struct xen_pvcalls_request *req; int notify, req_id, ret; - pvcalls_enter(); - if (!pvcalls_front_dev) { - pvcalls_exit(); - return -ENOTCONN; - } + map = pvcalls_enter_sock(sock); + if (IS_ERR(map)) + return PTR_ERR(map); bedata = dev_get_drvdata(&pvcalls_front_dev->dev); - map = (struct sock_mapping *) sock->sk->sk_send_head; - if (!map) { - pvcalls_exit(); - return -ENOTSOCK; - } - if (map->passive.status != PVCALLS_STATUS_BIND) { - pvcalls_exit(); + pvcalls_exit_sock(sock); return -EOPNOTSUPP; } @@ -717,7 +704,7 @@ int pvcalls_front_listen(struct socket *sock, int backlog) ret = get_request(bedata, &req_id); if (ret < 0) { spin_unlock(&bedata->socket_lock); - pvcalls_exit(); + pvcalls_exit_sock(sock); return ret; } req = RING_GET_REQUEST(&bedata->ring, req_id); @@ -741,7 +728,7 @@ int pvcalls_front_listen(struct socket *sock, int backlog) bedata->rsp[req_id].req_id = PVCALLS_INVALID_ID; map->passive.status = PVCALLS_STATUS_LISTEN; - pvcalls_exit(); + pvcalls_exit_sock(sock); return ret; } @@ -753,21 +740,13 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags) struct xen_pvcalls_request *req; int notify, req_id, ret, evtchn, nonblock; - pvcalls_enter(); - if (!pvcalls_front_dev) { - pvcalls_exit(); - return -ENOTCONN; - } + map = pvcalls_enter_sock(sock); + if (IS_ERR(map)) + return PTR_ERR(map); bedata = dev_get_drvdata(&pvcalls_front_dev->dev); - map = (struct sock_mapping *) sock->sk->sk_send_head; - if (!map) { - pvcalls_exit(); - return -ENOTSOCK; - } - if (map->passive.status != PVCALLS_STATUS_LISTEN) { - pvcalls_exit(); + pvcalls_exit_sock(sock); return -EINVAL; } @@ -785,13 +764,13 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags) goto received; } if (nonblock) { - pvcalls_exit(); + pvcalls_exit_sock(sock); return -EAGAIN; } if (wait_event_interruptible(map->passive.inflight_accept_req, !test_and_set_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT, (void *)&map->passive.flags))) { - pvcalls_exit(); + pvcalls_exit_sock(sock); return -EINTR; } } @@ -802,7 +781,7 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags) clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT, (void *)&map->passive.flags); spin_unlock(&bedata->socket_lock); - pvcalls_exit(); + pvcalls_exit_sock(sock); return ret; } map2 = kzalloc(sizeof(*map2), GFP_ATOMIC); @@ -810,7 +789,7 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags) clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT, (void *)&map->passive.flags); spin_unlock(&bedata->socket_lock); - pvcalls_exit(); + pvcalls_exit_sock(sock); return -ENOMEM; } ret = create_active(map2, &evtchn); @@ -819,7 +798,7 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags) clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT, (void *)&map->passive.flags); spin_unlock(&bedata->socket_lock); - pvcalls_exit(); + pvcalls_exit_sock(sock); return ret; } list_add_tail(&map2->list, &bedata->socket_mappings); @@ -841,13 +820,13 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags) /* We could check if we have received a response before returning. */ if (nonblock) { WRITE_ONCE(map->passive.inflight_req_id, req_id); - pvcalls_exit(); + pvcalls_exit_sock(sock); return -EAGAIN; } if (wait_event_interruptible(bedata->inflight_req, READ_ONCE(bedata->rsp[req_id].req_id) == req_id)) { - pvcalls_exit(); + pvcalls_exit_sock(sock); return -EINTR; } /* read req_id, then the content */ @@ -862,7 +841,7 @@ received: clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT, (void *)&map->passive.flags); pvcalls_front_free_map(bedata, map2); - pvcalls_exit(); + pvcalls_exit_sock(sock); return -ENOMEM; } newsock->sk->sk_send_head = (void *)map2; @@ -874,7 +853,7 @@ received: clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT, (void *)&map->passive.flags); wake_up(&map->passive.inflight_accept_req); - pvcalls_exit(); + pvcalls_exit_sock(sock); return ret; } @@ -965,23 +944,16 @@ __poll_t pvcalls_front_poll(struct file *file, struct socket *sock, struct sock_mapping *map; __poll_t ret; - pvcalls_enter(); - if (!pvcalls_front_dev) { - pvcalls_exit(); + map = pvcalls_enter_sock(sock); + if (IS_ERR(map)) return EPOLLNVAL; - } bedata = dev_get_drvdata(&pvcalls_front_dev->dev); - map = (struct sock_mapping *) sock->sk->sk_send_head; - if (!map) { - pvcalls_exit(); - return EPOLLNVAL; - } if (map->active_socket) ret = pvcalls_front_poll_active(file, bedata, map, wait); else ret = pvcalls_front_poll_passive(file, bedata, map, wait); - pvcalls_exit(); + pvcalls_exit_sock(sock); return ret; } @@ -995,25 +967,20 @@ int pvcalls_front_release(struct socket *sock) if (sock->sk == NULL) return 0; - pvcalls_enter(); - if (!pvcalls_front_dev) { - pvcalls_exit(); - return -EIO; + map = pvcalls_enter_sock(sock); + if (IS_ERR(map)) { + if (PTR_ERR(map) == -ENOTCONN) + return -EIO; + else + return 0; } - bedata = dev_get_drvdata(&pvcalls_front_dev->dev); - map = (struct sock_mapping *) sock->sk->sk_send_head; - if (map == NULL) { - pvcalls_exit(); - return 0; - } - spin_lock(&bedata->socket_lock); ret = get_request(bedata, &req_id); if (ret < 0) { spin_unlock(&bedata->socket_lock); - pvcalls_exit(); + pvcalls_exit_sock(sock); return ret; } sock->sk->sk_send_head = NULL; @@ -1043,14 +1010,20 @@ int pvcalls_front_release(struct socket *sock) /* * We need to make sure that sendmsg/recvmsg on this socket have * not started before we've cleared sk_send_head here. The - * easiest (though not optimal) way to guarantee this is to see - * that no pvcall (other than us) is in progress. + * easiest way to guarantee this is to see that no pvcalls + * (other than us) is in progress on this socket. */ - while (atomic_read(&pvcalls_refcount) > 1) + while (atomic_read(&map->refcount) > 1) cpu_relax(); pvcalls_front_free_map(bedata, map); } else { + wake_up(&bedata->inflight_req); + wake_up(&map->passive.inflight_accept_req); + + while (atomic_read(&map->refcount) > 1) + cpu_relax(); + spin_lock(&bedata->socket_lock); list_del(&map->list); spin_unlock(&bedata->socket_lock); diff --git a/drivers/xen/tmem.c b/drivers/xen/tmem.c index bf13d1ec51f3..04e7b3b29bac 100644 --- a/drivers/xen/tmem.c +++ b/drivers/xen/tmem.c @@ -284,6 +284,10 @@ static int tmem_frontswap_store(unsigned type, pgoff_t offset, int pool = tmem_frontswap_poolid; int ret; + /* THP isn't supported */ + if (PageTransHuge(page)) + return -1; + if (pool < 0) return -1; if (ind64 != ind) diff --git a/drivers/xen/xenbus/xenbus.h b/drivers/xen/xenbus/xenbus.h index 149c5e7efc89..092981171df1 100644 --- a/drivers/xen/xenbus/xenbus.h +++ b/drivers/xen/xenbus/xenbus.h @@ -76,6 +76,7 @@ struct xb_req_data { struct list_head list; wait_queue_head_t wq; struct xsd_sockmsg msg; + uint32_t caller_req_id; enum xsd_sockmsg_type type; char *body; const struct kvec *vec; diff --git a/drivers/xen/xenbus/xenbus_comms.c b/drivers/xen/xenbus/xenbus_comms.c index 5b081a01779d..d239fc3c5e3d 100644 --- a/drivers/xen/xenbus/xenbus_comms.c +++ b/drivers/xen/xenbus/xenbus_comms.c @@ -309,6 +309,7 @@ static int process_msg(void) goto out; if (req->state == xb_req_state_wait_reply) { + req->msg.req_id = req->caller_req_id; req->msg.type = state.msg.type; req->msg.len = state.msg.len; req->body = state.body; diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c index 3e59590c7254..3f3b29398ab8 100644 --- a/drivers/xen/xenbus/xenbus_xs.c +++ b/drivers/xen/xenbus/xenbus_xs.c @@ -227,6 +227,8 @@ static void xs_send(struct xb_req_data *req, struct xsd_sockmsg *msg) req->state = xb_req_state_queued; init_waitqueue_head(&req->wq); + /* Save the caller req_id and restore it later in the reply */ + req->caller_req_id = req->msg.req_id; req->msg.req_id = xs_request_enter(req); mutex_lock(&xb_write_mutex); @@ -310,6 +312,7 @@ static void *xs_talkv(struct xenbus_transaction t, req->num_vecs = num_vecs; req->cb = xs_wake_up; + msg.req_id = 0; msg.tx_id = t.id; msg.type = type; msg.len = 0; diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index e4054e533f6d..f94b2d8c744a 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1264,7 +1264,16 @@ again: while (node) { ref = rb_entry(node, struct prelim_ref, rbnode); node = rb_next(&ref->rbnode); - WARN_ON(ref->count < 0); + /* + * ref->count < 0 can happen here if there are delayed + * refs with a node->action of BTRFS_DROP_DELAYED_REF. + * prelim_ref_insert() relies on this when merging + * identical refs to keep the overall count correct. + * prelim_ref_insert() will merge only those refs + * which compare identically. Any refs having + * e.g. different offsets would not be merged, + * and would retain their original ref->count < 0. + */ if (roots && ref->count && ref->root_id && ref->parent == 0) { if (sc && sc->root_objectid && ref->root_id != sc->root_objectid) { diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index a1a40cf382e3..7ab5e0128f0c 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -821,7 +821,8 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info, spin_unlock(&delayed_refs->lock); if (qrecord_inserted) - return btrfs_qgroup_trace_extent_post(fs_info, record); + btrfs_qgroup_trace_extent_post(fs_info, record); + return 0; free_head_ref: diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 05751a677da4..c1618ab9fecf 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2147,6 +2147,10 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr, u64 bytes; struct request_queue *req_q; + if (!stripe->dev->bdev) { + ASSERT(btrfs_test_opt(fs_info, DEGRADED)); + continue; + } req_q = bdev_get_queue(stripe->dev->bdev); if (!blk_queue_discard(req_q)) continue; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 53ca025655fc..a79299a89b7d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1335,8 +1335,11 @@ next_slot: leaf = path->nodes[0]; if (path->slots[0] >= btrfs_header_nritems(leaf)) { ret = btrfs_next_leaf(root, path); - if (ret < 0) + if (ret < 0) { + if (cow_start != (u64)-1) + cur_offset = cow_start; goto error; + } if (ret > 0) break; leaf = path->nodes[0]; @@ -3385,6 +3388,11 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, ret = btrfs_orphan_reserve_metadata(trans, inode); ASSERT(!ret); if (ret) { + /* + * dec doesn't need spin_lock as ->orphan_block_rsv + * would be released only if ->orphan_inodes is + * zero. + */ atomic_dec(&root->orphan_inodes); clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED, &inode->runtime_flags); @@ -3399,12 +3407,17 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, if (insert >= 1) { ret = btrfs_insert_orphan_item(trans, root, btrfs_ino(inode)); if (ret) { - atomic_dec(&root->orphan_inodes); if (reserve) { clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED, &inode->runtime_flags); btrfs_orphan_release_metadata(inode); } + /* + * btrfs_orphan_commit_root may race with us and set + * ->orphan_block_rsv to zero, in order to avoid that, + * decrease ->orphan_inodes after everything is done. + */ + atomic_dec(&root->orphan_inodes); if (ret != -EEXIST) { clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, &inode->runtime_flags); @@ -3436,28 +3449,26 @@ static int btrfs_orphan_del(struct btrfs_trans_handle *trans, { struct btrfs_root *root = inode->root; int delete_item = 0; - int release_rsv = 0; int ret = 0; - spin_lock(&root->orphan_lock); if (test_and_clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, &inode->runtime_flags)) delete_item = 1; + if (delete_item && trans) + ret = btrfs_del_orphan_item(trans, root, btrfs_ino(inode)); + if (test_and_clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED, &inode->runtime_flags)) - release_rsv = 1; - spin_unlock(&root->orphan_lock); + btrfs_orphan_release_metadata(inode); - if (delete_item) { + /* + * btrfs_orphan_commit_root may race with us and set ->orphan_block_rsv + * to zero, in order to avoid that, decrease ->orphan_inodes after + * everything is done. + */ + if (delete_item) atomic_dec(&root->orphan_inodes); - if (trans) - ret = btrfs_del_orphan_item(trans, root, - btrfs_ino(inode)); - } - - if (release_rsv) - btrfs_orphan_release_metadata(inode); return ret; } @@ -5281,7 +5292,7 @@ void btrfs_evict_inode(struct inode *inode) trace_btrfs_inode_evict(inode); if (!root) { - kmem_cache_free(btrfs_inode_cachep, BTRFS_I(inode)); + clear_inode(inode); return; } diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 9e61dd624f7b..aa259d6986e1 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1442,8 +1442,13 @@ int btrfs_qgroup_trace_extent_post(struct btrfs_fs_info *fs_info, int ret; ret = btrfs_find_all_roots(NULL, fs_info, bytenr, 0, &old_root, false); - if (ret < 0) - return ret; + if (ret < 0) { + fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; + btrfs_warn(fs_info, +"error accounting new delayed refs extent (err code: %d), quota inconsistent", + ret); + return 0; + } /* * Here we don't need to get the lock of diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index afadaadab18e..4fd19b4d6675 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -29,6 +29,7 @@ #include "hash.h" #include "compression.h" #include "qgroup.h" +#include "inode-map.h" /* magic values for the inode_only field in btrfs_log_inode: * @@ -2472,6 +2473,9 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans, clean_tree_block(fs_info, next); btrfs_wait_tree_block_writeback(next); btrfs_tree_unlock(next); + } else { + if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags)) + clear_extent_buffer_dirty(next); } WARN_ON(root_owner != @@ -2552,6 +2556,9 @@ static noinline int walk_up_log_tree(struct btrfs_trans_handle *trans, clean_tree_block(fs_info, next); btrfs_wait_tree_block_writeback(next); btrfs_tree_unlock(next); + } else { + if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags)) + clear_extent_buffer_dirty(next); } WARN_ON(root_owner != BTRFS_TREE_LOG_OBJECTID); @@ -2630,6 +2637,9 @@ static int walk_log_tree(struct btrfs_trans_handle *trans, clean_tree_block(fs_info, next); btrfs_wait_tree_block_writeback(next); btrfs_tree_unlock(next); + } else { + if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags)) + clear_extent_buffer_dirty(next); } WARN_ON(log->root_key.objectid != @@ -3018,13 +3028,14 @@ static void free_log_tree(struct btrfs_trans_handle *trans, while (1) { ret = find_first_extent_bit(&log->dirty_log_pages, - 0, &start, &end, EXTENT_DIRTY | EXTENT_NEW, + 0, &start, &end, + EXTENT_DIRTY | EXTENT_NEW | EXTENT_NEED_WAIT, NULL); if (ret) break; clear_extent_bits(&log->dirty_log_pages, start, end, - EXTENT_DIRTY | EXTENT_NEW); + EXTENT_DIRTY | EXTENT_NEW | EXTENT_NEED_WAIT); } /* @@ -5677,6 +5688,23 @@ again: path); } + if (!ret && wc.stage == LOG_WALK_REPLAY_ALL) { + struct btrfs_root *root = wc.replay_dest; + + btrfs_release_path(path); + + /* + * We have just replayed everything, and the highest + * objectid of fs roots probably has changed in case + * some inode_item's got replayed. + * + * root->objectid_mutex is not acquired as log replay + * could only happen during mount. + */ + ret = btrfs_find_highest_objectid(root, + &root->highest_objectid); + } + key.offset = found_key.offset - 1; wc.replay_dest->log_root = NULL; free_extent_buffer(log->node); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index b5036bd69e6a..2ceb924ca0d6 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -645,6 +645,7 @@ static void btrfs_free_stale_devices(const char *path, btrfs_sysfs_remove_fsid(fs_devs); list_del(&fs_devs->list); free_fs_devices(fs_devs); + break; } else { fs_devs->num_devices--; list_del(&dev->dev_list); diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index cff79ea0c01d..5243989a60cc 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -482,7 +482,6 @@ static void lowcomms_error_report(struct sock *sk) { struct connection *con; struct sockaddr_storage saddr; - int buflen; void (*orig_report)(struct sock *) = NULL; read_lock_bh(&sk->sk_callback_lock); @@ -492,7 +491,7 @@ static void lowcomms_error_report(struct sock *sk) orig_report = listen_sock.sk_error_report; if (con->sock == NULL || - kernel_getpeername(con->sock, (struct sockaddr *)&saddr, &buflen)) { + kernel_getpeername(con->sock, (struct sockaddr *)&saddr) < 0) { printk_ratelimited(KERN_ERR "dlm: node %d: socket error " "sending to node %d, port %d, " "sk_err=%d/%d\n", dlm_our_nodeid(), @@ -757,8 +756,8 @@ static int tcp_accept_from_sock(struct connection *con) /* Get the connected socket's peer */ memset(&peeraddr, 0, sizeof(peeraddr)); - if (newsock->ops->getname(newsock, (struct sockaddr *)&peeraddr, - &len, 2)) { + len = newsock->ops->getname(newsock, (struct sockaddr *)&peeraddr, 2); + if (len < 0) { result = -ECONNABORTED; goto accept_err; } diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c index 5f22e74bbade..8e568428c88b 100644 --- a/fs/efivarfs/file.c +++ b/fs/efivarfs/file.c @@ -8,6 +8,7 @@ */ #include <linux/efi.h> +#include <linux/delay.h> #include <linux/fs.h> #include <linux/slab.h> #include <linux/mount.h> @@ -74,6 +75,11 @@ static ssize_t efivarfs_file_read(struct file *file, char __user *userbuf, ssize_t size = 0; int err; + while (!__ratelimit(&file->f_cred->user->ratelimit)) { + if (!msleep_interruptible(50)) + return -EINTR; + } + err = efivar_entry_size(var, &datasize); /* diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 86863792f36a..86d6a4435c87 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -716,7 +716,7 @@ int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length, __be64 *ptr; sector_t lblock; sector_t lend; - int ret; + int ret = 0; int eob; unsigned int len; struct buffer_head *bh; @@ -728,12 +728,14 @@ int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length, goto out; } - if ((flags & IOMAP_REPORT) && gfs2_is_stuffed(ip)) { - gfs2_stuffed_iomap(inode, iomap); - if (pos >= iomap->length) - return -ENOENT; - ret = 0; - goto out; + if (gfs2_is_stuffed(ip)) { + if (flags & IOMAP_REPORT) { + gfs2_stuffed_iomap(inode, iomap); + if (pos >= iomap->length) + ret = -ENOENT; + goto out; + } + BUG_ON(!(flags & IOMAP_WRITE)); } lblock = pos >> inode->i_blkbits; @@ -744,7 +746,7 @@ int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length, iomap->type = IOMAP_HOLE; iomap->length = (u64)(lend - lblock) << inode->i_blkbits; iomap->flags = IOMAP_F_MERGED; - bmap_lock(ip, 0); + bmap_lock(ip, flags & IOMAP_WRITE); /* * Directory data blocks have a struct gfs2_meta_header header, so the @@ -787,27 +789,28 @@ int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length, iomap->flags |= IOMAP_F_BOUNDARY; iomap->length = (u64)len << inode->i_blkbits; - ret = 0; - out_release: release_metapath(&mp); - bmap_unlock(ip, 0); + bmap_unlock(ip, flags & IOMAP_WRITE); out: trace_gfs2_iomap_end(ip, iomap, ret); return ret; do_alloc: - if (!(flags & IOMAP_WRITE)) { - if (pos >= i_size_read(inode)) { + if (flags & IOMAP_WRITE) { + ret = gfs2_iomap_alloc(inode, iomap, flags, &mp); + } else if (flags & IOMAP_REPORT) { + loff_t size = i_size_read(inode); + if (pos >= size) ret = -ENOENT; - goto out_release; - } - ret = 0; - iomap->length = hole_size(inode, lblock, &mp); - goto out_release; + else if (height <= ip->i_height) + iomap->length = hole_size(inode, lblock, &mp); + else + iomap->length = size - pos; + } else { + if (height <= ip->i_height) + iomap->length = hole_size(inode, lblock, &mp); } - - ret = gfs2_iomap_alloc(inode, iomap, flags, &mp); goto out_release; } diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 9c36d614bf89..2dee4e03ff1c 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -709,6 +709,7 @@ static struct pernet_operations lockd_net_ops = { .exit = lockd_exit_net, .id = &lockd_net_id, .size = sizeof(struct lockd_net), + .async = true, }; diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 7d893543cf3b..6c3083c992e5 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -2122,6 +2122,7 @@ static struct pernet_operations nfs_net_ops = { .exit = nfs_net_exit, .id = &nfs_net_id, .size = sizeof(struct nfs_net), + .async = true, }; /* diff --git a/fs/nfs_common/grace.c b/fs/nfs_common/grace.c index 5be08f02a76b..8c743a405df6 100644 --- a/fs/nfs_common/grace.c +++ b/fs/nfs_common/grace.c @@ -118,6 +118,7 @@ static struct pernet_operations grace_net_ops = { .exit = grace_exit_net, .id = &grace_net_id, .size = sizeof(struct list_head), + .async = true, }; static int __init diff --git a/fs/nsfs.c b/fs/nsfs.c index 36b0772701a0..60702d677bd4 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -184,6 +184,7 @@ int open_related_ns(struct ns_common *ns, return fd; } +EXPORT_SYMBOL_GPL(open_related_ns); static long ns_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index eac5140aac47..e5076185cc1e 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -1819,7 +1819,7 @@ int o2net_register_hb_callbacks(void) static int o2net_accept_one(struct socket *sock, int *more) { - int ret, slen; + int ret; struct sockaddr_in sin; struct socket *new_sock = NULL; struct o2nm_node *node = NULL; @@ -1864,9 +1864,7 @@ static int o2net_accept_one(struct socket *sock, int *more) goto out; } - slen = sizeof(sin); - ret = new_sock->ops->getname(new_sock, (struct sockaddr *) &sin, - &slen, 1); + ret = new_sock->ops->getname(new_sock, (struct sockaddr *) &sin, 1); if (ret < 0) goto out; diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index e8a93bc8285d..d1e82761de81 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -510,6 +510,10 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) /* we have to zero-fill user buffer even if no read */ if (copy_to_user(buffer, buf, tsz)) return -EFAULT; + } else if (m->type == KCORE_USER) { + /* User page is handled prior to normal kernel page: */ + if (copy_to_user(buffer, (char *)start, tsz)) + return -EFAULT; } else { if (kern_addr_valid(start)) { /* diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index 68c06ae7888c..da6f8733c9c5 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -237,6 +237,7 @@ static __net_exit void proc_net_ns_exit(struct net *net) static struct pernet_operations __net_initdata proc_net_ns_ops = { .init = proc_net_ns_init, .exit = proc_net_ns_exit, + .async = true, }; int __init proc_net_init(void) diff --git a/fs/signalfd.c b/fs/signalfd.c index 9990957264e3..76bf9cc62074 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -118,13 +118,22 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo, err |= __put_user(kinfo->si_trapno, &uinfo->ssi_trapno); #endif #ifdef BUS_MCEERR_AO - /* + /* + * Other callers might not initialize the si_lsb field, + * so check explicitly for the right codes here. + */ + if (kinfo->si_signo == SIGBUS && + kinfo->si_code == BUS_MCEERR_AO) + err |= __put_user((short) kinfo->si_addr_lsb, + &uinfo->ssi_addr_lsb); +#endif +#ifdef BUS_MCEERR_AR + /* * Other callers might not initialize the si_lsb field, * so check explicitly for the right codes here. */ if (kinfo->si_signo == SIGBUS && - (kinfo->si_code == BUS_MCEERR_AR || - kinfo->si_code == BUS_MCEERR_AO)) + kinfo->si_code == BUS_MCEERR_AR) err |= __put_user((short) kinfo->si_addr_lsb, &uinfo->ssi_addr_lsb); #endif diff --git a/include/asm-generic/bitops/lock.h b/include/asm-generic/bitops/lock.h index bc397573c43a..67ab280ad134 100644 --- a/include/asm-generic/bitops/lock.h +++ b/include/asm-generic/bitops/lock.h @@ -7,7 +7,8 @@ * @nr: Bit to set * @addr: Address to count from * - * This operation is atomic and provides acquire barrier semantics. + * This operation is atomic and provides acquire barrier semantics if + * the returned value is 0. * It can be used to implement bit locks. */ #define test_and_set_bit_lock(nr, addr) test_and_set_bit(nr, addr) diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h index 963b755d19b0..a7613e1b0c87 100644 --- a/include/asm-generic/bug.h +++ b/include/asm-generic/bug.h @@ -52,6 +52,7 @@ struct bug_entry { #ifndef HAVE_ARCH_BUG #define BUG() do { \ printk("BUG: failure at %s:%d/%s()!\n", __FILE__, __LINE__, __func__); \ + barrier_before_unreachable(); \ panic("BUG!"); \ } while (0) #endif diff --git a/include/drm/drm_atomic.h b/include/drm/drm_atomic.h index 1c27526c499e..cf13842a6dbd 100644 --- a/include/drm/drm_atomic.h +++ b/include/drm/drm_atomic.h @@ -134,6 +134,15 @@ struct drm_crtc_commit { * &drm_pending_vblank_event pointer to clean up private events. */ struct drm_pending_vblank_event *event; + + /** + * @abort_completion: + * + * A flag that's set after drm_atomic_helper_setup_commit takes a second + * reference for the completion of $drm_crtc_state.event. It's used by + * the free code to remove the second reference if commit fails. + */ + bool abort_completion; }; struct __drm_planes_state { diff --git a/include/drm/drm_crtc_helper.h b/include/drm/drm_crtc_helper.h index 76e237bd989b..6914633037a5 100644 --- a/include/drm/drm_crtc_helper.h +++ b/include/drm/drm_crtc_helper.h @@ -77,5 +77,6 @@ void drm_kms_helper_hotplug_event(struct drm_device *dev); void drm_kms_helper_poll_disable(struct drm_device *dev); void drm_kms_helper_poll_enable(struct drm_device *dev); +bool drm_kms_helper_is_poll_worker(void); #endif diff --git a/include/dt-bindings/net/ti-dp83867.h b/include/dt-bindings/net/ti-dp83867.h index 172744a72eb7..7b1656427cbe 100644 --- a/include/dt-bindings/net/ti-dp83867.h +++ b/include/dt-bindings/net/ti-dp83867.h @@ -42,4 +42,18 @@ #define DP83867_RGMIIDCTL_3_75_NS 0xe #define DP83867_RGMIIDCTL_4_00_NS 0xf +/* IO_MUX_CFG - Clock output selection */ +#define DP83867_CLK_O_SEL_CHN_A_RCLK 0x0 +#define DP83867_CLK_O_SEL_CHN_B_RCLK 0x1 +#define DP83867_CLK_O_SEL_CHN_C_RCLK 0x2 +#define DP83867_CLK_O_SEL_CHN_D_RCLK 0x3 +#define DP83867_CLK_O_SEL_CHN_A_RCLK_DIV5 0x4 +#define DP83867_CLK_O_SEL_CHN_B_RCLK_DIV5 0x5 +#define DP83867_CLK_O_SEL_CHN_C_RCLK_DIV5 0x6 +#define DP83867_CLK_O_SEL_CHN_D_RCLK_DIV5 0x7 +#define DP83867_CLK_O_SEL_CHN_A_TCLK 0x8 +#define DP83867_CLK_O_SEL_CHN_B_TCLK 0x9 +#define DP83867_CLK_O_SEL_CHN_C_TCLK 0xA +#define DP83867_CLK_O_SEL_CHN_D_TCLK 0xB +#define DP83867_CLK_O_SEL_REF_CLK 0xC #endif diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 64e10746f282..968173ec2726 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -587,7 +587,7 @@ extern int acpi_nvs_for_each_region(int (*func)(__u64, __u64, void *), const struct acpi_device_id *acpi_match_device(const struct acpi_device_id *ids, const struct device *dev); -void *acpi_get_match_data(const struct device *dev); +const void *acpi_device_get_match_data(const struct device *dev); extern bool acpi_driver_match_device(struct device *dev, const struct device_driver *drv); int acpi_device_uevent_modalias(struct device *, struct kobj_uevent_env *); @@ -766,7 +766,7 @@ static inline const struct acpi_device_id *acpi_match_device( return NULL; } -static inline void *acpi_get_match_data(const struct device *dev) +static inline const void *acpi_device_get_match_data(const struct device *dev) { return NULL; } diff --git a/include/linux/atalk.h b/include/linux/atalk.h index 4d356e168692..40373920ea58 100644 --- a/include/linux/atalk.h +++ b/include/linux/atalk.h @@ -113,10 +113,12 @@ extern void aarp_proto_init(void); /* Inter module exports */ /* Give a device find its atif control structure */ +#if IS_ENABLED(CONFIG_IRDA) || IS_ENABLED(CONFIG_ATALK) static inline struct atalk_iface *atalk_find_dev(struct net_device *dev) { return dev->atalk_ptr; } +#endif extern struct atalk_addr *atalk_find_dev_addr(struct net_device *dev); extern struct net_device *atrtr_get_dev(struct atalk_addr *sa); diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 3ce61342fa31..b0a7f315bfbe 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -136,15 +136,21 @@ enum virtchnl_ops { VIRTCHNL_OP_ENABLE_VLAN_STRIPPING = 27, VIRTCHNL_OP_DISABLE_VLAN_STRIPPING = 28, VIRTCHNL_OP_REQUEST_QUEUES = 29, + VIRTCHNL_OP_ENABLE_CHANNELS = 30, + VIRTCHNL_OP_DISABLE_CHANNELS = 31, + VIRTCHNL_OP_ADD_CLOUD_FILTER = 32, + VIRTCHNL_OP_DEL_CLOUD_FILTER = 33, }; -/* This macro is used to generate a compilation error if a structure +/* These macros are used to generate compilation errors if a structure/union * is not exactly the correct length. It gives a divide by zero error if the - * structure is not of the correct size, otherwise it creates an enum that is - * never used. + * structure/union is not of the correct size, otherwise it creates an enum + * that is never used. */ #define VIRTCHNL_CHECK_STRUCT_LEN(n, X) enum virtchnl_static_assert_enum_##X \ { virtchnl_static_assert_##X = (n)/((sizeof(struct X) == (n)) ? 1 : 0) } +#define VIRTCHNL_CHECK_UNION_LEN(n, X) enum virtchnl_static_asset_enum_##X \ + { virtchnl_static_assert_##X = (n)/((sizeof(union X) == (n)) ? 1 : 0) } /* Virtual channel message descriptor. This overlays the admin queue * descriptor. All other data is passed in external buffers. @@ -244,6 +250,7 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource); #define VIRTCHNL_VF_OFFLOAD_ENCAP 0X00100000 #define VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM 0X00200000 #define VIRTCHNL_VF_OFFLOAD_RX_ENCAP_CSUM 0X00400000 +#define VIRTCHNL_VF_OFFLOAD_ADQ 0X00800000 #define VF_BASE_MODE_OFFLOADS (VIRTCHNL_VF_OFFLOAD_L2 | \ VIRTCHNL_VF_OFFLOAD_VLAN | \ @@ -496,6 +503,81 @@ struct virtchnl_rss_hena { VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_rss_hena); +/* VIRTCHNL_OP_ENABLE_CHANNELS + * VIRTCHNL_OP_DISABLE_CHANNELS + * VF sends these messages to enable or disable channels based on + * the user specified queue count and queue offset for each traffic class. + * This struct encompasses all the information that the PF needs from + * VF to create a channel. + */ +struct virtchnl_channel_info { + u16 count; /* number of queues in a channel */ + u16 offset; /* queues in a channel start from 'offset' */ + u32 pad; + u64 max_tx_rate; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_channel_info); + +struct virtchnl_tc_info { + u32 num_tc; + u32 pad; + struct virtchnl_channel_info list[1]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(24, virtchnl_tc_info); + +/* VIRTCHNL_ADD_CLOUD_FILTER + * VIRTCHNL_DEL_CLOUD_FILTER + * VF sends these messages to add or delete a cloud filter based on the + * user specified match and action filters. These structures encompass + * all the information that the PF needs from the VF to add/delete a + * cloud filter. + */ + +struct virtchnl_l4_spec { + u8 src_mac[ETH_ALEN]; + u8 dst_mac[ETH_ALEN]; + __be16 vlan_id; + __be16 pad; /* reserved for future use */ + __be32 src_ip[4]; + __be32 dst_ip[4]; + __be16 src_port; + __be16 dst_port; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(52, virtchnl_l4_spec); + +union virtchnl_flow_spec { + struct virtchnl_l4_spec tcp_spec; + u8 buffer[128]; /* reserved for future use */ +}; + +VIRTCHNL_CHECK_UNION_LEN(128, virtchnl_flow_spec); + +enum virtchnl_action { + /* action types */ + VIRTCHNL_ACTION_DROP = 0, + VIRTCHNL_ACTION_TC_REDIRECT, +}; + +enum virtchnl_flow_type { + /* flow types */ + VIRTCHNL_TCP_V4_FLOW = 0, + VIRTCHNL_TCP_V6_FLOW, +}; + +struct virtchnl_filter { + union virtchnl_flow_spec data; + union virtchnl_flow_spec mask; + enum virtchnl_flow_type flow_type; + enum virtchnl_action action; + u32 action_meta; + __u8 field_flags; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(272, virtchnl_filter); + /* VIRTCHNL_OP_EVENT * PF sends this message to inform the VF driver of events that may affect it. * No direct response is expected from the VF, though it may generate other @@ -711,6 +793,25 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, case VIRTCHNL_OP_REQUEST_QUEUES: valid_len = sizeof(struct virtchnl_vf_res_request); break; + case VIRTCHNL_OP_ENABLE_CHANNELS: + valid_len = sizeof(struct virtchnl_tc_info); + if (msglen >= valid_len) { + struct virtchnl_tc_info *vti = + (struct virtchnl_tc_info *)msg; + valid_len += vti->num_tc * + sizeof(struct virtchnl_channel_info); + if (vti->num_tc == 0) + err_msg_format = true; + } + break; + case VIRTCHNL_OP_DISABLE_CHANNELS: + break; + case VIRTCHNL_OP_ADD_CLOUD_FILTER: + valid_len = sizeof(struct virtchnl_filter); + break; + case VIRTCHNL_OP_DEL_CLOUD_FILTER: + valid_len = sizeof(struct virtchnl_filter); + break; /* These are always errors coming from the VF. */ case VIRTCHNL_OP_EVENT: case VIRTCHNL_OP_UNKNOWN: diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 4f3df807cf8f..ed63f3b69c12 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -49,7 +49,7 @@ struct blk_stat_callback; #define BLKDEV_MIN_RQ 4 #define BLKDEV_MAX_RQ 128 /* Default maximum */ -/* Must be consisitent with blk_mq_poll_stats_bkt() */ +/* Must be consistent with blk_mq_poll_stats_bkt() */ #define BLK_MQ_POLL_STATS_BKTS 16 /* diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index a7f16e0f8d68..8a4566691c8f 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -96,7 +96,7 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled && sk) { \ + if (cgroup_bpf_enabled) { \ __ret = __cgroup_bpf_run_filter_sk(sk, \ BPF_CGROUP_INET_SOCK_CREATE); \ } \ diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 631354acfa72..901c1ccb3374 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -167,8 +167,6 @@ #if GCC_VERSION >= 40100 # define __compiletime_object_size(obj) __builtin_object_size(obj, 0) - -#define __nostackprotector __attribute__((__optimize__("no-stack-protector"))) #endif #if GCC_VERSION >= 40300 @@ -196,6 +194,11 @@ #endif /* __CHECKER__ */ #endif /* GCC_VERSION >= 40300 */ +#if GCC_VERSION >= 40400 +#define __optimize(level) __attribute__((__optimize__(level))) +#define __nostackprotector __optimize("no-stack-protector") +#endif /* GCC_VERSION >= 40400 */ + #if GCC_VERSION >= 40500 #ifndef __CHECKER__ @@ -205,6 +208,15 @@ #endif /* + * calling noreturn functions, __builtin_unreachable() and __builtin_trap() + * confuse the stack allocation in gcc, leading to overly large stack + * frames, see https://gcc.gnu.org/bugzilla/show_bug.cgi?id=82365 + * + * Adding an empty inline assembly before it works around the problem + */ +#define barrier_before_unreachable() asm volatile("") + +/* * Mark a position in code as unreachable. This can be used to * suppress control flow warnings after asm blocks that transfer * control elsewhere. @@ -214,7 +226,11 @@ * unreleased. Really, we need to have autoconf for the kernel. */ #define unreachable() \ - do { annotate_unreachable(); __builtin_unreachable(); } while (0) + do { \ + annotate_unreachable(); \ + barrier_before_unreachable(); \ + __builtin_unreachable(); \ + } while (0) /* Mark a function definition as prohibited from being cloned. */ #define __noclone __attribute__((__noclone__, __optimize__("no-tracer"))) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index c2cc57a2f508..ab4711c63601 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -86,6 +86,11 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, # define barrier_data(ptr) barrier() #endif +/* workaround for GCC PR82365 if needed */ +#ifndef barrier_before_unreachable +# define barrier_before_unreachable() do { } while (0) +#endif + /* Unreachable code */ #ifdef CONFIG_STACK_VALIDATION /* @@ -277,6 +282,10 @@ unsigned long read_word_at_a_time(const void *addr) #endif /* __ASSEMBLY__ */ +#ifndef __optimize +# define __optimize(level) +#endif + /* Compile time object size, -1 for unknown */ #ifndef __compiletime_object_size # define __compiletime_object_size(obj) -1 diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 871f9e21810c..0b3fc229086c 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -225,7 +225,7 @@ static inline void cpuidle_coupled_parallel_barrier(struct cpuidle_device *dev, } #endif -#ifdef CONFIG_ARCH_HAS_CPU_RELAX +#if defined(CONFIG_CPU_IDLE) && defined(CONFIG_ARCH_HAS_CPU_RELAX) void cpuidle_poll_state_init(struct cpuidle_driver *drv); #else static inline void cpuidle_poll_state_init(struct cpuidle_driver *drv) {} diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index d4a2a7dcd72d..bf53d893ad02 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -170,6 +170,8 @@ static inline unsigned int cpumask_local_spread(unsigned int i, int node) for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask) #define for_each_cpu_not(cpu, mask) \ for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask) +#define for_each_cpu_wrap(cpu, mask, start) \ + for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask, (void)(start)) #define for_each_cpu_and(cpu, mask, and) \ for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask, (void)and) #else diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 34fe8463d10e..eb9eab4ecd6d 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -578,7 +578,7 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) /* * This is a hack for the legacy x86 forbid_dac and iommu_sac_force. Please - * don't use this is new code. + * don't use this in new code. */ #ifndef arch_dma_supported #define arch_dma_supported(dev, mask) (1) diff --git a/include/linux/filter.h b/include/linux/filter.h index 276932d75975..fdb691b520c0 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -20,7 +20,6 @@ #include <linux/set_memory.h> #include <linux/kallsyms.h> -#include <net/xdp.h> #include <net/sch_generic.h> #include <uapi/linux/filter.h> @@ -30,6 +29,7 @@ struct sk_buff; struct sock; struct seccomp_data; struct bpf_prog_aux; +struct xdp_rxq_info; /* ArgX, context and stack frame pointer register positions. Note, * Arg1, Arg2, Arg3, etc are used as argument mappings of function diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 4fa1a489efe4..4fe8f289b3f6 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -73,8 +73,8 @@ struct fwnode_operations { struct fwnode_handle *(*get)(struct fwnode_handle *fwnode); void (*put)(struct fwnode_handle *fwnode); bool (*device_is_available)(const struct fwnode_handle *fwnode); - void *(*device_get_match_data)(const struct fwnode_handle *fwnode, - const struct device *dev); + const void *(*device_get_match_data)(const struct fwnode_handle *fwnode, + const struct device *dev); bool (*property_present)(const struct fwnode_handle *fwnode, const char *propname); int (*property_read_int_array)(const struct fwnode_handle *fwnode, diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index ee6657a0ed69..8fe7e4306816 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -8,6 +8,7 @@ * Copyright (c) 2006, Michael Wu <flamingice@sourmilk.net> * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH * Copyright (c) 2016 - 2017 Intel Deutschland GmbH + * Copyright (c) 2018 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -2111,7 +2112,7 @@ enum ieee80211_key_len { #define FILS_ERP_MAX_REALM_LEN 253 #define FILS_ERP_MAX_RRK_LEN 64 -#define PMK_MAX_LEN 48 +#define PMK_MAX_LEN 64 /* Public action codes (IEEE Std 802.11-2016, 9.6.8.1, Table 9-307) */ enum ieee80211_pub_actioncode { @@ -2502,6 +2503,17 @@ static inline u8 *ieee80211_get_qos_ctl(struct ieee80211_hdr *hdr) } /** + * ieee80211_get_tid - get qos TID + * @hdr: the frame + */ +static inline u8 ieee80211_get_tid(struct ieee80211_hdr *hdr) +{ + u8 *qc = ieee80211_get_qos_ctl(hdr); + + return qc[0] & IEEE80211_QOS_CTL_TID_MASK; +} + +/** * ieee80211_get_SA - get pointer to SA * @hdr: the frame * diff --git a/include/linux/kconfig.h b/include/linux/kconfig.h index fec5076eda91..dcde9471897d 100644 --- a/include/linux/kconfig.h +++ b/include/linux/kconfig.h @@ -4,6 +4,12 @@ #include <generated/autoconf.h> +#ifdef CONFIG_CPU_BIG_ENDIAN +#define __BIG_ENDIAN 4321 +#else +#define __LITTLE_ENDIAN 1234 +#endif + #define __ARG_PLACEHOLDER_1 0, #define __take_second_arg(__ignored, val, ...) val @@ -64,4 +70,7 @@ */ #define IS_ENABLED(option) __or(IS_BUILTIN(option), IS_MODULE(option)) +/* Make sure we always have all types and struct attributes defined. */ +#include <linux/compiler_types.h> + #endif /* __LINUX_KCONFIG_H */ diff --git a/include/linux/kcore.h b/include/linux/kcore.h index 7ff25a808fef..80db19d3a505 100644 --- a/include/linux/kcore.h +++ b/include/linux/kcore.h @@ -10,6 +10,7 @@ enum kcore_type { KCORE_VMALLOC, KCORE_RAM, KCORE_VMEMMAP, + KCORE_USER, KCORE_OTHER, }; diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 882046863581..c46016bb25eb 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -523,9 +523,11 @@ static inline void __mod_memcg_state(struct mem_cgroup *memcg, static inline void mod_memcg_state(struct mem_cgroup *memcg, int idx, int val) { - preempt_disable(); + unsigned long flags; + + local_irq_save(flags); __mod_memcg_state(memcg, idx, val); - preempt_enable(); + local_irq_restore(flags); } /** @@ -606,9 +608,11 @@ static inline void __mod_lruvec_state(struct lruvec *lruvec, static inline void mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { - preempt_disable(); + unsigned long flags; + + local_irq_save(flags); __mod_lruvec_state(lruvec, idx, val); - preempt_enable(); + local_irq_restore(flags); } static inline void __mod_lruvec_page_state(struct page *page, @@ -630,9 +634,11 @@ static inline void __mod_lruvec_page_state(struct page *page, static inline void mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { - preempt_disable(); + unsigned long flags; + + local_irq_save(flags); __mod_lruvec_page_state(page, idx, val); - preempt_enable(); + local_irq_restore(flags); } unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, @@ -659,9 +665,11 @@ static inline void __count_memcg_events(struct mem_cgroup *memcg, static inline void count_memcg_events(struct mem_cgroup *memcg, int idx, unsigned long count) { - preempt_disable(); + unsigned long flags; + + local_irq_save(flags); __count_memcg_events(memcg, idx, count); - preempt_enable(); + local_irq_restore(flags); } /* idx can be of type enum memcg_event_item or vm_event_item */ diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index c30b32e3c862..10191c28fc04 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -127,10 +127,4 @@ static __always_inline enum lru_list page_lru(struct page *page) #define lru_to_page(head) (list_entry((head)->prev, struct page, lru)) -#ifdef arch_unmap_kpfn -extern void arch_unmap_kpfn(unsigned long pfn); -#else -static __always_inline void arch_unmap_kpfn(unsigned long pfn) { } -#endif - #endif diff --git a/include/linux/net.h b/include/linux/net.h index 91216b16feb7..000d1aada74f 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -146,7 +146,7 @@ struct proto_ops { struct socket *newsock, int flags, bool kern); int (*getname) (struct socket *sock, struct sockaddr *addr, - int *sockaddr_len, int peer); + int peer); __poll_t (*poll) (struct file *file, struct socket *sock, struct poll_table_struct *wait); int (*ioctl) (struct socket *sock, unsigned int cmd, @@ -294,10 +294,8 @@ int kernel_listen(struct socket *sock, int backlog); int kernel_accept(struct socket *sock, struct socket **newsock, int flags); int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen, int flags); -int kernel_getsockname(struct socket *sock, struct sockaddr *addr, - int *addrlen); -int kernel_getpeername(struct socket *sock, struct sockaddr *addr, - int *addrlen); +int kernel_getsockname(struct socket *sock, struct sockaddr *addr); +int kernel_getpeername(struct socket *sock, struct sockaddr *addr); int kernel_getsockopt(struct socket *sock, int level, int optname, char *optval, int *optlen); int kernel_setsockopt(struct socket *sock, int level, int optname, char *optval, diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5eef6c8e2741..dbe6344b727a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1798,11 +1798,17 @@ struct net_device { #if IS_ENABLED(CONFIG_TIPC) struct tipc_bearer __rcu *tipc_ptr; #endif +#if IS_ENABLED(CONFIG_IRDA) || IS_ENABLED(CONFIG_ATALK) void *atalk_ptr; +#endif struct in_device __rcu *ip_ptr; +#if IS_ENABLED(CONFIG_DECNET) struct dn_dev __rcu *dn_ptr; +#endif struct inet6_dev __rcu *ip6_ptr; +#if IS_ENABLED(CONFIG_AX25) void *ax25_ptr; +#endif struct wireless_dev *ieee80211_ptr; struct wpan_dev *ieee802154_ptr; #if IS_ENABLED(CONFIG_MPLS_ROUTING) diff --git a/include/linux/nospec.h b/include/linux/nospec.h index b99bced39ac2..fbc98e2c8228 100644 --- a/include/linux/nospec.h +++ b/include/linux/nospec.h @@ -20,20 +20,6 @@ static inline unsigned long array_index_mask_nospec(unsigned long index, unsigned long size) { /* - * Warn developers about inappropriate array_index_nospec() usage. - * - * Even if the CPU speculates past the WARN_ONCE branch, the - * sign bit of @index is taken into account when generating the - * mask. - * - * This warning is compiled out when the compiler can infer that - * @index and @size are less than LONG_MAX. - */ - if (WARN_ONCE(index > LONG_MAX || size > LONG_MAX, - "array_index_nospec() limited to range of [0, LONG_MAX]\n")) - return 0; - - /* * Always calculate and emit the mask even if the compiler * thinks the mask is not needed. The compiler does not take * into account the value of @index under speculation. @@ -44,6 +30,26 @@ static inline unsigned long array_index_mask_nospec(unsigned long index, #endif /* + * Warn developers about inappropriate array_index_nospec() usage. + * + * Even if the CPU speculates past the WARN_ONCE branch, the + * sign bit of @index is taken into account when generating the + * mask. + * + * This warning is compiled out when the compiler can infer that + * @index and @size are less than LONG_MAX. + */ +#define array_index_mask_nospec_check(index, size) \ +({ \ + if (WARN_ONCE(index > LONG_MAX || size > LONG_MAX, \ + "array_index_nospec() limited to range of [0, LONG_MAX]\n")) \ + _mask = 0; \ + else \ + _mask = array_index_mask_nospec(index, size); \ + _mask; \ +}) + +/* * array_index_nospec - sanitize an array index after a bounds check * * For a code sequence like: @@ -61,7 +67,7 @@ static inline unsigned long array_index_mask_nospec(unsigned long index, ({ \ typeof(index) _i = (index); \ typeof(size) _s = (size); \ - unsigned long _mask = array_index_mask_nospec(_i, _s); \ + unsigned long _mask = array_index_mask_nospec_check(_i, _s); \ \ BUILD_BUG_ON(sizeof(_i) > sizeof(long)); \ BUILD_BUG_ON(sizeof(_s) > sizeof(long)); \ diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index af0f44effd44..40036a57d072 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -14,26 +14,10 @@ #include <linux/interrupt.h> #include <linux/perf_event.h> +#include <linux/platform_device.h> #include <linux/sysfs.h> #include <asm/cputype.h> -/* - * struct arm_pmu_platdata - ARM PMU platform data - * - * @handle_irq: an optional handler which will be called from the - * interrupt and passed the address of the low level handler, - * and can be used to implement any platform specific handling - * before or after calling it. - * - * @irq_flags: if non-zero, these flags will be passed to request_irq - * when requesting interrupts for this PMU device. - */ -struct arm_pmu_platdata { - irqreturn_t (*handle_irq)(int irq, void *dev, - irq_handler_t pmu_handler); - unsigned long irq_flags; -}; - #ifdef CONFIG_ARM_PMU /* @@ -92,7 +76,6 @@ enum armpmu_attr_groups { struct arm_pmu { struct pmu pmu; - cpumask_t active_irqs; cpumask_t supported_cpus; char *name; irqreturn_t (*handle_irq)(int irq_num, void *dev); @@ -174,12 +157,11 @@ static inline int arm_pmu_acpi_probe(armpmu_init_fn init_fn) { return 0; } /* Internal functions only for core arm_pmu code */ struct arm_pmu *armpmu_alloc(void); +struct arm_pmu *armpmu_alloc_atomic(void); void armpmu_free(struct arm_pmu *pmu); int armpmu_register(struct arm_pmu *pmu); -int armpmu_request_irqs(struct arm_pmu *armpmu); -void armpmu_free_irqs(struct arm_pmu *armpmu); -int armpmu_request_irq(struct arm_pmu *armpmu, int cpu); -void armpmu_free_irq(struct arm_pmu *armpmu, int cpu); +int armpmu_request_irq(int irq, int cpu); +void armpmu_free_irq(int irq, int cpu); #define ARMV8_PMU_PDEV_NAME "armv8-pmu" diff --git a/include/linux/property.h b/include/linux/property.h index 769d372c1edf..2eea4b310fc2 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -283,7 +283,7 @@ bool device_dma_supported(struct device *dev); enum dev_dma_attr device_get_dma_attr(struct device *dev); -void *device_get_match_data(struct device *dev); +const void *device_get_match_data(struct device *dev); int device_get_phy_mode(struct device *dev); diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h index a079656b614c..059242030631 100644 --- a/include/linux/ptp_classify.h +++ b/include/linux/ptp_classify.h @@ -75,5 +75,9 @@ void __init ptp_classifier_init(void); static inline void ptp_classifier_init(void) { } +static inline unsigned int ptp_classify_raw(struct sk_buff *skb) +{ + return PTP_CLASS_NONE; +} #endif #endif /* _PTP_CLASSIFY_H_ */ diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h index b884b7794187..6894976b54e3 100644 --- a/include/linux/ptr_ring.h +++ b/include/linux/ptr_ring.h @@ -296,13 +296,14 @@ static inline void *__ptr_ring_consume(struct ptr_ring *r) { void *ptr; + /* The READ_ONCE in __ptr_ring_peek guarantees that anyone + * accessing data through the pointer is up to date. Pairs + * with smp_wmb in __ptr_ring_produce. + */ ptr = __ptr_ring_peek(r); if (ptr) __ptr_ring_discard_one(r); - /* Make sure anyone accessing data through the pointer is up to date. */ - /* Pairs with smp_wmb in __ptr_ring_produce. */ - smp_read_barrier_depends(); return ptr; } @@ -469,7 +470,7 @@ static inline int ptr_ring_consume_batched_bh(struct ptr_ring *r, */ static inline void **__ptr_ring_init_queue_alloc(unsigned int size, gfp_t gfp) { - if (size * sizeof(void *) > KMALLOC_MAX_SIZE) + if (size > KMALLOC_MAX_SIZE / sizeof(void *)) return NULL; return kvmalloc_array(size, sizeof(void *), gfp | __GFP_ZERO); } diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 1fdcde96eb65..3573b4bf2fdf 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -35,7 +35,7 @@ extern int rtnl_trylock(void); extern int rtnl_is_locked(void); extern wait_queue_head_t netdev_unregistering_wq; -extern struct mutex net_mutex; +extern struct rw_semaphore net_sem; #ifdef CONFIG_PROVE_LOCKING extern bool lockdep_rtnl_is_held(void); diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 1149533aa2fa..9806184bb3d5 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -36,7 +36,18 @@ static inline void mmgrab(struct mm_struct *mm) atomic_inc(&mm->mm_count); } -extern void mmdrop(struct mm_struct *mm); +extern void __mmdrop(struct mm_struct *mm); + +static inline void mmdrop(struct mm_struct *mm) +{ + /* + * The implicit full barrier implied by atomic_dec_and_test() is + * required by the membarrier system call before returning to + * user-space, after storing to rq->curr. + */ + if (unlikely(atomic_dec_and_test(&mm->mm_count))) + __mmdrop(mm); +} /** * mmget() - Pin the address space associated with a &struct mm_struct. diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h index 0dcf4e480ef7..96fe289c4c6e 100644 --- a/include/linux/sched/user.h +++ b/include/linux/sched/user.h @@ -4,6 +4,7 @@ #include <linux/uidgid.h> #include <linux/atomic.h> +#include <linux/ratelimit.h> struct key; @@ -41,6 +42,9 @@ struct user_struct { defined(CONFIG_NET) atomic_long_t locked_vm; #endif + + /* Miscellaneous per-user rate limit */ + struct ratelimit_state ratelimit; }; extern int uids_sysfs_init(void); diff --git a/include/linux/semaphore.h b/include/linux/semaphore.h index dc368b8ce215..11c86fbfeb98 100644 --- a/include/linux/semaphore.h +++ b/include/linux/semaphore.h @@ -4,7 +4,7 @@ * * Distributed under the terms of the GNU GPL, version 2 * - * Please see kernel/semaphore.c for documentation of these functions + * Please see kernel/locking/semaphore.c for documentation of these functions */ #ifndef __LINUX_SEMAPHORE_H #define __LINUX_SEMAPHORE_H diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5ebc0f869720..9bc1750ca3d3 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -466,6 +466,9 @@ struct ubuf_info { #define skb_uarg(SKB) ((struct ubuf_info *)(skb_shinfo(SKB)->destructor_arg)) +int mm_account_pinned_pages(struct mmpin *mmp, size_t size); +void mm_unaccount_pinned_pages(struct mmpin *mmp); + struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size); struct ubuf_info *sock_zerocopy_realloc(struct sock *sk, size_t size, struct ubuf_info *uarg); @@ -3646,7 +3649,7 @@ static inline bool __skb_checksum_validate_needed(struct sk_buff *skb, return true; } -/* For small packets <= CHECKSUM_BREAK peform checksum complete directly +/* For small packets <= CHECKSUM_BREAK perform checksum complete directly * in checksum_init. */ #define CHECKSUM_BREAK 76 diff --git a/include/linux/socket.h b/include/linux/socket.h index 9286a5a8c60c..1ce1f768a58c 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -353,4 +353,6 @@ extern int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen unsigned int flags, struct timespec *timeout); extern int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, unsigned int flags); + +extern struct ns_common *get_net_ns(struct ns_common *ns); #endif /* _LINUX_SOCKET_H */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 7b6a59f722a3..a1a3f4ed94ce 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -337,8 +337,6 @@ extern void deactivate_file_page(struct page *page); extern void mark_page_lazyfree(struct page *page); extern void swap_setup(void); -extern void add_page_to_unevictable_list(struct page *page); - extern void lru_cache_add_active_or_unevictable(struct page *page, struct vm_area_struct *vma); diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 4a54ef96aff5..bc0cda180c8b 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -465,6 +465,7 @@ extern bool cancel_delayed_work_sync(struct delayed_work *dwork); extern void workqueue_set_max_active(struct workqueue_struct *wq, int max_active); +extern struct work_struct *current_work(void); extern bool current_is_workqueue_rescuer(void); extern bool workqueue_congested(int cpu, struct workqueue_struct *wq); extern unsigned int work_busy(struct work_struct *work); diff --git a/include/net/Space.h b/include/net/Space.h index 27fb5c937c4f..336da258885a 100644 --- a/include/net/Space.h +++ b/include/net/Space.h @@ -20,7 +20,6 @@ struct net_device *cs89x0_probe(int unit); struct net_device *mvme147lance_probe(int unit); struct net_device *tc515_probe(int unit); struct net_device *lance_probe(int unit); -struct net_device *mac8390_probe(int unit); struct net_device *mac89x0_probe(int unit); struct net_device *cops_probe(int unit); struct net_device *ltpc_probe(void); diff --git a/include/net/act_api.h b/include/net/act_api.h index 6ed9692f20bd..9c2f22695025 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -87,12 +87,15 @@ struct tc_action_ops { struct tcf_result *); int (*dump)(struct sk_buff *, struct tc_action *, int, int); void (*cleanup)(struct tc_action *); - int (*lookup)(struct net *, struct tc_action **, u32); + int (*lookup)(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack); int (*init)(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **act, int ovr, - int bind); + int bind, struct netlink_ext_ack *extack); int (*walk)(struct net *, struct sk_buff *, - struct netlink_callback *, int, const struct tc_action_ops *); + struct netlink_callback *, int, + const struct tc_action_ops *, + struct netlink_ext_ack *); void (*stats_update)(struct tc_action *, u64, u32, u64); struct net_device *(*get_dev)(const struct tc_action *a); }; @@ -137,7 +140,8 @@ static inline void tc_action_net_exit(struct list_head *net_list, int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops); + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack); int tcf_idr_search(struct tc_action_net *tn, struct tc_action **a, u32 index); bool tcf_idr_check(struct tc_action_net *tn, u32 index, struct tc_action **a, int bind); @@ -162,10 +166,11 @@ int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions, int nr_actions, struct tcf_result *res); int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, char *name, int ovr, int bind, - struct list_head *actions); + struct list_head *actions, struct netlink_ext_ack *extack); struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, - char *name, int ovr, int bind); + char *name, int ovr, int bind, + struct netlink_ext_ack *extack); int tcf_action_dump(struct sk_buff *skb, struct list_head *, int, int); int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int); int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int); diff --git a/include/net/ax25.h b/include/net/ax25.h index 76fb39c272a7..c91bc87931c7 100644 --- a/include/net/ax25.h +++ b/include/net/ax25.h @@ -318,10 +318,12 @@ void ax25_digi_invert(const ax25_digi *, ax25_digi *); extern ax25_dev *ax25_dev_list; extern spinlock_t ax25_dev_lock; +#if IS_ENABLED(CONFIG_AX25) static inline ax25_dev *ax25_dev_ax25dev(struct net_device *dev) { return dev->ax25_ptr; } +#endif ax25_dev *ax25_addr_ax25dev(ax25_address *); void ax25_dev_device_up(struct net_device *); diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 81174f9b8d14..56e905cd4b07 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1147,6 +1147,7 @@ struct cfg80211_tid_stats { * @rx_duration: aggregate PPDU duration(usecs) for all the frames from a peer * @pertid: per-TID statistics, see &struct cfg80211_tid_stats, using the last * (IEEE80211_NUM_TIDS) index for MSDUs not encapsulated in QoS-MPDUs. + * @ack_signal: signal strength (in dBm) of the last ACK frame. */ struct station_info { u64 filled; @@ -1191,6 +1192,7 @@ struct station_info { u64 rx_duration; u8 rx_beacon_signal_avg; struct cfg80211_tid_stats pertid[IEEE80211_NUM_TIDS + 1]; + s8 ack_signal; }; #if IS_ENABLED(CONFIG_CFG80211) @@ -1905,11 +1907,16 @@ struct cfg80211_auth_request { * @ASSOC_REQ_DISABLE_HT: Disable HT (802.11n) * @ASSOC_REQ_DISABLE_VHT: Disable VHT * @ASSOC_REQ_USE_RRM: Declare RRM capability in this association + * @CONNECT_REQ_EXTERNAL_AUTH_SUPPORT: User space indicates external + * authentication capability. Drivers can offload authentication to + * userspace if this flag is set. Only applicable for cfg80211_connect() + * request (connect callback). */ enum cfg80211_assoc_req_flags { - ASSOC_REQ_DISABLE_HT = BIT(0), - ASSOC_REQ_DISABLE_VHT = BIT(1), - ASSOC_REQ_USE_RRM = BIT(2), + ASSOC_REQ_DISABLE_HT = BIT(0), + ASSOC_REQ_DISABLE_VHT = BIT(1), + ASSOC_REQ_USE_RRM = BIT(2), + CONNECT_REQ_EXTERNAL_AUTH_SUPPORT = BIT(3), }; /** @@ -2601,6 +2608,33 @@ struct cfg80211_pmk_conf { }; /** + * struct cfg80211_external_auth_params - Trigger External authentication. + * + * Commonly used across the external auth request and event interfaces. + * + * @action: action type / trigger for external authentication. Only significant + * for the authentication request event interface (driver to user space). + * @bssid: BSSID of the peer with which the authentication has + * to happen. Used by both the authentication request event and + * authentication response command interface. + * @ssid: SSID of the AP. Used by both the authentication request event and + * authentication response command interface. + * @key_mgmt_suite: AKM suite of the respective authentication. Used by the + * authentication request event interface. + * @status: status code, %WLAN_STATUS_SUCCESS for successful authentication, + * use %WLAN_STATUS_UNSPECIFIED_FAILURE if user space cannot give you + * the real status code for failures. Used only for the authentication + * response command interface (user space to driver). + */ +struct cfg80211_external_auth_params { + enum nl80211_external_auth_action action; + u8 bssid[ETH_ALEN] __aligned(2); + struct cfg80211_ssid ssid; + unsigned int key_mgmt_suite; + u16 status; +}; + +/** * struct cfg80211_ops - backend description for wireless configuration * * This struct is registered by fullmac card drivers and/or wireless stacks @@ -2923,6 +2957,9 @@ struct cfg80211_pmk_conf { * (invoked with the wireless_dev mutex held) * @del_pmk: delete the previously configured PMK for the given authenticator. * (invoked with the wireless_dev mutex held) + * + * @external_auth: indicates result of offloaded authentication processing from + * user space */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow); @@ -3216,6 +3253,8 @@ struct cfg80211_ops { const struct cfg80211_pmk_conf *conf); int (*del_pmk)(struct wiphy *wiphy, struct net_device *dev, const u8 *aa); + int (*external_auth)(struct wiphy *wiphy, struct net_device *dev, + struct cfg80211_external_auth_params *params); }; /* @@ -3517,6 +3556,35 @@ enum wiphy_vendor_command_flags { }; /** + * enum wiphy_opmode_flag - Station's ht/vht operation mode information flags + * + * @STA_OPMODE_MAX_BW_CHANGED: Max Bandwidth changed + * @STA_OPMODE_SMPS_MODE_CHANGED: SMPS mode changed + * @STA_OPMODE_N_SS_CHANGED: max N_SS (number of spatial streams) changed + * + */ +enum wiphy_opmode_flag { + STA_OPMODE_MAX_BW_CHANGED = BIT(0), + STA_OPMODE_SMPS_MODE_CHANGED = BIT(1), + STA_OPMODE_N_SS_CHANGED = BIT(2), +}; + +/** + * struct sta_opmode_info - Station's ht/vht operation mode information + * @changed: contains value from &enum wiphy_opmode_flag + * @smps_mode: New SMPS mode of a station + * @bw: new max bandwidth value of a station + * @rx_nss: new rx_nss value of a station + */ + +struct sta_opmode_info { + u32 changed; + u8 smps_mode; + u8 bw; + u8 rx_nss; +}; + +/** * struct wiphy_vendor_command - vendor command definition * @info: vendor command identifying information, as used in nl80211 * @flags: flags, see &enum wiphy_vendor_command_flags @@ -5685,6 +5753,20 @@ void cfg80211_radar_event(struct wiphy *wiphy, struct cfg80211_chan_def *chandef, gfp_t gfp); /** + * cfg80211_sta_opmode_change_notify - STA's ht/vht operation mode change event + * @dev: network device + * @mac: MAC address of a station which opmode got modified + * @sta_opmode: station's current opmode value + * @gfp: context flags + * + * Driver should call this function when station's opmode modified via action + * frame. + */ +void cfg80211_sta_opmode_change_notify(struct net_device *dev, const u8 *mac, + struct sta_opmode_info *sta_opmode, + gfp_t gfp); + +/** * cfg80211_cac_event - Channel availability check (CAC) event * @netdev: network device * @chandef: chandef for the current channel @@ -5758,10 +5840,13 @@ bool cfg80211_rx_unexpected_4addr_frame(struct net_device *dev, * @addr: the address of the peer * @cookie: the cookie filled in @probe_client previously * @acked: indicates whether probe was acked or not + * @ack_signal: signal strength (in dBm) of the ACK frame. + * @is_valid_ack_signal: indicates the ack_signal is valid or not. * @gfp: allocation flags */ void cfg80211_probe_status(struct net_device *dev, const u8 *addr, - u64 cookie, bool acked, gfp_t gfp); + u64 cookie, bool acked, s32 ack_signal, + bool is_valid_ack_signal, gfp_t gfp); /** * cfg80211_report_obss_beacon - report beacon from other APs @@ -6202,6 +6287,17 @@ void cfg80211_nan_func_terminated(struct wireless_dev *wdev, /* ethtool helper */ void cfg80211_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info); +/** + * cfg80211_external_auth_request - userspace request for authentication + * @netdev: network device + * @params: External authentication parameters + * @gfp: allocation flags + * Returns: 0 on success, < 0 on error + */ +int cfg80211_external_auth_request(struct net_device *netdev, + struct cfg80211_external_auth_params *params, + gfp_t gfp); + /* Logging, debugging and troubleshooting/diagnostic helpers. */ /* wiphy_printk helpers, similar to dev_printk */ diff --git a/include/net/devlink.h b/include/net/devlink.h index 6545b03e97f7..8d1c3f276dea 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -234,13 +234,9 @@ struct devlink_dpipe_headers { /** * struct devlink_resource_ops - resource ops * @occ_get: get the occupied size - * @size_validate: validate the size of the resource before update, reload - * is needed for changes to take place */ struct devlink_resource_ops { u64 (*occ_get)(struct devlink *devlink); - int (*size_validate)(struct devlink *devlink, u64 size, - struct netlink_ext_ack *extack); }; /** diff --git a/include/net/dsa.h b/include/net/dsa.h index 6cb602dd970c..0ad17b63684d 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -19,6 +19,7 @@ #include <linux/workqueue.h> #include <linux/of.h> #include <linux/ethtool.h> +#include <linux/net_tstamp.h> #include <net/devlink.h> #include <net/switchdev.h> @@ -101,6 +102,7 @@ struct dsa_platform_data { }; struct packet_type; +struct dsa_switch; struct dsa_device_ops { struct sk_buff *(*xmit)(struct sk_buff *skb, struct net_device *dev); @@ -368,6 +370,12 @@ struct dsa_switch_ops { struct ethtool_wolinfo *w); /* + * ethtool timestamp info + */ + int (*get_ts_info)(struct dsa_switch *ds, int port, + struct ethtool_ts_info *ts); + + /* * Suspend and resume */ int (*suspend)(struct dsa_switch *ds); @@ -469,6 +477,18 @@ struct dsa_switch_ops { int port, struct net_device *br); void (*crosschip_bridge_leave)(struct dsa_switch *ds, int sw_index, int port, struct net_device *br); + + /* + * PTP functionality + */ + int (*port_hwtstamp_get)(struct dsa_switch *ds, int port, + struct ifreq *ifr); + int (*port_hwtstamp_set)(struct dsa_switch *ds, int port, + struct ifreq *ifr); + bool (*port_txtstamp)(struct dsa_switch *ds, int port, + struct sk_buff *clone, unsigned int type); + bool (*port_rxtstamp)(struct dsa_switch *ds, int port, + struct sk_buff *skb, unsigned int type); }; struct dsa_switch_driver { diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index 648caf90ec07..b3d216249240 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -26,7 +26,8 @@ struct fib_rule { u32 table; u8 action; u8 l3mdev; - /* 2 bytes hole, try to use */ + u8 proto; + /* 1 byte hole, try to use */ u32 target; __be64 tun_id; struct fib_rule __rcu *ctarget; @@ -108,7 +109,8 @@ struct fib_rule_notifier_info { [FRA_SUPPRESS_IFGROUP] = { .type = NLA_U32 }, \ [FRA_GOTO] = { .type = NLA_U32 }, \ [FRA_L3MDEV] = { .type = NLA_U8 }, \ - [FRA_UID_RANGE] = { .len = sizeof(struct fib_rule_uid_range) } + [FRA_UID_RANGE] = { .len = sizeof(struct fib_rule_uid_range) }, \ + [FRA_PROTOCOL] = { .type = NLA_U8 } static inline void fib_rule_get(struct fib_rule *rule) { diff --git a/include/net/gre.h b/include/net/gre.h index f90585decbce..797142eee9cd 100644 --- a/include/net/gre.h +++ b/include/net/gre.h @@ -37,6 +37,9 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name, int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, bool *csum_err, __be16 proto, int nhs); +bool is_gretap_dev(const struct net_device *dev); +bool is_ip6gretap_dev(const struct net_device *dev); + static inline int gre_calc_hlen(__be16 o_flags) { int addend = 4; diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h index d91f9e7f4d71..960236fb1681 100644 --- a/include/net/ieee80211_radiotap.h +++ b/include/net/ieee80211_radiotap.h @@ -149,6 +149,8 @@ enum ieee80211_radiotap_ampdu_flags { IEEE80211_RADIOTAP_AMPDU_IS_LAST = 0x0008, IEEE80211_RADIOTAP_AMPDU_DELIM_CRC_ERR = 0x0010, IEEE80211_RADIOTAP_AMPDU_DELIM_CRC_KNOWN = 0x0020, + IEEE80211_RADIOTAP_AMPDU_EOF = 0x0040, + IEEE80211_RADIOTAP_AMPDU_EOF_KNOWN = 0x0080, }; /* for IEEE80211_RADIOTAP_VHT */ diff --git a/include/net/inet_common.h b/include/net/inet_common.h index 5a54c9570977..500f81375200 100644 --- a/include/net/inet_common.h +++ b/include/net/inet_common.h @@ -32,7 +32,7 @@ int inet_shutdown(struct socket *sock, int how); int inet_listen(struct socket *sock, int backlog); void inet_sock_destruct(struct sock *sk); int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); -int inet_getname(struct socket *sock, struct sockaddr *uaddr, int *uaddr_len, +int inet_getname(struct socket *sock, struct sockaddr *uaddr, int peer); int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); int inet_ctl_sock_create(struct sock **sk, unsigned short family, diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 1f16773cfd76..cbe5addb9293 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -254,6 +254,22 @@ static inline __be32 tunnel_id_to_key32(__be64 tun_id) #ifdef CONFIG_INET +static inline void ip_tunnel_init_flow(struct flowi4 *fl4, + int proto, + __be32 daddr, __be32 saddr, + __be32 key, __u8 tos, int oif, + __u32 mark) +{ + memset(fl4, 0, sizeof(*fl4)); + fl4->flowi4_oif = oif; + fl4->daddr = daddr; + fl4->saddr = saddr; + fl4->flowi4_tos = tos; + fl4->flowi4_proto = proto; + fl4->fl4_gre_key = key; + fl4->flowi4_mark = mark; +} + int ip_tunnel_init(struct net_device *dev); void ip_tunnel_uninit(struct net_device *dev); void ip_tunnel_dellink(struct net_device *dev, struct list_head *head); diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 8606c9113d3f..7a98cd583c73 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -1056,7 +1056,7 @@ void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu); int inet6_release(struct socket *sock); int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); -int inet6_getname(struct socket *sock, struct sockaddr *uaddr, int *uaddr_len, +int inet6_getname(struct socket *sock, struct sockaddr *uaddr, int peer); int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h index d747ef975cd8..33fd9ba7e0e5 100644 --- a/include/net/lwtunnel.h +++ b/include/net/lwtunnel.h @@ -127,6 +127,17 @@ int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb); int lwtunnel_input(struct sk_buff *skb); int lwtunnel_xmit(struct sk_buff *skb); +static inline void lwtunnel_set_redirect(struct dst_entry *dst) +{ + if (lwtunnel_output_redirect(dst->lwtstate)) { + dst->lwtstate->orig_output = dst->output; + dst->output = lwtunnel_output; + } + if (lwtunnel_input_redirect(dst->lwtstate)) { + dst->lwtstate->orig_input = dst->input; + dst->input = lwtunnel_input; + } +} #else static inline void lwtstate_free(struct lwtunnel_state *lws) @@ -158,6 +169,10 @@ static inline bool lwtunnel_xmit_redirect(struct lwtunnel_state *lwtstate) return false; } +static inline void lwtunnel_set_redirect(struct dst_entry *dst) +{ +} + static inline unsigned int lwtunnel_headroom(struct lwtunnel_state *lwtstate, unsigned int mtu) { diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 906e90223066..2fd59ed3be00 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -6,6 +6,7 @@ * Copyright 2007-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015 - 2017 Intel Deutschland GmbH + * Copyright (C) 2018 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -934,6 +935,7 @@ struct ieee80211_tx_info { u8 ampdu_len; u8 antenna; u16 tx_time; + bool is_valid_ack_signal; void *status_driver_data[19 / sizeof(void *)]; } status; struct { @@ -1098,6 +1100,9 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) * the first subframe. * @RX_FLAG_ICV_STRIPPED: The ICV is stripped from this frame. CRC checking must * be done in the hardware. + * @RX_FLAG_AMPDU_EOF_BIT: Value of the EOF bit in the A-MPDU delimiter for this + * frame + * @RX_FLAG_AMPDU_EOF_BIT_KNOWN: The EOF value is known */ enum mac80211_rx_flags { RX_FLAG_MMIC_ERROR = BIT(0), @@ -1124,6 +1129,8 @@ enum mac80211_rx_flags { RX_FLAG_MIC_STRIPPED = BIT(21), RX_FLAG_ALLOW_SAME_PN = BIT(22), RX_FLAG_ICV_STRIPPED = BIT(23), + RX_FLAG_AMPDU_EOF_BIT = BIT(24), + RX_FLAG_AMPDU_EOF_BIT_KNOWN = BIT(25), }; /** @@ -2063,6 +2070,14 @@ struct ieee80211_txq { * @IEEE80211_HW_SUPPORTS_TDLS_BUFFER_STA: Hardware supports buffer STA on * TDLS links. * + * @IEEE80211_HW_DEAUTH_NEED_MGD_TX_PREP: The driver requires the + * mgd_prepare_tx() callback to be called before transmission of a + * deauthentication frame in case the association was completed but no + * beacon was heard. This is required in multi-channel scenarios, where the + * virtual interface might not be given air time for the transmission of + * the frame, as it is not synced with the AP/P2P GO yet, and thus the + * deauthentication frame might not be transmitted. + * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { @@ -2106,6 +2121,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_REPORTS_LOW_ACK, IEEE80211_HW_SUPPORTS_TX_FRAG, IEEE80211_HW_SUPPORTS_TDLS_BUFFER_STA, + IEEE80211_HW_DEAUTH_NEED_MGD_TX_PREP, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS @@ -3350,6 +3366,9 @@ enum ieee80211_reconfig_type { * management frame prior to having successfully associated to allow the * driver to give it channel time for the transmission, to get a response * and to be able to synchronize with the GO. + * For drivers that set %IEEE80211_HW_DEAUTH_NEED_MGD_TX_PREP, mac80211 + * would also call this function before transmitting a deauthentication + * frame in case that no beacon was heard from the AP/P2P GO. * The callback will be called before each transmission and upon return * mac80211 will transmit the frame right away. * The callback is optional and can (should!) sleep. @@ -4149,7 +4168,7 @@ void ieee80211_sta_uapsd_trigger(struct ieee80211_sta *sta, u8 tid); * The TX headroom reserved by mac80211 for its own tx_status functions. * This is enough for the radiotap header. */ -#define IEEE80211_TX_STATUS_HEADROOM 14 +#define IEEE80211_TX_STATUS_HEADROOM ALIGN(14, 4) /** * ieee80211_sta_set_buffered - inform mac80211 about driver-buffered frames diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index f306b2aa15a4..d4417495773a 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -59,8 +59,12 @@ struct net { atomic64_t cookie_gen; struct list_head list; /* list of network namespaces */ - struct list_head cleanup_list; /* namespaces on death row */ - struct list_head exit_list; /* Use only net_mutex */ + struct list_head exit_list; /* To linked to call pernet exit + * methods on dead net (net_sem + * read locked), or to unregister + * pernet ops (net_sem wr locked). + */ + struct llist_node cleanup_list; /* namespaces on death row */ struct user_namespace *user_ns; /* Owning user namespace */ struct ucounts *ucounts; @@ -89,7 +93,7 @@ struct net { /* core fib_rules */ struct list_head rules_ops; - struct list_head fib_notifier_ops; /* protected by net_mutex */ + struct list_head fib_notifier_ops; /* protected by net_sem */ struct net_device *loopback_dev; /* The loopback */ struct netns_core core; @@ -313,6 +317,12 @@ struct pernet_operations { void (*exit_batch)(struct list_head *net_exit_list); unsigned int *id; size_t size; + /* + * Indicates above methods are allowed to be executed in parallel + * with methods of any other pernet_operations, i.e. they are not + * need write locked net_sem. + */ + bool async; }; /* diff --git a/include/net/regulatory.h b/include/net/regulatory.h index ebc5a2ed8631..f83cacce3308 100644 --- a/include/net/regulatory.h +++ b/include/net/regulatory.h @@ -78,7 +78,7 @@ struct regulatory_request { int wiphy_idx; enum nl80211_reg_initiator initiator; enum nl80211_user_reg_hint_type user_reg_hint_type; - char alpha2[2]; + char alpha2[3]; enum nl80211_dfs_regions dfs_region; bool intersect; bool processed; diff --git a/include/net/route.h b/include/net/route.h index 1eb9ce470e25..158833ea7988 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -65,8 +65,6 @@ struct rtable { /* Miscellaneous cached information */ u32 rt_pmtu; - u32 rt_table_id; - struct list_head rt_uncached; struct uncached_list *rt_uncached_list; }; diff --git a/include/net/sock.h b/include/net/sock.h index 169c92afcafa..b9624581d639 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -417,6 +417,7 @@ struct sock { struct page_frag sk_frag; netdev_features_t sk_route_caps; netdev_features_t sk_route_nocaps; + netdev_features_t sk_route_forced_caps; int sk_gso_type; unsigned int sk_gso_max_size; gfp_t sk_allocation; @@ -1584,7 +1585,7 @@ int sock_no_bind(struct socket *, struct sockaddr *, int); int sock_no_connect(struct socket *, struct sockaddr *, int, int); int sock_no_socketpair(struct socket *, struct socket *); int sock_no_accept(struct socket *, struct socket *, int, bool); -int sock_no_getname(struct socket *, struct sockaddr *, int *, int); +int sock_no_getname(struct socket *, struct sockaddr *, int); __poll_t sock_no_poll(struct file *, struct socket *, struct poll_table_struct *); int sock_no_ioctl(struct socket *, unsigned int, unsigned long); @@ -1862,15 +1863,6 @@ static inline void sk_nocaps_add(struct sock *sk, netdev_features_t flags) sk->sk_route_caps &= ~flags; } -static inline bool sk_check_csum_caps(struct sock *sk) -{ - return (sk->sk_route_caps & NETIF_F_HW_CSUM) || - (sk->sk_family == PF_INET && - (sk->sk_route_caps & NETIF_F_IP_CSUM)) || - (sk->sk_family == PF_INET6 && - (sk->sk_route_caps & NETIF_F_IPV6_CSUM)); -} - static inline int skb_do_copy_data_nocache(struct sock *sk, struct sk_buff *skb, struct iov_iter *from, char *to, int copy, int offset) diff --git a/include/net/tcp.h b/include/net/tcp.h index e3fc667f9ac2..92b06c6e7732 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -374,7 +374,8 @@ enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, const struct tcphdr *th); struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, - struct request_sock *req, bool fastopen); + struct request_sock *req, bool fastopen, + bool *lost_race); int tcp_child_process(struct sock *parent, struct sock *child, struct sk_buff *skb); void tcp_enter_loss(struct sock *sk); diff --git a/include/net/tcp_states.h b/include/net/tcp_states.h index 50e78a74d0df..2875e169d744 100644 --- a/include/net/tcp_states.h +++ b/include/net/tcp_states.h @@ -32,21 +32,21 @@ enum { #define TCP_STATE_MASK 0xF -#define TCP_ACTION_FIN (1 << 7) +#define TCP_ACTION_FIN (1 << TCP_CLOSE) enum { - TCPF_ESTABLISHED = (1 << 1), - TCPF_SYN_SENT = (1 << 2), - TCPF_SYN_RECV = (1 << 3), - TCPF_FIN_WAIT1 = (1 << 4), - TCPF_FIN_WAIT2 = (1 << 5), - TCPF_TIME_WAIT = (1 << 6), - TCPF_CLOSE = (1 << 7), - TCPF_CLOSE_WAIT = (1 << 8), - TCPF_LAST_ACK = (1 << 9), - TCPF_LISTEN = (1 << 10), - TCPF_CLOSING = (1 << 11), - TCPF_NEW_SYN_RECV = (1 << 12), + TCPF_ESTABLISHED = (1 << TCP_ESTABLISHED), + TCPF_SYN_SENT = (1 << TCP_SYN_SENT), + TCPF_SYN_RECV = (1 << TCP_SYN_RECV), + TCPF_FIN_WAIT1 = (1 << TCP_FIN_WAIT1), + TCPF_FIN_WAIT2 = (1 << TCP_FIN_WAIT2), + TCPF_TIME_WAIT = (1 << TCP_TIME_WAIT), + TCPF_CLOSE = (1 << TCP_CLOSE), + TCPF_CLOSE_WAIT = (1 << TCP_CLOSE_WAIT), + TCPF_LAST_ACK = (1 << TCP_LAST_ACK), + TCPF_LISTEN = (1 << TCP_LISTEN), + TCPF_CLOSING = (1 << TCP_CLOSING), + TCPF_NEW_SYN_RECV = (1 << TCP_NEW_SYN_RECV), }; #endif /* _LINUX_TCP_STATES_H */ diff --git a/include/net/udplite.h b/include/net/udplite.h index 81bdbf97319b..9185e45b997f 100644 --- a/include/net/udplite.h +++ b/include/net/udplite.h @@ -64,6 +64,7 @@ static inline int udplite_checksum_init(struct sk_buff *skb, struct udphdr *uh) UDP_SKB_CB(skb)->cscov = cscov; if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; + skb->csum_valid = 0; } return 0; diff --git a/include/rdma/restrack.h b/include/rdma/restrack.h index c2d81167c858..2cdf8dcf4bdc 100644 --- a/include/rdma/restrack.h +++ b/include/rdma/restrack.h @@ -29,10 +29,6 @@ enum rdma_restrack_type { */ RDMA_RESTRACK_QP, /** - * @RDMA_RESTRACK_XRCD: XRC domain (XRCD) - */ - RDMA_RESTRACK_XRCD, - /** * @RDMA_RESTRACK_MAX: Last entry, used for array dclarations */ RDMA_RESTRACK_MAX diff --git a/include/rdma/uverbs_ioctl.h b/include/rdma/uverbs_ioctl.h index 6da44079aa58..38287d9d23a1 100644 --- a/include/rdma/uverbs_ioctl.h +++ b/include/rdma/uverbs_ioctl.h @@ -276,10 +276,7 @@ struct uverbs_object_tree_def { */ struct uverbs_ptr_attr { - union { - u64 data; - void __user *ptr; - }; + u64 data; u16 len; /* Combination of bits from enum UVERBS_ATTR_F_XXXX */ u16 flags; @@ -351,38 +348,60 @@ static inline const struct uverbs_attr *uverbs_attr_get(const struct uverbs_attr } static inline int uverbs_copy_to(const struct uverbs_attr_bundle *attrs_bundle, - size_t idx, const void *from) + size_t idx, const void *from, size_t size) { const struct uverbs_attr *attr = uverbs_attr_get(attrs_bundle, idx); u16 flags; + size_t min_size; if (IS_ERR(attr)) return PTR_ERR(attr); + min_size = min_t(size_t, attr->ptr_attr.len, size); + if (copy_to_user(u64_to_user_ptr(attr->ptr_attr.data), from, min_size)) + return -EFAULT; + flags = attr->ptr_attr.flags | UVERBS_ATTR_F_VALID_OUTPUT; - return (!copy_to_user(attr->ptr_attr.ptr, from, attr->ptr_attr.len) && - !put_user(flags, &attr->uattr->flags)) ? 0 : -EFAULT; + if (put_user(flags, &attr->uattr->flags)) + return -EFAULT; + + return 0; } -static inline int _uverbs_copy_from(void *to, size_t to_size, +static inline bool uverbs_attr_ptr_is_inline(const struct uverbs_attr *attr) +{ + return attr->ptr_attr.len <= sizeof(attr->ptr_attr.data); +} + +static inline int _uverbs_copy_from(void *to, const struct uverbs_attr_bundle *attrs_bundle, - size_t idx) + size_t idx, + size_t size) { const struct uverbs_attr *attr = uverbs_attr_get(attrs_bundle, idx); if (IS_ERR(attr)) return PTR_ERR(attr); - if (to_size <= sizeof(((struct ib_uverbs_attr *)0)->data)) + /* + * Validation ensures attr->ptr_attr.len >= size. If the caller is + * using UVERBS_ATTR_SPEC_F_MIN_SZ then it must call copy_from with + * the right size. + */ + if (unlikely(size < attr->ptr_attr.len)) + return -EINVAL; + + if (uverbs_attr_ptr_is_inline(attr)) memcpy(to, &attr->ptr_attr.data, attr->ptr_attr.len); - else if (copy_from_user(to, attr->ptr_attr.ptr, attr->ptr_attr.len)) + else if (copy_from_user(to, u64_to_user_ptr(attr->ptr_attr.data), + attr->ptr_attr.len)) return -EFAULT; return 0; } #define uverbs_copy_from(to, attrs_bundle, idx) \ - _uverbs_copy_from(to, sizeof(*(to)), attrs_bundle, idx) + _uverbs_copy_from(to, attrs_bundle, idx, sizeof(*to)) /* ================================================= * Definitions -> Specs infrastructure diff --git a/include/sound/ac97/regs.h b/include/sound/ac97/regs.h index 4bb86d379bd5..9a4fa0c3264a 100644 --- a/include/sound/ac97/regs.h +++ b/include/sound/ac97/regs.h @@ -31,7 +31,7 @@ #define AC97_HEADPHONE 0x04 /* Headphone Volume (optional) */ #define AC97_MASTER_MONO 0x06 /* Master Volume Mono (optional) */ #define AC97_MASTER_TONE 0x08 /* Master Tone (Bass & Treble) (optional) */ -#define AC97_PC_BEEP 0x0a /* PC Beep Volume (optinal) */ +#define AC97_PC_BEEP 0x0a /* PC Beep Volume (optional) */ #define AC97_PHONE 0x0c /* Phone Volume (optional) */ #define AC97_MIC 0x0e /* MIC Volume */ #define AC97_LINE 0x10 /* Line In Volume */ diff --git a/include/trace/events/xen.h b/include/trace/events/xen.h index b8adf05c534e..7dd8f34c37df 100644 --- a/include/trace/events/xen.h +++ b/include/trace/events/xen.h @@ -368,7 +368,7 @@ TRACE_EVENT(xen_mmu_flush_tlb, TP_printk("%s", "") ); -TRACE_EVENT(xen_mmu_flush_tlb_single, +TRACE_EVENT(xen_mmu_flush_tlb_one_user, TP_PROTO(unsigned long addr), TP_ARGS(addr), TP_STRUCT__entry( diff --git a/include/uapi/linux/fib_rules.h b/include/uapi/linux/fib_rules.h index 2b642bf9b5a0..77d90ae38114 100644 --- a/include/uapi/linux/fib_rules.h +++ b/include/uapi/linux/fib_rules.h @@ -23,7 +23,7 @@ struct fib_rule_hdr { __u8 tos; __u8 table; - __u8 res1; /* reserved */ + __u8 res1; /* reserved */ __u8 res2; /* reserved */ __u8 action; @@ -58,6 +58,7 @@ enum { FRA_PAD, FRA_L3MDEV, /* iif or oif is l3mdev goto its table */ FRA_UID_RANGE, /* UID range */ + FRA_PROTOCOL, /* Originator of the rule */ __FRA_MAX }; diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index f8cb5760ea4f..2e4a6c1accaa 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -23,7 +23,6 @@ #define _UAPI_LINUX_IF_ETHER_H #include <linux/types.h> -#include <linux/libc-compat.h> /* * IEEE 802.3 Ethernet magic constants. The frame sizes omit the preamble @@ -89,6 +88,7 @@ #define ETH_P_AOE 0x88A2 /* ATA over Ethernet */ #define ETH_P_8021AD 0x88A8 /* 802.1ad Service VLAN */ #define ETH_P_802_EX1 0x88B5 /* 802.1 Local Experimental 1. */ +#define ETH_P_PREAUTH 0x88C7 /* 802.11 Preauthentication */ #define ETH_P_TIPC 0x88CA /* TIPC */ #define ETH_P_MACSEC 0x88E5 /* 802.1ae MACsec */ #define ETH_P_8021AH 0x88E7 /* 802.1ah Backbone Service Tag */ @@ -151,6 +151,11 @@ * This is an Ethernet frame header. */ +/* allow libcs like musl to deactivate this, glibc does not implement this. */ +#ifndef __UAPI_DEF_ETHHDR +#define __UAPI_DEF_ETHHDR 1 +#endif + #if __UAPI_DEF_ETHHDR struct ethhdr { unsigned char h_dest[ETH_ALEN]; /* destination eth addr */ diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 6d9447700e18..11d0c0ea2bfa 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -941,4 +941,22 @@ enum { IFLA_EVENT_BONDING_OPTIONS, /* change in bonding options */ }; +/* tun section */ + +enum { + IFLA_TUN_UNSPEC, + IFLA_TUN_OWNER, + IFLA_TUN_GROUP, + IFLA_TUN_TYPE, + IFLA_TUN_PI, + IFLA_TUN_VNET_HDR, + IFLA_TUN_PERSIST, + IFLA_TUN_MULTI_QUEUE, + IFLA_TUN_NUM_QUEUES, + IFLA_TUN_NUM_DISABLED_QUEUES, + __IFLA_TUN_MAX, +}; + +#define IFLA_TUN_MAX (__IFLA_TUN_MAX - 1) + #endif /* _UAPI_LINUX_IF_LINK_H */ diff --git a/include/uapi/linux/libc-compat.h b/include/uapi/linux/libc-compat.h index fc29efaa918c..8254c937c9f4 100644 --- a/include/uapi/linux/libc-compat.h +++ b/include/uapi/linux/libc-compat.h @@ -264,10 +264,4 @@ #endif /* __GLIBC__ */ -/* Definitions for if_ether.h */ -/* allow libcs like musl to deactivate this, glibc does not implement this. */ -#ifndef __UAPI_DEF_ETHHDR -#define __UAPI_DEF_ETHHDR 1 -#endif - #endif /* _UAPI_LIBC_COMPAT_H */ diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index c587a61c32bf..c13c84304be3 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -992,6 +992,32 @@ * * @NL80211_CMD_RELOAD_REGDB: Request that the regdb firmware file is reloaded. * + * @NL80211_CMD_EXTERNAL_AUTH: This interface is exclusively defined for host + * drivers that do not define separate commands for authentication and + * association, but rely on user space for the authentication to happen. + * This interface acts both as the event request (driver to user space) + * to trigger the authentication and command response (userspace to + * driver) to indicate the authentication status. + * + * User space uses the %NL80211_CMD_CONNECT command to the host driver to + * trigger a connection. The host driver selects a BSS and further uses + * this interface to offload only the authentication part to the user + * space. Authentication frames are passed between the driver and user + * space through the %NL80211_CMD_FRAME interface. Host driver proceeds + * further with the association after getting successful authentication + * status. User space indicates the authentication status through + * %NL80211_ATTR_STATUS_CODE attribute in %NL80211_CMD_EXTERNAL_AUTH + * command interface. + * + * Host driver reports this status on an authentication failure to the + * user space through the connect result as the user space would have + * initiated the connection through the connect request. + * + * @NL80211_CMD_STA_OPMODE_CHANGED: An event that notify station's + * ht opmode or vht opmode changes using any of &NL80211_ATTR_SMPS_MODE, + * &NL80211_ATTR_CHANNEL_WIDTH,&NL80211_ATTR_NSS attributes with its + * address(specified in &NL80211_ATTR_MAC). + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -1198,6 +1224,10 @@ enum nl80211_commands { NL80211_CMD_RELOAD_REGDB, + NL80211_CMD_EXTERNAL_AUTH, + + NL80211_CMD_STA_OPMODE_CHANGED, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -2153,6 +2183,19 @@ enum nl80211_commands { * @NL80211_ATTR_PMKR0_NAME: PMK-R0 Name for offloaded FT. * @NL80211_ATTR_PORT_AUTHORIZED: (reserved) * + * @NL80211_ATTR_EXTERNAL_AUTH_ACTION: Identify the requested external + * authentication operation (u32 attribute with an + * &enum nl80211_external_auth_action value). This is used with the + * &NL80211_CMD_EXTERNAL_AUTH request event. + * @NL80211_ATTR_EXTERNAL_AUTH_SUPPORT: Flag attribute indicating that the user + * space supports external authentication. This attribute shall be used + * only with %NL80211_CMD_CONNECT request. The driver may offload + * authentication processing to user space if this capability is indicated + * in NL80211_CMD_CONNECT requests from the user space. + * + * @NL80211_ATTR_NSS: Station's New/updated RX_NSS value notified using this + * u8 attribute. This is used with %NL80211_CMD_STA_OPMODE_CHANGED. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -2579,6 +2622,12 @@ enum nl80211_attrs { NL80211_ATTR_PMKR0_NAME, NL80211_ATTR_PORT_AUTHORIZED, + NL80211_ATTR_EXTERNAL_AUTH_ACTION, + NL80211_ATTR_EXTERNAL_AUTH_SUPPORT, + + NL80211_ATTR_NSS, + NL80211_ATTR_ACK_SIGNAL, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -2899,6 +2948,7 @@ enum nl80211_sta_bss_param { * @NL80211_STA_INFO_RX_DURATION: aggregate PPDU duration for all frames * received from the station (u64, usec) * @NL80211_STA_INFO_PAD: attribute used for padding for 64-bit alignment + * @NL80211_STA_INFO_ACK_SIGNAL: signal strength of the last ACK frame(u8, dBm) * @__NL80211_STA_INFO_AFTER_LAST: internal * @NL80211_STA_INFO_MAX: highest possible station info attribute */ @@ -2937,6 +2987,7 @@ enum nl80211_sta_info { NL80211_STA_INFO_TID_STATS, NL80211_STA_INFO_RX_DURATION, NL80211_STA_INFO_PAD, + NL80211_STA_INFO_ACK_SIGNAL, /* keep last */ __NL80211_STA_INFO_AFTER_LAST, @@ -4945,6 +4996,9 @@ enum nl80211_feature_flags { * probe request tx deferral and suppression * @NL80211_EXT_FEATURE_MFP_OPTIONAL: Driver supports the %NL80211_MFP_OPTIONAL * value in %NL80211_ATTR_USE_MFP. + * @NL80211_EXT_FEATURE_LOW_SPAN_SCAN: Driver supports low span scan. + * @NL80211_EXT_FEATURE_LOW_POWER_SCAN: Driver supports low power scan. + * @NL80211_EXT_FEATURE_HIGH_ACCURACY_SCAN: Driver supports high accuracy scan. * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. @@ -4972,6 +5026,9 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_OCE_PROBE_REQ_HIGH_TX_RATE, NL80211_EXT_FEATURE_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION, NL80211_EXT_FEATURE_MFP_OPTIONAL, + NL80211_EXT_FEATURE_LOW_SPAN_SCAN, + NL80211_EXT_FEATURE_LOW_POWER_SCAN, + NL80211_EXT_FEATURE_HIGH_ACCURACY_SCAN, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, @@ -5032,6 +5089,10 @@ enum nl80211_timeout_reason { * of NL80211_CMD_TRIGGER_SCAN and NL80211_CMD_START_SCHED_SCAN * requests. * + * NL80211_SCAN_FLAG_LOW_SPAN, NL80211_SCAN_FLAG_LOW_POWER, and + * NL80211_SCAN_FLAG_HIGH_ACCURACY flags are exclusive of each other, i.e., only + * one of them can be used in the request. + * * @NL80211_SCAN_FLAG_LOW_PRIORITY: scan request has low priority * @NL80211_SCAN_FLAG_FLUSH: flush cache before scanning * @NL80211_SCAN_FLAG_AP: force a scan even if the interface is configured @@ -5059,7 +5120,20 @@ enum nl80211_timeout_reason { * and suppression (if it has received a broadcast Probe Response frame, * Beacon frame or FILS Discovery frame from an AP that the STA considers * a suitable candidate for (re-)association - suitable in terms of - * SSID and/or RSSI + * SSID and/or RSSI. + * @NL80211_SCAN_FLAG_LOW_SPAN: Span corresponds to the total time taken to + * accomplish the scan. Thus, this flag intends the driver to perform the + * scan request with lesser span/duration. It is specific to the driver + * implementations on how this is accomplished. Scan accuracy may get + * impacted with this flag. + * @NL80211_SCAN_FLAG_LOW_POWER: This flag intends the scan attempts to consume + * optimal possible power. Drivers can resort to their specific means to + * optimize the power. Scan accuracy may get impacted with this flag. + * @NL80211_SCAN_FLAG_HIGH_ACCURACY: Accuracy here intends to the extent of scan + * results obtained. Thus HIGH_ACCURACY scan flag aims to get maximum + * possible scan results. This flag hints the driver to use the best + * possible scan configuration to improve the accuracy in scanning. + * Latency and power use may get impacted with this flag. */ enum nl80211_scan_flags { NL80211_SCAN_FLAG_LOW_PRIORITY = 1<<0, @@ -5070,6 +5144,9 @@ enum nl80211_scan_flags { NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP = 1<<5, NL80211_SCAN_FLAG_OCE_PROBE_REQ_HIGH_TX_RATE = 1<<6, NL80211_SCAN_FLAG_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION = 1<<7, + NL80211_SCAN_FLAG_LOW_SPAN = 1<<8, + NL80211_SCAN_FLAG_LOW_POWER = 1<<9, + NL80211_SCAN_FLAG_HIGH_ACCURACY = 1<<10, }; /** @@ -5469,4 +5546,15 @@ enum nl80211_nan_match_attributes { NL80211_NAN_MATCH_ATTR_MAX = NUM_NL80211_NAN_MATCH_ATTR - 1 }; +/** + * nl80211_external_auth_action - Action to perform with external + * authentication request. Used by NL80211_ATTR_EXTERNAL_AUTH_ACTION. + * @NL80211_EXTERNAL_AUTH_START: Start the authentication. + * @NL80211_EXTERNAL_AUTH_ABORT: Abort the ongoing authentication. + */ +enum nl80211_external_auth_action { + NL80211_EXTERNAL_AUTH_START, + NL80211_EXTERNAL_AUTH_ABORT, +}; + #endif /* __LINUX_NL80211_H */ diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 46c506615f4a..7cafb26df555 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -555,7 +555,8 @@ enum { #define TCF_EM_VLAN 6 #define TCF_EM_CANID 7 #define TCF_EM_IPSET 8 -#define TCF_EM_MAX 8 +#define TCF_EM_IPT 9 +#define TCF_EM_MAX 9 enum { TCF_EM_PROG_TC diff --git a/include/uapi/linux/ptrace.h b/include/uapi/linux/ptrace.h index e46d82b91166..d5a1b8a492b9 100644 --- a/include/uapi/linux/ptrace.h +++ b/include/uapi/linux/ptrace.h @@ -69,8 +69,8 @@ struct ptrace_peeksiginfo_args { #define PTRACE_SECCOMP_GET_METADATA 0x420d struct seccomp_metadata { - unsigned long filter_off; /* Input: which filter */ - unsigned int flags; /* Output: filter's flags */ + __u64 filter_off; /* Input: which filter */ + __u64 flags; /* Output: filter's flags */ }; /* Read signals from a shared (process wide) queue */ diff --git a/include/uapi/linux/rds.h b/include/uapi/linux/rds.h index e71d4491f225..a66b213de3d7 100644 --- a/include/uapi/linux/rds.h +++ b/include/uapi/linux/rds.h @@ -103,6 +103,8 @@ #define RDS_CMSG_MASKED_ATOMIC_FADD 8 #define RDS_CMSG_MASKED_ATOMIC_CSWP 9 #define RDS_CMSG_RXPATH_LATENCY 11 +#define RDS_CMSG_ZCOPY_COOKIE 12 +#define RDS_CMSG_ZCOPY_COMPLETION 13 #define RDS_INFO_FIRST 10000 #define RDS_INFO_COUNTERS 10000 @@ -316,6 +318,12 @@ struct rds_rdma_notify { #define RDS_RDMA_DROPPED 3 #define RDS_RDMA_OTHER_ERROR 4 +#define RDS_MAX_ZCOOKIES 8 +struct rds_zcopy_cookies { + __u32 num; + __u32 cookies[RDS_MAX_ZCOOKIES]; +}; + /* * Common set of flags for all RDMA related structs */ diff --git a/include/uapi/linux/tc_ematch/tc_em_ipt.h b/include/uapi/linux/tc_ematch/tc_em_ipt.h new file mode 100644 index 000000000000..49a65530992c --- /dev/null +++ b/include/uapi/linux/tc_ematch/tc_em_ipt.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __LINUX_TC_EM_IPT_H +#define __LINUX_TC_EM_IPT_H + +#include <linux/types.h> +#include <linux/pkt_cls.h> + +enum { + TCA_EM_IPT_UNSPEC, + TCA_EM_IPT_HOOK, + TCA_EM_IPT_MATCH_NAME, + TCA_EM_IPT_MATCH_REVISION, + TCA_EM_IPT_NFPROTO, + TCA_EM_IPT_MATCH_DATA, + __TCA_EM_IPT_MAX +}; + +#define TCA_EM_IPT_MAX (__TCA_EM_IPT_MAX - 1) + +#endif diff --git a/include/uapi/rdma/rdma_user_ioctl.h b/include/uapi/rdma/rdma_user_ioctl.h index 03557b5f9aa6..46de0885e800 100644 --- a/include/uapi/rdma/rdma_user_ioctl.h +++ b/include/uapi/rdma/rdma_user_ioctl.h @@ -65,7 +65,7 @@ struct ib_uverbs_attr { __u16 len; /* only for pointers */ __u16 flags; /* combination of UVERBS_ATTR_F_XXXX */ __u16 reserved; - __u64 data; /* ptr to command, inline data or idr/fd */ + __aligned_u64 data; /* ptr to command, inline data or idr/fd */ }; struct ib_uverbs_ioctl_hdr { @@ -73,7 +73,7 @@ struct ib_uverbs_ioctl_hdr { __u16 object_id; __u16 method_id; __u16 num_attrs; - __u64 reserved; + __aligned_u64 reserved; struct ib_uverbs_attr attrs[0]; }; diff --git a/kernel/audit.c b/kernel/audit.c index 227db99b0f19..5e49b614d0e6 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1526,6 +1526,7 @@ static struct pernet_operations audit_net_ops __net_initdata = { .exit = audit_net_exit, .id = &audit_net_id, .size = sizeof(struct audit_net), + .async = true, }; /* Initialize audit support at boot time. */ diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index b1f66480135b..14750e7c5ee4 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -26,8 +26,10 @@ static void bpf_array_free_percpu(struct bpf_array *array) { int i; - for (i = 0; i < array->map.max_entries; i++) + for (i = 0; i < array->map.max_entries; i++) { free_percpu(array->pptrs[i]); + cond_resched(); + } } static int bpf_array_alloc_percpu(struct bpf_array *array) @@ -43,6 +45,7 @@ static int bpf_array_alloc_percpu(struct bpf_array *array) return -ENOMEM; } array->pptrs[i] = ptr; + cond_resched(); } return 0; @@ -73,11 +76,11 @@ static int array_map_alloc_check(union bpf_attr *attr) static struct bpf_map *array_map_alloc(union bpf_attr *attr) { bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY; - int numa_node = bpf_map_attr_numa_node(attr); + int ret, numa_node = bpf_map_attr_numa_node(attr); u32 elem_size, index_mask, max_entries; bool unpriv = !capable(CAP_SYS_ADMIN); + u64 cost, array_size, mask64; struct bpf_array *array; - u64 array_size, mask64; elem_size = round_up(attr->value_size, 8); @@ -109,8 +112,19 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) array_size += (u64) max_entries * elem_size; /* make sure there is no u32 overflow later in round_up() */ - if (array_size >= U32_MAX - PAGE_SIZE) + cost = array_size; + if (cost >= U32_MAX - PAGE_SIZE) return ERR_PTR(-ENOMEM); + if (percpu) { + cost += (u64)attr->max_entries * elem_size * num_possible_cpus(); + if (cost >= U32_MAX - PAGE_SIZE) + return ERR_PTR(-ENOMEM); + } + cost = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + + ret = bpf_map_precharge_memlock(cost); + if (ret < 0) + return ERR_PTR(ret); /* allocate all map elements and zero-initialize them */ array = bpf_map_area_alloc(array_size, numa_node); @@ -121,20 +135,13 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) /* copy mandatory map attributes */ bpf_map_init_from_attr(&array->map, attr); + array->map.pages = cost; array->elem_size = elem_size; - if (!percpu) - goto out; - - array_size += (u64) attr->max_entries * elem_size * num_possible_cpus(); - - if (array_size >= U32_MAX - PAGE_SIZE || - bpf_array_alloc_percpu(array)) { + if (percpu && bpf_array_alloc_percpu(array)) { bpf_map_area_free(array); return ERR_PTR(-ENOMEM); } -out: - array->map.pages = round_up(array_size, PAGE_SIZE) >> PAGE_SHIFT; return &array->map; } diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 29ca9208dcfa..d315b393abdd 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1590,7 +1590,7 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs, * so always copy 'cnt' prog_ids to the user. * In a rare race the user will see zero prog_ids */ - ids = kcalloc(cnt, sizeof(u32), GFP_USER); + ids = kcalloc(cnt, sizeof(u32), GFP_USER | __GFP_NOWARN); if (!ids) return -ENOMEM; rcu_read_lock(); diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index fbfdada6caee..a4bb0b34375a 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -334,7 +334,7 @@ static int cpu_map_kthread_run(void *data) static struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu, int map_id) { - gfp_t gfp = GFP_ATOMIC|__GFP_NOWARN; + gfp_t gfp = GFP_KERNEL | __GFP_NOWARN; struct bpf_cpu_map_entry *rcpu; int numa, err; diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 7b469d10d0e9..b4b5b81e7251 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -555,7 +555,10 @@ static void trie_free(struct bpf_map *map) struct lpm_trie_node __rcu **slot; struct lpm_trie_node *node; - raw_spin_lock(&trie->lock); + /* Wait for outstanding programs to complete + * update/lookup/delete/get_next_key and free the trie. + */ + synchronize_rcu(); /* Always start at the root and walk down to a node that has no * children. Then free that node, nullify its reference in the parent @@ -566,10 +569,9 @@ static void trie_free(struct bpf_map *map) slot = &trie->root; for (;;) { - node = rcu_dereference_protected(*slot, - lockdep_is_held(&trie->lock)); + node = rcu_dereference_protected(*slot, 1); if (!node) - goto unlock; + goto out; if (rcu_access_pointer(node->child[0])) { slot = &node->child[0]; @@ -587,8 +589,8 @@ static void trie_free(struct bpf_map *map) } } -unlock: - raw_spin_unlock(&trie->lock); +out: + kfree(trie); } static int trie_get_next_key(struct bpf_map *map, void *_key, void *_next_key) diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 48c33417d13c..a927e89dad6e 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -521,8 +521,8 @@ static struct smap_psock *smap_init_psock(struct sock *sock, static struct bpf_map *sock_map_alloc(union bpf_attr *attr) { struct bpf_stab *stab; - int err = -EINVAL; u64 cost; + int err; if (!capable(CAP_NET_ADMIN)) return ERR_PTR(-EPERM); @@ -547,6 +547,7 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr) /* make sure page count doesn't overflow */ cost = (u64) stab->map.max_entries * sizeof(struct sock *); + err = -EINVAL; if (cost >= U32_MAX - PAGE_SIZE) goto free_stab; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 5fb69a85d967..3c74b163eaeb 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -508,10 +508,6 @@ err: static const int caller_saved[CALLER_SAVED_REGS] = { BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5 }; -#define CALLEE_SAVED_REGS 5 -static const int callee_saved[CALLEE_SAVED_REGS] = { - BPF_REG_6, BPF_REG_7, BPF_REG_8, BPF_REG_9 -}; static void __mark_reg_not_init(struct bpf_reg_state *reg); diff --git a/kernel/fork.c b/kernel/fork.c index be8aa5b98666..e5d9d405ae4e 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -592,7 +592,7 @@ static void check_mm(struct mm_struct *mm) * is dropped: either by a lazy thread or by * mmput. Free the page directory and the mm. */ -static void __mmdrop(struct mm_struct *mm) +void __mmdrop(struct mm_struct *mm) { BUG_ON(mm == &init_mm); mm_free_pgd(mm); @@ -603,18 +603,7 @@ static void __mmdrop(struct mm_struct *mm) put_user_ns(mm->user_ns); free_mm(mm); } - -void mmdrop(struct mm_struct *mm) -{ - /* - * The implicit full barrier implied by atomic_dec_and_test() is - * required by the membarrier system call before returning to - * user-space, after storing to rq->curr. - */ - if (unlikely(atomic_dec_and_test(&mm->mm_count))) - __mmdrop(mm); -} -EXPORT_SYMBOL_GPL(mmdrop); +EXPORT_SYMBOL_GPL(__mmdrop); static void mmdrop_async_fn(struct work_struct *work) { diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index e6a9c36470ee..82b8b18ee1eb 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -1726,25 +1726,14 @@ static int irq_domain_debug_show(struct seq_file *m, void *p) irq_domain_debug_show_one(m, d, 0); return 0; } - -static int irq_domain_debug_open(struct inode *inode, struct file *file) -{ - return single_open(file, irq_domain_debug_show, inode->i_private); -} - -static const struct file_operations dfs_domain_ops = { - .open = irq_domain_debug_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(irq_domain_debug); static void debugfs_add_domain_dir(struct irq_domain *d) { if (!d->name || !domain_dir || d->debugfs_file) return; d->debugfs_file = debugfs_create_file(d->name, 0444, domain_dir, d, - &dfs_domain_ops); + &irq_domain_debug_fops); } static void debugfs_remove_domain_dir(struct irq_domain *d) @@ -1760,7 +1749,8 @@ void __init irq_domain_debugfs_init(struct dentry *root) if (!domain_dir) return; - debugfs_create_file("default", 0444, domain_dir, NULL, &dfs_domain_ops); + debugfs_create_file("default", 0444, domain_dir, NULL, + &irq_domain_debug_fops); mutex_lock(&irq_domain_mutex); list_for_each_entry(d, &irq_domain_list, link) debugfs_add_domain_dir(d); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index da2ccf142358..102160ff5c66 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -978,67 +978,90 @@ static int prepare_kprobe(struct kprobe *p) } /* Caller must lock kprobe_mutex */ -static void arm_kprobe_ftrace(struct kprobe *p) +static int arm_kprobe_ftrace(struct kprobe *p) { - int ret; + int ret = 0; ret = ftrace_set_filter_ip(&kprobe_ftrace_ops, (unsigned long)p->addr, 0, 0); - WARN(ret < 0, "Failed to arm kprobe-ftrace at %p (%d)\n", p->addr, ret); - kprobe_ftrace_enabled++; - if (kprobe_ftrace_enabled == 1) { + if (ret) { + pr_debug("Failed to arm kprobe-ftrace at %p (%d)\n", p->addr, ret); + return ret; + } + + if (kprobe_ftrace_enabled == 0) { ret = register_ftrace_function(&kprobe_ftrace_ops); - WARN(ret < 0, "Failed to init kprobe-ftrace (%d)\n", ret); + if (ret) { + pr_debug("Failed to init kprobe-ftrace (%d)\n", ret); + goto err_ftrace; + } } + + kprobe_ftrace_enabled++; + return ret; + +err_ftrace: + /* + * Note: Since kprobe_ftrace_ops has IPMODIFY set, and ftrace requires a + * non-empty filter_hash for IPMODIFY ops, we're safe from an accidental + * empty filter_hash which would undesirably trace all functions. + */ + ftrace_set_filter_ip(&kprobe_ftrace_ops, (unsigned long)p->addr, 1, 0); + return ret; } /* Caller must lock kprobe_mutex */ -static void disarm_kprobe_ftrace(struct kprobe *p) +static int disarm_kprobe_ftrace(struct kprobe *p) { - int ret; + int ret = 0; - kprobe_ftrace_enabled--; - if (kprobe_ftrace_enabled == 0) { + if (kprobe_ftrace_enabled == 1) { ret = unregister_ftrace_function(&kprobe_ftrace_ops); - WARN(ret < 0, "Failed to init kprobe-ftrace (%d)\n", ret); + if (WARN(ret < 0, "Failed to unregister kprobe-ftrace (%d)\n", ret)) + return ret; } + + kprobe_ftrace_enabled--; + ret = ftrace_set_filter_ip(&kprobe_ftrace_ops, (unsigned long)p->addr, 1, 0); WARN(ret < 0, "Failed to disarm kprobe-ftrace at %p (%d)\n", p->addr, ret); + return ret; } #else /* !CONFIG_KPROBES_ON_FTRACE */ #define prepare_kprobe(p) arch_prepare_kprobe(p) -#define arm_kprobe_ftrace(p) do {} while (0) -#define disarm_kprobe_ftrace(p) do {} while (0) +#define arm_kprobe_ftrace(p) (-ENODEV) +#define disarm_kprobe_ftrace(p) (-ENODEV) #endif /* Arm a kprobe with text_mutex */ -static void arm_kprobe(struct kprobe *kp) +static int arm_kprobe(struct kprobe *kp) { - if (unlikely(kprobe_ftrace(kp))) { - arm_kprobe_ftrace(kp); - return; - } + if (unlikely(kprobe_ftrace(kp))) + return arm_kprobe_ftrace(kp); + cpus_read_lock(); mutex_lock(&text_mutex); __arm_kprobe(kp); mutex_unlock(&text_mutex); cpus_read_unlock(); + + return 0; } /* Disarm a kprobe with text_mutex */ -static void disarm_kprobe(struct kprobe *kp, bool reopt) +static int disarm_kprobe(struct kprobe *kp, bool reopt) { - if (unlikely(kprobe_ftrace(kp))) { - disarm_kprobe_ftrace(kp); - return; - } + if (unlikely(kprobe_ftrace(kp))) + return disarm_kprobe_ftrace(kp); cpus_read_lock(); mutex_lock(&text_mutex); __disarm_kprobe(kp, reopt); mutex_unlock(&text_mutex); cpus_read_unlock(); + + return 0; } /* @@ -1362,9 +1385,15 @@ out: if (ret == 0 && kprobe_disabled(ap) && !kprobe_disabled(p)) { ap->flags &= ~KPROBE_FLAG_DISABLED; - if (!kprobes_all_disarmed) + if (!kprobes_all_disarmed) { /* Arm the breakpoint again. */ - arm_kprobe(ap); + ret = arm_kprobe(ap); + if (ret) { + ap->flags |= KPROBE_FLAG_DISABLED; + list_del_rcu(&p->list); + synchronize_sched(); + } + } } return ret; } @@ -1573,8 +1602,14 @@ int register_kprobe(struct kprobe *p) hlist_add_head_rcu(&p->hlist, &kprobe_table[hash_ptr(p->addr, KPROBE_HASH_BITS)]); - if (!kprobes_all_disarmed && !kprobe_disabled(p)) - arm_kprobe(p); + if (!kprobes_all_disarmed && !kprobe_disabled(p)) { + ret = arm_kprobe(p); + if (ret) { + hlist_del_rcu(&p->hlist); + synchronize_sched(); + goto out; + } + } /* Try to optimize kprobe */ try_to_optimize_kprobe(p); @@ -1608,11 +1643,12 @@ static int aggr_kprobe_disabled(struct kprobe *ap) static struct kprobe *__disable_kprobe(struct kprobe *p) { struct kprobe *orig_p; + int ret; /* Get an original kprobe for return */ orig_p = __get_valid_kprobe(p); if (unlikely(orig_p == NULL)) - return NULL; + return ERR_PTR(-EINVAL); if (!kprobe_disabled(p)) { /* Disable probe if it is a child probe */ @@ -1626,8 +1662,13 @@ static struct kprobe *__disable_kprobe(struct kprobe *p) * should have already been disarmed, so * skip unneed disarming process. */ - if (!kprobes_all_disarmed) - disarm_kprobe(orig_p, true); + if (!kprobes_all_disarmed) { + ret = disarm_kprobe(orig_p, true); + if (ret) { + p->flags &= ~KPROBE_FLAG_DISABLED; + return ERR_PTR(ret); + } + } orig_p->flags |= KPROBE_FLAG_DISABLED; } } @@ -1644,8 +1685,8 @@ static int __unregister_kprobe_top(struct kprobe *p) /* Disable kprobe. This will disarm it if needed. */ ap = __disable_kprobe(p); - if (ap == NULL) - return -EINVAL; + if (IS_ERR(ap)) + return PTR_ERR(ap); if (ap == p) /* @@ -2078,12 +2119,14 @@ static void kill_kprobe(struct kprobe *p) int disable_kprobe(struct kprobe *kp) { int ret = 0; + struct kprobe *p; mutex_lock(&kprobe_mutex); /* Disable this kprobe */ - if (__disable_kprobe(kp) == NULL) - ret = -EINVAL; + p = __disable_kprobe(kp); + if (IS_ERR(p)) + ret = PTR_ERR(p); mutex_unlock(&kprobe_mutex); return ret; @@ -2116,7 +2159,9 @@ int enable_kprobe(struct kprobe *kp) if (!kprobes_all_disarmed && kprobe_disabled(p)) { p->flags &= ~KPROBE_FLAG_DISABLED; - arm_kprobe(p); + ret = arm_kprobe(p); + if (ret) + p->flags |= KPROBE_FLAG_DISABLED; } out: mutex_unlock(&kprobe_mutex); @@ -2407,11 +2452,12 @@ static const struct file_operations debugfs_kprobe_blacklist_ops = { .release = seq_release, }; -static void arm_all_kprobes(void) +static int arm_all_kprobes(void) { struct hlist_head *head; struct kprobe *p; - unsigned int i; + unsigned int i, total = 0, errors = 0; + int err, ret = 0; mutex_lock(&kprobe_mutex); @@ -2428,46 +2474,74 @@ static void arm_all_kprobes(void) /* Arming kprobes doesn't optimize kprobe itself */ for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; - hlist_for_each_entry_rcu(p, head, hlist) - if (!kprobe_disabled(p)) - arm_kprobe(p); + /* Arm all kprobes on a best-effort basis */ + hlist_for_each_entry_rcu(p, head, hlist) { + if (!kprobe_disabled(p)) { + err = arm_kprobe(p); + if (err) { + errors++; + ret = err; + } + total++; + } + } } - printk(KERN_INFO "Kprobes globally enabled\n"); + if (errors) + pr_warn("Kprobes globally enabled, but failed to arm %d out of %d probes\n", + errors, total); + else + pr_info("Kprobes globally enabled\n"); already_enabled: mutex_unlock(&kprobe_mutex); - return; + return ret; } -static void disarm_all_kprobes(void) +static int disarm_all_kprobes(void) { struct hlist_head *head; struct kprobe *p; - unsigned int i; + unsigned int i, total = 0, errors = 0; + int err, ret = 0; mutex_lock(&kprobe_mutex); /* If kprobes are already disarmed, just return */ if (kprobes_all_disarmed) { mutex_unlock(&kprobe_mutex); - return; + return 0; } kprobes_all_disarmed = true; - printk(KERN_INFO "Kprobes globally disabled\n"); for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; + /* Disarm all kprobes on a best-effort basis */ hlist_for_each_entry_rcu(p, head, hlist) { - if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p)) - disarm_kprobe(p, false); + if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p)) { + err = disarm_kprobe(p, false); + if (err) { + errors++; + ret = err; + } + total++; + } } } + + if (errors) + pr_warn("Kprobes globally disabled, but failed to disarm %d out of %d probes\n", + errors, total); + else + pr_info("Kprobes globally disabled\n"); + mutex_unlock(&kprobe_mutex); /* Wait for disarming all kprobes by optimizer */ wait_for_kprobe_optimizer(); + + return ret; } /* @@ -2494,6 +2568,7 @@ static ssize_t write_enabled_file_bool(struct file *file, { char buf[32]; size_t buf_size; + int ret = 0; buf_size = min(count, (sizeof(buf)-1)); if (copy_from_user(buf, user_buf, buf_size)) @@ -2504,17 +2579,20 @@ static ssize_t write_enabled_file_bool(struct file *file, case 'y': case 'Y': case '1': - arm_all_kprobes(); + ret = arm_all_kprobes(); break; case 'n': case 'N': case '0': - disarm_all_kprobes(); + ret = disarm_all_kprobes(); break; default: return -EINVAL; } + if (ret) + return ret; + return count; } diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c index 38ece035039e..d880296245c5 100644 --- a/kernel/locking/qspinlock.c +++ b/kernel/locking/qspinlock.c @@ -379,6 +379,14 @@ queue: tail = encode_tail(smp_processor_id(), idx); node += idx; + + /* + * Ensure that we increment the head node->count before initialising + * the actual node. If the compiler is kind enough to reorder these + * stores, then an IRQ could overwrite our assignments. + */ + barrier(); + node->locked = 0; node->next = NULL; pv_init_node(node); @@ -408,14 +416,15 @@ queue: */ if (old & _Q_TAIL_MASK) { prev = decode_tail(old); + /* - * The above xchg_tail() is also a load of @lock which - * generates, through decode_tail(), a pointer. The address - * dependency matches the RELEASE of xchg_tail() such that - * the subsequent access to @prev happens after. + * We must ensure that the stores to @node are observed before + * the write to prev->next. The address dependency from + * xchg_tail is not sufficient to ensure this because the read + * component of xchg_tail is unordered with respect to the + * initialisation of @node. */ - - WRITE_ONCE(prev->next, node); + smp_store_release(&prev->next, node); pv_wait_node(node, prev); arch_mcs_spin_lock_contended(&node->locked); diff --git a/kernel/relay.c b/kernel/relay.c index c3029402f15c..c955b10c973c 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -163,7 +163,7 @@ static struct rchan_buf *relay_create_buf(struct rchan *chan) { struct rchan_buf *buf; - if (chan->n_subbufs > UINT_MAX / sizeof(size_t *)) + if (chan->n_subbufs > KMALLOC_MAX_SIZE / sizeof(size_t *)) return NULL; buf = kzalloc(sizeof(struct rchan_buf), GFP_KERNEL); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index bf724c1952ea..e7c535eee0a6 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2601,19 +2601,31 @@ static inline void finish_task(struct task_struct *prev) #endif } -static inline void finish_lock_switch(struct rq *rq) +static inline void +prepare_lock_switch(struct rq *rq, struct task_struct *next, struct rq_flags *rf) { + /* + * Since the runqueue lock will be released by the next + * task (which is an invalid locking op but in the case + * of the scheduler it's an obvious special-case), so we + * do an early lockdep release here: + */ + rq_unpin_lock(rq, rf); + spin_release(&rq->lock.dep_map, 1, _THIS_IP_); #ifdef CONFIG_DEBUG_SPINLOCK /* this is a valid case when another task releases the spinlock */ - rq->lock.owner = current; + rq->lock.owner = next; #endif +} + +static inline void finish_lock_switch(struct rq *rq) +{ /* * If we are tracking spinlock dependencies then we have to * fix up the runqueue lock - which gets 'carried over' from * prev into current: */ spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_); - raw_spin_unlock_irq(&rq->lock); } @@ -2844,14 +2856,7 @@ context_switch(struct rq *rq, struct task_struct *prev, rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP); - /* - * Since the runqueue lock will be released by the next - * task (which is an invalid locking op but in the case - * of the scheduler it's an obvious special-case), so we - * do an early lockdep release here: - */ - rq_unpin_lock(rq, rf); - spin_release(&rq->lock.dep_map, 1, _THIS_IP_); + prepare_lock_switch(rq, next, rf); /* Here we just switch the register state and the stack. */ switch_to(prev, next, prev); diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index dd062a1c8cf0..7936f548e071 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -19,8 +19,6 @@ #include "sched.h" -#define SUGOV_KTHREAD_PRIORITY 50 - struct sugov_tunables { struct gov_attr_set attr_set; unsigned int rate_limit_us; diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 9bb0e0c412ec..9df09782025c 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1153,6 +1153,7 @@ static void update_curr_dl(struct rq *rq) struct sched_dl_entity *dl_se = &curr->dl; u64 delta_exec, scaled_delta_exec; int cpu = cpu_of(rq); + u64 now; if (!dl_task(curr) || !on_dl_rq(dl_se)) return; @@ -1165,7 +1166,8 @@ static void update_curr_dl(struct rq *rq) * natural solution, but the full ramifications of this * approach need further study. */ - delta_exec = rq_clock_task(rq) - curr->se.exec_start; + now = rq_clock_task(rq); + delta_exec = now - curr->se.exec_start; if (unlikely((s64)delta_exec <= 0)) { if (unlikely(dl_se->dl_yielded)) goto throttle; @@ -1178,7 +1180,7 @@ static void update_curr_dl(struct rq *rq) curr->se.sum_exec_runtime += delta_exec; account_group_exec_runtime(curr, delta_exec); - curr->se.exec_start = rq_clock_task(rq); + curr->se.exec_start = now; cgroup_account_cputime(curr, delta_exec); sched_rt_avg_update(rq, delta_exec); diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 663b2355a3aa..aad49451584e 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -950,12 +950,13 @@ static void update_curr_rt(struct rq *rq) { struct task_struct *curr = rq->curr; struct sched_rt_entity *rt_se = &curr->rt; - u64 now = rq_clock_task(rq); u64 delta_exec; + u64 now; if (curr->sched_class != &rt_sched_class) return; + now = rq_clock_task(rq); delta_exec = now - curr->se.exec_start; if (unlikely((s64)delta_exec <= 0)) return; diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 940fa408a288..dc77548167ef 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -1076,14 +1076,16 @@ long seccomp_get_metadata(struct task_struct *task, size = min_t(unsigned long, size, sizeof(kmd)); - if (copy_from_user(&kmd, data, size)) + if (size < sizeof(kmd.filter_off)) + return -EINVAL; + + if (copy_from_user(&kmd.filter_off, data, sizeof(kmd.filter_off))) return -EFAULT; filter = get_nth_filter(task, kmd.filter_off); if (IS_ERR(filter)) return PTR_ERR(filter); - memset(&kmd, 0, sizeof(kmd)); if (filter->log) kmd.flags |= SECCOMP_FILTER_FLAG_LOG; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index fc2838ac8b78..c0a9e310d715 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -872,6 +872,8 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info) return -EINVAL; if (copy_from_user(&query, uquery, sizeof(query))) return -EFAULT; + if (query.ids_len > BPF_TRACE_MAX_PROGS) + return -E2BIG; mutex_lock(&bpf_event_mutex); ret = bpf_prog_array_copy_info(event->tp_event->prog_array, diff --git a/kernel/user.c b/kernel/user.c index 9a20acce460d..36288d840675 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -101,6 +101,7 @@ struct user_struct root_user = { .sigpending = ATOMIC_INIT(0), .locked_shm = 0, .uid = GLOBAL_ROOT_UID, + .ratelimit = RATELIMIT_STATE_INIT(root_user.ratelimit, 0, 0), }; /* @@ -191,6 +192,8 @@ struct user_struct *alloc_uid(kuid_t uid) new->uid = uid; atomic_set(&new->__count, 1); + ratelimit_state_init(&new->ratelimit, HZ, 100); + ratelimit_set_flags(&new->ratelimit, RATELIMIT_MSG_ON_RELEASE); /* * Before adding this, check whether we raced diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 017044c26233..bb9a519cbf50 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -4180,6 +4180,22 @@ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active) EXPORT_SYMBOL_GPL(workqueue_set_max_active); /** + * current_work - retrieve %current task's work struct + * + * Determine if %current task is a workqueue worker and what it's working on. + * Useful to find out the context that the %current task is running in. + * + * Return: work struct if %current task is a workqueue worker, %NULL otherwise. + */ +struct work_struct *current_work(void) +{ + struct worker *worker = current_wq_worker(); + + return worker ? worker->current_work : NULL; +} +EXPORT_SYMBOL(current_work); + +/** * current_is_workqueue_rescuer - is %current workqueue rescuer? * * Determine whether %current is a workqueue rescuer. Can be used from diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 6088408ef26c..64155e310a9f 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1642,6 +1642,7 @@ config DMA_API_DEBUG menuconfig RUNTIME_TESTING_MENU bool "Runtime Testing" + def_bool y if RUNTIME_TESTING_MENU diff --git a/lib/dma-direct.c b/lib/dma-direct.c index 40b1f92f2214..c9e8e21cb334 100644 --- a/lib/dma-direct.c +++ b/lib/dma-direct.c @@ -84,6 +84,10 @@ again: return page_address(page); } +/* + * NOTE: this function must never look at the dma_addr argument, because we want + * to be able to use it as a helper for iommu implementations as well. + */ void dma_direct_free(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs) { @@ -152,5 +156,6 @@ const struct dma_map_ops dma_direct_ops = { .map_sg = dma_direct_map_sg, .dma_supported = dma_direct_supported, .mapping_error = dma_direct_mapping_error, + .is_phys = 1, }; EXPORT_SYMBOL(dma_direct_ops); diff --git a/lib/idr.c b/lib/idr.c index c98d77fcf393..99ec5bc89d25 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -431,7 +431,6 @@ int ida_get_new_above(struct ida *ida, int start, int *id) bitmap = this_cpu_xchg(ida_bitmap, NULL); if (!bitmap) return -EAGAIN; - memset(bitmap, 0, sizeof(*bitmap)); bitmap->bitmap[0] = tmp >> RADIX_TREE_EXCEPTIONAL_SHIFT; rcu_assign_pointer(*slot, bitmap); } @@ -464,7 +463,6 @@ int ida_get_new_above(struct ida *ida, int start, int *id) bitmap = this_cpu_xchg(ida_bitmap, NULL); if (!bitmap) return -EAGAIN; - memset(bitmap, 0, sizeof(*bitmap)); __set_bit(bit, bitmap->bitmap); radix_tree_iter_replace(root, &iter, slot, bitmap); } diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c index 9fe6ec8fda28..9539d7ab3ea8 100644 --- a/lib/kobject_uevent.c +++ b/lib/kobject_uevent.c @@ -650,6 +650,7 @@ found: static struct pernet_operations uevent_net_ops = { .init = uevent_net_init, .exit = uevent_net_exit, + .async = true, }; static int __init kobject_uevent_init(void) diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 0a7ae3288a24..8e00138d593f 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -2125,7 +2125,7 @@ int ida_pre_get(struct ida *ida, gfp_t gfp) preempt_enable(); if (!this_cpu_read(ida_bitmap)) { - struct ida_bitmap *bitmap = kmalloc(sizeof(*bitmap), gfp); + struct ida_bitmap *bitmap = kzalloc(sizeof(*bitmap), gfp); if (!bitmap) return 0; if (this_cpu_cmpxchg(ida_bitmap, NULL, bitmap)) diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 77ee6ced11b1..d7a708f82559 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -1849,7 +1849,7 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr, { const int default_width = 2 * sizeof(void *); - if (!ptr && *fmt != 'K') { + if (!ptr && *fmt != 'K' && *fmt != 'x') { /* * Print (null) with the same width as a pointer so it makes * tabular output look nice. diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 4b80ccee4535..8291b75f42c8 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1139,8 +1139,6 @@ int memory_failure(unsigned long pfn, int flags) return 0; } - arch_unmap_kpfn(pfn); - orig_head = hpage = compound_head(p); num_poisoned_pages_inc(); diff --git a/mm/memory.c b/mm/memory.c index dd8de96f5547..5fcfc24904d1 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -80,7 +80,7 @@ #include "internal.h" -#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS +#if defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) && !defined(CONFIG_COMPILE_TEST) #warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid. #endif diff --git a/mm/mlock.c b/mm/mlock.c index 79398200e423..74e5a6547c3d 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -64,6 +64,12 @@ void clear_page_mlock(struct page *page) mod_zone_page_state(page_zone(page), NR_MLOCK, -hpage_nr_pages(page)); count_vm_event(UNEVICTABLE_PGCLEARED); + /* + * The previous TestClearPageMlocked() corresponds to the smp_mb() + * in __pagevec_lru_add_fn(). + * + * See __pagevec_lru_add_fn for more explanation. + */ if (!isolate_lru_page(page)) { putback_lru_page(page); } else { diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 81e18ceef579..cb416723538f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -46,6 +46,7 @@ #include <linux/stop_machine.h> #include <linux/sort.h> #include <linux/pfn.h> +#include <xen/xen.h> #include <linux/backing-dev.h> #include <linux/fault-inject.h> #include <linux/page-isolation.h> @@ -347,6 +348,9 @@ static inline bool update_defer_init(pg_data_t *pgdat, /* Always populate low zones for address-constrained allocations */ if (zone_end < pgdat_end_pfn(pgdat)) return true; + /* Xen PV domains need page structures early */ + if (xen_pv_domain()) + return true; (*nr_initialised)++; if ((*nr_initialised > pgdat->static_init_pgcnt) && (pfn & (PAGES_PER_SECTION - 1)) == 0) { diff --git a/mm/swap.c b/mm/swap.c index 567a7b96e41d..0f17330dd0e5 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -446,30 +446,6 @@ void lru_cache_add(struct page *page) } /** - * add_page_to_unevictable_list - add a page to the unevictable list - * @page: the page to be added to the unevictable list - * - * Add page directly to its zone's unevictable list. To avoid races with - * tasks that might be making the page evictable, through eg. munlock, - * munmap or exit, while it's not on the lru, we want to add the page - * while it's locked or otherwise "invisible" to other tasks. This is - * difficult to do when using the pagevec cache, so bypass that. - */ -void add_page_to_unevictable_list(struct page *page) -{ - struct pglist_data *pgdat = page_pgdat(page); - struct lruvec *lruvec; - - spin_lock_irq(&pgdat->lru_lock); - lruvec = mem_cgroup_page_lruvec(page, pgdat); - ClearPageActive(page); - SetPageUnevictable(page); - SetPageLRU(page); - add_page_to_lru_list(page, lruvec, LRU_UNEVICTABLE); - spin_unlock_irq(&pgdat->lru_lock); -} - -/** * lru_cache_add_active_or_unevictable * @page: the page to be added to LRU * @vma: vma in which page is mapped for determining reclaimability @@ -484,13 +460,9 @@ void lru_cache_add_active_or_unevictable(struct page *page, { VM_BUG_ON_PAGE(PageLRU(page), page); - if (likely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED)) { + if (likely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED)) SetPageActive(page); - lru_cache_add(page); - return; - } - - if (!TestSetPageMlocked(page)) { + else if (!TestSetPageMlocked(page)) { /* * We use the irq-unsafe __mod_zone_page_stat because this * counter is not modified from interrupt context, and the pte @@ -500,7 +472,7 @@ void lru_cache_add_active_or_unevictable(struct page *page, hpage_nr_pages(page)); count_vm_event(UNEVICTABLE_PGMLOCKED); } - add_page_to_unevictable_list(page); + lru_cache_add(page); } /* @@ -886,15 +858,55 @@ void lru_add_page_tail(struct page *page, struct page *page_tail, static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec, void *arg) { - int file = page_is_file_cache(page); - int active = PageActive(page); - enum lru_list lru = page_lru(page); + enum lru_list lru; + int was_unevictable = TestClearPageUnevictable(page); VM_BUG_ON_PAGE(PageLRU(page), page); SetPageLRU(page); + /* + * Page becomes evictable in two ways: + * 1) Within LRU lock [munlock_vma_pages() and __munlock_pagevec()]. + * 2) Before acquiring LRU lock to put the page to correct LRU and then + * a) do PageLRU check with lock [check_move_unevictable_pages] + * b) do PageLRU check before lock [clear_page_mlock] + * + * (1) & (2a) are ok as LRU lock will serialize them. For (2b), we need + * following strict ordering: + * + * #0: __pagevec_lru_add_fn #1: clear_page_mlock + * + * SetPageLRU() TestClearPageMlocked() + * smp_mb() // explicit ordering // above provides strict + * // ordering + * PageMlocked() PageLRU() + * + * + * if '#1' does not observe setting of PG_lru by '#0' and fails + * isolation, the explicit barrier will make sure that page_evictable + * check will put the page in correct LRU. Without smp_mb(), SetPageLRU + * can be reordered after PageMlocked check and can make '#1' to fail + * the isolation of the page whose Mlocked bit is cleared (#0 is also + * looking at the same page) and the evictable page will be stranded + * in an unevictable LRU. + */ + smp_mb(); + + if (page_evictable(page)) { + lru = page_lru(page); + update_page_reclaim_stat(lruvec, page_is_file_cache(page), + PageActive(page)); + if (was_unevictable) + count_vm_event(UNEVICTABLE_PGRESCUED); + } else { + lru = LRU_UNEVICTABLE; + ClearPageActive(page); + SetPageUnevictable(page); + if (!was_unevictable) + count_vm_event(UNEVICTABLE_PGCULLED); + } + add_page_to_lru_list(page, lruvec, lru); - update_page_reclaim_stat(lruvec, file, active); trace_mm_lru_insertion(page, lru); } @@ -913,7 +925,7 @@ EXPORT_SYMBOL(__pagevec_lru_add); * @pvec: Where the resulting entries are placed * @mapping: The address_space to search * @start: The starting entry index - * @nr_pages: The maximum number of pages + * @nr_entries: The maximum number of pages * @indices: The cache indices corresponding to the entries in @pvec * * pagevec_lookup_entries() will search for and return a group of up diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 673942094328..ebff729cc956 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1943,11 +1943,15 @@ void *vmalloc_exec(unsigned long size) } #if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32) -#define GFP_VMALLOC32 GFP_DMA32 | GFP_KERNEL +#define GFP_VMALLOC32 (GFP_DMA32 | GFP_KERNEL) #elif defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA) -#define GFP_VMALLOC32 GFP_DMA | GFP_KERNEL +#define GFP_VMALLOC32 (GFP_DMA | GFP_KERNEL) #else -#define GFP_VMALLOC32 GFP_KERNEL +/* + * 64b systems should always have either DMA or DMA32 zones. For others + * GFP_DMA32 should do the right thing and use the normal zone. + */ +#define GFP_VMALLOC32 GFP_DMA32 | GFP_KERNEL #endif /** diff --git a/mm/vmscan.c b/mm/vmscan.c index 444749669187..bee53495a829 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -769,64 +769,7 @@ int remove_mapping(struct address_space *mapping, struct page *page) */ void putback_lru_page(struct page *page) { - bool is_unevictable; - int was_unevictable = PageUnevictable(page); - - VM_BUG_ON_PAGE(PageLRU(page), page); - -redo: - ClearPageUnevictable(page); - - if (page_evictable(page)) { - /* - * For evictable pages, we can use the cache. - * In event of a race, worst case is we end up with an - * unevictable page on [in]active list. - * We know how to handle that. - */ - is_unevictable = false; - lru_cache_add(page); - } else { - /* - * Put unevictable pages directly on zone's unevictable - * list. - */ - is_unevictable = true; - add_page_to_unevictable_list(page); - /* - * When racing with an mlock or AS_UNEVICTABLE clearing - * (page is unlocked) make sure that if the other thread - * does not observe our setting of PG_lru and fails - * isolation/check_move_unevictable_pages, - * we see PG_mlocked/AS_UNEVICTABLE cleared below and move - * the page back to the evictable list. - * - * The other side is TestClearPageMlocked() or shmem_lock(). - */ - smp_mb(); - } - - /* - * page's status can change while we move it among lru. If an evictable - * page is on unevictable list, it never be freed. To avoid that, - * check after we added it to the list, again. - */ - if (is_unevictable && page_evictable(page)) { - if (!isolate_lru_page(page)) { - put_page(page); - goto redo; - } - /* This means someone else dropped this page from LRU - * So, it will be freed or putback to LRU again. There is - * nothing to do here. - */ - } - - if (was_unevictable && !is_unevictable) - count_vm_event(UNEVICTABLE_PGRESCUED); - else if (!was_unevictable && is_unevictable) - count_vm_event(UNEVICTABLE_PGCULLED); - + lru_cache_add(page); put_page(page); /* drop ref from isolate */ } diff --git a/mm/zpool.c b/mm/zpool.c index f8cb83e7699b..01a771e304fa 100644 --- a/mm/zpool.c +++ b/mm/zpool.c @@ -360,7 +360,7 @@ u64 zpool_get_total_size(struct zpool *zpool) /** * zpool_evictable() - Test if zpool is potentially evictable - * @pool The zpool to test + * @zpool: The zpool to test * * Zpool is only potentially evictable when it's created with struct * zpool_ops.evict and its driver implements struct zpool_driver.shrink. diff --git a/mm/zswap.c b/mm/zswap.c index c004aa4fd3f4..61a5c41972db 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1007,6 +1007,12 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset, u8 *src, *dst; struct zswap_header zhdr = { .swpentry = swp_entry(type, offset) }; + /* THP isn't supported */ + if (PageTransHuge(page)) { + ret = -EINVAL; + goto reject; + } + if (!zswap_enabled || !tree) { ret = -ENODEV; goto reject; diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index bad01b14a4ad..bd0ed39f65fb 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -729,6 +729,7 @@ static struct pernet_operations vlan_net_ops = { .exit = vlan_exit_net, .id = &vlan_net_id, .size = sizeof(struct vlan_net), + .async = true, }; static int __init vlan_proto_init(void) diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index f3a4efcf1456..3aa5a93ad107 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -160,7 +160,8 @@ static void req_done(struct virtqueue *vq) spin_unlock_irqrestore(&chan->lock, flags); /* Wakeup if anyone waiting for VirtIO ring space. */ wake_up(chan->vc_wq); - p9_client_cb(chan->client, req, REQ_STATUS_RCVD); + if (len) + p9_client_cb(chan->client, req, REQ_STATUS_RCVD); } } diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 03a9fc0771c0..9b6bc5abe946 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1238,7 +1238,7 @@ out: * fields into the sockaddr. */ static int atalk_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { struct sockaddr_at sat; struct sock *sk = sock->sk; @@ -1251,7 +1251,6 @@ static int atalk_getname(struct socket *sock, struct sockaddr *uaddr, if (atalk_autobind(sk) < 0) goto out; - *uaddr_len = sizeof(struct sockaddr_at); memset(&sat, 0, sizeof(sat)); if (peer) { @@ -1268,9 +1267,9 @@ static int atalk_getname(struct socket *sock, struct sockaddr *uaddr, sat.sat_port = at->src_port; } - err = 0; sat.sat_family = AF_APPLETALK; memcpy(uaddr, &sat, sizeof(sat)); + err = sizeof(struct sockaddr_at); out: release_sock(sk); diff --git a/net/atm/pvc.c b/net/atm/pvc.c index e1140b3bdcaa..2cb10af16afc 100644 --- a/net/atm/pvc.c +++ b/net/atm/pvc.c @@ -87,21 +87,20 @@ static int pvc_getsockopt(struct socket *sock, int level, int optname, } static int pvc_getname(struct socket *sock, struct sockaddr *sockaddr, - int *sockaddr_len, int peer) + int peer) { struct sockaddr_atmpvc *addr; struct atm_vcc *vcc = ATM_SD(sock); if (!vcc->dev || !test_bit(ATM_VF_ADDR, &vcc->flags)) return -ENOTCONN; - *sockaddr_len = sizeof(struct sockaddr_atmpvc); addr = (struct sockaddr_atmpvc *)sockaddr; memset(addr, 0, sizeof(*addr)); addr->sap_family = AF_ATMPVC; addr->sap_addr.itf = vcc->dev->number; addr->sap_addr.vpi = vcc->vpi; addr->sap_addr.vci = vcc->vci; - return 0; + return sizeof(struct sockaddr_atmpvc); } static const struct proto_ops pvc_proto_ops = { diff --git a/net/atm/svc.c b/net/atm/svc.c index c458adcbc177..2f91b766ac42 100644 --- a/net/atm/svc.c +++ b/net/atm/svc.c @@ -419,15 +419,14 @@ out: } static int svc_getname(struct socket *sock, struct sockaddr *sockaddr, - int *sockaddr_len, int peer) + int peer) { struct sockaddr_atmsvc *addr; - *sockaddr_len = sizeof(struct sockaddr_atmsvc); addr = (struct sockaddr_atmsvc *) sockaddr; memcpy(addr, peer ? &ATM_SD(sock)->remote : &ATM_SD(sock)->local, sizeof(struct sockaddr_atmsvc)); - return 0; + return sizeof(struct sockaddr_atmsvc); } int svc_change_qos(struct atm_vcc *vcc, struct atm_qos *qos) diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 47fdd399626b..c8319ed48485 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -1388,7 +1388,7 @@ out: } static int ax25_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { struct full_sockaddr_ax25 *fsa = (struct full_sockaddr_ax25 *)uaddr; struct sock *sk = sock->sk; @@ -1427,7 +1427,7 @@ static int ax25_getname(struct socket *sock, struct sockaddr *uaddr, fsa->fsa_digipeater[0] = null_ax25_address; } } - *uaddr_len = sizeof (struct full_sockaddr_ax25); + err = sizeof (struct full_sockaddr_ax25); out: release_sock(sk); diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index 3394e6791673..66c0781773df 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -934,8 +934,8 @@ static bool is_advertising_allowed(struct hci_dev *hdev, bool connectable) /* Slave connection state and connectable mode bit 38 * and scannable bit 21. */ - if (connectable && (!(hdev->le_states[4] & 0x01) || - !(hdev->le_states[2] & 0x40))) + if (connectable && (!(hdev->le_states[4] & 0x40) || + !(hdev->le_states[2] & 0x20))) return false; } @@ -948,7 +948,7 @@ static bool is_advertising_allowed(struct hci_dev *hdev, bool connectable) /* Master connection state and connectable mode bit 35 and * scannable 19. */ - if (connectable && (!(hdev->le_states[4] & 0x10) || + if (connectable && (!(hdev->le_states[4] & 0x08) || !(hdev->le_states[2] & 0x08))) return false; } diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 923e9a271872..1506e1632394 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -1340,7 +1340,7 @@ done: } static int hci_sock_getname(struct socket *sock, struct sockaddr *addr, - int *addr_len, int peer) + int peer) { struct sockaddr_hci *haddr = (struct sockaddr_hci *)addr; struct sock *sk = sock->sk; @@ -1360,10 +1360,10 @@ static int hci_sock_getname(struct socket *sock, struct sockaddr *addr, goto done; } - *addr_len = sizeof(*haddr); haddr->hci_family = AF_BLUETOOTH; haddr->hci_dev = hdev->id; haddr->hci_channel= hci_pi(sk)->channel; + err = sizeof(*haddr); done: release_sock(sk); diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 67a8642f57ea..686bdc6b35b0 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -358,7 +358,7 @@ done: } static int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr, - int *len, int peer) + int peer) { struct sockaddr_l2 *la = (struct sockaddr_l2 *) addr; struct sock *sk = sock->sk; @@ -373,7 +373,6 @@ static int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr, memset(la, 0, sizeof(struct sockaddr_l2)); addr->sa_family = AF_BLUETOOTH; - *len = sizeof(struct sockaddr_l2); la->l2_psm = chan->psm; @@ -387,7 +386,7 @@ static int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr, la->l2_bdaddr_type = chan->src_type; } - return 0; + return sizeof(struct sockaddr_l2); } static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 1aaccf637479..93a3b219db09 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -533,7 +533,7 @@ done: return err; } -static int rfcomm_sock_getname(struct socket *sock, struct sockaddr *addr, int *len, int peer) +static int rfcomm_sock_getname(struct socket *sock, struct sockaddr *addr, int peer) { struct sockaddr_rc *sa = (struct sockaddr_rc *) addr; struct sock *sk = sock->sk; @@ -552,8 +552,7 @@ static int rfcomm_sock_getname(struct socket *sock, struct sockaddr *addr, int * else bacpy(&sa->rc_bdaddr, &rfcomm_pi(sk)->src); - *len = sizeof(struct sockaddr_rc); - return 0; + return sizeof(struct sockaddr_rc); } static int rfcomm_sock_sendmsg(struct socket *sock, struct msghdr *msg, diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 08df57665e1f..413b8ee49fec 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -680,7 +680,7 @@ done: } static int sco_sock_getname(struct socket *sock, struct sockaddr *addr, - int *len, int peer) + int peer) { struct sockaddr_sco *sa = (struct sockaddr_sco *) addr; struct sock *sk = sock->sk; @@ -688,14 +688,13 @@ static int sco_sock_getname(struct socket *sock, struct sockaddr *addr, BT_DBG("sock %p, sk %p", sock, sk); addr->sa_family = AF_BLUETOOTH; - *len = sizeof(struct sockaddr_sco); if (peer) bacpy(&sa->sco_bdaddr, &sco_pi(sk)->dst); else bacpy(&sa->sco_bdaddr, &sco_pi(sk)->src); - return 0; + return sizeof(struct sockaddr_sco); } static int sco_sock_sendmsg(struct socket *sock, struct msghdr *msg, diff --git a/net/bridge/br.c b/net/bridge/br.c index 6bf06e756df2..7770481a6506 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -188,6 +188,7 @@ static void __net_exit br_net_exit(struct net *net) static struct pernet_operations br_net_ops = { .exit = br_net_exit, + .async = true, }; static const struct stp_proto br_stp_proto = { diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 27f1d4f2114a..484f54150525 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -967,6 +967,7 @@ static struct pernet_operations brnf_net_ops __read_mostly = { .exit = brnf_exit_net, .id = &brnf_net_id, .size = sizeof(struct brnf_net), + .async = true, }; static struct notifier_block brnf_notifier __read_mostly = { diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index 0254c35b2bf0..126a8ea73c96 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -255,6 +255,9 @@ static ssize_t brport_show(struct kobject *kobj, struct brport_attribute *brport_attr = to_brport_attr(attr); struct net_bridge_port *p = to_brport(kobj); + if (!brport_attr->show) + return -EINVAL; + return brport_attr->show(p, buf); } diff --git a/net/bridge/netfilter/ebt_among.c b/net/bridge/netfilter/ebt_among.c index 279527f8b1fe..ce7152a12bd8 100644 --- a/net/bridge/netfilter/ebt_among.c +++ b/net/bridge/netfilter/ebt_among.c @@ -187,17 +187,17 @@ static int ebt_among_mt_check(const struct xt_mtchk_param *par) expected_length += ebt_mac_wormhash_size(wh_src); if (em->match_size != EBT_ALIGN(expected_length)) { - pr_info("wrong size: %d against expected %d, rounded to %zd\n", - em->match_size, expected_length, - EBT_ALIGN(expected_length)); + pr_err_ratelimited("wrong size: %d against expected %d, rounded to %zd\n", + em->match_size, expected_length, + EBT_ALIGN(expected_length)); return -EINVAL; } if (wh_dst && (err = ebt_mac_wormhash_check_integrity(wh_dst))) { - pr_info("dst integrity fail: %x\n", -err); + pr_err_ratelimited("dst integrity fail: %x\n", -err); return -EINVAL; } if (wh_src && (err = ebt_mac_wormhash_check_integrity(wh_src))) { - pr_info("src integrity fail: %x\n", -err); + pr_err_ratelimited("src integrity fail: %x\n", -err); return -EINVAL; } return 0; diff --git a/net/bridge/netfilter/ebt_limit.c b/net/bridge/netfilter/ebt_limit.c index 61a9f1be1263..165b9d678cf1 100644 --- a/net/bridge/netfilter/ebt_limit.c +++ b/net/bridge/netfilter/ebt_limit.c @@ -72,8 +72,8 @@ static int ebt_limit_mt_check(const struct xt_mtchk_param *par) /* Check for overflow. */ if (info->burst == 0 || user2credits(info->avg * info->burst) < user2credits(info->avg)) { - pr_info("overflow, try lower: %u/%u\n", - info->avg, info->burst); + pr_info_ratelimited("overflow, try lower: %u/%u\n", + info->avg, info->burst); return -EINVAL; } diff --git a/net/can/bcm.c b/net/can/bcm.c index ac5e5e34fee3..26730d39e048 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1717,6 +1717,7 @@ static void canbcm_pernet_exit(struct net *net) static struct pernet_operations canbcm_pernet_ops __read_mostly = { .init = canbcm_pernet_init, .exit = canbcm_pernet_exit, + .async = true, }; static int __init bcm_module_init(void) diff --git a/net/can/raw.c b/net/can/raw.c index f2ecc43376a1..1051eee82581 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -470,7 +470,7 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) } static int raw_getname(struct socket *sock, struct sockaddr *uaddr, - int *len, int peer) + int peer) { struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct sock *sk = sock->sk; @@ -483,9 +483,7 @@ static int raw_getname(struct socket *sock, struct sockaddr *uaddr, addr->can_family = AF_CAN; addr->can_ifindex = ro->ifindex; - *len = sizeof(*addr); - - return 0; + return sizeof(*addr); } static int raw_setsockopt(struct socket *sock, int level, int optname, diff --git a/net/core/dev.c b/net/core/dev.c index dda9d7b9a840..5bdcc5a161fe 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2382,8 +2382,11 @@ EXPORT_SYMBOL(netdev_set_num_tc); */ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) { + bool disabling; int rc; + disabling = txq < dev->real_num_tx_queues; + if (txq < 1 || txq > dev->num_tx_queues) return -EINVAL; @@ -2399,15 +2402,19 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) if (dev->num_tc) netif_setup_tc(dev, txq); - if (txq < dev->real_num_tx_queues) { + dev->real_num_tx_queues = txq; + + if (disabling) { + synchronize_net(); qdisc_reset_all_tx_gt(dev, txq); #ifdef CONFIG_XPS netif_reset_xps_queues_gt(dev, txq); #endif } + } else { + dev->real_num_tx_queues = txq; } - dev->real_num_tx_queues = txq; return 0; } EXPORT_SYMBOL(netif_set_real_num_tx_queues); @@ -8134,8 +8141,9 @@ void netdev_run_todo(void) BUG_ON(!list_empty(&dev->ptype_specific)); WARN_ON(rcu_access_pointer(dev->ip_ptr)); WARN_ON(rcu_access_pointer(dev->ip6_ptr)); +#if IS_ENABLED(CONFIG_DECNET) WARN_ON(dev->dn_ptr); - +#endif if (dev->priv_destructor) dev->priv_destructor(dev); if (dev->needs_free_netdev) @@ -8833,6 +8841,7 @@ static void __net_exit netdev_exit(struct net *net) static struct pernet_operations __net_initdata netdev_net_ops = { .init = netdev_init, .exit = netdev_exit, + .async = true, }; static void __net_exit default_device_exit(struct net *net) @@ -8933,6 +8942,7 @@ static void __net_exit default_device_exit_batch(struct list_head *net_list) static struct pernet_operations __net_initdata default_device_ops = { .exit = default_device_exit, .exit_batch = default_device_exit_batch, + .async = true, }; /* diff --git a/net/core/devlink.c b/net/core/devlink.c index 18d385ed8237..88e846779269 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -2338,6 +2338,32 @@ out: resource->size_valid = size_valid; } +static int +devlink_resource_validate_size(struct devlink_resource *resource, u64 size, + struct netlink_ext_ack *extack) +{ + u64 reminder; + int err = 0; + + if (size > resource->size_params->size_max) { + NL_SET_ERR_MSG_MOD(extack, "Size larger than maximum"); + err = -EINVAL; + } + + if (size < resource->size_params->size_min) { + NL_SET_ERR_MSG_MOD(extack, "Size smaller than minimum"); + err = -EINVAL; + } + + div64_u64_rem(size, resource->size_params->size_granularity, &reminder); + if (reminder) { + NL_SET_ERR_MSG_MOD(extack, "Wrong granularity"); + err = -EINVAL; + } + + return err; +} + static int devlink_nl_cmd_resource_set(struct sk_buff *skb, struct genl_info *info) { @@ -2356,12 +2382,8 @@ static int devlink_nl_cmd_resource_set(struct sk_buff *skb, if (!resource) return -EINVAL; - if (!resource->resource_ops->size_validate) - return -EINVAL; - size = nla_get_u64(info->attrs[DEVLINK_ATTR_RESOURCE_SIZE]); - err = resource->resource_ops->size_validate(devlink, size, - info->extack); + err = devlink_resource_validate_size(resource, size, info->extack); if (err) return err; diff --git a/net/core/fib_notifier.c b/net/core/fib_notifier.c index 0c048bdeb016..5ace0705a3f9 100644 --- a/net/core/fib_notifier.c +++ b/net/core/fib_notifier.c @@ -171,6 +171,7 @@ static void __net_exit fib_notifier_net_exit(struct net *net) static struct pernet_operations fib_notifier_net_ops = { .init = fib_notifier_net_init, .exit = fib_notifier_net_exit, + .async = true, }; static int __init fib_notifier_init(void) diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 98e1066c3d55..a6aea805a0a2 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -51,6 +51,7 @@ int fib_default_rule_add(struct fib_rules_ops *ops, r->pref = pref; r->table = table; r->flags = flags; + r->proto = RTPROT_KERNEL; r->fr_net = ops->fro_net; r->uid_range = fib_kuid_range_unset; @@ -469,6 +470,9 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, rule->pref = tb[FRA_PRIORITY] ? nla_get_u32(tb[FRA_PRIORITY]) : fib_default_rule_pref(ops); + rule->proto = tb[FRA_PROTOCOL] ? + nla_get_u8(tb[FRA_PROTOCOL]) : RTPROT_UNSPEC; + if (tb[FRA_IIFNAME]) { struct net_device *dev; @@ -664,6 +668,10 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh, } list_for_each_entry(rule, &ops->rules_list, list) { + if (tb[FRA_PROTOCOL] && + (rule->proto != nla_get_u8(tb[FRA_PROTOCOL]))) + continue; + if (frh->action && (frh->action != rule->action)) continue; @@ -781,7 +789,8 @@ static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops, + nla_total_size(4) /* FRA_FWMARK */ + nla_total_size(4) /* FRA_FWMASK */ + nla_total_size_64bit(8) /* FRA_TUN_ID */ - + nla_total_size(sizeof(struct fib_kuid_range)); + + nla_total_size(sizeof(struct fib_kuid_range)) + + nla_total_size(1); /* FRA_PROTOCOL */ if (ops->nlmsg_payload) payload += ops->nlmsg_payload(rule); @@ -812,6 +821,9 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, frh->action = rule->action; frh->flags = rule->flags; + if (nla_put_u8(skb, FRA_PROTOCOL, rule->proto)) + goto nla_put_failure; + if (rule->action == FR_ACT_GOTO && rcu_access_pointer(rule->ctarget) == NULL) frh->flags |= FIB_RULE_UNRESOLVED; @@ -1030,6 +1042,7 @@ static void __net_exit fib_rules_net_exit(struct net *net) static struct pernet_operations fib_rules_net_ops = { .init = fib_rules_net_init, .exit = fib_rules_net_exit, + .async = true, }; static int __init fib_rules_init(void) diff --git a/net/core/filter.c b/net/core/filter.c index 08ab4c65a998..0c121adbdbaa 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3381,17 +3381,13 @@ BPF_CALL_2(bpf_sock_ops_cb_flags_set, struct bpf_sock_ops_kern *, bpf_sock, struct sock *sk = bpf_sock->sk; int val = argval & BPF_SOCK_OPS_ALL_CB_FLAGS; - if (!sk_fullsock(sk)) + if (!IS_ENABLED(CONFIG_INET) || !sk_fullsock(sk)) return -EINVAL; -#ifdef CONFIG_INET if (val) tcp_sk(sk)->bpf_sock_ops_cb_flags = val; return argval & (~BPF_SOCK_OPS_ALL_CB_FLAGS); -#else - return -EINVAL; -#endif } static const struct bpf_func_proto bpf_sock_ops_cb_flags_set_proto = { diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index 0a3f88f08727..98fd12721221 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -66,6 +66,7 @@ struct net_rate_estimator { static void est_fetch_counters(struct net_rate_estimator *e, struct gnet_stats_basic_packed *b) { + memset(b, 0, sizeof(*b)); if (e->stats_lock) spin_lock(e->stats_lock); diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c index e010bb800d7b..65b51e778782 100644 --- a/net/core/net-procfs.c +++ b/net/core/net-procfs.c @@ -349,6 +349,7 @@ static void __net_exit dev_proc_net_exit(struct net *net) static struct pernet_operations __net_initdata dev_proc_ops = { .init = dev_proc_net_init, .exit = dev_proc_net_exit, + .async = true, }; static int dev_mc_seq_show(struct seq_file *seq, void *v) @@ -405,6 +406,7 @@ static void __net_exit dev_mc_net_exit(struct net *net) static struct pernet_operations __net_initdata dev_mc_net_ops = { .init = dev_mc_net_init, .exit = dev_mc_net_exit, + .async = true, }; int __init dev_proc_init(void) diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 3cad5f51afd3..690e78c6af45 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -29,7 +29,6 @@ static LIST_HEAD(pernet_list); static struct list_head *first_device = &pernet_list; -DEFINE_MUTEX(net_mutex); LIST_HEAD(net_namespace_list); EXPORT_SYMBOL_GPL(net_namespace_list); @@ -41,6 +40,12 @@ struct net init_net = { EXPORT_SYMBOL(init_net); static bool init_net_initialized; +static unsigned nr_sync_pernet_ops; +/* + * net_sem: protects: pernet_list, net_generic_ids, nr_sync_pernet_ops, + * init_net_initialized and first_device pointer. + */ +DECLARE_RWSEM(net_sem); #define MIN_PERNET_OPS_ID \ ((sizeof(struct net_generic) + sizeof(void *) - 1) / sizeof(void *)) @@ -65,11 +70,10 @@ static int net_assign_generic(struct net *net, unsigned int id, void *data) { struct net_generic *ng, *old_ng; - BUG_ON(!mutex_is_locked(&net_mutex)); BUG_ON(id < MIN_PERNET_OPS_ID); old_ng = rcu_dereference_protected(net->gen, - lockdep_is_held(&net_mutex)); + lockdep_is_held(&net_sem)); if (old_ng->s.len > id) { old_ng->ptr[id] = data; return 0; @@ -286,7 +290,7 @@ struct net *get_net_ns_by_id(struct net *net, int id) */ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) { - /* Must be called with net_mutex held */ + /* Must be called with net_sem held */ const struct pernet_operations *ops, *saved_ops; int error = 0; LIST_HEAD(net_exit_list); @@ -303,6 +307,9 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) if (error < 0) goto out_undo; } + rtnl_lock(); + list_add_tail_rcu(&net->list, &net_namespace_list); + rtnl_unlock(); out: return error; @@ -331,6 +338,7 @@ static int __net_init net_defaults_init_net(struct net *net) static struct pernet_operations net_defaults_ops = { .init = net_defaults_init_net, + .async = true, }; static __init int net_defaults_init(void) @@ -354,7 +362,7 @@ static void dec_net_namespaces(struct ucounts *ucounts) dec_ucount(ucounts, UCOUNT_NET_NAMESPACES); } -static struct kmem_cache *net_cachep; +static struct kmem_cache *net_cachep __ro_after_init; static struct workqueue_struct *netns_wq; static struct net *net_alloc(void) @@ -397,6 +405,7 @@ struct net *copy_net_ns(unsigned long flags, { struct ucounts *ucounts; struct net *net; + unsigned write; int rv; if (!(flags & CLONE_NEWNET)) @@ -408,32 +417,38 @@ struct net *copy_net_ns(unsigned long flags, net = net_alloc(); if (!net) { - dec_net_namespaces(ucounts); - return ERR_PTR(-ENOMEM); + rv = -ENOMEM; + goto dec_ucounts; } - + refcount_set(&net->passive, 1); + net->ucounts = ucounts; get_user_ns(user_ns); +again: + write = READ_ONCE(nr_sync_pernet_ops); + if (write) + rv = down_write_killable(&net_sem); + else + rv = down_read_killable(&net_sem); + if (rv < 0) + goto put_userns; - rv = mutex_lock_killable(&net_mutex); - if (rv < 0) { - net_free(net); - dec_net_namespaces(ucounts); - put_user_ns(user_ns); - return ERR_PTR(rv); + if (!write && unlikely(READ_ONCE(nr_sync_pernet_ops))) { + up_read(&net_sem); + goto again; } - - net->ucounts = ucounts; rv = setup_net(net, user_ns); - if (rv == 0) { - rtnl_lock(); - list_add_tail_rcu(&net->list, &net_namespace_list); - rtnl_unlock(); - } - mutex_unlock(&net_mutex); + + if (write) + up_write(&net_sem); + else + up_read(&net_sem); + if (rv < 0) { - dec_net_namespaces(ucounts); +put_userns: put_user_ns(user_ns); net_drop_ns(net); +dec_ucounts: + dec_net_namespaces(ucounts); return ERR_PTR(rv); } return net; @@ -466,26 +481,33 @@ static void unhash_nsid(struct net *net, struct net *last) spin_unlock_bh(&net->nsid_lock); } -static DEFINE_SPINLOCK(cleanup_list_lock); -static LIST_HEAD(cleanup_list); /* Must hold cleanup_list_lock to touch */ +static LLIST_HEAD(cleanup_list); static void cleanup_net(struct work_struct *work) { const struct pernet_operations *ops; struct net *net, *tmp, *last; - struct list_head net_kill_list; + struct llist_node *net_kill_list; LIST_HEAD(net_exit_list); + unsigned write; /* Atomically snapshot the list of namespaces to cleanup */ - spin_lock_irq(&cleanup_list_lock); - list_replace_init(&cleanup_list, &net_kill_list); - spin_unlock_irq(&cleanup_list_lock); + net_kill_list = llist_del_all(&cleanup_list); +again: + write = READ_ONCE(nr_sync_pernet_ops); + if (write) + down_write(&net_sem); + else + down_read(&net_sem); - mutex_lock(&net_mutex); + if (!write && unlikely(READ_ONCE(nr_sync_pernet_ops))) { + up_read(&net_sem); + goto again; + } /* Don't let anyone else find us. */ rtnl_lock(); - list_for_each_entry(net, &net_kill_list, cleanup_list) + llist_for_each_entry(net, net_kill_list, cleanup_list) list_del_rcu(&net->list); /* Cache last net. After we unlock rtnl, no one new net * added to net_namespace_list can assign nsid pointer @@ -500,7 +522,7 @@ static void cleanup_net(struct work_struct *work) last = list_last_entry(&net_namespace_list, struct net, list); rtnl_unlock(); - list_for_each_entry(net, &net_kill_list, cleanup_list) { + llist_for_each_entry(net, net_kill_list, cleanup_list) { unhash_nsid(net, last); list_add_tail(&net->exit_list, &net_exit_list); } @@ -520,7 +542,10 @@ static void cleanup_net(struct work_struct *work) list_for_each_entry_reverse(ops, &pernet_list, list) ops_free_list(ops, &net_exit_list); - mutex_unlock(&net_mutex); + if (write) + up_write(&net_sem); + else + up_read(&net_sem); /* Ensure there are no outstanding rcu callbacks using this * network namespace. @@ -547,8 +572,8 @@ static void cleanup_net(struct work_struct *work) */ void net_ns_barrier(void) { - mutex_lock(&net_mutex); - mutex_unlock(&net_mutex); + down_write(&net_sem); + up_write(&net_sem); } EXPORT_SYMBOL(net_ns_barrier); @@ -557,13 +582,8 @@ static DECLARE_WORK(net_cleanup_work, cleanup_net); void __put_net(struct net *net) { /* Cleanup the network namespace in process context */ - unsigned long flags; - - spin_lock_irqsave(&cleanup_list_lock, flags); - list_add(&net->cleanup_list, &cleanup_list); - spin_unlock_irqrestore(&cleanup_list_lock, flags); - - queue_work(netns_wq, &net_cleanup_work); + if (llist_add(&net->cleanup_list, &cleanup_list)) + queue_work(netns_wq, &net_cleanup_work); } EXPORT_SYMBOL_GPL(__put_net); @@ -633,6 +653,7 @@ static __net_exit void net_ns_net_exit(struct net *net) static struct pernet_operations __net_initdata net_ns_ops = { .init = net_ns_net_init, .exit = net_ns_net_exit, + .async = true, }; static const struct nla_policy rtnl_net_policy[NETNSA_MAX + 1] = { @@ -875,17 +896,12 @@ static int __init net_ns_init(void) rcu_assign_pointer(init_net.gen, ng); - mutex_lock(&net_mutex); + down_write(&net_sem); if (setup_net(&init_net, &init_user_ns)) panic("Could not setup the initial network namespace"); init_net_initialized = true; - - rtnl_lock(); - list_add_tail_rcu(&init_net.list, &net_namespace_list); - rtnl_unlock(); - - mutex_unlock(&net_mutex); + up_write(&net_sem); register_pernet_subsys(&net_ns_ops); @@ -989,6 +1005,9 @@ again: rcu_barrier(); if (ops->id) ida_remove(&net_generic_ids, *ops->id); + } else if (!ops->async) { + pr_info_once("Pernet operations %ps are sync.\n", ops); + nr_sync_pernet_ops++; } return error; @@ -996,7 +1015,8 @@ again: static void unregister_pernet_operations(struct pernet_operations *ops) { - + if (!ops->async) + BUG_ON(nr_sync_pernet_ops-- == 0); __unregister_pernet_operations(ops); rcu_barrier(); if (ops->id) @@ -1025,9 +1045,9 @@ static void unregister_pernet_operations(struct pernet_operations *ops) int register_pernet_subsys(struct pernet_operations *ops) { int error; - mutex_lock(&net_mutex); + down_write(&net_sem); error = register_pernet_operations(first_device, ops); - mutex_unlock(&net_mutex); + up_write(&net_sem); return error; } EXPORT_SYMBOL_GPL(register_pernet_subsys); @@ -1043,9 +1063,9 @@ EXPORT_SYMBOL_GPL(register_pernet_subsys); */ void unregister_pernet_subsys(struct pernet_operations *ops) { - mutex_lock(&net_mutex); + down_write(&net_sem); unregister_pernet_operations(ops); - mutex_unlock(&net_mutex); + up_write(&net_sem); } EXPORT_SYMBOL_GPL(unregister_pernet_subsys); @@ -1071,11 +1091,11 @@ EXPORT_SYMBOL_GPL(unregister_pernet_subsys); int register_pernet_device(struct pernet_operations *ops) { int error; - mutex_lock(&net_mutex); + down_write(&net_sem); error = register_pernet_operations(&pernet_list, ops); if (!error && (first_device == &pernet_list)) first_device = &ops->list; - mutex_unlock(&net_mutex); + up_write(&net_sem); return error; } EXPORT_SYMBOL_GPL(register_pernet_device); @@ -1091,11 +1111,11 @@ EXPORT_SYMBOL_GPL(register_pernet_device); */ void unregister_pernet_device(struct pernet_operations *ops) { - mutex_lock(&net_mutex); + down_write(&net_sem); if (&ops->list == first_device) first_device = first_device->next; unregister_pernet_operations(ops); - mutex_unlock(&net_mutex); + up_write(&net_sem); } EXPORT_SYMBOL_GPL(unregister_pernet_device); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index bc290413a49d..67f375cfb982 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -454,11 +454,11 @@ static void rtnl_lock_unregistering_all(void) void rtnl_link_unregister(struct rtnl_link_ops *ops) { /* Close the race with cleanup_net() */ - mutex_lock(&net_mutex); + down_write(&net_sem); rtnl_lock_unregistering_all(); __rtnl_link_unregister(ops); rtnl_unlock(); - mutex_unlock(&net_mutex); + up_write(&net_sem); } EXPORT_SYMBOL_GPL(rtnl_link_unregister); @@ -4724,6 +4724,7 @@ static void __net_exit rtnetlink_net_exit(struct net *net) static struct pernet_operations rtnetlink_net_ops = { .init = rtnetlink_net_init, .exit = rtnetlink_net_exit, + .async = true, }; void __init rtnetlink_init(void) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 09bd89c90a71..96d36b81a3a5 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -77,8 +77,8 @@ #include <linux/capability.h> #include <linux/user_namespace.h> -struct kmem_cache *skbuff_head_cache __read_mostly; -static struct kmem_cache *skbuff_fclone_cache __read_mostly; +struct kmem_cache *skbuff_head_cache __ro_after_init; +static struct kmem_cache *skbuff_fclone_cache __ro_after_init; int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS; EXPORT_SYMBOL(sysctl_max_skb_frags); @@ -890,7 +890,7 @@ struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src) } EXPORT_SYMBOL_GPL(skb_morph); -static int mm_account_pinned_pages(struct mmpin *mmp, size_t size) +int mm_account_pinned_pages(struct mmpin *mmp, size_t size) { unsigned long max_pg, num_pg, new_pg, old_pg; struct user_struct *user; @@ -919,14 +919,16 @@ static int mm_account_pinned_pages(struct mmpin *mmp, size_t size) return 0; } +EXPORT_SYMBOL_GPL(mm_account_pinned_pages); -static void mm_unaccount_pinned_pages(struct mmpin *mmp) +void mm_unaccount_pinned_pages(struct mmpin *mmp) { if (mmp->user) { atomic_long_sub(mmp->num_pg, &mmp->user->locked_vm); free_uid(mmp->user); } } +EXPORT_SYMBOL_GPL(mm_unaccount_pinned_pages); struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size) { diff --git a/net/core/sock.c b/net/core/sock.c index c501499a04fe..507d8c6c4319 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1049,18 +1049,21 @@ set_rcvbuf: break; case SO_ZEROCOPY: - if (sk->sk_family != PF_INET && sk->sk_family != PF_INET6) + if (sk->sk_family == PF_INET || sk->sk_family == PF_INET6) { + if (sk->sk_protocol != IPPROTO_TCP) + ret = -ENOTSUPP; + else if (sk->sk_state != TCP_CLOSE) + ret = -EBUSY; + } else if (sk->sk_family != PF_RDS) { ret = -ENOTSUPP; - else if (sk->sk_protocol != IPPROTO_TCP) - ret = -ENOTSUPP; - else if (sk->sk_state != TCP_CLOSE) - ret = -EBUSY; - else if (val < 0 || val > 1) - ret = -EINVAL; - else - sock_valbool_flag(sk, SOCK_ZEROCOPY, valbool); - break; - + } + if (!ret) { + if (val < 0 || val > 1) + ret = -EINVAL; + else + sock_valbool_flag(sk, SOCK_ZEROCOPY, valbool); + break; + } default: ret = -ENOPROTOOPT; break; @@ -1274,7 +1277,8 @@ int sock_getsockopt(struct socket *sock, int level, int optname, { char address[128]; - if (sock->ops->getname(sock, (struct sockaddr *)address, &lv, 2)) + lv = sock->ops->getname(sock, (struct sockaddr *)address, 2); + if (lv < 0) return -ENOTCONN; if (lv < len) return -EINVAL; @@ -1773,7 +1777,7 @@ 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; + sk->sk_route_caps = dst->dev->features | sk->sk_route_forced_caps; if (sk->sk_route_caps & NETIF_F_GSO) sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE; sk->sk_route_caps &= ~sk->sk_route_nocaps; @@ -2497,7 +2501,7 @@ int sock_no_accept(struct socket *sock, struct socket *newsock, int flags, EXPORT_SYMBOL(sock_no_accept); int sock_no_getname(struct socket *sock, struct sockaddr *saddr, - int *len, int peer) + int peer) { return -EOPNOTSUPP; } @@ -3111,6 +3115,7 @@ static void __net_exit sock_inuse_exit_net(struct net *net) static struct pernet_operations net_inuse_ops = { .init = sock_inuse_init_net, .exit = sock_inuse_exit_net, + .async = true, }; static __init int net_inuse_init(void) @@ -3384,6 +3389,7 @@ static __net_exit void proto_exit_net(struct net *net) static __net_initdata struct pernet_operations proto_net_ops = { .init = proto_init_net, .exit = proto_exit_net, + .async = true, }; static int __init proto_init(void) diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index 146b50e30659..aee5642affd9 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -328,6 +328,7 @@ static void __net_exit diag_net_exit(struct net *net) static struct pernet_operations diag_net_ops = { .init = diag_net_init, .exit = diag_net_exit, + .async = true, }; static int __init sock_diag_init(void) diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index f2d0462611c3..d714f65782b7 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -572,6 +572,7 @@ static __net_exit void sysctl_core_net_exit(struct net *net) static __net_initdata struct pernet_operations sysctl_core_ops = { .init = sysctl_core_net_init, .exit = sysctl_core_net_exit, + .async = true, }; static __init int sysctl_core_init(void) diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 91dd09f79808..2ee8306c23e3 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -1180,14 +1180,12 @@ static int dn_accept(struct socket *sock, struct socket *newsock, int flags, } -static int dn_getname(struct socket *sock, struct sockaddr *uaddr,int *uaddr_len,int peer) +static int dn_getname(struct socket *sock, struct sockaddr *uaddr,int peer) { struct sockaddr_dn *sa = (struct sockaddr_dn *)uaddr; struct sock *sk = sock->sk; struct dn_scp *scp = DN_SK(sk); - *uaddr_len = sizeof(struct sockaddr_dn); - lock_sock(sk); if (peer) { @@ -1205,7 +1203,7 @@ static int dn_getname(struct socket *sock, struct sockaddr *uaddr,int *uaddr_len release_sock(sk); - return 0; + return sizeof(struct sockaddr_dn); } @@ -1338,6 +1336,12 @@ static int dn_setsockopt(struct socket *sock, int level, int optname, char __use lock_sock(sk); err = __dn_setsockopt(sock, level, optname, optval, optlen, 0); release_sock(sk); +#ifdef CONFIG_NETFILTER + /* we need to exclude all possible ENOPROTOOPTs except default case */ + if (err == -ENOPROTOOPT && optname != DSO_LINKINFO && + optname != DSO_STREAM && optname != DSO_SEQPACKET) + err = nf_setsockopt(sk, PF_DECnet, optname, optval, optlen); +#endif return err; } @@ -1445,15 +1449,6 @@ static int __dn_setsockopt(struct socket *sock, int level,int optname, char __us dn_nsp_send_disc(sk, 0x38, 0, sk->sk_allocation); break; - default: -#ifdef CONFIG_NETFILTER - return nf_setsockopt(sk, PF_DECnet, optname, optval, optlen); -#endif - case DSO_LINKINFO: - case DSO_STREAM: - case DSO_SEQPACKET: - return -ENOPROTOOPT; - case DSO_MAXWINDOW: if (optlen != sizeof(unsigned long)) return -EINVAL; @@ -1501,6 +1496,12 @@ static int __dn_setsockopt(struct socket *sock, int level,int optname, char __us return -EINVAL; scp->info_loc = u.info; break; + + case DSO_LINKINFO: + case DSO_STREAM: + case DSO_SEQPACKET: + default: + return -ENOPROTOOPT; } return 0; @@ -1514,6 +1515,20 @@ static int dn_getsockopt(struct socket *sock, int level, int optname, char __use lock_sock(sk); err = __dn_getsockopt(sock, level, optname, optval, optlen, 0); release_sock(sk); +#ifdef CONFIG_NETFILTER + if (err == -ENOPROTOOPT && optname != DSO_STREAM && + optname != DSO_SEQPACKET && optname != DSO_CONACCEPT && + optname != DSO_CONREJECT) { + int len; + + if (get_user(len, optlen)) + return -EFAULT; + + err = nf_getsockopt(sk, PF_DECnet, optname, optval, &len); + if (err >= 0) + err = put_user(len, optlen); + } +#endif return err; } @@ -1579,26 +1594,6 @@ static int __dn_getsockopt(struct socket *sock, int level,int optname, char __us r_data = &link; break; - default: -#ifdef CONFIG_NETFILTER - { - int ret, len; - - if (get_user(len, optlen)) - return -EFAULT; - - ret = nf_getsockopt(sk, PF_DECnet, optname, optval, &len); - if (ret >= 0) - ret = put_user(len, optlen); - return ret; - } -#endif - case DSO_STREAM: - case DSO_SEQPACKET: - case DSO_CONACCEPT: - case DSO_CONREJECT: - return -ENOPROTOOPT; - case DSO_MAXWINDOW: if (r_len > sizeof(unsigned long)) r_len = sizeof(unsigned long); @@ -1630,6 +1625,13 @@ static int __dn_getsockopt(struct socket *sock, int level,int optname, char __us r_len = sizeof(unsigned char); r_data = &scp->info_rem; break; + + case DSO_STREAM: + case DSO_SEQPACKET: + case DSO_CONACCEPT: + case DSO_CONREJECT: + default: + return -ENOPROTOOPT; } if (r_data) { diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 6a9d0f50fbee..e63c554e0623 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -23,6 +23,7 @@ #include <linux/netdevice.h> #include <linux/sysfs.h> #include <linux/phy_fixed.h> +#include <linux/ptp_classify.h> #include <linux/gpio/consumer.h> #include <linux/etherdevice.h> @@ -122,6 +123,38 @@ struct net_device *dsa_dev_to_net_device(struct device *dev) } EXPORT_SYMBOL_GPL(dsa_dev_to_net_device); +/* Determine if we should defer delivery of skb until we have a rx timestamp. + * + * Called from dsa_switch_rcv. For now, this will only work if tagging is + * enabled on the switch. Normally the MAC driver would retrieve the hardware + * timestamp when it reads the packet out of the hardware. However in a DSA + * switch, the DSA driver owning the interface to which the packet is + * delivered is never notified unless we do so here. + */ +static bool dsa_skb_defer_rx_timestamp(struct dsa_slave_priv *p, + struct sk_buff *skb) +{ + struct dsa_switch *ds = p->dp->ds; + unsigned int type; + + if (skb_headroom(skb) < ETH_HLEN) + return false; + + __skb_push(skb, ETH_HLEN); + + type = ptp_classify_raw(skb); + + __skb_pull(skb, ETH_HLEN); + + if (type == PTP_CLASS_NONE) + return false; + + if (likely(ds->ops->port_rxtstamp)) + return ds->ops->port_rxtstamp(ds, p->dp->index, skb, type); + + return false; +} + static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *unused) { @@ -157,6 +190,9 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, s->rx_bytes += skb->len; u64_stats_update_end(&s->syncp); + if (dsa_skb_defer_rx_timestamp(p, skb)) + return 0; + netif_receive_skb(skb); return 0; diff --git a/net/dsa/slave.c b/net/dsa/slave.c index f52307296de4..3376dad6dcfd 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -21,6 +21,7 @@ #include <net/tc_act/tc_mirred.h> #include <linux/if_bridge.h> #include <linux/netpoll.h> +#include <linux/ptp_classify.h> #include "dsa_priv.h" @@ -255,6 +256,22 @@ dsa_slave_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { + struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_switch *ds = p->dp->ds; + int port = p->dp->index; + + /* Pass through to switch driver if it supports timestamping */ + switch (cmd) { + case SIOCGHWTSTAMP: + if (ds->ops->port_hwtstamp_get) + return ds->ops->port_hwtstamp_get(ds, port, ifr); + break; + case SIOCSHWTSTAMP: + if (ds->ops->port_hwtstamp_set) + return ds->ops->port_hwtstamp_set(ds, port, ifr); + break; + } + if (!dev->phydev) return -ENODEV; @@ -385,6 +402,30 @@ static inline netdev_tx_t dsa_slave_netpoll_send_skb(struct net_device *dev, return NETDEV_TX_OK; } +static void dsa_skb_tx_timestamp(struct dsa_slave_priv *p, + struct sk_buff *skb) +{ + struct dsa_switch *ds = p->dp->ds; + struct sk_buff *clone; + unsigned int type; + + type = ptp_classify_raw(skb); + if (type == PTP_CLASS_NONE) + return; + + if (!ds->ops->port_txtstamp) + return; + + clone = skb_clone_sk(skb); + if (!clone) + return; + + if (ds->ops->port_txtstamp(ds, p->dp->index, clone, type)) + return; + + kfree_skb(clone); +} + static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); @@ -397,6 +438,11 @@ static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev) s->tx_bytes += skb->len; u64_stats_update_end(&s->syncp); + /* Identify PTP protocol packets, clone them, and pass them to the + * switch driver + */ + dsa_skb_tx_timestamp(p, skb); + /* Transmit function may have to reallocate the original SKB, * in which case it must have freed it. Only free it here on error. */ @@ -918,6 +964,18 @@ static int dsa_slave_set_rxnfc(struct net_device *dev, return ds->ops->set_rxnfc(ds, dp->index, nfc); } +static int dsa_slave_get_ts_info(struct net_device *dev, + struct ethtool_ts_info *ts) +{ + struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_switch *ds = p->dp->ds; + + if (!ds->ops->get_ts_info) + return -EOPNOTSUPP; + + return ds->ops->get_ts_info(ds, p->dp->index, ts); +} + static const struct ethtool_ops dsa_slave_ethtool_ops = { .get_drvinfo = dsa_slave_get_drvinfo, .get_regs_len = dsa_slave_get_regs_len, @@ -938,6 +996,7 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = { .set_link_ksettings = phy_ethtool_set_link_ksettings, .get_rxnfc = dsa_slave_get_rxnfc, .set_rxnfc = dsa_slave_set_rxnfc, + .get_ts_info = dsa_slave_get_ts_info, }; /* legacy way, bypassing the bridge *****************************************/ diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c index 974765b7d92a..e4f305320519 100644 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@ -104,6 +104,7 @@ static void lowpan_setup(struct net_device *ldev) /* We need an ipv6hdr as minimum len when calling xmit */ ldev->hard_header_len = sizeof(struct ipv6hdr); ldev->flags = IFF_BROADCAST | IFF_MULTICAST; + ldev->priv_flags |= IFF_NO_QUEUE; ldev->netdev_ops = &lowpan_netdev_ops; ldev->header_ops = &lowpan_header_ops; diff --git a/net/ieee802154/core.c b/net/ieee802154/core.c index cb7176cd4cd6..9104943c15ba 100644 --- a/net/ieee802154/core.c +++ b/net/ieee802154/core.c @@ -345,6 +345,7 @@ static void __net_exit cfg802154_pernet_exit(struct net *net) static struct pernet_operations cfg802154_pernet_ops = { .exit = cfg802154_pernet_exit, + .async = true, }; static int __init wpan_phy_class_init(void) diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index e4329e161943..e8c7fad8c329 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -723,7 +723,7 @@ EXPORT_SYMBOL(inet_accept); * This does both peername and sockname. */ int inet_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); @@ -745,8 +745,7 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr, sin->sin_addr.s_addr = addr; } memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); - *uaddr_len = sizeof(*sin); - return 0; + return sizeof(*sin); } EXPORT_SYMBOL(inet_getname); @@ -1736,6 +1735,7 @@ static __net_exit void ipv4_mib_exit_net(struct net *net) static __net_initdata struct pernet_operations ipv4_mib_ops = { .init = ipv4_mib_init_net, .exit = ipv4_mib_exit_net, + .async = true, }; static int __init init_ipv4_mibs(void) @@ -1789,6 +1789,7 @@ static __net_exit void inet_exit_net(struct net *net) static __net_initdata struct pernet_operations af_inet_ops = { .init = inet_init_net, .exit = inet_exit_net, + .async = true, }; static int __init init_inet_pernet_ops(void) diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index f28f06c91ead..7dc9de8444a9 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1447,6 +1447,7 @@ static void __net_exit arp_net_exit(struct net *net) static struct pernet_operations arp_net_ops = { .init = arp_net_init, .exit = arp_net_exit, + .async = true, }; static int __init arp_proc_init(void) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 40f001782c1b..5ae0d1f097ca 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -2469,6 +2469,7 @@ static __net_exit void devinet_exit_net(struct net *net) static __net_initdata struct pernet_operations devinet_ops = { .init = devinet_init_net, .exit = devinet_exit_net, + .async = true, }; static struct rtnl_af_ops inet_af_ops __read_mostly = { diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index f05afaf3235c..ac71c3d496c0 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1362,6 +1362,7 @@ static void __net_exit fib_net_exit(struct net *net) static struct pernet_operations fib_net_ops = { .init = fib_net_init, .exit = fib_net_exit, + .async = true, }; void __init ip_fib_init(void) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index c586597da20d..cd46d7666598 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -646,6 +646,11 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi, fi->fib_nh, cfg, extack)) return 1; } +#ifdef CONFIG_IP_ROUTE_CLASSID + if (cfg->fc_flow && + cfg->fc_flow != fi->fib_nh->nh_tclassid) + return 1; +#endif if ((!cfg->fc_oif || cfg->fc_oif == fi->fib_nh->nh_oif) && (!cfg->fc_gw || cfg->fc_gw == fi->fib_nh->nh_gw)) return 0; @@ -1760,13 +1765,11 @@ void fib_select_multipath(struct fib_result *res, int hash) void fib_select_path(struct net *net, struct fib_result *res, struct flowi4 *fl4, const struct sk_buff *skb) { - bool oif_check; - - oif_check = (fl4->flowi4_oif == 0 || - fl4->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF); + if (fl4->flowi4_oif && !(fl4->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF)) + goto check_saddr; #ifdef CONFIG_IP_ROUTE_MULTIPATH - if (res->fi->fib_nhs > 1 && oif_check) { + if (res->fi->fib_nhs > 1) { int h = fib_multipath_hash(res->fi, fl4, skb); fib_select_multipath(res, h); @@ -1775,10 +1778,10 @@ void fib_select_path(struct net *net, struct fib_result *res, #endif if (!res->prefixlen && res->table->tb_num_default > 1 && - res->type == RTN_UNICAST && oif_check) + res->type == RTN_UNICAST) fib_select_default(fl4, res); +check_saddr: if (!fl4->saddr) fl4->saddr = FIB_RES_PREFSRC(net, *res); } -EXPORT_SYMBOL_GPL(fib_select_path); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 5530cd6fdbc7..62243a8abf92 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -50,6 +50,7 @@ #define VERSION "0.409" +#include <linux/cache.h> #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/types.h> @@ -191,8 +192,8 @@ static size_t tnode_free_size; */ static const int sync_pages = 128; -static struct kmem_cache *fn_alias_kmem __read_mostly; -static struct kmem_cache *trie_leaf_kmem __read_mostly; +static struct kmem_cache *fn_alias_kmem __ro_after_init; +static struct kmem_cache *trie_leaf_kmem __ro_after_init; static inline struct tnode *tn_info(struct key_vector *kv) { diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 1617604c9284..cc56efa64d5c 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -1257,6 +1257,7 @@ fail: static struct pernet_operations __net_initdata icmp_sk_ops = { .init = icmp_sk_init, .exit = icmp_sk_exit, + .async = true, }; int __init icmp_init(void) diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index f2402581fef1..c2743763777e 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -3028,6 +3028,7 @@ static void __net_exit igmp_net_exit(struct net *net) static struct pernet_operations igmp_net_ops = { .init = igmp_net_init, .exit = igmp_net_exit, + .async = true, }; #endif diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index 914d56928578..1f04bd91fc2e 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -6,6 +6,7 @@ * Authors: Andrey V. Savochkin <saw@msu.ru> */ +#include <linux/cache.h> #include <linux/module.h> #include <linux/types.h> #include <linux/slab.h> @@ -51,7 +52,7 @@ * daddr: unchangeable */ -static struct kmem_cache *peer_cachep __read_mostly; +static struct kmem_cache *peer_cachep __ro_after_init; void inet_peer_base_init(struct inet_peer_base *bp) { diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index bbf1b94942c0..5e843ae5e468 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -885,6 +885,7 @@ static void __net_exit ipv4_frags_exit_net(struct net *net) static struct pernet_operations ip4_frags_ops = { .init = ipv4_frags_init_net, .exit = ipv4_frags_exit_net, + .async = true, }; void __init ipfrag_init(void) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 45d97e9b2759..0fe1d69b5df4 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1044,6 +1044,7 @@ static struct pernet_operations ipgre_net_ops = { .exit_batch = ipgre_exit_batch_net, .id = &ipgre_net_id, .size = sizeof(struct ip_tunnel_net), + .async = true, }; static int ipgre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], @@ -1322,6 +1323,12 @@ static void ipgre_tap_setup(struct net_device *dev) ip_tunnel_setup(dev, gre_tap_net_id); } +bool is_gretap_dev(const struct net_device *dev) +{ + return dev->netdev_ops == &gre_tap_netdev_ops; +} +EXPORT_SYMBOL_GPL(is_gretap_dev); + static int ipgre_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) @@ -1623,6 +1630,7 @@ static struct pernet_operations ipgre_tap_net_ops = { .exit_batch = ipgre_tap_exit_batch_net, .id = &gre_tap_net_id, .size = sizeof(struct ip_tunnel_net), + .async = true, }; static int __net_init erspan_init_net(struct net *net) @@ -1641,6 +1649,7 @@ static struct pernet_operations erspan_net_ops = { .exit_batch = erspan_exit_batch_net, .id = &erspan_net_id, .size = sizeof(struct ip_tunnel_net), + .async = true, }; static int __init ipgre_init(void) diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 008be04ac1cc..74c962b9b09c 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -258,7 +258,8 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg); if (!ipv6_addr_v4mapped(&src_info->ipi6_addr)) return -EINVAL; - ipc->oif = src_info->ipi6_ifindex; + if (src_info->ipi6_ifindex) + ipc->oif = src_info->ipi6_ifindex; ipc->addr = src_info->ipi6_addr.s6_addr32[3]; continue; } @@ -288,7 +289,8 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct in_pktinfo))) return -EINVAL; info = (struct in_pktinfo *)CMSG_DATA(cmsg); - ipc->oif = info->ipi_ifindex; + if (info->ipi_ifindex) + ipc->oif = info->ipi_ifindex; ipc->addr = info->ipi_spec_dst.s_addr; break; } @@ -1567,10 +1569,7 @@ int ip_getsockopt(struct sock *sk, int level, if (get_user(len, optlen)) return -EFAULT; - lock_sock(sk); - err = nf_getsockopt(sk, PF_INET, optname, optval, - &len); - release_sock(sk); + err = nf_getsockopt(sk, PF_INET, optname, optval, &len); if (err >= 0) err = put_user(len, optlen); return err; @@ -1602,9 +1601,7 @@ int compat_ip_getsockopt(struct sock *sk, int level, int optname, if (get_user(len, optlen)) return -EFAULT; - lock_sock(sk); err = compat_nf_getsockopt(sk, PF_INET, optname, optval, &len); - release_sock(sk); if (err >= 0) err = put_user(len, optlen); return err; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index d786a8441bce..b2117d89bc83 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -290,22 +290,6 @@ failed: return ERR_PTR(err); } -static inline void init_tunnel_flow(struct flowi4 *fl4, - int proto, - __be32 daddr, __be32 saddr, - __be32 key, __u8 tos, int oif, - __u32 mark) -{ - memset(fl4, 0, sizeof(*fl4)); - fl4->flowi4_oif = oif; - fl4->daddr = daddr; - fl4->saddr = saddr; - fl4->flowi4_tos = tos; - fl4->flowi4_proto = proto; - fl4->fl4_gre_key = key; - fl4->flowi4_mark = mark; -} - static int ip_tunnel_bind_dev(struct net_device *dev) { struct net_device *tdev = NULL; @@ -322,10 +306,10 @@ static int ip_tunnel_bind_dev(struct net_device *dev) struct flowi4 fl4; struct rtable *rt; - init_tunnel_flow(&fl4, iph->protocol, iph->daddr, - iph->saddr, tunnel->parms.o_key, - RT_TOS(iph->tos), tunnel->parms.link, - tunnel->fwmark); + ip_tunnel_init_flow(&fl4, iph->protocol, iph->daddr, + iph->saddr, tunnel->parms.o_key, + RT_TOS(iph->tos), tunnel->parms.link, + tunnel->fwmark); rt = ip_route_output_key(tunnel->net, &fl4); if (!IS_ERR(rt)) { @@ -581,8 +565,8 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto) else if (skb->protocol == htons(ETH_P_IPV6)) tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph); } - init_tunnel_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, 0, - RT_TOS(tos), tunnel->parms.link, tunnel->fwmark); + ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, 0, + RT_TOS(tos), tunnel->parms.link, tunnel->fwmark); if (tunnel->encap.type != TUNNEL_ENCAP_NONE) goto tx_error; rt = ip_route_output_key(tunnel->net, &fl4); @@ -711,14 +695,14 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, } if (tunnel->fwmark) { - init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr, - tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link, - tunnel->fwmark); + ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr, + tunnel->parms.o_key, RT_TOS(tos), + tunnel->parms.link, tunnel->fwmark); } else { - init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr, - tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link, - skb->mark); + ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr, + tunnel->parms.o_key, RT_TOS(tos), + tunnel->parms.link, skb->mark); } if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0) diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 51b1669334fe..b10bf563afd9 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -454,6 +454,7 @@ static struct pernet_operations vti_net_ops = { .exit_batch = vti_exit_batch_net, .id = &vti_net_id, .size = sizeof(struct ip_tunnel_net), + .async = true, }; static int vti_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index c891235b4966..9c5a4d164f09 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -669,6 +669,7 @@ static struct pernet_operations ipip_net_ops = { .exit_batch = ipip_exit_batch_net, .id = &ipip_net_id, .size = sizeof(struct ip_tunnel_net), + .async = true, }; static int __init ipip_init(void) diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index b05689bbba31..591d1fc80a1f 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -28,6 +28,7 @@ #include <linux/uaccess.h> #include <linux/types.h> +#include <linux/cache.h> #include <linux/capability.h> #include <linux/errno.h> #include <linux/timer.h> @@ -96,7 +97,7 @@ static DEFINE_SPINLOCK(mfc_unres_lock); * In this case data path is free of exclusive locks at all. */ -static struct kmem_cache *mrt_cachep __read_mostly; +static struct kmem_cache *mrt_cachep __ro_after_init; static struct mr_table *ipmr_new_table(struct net *net, u32 id); static void ipmr_free_table(struct mr_table *mrt); @@ -3327,6 +3328,7 @@ static void __net_exit ipmr_net_exit(struct net *net) static struct pernet_operations ipmr_net_ops = { .init = ipmr_net_init, .exit = ipmr_net_exit, + .async = true, }; int __init ip_mr_init(void) diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 4ffe302f9b82..e3e420f3ba7b 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -252,6 +252,10 @@ unsigned int arpt_do_table(struct sk_buff *skb, } if (table_base + v != arpt_next_entry(e)) { + if (unlikely(stackidx >= private->stacksize)) { + verdict = NF_DROP; + break; + } jumpstack[stackidx++] = e; } diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 9a71f3149507..d4f7584d2dbe 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -330,8 +330,13 @@ ipt_do_table(struct sk_buff *skb, continue; } if (table_base + v != ipt_next_entry(e) && - !(e->ip.flags & IPT_F_GOTO)) + !(e->ip.flags & IPT_F_GOTO)) { + if (unlikely(stackidx >= private->stacksize)) { + verdict = NF_DROP; + break; + } jumpstack[stackidx++] = e; + } e = get_entry(table_base, v); continue; @@ -1911,6 +1916,7 @@ static void __net_exit ip_tables_net_exit(struct net *net) static struct pernet_operations ip_tables_net_ops = { .init = ip_tables_net_init, .exit = ip_tables_net_exit, + .async = true, }; static int __init ip_tables_init(void) diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 3a84a60f6b39..08b3e48f44fc 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -107,12 +107,6 @@ clusterip_config_entry_put(struct net *net, struct clusterip_config *c) local_bh_disable(); if (refcount_dec_and_lock(&c->entries, &cn->lock)) { - list_del_rcu(&c->list); - spin_unlock(&cn->lock); - local_bh_enable(); - - unregister_netdevice_notifier(&c->notifier); - /* In case anyone still accesses the file, the open/close * functions are also incrementing the refcount on their own, * so it's safe to remove the entry even if it's in use. */ @@ -120,6 +114,12 @@ clusterip_config_entry_put(struct net *net, struct clusterip_config *c) if (cn->procdir) proc_remove(c->pde); #endif + list_del_rcu(&c->list); + spin_unlock(&cn->lock); + local_bh_enable(); + + unregister_netdevice_notifier(&c->notifier); + return; } local_bh_enable(); @@ -154,8 +154,12 @@ clusterip_config_find_get(struct net *net, __be32 clusterip, int entry) #endif if (unlikely(!refcount_inc_not_zero(&c->refcount))) c = NULL; - else if (entry) - refcount_inc(&c->entries); + else if (entry) { + if (unlikely(!refcount_inc_not_zero(&c->entries))) { + clusterip_config_put(c); + c = NULL; + } + } } rcu_read_unlock_bh(); @@ -836,6 +840,7 @@ static struct pernet_operations clusterip_net_ops = { .exit = clusterip_net_exit, .id = &clusterip_net_id, .size = sizeof(struct clusterip_net), + .async = true, }; static int __init clusterip_tg_init(void) diff --git a/net/ipv4/netfilter/ipt_ECN.c b/net/ipv4/netfilter/ipt_ECN.c index 270765236f5e..aaaf9a81fbc9 100644 --- a/net/ipv4/netfilter/ipt_ECN.c +++ b/net/ipv4/netfilter/ipt_ECN.c @@ -98,17 +98,15 @@ static int ecn_tg_check(const struct xt_tgchk_param *par) const struct ipt_ECN_info *einfo = par->targinfo; const struct ipt_entry *e = par->entryinfo; - if (einfo->operation & IPT_ECN_OP_MASK) { - pr_info("unsupported ECN operation %x\n", einfo->operation); + if (einfo->operation & IPT_ECN_OP_MASK) return -EINVAL; - } - if (einfo->ip_ect & ~IPT_ECN_IP_MASK) { - pr_info("new ECT codepoint %x out of mask\n", einfo->ip_ect); + + if (einfo->ip_ect & ~IPT_ECN_IP_MASK) return -EINVAL; - } + if ((einfo->operation & (IPT_ECN_OP_SET_ECE|IPT_ECN_OP_SET_CWR)) && (e->ip.proto != IPPROTO_TCP || (e->ip.invflags & XT_INV_PROTO))) { - pr_info("cannot use TCP operations on a non-tcp rule\n"); + pr_info_ratelimited("cannot use operation on non-tcp rule\n"); return -EINVAL; } return 0; diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c index 8bd0d7b26632..e8bed3390e58 100644 --- a/net/ipv4/netfilter/ipt_REJECT.c +++ b/net/ipv4/netfilter/ipt_REJECT.c @@ -74,13 +74,13 @@ static int reject_tg_check(const struct xt_tgchk_param *par) const struct ipt_entry *e = par->entryinfo; if (rejinfo->with == IPT_ICMP_ECHOREPLY) { - pr_info("ECHOREPLY no longer supported.\n"); + pr_info_ratelimited("ECHOREPLY no longer supported.\n"); return -EINVAL; } else if (rejinfo->with == IPT_TCP_RESET) { /* Must specify that it's a TCP packet */ if (e->ip.proto != IPPROTO_TCP || (e->ip.invflags & XT_INV_PROTO)) { - pr_info("TCP_RESET invalid for non-tcp\n"); + pr_info_ratelimited("TCP_RESET invalid for non-tcp\n"); return -EINVAL; } } diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c index 37fb9552e858..fd01f13c896a 100644 --- a/net/ipv4/netfilter/ipt_rpfilter.c +++ b/net/ipv4/netfilter/ipt_rpfilter.c @@ -105,14 +105,14 @@ static int rpfilter_check(const struct xt_mtchk_param *par) const struct xt_rpfilter_info *info = par->matchinfo; unsigned int options = ~XT_RPFILTER_OPTION_MASK; if (info->flags & options) { - pr_info("unknown options encountered"); + pr_info_ratelimited("unknown options\n"); return -EINVAL; } if (strcmp(par->table, "mangle") != 0 && strcmp(par->table, "raw") != 0) { - pr_info("match only valid in the \'raw\' " - "or \'mangle\' tables, not \'%s\'.\n", par->table); + pr_info_ratelimited("only valid in \'raw\' or \'mangle\' table, not \'%s\'\n", + par->table); return -EINVAL; } diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index 9ac92ea7b93c..c1c136a93911 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -87,6 +87,7 @@ static void __net_exit iptable_filter_net_exit(struct net *net) static struct pernet_operations iptable_filter_net_ops = { .init = iptable_filter_net_init, .exit = iptable_filter_net_exit, + .async = true, }; static int __init iptable_filter_init(void) diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index a0d3ad60a411..57244b62a4fc 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -118,6 +118,7 @@ static void __net_exit defrag4_net_exit(struct net *net) static struct pernet_operations defrag4_net_ops = { .exit = defrag4_net_exit, + .async = true, }; static int __init nf_defrag_init(void) diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index b8f0db54b197..0164def9c808 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -1204,6 +1204,7 @@ static void __net_exit ping_v4_proc_exit_net(struct net *net) static struct pernet_operations ping_v4_net_ops = { .init = ping_v4_proc_init_net, .exit = ping_v4_proc_exit_net, + .async = true, }; int __init ping_proc_init(void) diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index dc5edc8f7564..fdabc70283b6 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -549,6 +549,7 @@ static __net_exit void ip_proc_exit_net(struct net *net) static __net_initdata struct pernet_operations ip_proc_ops = { .init = ip_proc_init_net, .exit = ip_proc_exit_net, + .async = true, }; int __init ip_misc_proc_init(void) diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 9b367fc48d7d..54648d20bf0f 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -1156,6 +1156,7 @@ static __net_exit void raw_exit_net(struct net *net) static __net_initdata struct pernet_operations raw_net_ops = { .init = raw_init_net, .exit = raw_exit_net, + .async = true, }; int __init raw_proc_init(void) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 49cc1c1df1ba..26eefa2eaa44 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -417,6 +417,7 @@ static void __net_exit ip_rt_do_proc_exit(struct net *net) static struct pernet_operations ip_rt_proc_ops __net_initdata = { .init = ip_rt_do_proc_init, .exit = ip_rt_do_proc_exit, + .async = true, }; static int __init ip_rt_proc_init(void) @@ -1508,7 +1509,6 @@ struct rtable *rt_dst_alloc(struct net_device *dev, rt->rt_pmtu = 0; rt->rt_gateway = 0; rt->rt_uses_gateway = 0; - rt->rt_table_id = 0; INIT_LIST_HEAD(&rt->rt_uncached); rt->dst.output = ip_output; @@ -1644,19 +1644,6 @@ static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr) spin_unlock_bh(&fnhe_lock); } -static void set_lwt_redirect(struct rtable *rth) -{ - if (lwtunnel_output_redirect(rth->dst.lwtstate)) { - rth->dst.lwtstate->orig_output = rth->dst.output; - rth->dst.output = lwtunnel_output; - } - - if (lwtunnel_input_redirect(rth->dst.lwtstate)) { - rth->dst.lwtstate->orig_input = rth->dst.input; - rth->dst.input = lwtunnel_input; - } -} - /* called in rcu_read_lock() section */ static int __mkroute_input(struct sk_buff *skb, const struct fib_result *res, @@ -1739,15 +1726,13 @@ rt_cache: } rth->rt_is_input = 1; - if (res->table) - rth->rt_table_id = res->table->tb_id; RT_CACHE_STAT_INC(in_slow_tot); rth->dst.input = ip_forward; rt_set_nexthop(rth, daddr, res, fnhe, res->fi, res->type, itag, do_cache); - set_lwt_redirect(rth); + lwtunnel_set_redirect(&rth->dst); skb_dst_set(skb, &rth->dst); out: err = 0; @@ -1826,6 +1811,8 @@ int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4, return skb_get_hash_raw(skb) >> 1; memset(&hash_keys, 0, sizeof(hash_keys)); skb_flow_dissect_flow_keys(skb, &keys, flag); + + hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst; hash_keys.ports.src = keys.ports.src; @@ -1846,7 +1833,6 @@ int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4, return mhash >> 1; } -EXPORT_SYMBOL_GPL(fib_multipath_hash); #endif /* CONFIG_IP_ROUTE_MULTIPATH */ static int ip_mkroute_input(struct sk_buff *skb, @@ -2014,8 +2000,6 @@ local_input: rth->dst.tclassid = itag; #endif rth->rt_is_input = 1; - if (res->table) - rth->rt_table_id = res->table->tb_id; RT_CACHE_STAT_INC(in_slow_tot); if (res->type == RTN_UNREACHABLE) { @@ -2244,8 +2228,6 @@ add: return ERR_PTR(-ENOBUFS); rth->rt_iif = orig_oif; - if (res->table) - rth->rt_table_id = res->table->tb_id; RT_CACHE_STAT_INC(out_slow_tot); @@ -2267,7 +2249,7 @@ add: } rt_set_nexthop(rth, fl4->daddr, res, fnhe, fi, type, 0, do_cache); - set_lwt_redirect(rth); + lwtunnel_set_redirect(&rth->dst); return rth; } @@ -2775,7 +2757,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, rt->rt_flags |= RTCF_NOTIFY; if (rtm->rtm_flags & RTM_F_LOOKUP_TABLE) - table_id = rt->rt_table_id; + table_id = res.table ? res.table->tb_id : 0; if (rtm->rtm_flags & RTM_F_FIB_MATCH) { if (!res.fi) { @@ -2994,6 +2976,7 @@ static __net_exit void sysctl_route_net_exit(struct net *net) static __net_initdata struct pernet_operations sysctl_route_ops = { .init = sysctl_route_net_init, .exit = sysctl_route_net_exit, + .async = true, }; #endif @@ -3007,6 +2990,7 @@ static __net_init int rt_genid_init(struct net *net) static __net_initdata struct pernet_operations rt_genid_ops = { .init = rt_genid_init, + .async = true, }; static int __net_init ipv4_inetpeer_init(struct net *net) @@ -3032,6 +3016,7 @@ static void __net_exit ipv4_inetpeer_exit(struct net *net) static __net_initdata struct pernet_operations ipv4_inetpeer_ops = { .init = ipv4_inetpeer_init, .exit = ipv4_inetpeer_exit, + .async = true, }; #ifdef CONFIG_IP_ROUTE_CLASSID diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 93e172118a94..89683d868b37 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -1219,6 +1219,7 @@ static __net_exit void ipv4_sysctl_exit_net(struct net *net) static __net_initdata struct pernet_operations ipv4_sysctl_ops = { .init = ipv4_sysctl_init_net, .exit = ipv4_sysctl_exit_net, + .async = true, }; static __init int sysctl_ipv4_init(void) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 48636aee23c3..a33539798bf6 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -453,6 +453,7 @@ void tcp_init_sock(struct sock *sk) sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1]; sk_sockets_allocated_inc(sk); + sk->sk_route_forced_caps = NETIF_F_GSO; } EXPORT_SYMBOL(tcp_init_sock); @@ -897,7 +898,7 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now, struct tcp_sock *tp = tcp_sk(sk); u32 new_size_goal, size_goal; - if (!large_allowed || !sk_can_gso(sk)) + if (!large_allowed) return mss_now; /* Note : tcp_tso_autosize() will eventually split this later */ @@ -1062,8 +1063,7 @@ EXPORT_SYMBOL_GPL(do_tcp_sendpages); int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset, size_t size, int flags) { - if (!(sk->sk_route_caps & NETIF_F_SG) || - !sk_check_csum_caps(sk)) + if (!(sk->sk_route_caps & NETIF_F_SG)) return sock_no_sendpage_locked(sk, page, offset, size, flags); tcp_rate_check_app_limited(sk); /* is sending application-limited? */ @@ -1102,27 +1102,11 @@ static int linear_payload_sz(bool first_skb) return 0; } -static int select_size(const struct sock *sk, bool sg, bool first_skb, bool zc) +static int select_size(bool first_skb, bool zc) { - const struct tcp_sock *tp = tcp_sk(sk); - int tmp = tp->mss_cache; - - if (sg) { - if (zc) - return 0; - - if (sk_can_gso(sk)) { - tmp = linear_payload_sz(first_skb); - } else { - int pgbreak = SKB_MAX_HEAD(MAX_TCP_HEADER); - - if (tmp >= pgbreak && - tmp <= pgbreak + (MAX_SKB_FRAGS - 1) * PAGE_SIZE) - tmp = pgbreak; - } - } - - return tmp; + if (zc) + return 0; + return linear_payload_sz(first_skb); } void tcp_free_fastopen_req(struct tcp_sock *tp) @@ -1187,7 +1171,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) int flags, err, copied = 0; int mss_now = 0, size_goal, copied_syn = 0; bool process_backlog = false; - bool sg, zc = false; + bool zc = false; long timeo; flags = msg->msg_flags; @@ -1205,7 +1189,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) goto out_err; } - zc = sk_check_csum_caps(sk) && sk->sk_route_caps & NETIF_F_SG; + zc = sk->sk_route_caps & NETIF_F_SG; if (!zc) uarg->zerocopy = 0; } @@ -1268,18 +1252,12 @@ restart: if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) goto do_error; - sg = !!(sk->sk_route_caps & NETIF_F_SG); - while (msg_data_left(msg)) { int copy = 0; - int max = size_goal; skb = tcp_write_queue_tail(sk); - if (skb) { - if (skb->ip_summed == CHECKSUM_NONE) - max = mss_now; - copy = max - skb->len; - } + if (skb) + copy = size_goal - skb->len; if (copy <= 0 || !tcp_skb_can_collapse_to(skb)) { bool first_skb; @@ -1297,22 +1275,17 @@ new_segment: goto restart; } first_skb = tcp_rtx_and_write_queues_empty(sk); - linear = select_size(sk, sg, first_skb, zc); + linear = select_size(first_skb, zc); skb = sk_stream_alloc_skb(sk, linear, sk->sk_allocation, first_skb); if (!skb) goto wait_for_memory; process_backlog = true; - /* - * Check whether we can use HW checksum. - */ - if (sk_check_csum_caps(sk)) - skb->ip_summed = CHECKSUM_PARTIAL; + skb->ip_summed = CHECKSUM_PARTIAL; skb_entail(sk, skb); copy = size_goal; - max = size_goal; /* All packets are restored as if they have * already been sent. skb_mstamp isn't set to @@ -1343,7 +1316,7 @@ new_segment: if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { - if (i >= sysctl_max_skb_frags || !sg) { + if (i >= sysctl_max_skb_frags) { tcp_mark_push(tp, skb); goto new_segment; } @@ -1396,7 +1369,7 @@ new_segment: goto out; } - if (skb->len < max || (flags & MSG_OOB) || unlikely(tp->repair)) + if (skb->len < size_goal || (flags & MSG_OOB) || unlikely(tp->repair)) continue; if (forced_push(tp)) { diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 575d3c1fb6e8..06b9c4765f42 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1358,9 +1358,6 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, int len; int in_sack; - if (!sk_can_gso(sk)) - goto fallback; - /* Normally R but no L won't result in plain S */ if (!dup_sack && (TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_RETRANS)) == TCPCB_SACKED_RETRANS) @@ -5870,10 +5867,12 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) tp->rx_opt.saw_tstamp = 0; req = tp->fastopen_rsk; if (req) { + bool req_stolen; + WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV && sk->sk_state != TCP_FIN_WAIT1); - if (!tcp_check_req(sk, skb, req, true)) + if (!tcp_check_req(sk, skb, req, true, &req_stolen)) goto discard; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index f8ad397e285e..2c6aec2643e8 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -561,16 +561,9 @@ void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr) { struct tcphdr *th = tcp_hdr(skb); - if (skb->ip_summed == CHECKSUM_PARTIAL) { - th->check = ~tcp_v4_check(skb->len, saddr, daddr, 0); - skb->csum_start = skb_transport_header(skb) - skb->head; - skb->csum_offset = offsetof(struct tcphdr, check); - } else { - th->check = tcp_v4_check(skb->len, saddr, daddr, - csum_partial(th, - th->doff << 2, - skb->csum)); - } + th->check = ~tcp_v4_check(skb->len, saddr, daddr, 0); + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = offsetof(struct tcphdr, check); } /* This routine computes an IPv4 TCP checksum. */ @@ -1672,6 +1665,7 @@ process: if (sk->sk_state == TCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); + bool req_stolen = false; struct sock *nsk; sk = req->rsk_listener; @@ -1694,10 +1688,20 @@ process: th = (const struct tcphdr *)skb->data; iph = ip_hdr(skb); tcp_v4_fill_cb(skb, iph, th); - nsk = tcp_check_req(sk, skb, req, false); + nsk = tcp_check_req(sk, skb, req, false, &req_stolen); } if (!nsk) { reqsk_put(req); + if (req_stolen) { + /* Another cpu got exclusive access to req + * and created a full blown socket. + * Try to feed this packet to this socket + * instead of discarding it. + */ + tcp_v4_restore_cb(skb); + sock_put(sk); + goto lookup; + } goto discard_and_relse; } if (nsk == sk) { @@ -2387,6 +2391,7 @@ static void __net_exit tcp4_proc_exit_net(struct net *net) static struct pernet_operations tcp4_net_ops = { .init = tcp4_proc_init_net, .exit = tcp4_proc_exit_net, + .async = true, }; int __init tcp4_proc_init(void) @@ -2573,6 +2578,7 @@ static struct pernet_operations __net_initdata tcp_sk_ops = { .init = tcp_sk_init, .exit = tcp_sk_exit, .exit_batch = tcp_sk_exit_batch, + .async = true, }; void __init tcp_v4_init(void) diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 03b51cdcc731..aa6fea9f3328 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -1024,6 +1024,7 @@ static void __net_exit tcp_net_metrics_exit_batch(struct list_head *net_exit_lis static __net_initdata struct pernet_operations tcp_net_metrics_ops = { .init = tcp_net_metrics_init, .exit_batch = tcp_net_metrics_exit_batch, + .async = true, }; void __init tcp_metrics_init(void) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index a8384b0c11f8..e7e36433cdb5 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -578,7 +578,7 @@ EXPORT_SYMBOL(tcp_create_openreq_child); struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, struct request_sock *req, - bool fastopen) + bool fastopen, bool *req_stolen) { struct tcp_options_received tmp_opt; struct sock *child; @@ -785,6 +785,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, sock_rps_save_rxhash(child, skb); tcp_synack_rtt_meas(child, req); + *req_stolen = !own_req; return inet_csk_complete_hashdance(sk, child, req, own_req); listen_overflow: diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index e9f985e42405..49d043de3476 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1206,7 +1206,7 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) /* Initialize TSO segments for a packet. */ static void tcp_set_skb_tso_segs(struct sk_buff *skb, unsigned int mss_now) { - if (skb->len <= mss_now || skb->ip_summed == CHECKSUM_NONE) { + if (skb->len <= mss_now) { /* Avoid the costly divide in the normal * non-TSO case. */ @@ -1335,21 +1335,9 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, TCP_SKB_CB(buff)->sacked = TCP_SKB_CB(skb)->sacked; tcp_skb_fragment_eor(skb, buff); - if (!skb_shinfo(skb)->nr_frags && skb->ip_summed != CHECKSUM_PARTIAL) { - /* Copy and checksum data tail into the new buffer. */ - buff->csum = csum_partial_copy_nocheck(skb->data + len, - skb_put(buff, nsize), - nsize, 0); - - skb_trim(skb, len); - - skb->csum = csum_block_sub(skb->csum, buff->csum, len); - } else { - skb->ip_summed = CHECKSUM_PARTIAL; - skb_split(skb, buff, len); - } + skb_split(skb, buff, len); - buff->ip_summed = skb->ip_summed; + buff->ip_summed = CHECKSUM_PARTIAL; buff->tstamp = skb->tstamp; tcp_fragment_tstamp(skb, buff); @@ -1730,7 +1718,7 @@ u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, */ segs = max_t(u32, bytes / mss_now, min_tso_segs); - return min_t(u32, segs, sk->sk_gso_max_segs); + return segs; } EXPORT_SYMBOL(tcp_tso_autosize); @@ -1742,9 +1730,10 @@ static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now) const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops; u32 tso_segs = ca_ops->tso_segs_goal ? ca_ops->tso_segs_goal(sk) : 0; - return tso_segs ? : - tcp_tso_autosize(sk, mss_now, - sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs); + if (!tso_segs) + tso_segs = tcp_tso_autosize(sk, mss_now, + sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs); + return min_t(u32, tso_segs, sk->sk_gso_max_segs); } /* Returns the portion of skb which can be sent right away */ @@ -1901,7 +1890,7 @@ static int tso_fragment(struct sock *sk, enum tcp_queue tcp_queue, tcp_skb_fragment_eor(skb, buff); - buff->ip_summed = skb->ip_summed = CHECKSUM_PARTIAL; + buff->ip_summed = CHECKSUM_PARTIAL; skb_split(skb, buff, len); tcp_fragment_tstamp(skb, buff); @@ -2027,6 +2016,24 @@ static inline void tcp_mtu_check_reprobe(struct sock *sk) } } +static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len) +{ + struct sk_buff *skb, *next; + + skb = tcp_send_head(sk); + tcp_for_write_queue_from_safe(skb, next, sk) { + if (len <= skb->len) + break; + + if (unlikely(TCP_SKB_CB(skb)->eor)) + return false; + + len -= skb->len; + } + + return true; +} + /* Create a new MTU probe if we are ready. * MTU probe is regularly attempting to increase the path MTU by * deliberately sending larger packets. This discovers routing @@ -2099,6 +2106,9 @@ static int tcp_mtu_probe(struct sock *sk) return 0; } + if (!tcp_can_coalesce_send_queue_head(sk, probe_size)) + return -1; + /* We're allowed to probe. Build it now. */ nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC, false); if (!nskb) @@ -2113,7 +2123,7 @@ static int tcp_mtu_probe(struct sock *sk) TCP_SKB_CB(nskb)->tcp_flags = TCPHDR_ACK; TCP_SKB_CB(nskb)->sacked = 0; nskb->csum = 0; - nskb->ip_summed = skb->ip_summed; + nskb->ip_summed = CHECKSUM_PARTIAL; tcp_insert_write_queue_before(nskb, skb, sk); tcp_highest_sack_replace(sk, skb, nskb); @@ -2121,19 +2131,16 @@ static int tcp_mtu_probe(struct sock *sk) len = 0; tcp_for_write_queue_from_safe(skb, next, sk) { copy = min_t(int, skb->len, probe_size - len); - if (nskb->ip_summed) { - skb_copy_bits(skb, 0, skb_put(nskb, copy), copy); - } else { - __wsum csum = skb_copy_and_csum_bits(skb, 0, - skb_put(nskb, copy), - copy, 0); - nskb->csum = csum_block_add(nskb->csum, csum, len); - } + skb_copy_bits(skb, 0, skb_put(nskb, copy), copy); if (skb->len <= copy) { /* We've eaten all the data from this skb. * Throw it away. */ TCP_SKB_CB(nskb)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags; + /* If this is the last SKB we copy and eor is set + * we need to propagate it to the new skb. + */ + TCP_SKB_CB(nskb)->eor = TCP_SKB_CB(skb)->eor; tcp_unlink_write_queue(skb, sk); sk_wmem_free_skb(sk, skb); } else { @@ -2141,9 +2148,6 @@ static int tcp_mtu_probe(struct sock *sk) ~(TCPHDR_FIN|TCPHDR_PSH); if (!skb_shinfo(skb)->nr_frags) { skb_pull(skb, copy); - if (skb->ip_summed != CHECKSUM_PARTIAL) - skb->csum = csum_partial(skb->data, - skb->len, 0); } else { __pskb_trim_head(skb, copy); tcp_set_skb_tso_segs(skb, mss_now); @@ -2721,12 +2725,6 @@ static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) } tcp_highest_sack_replace(sk, next_skb, skb); - if (next_skb->ip_summed == CHECKSUM_PARTIAL) - skb->ip_summed = CHECKSUM_PARTIAL; - - if (skb->ip_summed != CHECKSUM_PARTIAL) - skb->csum = csum_block_add(skb->csum, next_skb->csum, skb_size); - /* Update sequence range on original skb. */ TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(next_skb)->end_seq; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index bfaefe560b5c..3013404d0935 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2024,6 +2024,11 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh, err = udplite_checksum_init(skb, uh); if (err) return err; + + if (UDP_SKB_CB(skb)->partial_cov) { + skb->csum = inet_compute_pseudo(skb, proto); + return 0; + } } /* Note, we are only interested in != 0 or == 0, thus the @@ -2757,6 +2762,7 @@ static void __net_exit udp4_proc_exit_net(struct net *net) static struct pernet_operations udp4_net_ops = { .init = udp4_proc_init_net, .exit = udp4_proc_exit_net, + .async = true, }; int __init udp4_proc_init(void) diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index f96614e9b9a5..72f2c3806408 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -104,6 +104,7 @@ static void __net_exit udplite4_proc_exit_net(struct net *net) static struct pernet_operations udplite4_net_ops = { .init = udplite4_proc_init_net, .exit = udplite4_proc_exit_net, + .async = true, }; static __init int udplite4_proc_init(void) diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 05017e2c849c..796ac4115485 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -100,7 +100,6 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, xdst->u.rt.rt_gateway = rt->rt_gateway; xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway; xdst->u.rt.rt_pmtu = rt->rt_pmtu; - xdst->u.rt.rt_table_id = rt->rt_table_id; INIT_LIST_HEAD(&xdst->u.rt.rt_uncached); return 0; @@ -365,6 +364,7 @@ static void __net_exit xfrm4_net_exit(struct net *net) static struct pernet_operations __net_initdata xfrm4_net_ops = { .init = xfrm4_net_init, .exit = xfrm4_net_exit, + .async = true, }; static void __init xfrm4_policy_init(void) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index e1846b97ee69..4facfe0b1888 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -4257,6 +4257,7 @@ static void __net_exit if6_proc_net_exit(struct net *net) static struct pernet_operations if6_proc_net_ops = { .init = if6_proc_net_init, .exit = if6_proc_net_exit, + .async = true, }; int __init if6_proc_init(void) @@ -6550,6 +6551,7 @@ static void __net_exit addrconf_exit_net(struct net *net) static struct pernet_operations addrconf_ops = { .init = addrconf_init_net, .exit = addrconf_exit_net, + .async = true, }; static struct rtnl_af_ops inet6_ops __read_mostly = { diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index 1d6ced37ad71..ba2e63633370 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -344,6 +344,7 @@ static void __net_exit ip6addrlbl_net_exit(struct net *net) static struct pernet_operations ipv6_addr_label_ops = { .init = ip6addrlbl_net_init, .exit = ip6addrlbl_net_exit, + .async = true, }; int __init ipv6_addr_label_init(void) diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 416917719a6f..dbbe04018813 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -470,7 +470,7 @@ EXPORT_SYMBOL_GPL(inet6_destroy_sock); */ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { struct sockaddr_in6 *sin = (struct sockaddr_in6 *)uaddr; struct sock *sk = sock->sk; @@ -500,8 +500,7 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, } sin->sin6_scope_id = ipv6_iface_scope_id(&sin->sin6_addr, sk->sk_bound_dev_if); - *uaddr_len = sizeof(*sin); - return 0; + return sizeof(*sin); } EXPORT_SYMBOL(inet6_getname); @@ -858,6 +857,7 @@ static void __net_exit inet6_net_exit(struct net *net) static struct pernet_operations inet6_net_ops = { .init = inet6_net_init, .exit = inet6_net_exit, + .async = true, }; static const struct ipv6_stub ipv6_stub_impl = { diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index b240f24a6e52..95a2c9e8699a 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -368,6 +368,7 @@ static void __net_exit fib6_rules_net_exit(struct net *net) static struct pernet_operations fib6_rules_net_ops = { .init = fib6_rules_net_init, .exit = fib6_rules_net_exit, + .async = true, }; int __init fib6_rules_init(void) diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 6ae5dd3f4d0d..4fa4f1b150a4 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -997,6 +997,7 @@ static void __net_exit icmpv6_sk_exit(struct net *net) static struct pernet_operations icmpv6_sk_ops = { .init = icmpv6_sk_init, .exit = icmpv6_sk_exit, + .async = true, }; int __init icmpv6_init(void) diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c index 44c39c5f0638..e438699f000f 100644 --- a/net/ipv6/ila/ila_xlat.c +++ b/net/ipv6/ila/ila_xlat.c @@ -613,6 +613,7 @@ static struct pernet_operations ila_net_ops = { .exit = ila_exit_net, .id = &ila_net_id, .size = sizeof(struct ila_net), + .async = true, }; static int ila_xlat_addr(struct sk_buff *skb, bool sir2ila) diff --git a/net/ipv6/ip6_checksum.c b/net/ipv6/ip6_checksum.c index ec43d18b5ff9..547515e8450a 100644 --- a/net/ipv6/ip6_checksum.c +++ b/net/ipv6/ip6_checksum.c @@ -73,6 +73,11 @@ int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto) err = udplite_checksum_init(skb, uh); if (err) return err; + + if (UDP_SKB_CB(skb)->partial_cov) { + skb->csum = ip6_compute_pseudo(skb, proto); + return 0; + } } /* To support RFC 6936 (allow zero checksum in UDP/IPV6 for tunnels) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 92b8d8c75eed..cab95cf3b39f 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -2160,6 +2160,7 @@ static void fib6_net_exit(struct net *net) static struct pernet_operations fib6_net_ops = { .init = fib6_net_init, .exit = fib6_net_exit, + .async = true, }; int __init fib6_init(void) diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 3dab664ff503..6ddf52282894 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -873,6 +873,7 @@ static void __net_exit ip6_flowlabel_net_exit(struct net *net) static struct pernet_operations ip6_flowlabel_net_ops = { .init = ip6_flowlabel_proc_init, .exit = ip6_flowlabel_net_exit, + .async = true, }; int ip6_flowlabel_init(void) diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 3c353125546d..4f150a394387 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1517,6 +1517,7 @@ static struct pernet_operations ip6gre_net_ops = { .exit_batch = ip6gre_exit_batch_net, .id = &ip6gre_net_id, .size = sizeof(struct ip6gre_net), + .async = true, }; static int ip6gre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], @@ -1784,6 +1785,12 @@ static void ip6gre_tap_setup(struct net_device *dev) netif_keep_dst(dev); } +bool is_ip6gretap_dev(const struct net_device *dev) +{ + return dev->netdev_ops == &ip6gre_tap_netdev_ops; +} +EXPORT_SYMBOL_GPL(is_ip6gretap_dev); + static bool ip6gre_netlink_encap_parms(struct nlattr *data[], struct ip_tunnel_encap *ipencap) { diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 4b15fe928278..869e2e6750f7 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -2250,6 +2250,7 @@ static struct pernet_operations ip6_tnl_net_ops = { .exit_batch = ip6_tnl_exit_batch_net, .id = &ip6_tnl_net_id, .size = sizeof(struct ip6_tnl_net), + .async = true, }; /** diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index fa3ae1cb50d3..c617ea17faa8 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -1148,6 +1148,7 @@ static struct pernet_operations vti6_net_ops = { .exit_batch = vti6_exit_batch_net, .id = &vti6_net_id, .size = sizeof(struct vti6_net), + .async = true, }; static struct xfrm6_protocol vti_esp6_protocol __read_mostly = { diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 9f6cace9c817..295eb5ecaee5 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1397,6 +1397,7 @@ static void __net_exit ip6mr_net_exit(struct net *net) static struct pernet_operations ip6mr_net_ops = { .init = ip6mr_net_init, .exit = ip6mr_net_exit, + .async = true, }; int __init ip6_mr_init(void) diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index d78d41fc4b1a..24535169663d 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -1367,10 +1367,7 @@ int ipv6_getsockopt(struct sock *sk, int level, int optname, if (get_user(len, optlen)) return -EFAULT; - lock_sock(sk); - err = nf_getsockopt(sk, PF_INET6, optname, optval, - &len); - release_sock(sk); + err = nf_getsockopt(sk, PF_INET6, optname, optval, &len); if (err >= 0) err = put_user(len, optlen); } @@ -1409,10 +1406,7 @@ int compat_ipv6_getsockopt(struct sock *sk, int level, int optname, if (get_user(len, optlen)) return -EFAULT; - lock_sock(sk); - err = compat_nf_getsockopt(sk, PF_INET6, - optname, optval, &len); - release_sock(sk); + err = compat_nf_getsockopt(sk, PF_INET6, optname, optval, &len); if (err >= 0) err = put_user(len, optlen); } diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 9b9d2ff01b35..d9bb933dd5c4 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -2997,6 +2997,7 @@ static void __net_exit igmp6_net_exit(struct net *net) static struct pernet_operations igmp6_net_ops = { .init = igmp6_net_init, .exit = igmp6_net_exit, + .async = true, }; int __init igmp6_init(void) diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index f61a5b613b52..0a19ce3a6f7f 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1882,6 +1882,7 @@ static void __net_exit ndisc_net_exit(struct net *net) static struct pernet_operations ndisc_net_ops = { .init = ndisc_net_init, .exit = ndisc_net_exit, + .async = true, }; int __init ndisc_init(void) diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index af4c917e0836..62358b93bbac 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -352,6 +352,10 @@ ip6t_do_table(struct sk_buff *skb, } if (table_base + v != ip6t_next_entry(e) && !(e->ipv6.flags & IP6T_F_GOTO)) { + if (unlikely(stackidx >= private->stacksize)) { + verdict = NF_DROP; + break; + } jumpstack[stackidx++] = e; } diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index fa51a205918d..38dea8ff680f 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -85,14 +85,14 @@ static int reject_tg6_check(const struct xt_tgchk_param *par) const struct ip6t_entry *e = par->entryinfo; if (rejinfo->with == IP6T_ICMP6_ECHOREPLY) { - pr_info("ECHOREPLY is not supported.\n"); + pr_info_ratelimited("ECHOREPLY is not supported\n"); return -EINVAL; } else if (rejinfo->with == IP6T_TCP_RESET) { /* Must specify that it's a TCP packet */ if (!(e->ipv6.flags & IP6T_F_PROTO) || e->ipv6.proto != IPPROTO_TCP || (e->ipv6.invflags & XT_INV_PROTO)) { - pr_info("TCP_RESET illegal for non-tcp\n"); + pr_info_ratelimited("TCP_RESET illegal for non-tcp\n"); return -EINVAL; } } diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c index b12e61b7b16c..94deb69bbbda 100644 --- a/net/ipv6/netfilter/ip6t_rpfilter.c +++ b/net/ipv6/netfilter/ip6t_rpfilter.c @@ -103,14 +103,14 @@ static int rpfilter_check(const struct xt_mtchk_param *par) unsigned int options = ~XT_RPFILTER_OPTION_MASK; if (info->flags & options) { - pr_info("unknown options encountered"); + pr_info_ratelimited("unknown options\n"); return -EINVAL; } if (strcmp(par->table, "mangle") != 0 && strcmp(par->table, "raw") != 0) { - pr_info("match only valid in the \'raw\' " - "or \'mangle\' tables, not \'%s\'.\n", par->table); + pr_info_ratelimited("only valid in \'raw\' or \'mangle\' table, not \'%s\'\n", + par->table); return -EINVAL; } diff --git a/net/ipv6/netfilter/ip6t_srh.c b/net/ipv6/netfilter/ip6t_srh.c index 9642164107ce..33719d5560c8 100644 --- a/net/ipv6/netfilter/ip6t_srh.c +++ b/net/ipv6/netfilter/ip6t_srh.c @@ -122,12 +122,14 @@ static int srh_mt6_check(const struct xt_mtchk_param *par) const struct ip6t_srh *srhinfo = par->matchinfo; if (srhinfo->mt_flags & ~IP6T_SRH_MASK) { - pr_err("unknown srh match flags %X\n", srhinfo->mt_flags); + pr_info_ratelimited("unknown srh match flags %X\n", + srhinfo->mt_flags); return -EINVAL; } if (srhinfo->mt_invflags & ~IP6T_SRH_INV_MASK) { - pr_err("unknown srh invflags %X\n", srhinfo->mt_invflags); + pr_info_ratelimited("unknown srh invflags %X\n", + srhinfo->mt_invflags); return -EINVAL; } diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c index c87b48359e8f..32f98bc06900 100644 --- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -103,6 +103,7 @@ static void __net_exit defrag6_net_exit(struct net *net) static struct pernet_operations defrag6_net_ops = { .exit = defrag6_net_exit, + .async = true, }; static int __init nf_defrag_init(void) diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index d12c55dad7d1..318c6e914234 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -240,6 +240,7 @@ static void __net_init ping_v6_proc_exit_net(struct net *net) static struct pernet_operations ping_v6_net_ops = { .init = ping_v6_proc_init_net, .exit = ping_v6_proc_exit_net, + .async = true, }; #endif diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index b67814242f78..b8858c546f41 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -343,6 +343,7 @@ static void __net_exit ipv6_proc_exit_net(struct net *net) static struct pernet_operations ipv6_proc_ops = { .init = ipv6_proc_init_net, .exit = ipv6_proc_exit_net, + .async = true, }; int __init ipv6_misc_proc_init(void) diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 4c25339b1984..10a4ac4933b7 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -1332,6 +1332,7 @@ static void __net_exit raw6_exit_net(struct net *net) static struct pernet_operations raw6_net_ops = { .init = raw6_init_net, .exit = raw6_exit_net, + .async = true, }; int __init raw6_proc_init(void) diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index afbc000ad4f2..b5da69c83123 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -733,6 +733,7 @@ static void __net_exit ipv6_frags_exit_net(struct net *net) static struct pernet_operations ip6_frags_ops = { .init = ipv6_frags_init_net, .exit = ipv6_frags_exit_net, + .async = true, }; int __init ipv6_frag_init(void) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 9dcfadddd800..aa709b644945 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2671,14 +2671,7 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg, if (err) goto out; rt->dst.lwtstate = lwtstate_get(lwtstate); - if (lwtunnel_output_redirect(rt->dst.lwtstate)) { - rt->dst.lwtstate->orig_output = rt->dst.output; - rt->dst.output = lwtunnel_output; - } - if (lwtunnel_input_redirect(rt->dst.lwtstate)) { - rt->dst.lwtstate->orig_input = rt->dst.input; - rt->dst.input = lwtunnel_input; - } + lwtunnel_set_redirect(&rt->dst); } ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len); @@ -4979,6 +4972,7 @@ static void __net_exit ip6_route_net_exit_late(struct net *net) static struct pernet_operations ip6_route_net_ops = { .init = ip6_route_net_init, .exit = ip6_route_net_exit, + .async = true, }; static int __net_init ipv6_inetpeer_init(struct net *net) @@ -5004,11 +4998,13 @@ static void __net_exit ipv6_inetpeer_exit(struct net *net) static struct pernet_operations ipv6_inetpeer_ops = { .init = ipv6_inetpeer_init, .exit = ipv6_inetpeer_exit, + .async = true, }; static struct pernet_operations ip6_route_net_late_ops = { .init = ip6_route_net_init_late, .exit = ip6_route_net_exit_late, + .async = true, }; static struct notifier_block ip6_route_dev_notifier = { diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 7f5621d09571..c3f13c3bd8a9 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -395,6 +395,7 @@ static void __net_exit seg6_net_exit(struct net *net) static struct pernet_operations ip6_segments_ops = { .init = seg6_net_init, .exit = seg6_net_exit, + .async = true, }; static const struct genl_ops seg6_genl_ops[] = { diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 3873d3877135..182db078f01e 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -182,7 +182,7 @@ static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn) #ifdef CONFIG_IPV6_SIT_6RD struct ip_tunnel *t = netdev_priv(dev); - if (t->dev == sitn->fb_tunnel_dev) { + if (dev == sitn->fb_tunnel_dev) { ipv6_addr_set(&t->ip6rd.prefix, htonl(0x20020000), 0, 0, 0); t->ip6rd.relay_prefix = 0; t->ip6rd.prefixlen = 16; @@ -1878,6 +1878,7 @@ static struct pernet_operations sit_net_ops = { .exit_batch = sit_exit_batch_net, .id = &sit_net_id, .size = sizeof(struct sit_net), + .async = true, }; static void __exit sit_cleanup(void) diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index a789a8ac6a64..262f791f1b9b 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -251,6 +251,7 @@ static void __net_exit ipv6_sysctl_net_exit(struct net *net) static struct pernet_operations ipv6_sysctl_net_ops = { .init = ipv6_sysctl_net_init, .exit = ipv6_sysctl_net_exit, + .async = true, }; static struct ctl_table_header *ip6_header; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 412139f4eccd..5425d7b100ee 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1451,6 +1451,7 @@ process: if (sk->sk_state == TCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); + bool req_stolen = false; struct sock *nsk; sk = req->rsk_listener; @@ -1470,10 +1471,20 @@ process: th = (const struct tcphdr *)skb->data; hdr = ipv6_hdr(skb); tcp_v6_fill_cb(skb, hdr, th); - nsk = tcp_check_req(sk, skb, req, false); + nsk = tcp_check_req(sk, skb, req, false, &req_stolen); } if (!nsk) { reqsk_put(req); + if (req_stolen) { + /* Another cpu got exclusive access to req + * and created a full blown socket. + * Try to feed this packet to this socket + * instead of discarding it. + */ + tcp_v6_restore_cb(skb); + sock_put(sk); + goto lookup; + } goto discard_and_relse; } if (nsk == sk) { @@ -1996,6 +2007,7 @@ static struct pernet_operations tcpv6_net_ops = { .init = tcpv6_net_init, .exit = tcpv6_net_exit, .exit_batch = tcpv6_net_exit_batch, + .async = true, }; int __init tcpv6_init(void) diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index 14ae32bb1f3d..f3839780dc31 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -123,6 +123,7 @@ static void __net_exit udplite6_proc_exit_net(struct net *net) static struct pernet_operations udplite6_net_ops = { .init = udplite6_proc_init_net, .exit = udplite6_proc_exit_net, + .async = true, }; int __init udplite6_proc_init(void) diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 09fb44ee3b45..88cd0c90fa81 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -395,6 +395,7 @@ static void __net_exit xfrm6_net_exit(struct net *net) static struct pernet_operations xfrm6_net_ops = { .init = xfrm6_net_init, .exit = xfrm6_net_exit, + .async = true, }; int __init xfrm6_init(void) diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index f85f0d7480ac..a9673619e0e9 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -353,6 +353,7 @@ static struct pernet_operations xfrm6_tunnel_net_ops = { .exit = xfrm6_tunnel_net_exit, .id = &xfrm6_tunnel_net_id, .size = sizeof(struct xfrm6_tunnel_net), + .async = true, }; static int __init xfrm6_tunnel_init(void) diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 1e8cc7bcbca3..81ce15ffb878 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -989,14 +989,13 @@ done: } static int iucv_sock_getname(struct socket *sock, struct sockaddr *addr, - int *len, int peer) + int peer) { struct sockaddr_iucv *siucv = (struct sockaddr_iucv *) addr; struct sock *sk = sock->sk; struct iucv_sock *iucv = iucv_sk(sk); addr->sa_family = AF_IUCV; - *len = sizeof(struct sockaddr_iucv); if (peer) { memcpy(siucv->siucv_user_id, iucv->dst_user_id, 8); @@ -1009,7 +1008,7 @@ static int iucv_sock_getname(struct socket *sock, struct sockaddr *addr, memset(&siucv->siucv_addr, 0, sizeof(siucv->siucv_addr)); memset(&siucv->siucv_nodeid, 0, sizeof(siucv->siucv_nodeid)); - return 0; + return sizeof(struct sockaddr_iucv); } /** diff --git a/net/kcm/kcmproc.c b/net/kcm/kcmproc.c index 9d5649e4e8b7..2c1c8b3e4452 100644 --- a/net/kcm/kcmproc.c +++ b/net/kcm/kcmproc.c @@ -433,6 +433,7 @@ static void kcm_proc_exit_net(struct net *net) static struct pernet_operations kcm_net_ops = { .init = kcm_proc_init_net, .exit = kcm_proc_exit_net, + .async = true, }; int __init kcm_proc_init(void) diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index f297d53a11aa..a6cd0712e063 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -1417,6 +1417,7 @@ static int kcm_attach(struct socket *sock, struct socket *csock, */ if (csk->sk_user_data) { write_unlock_bh(&csk->sk_callback_lock); + strp_stop(&psock->strp); strp_done(&psock->strp); kmem_cache_free(kcm_psockp, psock); return -EALREADY; @@ -2014,6 +2015,7 @@ static struct pernet_operations kcm_net_ops = { .exit = kcm_exit_net, .id = &kcm_net_id, .size = sizeof(struct kcm_net), + .async = true, }; static int __init kcm_init(void) diff --git a/net/key/af_key.c b/net/key/af_key.c index 7e2e7188e7f4..3ac08ab26207 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -3863,6 +3863,7 @@ static struct pernet_operations pfkey_net_ops = { .exit = pfkey_net_exit, .id = &pfkey_net_id, .size = sizeof(struct netns_pfkey), + .async = true, }; static void __exit ipsec_pfkey_exit(void) diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index ff61124fdf59..4614585e1720 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -349,7 +349,7 @@ static int l2tp_ip_disconnect(struct sock *sk, int flags) } static int l2tp_ip_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); @@ -370,8 +370,7 @@ static int l2tp_ip_getname(struct socket *sock, struct sockaddr *uaddr, lsa->l2tp_conn_id = lsk->conn_id; lsa->l2tp_addr.s_addr = addr; } - *uaddr_len = sizeof(*lsa); - return 0; + return sizeof(*lsa); } static int l2tp_ip_backlog_recv(struct sock *sk, struct sk_buff *skb) diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 192344688c06..efea58b66295 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -421,7 +421,7 @@ static int l2tp_ip6_disconnect(struct sock *sk, int flags) } static int l2tp_ip6_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { struct sockaddr_l2tpip6 *lsa = (struct sockaddr_l2tpip6 *)uaddr; struct sock *sk = sock->sk; @@ -449,8 +449,7 @@ static int l2tp_ip6_getname(struct socket *sock, struct sockaddr *uaddr, } if (ipv6_addr_type(&lsa->l2tp_addr) & IPV6_ADDR_LINKLOCAL) lsa->l2tp_scope_id = sk->sk_bound_dev_if; - *uaddr_len = sizeof(*lsa); - return 0; + return sizeof(*lsa); } static int l2tp_ip6_backlog_recv(struct sock *sk, struct sk_buff *skb) diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 59f246d7b290..0c4f49a6a0cb 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -870,7 +870,7 @@ err: /* getname() support. */ static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr, - int *usockaddr_len, int peer) + int peer) { int len = 0; int error = 0; @@ -969,8 +969,7 @@ static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr, memcpy(uaddr, &sp, len); } - *usockaddr_len = len; - error = 0; + error = len; sock_put(sk); end: @@ -1771,6 +1770,7 @@ static struct pernet_operations pppol2tp_net_ops = { .init = pppol2tp_init_net, .exit = pppol2tp_exit_net, .id = &pppol2tp_net_id, + .async = true, }; /***************************************************************************** diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index c38d16f22d2a..01dcc0823d1f 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -971,7 +971,7 @@ release: * Return the address information of a socket. */ static int llc_ui_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddrlen, int peer) + int peer) { struct sockaddr_llc sllc; struct sock *sk = sock->sk; @@ -982,7 +982,6 @@ static int llc_ui_getname(struct socket *sock, struct sockaddr *uaddr, lock_sock(sk); if (sock_flag(sk, SOCK_ZAPPED)) goto out; - *uaddrlen = sizeof(sllc); if (peer) { rc = -ENOTCONN; if (sk->sk_state != TCP_ESTABLISHED) @@ -1003,9 +1002,9 @@ static int llc_ui_getname(struct socket *sock, struct sockaddr *uaddr, IFHWADDRLEN); } } - rc = 0; sllc.sllc_family = AF_LLC; memcpy(uaddr, &sllc, sizeof(sllc)); + rc = sizeof(sllc); out: release_sock(sk); return rc; diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index a8b1616cec41..1f3188d03840 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -8,6 +8,7 @@ * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2007-2010, Intel Corporation * Copyright(c) 2015-2017 Intel Deutschland GmbH + * Copyright (C) 2018 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -304,9 +305,6 @@ void ___ieee80211_start_rx_ba_session(struct sta_info *sta, * driver so reject the timeout update. */ status = WLAN_STATUS_REQUEST_DECLINED; - ieee80211_send_addba_resp(sta->sdata, sta->sta.addr, - tid, dialog_token, status, - 1, buf_size, timeout); goto end; } diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 46028e12e216..f4195a0f0279 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -2892,7 +2892,7 @@ cfg80211_beacon_dup(struct cfg80211_beacon_data *beacon) } if (beacon->probe_resp_len) { new_beacon->probe_resp_len = beacon->probe_resp_len; - beacon->probe_resp = pos; + new_beacon->probe_resp = pos; memcpy(pos, beacon->probe_resp, beacon->probe_resp_len); pos += beacon->probe_resp_len; } diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 1f466d12a6bc..a75653affbf7 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -212,6 +212,7 @@ static const char *hw_flag_names[] = { FLAG(REPORTS_LOW_ACK), FLAG(SUPPORTS_TX_FRAG), FLAG(SUPPORTS_TDLS_BUFFER_STA), + FLAG(DEAUTH_NEED_MGD_TX_PREP), #undef FLAG }; diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index 444ea8d127fe..4105081dc1df 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -160,12 +160,12 @@ static ssize_t sta_aqm_read(struct file *file, char __user *userbuf, sta->cparams.ecn ? "yes" : "no"); p += scnprintf(p, bufsz+buf-p, - "tid ac backlog-bytes backlog-packets new-flows drops marks overlimit collisions tx-bytes tx-packets\n"); + "tid ac backlog-bytes backlog-packets new-flows drops marks overlimit collisions tx-bytes tx-packets flags\n"); for (i = 0; i < IEEE80211_NUM_TIDS; i++) { txqi = to_txq_info(sta->sta.txq[i]); p += scnprintf(p, bufsz+buf-p, - "%d %d %u %u %u %u %u %u %u %u %u\n", + "%d %d %u %u %u %u %u %u %u %u %u 0x%lx(%s%s%s)\n", txqi->txq.tid, txqi->txq.ac, txqi->tin.backlog_bytes, @@ -176,7 +176,11 @@ static ssize_t sta_aqm_read(struct file *file, char __user *userbuf, txqi->tin.overlimit, txqi->tin.collisions, txqi->tin.tx_bytes, - txqi->tin.tx_packets); + txqi->tin.tx_packets, + txqi->flags, + txqi->flags & (1<<IEEE80211_TXQ_STOP) ? "STOP" : "RUN", + txqi->flags & (1<<IEEE80211_TXQ_AMPDU) ? " AMPDU" : "", + txqi->flags & (1<<IEEE80211_TXQ_NO_AMSDU) ? " NO-AMSDU" : ""); } rcu_read_unlock(); diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 26900025de2f..ae9c33cd8ada 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1467,7 +1467,7 @@ struct ieee802_11_elems { const struct ieee80211_timeout_interval_ie *timeout_int; const u8 *opmode_notif; const struct ieee80211_sec_chan_offs_ie *sec_chan_offs; - const struct ieee80211_mesh_chansw_params_ie *mesh_chansw_params_ie; + struct ieee80211_mesh_chansw_params_ie *mesh_chansw_params_ie; const struct ieee80211_bss_max_idle_period_ie *max_idle_period_ie; /* length of them, respectively */ diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 5fe01f82df12..d13ba064951f 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1324,8 +1324,7 @@ static void ieee80211_iface_work(struct work_struct *work) mutex_lock(&local->sta_mtx); sta = sta_info_get_bss(sdata, mgmt->sa); if (sta) { - u16 tid = *ieee80211_get_qos_ctl(hdr) & - IEEE80211_QOS_CTL_TID_MASK; + u16 tid = ieee80211_get_tid(hdr); __ieee80211_stop_rx_ba_session( sta, tid, WLAN_BACK_RECIPIENT, diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 73ac607beb5d..6a381cbe1e33 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -1255,13 +1255,12 @@ int ieee80211_mesh_csa_beacon(struct ieee80211_sub_if_data *sdata, } static int mesh_fwd_csa_frame(struct ieee80211_sub_if_data *sdata, - struct ieee80211_mgmt *mgmt, size_t len) + struct ieee80211_mgmt *mgmt, size_t len, + struct ieee802_11_elems *elems) { struct ieee80211_mgmt *mgmt_fwd; struct sk_buff *skb; struct ieee80211_local *local = sdata->local; - u8 *pos = mgmt->u.action.u.chan_switch.variable; - size_t offset_ttl; skb = dev_alloc_skb(local->tx_headroom + len); if (!skb) @@ -1269,13 +1268,9 @@ static int mesh_fwd_csa_frame(struct ieee80211_sub_if_data *sdata, skb_reserve(skb, local->tx_headroom); mgmt_fwd = skb_put(skb, len); - /* offset_ttl is based on whether the secondary channel - * offset is available or not. Subtract 1 from the mesh TTL - * and disable the initiator flag before forwarding. - */ - offset_ttl = (len < 42) ? 7 : 10; - *(pos + offset_ttl) -= 1; - *(pos + offset_ttl + 1) &= ~WLAN_EID_CHAN_SWITCH_PARAM_INITIATOR; + elems->mesh_chansw_params_ie->mesh_ttl--; + elems->mesh_chansw_params_ie->mesh_flags &= + ~WLAN_EID_CHAN_SWITCH_PARAM_INITIATOR; memcpy(mgmt_fwd, mgmt, len); eth_broadcast_addr(mgmt_fwd->da); @@ -1323,7 +1318,7 @@ static void mesh_rx_csa_frame(struct ieee80211_sub_if_data *sdata, /* forward or re-broadcast the CSA frame */ if (fwd_csa) { - if (mesh_fwd_csa_frame(sdata, mgmt, len) < 0) + if (mesh_fwd_csa_frame(sdata, mgmt, len, &elems) < 0) mcsa_dbg(sdata, "Failed to forward the CSA frame"); } } diff --git a/net/mac80211/michael.c b/net/mac80211/michael.c index 408649bd4702..37e172701a63 100644 --- a/net/mac80211/michael.c +++ b/net/mac80211/michael.c @@ -35,7 +35,7 @@ static void michael_mic_hdr(struct michael_mic_ctx *mctx, const u8 *key, da = ieee80211_get_DA(hdr); sa = ieee80211_get_SA(hdr); if (ieee80211_is_data_qos(hdr->frame_control)) - tid = *ieee80211_get_qos_ctl(hdr) & IEEE80211_QOS_CTL_TID_MASK; + tid = ieee80211_get_tid(hdr); else tid = 0; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 39b660b9a908..0024eff9bb84 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -7,6 +7,7 @@ * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015 - 2017 Intel Deutschland GmbH + * Copyright (C) 2018 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -2008,9 +2009,22 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, ieee80211_flush_queues(local, sdata, true); /* deauthenticate/disassociate now */ - if (tx || frame_buf) + if (tx || frame_buf) { + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + + /* + * In multi channel scenarios guarantee that the virtual + * interface is granted immediate airtime to transmit the + * deauthentication frame by calling mgd_prepare_tx, if the + * driver requested so. + */ + if (ieee80211_hw_check(&local->hw, DEAUTH_NEED_MGD_TX_PREP) && + !ifmgd->have_beacon) + drv_mgd_prepare_tx(sdata->local, sdata); + ieee80211_send_deauth_disassoc(sdata, ifmgd->bssid, stype, reason, tx, frame_buf); + } /* flush out frame - make sure the deauth was actually sent */ if (tx) @@ -2151,7 +2165,7 @@ static void ieee80211_sta_tx_wmm_ac_notify(struct ieee80211_sub_if_data *sdata, u16 tx_time) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - u16 tid = *ieee80211_get_qos_ctl(hdr) & IEEE80211_QOS_CTL_TID_MASK; + u16 tid = ieee80211_get_tid(hdr); int ac = ieee80211_ac_from_tid(tid); struct ieee80211_sta_tx_tspec *tx_tspec = &ifmgd->tx_tspec[ac]; unsigned long now = jiffies; diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 4a5bdad9f303..fb586b6e5d49 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -669,7 +669,7 @@ minstrel_aggr_check(struct ieee80211_sta *pubsta, struct sk_buff *skb) if (unlikely(skb->protocol == cpu_to_be16(ETH_P_PAE))) return; - tid = *ieee80211_get_qos_ctl(hdr) & IEEE80211_QOS_CTL_TID_MASK; + tid = ieee80211_get_tid(hdr); if (likely(sta->ampdu_mlme.tid_tx[tid])) return; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index fd580614085b..3dc162ddc3a6 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -439,6 +439,10 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, flags |= IEEE80211_RADIOTAP_AMPDU_DELIM_CRC_ERR; if (status->flag & RX_FLAG_AMPDU_DELIM_CRC_KNOWN) flags |= IEEE80211_RADIOTAP_AMPDU_DELIM_CRC_KNOWN; + if (status->flag & RX_FLAG_AMPDU_EOF_BIT_KNOWN) + flags |= IEEE80211_RADIOTAP_AMPDU_EOF_KNOWN; + if (status->flag & RX_FLAG_AMPDU_EOF_BIT) + flags |= IEEE80211_RADIOTAP_AMPDU_EOF; put_unaligned_le16(flags, pos); pos += 2; if (status->flag & RX_FLAG_AMPDU_DELIM_CRC_KNOWN) @@ -1185,7 +1189,7 @@ static void ieee80211_rx_reorder_ampdu(struct ieee80211_rx_data *rx, ack_policy = *ieee80211_get_qos_ctl(hdr) & IEEE80211_QOS_CTL_ACK_POLICY_MASK; - tid = *ieee80211_get_qos_ctl(hdr) & IEEE80211_QOS_CTL_TID_MASK; + tid = ieee80211_get_tid(hdr); tid_agg_rx = rcu_dereference(sta->ampdu_mlme.tid_rx[tid]); if (!tid_agg_rx) { @@ -1524,9 +1528,7 @@ ieee80211_rx_h_uapsd_and_pspoll(struct ieee80211_rx_data *rx) ieee80211_has_pm(hdr->frame_control) && (ieee80211_is_data_qos(hdr->frame_control) || ieee80211_is_qos_nullfunc(hdr->frame_control))) { - u8 tid; - - tid = *ieee80211_get_qos_ctl(hdr) & IEEE80211_QOS_CTL_TID_MASK; + u8 tid = ieee80211_get_tid(hdr); ieee80211_sta_uapsd_trigger(&rx->sta->sta, tid); } @@ -2848,6 +2850,7 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) case WLAN_HT_ACTION_SMPS: { struct ieee80211_supported_band *sband; enum ieee80211_smps_mode smps_mode; + struct sta_opmode_info sta_opmode = {}; /* convert to HT capability */ switch (mgmt->u.action.u.ht_smps.smps_control) { @@ -2868,17 +2871,24 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) if (rx->sta->sta.smps_mode == smps_mode) goto handled; rx->sta->sta.smps_mode = smps_mode; + sta_opmode.smps_mode = smps_mode; + sta_opmode.changed = STA_OPMODE_SMPS_MODE_CHANGED; sband = rx->local->hw.wiphy->bands[status->band]; rate_control_rate_update(local, sband, rx->sta, IEEE80211_RC_SMPS_CHANGED); + cfg80211_sta_opmode_change_notify(sdata->dev, + rx->sta->addr, + &sta_opmode, + GFP_KERNEL); goto handled; } case WLAN_HT_ACTION_NOTIFY_CHANWIDTH: { struct ieee80211_supported_band *sband; u8 chanwidth = mgmt->u.action.u.ht_notify_cw.chanwidth; enum ieee80211_sta_rx_bandwidth max_bw, new_bw; + struct sta_opmode_info sta_opmode = {}; /* If it doesn't support 40 MHz it can't change ... */ if (!(rx->sta->sta.ht_cap.cap & @@ -2899,9 +2909,15 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) rx->sta->sta.bandwidth = new_bw; sband = rx->local->hw.wiphy->bands[status->band]; + sta_opmode.bw = new_bw; + sta_opmode.changed = STA_OPMODE_MAX_BW_CHANGED; rate_control_rate_update(local, sband, rx->sta, IEEE80211_RC_BW_CHANGED); + cfg80211_sta_opmode_change_notify(sdata->dev, + rx->sta->addr, + &sta_opmode, + GFP_KERNEL); goto handled; } default: diff --git a/net/mac80211/spectmgmt.c b/net/mac80211/spectmgmt.c index ee0181778a42..029334835747 100644 --- a/net/mac80211/spectmgmt.c +++ b/net/mac80211/spectmgmt.c @@ -8,6 +8,7 @@ * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2007-2008, Intel Corporation * Copyright 2008, Johannes Berg <johannes@sipsolutions.net> + * Copyright (C) 2018 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -27,7 +28,7 @@ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, u32 sta_flags, u8 *bssid, struct ieee80211_csa_ie *csa_ie) { - enum nl80211_band new_band; + enum nl80211_band new_band = current_band; int new_freq; u8 new_chan_no; struct ieee80211_channel *new_chan; @@ -55,15 +56,13 @@ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, elems->ext_chansw_ie->new_operating_class, &new_band)) { sdata_info(sdata, - "cannot understand ECSA IE operating class %d, disconnecting\n", + "cannot understand ECSA IE operating class, %d, ignoring\n", elems->ext_chansw_ie->new_operating_class); - return -EINVAL; } new_chan_no = elems->ext_chansw_ie->new_ch_num; csa_ie->count = elems->ext_chansw_ie->count; csa_ie->mode = elems->ext_chansw_ie->mode; } else if (elems->ch_switch_ie) { - new_band = current_band; new_chan_no = elems->ch_switch_ie->new_ch_num; csa_ie->count = elems->ch_switch_ie->count; csa_ie->mode = elems->ch_switch_ie->mode; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 0c5627f8a104..655c3d8b0d80 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -314,7 +314,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, if (ieee80211_hw_check(hw, USES_RSS)) { sta->pcpu_rx_stats = - alloc_percpu(struct ieee80211_sta_rx_stats); + alloc_percpu_gfp(struct ieee80211_sta_rx_stats, gfp); if (!sta->pcpu_rx_stats) goto free; } @@ -433,6 +433,7 @@ free_txq: if (sta->sta.txq[0]) kfree(to_txq_info(sta->sta.txq[0])); free: + free_percpu(sta->pcpu_rx_stats); #ifdef CONFIG_MAC80211_MESH kfree(sta->mesh); #endif @@ -2287,6 +2288,12 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) sinfo->filled |= BIT(NL80211_STA_INFO_EXPECTED_THROUGHPUT); sinfo->expected_throughput = thr; } + + if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_ACK_SIGNAL)) && + sta->status_stats.ack_signal_filled) { + sinfo->ack_signal = sta->status_stats.last_ack_signal; + sinfo->filled |= BIT_ULL(NL80211_STA_INFO_ACK_SIGNAL); + } } u32 sta_get_expected_throughput(struct sta_info *sta) diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index cd53619435b6..f64eb86ca64b 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -548,6 +548,8 @@ struct sta_info { u64 msdu_retries[IEEE80211_NUM_TIDS + 1]; u64 msdu_failed[IEEE80211_NUM_TIDS + 1]; unsigned long last_ack; + s8 last_ack_signal; + bool ack_signal_filled; } status_stats; /* Updated from TX path only, no locking requirements */ diff --git a/net/mac80211/status.c b/net/mac80211/status.c index da7427a41529..743e89c5926c 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -187,9 +187,16 @@ static void ieee80211_frame_acked(struct sta_info *sta, struct sk_buff *skb) struct ieee80211_mgmt *mgmt = (void *) skb->data; struct ieee80211_local *local = sta->local; struct ieee80211_sub_if_data *sdata = sta->sdata; + struct ieee80211_tx_info *txinfo = IEEE80211_SKB_CB(skb); - if (ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) + if (ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) { sta->status_stats.last_ack = jiffies; + if (txinfo->status.is_valid_ack_signal) { + sta->status_stats.last_ack_signal = + (s8)txinfo->status.ack_signal; + sta->status_stats.ack_signal_filled = true; + } + } if (ieee80211_is_data_qos(mgmt->frame_control)) { struct ieee80211_hdr *hdr = (void *) skb->data; @@ -487,6 +494,8 @@ static void ieee80211_report_ack_skb(struct ieee80211_local *local, ieee80211_is_qos_nullfunc(hdr->frame_control)) cfg80211_probe_status(sdata->dev, hdr->addr1, cookie, acked, + info->status.ack_signal, + info->status.is_valid_ack_signal, GFP_ATOMIC); else cfg80211_mgmt_tx_status(&sdata->wdev, cookie, diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 25904af38839..7643178ef132 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -797,7 +797,6 @@ ieee80211_tx_h_sequence(struct ieee80211_tx_data *tx) { struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb); struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data; - u8 *qc; int tid; /* @@ -844,9 +843,7 @@ ieee80211_tx_h_sequence(struct ieee80211_tx_data *tx) return TX_CONTINUE; /* include per-STA, per-TID sequence counter */ - - qc = ieee80211_get_qos_ctl(hdr); - tid = *qc & IEEE80211_QOS_CTL_TID_MASK; + tid = ieee80211_get_tid(hdr); tx->sta->tx_stats.msdu[tid]++; hdr->seq_ctrl = ieee80211_tx_next_seq(tx->sta, tid); @@ -1158,7 +1155,6 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, struct ieee80211_hdr *hdr; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); int tid; - u8 *qc; memset(tx, 0, sizeof(*tx)); tx->skb = skb; @@ -1198,8 +1194,7 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, !ieee80211_hw_check(&local->hw, TX_AMPDU_SETUP_IN_HW)) { struct tid_ampdu_tx *tid_tx; - qc = ieee80211_get_qos_ctl(hdr); - tid = *qc & IEEE80211_QOS_CTL_TID_MASK; + tid = ieee80211_get_tid(hdr); tid_tx = rcu_dereference(tx->sta->ampdu_mlme.tid_tx[tid]); if (tid_tx) { @@ -1921,7 +1916,7 @@ void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, { struct ieee80211_local *local = sdata->local; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; + struct ieee80211_hdr *hdr; int headroom; bool may_encrypt; diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index b9276ac849fa..5714dee76b12 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -447,6 +447,7 @@ u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, enum nl80211_band band) { enum ieee80211_sta_rx_bandwidth new_bw; + struct sta_opmode_info sta_opmode = {}; u32 changed = 0; u8 nss; @@ -460,7 +461,9 @@ u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, if (sta->sta.rx_nss != nss) { sta->sta.rx_nss = nss; + sta_opmode.rx_nss = nss; changed |= IEEE80211_RC_NSS_CHANGED; + sta_opmode.changed |= STA_OPMODE_N_SS_CHANGED; } switch (opmode & IEEE80211_OPMODE_NOTIF_CHANWIDTH_MASK) { @@ -481,9 +484,15 @@ u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, new_bw = ieee80211_sta_cur_vht_bw(sta); if (new_bw != sta->sta.bandwidth) { sta->sta.bandwidth = new_bw; + sta_opmode.bw = new_bw; changed |= IEEE80211_RC_BW_CHANGED; + sta_opmode.changed |= STA_OPMODE_MAX_BW_CHANGED; } + if (sta_opmode.changed) + cfg80211_sta_opmode_change_notify(sdata->dev, sta->addr, + &sta_opmode, GFP_KERNEL); + return changed; } diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index 785056cb76f6..58d0b258b684 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -340,7 +340,7 @@ static void ccmp_special_blocks(struct sk_buff *skb, u8 *pn, u8 *b_0, u8 *aad) a4_included = ieee80211_has_a4(hdr->frame_control); if (ieee80211_is_data_qos(hdr->frame_control)) - qos_tid = *ieee80211_get_qos_ctl(hdr) & IEEE80211_QOS_CTL_TID_MASK; + qos_tid = ieee80211_get_tid(hdr); else qos_tid = 0; @@ -601,8 +601,7 @@ static void gcmp_special_blocks(struct sk_buff *skb, u8 *pn, u8 *j_0, u8 *aad) aad[23] = 0; if (ieee80211_is_data_qos(hdr->frame_control)) - qos_tid = *ieee80211_get_qos_ctl(hdr) & - IEEE80211_QOS_CTL_TID_MASK; + qos_tid = ieee80211_get_tid(hdr); else qos_tid = 0; @@ -867,8 +866,7 @@ ieee80211_crypto_cs_decrypt(struct ieee80211_rx_data *rx) return RX_DROP_UNUSABLE; if (ieee80211_is_data_qos(hdr->frame_control)) - qos_tid = *ieee80211_get_qos_ctl(hdr) & - IEEE80211_QOS_CTL_TID_MASK; + qos_tid = ieee80211_get_tid(hdr); else qos_tid = 0; diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 0f6b8172fb9a..d72cc786c7b7 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -629,6 +629,7 @@ static void __net_exit netfilter_net_exit(struct net *net) static struct pernet_operations netfilter_net_ops = { .init = netfilter_net_init, .exit = netfilter_net_exit, + .async = true, }; int __init netfilter_init(void) diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index d625179de485..6a340c94c4b8 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -604,6 +604,7 @@ static void __net_exit __ip_vs_lblc_exit(struct net *net) { } static struct pernet_operations ip_vs_lblc_ops = { .init = __ip_vs_lblc_init, .exit = __ip_vs_lblc_exit, + .async = true, }; static int __init ip_vs_lblc_init(void) diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index 84c57b62a588..0627881128da 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -789,6 +789,7 @@ static void __net_exit __ip_vs_lblcr_exit(struct net *net) { } static struct pernet_operations ip_vs_lblcr_ops = { .init = __ip_vs_lblcr_init, .exit = __ip_vs_lblcr_exit, + .async = true, }; static int __init ip_vs_lblcr_init(void) diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index c2c1b16b7538..1ba3da51050d 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -577,6 +577,7 @@ static void __net_exit nf_log_net_exit(struct net *net) static struct pernet_operations nf_log_net_ops = { .init = nf_log_net_init, .exit = nf_log_net_exit, + .async = true, }; int __init netfilter_log_init(void) diff --git a/net/netfilter/nf_nat_proto_common.c b/net/netfilter/nf_nat_proto_common.c index fbce552a796e..7d7466dbf663 100644 --- a/net/netfilter/nf_nat_proto_common.c +++ b/net/netfilter/nf_nat_proto_common.c @@ -41,7 +41,7 @@ void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto, const struct nf_conn *ct, u16 *rover) { - unsigned int range_size, min, i; + unsigned int range_size, min, max, i; __be16 *portptr; u_int16_t off; @@ -71,7 +71,10 @@ void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto, } } else { min = ntohs(range->min_proto.all); - range_size = ntohs(range->max_proto.all) - min + 1; + max = ntohs(range->max_proto.all); + if (unlikely(max < min)) + swap(max, min); + range_size = max - min + 1; } if (range->flags & NF_NAT_RANGE_PROTO_RANDOM) { diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index 92139a087260..64b875e452ca 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -398,6 +398,7 @@ static struct pernet_operations synproxy_net_ops = { .exit = synproxy_net_exit, .id = &synproxy_net_id, .size = sizeof(struct synproxy_net), + .async = true, }; static int __init synproxy_core_init(void) diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 2f685ee1f9c8..d9deebe599ec 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -434,36 +434,35 @@ int xt_check_match(struct xt_mtchk_param *par, * ebt_among is exempt from centralized matchsize checking * because it uses a dynamic-size data set. */ - pr_err("%s_tables: %s.%u match: invalid size " - "%u (kernel) != (user) %u\n", - xt_prefix[par->family], par->match->name, - par->match->revision, - XT_ALIGN(par->match->matchsize), size); + pr_err_ratelimited("%s_tables: %s.%u match: invalid size %u (kernel) != (user) %u\n", + xt_prefix[par->family], par->match->name, + par->match->revision, + XT_ALIGN(par->match->matchsize), size); return -EINVAL; } if (par->match->table != NULL && strcmp(par->match->table, par->table) != 0) { - pr_err("%s_tables: %s match: only valid in %s table, not %s\n", - xt_prefix[par->family], par->match->name, - par->match->table, par->table); + pr_info_ratelimited("%s_tables: %s match: only valid in %s table, not %s\n", + xt_prefix[par->family], par->match->name, + par->match->table, par->table); return -EINVAL; } if (par->match->hooks && (par->hook_mask & ~par->match->hooks) != 0) { char used[64], allow[64]; - pr_err("%s_tables: %s match: used from hooks %s, but only " - "valid from %s\n", - xt_prefix[par->family], par->match->name, - textify_hooks(used, sizeof(used), par->hook_mask, - par->family), - textify_hooks(allow, sizeof(allow), par->match->hooks, - par->family)); + pr_info_ratelimited("%s_tables: %s match: used from hooks %s, but only valid from %s\n", + xt_prefix[par->family], par->match->name, + textify_hooks(used, sizeof(used), + par->hook_mask, par->family), + textify_hooks(allow, sizeof(allow), + par->match->hooks, + par->family)); return -EINVAL; } if (par->match->proto && (par->match->proto != proto || inv_proto)) { - pr_err("%s_tables: %s match: only valid for protocol %u\n", - xt_prefix[par->family], par->match->name, - par->match->proto); + pr_info_ratelimited("%s_tables: %s match: only valid for protocol %u\n", + xt_prefix[par->family], par->match->name, + par->match->proto); return -EINVAL; } if (par->match->checkentry != NULL) { @@ -814,36 +813,35 @@ int xt_check_target(struct xt_tgchk_param *par, int ret; if (XT_ALIGN(par->target->targetsize) != size) { - pr_err("%s_tables: %s.%u target: invalid size " - "%u (kernel) != (user) %u\n", - xt_prefix[par->family], par->target->name, - par->target->revision, - XT_ALIGN(par->target->targetsize), size); + pr_err_ratelimited("%s_tables: %s.%u target: invalid size %u (kernel) != (user) %u\n", + xt_prefix[par->family], par->target->name, + par->target->revision, + XT_ALIGN(par->target->targetsize), size); return -EINVAL; } if (par->target->table != NULL && strcmp(par->target->table, par->table) != 0) { - pr_err("%s_tables: %s target: only valid in %s table, not %s\n", - xt_prefix[par->family], par->target->name, - par->target->table, par->table); + pr_info_ratelimited("%s_tables: %s target: only valid in %s table, not %s\n", + xt_prefix[par->family], par->target->name, + par->target->table, par->table); return -EINVAL; } if (par->target->hooks && (par->hook_mask & ~par->target->hooks) != 0) { char used[64], allow[64]; - pr_err("%s_tables: %s target: used from hooks %s, but only " - "usable from %s\n", - xt_prefix[par->family], par->target->name, - textify_hooks(used, sizeof(used), par->hook_mask, - par->family), - textify_hooks(allow, sizeof(allow), par->target->hooks, - par->family)); + pr_info_ratelimited("%s_tables: %s target: used from hooks %s, but only usable from %s\n", + xt_prefix[par->family], par->target->name, + textify_hooks(used, sizeof(used), + par->hook_mask, par->family), + textify_hooks(allow, sizeof(allow), + par->target->hooks, + par->family)); return -EINVAL; } if (par->target->proto && (par->target->proto != proto || inv_proto)) { - pr_err("%s_tables: %s target: only valid for protocol %u\n", - xt_prefix[par->family], par->target->name, - par->target->proto); + pr_info_ratelimited("%s_tables: %s target: only valid for protocol %u\n", + xt_prefix[par->family], par->target->name, + par->target->proto); return -EINVAL; } if (par->target->checkentry != NULL) { @@ -1004,10 +1002,6 @@ struct xt_table_info *xt_alloc_table_info(unsigned int size) if (sz < sizeof(*info)) return NULL; - /* Pedantry: prevent them from hitting BUG() in vmalloc.c --RR */ - if ((size >> PAGE_SHIFT) + 2 > totalram_pages) - return NULL; - /* __GFP_NORETRY is not fully supported by kvmalloc but it should * work reasonably well if sz is too large and bail out rather * than shoot all processes down before realizing there is nothing @@ -1765,6 +1759,7 @@ static void __net_exit xt_net_exit(struct net *net) static struct pernet_operations xt_net_ops = { .init = xt_net_init, .exit = xt_net_exit, + .async = true, }; static int __init xt_init(void) diff --git a/net/netfilter/xt_AUDIT.c b/net/netfilter/xt_AUDIT.c index c502419d6306..f368ee6741db 100644 --- a/net/netfilter/xt_AUDIT.c +++ b/net/netfilter/xt_AUDIT.c @@ -120,8 +120,8 @@ static int audit_tg_check(const struct xt_tgchk_param *par) const struct xt_audit_info *info = par->targinfo; if (info->type > XT_AUDIT_TYPE_MAX) { - pr_info("Audit type out of range (valid range: 0..%hhu)\n", - XT_AUDIT_TYPE_MAX); + pr_info_ratelimited("Audit type out of range (valid range: 0..%hhu)\n", + XT_AUDIT_TYPE_MAX); return -ERANGE; } diff --git a/net/netfilter/xt_CHECKSUM.c b/net/netfilter/xt_CHECKSUM.c index 0f642ef8cd26..9f4151ec3e06 100644 --- a/net/netfilter/xt_CHECKSUM.c +++ b/net/netfilter/xt_CHECKSUM.c @@ -36,13 +36,13 @@ static int checksum_tg_check(const struct xt_tgchk_param *par) const struct xt_CHECKSUM_info *einfo = par->targinfo; if (einfo->operation & ~XT_CHECKSUM_OP_FILL) { - pr_info("unsupported CHECKSUM operation %x\n", einfo->operation); + pr_info_ratelimited("unsupported CHECKSUM operation %x\n", + einfo->operation); return -EINVAL; } - if (!einfo->operation) { - pr_info("no CHECKSUM operation enabled\n"); + if (!einfo->operation) return -EINVAL; - } + return 0; } diff --git a/net/netfilter/xt_CONNSECMARK.c b/net/netfilter/xt_CONNSECMARK.c index da56c06a443c..f3f1caac949b 100644 --- a/net/netfilter/xt_CONNSECMARK.c +++ b/net/netfilter/xt_CONNSECMARK.c @@ -91,8 +91,8 @@ static int connsecmark_tg_check(const struct xt_tgchk_param *par) if (strcmp(par->table, "mangle") != 0 && strcmp(par->table, "security") != 0) { - pr_info("target only valid in the \'mangle\' " - "or \'security\' tables, not \'%s\'.\n", par->table); + pr_info_ratelimited("only valid in \'mangle\' or \'security\' table, not \'%s\'\n", + par->table); return -EINVAL; } @@ -102,14 +102,14 @@ static int connsecmark_tg_check(const struct xt_tgchk_param *par) break; default: - pr_info("invalid mode: %hu\n", info->mode); + pr_info_ratelimited("invalid mode: %hu\n", info->mode); return -EINVAL; } ret = nf_ct_netns_get(par->net, par->family); if (ret < 0) - pr_info("cannot load conntrack support for proto=%u\n", - par->family); + pr_info_ratelimited("cannot load conntrack support for proto=%u\n", + par->family); return ret; } diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index 5a152e2acfd5..8790190c6feb 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -82,15 +82,14 @@ xt_ct_set_helper(struct nf_conn *ct, const char *helper_name, proto = xt_ct_find_proto(par); if (!proto) { - pr_info("You must specify a L4 protocol, and not use " - "inversions on it.\n"); + pr_info_ratelimited("You must specify a L4 protocol and not use inversions on it\n"); return -ENOENT; } helper = nf_conntrack_helper_try_module_get(helper_name, par->family, proto); if (helper == NULL) { - pr_info("No such helper \"%s\"\n", helper_name); + pr_info_ratelimited("No such helper \"%s\"\n", helper_name); return -ENOENT; } @@ -124,6 +123,7 @@ xt_ct_set_timeout(struct nf_conn *ct, const struct xt_tgchk_param *par, const struct nf_conntrack_l4proto *l4proto; struct ctnl_timeout *timeout; struct nf_conn_timeout *timeout_ext; + const char *errmsg = NULL; int ret = 0; u8 proto; @@ -131,29 +131,29 @@ xt_ct_set_timeout(struct nf_conn *ct, const struct xt_tgchk_param *par, timeout_find_get = rcu_dereference(nf_ct_timeout_find_get_hook); if (timeout_find_get == NULL) { ret = -ENOENT; - pr_info("Timeout policy base is empty\n"); + errmsg = "Timeout policy base is empty"; goto out; } proto = xt_ct_find_proto(par); if (!proto) { ret = -EINVAL; - pr_info("You must specify a L4 protocol, and not use " - "inversions on it.\n"); + errmsg = "You must specify a L4 protocol and not use inversions on it"; goto out; } timeout = timeout_find_get(par->net, timeout_name); if (timeout == NULL) { ret = -ENOENT; - pr_info("No such timeout policy \"%s\"\n", timeout_name); + pr_info_ratelimited("No such timeout policy \"%s\"\n", + timeout_name); goto out; } if (timeout->l3num != par->family) { ret = -EINVAL; - pr_info("Timeout policy `%s' can only be used by L3 protocol " - "number %d\n", timeout_name, timeout->l3num); + pr_info_ratelimited("Timeout policy `%s' can only be used by L%d protocol number %d\n", + timeout_name, 3, timeout->l3num); goto err_put_timeout; } /* Make sure the timeout policy matches any existing protocol tracker, @@ -162,9 +162,8 @@ xt_ct_set_timeout(struct nf_conn *ct, const struct xt_tgchk_param *par, l4proto = __nf_ct_l4proto_find(par->family, proto); if (timeout->l4proto->l4proto != l4proto->l4proto) { ret = -EINVAL; - pr_info("Timeout policy `%s' can only be used by L4 protocol " - "number %d\n", - timeout_name, timeout->l4proto->l4proto); + pr_info_ratelimited("Timeout policy `%s' can only be used by L%d protocol number %d\n", + timeout_name, 4, timeout->l4proto->l4proto); goto err_put_timeout; } timeout_ext = nf_ct_timeout_ext_add(ct, timeout, GFP_ATOMIC); @@ -180,6 +179,8 @@ err_put_timeout: __xt_ct_tg_timeout_put(timeout); out: rcu_read_unlock(); + if (errmsg) + pr_info_ratelimited("%s\n", errmsg); return ret; #else return -EOPNOTSUPP; diff --git a/net/netfilter/xt_DSCP.c b/net/netfilter/xt_DSCP.c index 3f83d38c4e5b..098ed851b7a7 100644 --- a/net/netfilter/xt_DSCP.c +++ b/net/netfilter/xt_DSCP.c @@ -66,10 +66,8 @@ static int dscp_tg_check(const struct xt_tgchk_param *par) { const struct xt_DSCP_info *info = par->targinfo; - if (info->dscp > XT_DSCP_MAX) { - pr_info("dscp %x out of range\n", info->dscp); + if (info->dscp > XT_DSCP_MAX) return -EDOM; - } return 0; } diff --git a/net/netfilter/xt_HL.c b/net/netfilter/xt_HL.c index 1535e87ed9bd..4653b071bed4 100644 --- a/net/netfilter/xt_HL.c +++ b/net/netfilter/xt_HL.c @@ -105,10 +105,8 @@ static int ttl_tg_check(const struct xt_tgchk_param *par) { const struct ipt_TTL_info *info = par->targinfo; - if (info->mode > IPT_TTL_MAXMODE) { - pr_info("TTL: invalid or unknown mode %u\n", info->mode); + if (info->mode > IPT_TTL_MAXMODE) return -EINVAL; - } if (info->mode != IPT_TTL_SET && info->ttl == 0) return -EINVAL; return 0; @@ -118,15 +116,10 @@ static int hl_tg6_check(const struct xt_tgchk_param *par) { const struct ip6t_HL_info *info = par->targinfo; - if (info->mode > IP6T_HL_MAXMODE) { - pr_info("invalid or unknown mode %u\n", info->mode); + if (info->mode > IP6T_HL_MAXMODE) return -EINVAL; - } - if (info->mode != IP6T_HL_SET && info->hop_limit == 0) { - pr_info("increment/decrement does not " - "make sense with value 0\n"); + if (info->mode != IP6T_HL_SET && info->hop_limit == 0) return -EINVAL; - } return 0; } diff --git a/net/netfilter/xt_HMARK.c b/net/netfilter/xt_HMARK.c index 60e6dbe12460..9c75f419cd80 100644 --- a/net/netfilter/xt_HMARK.c +++ b/net/netfilter/xt_HMARK.c @@ -9,6 +9,8 @@ * the Free Software Foundation. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/skbuff.h> #include <linux/icmp.h> @@ -312,29 +314,30 @@ hmark_tg_v4(struct sk_buff *skb, const struct xt_action_param *par) static int hmark_tg_check(const struct xt_tgchk_param *par) { const struct xt_hmark_info *info = par->targinfo; + const char *errmsg = "proto mask must be zero with L3 mode"; - if (!info->hmodulus) { - pr_info("xt_HMARK: hash modulus can't be zero\n"); + if (!info->hmodulus) return -EINVAL; - } + if (info->proto_mask && - (info->flags & XT_HMARK_FLAG(XT_HMARK_METHOD_L3))) { - pr_info("xt_HMARK: proto mask must be zero with L3 mode\n"); - return -EINVAL; - } + (info->flags & XT_HMARK_FLAG(XT_HMARK_METHOD_L3))) + goto err; + if (info->flags & XT_HMARK_FLAG(XT_HMARK_SPI_MASK) && (info->flags & (XT_HMARK_FLAG(XT_HMARK_SPORT_MASK) | - XT_HMARK_FLAG(XT_HMARK_DPORT_MASK)))) { - pr_info("xt_HMARK: spi-mask and port-mask can't be combined\n"); + XT_HMARK_FLAG(XT_HMARK_DPORT_MASK)))) return -EINVAL; - } + if (info->flags & XT_HMARK_FLAG(XT_HMARK_SPI) && (info->flags & (XT_HMARK_FLAG(XT_HMARK_SPORT) | XT_HMARK_FLAG(XT_HMARK_DPORT)))) { - pr_info("xt_HMARK: spi-set and port-set can't be combined\n"); - return -EINVAL; + errmsg = "spi-set and port-set can't be combined"; + goto err; } return 0; +err: + pr_info_ratelimited("%s\n", errmsg); + return -EINVAL; } static struct xt_target hmark_tg_reg[] __read_mostly = { diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index 6c2482b709b1..1ac6600bfafd 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -146,11 +146,11 @@ static int idletimer_tg_create(struct idletimer_tg_info *info) timer_setup(&info->timer->timer, idletimer_tg_expired, 0); info->timer->refcnt = 1; + INIT_WORK(&info->timer->work, idletimer_tg_work); + mod_timer(&info->timer->timer, msecs_to_jiffies(info->timeout * 1000) + jiffies); - INIT_WORK(&info->timer->work, idletimer_tg_work); - return 0; out_free_attr: @@ -191,7 +191,10 @@ static int idletimer_tg_checkentry(const struct xt_tgchk_param *par) pr_debug("timeout value is zero\n"); return -EINVAL; } - + if (info->timeout >= INT_MAX / 1000) { + pr_debug("timeout value is too big\n"); + return -EINVAL; + } if (info->label[0] == '\0' || strnlen(info->label, MAX_IDLETIMER_LABEL_SIZE) == MAX_IDLETIMER_LABEL_SIZE) { diff --git a/net/netfilter/xt_LED.c b/net/netfilter/xt_LED.c index 1dcad893df78..19846445504d 100644 --- a/net/netfilter/xt_LED.c +++ b/net/netfilter/xt_LED.c @@ -111,10 +111,8 @@ static int led_tg_check(const struct xt_tgchk_param *par) struct xt_led_info_internal *ledinternal; int err; - if (ledinfo->id[0] == '\0') { - pr_info("No 'id' parameter given.\n"); + if (ledinfo->id[0] == '\0') return -EINVAL; - } mutex_lock(&xt_led_mutex); @@ -138,13 +136,14 @@ static int led_tg_check(const struct xt_tgchk_param *par) err = led_trigger_register(&ledinternal->netfilter_led_trigger); if (err) { - pr_err("Trigger name is already in use.\n"); + pr_info_ratelimited("Trigger name is already in use.\n"); goto exit_alloc; } - /* See if we need to set up a timer */ - if (ledinfo->delay > 0) - timer_setup(&ledinternal->timer, led_timeout_callback, 0); + /* Since the letinternal timer can be shared between multiple targets, + * always set it up, even if the current target does not need it + */ + timer_setup(&ledinternal->timer, led_timeout_callback, 0); list_add_tail(&ledinternal->list, &xt_led_triggers); @@ -181,8 +180,7 @@ static void led_tg_destroy(const struct xt_tgdtor_param *par) list_del(&ledinternal->list); - if (ledinfo->delay > 0) - del_timer_sync(&ledinternal->timer); + del_timer_sync(&ledinternal->timer); led_trigger_unregister(&ledinternal->netfilter_led_trigger); diff --git a/net/netfilter/xt_NFQUEUE.c b/net/netfilter/xt_NFQUEUE.c index a360b99a958a..a9aca80a32ae 100644 --- a/net/netfilter/xt_NFQUEUE.c +++ b/net/netfilter/xt_NFQUEUE.c @@ -8,6 +8,8 @@ * */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/skbuff.h> @@ -67,13 +69,13 @@ static int nfqueue_tg_check(const struct xt_tgchk_param *par) init_hashrandom(&jhash_initval); if (info->queues_total == 0) { - pr_err("NFQUEUE: number of total queues is 0\n"); + pr_info_ratelimited("number of total queues is 0\n"); return -EINVAL; } maxid = info->queues_total - 1 + info->queuenum; if (maxid > 0xffff) { - pr_err("NFQUEUE: number of queues (%u) out of range (got %u)\n", - info->queues_total, maxid); + pr_info_ratelimited("number of queues (%u) out of range (got %u)\n", + info->queues_total, maxid); return -ERANGE; } if (par->target->revision == 2 && info->flags > 1) diff --git a/net/netfilter/xt_SECMARK.c b/net/netfilter/xt_SECMARK.c index 9faf5e050b79..4ad5fe27e08b 100644 --- a/net/netfilter/xt_SECMARK.c +++ b/net/netfilter/xt_SECMARK.c @@ -60,18 +60,20 @@ static int checkentry_lsm(struct xt_secmark_target_info *info) &info->secid); if (err) { if (err == -EINVAL) - pr_info("invalid security context \'%s\'\n", info->secctx); + pr_info_ratelimited("invalid security context \'%s\'\n", + info->secctx); return err; } if (!info->secid) { - pr_info("unable to map security context \'%s\'\n", info->secctx); + pr_info_ratelimited("unable to map security context \'%s\'\n", + info->secctx); return -ENOENT; } err = security_secmark_relabel_packet(info->secid); if (err) { - pr_info("unable to obtain relabeling permission\n"); + pr_info_ratelimited("unable to obtain relabeling permission\n"); return err; } @@ -86,14 +88,14 @@ static int secmark_tg_check(const struct xt_tgchk_param *par) if (strcmp(par->table, "mangle") != 0 && strcmp(par->table, "security") != 0) { - pr_info("target only valid in the \'mangle\' " - "or \'security\' tables, not \'%s\'.\n", par->table); + pr_info_ratelimited("only valid in \'mangle\' or \'security\' table, not \'%s\'\n", + par->table); return -EINVAL; } if (mode && mode != info->mode) { - pr_info("mode already set to %hu cannot mix with " - "rules for mode %hu\n", mode, info->mode); + pr_info_ratelimited("mode already set to %hu cannot mix with rules for mode %hu\n", + mode, info->mode); return -EINVAL; } @@ -101,7 +103,7 @@ static int secmark_tg_check(const struct xt_tgchk_param *par) case SECMARK_MODE_SEL: break; default: - pr_info("invalid mode: %hu\n", info->mode); + pr_info_ratelimited("invalid mode: %hu\n", info->mode); return -EINVAL; } diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index 99bb8e410f22..98efb202f8b4 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -273,8 +273,7 @@ static int tcpmss_tg4_check(const struct xt_tgchk_param *par) (par->hook_mask & ~((1 << NF_INET_FORWARD) | (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_POST_ROUTING))) != 0) { - pr_info("path-MTU clamping only supported in " - "FORWARD, OUTPUT and POSTROUTING hooks\n"); + pr_info_ratelimited("path-MTU clamping only supported in FORWARD, OUTPUT and POSTROUTING hooks\n"); return -EINVAL; } if (par->nft_compat) @@ -283,7 +282,7 @@ static int tcpmss_tg4_check(const struct xt_tgchk_param *par) xt_ematch_foreach(ematch, e) if (find_syn_match(ematch)) return 0; - pr_info("Only works on TCP SYN packets\n"); + pr_info_ratelimited("Only works on TCP SYN packets\n"); return -EINVAL; } @@ -298,8 +297,7 @@ static int tcpmss_tg6_check(const struct xt_tgchk_param *par) (par->hook_mask & ~((1 << NF_INET_FORWARD) | (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_POST_ROUTING))) != 0) { - pr_info("path-MTU clamping only supported in " - "FORWARD, OUTPUT and POSTROUTING hooks\n"); + pr_info_ratelimited("path-MTU clamping only supported in FORWARD, OUTPUT and POSTROUTING hooks\n"); return -EINVAL; } if (par->nft_compat) @@ -308,7 +306,7 @@ static int tcpmss_tg6_check(const struct xt_tgchk_param *par) xt_ematch_foreach(ematch, e) if (find_syn_match(ematch)) return 0; - pr_info("Only works on TCP SYN packets\n"); + pr_info_ratelimited("Only works on TCP SYN packets\n"); return -EINVAL; } #endif diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index 17d7705e3bd4..8c89323c06af 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -540,8 +540,7 @@ static int tproxy_tg6_check(const struct xt_tgchk_param *par) !(i->invflags & IP6T_INV_PROTO)) return 0; - pr_info("Can be used only in combination with " - "either -p tcp or -p udp\n"); + pr_info_ratelimited("Can be used only with -p tcp or -p udp\n"); return -EINVAL; } #endif @@ -559,8 +558,7 @@ static int tproxy_tg4_check(const struct xt_tgchk_param *par) && !(i->invflags & IPT_INV_PROTO)) return 0; - pr_info("Can be used only in combination with " - "either -p tcp or -p udp\n"); + pr_info_ratelimited("Can be used only with -p tcp or -p udp\n"); return -EINVAL; } diff --git a/net/netfilter/xt_addrtype.c b/net/netfilter/xt_addrtype.c index 911a7c0da504..89e281b3bfc2 100644 --- a/net/netfilter/xt_addrtype.c +++ b/net/netfilter/xt_addrtype.c @@ -164,48 +164,47 @@ addrtype_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) static int addrtype_mt_checkentry_v1(const struct xt_mtchk_param *par) { + const char *errmsg = "both incoming and outgoing interface limitation cannot be selected"; struct xt_addrtype_info_v1 *info = par->matchinfo; if (info->flags & XT_ADDRTYPE_LIMIT_IFACE_IN && - info->flags & XT_ADDRTYPE_LIMIT_IFACE_OUT) { - pr_info("both incoming and outgoing " - "interface limitation cannot be selected\n"); - return -EINVAL; - } + info->flags & XT_ADDRTYPE_LIMIT_IFACE_OUT) + goto err; if (par->hook_mask & ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN)) && info->flags & XT_ADDRTYPE_LIMIT_IFACE_OUT) { - pr_info("output interface limitation " - "not valid in PREROUTING and INPUT\n"); - return -EINVAL; + errmsg = "output interface limitation not valid in PREROUTING and INPUT"; + goto err; } if (par->hook_mask & ((1 << NF_INET_POST_ROUTING) | (1 << NF_INET_LOCAL_OUT)) && info->flags & XT_ADDRTYPE_LIMIT_IFACE_IN) { - pr_info("input interface limitation " - "not valid in POSTROUTING and OUTPUT\n"); - return -EINVAL; + errmsg = "input interface limitation not valid in POSTROUTING and OUTPUT"; + goto err; } #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) if (par->family == NFPROTO_IPV6) { if ((info->source | info->dest) & XT_ADDRTYPE_BLACKHOLE) { - pr_err("ipv6 BLACKHOLE matching not supported\n"); - return -EINVAL; + errmsg = "ipv6 BLACKHOLE matching not supported"; + goto err; } if ((info->source | info->dest) >= XT_ADDRTYPE_PROHIBIT) { - pr_err("ipv6 PROHIBIT (THROW, NAT ..) matching not supported\n"); - return -EINVAL; + errmsg = "ipv6 PROHIBIT (THROW, NAT ..) matching not supported"; + goto err; } if ((info->source | info->dest) & XT_ADDRTYPE_BROADCAST) { - pr_err("ipv6 does not support BROADCAST matching\n"); - return -EINVAL; + errmsg = "ipv6 does not support BROADCAST matching"; + goto err; } } #endif return 0; +err: + pr_info_ratelimited("%s\n", errmsg); + return -EINVAL; } static struct xt_match addrtype_mt_reg[] __read_mostly = { diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c index 06b090d8e901..a2cf8a6236d6 100644 --- a/net/netfilter/xt_bpf.c +++ b/net/netfilter/xt_bpf.c @@ -7,6 +7,8 @@ * published by the Free Software Foundation. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/syscalls.h> #include <linux/skbuff.h> @@ -34,7 +36,7 @@ static int __bpf_mt_check_bytecode(struct sock_filter *insns, __u16 len, program.filter = insns; if (bpf_prog_create(ret, &program)) { - pr_info("bpf: check failed: parse error\n"); + pr_info_ratelimited("check failed: parse error\n"); return -EINVAL; } diff --git a/net/netfilter/xt_cgroup.c b/net/netfilter/xt_cgroup.c index 891f4e7e8ea7..7df2dece57d3 100644 --- a/net/netfilter/xt_cgroup.c +++ b/net/netfilter/xt_cgroup.c @@ -12,6 +12,8 @@ * published by the Free Software Foundation. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/skbuff.h> #include <linux/module.h> #include <linux/netfilter/x_tables.h> @@ -48,7 +50,7 @@ static int cgroup_mt_check_v1(const struct xt_mtchk_param *par) } if (info->has_path && info->has_classid) { - pr_info("xt_cgroup: both path and classid specified\n"); + pr_info_ratelimited("path and classid specified\n"); return -EINVAL; } @@ -56,8 +58,8 @@ static int cgroup_mt_check_v1(const struct xt_mtchk_param *par) if (info->has_path) { cgrp = cgroup_get_from_path(info->path); if (IS_ERR(cgrp)) { - pr_info("xt_cgroup: invalid path, errno=%ld\n", - PTR_ERR(cgrp)); + pr_info_ratelimited("invalid path, errno=%ld\n", + PTR_ERR(cgrp)); return -EINVAL; } info->priv = cgrp; diff --git a/net/netfilter/xt_cluster.c b/net/netfilter/xt_cluster.c index 57ef175dfbfa..0068688995c8 100644 --- a/net/netfilter/xt_cluster.c +++ b/net/netfilter/xt_cluster.c @@ -135,14 +135,12 @@ static int xt_cluster_mt_checkentry(const struct xt_mtchk_param *par) struct xt_cluster_match_info *info = par->matchinfo; if (info->total_nodes > XT_CLUSTER_NODES_MAX) { - pr_info("you have exceeded the maximum " - "number of cluster nodes (%u > %u)\n", - info->total_nodes, XT_CLUSTER_NODES_MAX); + pr_info_ratelimited("you have exceeded the maximum number of cluster nodes (%u > %u)\n", + info->total_nodes, XT_CLUSTER_NODES_MAX); return -EINVAL; } if (info->node_mask >= (1ULL << info->total_nodes)) { - pr_info("this node mask cannot be " - "higher than the total number of nodes\n"); + pr_info_ratelimited("node mask cannot exceed total number of nodes\n"); return -EDOM; } return 0; diff --git a/net/netfilter/xt_connbytes.c b/net/netfilter/xt_connbytes.c index cad0b7b5eb35..93cb018c3055 100644 --- a/net/netfilter/xt_connbytes.c +++ b/net/netfilter/xt_connbytes.c @@ -112,8 +112,8 @@ static int connbytes_mt_check(const struct xt_mtchk_param *par) ret = nf_ct_netns_get(par->net, par->family); if (ret < 0) - pr_info("cannot load conntrack support for proto=%u\n", - par->family); + pr_info_ratelimited("cannot load conntrack support for proto=%u\n", + par->family); /* * This filter cannot function correctly unless connection tracking diff --git a/net/netfilter/xt_connlabel.c b/net/netfilter/xt_connlabel.c index 23372879e6e3..4fa4efd24353 100644 --- a/net/netfilter/xt_connlabel.c +++ b/net/netfilter/xt_connlabel.c @@ -57,14 +57,15 @@ static int connlabel_mt_check(const struct xt_mtchk_param *par) int ret; if (info->options & ~options) { - pr_err("Unknown options in mask %x\n", info->options); + pr_info_ratelimited("Unknown options in mask %x\n", + info->options); return -EINVAL; } ret = nf_ct_netns_get(par->net, par->family); if (ret < 0) { - pr_info("cannot load conntrack support for proto=%u\n", - par->family); + pr_info_ratelimited("cannot load conntrack support for proto=%u\n", + par->family); return ret; } diff --git a/net/netfilter/xt_connmark.c b/net/netfilter/xt_connmark.c index ec377cc6a369..809639ce6f5a 100644 --- a/net/netfilter/xt_connmark.c +++ b/net/netfilter/xt_connmark.c @@ -79,8 +79,8 @@ static int connmark_tg_check(const struct xt_tgchk_param *par) ret = nf_ct_netns_get(par->net, par->family); if (ret < 0) - pr_info("cannot load conntrack support for proto=%u\n", - par->family); + pr_info_ratelimited("cannot load conntrack support for proto=%u\n", + par->family); return ret; } @@ -109,8 +109,8 @@ static int connmark_mt_check(const struct xt_mtchk_param *par) ret = nf_ct_netns_get(par->net, par->family); if (ret < 0) - pr_info("cannot load conntrack support for proto=%u\n", - par->family); + pr_info_ratelimited("cannot load conntrack support for proto=%u\n", + par->family); return ret; } diff --git a/net/netfilter/xt_conntrack.c b/net/netfilter/xt_conntrack.c index 39cf1d019240..df80fe7d391c 100644 --- a/net/netfilter/xt_conntrack.c +++ b/net/netfilter/xt_conntrack.c @@ -272,8 +272,8 @@ static int conntrack_mt_check(const struct xt_mtchk_param *par) ret = nf_ct_netns_get(par->net, par->family); if (ret < 0) - pr_info("cannot load conntrack support for proto=%u\n", - par->family); + pr_info_ratelimited("cannot load conntrack support for proto=%u\n", + par->family); return ret; } diff --git a/net/netfilter/xt_dscp.c b/net/netfilter/xt_dscp.c index 236ac8008909..a4c2b862f820 100644 --- a/net/netfilter/xt_dscp.c +++ b/net/netfilter/xt_dscp.c @@ -46,10 +46,8 @@ static int dscp_mt_check(const struct xt_mtchk_param *par) { const struct xt_dscp_info *info = par->matchinfo; - if (info->dscp > XT_DSCP_MAX) { - pr_info("dscp %x out of range\n", info->dscp); + if (info->dscp > XT_DSCP_MAX) return -EDOM; - } return 0; } diff --git a/net/netfilter/xt_ecn.c b/net/netfilter/xt_ecn.c index 3c831a8efebc..c7ad4afa5fb8 100644 --- a/net/netfilter/xt_ecn.c +++ b/net/netfilter/xt_ecn.c @@ -97,7 +97,7 @@ static int ecn_mt_check4(const struct xt_mtchk_param *par) if (info->operation & (XT_ECN_OP_MATCH_ECE | XT_ECN_OP_MATCH_CWR) && (ip->proto != IPPROTO_TCP || ip->invflags & IPT_INV_PROTO)) { - pr_info("cannot match TCP bits in rule for non-tcp packets\n"); + pr_info_ratelimited("cannot match TCP bits for non-tcp packets\n"); return -EINVAL; } @@ -139,7 +139,7 @@ static int ecn_mt_check6(const struct xt_mtchk_param *par) if (info->operation & (XT_ECN_OP_MATCH_ECE | XT_ECN_OP_MATCH_CWR) && (ip->proto != IPPROTO_TCP || ip->invflags & IP6T_INV_PROTO)) { - pr_info("cannot match TCP bits in rule for non-tcp packets\n"); + pr_info_ratelimited("cannot match TCP bits for non-tcp packets\n"); return -EINVAL; } diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index ca6847403ca2..db2fe0911740 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -523,7 +523,8 @@ static u64 user2rate(u64 user) if (user != 0) { return div64_u64(XT_HASHLIMIT_SCALE_v2, user); } else { - pr_warn("invalid rate from userspace: %llu\n", user); + pr_info_ratelimited("invalid rate from userspace: %llu\n", + user); return 0; } } @@ -774,7 +775,7 @@ hashlimit_mt_common(const struct sk_buff *skb, struct xt_action_param *par, if (!dh->rateinfo.prev_window && (dh->rateinfo.current_rate <= dh->rateinfo.burst)) { spin_unlock(&dh->lock); - rcu_read_unlock_bh(); + local_bh_enable(); return !(cfg->mode & XT_HASHLIMIT_INVERT); } else { goto overlimit; @@ -865,33 +866,34 @@ static int hashlimit_mt_check_common(const struct xt_mtchk_param *par, } if (cfg->mode & ~XT_HASHLIMIT_ALL) { - pr_info("Unknown mode mask %X, kernel too old?\n", - cfg->mode); + pr_info_ratelimited("Unknown mode mask %X, kernel too old?\n", + cfg->mode); return -EINVAL; } /* Check for overflow. */ if (revision >= 3 && cfg->mode & XT_HASHLIMIT_RATE_MATCH) { if (cfg->avg == 0 || cfg->avg > U32_MAX) { - pr_info("hashlimit invalid rate\n"); + pr_info_ratelimited("invalid rate\n"); return -ERANGE; } if (cfg->interval == 0) { - pr_info("hashlimit invalid interval\n"); + pr_info_ratelimited("invalid interval\n"); return -EINVAL; } } else if (cfg->mode & XT_HASHLIMIT_BYTES) { if (user2credits_byte(cfg->avg) == 0) { - pr_info("overflow, rate too high: %llu\n", cfg->avg); + pr_info_ratelimited("overflow, rate too high: %llu\n", + cfg->avg); return -EINVAL; } } else if (cfg->burst == 0 || - user2credits(cfg->avg * cfg->burst, revision) < - user2credits(cfg->avg, revision)) { - pr_info("overflow, try lower: %llu/%llu\n", - cfg->avg, cfg->burst); - return -ERANGE; + user2credits(cfg->avg * cfg->burst, revision) < + user2credits(cfg->avg, revision)) { + pr_info_ratelimited("overflow, try lower: %llu/%llu\n", + cfg->avg, cfg->burst); + return -ERANGE; } mutex_lock(&hashlimit_mutex); @@ -1343,6 +1345,7 @@ static struct pernet_operations hashlimit_net_ops = { .exit = hashlimit_net_exit, .id = &hashlimit_net_id, .size = sizeof(struct hashlimit_net), + .async = true, }; static int __init hashlimit_mt_init(void) diff --git a/net/netfilter/xt_helper.c b/net/netfilter/xt_helper.c index 38a78151c0e9..fd077aeaaed9 100644 --- a/net/netfilter/xt_helper.c +++ b/net/netfilter/xt_helper.c @@ -61,8 +61,8 @@ static int helper_mt_check(const struct xt_mtchk_param *par) ret = nf_ct_netns_get(par->net, par->family); if (ret < 0) { - pr_info("cannot load conntrack support for proto=%u\n", - par->family); + pr_info_ratelimited("cannot load conntrack support for proto=%u\n", + par->family); return ret; } info->name[sizeof(info->name) - 1] = '\0'; diff --git a/net/netfilter/xt_ipcomp.c b/net/netfilter/xt_ipcomp.c index 7ca64a50db04..57f1df575701 100644 --- a/net/netfilter/xt_ipcomp.c +++ b/net/netfilter/xt_ipcomp.c @@ -72,7 +72,7 @@ static int comp_mt_check(const struct xt_mtchk_param *par) /* Must specify no unknown invflags */ if (compinfo->invflags & ~XT_IPCOMP_INV_MASK) { - pr_err("unknown flags %X\n", compinfo->invflags); + pr_info_ratelimited("unknown flags %X\n", compinfo->invflags); return -EINVAL; } return 0; diff --git a/net/netfilter/xt_ipvs.c b/net/netfilter/xt_ipvs.c index 42540d26c2b8..1d950a6100af 100644 --- a/net/netfilter/xt_ipvs.c +++ b/net/netfilter/xt_ipvs.c @@ -158,7 +158,8 @@ static int ipvs_mt_check(const struct xt_mtchk_param *par) && par->family != NFPROTO_IPV6 #endif ) { - pr_info("protocol family %u not supported\n", par->family); + pr_info_ratelimited("protocol family %u not supported\n", + par->family); return -EINVAL; } diff --git a/net/netfilter/xt_l2tp.c b/net/netfilter/xt_l2tp.c index 8aee572771f2..c43482bf48e6 100644 --- a/net/netfilter/xt_l2tp.c +++ b/net/netfilter/xt_l2tp.c @@ -216,7 +216,7 @@ static int l2tp_mt_check(const struct xt_mtchk_param *par) /* Check for invalid flags */ if (info->flags & ~(XT_L2TP_TID | XT_L2TP_SID | XT_L2TP_VERSION | XT_L2TP_TYPE)) { - pr_info("unknown flags: %x\n", info->flags); + pr_info_ratelimited("unknown flags: %x\n", info->flags); return -EINVAL; } @@ -225,7 +225,8 @@ static int l2tp_mt_check(const struct xt_mtchk_param *par) (!(info->flags & XT_L2TP_SID)) && ((!(info->flags & XT_L2TP_TYPE)) || (info->type != XT_L2TP_TYPE_CONTROL))) { - pr_info("invalid flags combination: %x\n", info->flags); + pr_info_ratelimited("invalid flags combination: %x\n", + info->flags); return -EINVAL; } @@ -234,19 +235,22 @@ static int l2tp_mt_check(const struct xt_mtchk_param *par) */ if (info->flags & XT_L2TP_VERSION) { if ((info->version < 2) || (info->version > 3)) { - pr_info("wrong L2TP version: %u\n", info->version); + pr_info_ratelimited("wrong L2TP version: %u\n", + info->version); return -EINVAL; } if (info->version == 2) { if ((info->flags & XT_L2TP_TID) && (info->tid > 0xffff)) { - pr_info("v2 tid > 0xffff: %u\n", info->tid); + pr_info_ratelimited("v2 tid > 0xffff: %u\n", + info->tid); return -EINVAL; } if ((info->flags & XT_L2TP_SID) && (info->sid > 0xffff)) { - pr_info("v2 sid > 0xffff: %u\n", info->sid); + pr_info_ratelimited("v2 sid > 0xffff: %u\n", + info->sid); return -EINVAL; } } @@ -268,13 +272,13 @@ static int l2tp_mt_check4(const struct xt_mtchk_param *par) if ((ip->proto != IPPROTO_UDP) && (ip->proto != IPPROTO_L2TP)) { - pr_info("missing protocol rule (udp|l2tpip)\n"); + pr_info_ratelimited("missing protocol rule (udp|l2tpip)\n"); return -EINVAL; } if ((ip->proto == IPPROTO_L2TP) && (info->version == 2)) { - pr_info("v2 doesn't support IP mode\n"); + pr_info_ratelimited("v2 doesn't support IP mode\n"); return -EINVAL; } @@ -295,13 +299,13 @@ static int l2tp_mt_check6(const struct xt_mtchk_param *par) if ((ip->proto != IPPROTO_UDP) && (ip->proto != IPPROTO_L2TP)) { - pr_info("missing protocol rule (udp|l2tpip)\n"); + pr_info_ratelimited("missing protocol rule (udp|l2tpip)\n"); return -EINVAL; } if ((ip->proto == IPPROTO_L2TP) && (info->version == 2)) { - pr_info("v2 doesn't support IP mode\n"); + pr_info_ratelimited("v2 doesn't support IP mode\n"); return -EINVAL; } diff --git a/net/netfilter/xt_limit.c b/net/netfilter/xt_limit.c index 61403b77361c..55d18cd67635 100644 --- a/net/netfilter/xt_limit.c +++ b/net/netfilter/xt_limit.c @@ -106,8 +106,8 @@ static int limit_mt_check(const struct xt_mtchk_param *par) /* Check for overflow. */ if (r->burst == 0 || user2credits(r->avg * r->burst) < user2credits(r->avg)) { - pr_info("Overflow, try lower: %u/%u\n", - r->avg, r->burst); + pr_info_ratelimited("Overflow, try lower: %u/%u\n", + r->avg, r->burst); return -ERANGE; } diff --git a/net/netfilter/xt_nat.c b/net/netfilter/xt_nat.c index 0fd14d1eb09d..bdb689cdc829 100644 --- a/net/netfilter/xt_nat.c +++ b/net/netfilter/xt_nat.c @@ -8,6 +8,8 @@ * published by the Free Software Foundation. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/skbuff.h> #include <linux/netfilter.h> @@ -19,8 +21,7 @@ static int xt_nat_checkentry_v0(const struct xt_tgchk_param *par) const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; if (mr->rangesize != 1) { - pr_info("%s: multiple ranges no longer supported\n", - par->target->name); + pr_info_ratelimited("multiple ranges no longer supported\n"); return -EINVAL; } return nf_ct_netns_get(par->net, par->family); diff --git a/net/netfilter/xt_nfacct.c b/net/netfilter/xt_nfacct.c index 6f92d25590a8..c8674deed4eb 100644 --- a/net/netfilter/xt_nfacct.c +++ b/net/netfilter/xt_nfacct.c @@ -6,6 +6,8 @@ * it under the terms of the GNU General Public License version 2 (or any * later at your option) as published by the Free Software Foundation. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/skbuff.h> @@ -39,8 +41,8 @@ nfacct_mt_checkentry(const struct xt_mtchk_param *par) nfacct = nfnl_acct_find_get(par->net, info->name); if (nfacct == NULL) { - pr_info("xt_nfacct: accounting object with name `%s' " - "does not exists\n", info->name); + pr_info_ratelimited("accounting object `%s' does not exists\n", + info->name); return -ENOENT; } info->nfacct = nfacct; diff --git a/net/netfilter/xt_physdev.c b/net/netfilter/xt_physdev.c index bb33598e4530..9d6d67b953ac 100644 --- a/net/netfilter/xt_physdev.c +++ b/net/netfilter/xt_physdev.c @@ -107,9 +107,7 @@ static int physdev_mt_check(const struct xt_mtchk_param *par) info->invert & XT_PHYSDEV_OP_BRIDGED) && par->hook_mask & ((1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_FORWARD) | (1 << NF_INET_POST_ROUTING))) { - pr_info("using --physdev-out and --physdev-is-out are only " - "supported in the FORWARD and POSTROUTING chains with " - "bridged traffic.\n"); + pr_info_ratelimited("--physdev-out and --physdev-is-out only supported in the FORWARD and POSTROUTING chains with bridged traffic\n"); if (par->hook_mask & (1 << NF_INET_LOCAL_OUT)) return -EINVAL; } diff --git a/net/netfilter/xt_policy.c b/net/netfilter/xt_policy.c index 5639fb03bdd9..13f8ccf946d6 100644 --- a/net/netfilter/xt_policy.c +++ b/net/netfilter/xt_policy.c @@ -132,26 +132,29 @@ policy_mt(const struct sk_buff *skb, struct xt_action_param *par) static int policy_mt_check(const struct xt_mtchk_param *par) { const struct xt_policy_info *info = par->matchinfo; + const char *errmsg = "neither incoming nor outgoing policy selected"; + + if (!(info->flags & (XT_POLICY_MATCH_IN|XT_POLICY_MATCH_OUT))) + goto err; - if (!(info->flags & (XT_POLICY_MATCH_IN|XT_POLICY_MATCH_OUT))) { - pr_info("neither incoming nor outgoing policy selected\n"); - return -EINVAL; - } if (par->hook_mask & ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN)) && info->flags & XT_POLICY_MATCH_OUT) { - pr_info("output policy not valid in PREROUTING and INPUT\n"); - return -EINVAL; + errmsg = "output policy not valid in PREROUTING and INPUT"; + goto err; } if (par->hook_mask & ((1 << NF_INET_POST_ROUTING) | (1 << NF_INET_LOCAL_OUT)) && info->flags & XT_POLICY_MATCH_IN) { - pr_info("input policy not valid in POSTROUTING and OUTPUT\n"); - return -EINVAL; + errmsg = "input policy not valid in POSTROUTING and OUTPUT"; + goto err; } if (info->len > XT_POLICY_MAX_ELEM) { - pr_info("too many policy elements\n"); - return -EINVAL; + errmsg = "too many policy elements"; + goto err; } return 0; +err: + pr_info_ratelimited("%s\n", errmsg); + return -EINVAL; } static struct xt_match policy_mt_reg[] __read_mostly = { diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index 245fa350a7a8..19efdb757944 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -342,8 +342,8 @@ static int recent_mt_check(const struct xt_mtchk_param *par, net_get_random_once(&hash_rnd, sizeof(hash_rnd)); if (info->check_set & ~XT_RECENT_VALID_FLAGS) { - pr_info("Unsupported user space flags (%08x)\n", - info->check_set); + pr_info_ratelimited("Unsupported userspace flags (%08x)\n", + info->check_set); return -EINVAL; } if (hweight8(info->check_set & @@ -357,8 +357,8 @@ static int recent_mt_check(const struct xt_mtchk_param *par, if ((info->check_set & XT_RECENT_REAP) && !info->seconds) return -EINVAL; if (info->hit_count >= XT_RECENT_MAX_NSTAMPS) { - pr_info("hitcount (%u) is larger than allowed maximum (%u)\n", - info->hit_count, XT_RECENT_MAX_NSTAMPS - 1); + pr_info_ratelimited("hitcount (%u) is larger than allowed maximum (%u)\n", + info->hit_count, XT_RECENT_MAX_NSTAMPS - 1); return -EINVAL; } if (info->name[0] == '\0' || @@ -587,7 +587,7 @@ recent_mt_proc_write(struct file *file, const char __user *input, add = true; break; default: - pr_info("Need \"+ip\", \"-ip\" or \"/\"\n"); + pr_info_ratelimited("Need \"+ip\", \"-ip\" or \"/\"\n"); return -EINVAL; } @@ -601,10 +601,8 @@ recent_mt_proc_write(struct file *file, const char __user *input, succ = in4_pton(c, size, (void *)&addr, '\n', NULL); } - if (!succ) { - pr_info("illegal address written to procfs\n"); + if (!succ) return -EINVAL; - } spin_lock_bh(&recent_lock); e = recent_entry_lookup(t, &addr, family, 0); @@ -689,6 +687,7 @@ static struct pernet_operations recent_net_ops = { .exit = recent_net_exit, .id = &recent_net_id, .size = sizeof(struct recent_net), + .async = true, }; static struct xt_match recent_mt_reg[] __read_mostly = { diff --git a/net/netfilter/xt_set.c b/net/netfilter/xt_set.c index 16b6b11ee83f..6f4c5217d835 100644 --- a/net/netfilter/xt_set.c +++ b/net/netfilter/xt_set.c @@ -92,12 +92,12 @@ set_match_v0_checkentry(const struct xt_mtchk_param *par) index = ip_set_nfnl_get_byindex(par->net, info->match_set.index); if (index == IPSET_INVALID_ID) { - pr_warn("Cannot find set identified by id %u to match\n", - info->match_set.index); + pr_info_ratelimited("Cannot find set identified by id %u to match\n", + info->match_set.index); return -ENOENT; } if (info->match_set.u.flags[IPSET_DIM_MAX - 1] != 0) { - pr_warn("Protocol error: set match dimension is over the limit!\n"); + pr_info_ratelimited("set match dimension is over the limit!\n"); ip_set_nfnl_put(par->net, info->match_set.index); return -ERANGE; } @@ -143,12 +143,12 @@ set_match_v1_checkentry(const struct xt_mtchk_param *par) index = ip_set_nfnl_get_byindex(par->net, info->match_set.index); if (index == IPSET_INVALID_ID) { - pr_warn("Cannot find set identified by id %u to match\n", - info->match_set.index); + pr_info_ratelimited("Cannot find set identified by id %u to match\n", + info->match_set.index); return -ENOENT; } if (info->match_set.dim > IPSET_DIM_MAX) { - pr_warn("Protocol error: set match dimension is over the limit!\n"); + pr_info_ratelimited("set match dimension is over the limit!\n"); ip_set_nfnl_put(par->net, info->match_set.index); return -ERANGE; } @@ -241,8 +241,8 @@ set_target_v0_checkentry(const struct xt_tgchk_param *par) if (info->add_set.index != IPSET_INVALID_ID) { index = ip_set_nfnl_get_byindex(par->net, info->add_set.index); if (index == IPSET_INVALID_ID) { - pr_warn("Cannot find add_set index %u as target\n", - info->add_set.index); + pr_info_ratelimited("Cannot find add_set index %u as target\n", + info->add_set.index); return -ENOENT; } } @@ -250,8 +250,8 @@ set_target_v0_checkentry(const struct xt_tgchk_param *par) if (info->del_set.index != IPSET_INVALID_ID) { index = ip_set_nfnl_get_byindex(par->net, info->del_set.index); if (index == IPSET_INVALID_ID) { - pr_warn("Cannot find del_set index %u as target\n", - info->del_set.index); + pr_info_ratelimited("Cannot find del_set index %u as target\n", + info->del_set.index); if (info->add_set.index != IPSET_INVALID_ID) ip_set_nfnl_put(par->net, info->add_set.index); return -ENOENT; @@ -259,7 +259,7 @@ set_target_v0_checkentry(const struct xt_tgchk_param *par) } if (info->add_set.u.flags[IPSET_DIM_MAX - 1] != 0 || info->del_set.u.flags[IPSET_DIM_MAX - 1] != 0) { - pr_warn("Protocol error: SET target dimension is over the limit!\n"); + pr_info_ratelimited("SET target dimension over the limit!\n"); if (info->add_set.index != IPSET_INVALID_ID) ip_set_nfnl_put(par->net, info->add_set.index); if (info->del_set.index != IPSET_INVALID_ID) @@ -316,8 +316,8 @@ set_target_v1_checkentry(const struct xt_tgchk_param *par) if (info->add_set.index != IPSET_INVALID_ID) { index = ip_set_nfnl_get_byindex(par->net, info->add_set.index); if (index == IPSET_INVALID_ID) { - pr_warn("Cannot find add_set index %u as target\n", - info->add_set.index); + pr_info_ratelimited("Cannot find add_set index %u as target\n", + info->add_set.index); return -ENOENT; } } @@ -325,8 +325,8 @@ set_target_v1_checkentry(const struct xt_tgchk_param *par) if (info->del_set.index != IPSET_INVALID_ID) { index = ip_set_nfnl_get_byindex(par->net, info->del_set.index); if (index == IPSET_INVALID_ID) { - pr_warn("Cannot find del_set index %u as target\n", - info->del_set.index); + pr_info_ratelimited("Cannot find del_set index %u as target\n", + info->del_set.index); if (info->add_set.index != IPSET_INVALID_ID) ip_set_nfnl_put(par->net, info->add_set.index); return -ENOENT; @@ -334,7 +334,7 @@ set_target_v1_checkentry(const struct xt_tgchk_param *par) } if (info->add_set.dim > IPSET_DIM_MAX || info->del_set.dim > IPSET_DIM_MAX) { - pr_warn("Protocol error: SET target dimension is over the limit!\n"); + pr_info_ratelimited("SET target dimension over the limit!\n"); if (info->add_set.index != IPSET_INVALID_ID) ip_set_nfnl_put(par->net, info->add_set.index); if (info->del_set.index != IPSET_INVALID_ID) @@ -444,8 +444,8 @@ set_target_v3_checkentry(const struct xt_tgchk_param *par) index = ip_set_nfnl_get_byindex(par->net, info->add_set.index); if (index == IPSET_INVALID_ID) { - pr_warn("Cannot find add_set index %u as target\n", - info->add_set.index); + pr_info_ratelimited("Cannot find add_set index %u as target\n", + info->add_set.index); return -ENOENT; } } @@ -454,8 +454,8 @@ set_target_v3_checkentry(const struct xt_tgchk_param *par) index = ip_set_nfnl_get_byindex(par->net, info->del_set.index); if (index == IPSET_INVALID_ID) { - pr_warn("Cannot find del_set index %u as target\n", - info->del_set.index); + pr_info_ratelimited("Cannot find del_set index %u as target\n", + info->del_set.index); if (info->add_set.index != IPSET_INVALID_ID) ip_set_nfnl_put(par->net, info->add_set.index); @@ -465,7 +465,7 @@ set_target_v3_checkentry(const struct xt_tgchk_param *par) if (info->map_set.index != IPSET_INVALID_ID) { if (strncmp(par->table, "mangle", 7)) { - pr_warn("--map-set only usable from mangle table\n"); + pr_info_ratelimited("--map-set only usable from mangle table\n"); return -EINVAL; } if (((info->flags & IPSET_FLAG_MAP_SKBPRIO) | @@ -473,14 +473,14 @@ set_target_v3_checkentry(const struct xt_tgchk_param *par) !(par->hook_mask & (1 << NF_INET_FORWARD | 1 << NF_INET_LOCAL_OUT | 1 << NF_INET_POST_ROUTING))) { - pr_warn("mapping of prio or/and queue is allowed only from OUTPUT/FORWARD/POSTROUTING chains\n"); + pr_info_ratelimited("mapping of prio or/and queue is allowed only from OUTPUT/FORWARD/POSTROUTING chains\n"); return -EINVAL; } index = ip_set_nfnl_get_byindex(par->net, info->map_set.index); if (index == IPSET_INVALID_ID) { - pr_warn("Cannot find map_set index %u as target\n", - info->map_set.index); + pr_info_ratelimited("Cannot find map_set index %u as target\n", + info->map_set.index); if (info->add_set.index != IPSET_INVALID_ID) ip_set_nfnl_put(par->net, info->add_set.index); @@ -494,7 +494,7 @@ set_target_v3_checkentry(const struct xt_tgchk_param *par) if (info->add_set.dim > IPSET_DIM_MAX || info->del_set.dim > IPSET_DIM_MAX || info->map_set.dim > IPSET_DIM_MAX) { - pr_warn("Protocol error: SET target dimension is over the limit!\n"); + pr_info_ratelimited("SET target dimension over the limit!\n"); if (info->add_set.index != IPSET_INVALID_ID) ip_set_nfnl_put(par->net, info->add_set.index); if (info->del_set.index != IPSET_INVALID_ID) diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 575d2153e3b8..2ac7f674d19b 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -171,7 +171,8 @@ static int socket_mt_v1_check(const struct xt_mtchk_param *par) return err; if (info->flags & ~XT_SOCKET_FLAGS_V1) { - pr_info("unknown flags 0x%x\n", info->flags & ~XT_SOCKET_FLAGS_V1); + pr_info_ratelimited("unknown flags 0x%x\n", + info->flags & ~XT_SOCKET_FLAGS_V1); return -EINVAL; } return 0; @@ -187,7 +188,8 @@ static int socket_mt_v2_check(const struct xt_mtchk_param *par) return err; if (info->flags & ~XT_SOCKET_FLAGS_V2) { - pr_info("unknown flags 0x%x\n", info->flags & ~XT_SOCKET_FLAGS_V2); + pr_info_ratelimited("unknown flags 0x%x\n", + info->flags & ~XT_SOCKET_FLAGS_V2); return -EINVAL; } return 0; @@ -203,8 +205,8 @@ static int socket_mt_v3_check(const struct xt_mtchk_param *par) if (err) return err; if (info->flags & ~XT_SOCKET_FLAGS_V3) { - pr_info("unknown flags 0x%x\n", - info->flags & ~XT_SOCKET_FLAGS_V3); + pr_info_ratelimited("unknown flags 0x%x\n", + info->flags & ~XT_SOCKET_FLAGS_V3); return -EINVAL; } return 0; diff --git a/net/netfilter/xt_state.c b/net/netfilter/xt_state.c index 5fbd79194d21..0b41c0befe3c 100644 --- a/net/netfilter/xt_state.c +++ b/net/netfilter/xt_state.c @@ -44,8 +44,8 @@ static int state_mt_check(const struct xt_mtchk_param *par) ret = nf_ct_netns_get(par->net, par->family); if (ret < 0) - pr_info("cannot load conntrack support for proto=%u\n", - par->family); + pr_info_ratelimited("cannot load conntrack support for proto=%u\n", + par->family); return ret; } diff --git a/net/netfilter/xt_time.c b/net/netfilter/xt_time.c index 1b01eec1fbda..0160f505e337 100644 --- a/net/netfilter/xt_time.c +++ b/net/netfilter/xt_time.c @@ -235,13 +235,13 @@ static int time_mt_check(const struct xt_mtchk_param *par) if (info->daytime_start > XT_TIME_MAX_DAYTIME || info->daytime_stop > XT_TIME_MAX_DAYTIME) { - pr_info("invalid argument - start or " - "stop time greater than 23:59:59\n"); + pr_info_ratelimited("invalid argument - start or stop time greater than 23:59:59\n"); return -EDOM; } if (info->flags & ~XT_TIME_ALL_FLAGS) { - pr_info("unknown flags 0x%x\n", info->flags & ~XT_TIME_ALL_FLAGS); + pr_info_ratelimited("unknown flags 0x%x\n", + info->flags & ~XT_TIME_ALL_FLAGS); return -EINVAL; } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 2ad445c1d27c..5d10dcfe6411 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -253,6 +253,7 @@ static struct pernet_operations netlink_tap_net_ops = { .exit = netlink_tap_exit_net, .id = &netlink_tap_net_id, .size = sizeof(struct netlink_tap_net), + .async = true, }; static bool netlink_filter_tap(const struct sk_buff *skb) @@ -1105,7 +1106,7 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr, } static int netlink_getname(struct socket *sock, struct sockaddr *addr, - int *addr_len, int peer) + int peer) { struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); @@ -1113,7 +1114,6 @@ static int netlink_getname(struct socket *sock, struct sockaddr *addr, nladdr->nl_family = AF_NETLINK; nladdr->nl_pad = 0; - *addr_len = sizeof(*nladdr); if (peer) { nladdr->nl_pid = nlk->dst_portid; @@ -1124,7 +1124,7 @@ static int netlink_getname(struct socket *sock, struct sockaddr *addr, nladdr->nl_groups = nlk->groups ? nlk->groups[0] : 0; netlink_unlock_table(); } - return 0; + return sizeof(*nladdr); } static int netlink_ioctl(struct socket *sock, unsigned int cmd, @@ -2308,7 +2308,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, if (cb->start) { ret = cb->start(cb); if (ret) - goto error_unlock; + goto error_put; } nlk->cb_running = true; @@ -2328,6 +2328,8 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, */ return -EINTR; +error_put: + module_put(control->module); error_unlock: sock_put(sk); mutex_unlock(nlk->cb_mutex); @@ -2724,6 +2726,7 @@ static void __init netlink_add_usersock_entry(void) static struct pernet_operations __net_initdata netlink_net_ops = { .init = netlink_net_init, .exit = netlink_net_exit, + .async = true, }; static inline u32 netlink_hash(const void *data, u32 len, u32 seed) diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 6f02499ef007..a6f63a5faee7 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -1035,6 +1035,7 @@ static void __net_exit genl_pernet_exit(struct net *net) static struct pernet_operations genl_pernet_ops = { .init = genl_pernet_init, .exit = genl_pernet_exit, + .async = true, }; static int __init genl_init(void) diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 9ba30c63be3d..35bb6807927f 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -829,11 +829,12 @@ out_release: } static int nr_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { struct full_sockaddr_ax25 *sax = (struct full_sockaddr_ax25 *)uaddr; struct sock *sk = sock->sk; struct nr_sock *nr = nr_sk(sk); + int uaddr_len; memset(&sax->fsa_ax25, 0, sizeof(struct sockaddr_ax25)); @@ -848,16 +849,16 @@ static int nr_getname(struct socket *sock, struct sockaddr *uaddr, sax->fsa_ax25.sax25_call = nr->user_addr; memset(sax->fsa_digipeater, 0, sizeof(sax->fsa_digipeater)); sax->fsa_digipeater[0] = nr->dest_addr; - *uaddr_len = sizeof(struct full_sockaddr_ax25); + uaddr_len = sizeof(struct full_sockaddr_ax25); } else { sax->fsa_ax25.sax25_family = AF_NETROM; sax->fsa_ax25.sax25_ndigis = 0; sax->fsa_ax25.sax25_call = nr->source_addr; - *uaddr_len = sizeof(struct sockaddr_ax25); + uaddr_len = sizeof(struct sockaddr_ax25); } release_sock(sk); - return 0; + return uaddr_len; } int nr_rx_frame(struct sk_buff *skb, struct net_device *dev) diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c index 367d8c027101..2ceefa183cee 100644 --- a/net/nfc/llcp_commands.c +++ b/net/nfc/llcp_commands.c @@ -149,6 +149,10 @@ struct nfc_llcp_sdp_tlv *nfc_llcp_build_sdreq_tlv(u8 tid, char *uri, pr_debug("uri: %s, len: %zu\n", uri, uri_len); + /* sdreq->tlv_len is u8, takes uri_len, + 3 for header, + 1 for NULL */ + if (WARN_ON_ONCE(uri_len > U8_MAX - 4)) + return NULL; + sdreq = kzalloc(sizeof(struct nfc_llcp_sdp_tlv), GFP_KERNEL); if (sdreq == NULL) return NULL; diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index 376040092142..ea0c0c6f1874 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -497,7 +497,7 @@ error: } static int llcp_sock_getname(struct socket *sock, struct sockaddr *uaddr, - int *len, int peer) + int peer) { struct sock *sk = sock->sk; struct nfc_llcp_sock *llcp_sock = nfc_llcp_sock(sk); @@ -510,7 +510,6 @@ static int llcp_sock_getname(struct socket *sock, struct sockaddr *uaddr, llcp_sock->dsap, llcp_sock->ssap); memset(llcp_addr, 0, sizeof(*llcp_addr)); - *len = sizeof(struct sockaddr_nfc_llcp); lock_sock(sk); if (!llcp_sock->dev) { @@ -528,7 +527,7 @@ static int llcp_sock_getname(struct socket *sock, struct sockaddr *uaddr, llcp_addr->service_name_len); release_sock(sk); - return 0; + return sizeof(struct sockaddr_nfc_llcp); } static inline __poll_t llcp_accept_poll(struct sock *parent) diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index c0b83dc9d993..f018eafc2a0d 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -61,7 +61,8 @@ static const struct nla_policy nfc_genl_policy[NFC_ATTR_MAX + 1] = { }; static const struct nla_policy nfc_sdp_genl_policy[NFC_SDP_ATTR_MAX + 1] = { - [NFC_SDP_ATTR_URI] = { .type = NLA_STRING }, + [NFC_SDP_ATTR_URI] = { .type = NLA_STRING, + .len = U8_MAX - 4 }, [NFC_SDP_ATTR_SAP] = { .type = NLA_U8 }, }; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index e0f3f4aeeb4f..2c5a6fe5d749 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3409,7 +3409,7 @@ out: } static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { struct net_device *dev; struct sock *sk = sock->sk; @@ -3424,13 +3424,12 @@ static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr, if (dev) strlcpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data)); rcu_read_unlock(); - *uaddr_len = sizeof(*uaddr); - return 0; + return sizeof(*uaddr); } static int packet_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { struct net_device *dev; struct sock *sk = sock->sk; @@ -3455,9 +3454,8 @@ static int packet_getname(struct socket *sock, struct sockaddr *uaddr, sll->sll_halen = 0; } rcu_read_unlock(); - *uaddr_len = offsetof(struct sockaddr_ll, sll_addr) + sll->sll_halen; - return 0; + return offsetof(struct sockaddr_ll, sll_addr) + sll->sll_halen; } static int packet_dev_mc(struct net_device *dev, struct packet_mclist *i, @@ -4559,6 +4557,7 @@ static void __net_exit packet_net_exit(struct net *net) static struct pernet_operations packet_net_ops = { .init = packet_net_init, .exit = packet_net_exit, + .async = true, }; diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c index 77787512fc32..9454e8393793 100644 --- a/net/phonet/pn_dev.c +++ b/net/phonet/pn_dev.c @@ -342,6 +342,7 @@ static struct pernet_operations phonet_net_ops = { .exit = phonet_exit_net, .id = &phonet_net_id, .size = sizeof(struct phonet_net), + .async = true, }; /* Initialize Phonet devices list */ diff --git a/net/phonet/socket.c b/net/phonet/socket.c index fffcd69f63ff..f9b40e6a18a5 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -326,7 +326,7 @@ static int pn_socket_accept(struct socket *sock, struct socket *newsock, } static int pn_socket_getname(struct socket *sock, struct sockaddr *addr, - int *sockaddr_len, int peer) + int peer) { struct sock *sk = sock->sk; struct pn_sock *pn = pn_sk(sk); @@ -337,8 +337,7 @@ static int pn_socket_getname(struct socket *sock, struct sockaddr *addr, pn_sockaddr_set_object((struct sockaddr_pn *)addr, pn->sobject); - *sockaddr_len = sizeof(struct sockaddr_pn); - return 0; + return sizeof(struct sockaddr_pn); } static __poll_t pn_socket_poll(struct file *file, struct socket *sock, diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index 5fb3929e3d7d..b33e5aeb4c06 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -893,7 +893,7 @@ static int qrtr_connect(struct socket *sock, struct sockaddr *saddr, } static int qrtr_getname(struct socket *sock, struct sockaddr *saddr, - int *len, int peer) + int peer) { struct qrtr_sock *ipc = qrtr_sk(sock->sk); struct sockaddr_qrtr qaddr; @@ -912,12 +912,11 @@ static int qrtr_getname(struct socket *sock, struct sockaddr *saddr, } release_sock(sk); - *len = sizeof(qaddr); qaddr.sq_family = AF_QIPCRTR; memcpy(saddr, &qaddr, sizeof(qaddr)); - return 0; + return sizeof(qaddr); } static int qrtr_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index 744c637c86b0..f7126108a811 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -77,6 +77,7 @@ static int rds_release(struct socket *sock) rds_send_drop_to(rs, NULL); rds_rdma_drop_keys(rs); rds_notify_queue_get(rs, NULL); + __skb_queue_purge(&rs->rs_zcookie_queue); spin_lock_bh(&rds_sock_lock); list_del_init(&rs->rs_item); @@ -110,7 +111,7 @@ void rds_wake_sk_sleep(struct rds_sock *rs) } static int rds_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { struct sockaddr_in *sin = (struct sockaddr_in *)uaddr; struct rds_sock *rs = rds_sk_to_rs(sock->sk); @@ -131,8 +132,7 @@ static int rds_getname(struct socket *sock, struct sockaddr *uaddr, sin->sin_family = AF_INET; - *uaddr_len = sizeof(*sin); - return 0; + return sizeof(*sin); } /* @@ -145,7 +145,7 @@ static int rds_getname(struct socket *sock, struct sockaddr *uaddr, * - to signal that a previously congested destination may have become * uncongested * - A notification has been queued to the socket (this can be a congestion - * update, or a RDMA completion). + * update, or a RDMA completion, or a MSG_ZEROCOPY completion). * * EPOLLOUT is asserted if there is room on the send queue. This does not mean * however, that the next sendmsg() call will succeed. If the application tries @@ -179,10 +179,13 @@ static __poll_t rds_poll(struct file *file, struct socket *sock, spin_unlock(&rs->rs_lock); } if (!list_empty(&rs->rs_recv_queue) || - !list_empty(&rs->rs_notify_queue)) + !list_empty(&rs->rs_notify_queue) || + !skb_queue_empty(&rs->rs_zcookie_queue)) mask |= (EPOLLIN | EPOLLRDNORM); if (rs->rs_snd_bytes < rds_sk_sndbuf(rs)) mask |= (EPOLLOUT | EPOLLWRNORM); + if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) + mask |= POLLERR; read_unlock_irqrestore(&rs->rs_recv_lock, flags); /* clear state any time we wake a seen-congested socket */ @@ -512,6 +515,7 @@ static int __rds_create(struct socket *sock, struct sock *sk, int protocol) INIT_LIST_HEAD(&rs->rs_recv_queue); INIT_LIST_HEAD(&rs->rs_notify_queue); INIT_LIST_HEAD(&rs->rs_cong_list); + skb_queue_head_init(&rs->rs_zcookie_queue); spin_lock_init(&rs->rs_rdma_lock); rs->rs_rdma_keys = RB_ROOT; rs->rs_rx_traces = 0; diff --git a/net/rds/connection.c b/net/rds/connection.c index 94e190febfdd..2da3176bf792 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -224,7 +224,7 @@ static struct rds_connection *__rds_conn_create(struct net *net, if (rds_destroy_pending(conn)) ret = -ENETDOWN; else - ret = trans->conn_alloc(conn, gfp); + ret = trans->conn_alloc(conn, GFP_ATOMIC); if (ret) { rcu_read_unlock(); kfree(conn->c_path); diff --git a/net/rds/message.c b/net/rds/message.c index 4318cc9b78f7..116cf87ccb89 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -33,6 +33,9 @@ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/export.h> +#include <linux/skbuff.h> +#include <linux/list.h> +#include <linux/errqueue.h> #include "rds.h" @@ -53,20 +56,84 @@ void rds_message_addref(struct rds_message *rm) } EXPORT_SYMBOL_GPL(rds_message_addref); +static inline bool skb_zcookie_add(struct sk_buff *skb, u32 cookie) +{ + struct rds_zcopy_cookies *ck = (struct rds_zcopy_cookies *)skb->cb; + int ncookies = ck->num; + + if (ncookies == RDS_MAX_ZCOOKIES) + return false; + ck->cookies[ncookies] = cookie; + ck->num = ++ncookies; + return true; +} + +static void rds_rm_zerocopy_callback(struct rds_sock *rs, + struct rds_znotifier *znotif) +{ + struct sk_buff *skb, *tail; + unsigned long flags; + struct sk_buff_head *q; + u32 cookie = znotif->z_cookie; + struct rds_zcopy_cookies *ck; + + q = &rs->rs_zcookie_queue; + spin_lock_irqsave(&q->lock, flags); + tail = skb_peek_tail(q); + + if (tail && skb_zcookie_add(tail, cookie)) { + spin_unlock_irqrestore(&q->lock, flags); + mm_unaccount_pinned_pages(&znotif->z_mmp); + consume_skb(rds_skb_from_znotifier(znotif)); + /* caller invokes rds_wake_sk_sleep() */ + return; + } + + skb = rds_skb_from_znotifier(znotif); + ck = (struct rds_zcopy_cookies *)skb->cb; + memset(ck, 0, sizeof(*ck)); + WARN_ON(!skb_zcookie_add(skb, cookie)); + + __skb_queue_tail(q, skb); + + spin_unlock_irqrestore(&q->lock, flags); + /* caller invokes rds_wake_sk_sleep() */ + + mm_unaccount_pinned_pages(&znotif->z_mmp); +} + /* * This relies on dma_map_sg() not touching sg[].page during merging. */ static void rds_message_purge(struct rds_message *rm) { - unsigned long i; + unsigned long i, flags; + bool zcopy = false; if (unlikely(test_bit(RDS_MSG_PAGEVEC, &rm->m_flags))) return; + spin_lock_irqsave(&rm->m_rs_lock, flags); + if (rm->m_rs) { + struct rds_sock *rs = rm->m_rs; + + if (rm->data.op_mmp_znotifier) { + zcopy = true; + rds_rm_zerocopy_callback(rs, rm->data.op_mmp_znotifier); + rds_wake_sk_sleep(rs); + rm->data.op_mmp_znotifier = NULL; + } + sock_put(rds_rs_to_sk(rs)); + rm->m_rs = NULL; + } + spin_unlock_irqrestore(&rm->m_rs_lock, flags); + for (i = 0; i < rm->data.op_nents; i++) { - rdsdebug("putting data page %p\n", (void *)sg_page(&rm->data.op_sg[i])); /* XXX will have to put_page for page refs */ - __free_page(sg_page(&rm->data.op_sg[i])); + if (!zcopy) + __free_page(sg_page(&rm->data.op_sg[i])); + else + put_page(sg_page(&rm->data.op_sg[i])); } rm->data.op_nents = 0; @@ -266,12 +333,14 @@ struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned in return rm; } -int rds_message_copy_from_user(struct rds_message *rm, struct iov_iter *from) +int rds_message_copy_from_user(struct rds_message *rm, struct iov_iter *from, + bool zcopy) { unsigned long to_copy, nbytes; unsigned long sg_off; struct scatterlist *sg; int ret = 0; + int length = iov_iter_count(from); rm->m_inc.i_hdr.h_len = cpu_to_be32(iov_iter_count(from)); @@ -281,6 +350,55 @@ int rds_message_copy_from_user(struct rds_message *rm, struct iov_iter *from) sg = rm->data.op_sg; sg_off = 0; /* Dear gcc, sg->page will be null from kzalloc. */ + if (zcopy) { + int total_copied = 0; + struct sk_buff *skb; + + skb = alloc_skb(0, GFP_KERNEL); + if (!skb) + return -ENOMEM; + BUILD_BUG_ON(sizeof(skb->cb) < + max_t(int, sizeof(struct rds_znotifier), + sizeof(struct rds_zcopy_cookies))); + rm->data.op_mmp_znotifier = RDS_ZCOPY_SKB(skb); + if (mm_account_pinned_pages(&rm->data.op_mmp_znotifier->z_mmp, + length)) { + ret = -ENOMEM; + goto err; + } + while (iov_iter_count(from)) { + struct page *pages; + size_t start; + ssize_t copied; + + copied = iov_iter_get_pages(from, &pages, PAGE_SIZE, + 1, &start); + if (copied < 0) { + struct mmpin *mmp; + int i; + + for (i = 0; i < rm->data.op_nents; i++) + put_page(sg_page(&rm->data.op_sg[i])); + mmp = &rm->data.op_mmp_znotifier->z_mmp; + mm_unaccount_pinned_pages(mmp); + ret = -EFAULT; + goto err; + } + total_copied += copied; + iov_iter_advance(from, copied); + length -= copied; + sg_set_page(sg, pages, copied, start); + rm->data.op_nents++; + sg++; + } + WARN_ON_ONCE(length != 0); + return ret; +err: + consume_skb(skb); + rm->data.op_mmp_znotifier = NULL; + return ret; + } /* zcopy */ + while (iov_iter_count(from)) { if (!sg_page(sg)) { ret = rds_page_remainder_alloc(sg, iov_iter_count(from), diff --git a/net/rds/rds.h b/net/rds/rds.h index 7301b9b01890..33b16353d8f3 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -356,6 +356,19 @@ static inline u32 rds_rdma_cookie_offset(rds_rdma_cookie_t cookie) #define RDS_MSG_PAGEVEC 7 #define RDS_MSG_FLUSH 8 +struct rds_znotifier { + struct list_head z_list; + struct mmpin z_mmp; + u32 z_cookie; +}; + +#define RDS_ZCOPY_SKB(__skb) ((struct rds_znotifier *)&((__skb)->cb[0])) + +static inline struct sk_buff *rds_skb_from_znotifier(struct rds_znotifier *z) +{ + return container_of((void *)z, struct sk_buff, cb); +} + struct rds_message { refcount_t m_refcount; struct list_head m_sock_item; @@ -436,6 +449,7 @@ struct rds_message { unsigned int op_count; unsigned int op_dmasg; unsigned int op_dmaoff; + struct rds_znotifier *op_mmp_znotifier; struct scatterlist *op_sg; } data; }; @@ -589,6 +603,8 @@ struct rds_sock { /* Socket receive path trace points*/ u8 rs_rx_traces; u8 rs_rx_trace[RDS_MSG_RX_DGRAM_TRACE_MAX]; + + struct sk_buff_head rs_zcookie_queue; }; static inline struct rds_sock *rds_sk_to_rs(const struct sock *sk) @@ -771,7 +787,8 @@ rds_conn_connecting(struct rds_connection *conn) /* message.c */ struct rds_message *rds_message_alloc(unsigned int nents, gfp_t gfp); struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents); -int rds_message_copy_from_user(struct rds_message *rm, struct iov_iter *from); +int rds_message_copy_from_user(struct rds_message *rm, struct iov_iter *from, + bool zcopy); struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned int total_len); void rds_message_populate_header(struct rds_header *hdr, __be16 sport, __be16 dport, u64 seq); diff --git a/net/rds/recv.c b/net/rds/recv.c index b25bcfe411ca..d50747725221 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -577,6 +577,32 @@ out: return ret; } +static bool rds_recvmsg_zcookie(struct rds_sock *rs, struct msghdr *msg) +{ + struct sk_buff *skb; + struct sk_buff_head *q = &rs->rs_zcookie_queue; + struct rds_zcopy_cookies *done; + + if (!msg->msg_control) + return false; + + if (!sock_flag(rds_rs_to_sk(rs), SOCK_ZEROCOPY) || + msg->msg_controllen < CMSG_SPACE(sizeof(*done))) + return false; + + skb = skb_dequeue(q); + if (!skb) + return false; + done = (struct rds_zcopy_cookies *)skb->cb; + if (put_cmsg(msg, SOL_RDS, RDS_CMSG_ZCOPY_COMPLETION, sizeof(*done), + done)) { + skb_queue_head(q, skb); + return false; + } + consume_skb(skb); + return true; +} + int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int msg_flags) { @@ -594,6 +620,8 @@ int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, if (msg_flags & MSG_OOB) goto out; + if (msg_flags & MSG_ERRQUEUE) + return sock_recv_errqueue(sk, msg, size, SOL_IP, IP_RECVERR); while (1) { /* If there are pending notifications, do those - and nothing else */ @@ -609,7 +637,9 @@ int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, if (!rds_next_incoming(rs, &inc)) { if (nonblock) { - ret = -EAGAIN; + bool reaped = rds_recvmsg_zcookie(rs, msg); + + ret = reaped ? 0 : -EAGAIN; break; } @@ -658,6 +688,7 @@ int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, ret = -EFAULT; goto out; } + rds_recvmsg_zcookie(rs, msg); rds_stats_inc(s_recv_delivered); diff --git a/net/rds/send.c b/net/rds/send.c index b1b0022b8370..acad04243b41 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -649,7 +649,6 @@ static void rds_send_remove_from_sock(struct list_head *messages, int status) rm->rdma.op_notifier = NULL; } was_on_sock = 1; - rm->m_rs = NULL; } spin_unlock(&rs->rs_lock); @@ -756,9 +755,6 @@ void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest) */ if (!test_and_clear_bit(RDS_MSG_ON_CONN, &rm->m_flags)) { spin_unlock_irqrestore(&cp->cp_lock, flags); - spin_lock_irqsave(&rm->m_rs_lock, flags); - rm->m_rs = NULL; - spin_unlock_irqrestore(&rm->m_rs_lock, flags); continue; } list_del_init(&rm->m_conn_item); @@ -774,7 +770,6 @@ void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest) __rds_send_complete(rs, rm, RDS_RDMA_CANCELED); spin_unlock(&rs->rs_lock); - rm->m_rs = NULL; spin_unlock_irqrestore(&rm->m_rs_lock, flags); rds_message_put(rm); @@ -798,7 +793,6 @@ void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest) __rds_send_complete(rs, rm, RDS_RDMA_CANCELED); spin_unlock(&rs->rs_lock); - rm->m_rs = NULL; spin_unlock_irqrestore(&rm->m_rs_lock, flags); rds_message_put(rm); @@ -849,6 +843,7 @@ static int rds_send_queue_rm(struct rds_sock *rs, struct rds_connection *conn, list_add_tail(&rm->m_sock_item, &rs->rs_send_queue); set_bit(RDS_MSG_ON_SOCK, &rm->m_flags); rds_message_addref(rm); + sock_hold(rds_rs_to_sk(rs)); rm->m_rs = rs; /* The code ordering is a little weird, but we're @@ -880,12 +875,13 @@ out: * rds_message is getting to be quite complicated, and we'd like to allocate * it all in one go. This figures out how big it needs to be up front. */ -static int rds_rm_size(struct msghdr *msg, int data_len) +static int rds_rm_size(struct msghdr *msg, int num_sgs) { struct cmsghdr *cmsg; int size = 0; int cmsg_groups = 0; int retval; + bool zcopy_cookie = false; for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) @@ -904,6 +900,10 @@ static int rds_rm_size(struct msghdr *msg, int data_len) break; + case RDS_CMSG_ZCOPY_COOKIE: + zcopy_cookie = true; + /* fall through */ + case RDS_CMSG_RDMA_DEST: case RDS_CMSG_RDMA_MAP: cmsg_groups |= 2; @@ -924,7 +924,10 @@ static int rds_rm_size(struct msghdr *msg, int data_len) } - size += ceil(data_len, PAGE_SIZE) * sizeof(struct scatterlist); + if ((msg->msg_flags & MSG_ZEROCOPY) && !zcopy_cookie) + return -EINVAL; + + size += num_sgs * sizeof(struct scatterlist); /* Ensure (DEST, MAP) are never used with (ARGS, ATOMIC) */ if (cmsg_groups == 3) @@ -933,6 +936,19 @@ static int rds_rm_size(struct msghdr *msg, int data_len) return size; } +static int rds_cmsg_zcopy(struct rds_sock *rs, struct rds_message *rm, + struct cmsghdr *cmsg) +{ + u32 *cookie; + + if (cmsg->cmsg_len < CMSG_LEN(sizeof(*cookie)) || + !rm->data.op_mmp_znotifier) + return -EINVAL; + cookie = CMSG_DATA(cmsg); + rm->data.op_mmp_znotifier->z_cookie = *cookie; + return 0; +} + static int rds_cmsg_send(struct rds_sock *rs, struct rds_message *rm, struct msghdr *msg, int *allocated_mr) { @@ -975,6 +991,10 @@ static int rds_cmsg_send(struct rds_sock *rs, struct rds_message *rm, ret = rds_cmsg_atomic(rs, rm, cmsg); break; + case RDS_CMSG_ZCOPY_COOKIE: + ret = rds_cmsg_zcopy(rs, rm, cmsg); + break; + default: return -EINVAL; } @@ -1045,10 +1065,13 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) long timeo = sock_sndtimeo(sk, nonblock); struct rds_conn_path *cpath; size_t total_payload_len = payload_len, rdma_payload_len = 0; + bool zcopy = ((msg->msg_flags & MSG_ZEROCOPY) && + sock_flag(rds_rs_to_sk(rs), SOCK_ZEROCOPY)); + int num_sgs = ceil(payload_len, PAGE_SIZE); /* Mirror Linux UDP mirror of BSD error message compatibility */ /* XXX: Perhaps MSG_MORE someday */ - if (msg->msg_flags & ~(MSG_DONTWAIT | MSG_CMSG_COMPAT)) { + if (msg->msg_flags & ~(MSG_DONTWAIT | MSG_CMSG_COMPAT | MSG_ZEROCOPY)) { ret = -EOPNOTSUPP; goto out; } @@ -1092,8 +1115,15 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) goto out; } + if (zcopy) { + if (rs->rs_transport->t_type != RDS_TRANS_TCP) { + ret = -EOPNOTSUPP; + goto out; + } + num_sgs = iov_iter_npages(&msg->msg_iter, INT_MAX); + } /* size of rm including all sgs */ - ret = rds_rm_size(msg, payload_len); + ret = rds_rm_size(msg, num_sgs); if (ret < 0) goto out; @@ -1105,12 +1135,12 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) /* Attach data to the rm */ if (payload_len) { - rm->data.op_sg = rds_message_alloc_sgs(rm, ceil(payload_len, PAGE_SIZE)); + rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs); if (!rm->data.op_sg) { ret = -ENOMEM; goto out; } - ret = rds_message_copy_from_user(rm, &msg->msg_iter); + ret = rds_message_copy_from_user(rm, &msg->msg_iter, zcopy); if (ret) goto out; } diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 44c4652721af..08230a145042 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -227,7 +227,6 @@ static void rds_tcp_tc_info(struct socket *rds_sock, unsigned int len, struct rds_tcp_connection *tc; unsigned long flags; struct sockaddr_in sin; - int sinlen; struct socket *sock; spin_lock_irqsave(&rds_tcp_tc_list_lock, flags); @@ -239,12 +238,10 @@ static void rds_tcp_tc_info(struct socket *rds_sock, unsigned int len, sock = tc->t_sock; if (sock) { - sock->ops->getname(sock, (struct sockaddr *)&sin, - &sinlen, 0); + sock->ops->getname(sock, (struct sockaddr *)&sin, 0); tsinfo.local_addr = sin.sin_addr.s_addr; tsinfo.local_port = sin.sin_port; - sock->ops->getname(sock, (struct sockaddr *)&sin, - &sinlen, 1); + sock->ops->getname(sock, (struct sockaddr *)&sin, 1); tsinfo.peer_addr = sin.sin_addr.s_addr; tsinfo.peer_port = sin.sin_port; } diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 083bd251406f..5170373b797c 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -938,7 +938,7 @@ out_release: } static int rose_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { struct full_sockaddr_rose *srose = (struct full_sockaddr_rose *)uaddr; struct sock *sk = sock->sk; @@ -964,8 +964,7 @@ static int rose_getname(struct socket *sock, struct sockaddr *uaddr, srose->srose_digis[n] = rose->source_digis[n]; } - *uaddr_len = sizeof(struct full_sockaddr_rose); - return 0; + return sizeof(struct full_sockaddr_rose); } int rose_rx_call_request(struct sk_buff *skb, struct net_device *dev, struct rose_neigh *neigh, unsigned int lci) diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 42410e910aff..cf73dc006c3b 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -445,7 +445,7 @@ send_fragmentable: (char *)&opt, sizeof(opt)); if (ret == 0) { ret = kernel_sendmsg(conn->params.local->socket, &msg, - iov, 1, iov[0].iov_len); + iov, 2, len); opt = IPV6_PMTUDISC_DO; kernel_setsockopt(conn->params.local->socket, diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index cc21e8db25b0..9d45d8b56744 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -517,9 +517,10 @@ try_again: ret = put_cmsg(msg, SOL_RXRPC, RXRPC_USER_CALL_ID, sizeof(unsigned int), &id32); } else { + unsigned long idl = call->user_call_ID; + ret = put_cmsg(msg, SOL_RXRPC, RXRPC_USER_CALL_ID, - sizeof(unsigned long), - &call->user_call_ID); + sizeof(unsigned long), &idl); } if (ret < 0) goto error_unlock_call; diff --git a/net/sched/Kconfig b/net/sched/Kconfig index f24a6ae6819a..a01169fb5325 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -658,6 +658,18 @@ config NET_EMATCH_IPSET To compile this code as a module, choose M here: the module will be called em_ipset. +config NET_EMATCH_IPT + tristate "IPtables Matches" + depends on NET_EMATCH && NETFILTER && NETFILTER_XTABLES + ---help--- + Say Y here to be able to classify packets based on iptables + matches. + Current supported match is "policy" which allows packet classification + based on IPsec policy that was used during decapsulation + + To compile this code as a module, choose M here: the + module will be called em_ipt. + config NET_CLS_ACT bool "Actions" select NET_CLS diff --git a/net/sched/Makefile b/net/sched/Makefile index 5b635447e3f8..8811d3804878 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -75,3 +75,4 @@ obj-$(CONFIG_NET_EMATCH_META) += em_meta.o obj-$(CONFIG_NET_EMATCH_TEXT) += em_text.o obj-$(CONFIG_NET_EMATCH_CANID) += em_canid.o obj-$(CONFIG_NET_EMATCH_IPSET) += em_ipset.o +obj-$(CONFIG_NET_EMATCH_IPT) += em_ipt.o diff --git a/net/sched/act_api.c b/net/sched/act_api.c index eba6682727dd..1f65d6ada9ff 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -202,7 +202,8 @@ nla_put_failure: int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tcf_idrinfo *idrinfo = tn->idrinfo; @@ -211,7 +212,8 @@ int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb, } else if (type == RTM_GETACTION) { return tcf_dump_walker(idrinfo, skb, cb); } else { - WARN(1, "tcf_generic_walker: unknown action %d\n", type); + WARN(1, "tcf_generic_walker: unknown command %d\n", type); + NL_SET_ERR_MSG(extack, "tcf_generic_walker: unknown command"); return -EINVAL; } } @@ -605,7 +607,8 @@ static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb) struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, - char *name, int ovr, int bind) + char *name, int ovr, int bind, + struct netlink_ext_ack *extack) { struct tc_action *a; struct tc_action_ops *a_o; @@ -616,31 +619,40 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, int err; if (name == NULL) { - err = nla_parse_nested(tb, TCA_ACT_MAX, nla, NULL, NULL); + err = nla_parse_nested(tb, TCA_ACT_MAX, nla, NULL, extack); if (err < 0) goto err_out; err = -EINVAL; kind = tb[TCA_ACT_KIND]; - if (kind == NULL) + if (!kind) { + NL_SET_ERR_MSG(extack, "TC action kind must be specified"); goto err_out; - if (nla_strlcpy(act_name, kind, IFNAMSIZ) >= IFNAMSIZ) + } + if (nla_strlcpy(act_name, kind, IFNAMSIZ) >= IFNAMSIZ) { + NL_SET_ERR_MSG(extack, "TC action name too long"); goto err_out; + } if (tb[TCA_ACT_COOKIE]) { int cklen = nla_len(tb[TCA_ACT_COOKIE]); - if (cklen > TC_COOKIE_MAX_SIZE) + if (cklen > TC_COOKIE_MAX_SIZE) { + NL_SET_ERR_MSG(extack, "TC cookie size above the maximum"); goto err_out; + } cookie = nla_memdup_cookie(tb); if (!cookie) { + NL_SET_ERR_MSG(extack, "No memory to generate TC cookie"); err = -ENOMEM; goto err_out; } } } else { - err = -EINVAL; - if (strlcpy(act_name, name, IFNAMSIZ) >= IFNAMSIZ) + if (strlcpy(act_name, name, IFNAMSIZ) >= IFNAMSIZ) { + NL_SET_ERR_MSG(extack, "TC action name too long"); + err = -EINVAL; goto err_out; + } } a_o = tc_lookup_action_n(act_name); @@ -663,15 +675,17 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, goto err_mod; } #endif + NL_SET_ERR_MSG(extack, "Failed to load TC action module"); err = -ENOENT; goto err_out; } /* backward compatibility for policer */ if (name == NULL) - err = a_o->init(net, tb[TCA_ACT_OPTIONS], est, &a, ovr, bind); + err = a_o->init(net, tb[TCA_ACT_OPTIONS], est, &a, ovr, bind, + extack); else - err = a_o->init(net, nla, est, &a, ovr, bind); + err = a_o->init(net, nla, est, &a, ovr, bind, extack); if (err < 0) goto err_mod; @@ -697,6 +711,7 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, list_add_tail(&a->list, &actions); tcf_action_destroy(&actions, bind); + NL_SET_ERR_MSG(extack, "Failed to init TC action chain"); return ERR_PTR(err); } } @@ -726,19 +741,20 @@ static void cleanup_a(struct list_head *actions, int ovr) int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, char *name, int ovr, int bind, - struct list_head *actions) + struct list_head *actions, struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; struct tc_action *act; int err; int i; - err = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL, NULL); + err = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL, extack); if (err < 0) return err; for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) { - act = tcf_action_init_1(net, tp, tb[i], est, name, ovr, bind); + act = tcf_action_init_1(net, tp, tb[i], est, name, ovr, bind, + extack); if (IS_ERR(act)) { err = PTR_ERR(act); goto err; @@ -822,7 +838,7 @@ static int tca_get_fill(struct sk_buff *skb, struct list_head *actions, t->tca__pad2 = 0; nest = nla_nest_start(skb, TCA_ACT_TAB); - if (nest == NULL) + if (!nest) goto out_nlmsg_trim; if (tcf_action_dump(skb, actions, bind, ref) < 0) @@ -840,7 +856,8 @@ out_nlmsg_trim: static int tcf_get_notify(struct net *net, u32 portid, struct nlmsghdr *n, - struct list_head *actions, int event) + struct list_head *actions, int event, + struct netlink_ext_ack *extack) { struct sk_buff *skb; @@ -849,6 +866,7 @@ tcf_get_notify(struct net *net, u32 portid, struct nlmsghdr *n, return -ENOBUFS; if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, event, 0, 0) <= 0) { + NL_SET_ERR_MSG(extack, "Failed to fill netlink attributes while adding TC action"); kfree_skb(skb); return -EINVAL; } @@ -857,7 +875,8 @@ tcf_get_notify(struct net *net, u32 portid, struct nlmsghdr *n, } static struct tc_action *tcf_action_get_1(struct net *net, struct nlattr *nla, - struct nlmsghdr *n, u32 portid) + struct nlmsghdr *n, u32 portid, + struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_ACT_MAX + 1]; const struct tc_action_ops *ops; @@ -865,22 +884,26 @@ static struct tc_action *tcf_action_get_1(struct net *net, struct nlattr *nla, int index; int err; - err = nla_parse_nested(tb, TCA_ACT_MAX, nla, NULL, NULL); + err = nla_parse_nested(tb, TCA_ACT_MAX, nla, NULL, extack); if (err < 0) goto err_out; err = -EINVAL; if (tb[TCA_ACT_INDEX] == NULL || - nla_len(tb[TCA_ACT_INDEX]) < sizeof(index)) + nla_len(tb[TCA_ACT_INDEX]) < sizeof(index)) { + NL_SET_ERR_MSG(extack, "Invalid TC action index value"); goto err_out; + } index = nla_get_u32(tb[TCA_ACT_INDEX]); err = -EINVAL; ops = tc_lookup_action(tb[TCA_ACT_KIND]); - if (!ops) /* could happen in batch of actions */ + if (!ops) { /* could happen in batch of actions */ + NL_SET_ERR_MSG(extack, "Specified TC action not found"); goto err_out; + } err = -ENOENT; - if (ops->lookup(net, &a, index) == 0) + if (ops->lookup(net, &a, index, extack) == 0) goto err_mod; module_put(ops->owner); @@ -893,7 +916,8 @@ err_out: } static int tca_action_flush(struct net *net, struct nlattr *nla, - struct nlmsghdr *n, u32 portid) + struct nlmsghdr *n, u32 portid, + struct netlink_ext_ack *extack) { struct sk_buff *skb; unsigned char *b; @@ -907,39 +931,45 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, int err = -ENOMEM; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); - if (!skb) { - pr_debug("tca_action_flush: failed skb alloc\n"); + if (!skb) return err; - } b = skb_tail_pointer(skb); - err = nla_parse_nested(tb, TCA_ACT_MAX, nla, NULL, NULL); + err = nla_parse_nested(tb, TCA_ACT_MAX, nla, NULL, extack); if (err < 0) goto err_out; err = -EINVAL; kind = tb[TCA_ACT_KIND]; ops = tc_lookup_action(kind); - if (!ops) /*some idjot trying to flush unknown action */ + if (!ops) { /*some idjot trying to flush unknown action */ + NL_SET_ERR_MSG(extack, "Cannot flush unknown TC action"); goto err_out; + } nlh = nlmsg_put(skb, portid, n->nlmsg_seq, RTM_DELACTION, sizeof(*t), 0); - if (!nlh) + if (!nlh) { + NL_SET_ERR_MSG(extack, "Failed to create TC action flush notification"); goto out_module_put; + } t = nlmsg_data(nlh); t->tca_family = AF_UNSPEC; t->tca__pad1 = 0; t->tca__pad2 = 0; nest = nla_nest_start(skb, TCA_ACT_TAB); - if (nest == NULL) + if (!nest) { + NL_SET_ERR_MSG(extack, "Failed to add new netlink message"); goto out_module_put; + } - err = ops->walk(net, skb, &dcb, RTM_DELACTION, ops); - if (err <= 0) + err = ops->walk(net, skb, &dcb, RTM_DELACTION, ops, extack); + if (err <= 0) { + nla_nest_cancel(skb, nest); goto out_module_put; + } nla_nest_end(skb, nest); @@ -950,6 +980,8 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, n->nlmsg_flags & NLM_F_ECHO); if (err > 0) return 0; + if (err < 0) + NL_SET_ERR_MSG(extack, "Failed to send TC action flush notification"); return err; @@ -962,7 +994,7 @@ err_out: static int tcf_del_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions, - u32 portid) + u32 portid, struct netlink_ext_ack *extack) { int ret; struct sk_buff *skb; @@ -973,6 +1005,7 @@ tcf_del_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions, if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, RTM_DELACTION, 0, 1) <= 0) { + NL_SET_ERR_MSG(extack, "Failed to fill netlink TC action attributes"); kfree_skb(skb); return -EINVAL; } @@ -980,6 +1013,7 @@ tcf_del_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions, /* now do the delete */ ret = tcf_action_destroy(actions, 0); if (ret < 0) { + NL_SET_ERR_MSG(extack, "Failed to delete TC action"); kfree_skb(skb); return ret; } @@ -993,26 +1027,27 @@ tcf_del_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions, static int tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, - u32 portid, int event) + u32 portid, int event, struct netlink_ext_ack *extack) { int i, ret; struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; struct tc_action *act; LIST_HEAD(actions); - ret = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL, NULL); + ret = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL, extack); if (ret < 0) return ret; if (event == RTM_DELACTION && n->nlmsg_flags & NLM_F_ROOT) { - if (tb[1] != NULL) - return tca_action_flush(net, tb[1], n, portid); - else - return -EINVAL; + if (tb[1]) + return tca_action_flush(net, tb[1], n, portid, extack); + + NL_SET_ERR_MSG(extack, "Invalid netlink attributes while flushing TC action"); + return -EINVAL; } for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) { - act = tcf_action_get_1(net, tb[i], n, portid); + act = tcf_action_get_1(net, tb[i], n, portid, extack); if (IS_ERR(act)) { ret = PTR_ERR(act); goto err; @@ -1022,9 +1057,9 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, } if (event == RTM_GETACTION) - ret = tcf_get_notify(net, portid, n, &actions, event); + ret = tcf_get_notify(net, portid, n, &actions, event, extack); else { /* delete */ - ret = tcf_del_notify(net, n, &actions, portid); + ret = tcf_del_notify(net, n, &actions, portid, extack); if (ret) goto err; return ret; @@ -1037,7 +1072,7 @@ err: static int tcf_add_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions, - u32 portid) + u32 portid, struct netlink_ext_ack *extack) { struct sk_buff *skb; int err = 0; @@ -1048,6 +1083,7 @@ tcf_add_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions, if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, n->nlmsg_flags, RTM_NEWACTION, 0, 0) <= 0) { + NL_SET_ERR_MSG(extack, "Failed to fill netlink attributes while deleting TC action"); kfree_skb(skb); return -EINVAL; } @@ -1060,16 +1096,18 @@ tcf_add_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions, } static int tcf_action_add(struct net *net, struct nlattr *nla, - struct nlmsghdr *n, u32 portid, int ovr) + struct nlmsghdr *n, u32 portid, int ovr, + struct netlink_ext_ack *extack) { int ret = 0; LIST_HEAD(actions); - ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, &actions); + ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, &actions, + extack); if (ret) return ret; - return tcf_add_notify(net, n, &actions, portid); + return tcf_add_notify(net, n, &actions, portid, extack); } static u32 tcaa_root_flags_allowed = TCA_FLAG_LARGE_DUMP_ON; @@ -1097,7 +1135,7 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, return ret; if (tca[TCA_ACT_TAB] == NULL) { - pr_notice("tc_ctl_action: received NO action attribs\n"); + NL_SET_ERR_MSG(extack, "Netlink action attributes missing"); return -EINVAL; } @@ -1113,17 +1151,18 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, if (n->nlmsg_flags & NLM_F_REPLACE) ovr = 1; replay: - ret = tcf_action_add(net, tca[TCA_ACT_TAB], n, portid, ovr); + ret = tcf_action_add(net, tca[TCA_ACT_TAB], n, portid, ovr, + extack); if (ret == -EAGAIN) goto replay; break; case RTM_DELACTION: ret = tca_action_gd(net, tca[TCA_ACT_TAB], n, - portid, RTM_DELACTION); + portid, RTM_DELACTION, extack); break; case RTM_GETACTION: ret = tca_action_gd(net, tca[TCA_ACT_TAB], n, - portid, RTM_GETACTION); + portid, RTM_GETACTION, extack); break; default: BUG(); @@ -1218,7 +1257,7 @@ static int tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb) if (nest == NULL) goto out_module_put; - ret = a_o->walk(net, skb, cb, RTM_GETACTION, a_o); + ret = a_o->walk(net, skb, cb, RTM_GETACTION, a_o, NULL); if (ret < 0) goto out_module_put; @@ -1454,6 +1493,7 @@ static struct pernet_operations tcf_action_net_ops = { .exit = tcf_action_net_exit, .id = &tcf_action_net_id, .size = sizeof(struct tcf_action_net), + .async = true, }; static int __init tc_action_init(void) diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index b3f2c15affa7..da72e0cf2b1f 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -272,7 +272,7 @@ static void tcf_bpf_prog_fill_cfg(const struct tcf_bpf *prog, static int tcf_bpf_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **act, - int replace, int bind) + int replace, int bind, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, bpf_net_id); struct nlattr *tb[TCA_ACT_BPF_MAX + 1]; @@ -367,14 +367,16 @@ static void tcf_bpf_cleanup(struct tc_action *act) static int tcf_bpf_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, bpf_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_bpf_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_bpf_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, bpf_net_id); @@ -411,6 +413,7 @@ static struct pernet_operations bpf_net_ops = { .exit_batch = bpf_exit_net, .id = &bpf_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; static int __init bpf_init_module(void) diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 2b15ba84e0c8..371e5e4ab3e2 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -96,7 +96,8 @@ static const struct nla_policy connmark_policy[TCA_CONNMARK_MAX + 1] = { static int tcf_connmark_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind) + int ovr, int bind, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, connmark_net_id); struct nlattr *tb[TCA_CONNMARK_MAX + 1]; @@ -176,14 +177,16 @@ nla_put_failure: static int tcf_connmark_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, connmark_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_connmark_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_connmark_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, connmark_net_id); @@ -219,6 +222,7 @@ static struct pernet_operations connmark_net_ops = { .exit_batch = connmark_exit_net, .id = &connmark_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; static int __init connmark_init_module(void) diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index b7ba9b06b147..1fb1f1f6a555 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -46,7 +46,7 @@ static struct tc_action_ops act_csum_ops; static int tcf_csum_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, - int bind) + int bind, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, csum_net_id); struct tcf_csum_params *params_old, *params_new; @@ -631,14 +631,16 @@ static void tcf_csum_cleanup(struct tc_action *a) static int tcf_csum_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, csum_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_csum_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_csum_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, csum_net_id); @@ -675,6 +677,7 @@ static struct pernet_operations csum_net_ops = { .exit_batch = csum_exit_net, .id = &csum_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; MODULE_DESCRIPTION("Checksum updating actions"); diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index b56986d41c87..74563254e676 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -56,7 +56,7 @@ static const struct nla_policy gact_policy[TCA_GACT_MAX + 1] = { static int tcf_gact_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind) + int ovr, int bind, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, gact_net_id); struct nlattr *tb[TCA_GACT_MAX + 1]; @@ -201,14 +201,16 @@ nla_put_failure: static int tcf_gact_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, gact_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_gact_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_gact_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, gact_net_id); @@ -245,6 +247,7 @@ static struct pernet_operations gact_net_ops = { .exit_batch = gact_exit_net, .id = &gact_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; MODULE_AUTHOR("Jamal Hadi Salim(2002-4)"); diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 5954e992685a..555b1caeff72 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -447,7 +447,7 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, static int tcf_ife_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind) + int ovr, int bind, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, ife_net_id); struct nlattr *tb[TCA_IFE_MAX + 1]; @@ -824,14 +824,16 @@ static int tcf_ife_act(struct sk_buff *skb, const struct tc_action *a, static int tcf_ife_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, ife_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_ife_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_ife_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, ife_net_id); @@ -868,6 +870,7 @@ static struct pernet_operations ife_net_ops = { .exit_batch = ife_exit_net, .id = &ife_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; static int __init ife_init_module(void) diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 06e380ae0928..10866717f88e 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -193,7 +193,7 @@ err1: static int tcf_ipt_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, - int bind) + int bind, struct netlink_ext_ack *extack) { return __tcf_ipt_init(net, ipt_net_id, nla, est, a, &act_ipt_ops, ovr, bind); @@ -201,7 +201,7 @@ static int tcf_ipt_init(struct net *net, struct nlattr *nla, static int tcf_xt_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, - int bind) + int bind, struct netlink_ext_ack *extack) { return __tcf_ipt_init(net, xt_net_id, nla, est, a, &act_xt_ops, ovr, bind); @@ -303,14 +303,16 @@ nla_put_failure: static int tcf_ipt_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, ipt_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_ipt_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_ipt_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, ipt_net_id); @@ -347,18 +349,21 @@ static struct pernet_operations ipt_net_ops = { .exit_batch = ipt_exit_net, .id = &ipt_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; static int tcf_xt_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, xt_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_xt_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_xt_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, xt_net_id); @@ -395,6 +400,7 @@ static struct pernet_operations xt_net_ops = { .exit_batch = xt_exit_net, .id = &xt_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; MODULE_AUTHOR("Jamal Hadi Salim(2002-13)"); diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index e6ff88f72900..64c86579c3d9 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -69,7 +69,7 @@ static struct tc_action_ops act_mirred_ops; static int tcf_mirred_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, - int bind) + int bind, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, mirred_net_id); struct nlattr *tb[TCA_MIRRED_MAX + 1]; @@ -80,13 +80,17 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, bool exists = false; int ret; - if (nla == NULL) + if (!nla) { + NL_SET_ERR_MSG_MOD(extack, "Mirred requires attributes to be passed"); return -EINVAL; - ret = nla_parse_nested(tb, TCA_MIRRED_MAX, nla, mirred_policy, NULL); + } + ret = nla_parse_nested(tb, TCA_MIRRED_MAX, nla, mirred_policy, extack); if (ret < 0) return ret; - if (tb[TCA_MIRRED_PARMS] == NULL) + if (!tb[TCA_MIRRED_PARMS]) { + NL_SET_ERR_MSG_MOD(extack, "Missing required mirred parameters"); return -EINVAL; + } parm = nla_data(tb[TCA_MIRRED_PARMS]); exists = tcf_idr_check(tn, parm->index, a, bind); @@ -102,6 +106,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, default: if (exists) tcf_idr_release(*a, bind); + NL_SET_ERR_MSG_MOD(extack, "Unknown mirred option"); return -EINVAL; } if (parm->ifindex) { @@ -117,8 +122,10 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, } if (!exists) { - if (dev == NULL) + if (!dev) { + NL_SET_ERR_MSG_MOD(extack, "Specified device does not exist"); return -EINVAL; + } ret = tcf_idr_create(tn, parm->index, est, a, &act_mirred_ops, bind, true); if (ret) @@ -265,14 +272,16 @@ nla_put_failure: static int tcf_mirred_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, mirred_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_mirred_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_mirred_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, mirred_net_id); @@ -344,6 +353,7 @@ static struct pernet_operations mirred_net_ops = { .exit_batch = mirred_exit_net, .id = &mirred_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; MODULE_AUTHOR("Jamal Hadi Salim(2002)"); diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 98c6a4b2f523..b1bc757f6491 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -37,7 +37,8 @@ static const struct nla_policy nat_policy[TCA_NAT_MAX + 1] = { }; static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, - struct tc_action **a, int ovr, int bind) + struct tc_action **a, int ovr, int bind, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, nat_net_id); struct nlattr *tb[TCA_NAT_MAX + 1]; @@ -277,14 +278,16 @@ nla_put_failure: static int tcf_nat_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, nat_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_nat_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_nat_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, nat_net_id); @@ -320,6 +323,7 @@ static struct pernet_operations nat_net_ops = { .exit_batch = nat_exit_net, .id = &nat_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; MODULE_DESCRIPTION("Stateless NAT actions"); diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 349beaffb29e..5e8cc8f63acd 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -132,7 +132,7 @@ static int tcf_pedit_key_ex_dump(struct sk_buff *skb, static int tcf_pedit_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind) + int ovr, int bind, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, pedit_net_id); struct nlattr *tb[TCA_PEDIT_MAX + 1]; @@ -419,14 +419,16 @@ nla_put_failure: static int tcf_pedit_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, pedit_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_pedit_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_pedit_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, pedit_net_id); @@ -463,6 +465,7 @@ static struct pernet_operations pedit_net_ops = { .exit_batch = pedit_exit_net, .id = &pedit_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; MODULE_AUTHOR("Jamal Hadi Salim(2002-4)"); diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 95d3c9097b25..51fe4fe343f7 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -58,11 +58,12 @@ static struct tc_action_ops act_police_ops; static int tcf_act_police_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, police_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = { @@ -74,7 +75,8 @@ static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = { static int tcf_act_police_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind) + int ovr, int bind, + struct netlink_ext_ack *extack) { int ret = 0, err; struct nlattr *tb[TCA_POLICE_MAX + 1]; @@ -304,7 +306,8 @@ nla_put_failure: return -1; } -static int tcf_police_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_police_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, police_net_id); @@ -344,6 +347,7 @@ static struct pernet_operations police_net_ops = { .exit_batch = police_exit_net, .id = &police_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; static int __init police_init_module(void) diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 1ba0df238756..238dfd27e995 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -37,7 +37,7 @@ static const struct nla_policy sample_policy[TCA_SAMPLE_MAX + 1] = { static int tcf_sample_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, - int bind) + int bind, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, sample_net_id); struct nlattr *tb[TCA_SAMPLE_MAX + 1]; @@ -202,14 +202,16 @@ nla_put_failure: static int tcf_sample_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, sample_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_sample_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_sample_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, sample_net_id); @@ -246,6 +248,7 @@ static struct pernet_operations sample_net_ops = { .exit_batch = sample_exit_net, .id = &sample_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; static int __init sample_init_module(void) diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 425eac11f6da..91816d73f3f3 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -79,7 +79,7 @@ static const struct nla_policy simple_policy[TCA_DEF_MAX + 1] = { static int tcf_simp_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind) + int ovr, int bind, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, simp_net_id); struct nlattr *tb[TCA_DEF_MAX + 1]; @@ -170,14 +170,16 @@ nla_put_failure: static int tcf_simp_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, simp_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_simp_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_simp_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, simp_net_id); @@ -214,6 +216,7 @@ static struct pernet_operations simp_net_ops = { .exit_batch = simp_exit_net, .id = &simp_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; MODULE_AUTHOR("Jamal Hadi Salim(2005)"); diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 5a3f691bb545..7971510fe61b 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -66,7 +66,7 @@ static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = { static int tcf_skbedit_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind) + int ovr, int bind, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, skbedit_net_id); struct nlattr *tb[TCA_SKBEDIT_MAX + 1]; @@ -208,14 +208,16 @@ nla_put_failure: static int tcf_skbedit_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, skbedit_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_skbedit_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_skbedit_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, skbedit_net_id); @@ -251,6 +253,7 @@ static struct pernet_operations skbedit_net_ops = { .exit_batch = skbedit_exit_net, .id = &skbedit_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; MODULE_AUTHOR("Alexander Duyck, <alexander.h.duyck@intel.com>"); diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index fa975262dbac..febec75f4f7a 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -84,7 +84,7 @@ static const struct nla_policy skbmod_policy[TCA_SKBMOD_MAX + 1] = { static int tcf_skbmod_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind) + int ovr, int bind, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, skbmod_net_id); struct nlattr *tb[TCA_SKBMOD_MAX + 1]; @@ -232,14 +232,16 @@ nla_put_failure: static int tcf_skbmod_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, skbmod_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_skbmod_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_skbmod_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, skbmod_net_id); @@ -276,6 +278,7 @@ static struct pernet_operations skbmod_net_ops = { .exit_batch = skbmod_exit_net, .id = &skbmod_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; MODULE_AUTHOR("Jamal Hadi Salim, <jhs@mojatatu.com>"); diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 0e23aac09ad6..9169b7e78ada 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -70,7 +70,7 @@ static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = { static int tunnel_key_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind) + int ovr, int bind, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); struct nlattr *tb[TCA_TUNNEL_KEY_MAX + 1]; @@ -291,14 +291,16 @@ nla_put_failure: static int tunnel_key_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tunnel_key_search(struct net *net, struct tc_action **a, u32 index) +static int tunnel_key_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); @@ -335,6 +337,7 @@ static struct pernet_operations tunnel_key_net_ops = { .exit_batch = tunnel_key_exit_net, .id = &tunnel_key_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; static int __init tunnel_key_init_module(void) diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index e1a1b3f3983a..c2ee7fd51cc9 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -109,7 +109,7 @@ static const struct nla_policy vlan_policy[TCA_VLAN_MAX + 1] = { static int tcf_vlan_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind) + int ovr, int bind, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, vlan_net_id); struct nlattr *tb[TCA_VLAN_MAX + 1]; @@ -267,14 +267,16 @@ nla_put_failure: static int tcf_vlan_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, vlan_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_vlan_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_vlan_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, vlan_net_id); @@ -311,6 +313,7 @@ static struct pernet_operations vlan_net_ops = { .exit_batch = vlan_exit_net, .id = &vlan_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; static int __init vlan_init_module(void) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 2bc1bc23d42e..19f9f421d5b7 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -376,17 +376,12 @@ struct tcf_net { static unsigned int tcf_net_id; static int tcf_block_insert(struct tcf_block *block, struct net *net, - u32 block_index, struct netlink_ext_ack *extack) + struct netlink_ext_ack *extack) { struct tcf_net *tn = net_generic(net, tcf_net_id); - int err; - err = idr_alloc_u32(&tn->idr, block, &block_index, block_index, - GFP_KERNEL); - if (err) - return err; - block->index = block_index; - return 0; + return idr_alloc_u32(&tn->idr, block, &block->index, block->index, + GFP_KERNEL); } static void tcf_block_remove(struct tcf_block *block, struct net *net) @@ -397,6 +392,7 @@ static void tcf_block_remove(struct tcf_block *block, struct net *net) } static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q, + u32 block_index, struct netlink_ext_ack *extack) { struct tcf_block *block; @@ -419,10 +415,13 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q, err = -ENOMEM; goto err_chain_create; } - block->net = qdisc_net(q); block->refcnt = 1; block->net = net; - block->q = q; + block->index = block_index; + + /* Don't store q pointer for blocks which are shared */ + if (!tcf_block_shared(block)) + block->q = q; return block; err_chain_create: @@ -518,13 +517,12 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q, } if (!block) { - block = tcf_block_create(net, q, extack); + block = tcf_block_create(net, q, ei->block_index, extack); if (IS_ERR(block)) return PTR_ERR(block); created = true; - if (ei->block_index) { - err = tcf_block_insert(block, net, - ei->block_index, extack); + if (tcf_block_shared(block)) { + err = tcf_block_insert(block, net, extack); if (err) goto err_block_insert; } @@ -1399,13 +1397,18 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) nla_get_u32(tca[TCA_CHAIN]) != chain->index) continue; if (!tcf_chain_dump(chain, q, parent, skb, cb, - index_start, &index)) + index_start, &index)) { + err = -EMSGSIZE; break; + } } cb->args[0] = index; out: + /* If we did no progress, the error (EMSGSIZE) is real */ + if (skb->len == 0 && err) + return err; return skb->len; } @@ -1434,7 +1437,7 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, if (exts->police && tb[exts->police]) { act = tcf_action_init_1(net, tp, tb[exts->police], rate_tlv, "police", ovr, - TCA_ACT_BIND); + TCA_ACT_BIND, extack); if (IS_ERR(act)) return PTR_ERR(act); @@ -1447,7 +1450,7 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, err = tcf_action_init(net, tp, tb[exts->action], rate_tlv, NULL, ovr, TCA_ACT_BIND, - &actions); + &actions, extack); if (err) return err; list_for_each_entry(act, &actions, list) @@ -1615,6 +1618,7 @@ static struct pernet_operations tcf_net_ops = { .exit = tcf_net_exit, .id = &tcf_net_id, .size = sizeof(struct tcf_net), + .async = true, }; static int __init tc_filter_init(void) diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 6c7601a530e3..ed8b6a24b9e9 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -96,7 +96,7 @@ struct tc_u_hnode { struct tc_u_common { struct tc_u_hnode __rcu *hlist; - struct tcf_block *block; + void *ptr; int refcnt; struct idr handle_idr; struct hlist_node hnode; @@ -330,9 +330,25 @@ static struct hlist_head *tc_u_common_hash; #define U32_HASH_SHIFT 10 #define U32_HASH_SIZE (1 << U32_HASH_SHIFT) +static void *tc_u_common_ptr(const struct tcf_proto *tp) +{ + struct tcf_block *block = tp->chain->block; + + /* The block sharing is currently supported only + * for classless qdiscs. In that case we use block + * for tc_u_common identification. In case the + * block is not shared, block->q is a valid pointer + * and we can use that. That works for classful qdiscs. + */ + if (tcf_block_shared(block)) + return block; + else + return block->q; +} + static unsigned int tc_u_hash(const struct tcf_proto *tp) { - return hash_ptr(tp->chain->block, U32_HASH_SHIFT); + return hash_ptr(tc_u_common_ptr(tp), U32_HASH_SHIFT); } static struct tc_u_common *tc_u_common_find(const struct tcf_proto *tp) @@ -342,7 +358,7 @@ static struct tc_u_common *tc_u_common_find(const struct tcf_proto *tp) h = tc_u_hash(tp); hlist_for_each_entry(tc, &tc_u_common_hash[h], hnode) { - if (tc->block == tp->chain->block) + if (tc->ptr == tc_u_common_ptr(tp)) return tc; } return NULL; @@ -371,7 +387,7 @@ static int u32_init(struct tcf_proto *tp) kfree(root_ht); return -ENOBUFS; } - tp_c->block = tp->chain->block; + tp_c->ptr = tc_u_common_ptr(tp); INIT_HLIST_NODE(&tp_c->hnode); idr_init(&tp_c->handle_idr); diff --git a/net/sched/em_ipt.c b/net/sched/em_ipt.c new file mode 100644 index 000000000000..a5f34e930eff --- /dev/null +++ b/net/sched/em_ipt.c @@ -0,0 +1,257 @@ +/* + * net/sched/em_ipt.c IPtables matches Ematch + * + * (c) 2018 Eyal Birger <eyal.birger@gmail.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/gfp.h> +#include <linux/module.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/skbuff.h> +#include <linux/tc_ematch/tc_em_ipt.h> +#include <linux/netfilter.h> +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter_ipv6/ip6_tables.h> +#include <net/pkt_cls.h> + +struct em_ipt_match { + const struct xt_match *match; + u32 hook; + u8 match_data[0] __aligned(8); +}; + +struct em_ipt_xt_match { + char *match_name; + int (*validate_match_data)(struct nlattr **tb, u8 mrev); +}; + +static const struct nla_policy em_ipt_policy[TCA_EM_IPT_MAX + 1] = { + [TCA_EM_IPT_MATCH_NAME] = { .type = NLA_STRING, + .len = XT_EXTENSION_MAXNAMELEN }, + [TCA_EM_IPT_MATCH_REVISION] = { .type = NLA_U8 }, + [TCA_EM_IPT_HOOK] = { .type = NLA_U32 }, + [TCA_EM_IPT_NFPROTO] = { .type = NLA_U8 }, + [TCA_EM_IPT_MATCH_DATA] = { .type = NLA_UNSPEC }, +}; + +static int check_match(struct net *net, struct em_ipt_match *im, int mdata_len) +{ + struct xt_mtchk_param mtpar = {}; + union { + struct ipt_entry e4; + struct ip6t_entry e6; + } e = {}; + + mtpar.net = net; + mtpar.table = "filter"; + mtpar.hook_mask = 1 << im->hook; + mtpar.family = im->match->family; + mtpar.match = im->match; + mtpar.entryinfo = &e; + mtpar.matchinfo = (void *)im->match_data; + return xt_check_match(&mtpar, mdata_len, 0, 0); +} + +static int policy_validate_match_data(struct nlattr **tb, u8 mrev) +{ + if (mrev != 0) { + pr_err("only policy match revision 0 supported"); + return -EINVAL; + } + + if (nla_get_u32(tb[TCA_EM_IPT_HOOK]) != NF_INET_PRE_ROUTING) { + pr_err("policy can only be matched on NF_INET_PRE_ROUTING"); + return -EINVAL; + } + + return 0; +} + +static const struct em_ipt_xt_match em_ipt_xt_matches[] = { + { + .match_name = "policy", + .validate_match_data = policy_validate_match_data + }, + {} +}; + +static struct xt_match *get_xt_match(struct nlattr **tb) +{ + const struct em_ipt_xt_match *m; + struct nlattr *mname_attr; + u8 nfproto, mrev = 0; + int ret; + + mname_attr = tb[TCA_EM_IPT_MATCH_NAME]; + for (m = em_ipt_xt_matches; m->match_name; m++) { + if (!nla_strcmp(mname_attr, m->match_name)) + break; + } + + if (!m->match_name) { + pr_err("Unsupported xt match"); + return ERR_PTR(-EINVAL); + } + + if (tb[TCA_EM_IPT_MATCH_REVISION]) + mrev = nla_get_u8(tb[TCA_EM_IPT_MATCH_REVISION]); + + ret = m->validate_match_data(tb, mrev); + if (ret < 0) + return ERR_PTR(ret); + + nfproto = nla_get_u8(tb[TCA_EM_IPT_NFPROTO]); + return xt_request_find_match(nfproto, m->match_name, mrev); +} + +static int em_ipt_change(struct net *net, void *data, int data_len, + struct tcf_ematch *em) +{ + struct nlattr *tb[TCA_EM_IPT_MAX + 1]; + struct em_ipt_match *im = NULL; + struct xt_match *match; + int mdata_len, ret; + + ret = nla_parse(tb, TCA_EM_IPT_MAX, data, data_len, em_ipt_policy, + NULL); + if (ret < 0) + return ret; + + if (!tb[TCA_EM_IPT_HOOK] || !tb[TCA_EM_IPT_MATCH_NAME] || + !tb[TCA_EM_IPT_MATCH_DATA] || !tb[TCA_EM_IPT_NFPROTO]) + return -EINVAL; + + match = get_xt_match(tb); + if (IS_ERR(match)) { + pr_err("unable to load match\n"); + return PTR_ERR(match); + } + + mdata_len = XT_ALIGN(nla_len(tb[TCA_EM_IPT_MATCH_DATA])); + im = kzalloc(sizeof(*im) + mdata_len, GFP_KERNEL); + if (!im) { + ret = -ENOMEM; + goto err; + } + + im->match = match; + im->hook = nla_get_u32(tb[TCA_EM_IPT_HOOK]); + nla_memcpy(im->match_data, tb[TCA_EM_IPT_MATCH_DATA], mdata_len); + + ret = check_match(net, im, mdata_len); + if (ret) + goto err; + + em->datalen = sizeof(*im) + mdata_len; + em->data = (unsigned long)im; + return 0; + +err: + kfree(im); + module_put(match->me); + return ret; +} + +static void em_ipt_destroy(struct tcf_ematch *em) +{ + struct em_ipt_match *im = (void *)em->data; + + if (!im) + return; + + if (im->match->destroy) { + struct xt_mtdtor_param par = { + .net = em->net, + .match = im->match, + .matchinfo = im->match_data, + .family = im->match->family + }; + im->match->destroy(&par); + } + module_put(im->match->me); + kfree((void *)im); +} + +static int em_ipt_match(struct sk_buff *skb, struct tcf_ematch *em, + struct tcf_pkt_info *info) +{ + const struct em_ipt_match *im = (const void *)em->data; + struct xt_action_param acpar = {}; + struct net_device *indev = NULL; + struct nf_hook_state state; + int ret; + + rcu_read_lock(); + + if (skb->skb_iif) + indev = dev_get_by_index_rcu(em->net, skb->skb_iif); + + nf_hook_state_init(&state, im->hook, im->match->family, + indev ?: skb->dev, skb->dev, NULL, em->net, NULL); + + acpar.match = im->match; + acpar.matchinfo = im->match_data; + acpar.state = &state; + + ret = im->match->match(skb, &acpar); + + rcu_read_unlock(); + return ret; +} + +static int em_ipt_dump(struct sk_buff *skb, struct tcf_ematch *em) +{ + struct em_ipt_match *im = (void *)em->data; + + if (nla_put_string(skb, TCA_EM_IPT_MATCH_NAME, im->match->name) < 0) + return -EMSGSIZE; + if (nla_put_u32(skb, TCA_EM_IPT_HOOK, im->hook) < 0) + return -EMSGSIZE; + if (nla_put_u8(skb, TCA_EM_IPT_MATCH_REVISION, im->match->revision) < 0) + return -EMSGSIZE; + if (nla_put_u8(skb, TCA_EM_IPT_NFPROTO, im->match->family) < 0) + return -EMSGSIZE; + if (nla_put(skb, TCA_EM_IPT_MATCH_DATA, + im->match->usersize ?: im->match->matchsize, + im->match_data) < 0) + return -EMSGSIZE; + + return 0; +} + +static struct tcf_ematch_ops em_ipt_ops = { + .kind = TCF_EM_IPT, + .change = em_ipt_change, + .destroy = em_ipt_destroy, + .match = em_ipt_match, + .dump = em_ipt_dump, + .owner = THIS_MODULE, + .link = LIST_HEAD_INIT(em_ipt_ops.link) +}; + +static int __init init_em_ipt(void) +{ + return tcf_em_register(&em_ipt_ops); +} + +static void __exit exit_em_ipt(void) +{ + tcf_em_unregister(&em_ipt_ops); +} + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Eyal Birger <eyal.birger@gmail.com>"); +MODULE_DESCRIPTION("TC extended match for IPtables matches"); + +module_init(init_em_ipt); +module_exit(exit_em_ipt); + +MODULE_ALIAS_TCF_EMATCH(TCF_EM_IPT); diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index d512f49ee83c..27e672c12492 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -2128,6 +2128,7 @@ static void __net_exit psched_net_exit(struct net *net) static struct pernet_operations psched_net_ops = { .init = psched_net_init, .exit = psched_net_exit, + .async = true, }; static int __init pktsched_init(void) diff --git a/net/sctp/Makefile b/net/sctp/Makefile index 6776582ec449..e845e4588535 100644 --- a/net/sctp/Makefile +++ b/net/sctp/Makefile @@ -15,6 +15,8 @@ sctp-y := sm_statetable.o sm_statefuns.o sm_sideeffect.o \ offload.o stream_sched.o stream_sched_prio.o \ stream_sched_rr.o stream_interleave.o +sctp_diag-y := diag.o + sctp-$(CONFIG_SCTP_DBG_OBJCNT) += objcnt.o sctp-$(CONFIG_PROC_FS) += proc.o sctp-$(CONFIG_SYSCTL) += sysctl.o diff --git a/net/sctp/debug.c b/net/sctp/debug.c index 291c97b07058..8f6c2e8c0953 100644 --- a/net/sctp/debug.c +++ b/net/sctp/debug.c @@ -81,6 +81,12 @@ const char *sctp_cname(const union sctp_subtype cid) case SCTP_CID_RECONF: return "RECONF"; + case SCTP_CID_I_DATA: + return "I_DATA"; + + case SCTP_CID_I_FWD_TSN: + return "I_FWD_TSN"; + default: break; } diff --git a/net/sctp/sctp_diag.c b/net/sctp/diag.c index a72a7d925d46..078f01a8d582 100644 --- a/net/sctp/sctp_diag.c +++ b/net/sctp/diag.c @@ -1,3 +1,34 @@ +/* SCTP kernel implementation + * (C) Copyright Red Hat Inc. 2017 + * + * This file is part of the SCTP kernel implementation + * + * These functions implement sctp diag support. + * + * This SCTP implementation is free software; + * you can redistribute it and/or modify it under the terms of + * the GNU General Public License as published by + * the Free Software Foundation; either version 2, or (at your option) + * any later version. + * + * This SCTP implementation is distributed in the hope that it + * will be useful, but WITHOUT ANY WARRANTY; without even the implied + * ************************ + * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + * See the GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with GNU CC; see the file COPYING. If not, see + * <http://www.gnu.org/licenses/>. + * + * Please send any bug reports or fixes you make to the + * email addresched(es): + * lksctp developers <linux-sctp@vger.kernel.org> + * + * Written or modified by: + * Xin Long <lucien.xin@gmail.com> + */ + #include <linux/module.h> #include <linux/inet_diag.h> #include <linux/sock_diag.h> diff --git a/net/sctp/input.c b/net/sctp/input.c index 141c9c466ec1..0247cc432e02 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -897,15 +897,12 @@ int sctp_hash_transport(struct sctp_transport *t) rhl_for_each_entry_rcu(transport, tmp, list, node) if (transport->asoc->ep == t->asoc->ep) { rcu_read_unlock(); - err = -EEXIST; - goto out; + return -EEXIST; } rcu_read_unlock(); err = rhltable_insert_key(&sctp_transport_hashtable, &arg, &t->node, sctp_hash_params); - -out: if (err) pr_err_once("insert transport fail, errno %d\n", err); diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index e35d4f73d2df..0d873c58e516 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -952,16 +952,16 @@ static int sctp_inet6_supported_addrs(const struct sctp_sock *opt, /* Handle SCTP_I_WANT_MAPPED_V4_ADDR for getpeername() and getsockname() */ static int sctp_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { int rc; - rc = inet6_getname(sock, uaddr, uaddr_len, peer); + rc = inet6_getname(sock, uaddr, peer); - if (rc != 0) + if (rc < 0) return rc; - *uaddr_len = sctp_v6_addr_to_user(sctp_sk(sock->sk), + rc = sctp_v6_addr_to_user(sctp_sk(sock->sk), (union sctp_addr *)uaddr); return rc; diff --git a/net/sctp/stream.c b/net/sctp/stream.c index cedf672487f9..f799043abec9 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -6,7 +6,7 @@ * * This file is part of the SCTP kernel implementation * - * These functions manipulate sctp tsn mapping array. + * This file contains sctp stream maniuplation primitives and helpers. * * This SCTP implementation is free software; * you can redistribute it and/or modify it under the terms of diff --git a/net/sctp/stream_interleave.c b/net/sctp/stream_interleave.c index 8c7cf8f08711..d3764c181299 100644 --- a/net/sctp/stream_interleave.c +++ b/net/sctp/stream_interleave.c @@ -3,7 +3,8 @@ * * This file is part of the SCTP kernel implementation * - * These functions manipulate sctp stream queue/scheduling. + * These functions implement sctp stream message interleaving, mostly + * including I-DATA and I-FORWARD-TSN chunks process. * * This SCTP implementation is free software; * you can redistribute it and/or modify it under the terms of @@ -954,12 +955,8 @@ static void sctp_renege_events(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk, __u32 freed = 0; __u16 needed; - if (chunk) { - needed = ntohs(chunk->chunk_hdr->length); - needed -= sizeof(struct sctp_idata_chunk); - } else { - needed = SCTP_DEFAULT_MAXWINDOW; - } + needed = ntohs(chunk->chunk_hdr->length) - + sizeof(struct sctp_idata_chunk); if (skb_queue_empty(&asoc->base.sk->sk_receive_queue)) { freed = sctp_ulpq_renege_list(ulpq, &ulpq->lobby, needed); @@ -971,9 +968,8 @@ static void sctp_renege_events(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk, needed); } - if (chunk && freed >= needed) - if (sctp_ulpevent_idata(ulpq, chunk, gfp) <= 0) - sctp_intl_start_pd(ulpq, gfp); + if (freed >= needed && sctp_ulpevent_idata(ulpq, chunk, gfp) <= 0) + sctp_intl_start_pd(ulpq, gfp); sk_mem_reclaim(asoc->base.sk); } diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index da1a5cdefd13..38ae22b65e77 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -281,7 +281,6 @@ int smc_netinfo_by_tcpsk(struct socket *clcsock, struct in_device *in_dev; struct sockaddr_in addr; int rc = -ENOENT; - int len; if (!dst) { rc = -ENOTCONN; @@ -293,7 +292,7 @@ int smc_netinfo_by_tcpsk(struct socket *clcsock, } /* get address to which the internal TCP socket is bound */ - kernel_getsockname(clcsock, (struct sockaddr *)&addr, &len); + kernel_getsockname(clcsock, (struct sockaddr *)&addr); /* analyze IPv4 specific data of net_device belonging to TCP socket */ rcu_read_lock(); in_dev = __in_dev_get_rcu(dst->dev); @@ -771,7 +770,7 @@ static void smc_listen_work(struct work_struct *work) u8 buf[SMC_CLC_MAX_LEN]; struct smc_link *link; int reason_code = 0; - int rc = 0, len; + int rc = 0; __be32 subnet; u8 prefix_len; u8 ibport; @@ -824,7 +823,7 @@ static void smc_listen_work(struct work_struct *work) } /* get address of the peer connected to the internal TCP socket */ - kernel_getpeername(newclcsock, (struct sockaddr *)&peeraddr, &len); + kernel_getpeername(newclcsock, (struct sockaddr *)&peeraddr); /* allocate connection / link group */ mutex_lock(&smc_create_lgr_pending); @@ -1075,7 +1074,7 @@ out: } static int smc_getname(struct socket *sock, struct sockaddr *addr, - int *len, int peer) + int peer) { struct smc_sock *smc; @@ -1085,7 +1084,7 @@ static int smc_getname(struct socket *sock, struct sockaddr *addr, smc = smc_sk(sock->sk); - return smc->clcsock->ops->getname(smc->clcsock, addr, len, peer); + return smc->clcsock->ops->getname(smc->clcsock, addr, peer); } static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) diff --git a/net/socket.c b/net/socket.c index a93c99b518ca..645d32b4872c 100644 --- a/net/socket.c +++ b/net/socket.c @@ -104,7 +104,6 @@ #include <linux/ipv6_route.h> #include <linux/route.h> #include <linux/sockios.h> -#include <linux/atalk.h> #include <net/busy_poll.h> #include <linux/errqueue.h> @@ -234,7 +233,7 @@ static int move_addr_to_user(struct sockaddr_storage *kaddr, int klen, return __put_user(klen, ulen); } -static struct kmem_cache *sock_inode_cachep __read_mostly; +static struct kmem_cache *sock_inode_cachep __ro_after_init; static struct inode *sock_alloc_inode(struct super_block *sb) { @@ -991,10 +990,11 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, * what to do with it - that's up to the protocol still. */ -static struct ns_common *get_net_ns(struct ns_common *ns) +struct ns_common *get_net_ns(struct ns_common *ns) { return &get_net(container_of(ns, struct net, ns))->ns; } +EXPORT_SYMBOL_GPL(get_net_ns); static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) { @@ -1573,8 +1573,9 @@ SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr, goto out_fd; if (upeer_sockaddr) { - if (newsock->ops->getname(newsock, (struct sockaddr *)&address, - &len, 2) < 0) { + len = newsock->ops->getname(newsock, + (struct sockaddr *)&address, 2); + if (len < 0) { err = -ECONNABORTED; goto out_fd; } @@ -1654,7 +1655,7 @@ SYSCALL_DEFINE3(getsockname, int, fd, struct sockaddr __user *, usockaddr, { struct socket *sock; struct sockaddr_storage address; - int len, err, fput_needed; + int err, fput_needed; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) @@ -1664,10 +1665,11 @@ SYSCALL_DEFINE3(getsockname, int, fd, struct sockaddr __user *, usockaddr, if (err) goto out_put; - err = sock->ops->getname(sock, (struct sockaddr *)&address, &len, 0); - if (err) + err = sock->ops->getname(sock, (struct sockaddr *)&address, 0); + if (err < 0) goto out_put; - err = move_addr_to_user(&address, len, usockaddr, usockaddr_len); + /* "err" is actually length in this case */ + err = move_addr_to_user(&address, err, usockaddr, usockaddr_len); out_put: fput_light(sock->file, fput_needed); @@ -1685,7 +1687,7 @@ SYSCALL_DEFINE3(getpeername, int, fd, struct sockaddr __user *, usockaddr, { struct socket *sock; struct sockaddr_storage address; - int len, err, fput_needed; + int err, fput_needed; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock != NULL) { @@ -1695,11 +1697,10 @@ SYSCALL_DEFINE3(getpeername, int, fd, struct sockaddr __user *, usockaddr, return err; } - err = - sock->ops->getname(sock, (struct sockaddr *)&address, &len, - 1); - if (!err) - err = move_addr_to_user(&address, len, usockaddr, + err = sock->ops->getname(sock, (struct sockaddr *)&address, 1); + if (err >= 0) + /* "err" is actually length in this case */ + err = move_addr_to_user(&address, err, usockaddr, usockaddr_len); fput_light(sock->file, fput_needed); } @@ -3166,17 +3167,15 @@ int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen, } EXPORT_SYMBOL(kernel_connect); -int kernel_getsockname(struct socket *sock, struct sockaddr *addr, - int *addrlen) +int kernel_getsockname(struct socket *sock, struct sockaddr *addr) { - return sock->ops->getname(sock, addr, addrlen, 0); + return sock->ops->getname(sock, addr, 0); } EXPORT_SYMBOL(kernel_getsockname); -int kernel_getpeername(struct socket *sock, struct sockaddr *addr, - int *addrlen) +int kernel_getpeername(struct socket *sock, struct sockaddr *addr) { - return sock->ops->getname(sock, addr, addrlen, 1); + return sock->ops->getname(sock, addr, 1); } EXPORT_SYMBOL(kernel_getpeername); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 6e432ecd7f99..806395687bb6 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1231,7 +1231,7 @@ static const struct sockaddr_in6 rpc_in6addr_loopback = { * negative errno is returned. */ static int rpc_sockname(struct net *net, struct sockaddr *sap, size_t salen, - struct sockaddr *buf, int buflen) + struct sockaddr *buf) { struct socket *sock; int err; @@ -1269,7 +1269,7 @@ static int rpc_sockname(struct net *net, struct sockaddr *sap, size_t salen, goto out_release; } - err = kernel_getsockname(sock, buf, &buflen); + err = kernel_getsockname(sock, buf); if (err < 0) { dprintk("RPC: getsockname failed (%d)\n", err); goto out_release; @@ -1353,7 +1353,7 @@ int rpc_localaddr(struct rpc_clnt *clnt, struct sockaddr *buf, size_t buflen) rcu_read_unlock(); rpc_set_port(sap, 0); - err = rpc_sockname(net, sap, salen, buf, buflen); + err = rpc_sockname(net, sap, salen, buf); put_net(net); if (err != 0) /* Couldn't discover local address, return ANYADDR */ diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 943f2a745cd5..08cd951aaeea 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -832,12 +832,13 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt) } set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags); - err = kernel_getpeername(newsock, sin, &slen); + err = kernel_getpeername(newsock, sin); if (err < 0) { net_warn_ratelimited("%s: peername failed (err %d)!\n", serv->sv_name, -err); goto failed; /* aborted connection or whatever */ } + slen = err; /* Ideally, we would want to reject connections from unauthorized * hosts here, but when we get encryption, the IP of the host won't @@ -866,7 +867,8 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt) if (IS_ERR(newsvsk)) goto failed; svc_xprt_set_remote(&newsvsk->sk_xprt, sin, slen); - err = kernel_getsockname(newsock, sin, &slen); + err = kernel_getsockname(newsock, sin); + slen = err; if (unlikely(err < 0)) { dprintk("svc_tcp_accept: kernel_getsockname error %d\n", -err); slen = offsetof(struct sockaddr, sa_data); @@ -1465,7 +1467,8 @@ int svc_addsock(struct svc_serv *serv, const int fd, char *name_return, err = PTR_ERR(svsk); goto out; } - if (kernel_getsockname(svsk->sk_sock, sin, &salen) == 0) + salen = kernel_getsockname(svsk->sk_sock, sin); + if (salen >= 0) svc_xprt_set_local(&svsk->sk_xprt, sin, salen); svc_add_new_perm_xprt(serv, &svsk->sk_xprt); return svc_one_sock_name(svsk, name_return, len); @@ -1539,10 +1542,10 @@ static struct svc_xprt *svc_create_socket(struct svc_serv *serv, if (error < 0) goto bummer; - newlen = len; - error = kernel_getsockname(sock, newsin, &newlen); + error = kernel_getsockname(sock, newsin); if (error < 0) goto bummer; + newlen = error; if (protocol == IPPROTO_TCP) { if ((error = kernel_listen(sock, 64)) < 0) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index a6b8c1f8f92a..956e29c1438d 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1794,10 +1794,9 @@ static void xs_sock_set_reuseport(struct socket *sock) static unsigned short xs_sock_getport(struct socket *sock) { struct sockaddr_storage buf; - int buflen; unsigned short port = 0; - if (kernel_getsockname(sock, (struct sockaddr *)&buf, &buflen) < 0) + if (kernel_getsockname(sock, (struct sockaddr *)&buf) < 0) goto out; switch (buf.ss_family) { case AF_INET6: diff --git a/net/sysctl_net.c b/net/sysctl_net.c index 9aed6fe1bf1a..f424539829b7 100644 --- a/net/sysctl_net.c +++ b/net/sysctl_net.c @@ -89,6 +89,7 @@ static void __net_exit sysctl_net_exit(struct net *net) static struct pernet_operations sysctl_pernet_ops = { .init = sysctl_net_init, .exit = sysctl_net_exit, + .async = true, }; static struct ctl_table_header *net_header; diff --git a/net/tipc/Makefile b/net/tipc/Makefile index 37bb0bfbd936..1edb7192aa2f 100644 --- a/net/tipc/Makefile +++ b/net/tipc/Makefile @@ -9,7 +9,7 @@ tipc-y += addr.o bcast.o bearer.o \ core.o link.o discover.o msg.o \ name_distr.o subscr.o monitor.o name_table.o net.o \ netlink.o netlink_compat.o node.o socket.o eth_media.o \ - server.o socket.o group.o + topsrv.o socket.o group.o tipc-$(CONFIG_TIPC_MEDIA_UDP) += udp_media.o tipc-$(CONFIG_TIPC_MEDIA_IB) += ib_media.o diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index c8001471da6c..f3d2e83313e1 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -813,7 +813,7 @@ err_out: return err; } -int tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info) +int __tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info) { int err; char *name; @@ -835,20 +835,27 @@ int tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info) name = nla_data(attrs[TIPC_NLA_BEARER_NAME]); - rtnl_lock(); bearer = tipc_bearer_find(net, name); - if (!bearer) { - rtnl_unlock(); + if (!bearer) return -EINVAL; - } bearer_disable(net, bearer); - rtnl_unlock(); return 0; } -int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info) +int tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info) +{ + int err; + + rtnl_lock(); + err = __tipc_nl_bearer_disable(skb, info); + rtnl_unlock(); + + return err; +} + +int __tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info) { int err; char *bearer; @@ -890,15 +897,18 @@ int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info) prio = nla_get_u32(props[TIPC_NLA_PROP_PRIO]); } + return tipc_enable_bearer(net, bearer, domain, prio, attrs); +} + +int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info) +{ + int err; + rtnl_lock(); - err = tipc_enable_bearer(net, bearer, domain, prio, attrs); - if (err) { - rtnl_unlock(); - return err; - } + err = __tipc_nl_bearer_enable(skb, info); rtnl_unlock(); - return 0; + return err; } int tipc_nl_bearer_add(struct sk_buff *skb, struct genl_info *info) @@ -944,13 +954,13 @@ int tipc_nl_bearer_add(struct sk_buff *skb, struct genl_info *info) return 0; } -int tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info) +int __tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info) { - int err; - char *name; struct tipc_bearer *b; struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1]; struct net *net = sock_net(skb->sk); + char *name; + int err; if (!info->attrs[TIPC_NLA_BEARER]) return -EINVAL; @@ -965,35 +975,42 @@ int tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info) return -EINVAL; name = nla_data(attrs[TIPC_NLA_BEARER_NAME]); - rtnl_lock(); b = tipc_bearer_find(net, name); - if (!b) { - rtnl_unlock(); + if (!b) return -EINVAL; - } if (attrs[TIPC_NLA_BEARER_PROP]) { struct nlattr *props[TIPC_NLA_PROP_MAX + 1]; err = tipc_nl_parse_link_prop(attrs[TIPC_NLA_BEARER_PROP], props); - if (err) { - rtnl_unlock(); + if (err) return err; - } - if (props[TIPC_NLA_PROP_TOL]) + if (props[TIPC_NLA_PROP_TOL]) { b->tolerance = nla_get_u32(props[TIPC_NLA_PROP_TOL]); + tipc_node_apply_tolerance(net, b); + } if (props[TIPC_NLA_PROP_PRIO]) b->priority = nla_get_u32(props[TIPC_NLA_PROP_PRIO]); if (props[TIPC_NLA_PROP_WIN]) b->window = nla_get_u32(props[TIPC_NLA_PROP_WIN]); } - rtnl_unlock(); return 0; } +int tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info) +{ + int err; + + rtnl_lock(); + err = __tipc_nl_bearer_set(skb, info); + rtnl_unlock(); + + return err; +} + static int __tipc_nl_add_media(struct tipc_nl_msg *msg, struct tipc_media *media, int nlflags) { @@ -1115,7 +1132,7 @@ err_out: return err; } -int tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info) +int __tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info) { int err; char *name; @@ -1133,22 +1150,17 @@ int tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info) return -EINVAL; name = nla_data(attrs[TIPC_NLA_MEDIA_NAME]); - rtnl_lock(); m = tipc_media_find(name); - if (!m) { - rtnl_unlock(); + if (!m) return -EINVAL; - } if (attrs[TIPC_NLA_MEDIA_PROP]) { struct nlattr *props[TIPC_NLA_PROP_MAX + 1]; err = tipc_nl_parse_link_prop(attrs[TIPC_NLA_MEDIA_PROP], props); - if (err) { - rtnl_unlock(); + if (err) return err; - } if (props[TIPC_NLA_PROP_TOL]) m->tolerance = nla_get_u32(props[TIPC_NLA_PROP_TOL]); @@ -1157,7 +1169,17 @@ int tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info) if (props[TIPC_NLA_PROP_WIN]) m->window = nla_get_u32(props[TIPC_NLA_PROP_WIN]); } - rtnl_unlock(); return 0; } + +int tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info) +{ + int err; + + rtnl_lock(); + err = __tipc_nl_media_set(skb, info); + rtnl_unlock(); + + return err; +} diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 42d6eeeb646d..a53613d95bc9 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -188,15 +188,19 @@ extern struct tipc_media udp_media_info; #endif int tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info); +int __tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info); int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info); +int __tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info); int tipc_nl_bearer_dump(struct sk_buff *skb, struct netlink_callback *cb); int tipc_nl_bearer_get(struct sk_buff *skb, struct genl_info *info); int tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info); +int __tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info); int tipc_nl_bearer_add(struct sk_buff *skb, struct genl_info *info); int tipc_nl_media_dump(struct sk_buff *skb, struct netlink_callback *cb); int tipc_nl_media_get(struct sk_buff *skb, struct genl_info *info); int tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info); +int __tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info); int tipc_media_set_priority(const char *name, u32 new_value); int tipc_media_set_window(const char *name, u32 new_value); diff --git a/net/tipc/core.h b/net/tipc/core.h index 20b21af2ff14..ff8b071654f5 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -64,7 +64,7 @@ struct tipc_bearer; struct tipc_bc_base; struct tipc_link; struct tipc_name_table; -struct tipc_server; +struct tipc_topsrv; struct tipc_monitor; #define TIPC_MOD_VER "2.0.0" @@ -112,7 +112,7 @@ struct tipc_net { struct list_head dist_queue; /* Topology subscription server */ - struct tipc_server *topsrv; + struct tipc_topsrv *topsrv; atomic_t subscription_count; }; @@ -131,7 +131,7 @@ static inline struct list_head *tipc_nodes(struct net *net) return &tipc_net(net)->node_list; } -static inline struct tipc_server *tipc_topsrv(struct net *net) +static inline struct tipc_topsrv *tipc_topsrv(struct net *net) { return tipc_net(net)->topsrv; } diff --git a/net/tipc/group.c b/net/tipc/group.c index 122162a31816..03086ccb7746 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -37,7 +37,7 @@ #include "addr.h" #include "group.h" #include "bcast.h" -#include "server.h" +#include "topsrv.h" #include "msg.h" #include "socket.h" #include "node.h" diff --git a/net/tipc/link.c b/net/tipc/link.c index 2d6b2aed30e0..3c230466804d 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -2126,7 +2126,8 @@ void tipc_link_set_tolerance(struct tipc_link *l, u32 tol, struct sk_buff_head *xmitq) { l->tolerance = tol; - tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, tol, 0, xmitq); + if (link_is_up(l)) + tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, tol, 0, xmitq); } void tipc_link_set_prio(struct tipc_link *l, u32 prio, diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index ed0457cc99d6..e01c9c691ba2 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -326,10 +326,10 @@ static struct publication *tipc_nameseq_insert_publ(struct net *net, /* Any subscriptions waiting for notification? */ list_for_each_entry_safe(s, st, &nseq->subscriptions, nameseq_list) { - tipc_subscrp_report_overlap(s, publ->lower, publ->upper, - TIPC_PUBLISHED, publ->ref, - publ->node, publ->scope, - created_subseq); + tipc_sub_report_overlap(s, publ->lower, publ->upper, + TIPC_PUBLISHED, publ->ref, + publ->node, publ->scope, + created_subseq); } return publ; } @@ -397,10 +397,9 @@ found: /* Notify any waiting subscriptions */ list_for_each_entry_safe(s, st, &nseq->subscriptions, nameseq_list) { - tipc_subscrp_report_overlap(s, publ->lower, publ->upper, - TIPC_WITHDRAWN, publ->ref, - publ->node, publ->scope, - removed_subseq); + tipc_sub_report_overlap(s, publ->lower, publ->upper, + TIPC_WITHDRAWN, publ->ref, publ->node, + publ->scope, removed_subseq); } return publ; @@ -412,33 +411,37 @@ found: * sequence overlapping with the requested sequence */ static void tipc_nameseq_subscribe(struct name_seq *nseq, - struct tipc_subscription *s, - bool status) + struct tipc_subscription *sub) { struct sub_seq *sseq = nseq->sseqs; struct tipc_name_seq ns; + struct tipc_subscr *s = &sub->evt.s; + bool no_status; - tipc_subscrp_convert_seq(&s->evt.s.seq, s->swap, &ns); + ns.type = tipc_sub_read(s, seq.type); + ns.lower = tipc_sub_read(s, seq.lower); + ns.upper = tipc_sub_read(s, seq.upper); + no_status = tipc_sub_read(s, filter) & TIPC_SUB_NO_STATUS; - tipc_subscrp_get(s); - list_add(&s->nameseq_list, &nseq->subscriptions); + tipc_sub_get(sub); + list_add(&sub->nameseq_list, &nseq->subscriptions); - if (!status || !sseq) + if (no_status || !sseq) return; while (sseq != &nseq->sseqs[nseq->first_free]) { - if (tipc_subscrp_check_overlap(&ns, sseq->lower, sseq->upper)) { + if (tipc_sub_check_overlap(&ns, sseq->lower, sseq->upper)) { struct publication *crs; struct name_info *info = sseq->info; int must_report = 1; list_for_each_entry(crs, &info->zone_list, zone_list) { - tipc_subscrp_report_overlap(s, sseq->lower, - sseq->upper, - TIPC_PUBLISHED, - crs->ref, crs->node, - crs->scope, - must_report); + tipc_sub_report_overlap(sub, sseq->lower, + sseq->upper, + TIPC_PUBLISHED, + crs->ref, crs->node, + crs->scope, + must_report); must_report = 0; } } @@ -808,24 +811,27 @@ int tipc_nametbl_withdraw(struct net *net, u32 type, u32 lower, u32 ref, /** * tipc_nametbl_subscribe - add a subscription object to the name table */ -void tipc_nametbl_subscribe(struct tipc_subscription *s, bool status) +void tipc_nametbl_subscribe(struct tipc_subscription *sub) { - struct tipc_net *tn = net_generic(s->net, tipc_net_id); - u32 type = tipc_subscrp_convert_seq_type(s->evt.s.seq.type, s->swap); + struct tipc_net *tn = tipc_net(sub->net); + struct tipc_subscr *s = &sub->evt.s; + u32 type = tipc_sub_read(s, seq.type); int index = hash(type); struct name_seq *seq; struct tipc_name_seq ns; spin_lock_bh(&tn->nametbl_lock); - seq = nametbl_find_seq(s->net, type); + seq = nametbl_find_seq(sub->net, type); if (!seq) seq = tipc_nameseq_create(type, &tn->nametbl->seq_hlist[index]); if (seq) { spin_lock_bh(&seq->lock); - tipc_nameseq_subscribe(seq, s, status); + tipc_nameseq_subscribe(seq, sub); spin_unlock_bh(&seq->lock); } else { - tipc_subscrp_convert_seq(&s->evt.s.seq, s->swap, &ns); + ns.type = tipc_sub_read(s, seq.type); + ns.lower = tipc_sub_read(s, seq.lower); + ns.upper = tipc_sub_read(s, seq.upper); pr_warn("Failed to create subscription for {%u,%u,%u}\n", ns.type, ns.lower, ns.upper); } @@ -835,18 +841,19 @@ void tipc_nametbl_subscribe(struct tipc_subscription *s, bool status) /** * tipc_nametbl_unsubscribe - remove a subscription object from name table */ -void tipc_nametbl_unsubscribe(struct tipc_subscription *s) +void tipc_nametbl_unsubscribe(struct tipc_subscription *sub) { - struct tipc_net *tn = net_generic(s->net, tipc_net_id); + struct tipc_subscr *s = &sub->evt.s; + struct tipc_net *tn = tipc_net(sub->net); struct name_seq *seq; - u32 type = tipc_subscrp_convert_seq_type(s->evt.s.seq.type, s->swap); + u32 type = tipc_sub_read(s, seq.type); spin_lock_bh(&tn->nametbl_lock); - seq = nametbl_find_seq(s->net, type); + seq = nametbl_find_seq(sub->net, type); if (seq != NULL) { spin_lock_bh(&seq->lock); - list_del_init(&s->nameseq_list); - tipc_subscrp_put(s); + list_del_init(&sub->nameseq_list); + tipc_sub_put(sub); if (!seq->first_free && list_empty(&seq->subscriptions)) { hlist_del_init_rcu(&seq->ns_list); kfree(seq->sseqs); diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h index f56e7cb3d436..17652602d5e2 100644 --- a/net/tipc/name_table.h +++ b/net/tipc/name_table.h @@ -120,7 +120,7 @@ struct publication *tipc_nametbl_insert_publ(struct net *net, u32 type, struct publication *tipc_nametbl_remove_publ(struct net *net, u32 type, u32 lower, u32 node, u32 ref, u32 key); -void tipc_nametbl_subscribe(struct tipc_subscription *s, bool status); +void tipc_nametbl_subscribe(struct tipc_subscription *s); void tipc_nametbl_unsubscribe(struct tipc_subscription *s); int tipc_nametbl_init(struct net *net); void tipc_nametbl_stop(struct net *net); diff --git a/net/tipc/net.c b/net/tipc/net.c index 719c5924b638..1a2fde0d6f61 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -200,7 +200,7 @@ out: return skb->len; } -int tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info) +int __tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info) { struct net *net = sock_net(skb->sk); struct tipc_net *tn = net_generic(net, tipc_net_id); @@ -241,10 +241,19 @@ int tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info) if (!tipc_addr_node_valid(addr)) return -EINVAL; - rtnl_lock(); tipc_net_start(net, addr); - rtnl_unlock(); } return 0; } + +int tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info) +{ + int err; + + rtnl_lock(); + err = __tipc_nl_net_set(skb, info); + rtnl_unlock(); + + return err; +} diff --git a/net/tipc/net.h b/net/tipc/net.h index c7c254902873..c0306aa2374b 100644 --- a/net/tipc/net.h +++ b/net/tipc/net.h @@ -47,5 +47,6 @@ void tipc_net_stop(struct net *net); int tipc_nl_net_dump(struct sk_buff *skb, struct netlink_callback *cb); int tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info); +int __tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info); #endif diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index e48f0b2c01b9..4492cda45566 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -285,10 +285,6 @@ static int __tipc_nl_compat_doit(struct tipc_nl_compat_cmd_doit *cmd, if (!trans_buf) return -ENOMEM; - err = (*cmd->transcode)(cmd, trans_buf, msg); - if (err) - goto trans_out; - attrbuf = kmalloc((tipc_genl_family.maxattr + 1) * sizeof(struct nlattr *), GFP_KERNEL); if (!attrbuf) { @@ -296,27 +292,34 @@ static int __tipc_nl_compat_doit(struct tipc_nl_compat_cmd_doit *cmd, goto trans_out; } - err = nla_parse(attrbuf, tipc_genl_family.maxattr, - (const struct nlattr *)trans_buf->data, - trans_buf->len, NULL, NULL); - if (err) - goto parse_out; - doit_buf = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!doit_buf) { err = -ENOMEM; - goto parse_out; + goto attrbuf_out; } - doit_buf->sk = msg->dst_sk; - memset(&info, 0, sizeof(info)); info.attrs = attrbuf; + rtnl_lock(); + err = (*cmd->transcode)(cmd, trans_buf, msg); + if (err) + goto doit_out; + + err = nla_parse(attrbuf, tipc_genl_family.maxattr, + (const struct nlattr *)trans_buf->data, + trans_buf->len, NULL, NULL); + if (err) + goto doit_out; + + doit_buf->sk = msg->dst_sk; + err = (*cmd->doit)(doit_buf, &info); +doit_out: + rtnl_unlock(); kfree_skb(doit_buf); -parse_out: +attrbuf_out: kfree(attrbuf); trans_out: kfree_skb(trans_buf); @@ -722,13 +725,13 @@ static int tipc_nl_compat_link_set(struct tipc_nl_compat_cmd_doit *cmd, media = tipc_media_find(lc->name); if (media) { - cmd->doit = &tipc_nl_media_set; + cmd->doit = &__tipc_nl_media_set; return tipc_nl_compat_media_set(skb, msg); } bearer = tipc_bearer_find(msg->net, lc->name); if (bearer) { - cmd->doit = &tipc_nl_bearer_set; + cmd->doit = &__tipc_nl_bearer_set; return tipc_nl_compat_bearer_set(skb, msg); } @@ -1089,12 +1092,12 @@ static int tipc_nl_compat_handle(struct tipc_nl_compat_msg *msg) return tipc_nl_compat_dumpit(&dump, msg); case TIPC_CMD_ENABLE_BEARER: msg->req_type = TIPC_TLV_BEARER_CONFIG; - doit.doit = tipc_nl_bearer_enable; + doit.doit = __tipc_nl_bearer_enable; doit.transcode = tipc_nl_compat_bearer_enable; return tipc_nl_compat_doit(&doit, msg); case TIPC_CMD_DISABLE_BEARER: msg->req_type = TIPC_TLV_BEARER_NAME; - doit.doit = tipc_nl_bearer_disable; + doit.doit = __tipc_nl_bearer_disable; doit.transcode = tipc_nl_compat_bearer_disable; return tipc_nl_compat_doit(&doit, msg); case TIPC_CMD_SHOW_LINK_STATS: @@ -1148,12 +1151,12 @@ static int tipc_nl_compat_handle(struct tipc_nl_compat_msg *msg) return tipc_nl_compat_dumpit(&dump, msg); case TIPC_CMD_SET_NODE_ADDR: msg->req_type = TIPC_TLV_NET_ADDR; - doit.doit = tipc_nl_net_set; + doit.doit = __tipc_nl_net_set; doit.transcode = tipc_nl_compat_net_set; return tipc_nl_compat_doit(&doit, msg); case TIPC_CMD_SET_NETID: msg->req_type = TIPC_TLV_UNSIGNED; - doit.doit = tipc_nl_net_set; + doit.doit = __tipc_nl_net_set; doit.transcode = tipc_nl_compat_net_set; return tipc_nl_compat_doit(&doit, msg); case TIPC_CMD_GET_NETID: diff --git a/net/tipc/node.c b/net/tipc/node.c index 9036d8756e73..389193d7cf67 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1618,6 +1618,30 @@ discard: kfree_skb(skb); } +void tipc_node_apply_tolerance(struct net *net, struct tipc_bearer *b) +{ + struct tipc_net *tn = tipc_net(net); + int bearer_id = b->identity; + struct sk_buff_head xmitq; + struct tipc_link_entry *e; + struct tipc_node *n; + + __skb_queue_head_init(&xmitq); + + rcu_read_lock(); + + list_for_each_entry_rcu(n, &tn->node_list, list) { + tipc_node_write_lock(n); + e = &n->links[bearer_id]; + if (e->link) + tipc_link_set_tolerance(e->link, b->tolerance, &xmitq); + tipc_node_write_unlock(n); + tipc_bearer_xmit(net, bearer_id, &xmitq, &e->maddr); + } + + rcu_read_unlock(); +} + int tipc_nl_peer_rm(struct sk_buff *skb, struct genl_info *info) { struct net *net = sock_net(skb->sk); diff --git a/net/tipc/node.h b/net/tipc/node.h index acd58d23a70e..4ce5e3a185c0 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -65,6 +65,7 @@ void tipc_node_check_dest(struct net *net, u32 onode, struct tipc_media_addr *maddr, bool *respond, bool *dupl_addr); void tipc_node_delete_links(struct net *net, int bearer_id); +void tipc_node_apply_tolerance(struct net *net, struct tipc_bearer *b); int tipc_node_get_linkname(struct net *net, u32 bearer_id, u32 node, char *linkname, size_t len); int tipc_node_xmit(struct net *net, struct sk_buff_head *list, u32 dnode, diff --git a/net/tipc/server.c b/net/tipc/server.c deleted file mode 100644 index df0c563c90cd..000000000000 --- a/net/tipc/server.c +++ /dev/null @@ -1,710 +0,0 @@ -/* - * net/tipc/server.c: TIPC server infrastructure - * - * Copyright (c) 2012-2013, Wind River Systems - * All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are met: - * - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. Neither the names of the copyright holders nor the names of its - * contributors may be used to endorse or promote products derived from - * this software without specific prior written permission. - * - * Alternatively, this software may be distributed under the terms of the - * GNU General Public License ("GPL") version 2 as published by the Free - * Software Foundation. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" - * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE - * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE - * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE - * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS - * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN - * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) - * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE - * POSSIBILITY OF SUCH DAMAGE. - */ - -#include "server.h" -#include "core.h" -#include "socket.h" -#include "addr.h" -#include "msg.h" -#include <net/sock.h> -#include <linux/module.h> - -/* Number of messages to send before rescheduling */ -#define MAX_SEND_MSG_COUNT 25 -#define MAX_RECV_MSG_COUNT 25 -#define CF_CONNECTED 1 -#define CF_SERVER 2 - -#define sock2con(x) ((struct tipc_conn *)(x)->sk_user_data) - -/** - * struct tipc_conn - TIPC connection structure - * @kref: reference counter to connection object - * @conid: connection identifier - * @sock: socket handler associated with connection - * @flags: indicates connection state - * @server: pointer to connected server - * @rwork: receive work item - * @usr_data: user-specified field - * @rx_action: what to do when connection socket is active - * @outqueue: pointer to first outbound message in queue - * @outqueue_lock: control access to the outqueue - * @outqueue: list of connection objects for its server - * @swork: send work item - */ -struct tipc_conn { - struct kref kref; - int conid; - struct socket *sock; - unsigned long flags; - struct tipc_server *server; - struct work_struct rwork; - int (*rx_action) (struct tipc_conn *con); - void *usr_data; - struct list_head outqueue; - spinlock_t outqueue_lock; - struct work_struct swork; -}; - -/* An entry waiting to be sent */ -struct outqueue_entry { - struct list_head list; - struct kvec iov; - struct sockaddr_tipc dest; -}; - -static void tipc_recv_work(struct work_struct *work); -static void tipc_send_work(struct work_struct *work); -static void tipc_clean_outqueues(struct tipc_conn *con); - -static void tipc_conn_kref_release(struct kref *kref) -{ - struct tipc_conn *con = container_of(kref, struct tipc_conn, kref); - struct tipc_server *s = con->server; - struct sockaddr_tipc *saddr = s->saddr; - struct socket *sock = con->sock; - struct sock *sk; - - if (sock) { - sk = sock->sk; - if (test_bit(CF_SERVER, &con->flags)) { - __module_get(sock->ops->owner); - __module_get(sk->sk_prot_creator->owner); - } - saddr->scope = -TIPC_NODE_SCOPE; - kernel_bind(sock, (struct sockaddr *)saddr, sizeof(*saddr)); - sock_release(sock); - con->sock = NULL; - } - spin_lock_bh(&s->idr_lock); - idr_remove(&s->conn_idr, con->conid); - s->idr_in_use--; - spin_unlock_bh(&s->idr_lock); - tipc_clean_outqueues(con); - kfree(con); -} - -static void conn_put(struct tipc_conn *con) -{ - kref_put(&con->kref, tipc_conn_kref_release); -} - -static void conn_get(struct tipc_conn *con) -{ - kref_get(&con->kref); -} - -static struct tipc_conn *tipc_conn_lookup(struct tipc_server *s, int conid) -{ - struct tipc_conn *con; - - spin_lock_bh(&s->idr_lock); - con = idr_find(&s->conn_idr, conid); - if (con) { - if (!test_bit(CF_CONNECTED, &con->flags) || - !kref_get_unless_zero(&con->kref)) - con = NULL; - } - spin_unlock_bh(&s->idr_lock); - return con; -} - -static void sock_data_ready(struct sock *sk) -{ - struct tipc_conn *con; - - read_lock_bh(&sk->sk_callback_lock); - con = sock2con(sk); - if (con && test_bit(CF_CONNECTED, &con->flags)) { - conn_get(con); - if (!queue_work(con->server->rcv_wq, &con->rwork)) - conn_put(con); - } - read_unlock_bh(&sk->sk_callback_lock); -} - -static void sock_write_space(struct sock *sk) -{ - struct tipc_conn *con; - - read_lock_bh(&sk->sk_callback_lock); - con = sock2con(sk); - if (con && test_bit(CF_CONNECTED, &con->flags)) { - conn_get(con); - if (!queue_work(con->server->send_wq, &con->swork)) - conn_put(con); - } - read_unlock_bh(&sk->sk_callback_lock); -} - -static void tipc_register_callbacks(struct socket *sock, struct tipc_conn *con) -{ - struct sock *sk = sock->sk; - - write_lock_bh(&sk->sk_callback_lock); - - sk->sk_data_ready = sock_data_ready; - sk->sk_write_space = sock_write_space; - sk->sk_user_data = con; - - con->sock = sock; - - write_unlock_bh(&sk->sk_callback_lock); -} - -static void tipc_close_conn(struct tipc_conn *con) -{ - struct tipc_server *s = con->server; - struct sock *sk = con->sock->sk; - bool disconnect = false; - - write_lock_bh(&sk->sk_callback_lock); - disconnect = test_and_clear_bit(CF_CONNECTED, &con->flags); - if (disconnect) { - sk->sk_user_data = NULL; - if (con->conid) - s->tipc_conn_release(con->conid, con->usr_data); - } - write_unlock_bh(&sk->sk_callback_lock); - - /* Handle concurrent calls from sending and receiving threads */ - if (!disconnect) - return; - - /* Don't flush pending works, -just let them expire */ - kernel_sock_shutdown(con->sock, SHUT_RDWR); - conn_put(con); -} - -static struct tipc_conn *tipc_alloc_conn(struct tipc_server *s) -{ - struct tipc_conn *con; - int ret; - - con = kzalloc(sizeof(struct tipc_conn), GFP_ATOMIC); - if (!con) - return ERR_PTR(-ENOMEM); - - kref_init(&con->kref); - INIT_LIST_HEAD(&con->outqueue); - spin_lock_init(&con->outqueue_lock); - INIT_WORK(&con->swork, tipc_send_work); - INIT_WORK(&con->rwork, tipc_recv_work); - - spin_lock_bh(&s->idr_lock); - ret = idr_alloc(&s->conn_idr, con, 0, 0, GFP_ATOMIC); - if (ret < 0) { - kfree(con); - spin_unlock_bh(&s->idr_lock); - return ERR_PTR(-ENOMEM); - } - con->conid = ret; - s->idr_in_use++; - spin_unlock_bh(&s->idr_lock); - - set_bit(CF_CONNECTED, &con->flags); - con->server = s; - - return con; -} - -static int tipc_receive_from_sock(struct tipc_conn *con) -{ - struct tipc_server *s = con->server; - struct sock *sk = con->sock->sk; - struct sockaddr_tipc addr; - struct msghdr msg = {}; - struct kvec iov; - void *buf; - int ret; - - buf = kmem_cache_alloc(s->rcvbuf_cache, GFP_ATOMIC); - if (!buf) { - ret = -ENOMEM; - goto out_close; - } - - iov.iov_base = buf; - iov.iov_len = s->max_rcvbuf_size; - msg.msg_name = &addr; - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, iov.iov_len); - ret = sock_recvmsg(con->sock, &msg, MSG_DONTWAIT); - if (ret <= 0) { - kmem_cache_free(s->rcvbuf_cache, buf); - goto out_close; - } - - read_lock_bh(&sk->sk_callback_lock); - if (test_bit(CF_CONNECTED, &con->flags)) - ret = s->tipc_conn_recvmsg(sock_net(con->sock->sk), con->conid, - &addr, con->usr_data, buf, ret); - read_unlock_bh(&sk->sk_callback_lock); - kmem_cache_free(s->rcvbuf_cache, buf); - if (ret < 0) - tipc_conn_terminate(s, con->conid); - return ret; - -out_close: - if (ret != -EWOULDBLOCK) - tipc_close_conn(con); - else if (ret == 0) - /* Don't return success if we really got EOF */ - ret = -EAGAIN; - - return ret; -} - -static int tipc_accept_from_sock(struct tipc_conn *con) -{ - struct tipc_server *s = con->server; - struct socket *sock = con->sock; - struct socket *newsock; - struct tipc_conn *newcon; - int ret; - - ret = kernel_accept(sock, &newsock, O_NONBLOCK); - if (ret < 0) - return ret; - - newcon = tipc_alloc_conn(con->server); - if (IS_ERR(newcon)) { - ret = PTR_ERR(newcon); - sock_release(newsock); - return ret; - } - - newcon->rx_action = tipc_receive_from_sock; - tipc_register_callbacks(newsock, newcon); - - /* Notify that new connection is incoming */ - newcon->usr_data = s->tipc_conn_new(newcon->conid); - if (!newcon->usr_data) { - sock_release(newsock); - conn_put(newcon); - return -ENOMEM; - } - - /* Wake up receive process in case of 'SYN+' message */ - newsock->sk->sk_data_ready(newsock->sk); - return ret; -} - -static struct socket *tipc_create_listen_sock(struct tipc_conn *con) -{ - struct tipc_server *s = con->server; - struct socket *sock = NULL; - int ret; - - ret = sock_create_kern(s->net, AF_TIPC, SOCK_SEQPACKET, 0, &sock); - if (ret < 0) - return NULL; - ret = kernel_setsockopt(sock, SOL_TIPC, TIPC_IMPORTANCE, - (char *)&s->imp, sizeof(s->imp)); - if (ret < 0) - goto create_err; - ret = kernel_bind(sock, (struct sockaddr *)s->saddr, sizeof(*s->saddr)); - if (ret < 0) - goto create_err; - - switch (s->type) { - case SOCK_STREAM: - case SOCK_SEQPACKET: - con->rx_action = tipc_accept_from_sock; - - ret = kernel_listen(sock, 0); - if (ret < 0) - goto create_err; - break; - case SOCK_DGRAM: - case SOCK_RDM: - con->rx_action = tipc_receive_from_sock; - break; - default: - pr_err("Unknown socket type %d\n", s->type); - goto create_err; - } - - /* As server's listening socket owner and creator is the same module, - * we have to decrease TIPC module reference count to guarantee that - * it remains zero after the server socket is created, otherwise, - * executing "rmmod" command is unable to make TIPC module deleted - * after TIPC module is inserted successfully. - * - * However, the reference count is ever increased twice in - * sock_create_kern(): one is to increase the reference count of owner - * of TIPC socket's proto_ops struct; another is to increment the - * reference count of owner of TIPC proto struct. Therefore, we must - * decrement the module reference count twice to ensure that it keeps - * zero after server's listening socket is created. Of course, we - * must bump the module reference count twice as well before the socket - * is closed. - */ - module_put(sock->ops->owner); - module_put(sock->sk->sk_prot_creator->owner); - set_bit(CF_SERVER, &con->flags); - - return sock; - -create_err: - kernel_sock_shutdown(sock, SHUT_RDWR); - sock_release(sock); - return NULL; -} - -static int tipc_open_listening_sock(struct tipc_server *s) -{ - struct socket *sock; - struct tipc_conn *con; - - con = tipc_alloc_conn(s); - if (IS_ERR(con)) - return PTR_ERR(con); - - sock = tipc_create_listen_sock(con); - if (!sock) { - idr_remove(&s->conn_idr, con->conid); - s->idr_in_use--; - kfree(con); - return -EINVAL; - } - - tipc_register_callbacks(sock, con); - return 0; -} - -static struct outqueue_entry *tipc_alloc_entry(void *data, int len) -{ - struct outqueue_entry *entry; - void *buf; - - entry = kmalloc(sizeof(struct outqueue_entry), GFP_ATOMIC); - if (!entry) - return NULL; - - buf = kmemdup(data, len, GFP_ATOMIC); - if (!buf) { - kfree(entry); - return NULL; - } - - entry->iov.iov_base = buf; - entry->iov.iov_len = len; - - return entry; -} - -static void tipc_free_entry(struct outqueue_entry *e) -{ - kfree(e->iov.iov_base); - kfree(e); -} - -static void tipc_clean_outqueues(struct tipc_conn *con) -{ - struct outqueue_entry *e, *safe; - - spin_lock_bh(&con->outqueue_lock); - list_for_each_entry_safe(e, safe, &con->outqueue, list) { - list_del(&e->list); - tipc_free_entry(e); - } - spin_unlock_bh(&con->outqueue_lock); -} - -int tipc_conn_sendmsg(struct tipc_server *s, int conid, - struct sockaddr_tipc *addr, void *data, size_t len) -{ - struct outqueue_entry *e; - struct tipc_conn *con; - - con = tipc_conn_lookup(s, conid); - if (!con) - return -EINVAL; - - if (!test_bit(CF_CONNECTED, &con->flags)) { - conn_put(con); - return 0; - } - - e = tipc_alloc_entry(data, len); - if (!e) { - conn_put(con); - return -ENOMEM; - } - - if (addr) - memcpy(&e->dest, addr, sizeof(struct sockaddr_tipc)); - - spin_lock_bh(&con->outqueue_lock); - list_add_tail(&e->list, &con->outqueue); - spin_unlock_bh(&con->outqueue_lock); - - if (!queue_work(s->send_wq, &con->swork)) - conn_put(con); - return 0; -} - -void tipc_conn_terminate(struct tipc_server *s, int conid) -{ - struct tipc_conn *con; - - con = tipc_conn_lookup(s, conid); - if (con) { - tipc_close_conn(con); - conn_put(con); - } -} - -bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type, u32 lower, - u32 upper, u32 filter, int *conid) -{ - struct tipc_subscriber *scbr; - struct tipc_subscr sub; - struct tipc_server *s; - struct tipc_conn *con; - - sub.seq.type = type; - sub.seq.lower = lower; - sub.seq.upper = upper; - sub.timeout = TIPC_WAIT_FOREVER; - sub.filter = filter; - *(u32 *)&sub.usr_handle = port; - - con = tipc_alloc_conn(tipc_topsrv(net)); - if (IS_ERR(con)) - return false; - - *conid = con->conid; - s = con->server; - scbr = s->tipc_conn_new(*conid); - if (!scbr) { - conn_put(con); - return false; - } - - con->usr_data = scbr; - con->sock = NULL; - s->tipc_conn_recvmsg(net, *conid, NULL, scbr, &sub, sizeof(sub)); - return true; -} - -void tipc_topsrv_kern_unsubscr(struct net *net, int conid) -{ - struct tipc_conn *con; - struct tipc_server *srv; - - con = tipc_conn_lookup(tipc_topsrv(net), conid); - if (!con) - return; - - test_and_clear_bit(CF_CONNECTED, &con->flags); - srv = con->server; - if (con->conid) - srv->tipc_conn_release(con->conid, con->usr_data); - conn_put(con); - conn_put(con); -} - -static void tipc_send_kern_top_evt(struct net *net, struct tipc_event *evt) -{ - u32 port = *(u32 *)&evt->s.usr_handle; - u32 self = tipc_own_addr(net); - struct sk_buff_head evtq; - struct sk_buff *skb; - - skb = tipc_msg_create(TOP_SRV, 0, INT_H_SIZE, sizeof(*evt), - self, self, port, port, 0); - if (!skb) - return; - msg_set_dest_droppable(buf_msg(skb), true); - memcpy(msg_data(buf_msg(skb)), evt, sizeof(*evt)); - skb_queue_head_init(&evtq); - __skb_queue_tail(&evtq, skb); - tipc_sk_rcv(net, &evtq); -} - -static void tipc_send_to_sock(struct tipc_conn *con) -{ - struct tipc_server *s = con->server; - struct outqueue_entry *e; - struct tipc_event *evt; - struct msghdr msg; - int count = 0; - int ret; - - spin_lock_bh(&con->outqueue_lock); - while (test_bit(CF_CONNECTED, &con->flags)) { - e = list_entry(con->outqueue.next, struct outqueue_entry, list); - if ((struct list_head *) e == &con->outqueue) - break; - - spin_unlock_bh(&con->outqueue_lock); - - if (con->sock) { - memset(&msg, 0, sizeof(msg)); - msg.msg_flags = MSG_DONTWAIT; - if (s->type == SOCK_DGRAM || s->type == SOCK_RDM) { - msg.msg_name = &e->dest; - msg.msg_namelen = sizeof(struct sockaddr_tipc); - } - ret = kernel_sendmsg(con->sock, &msg, &e->iov, 1, - e->iov.iov_len); - if (ret == -EWOULDBLOCK || ret == 0) { - cond_resched(); - goto out; - } else if (ret < 0) { - goto send_err; - } - } else { - evt = e->iov.iov_base; - tipc_send_kern_top_evt(s->net, evt); - } - /* Don't starve users filling buffers */ - if (++count >= MAX_SEND_MSG_COUNT) { - cond_resched(); - count = 0; - } - - spin_lock_bh(&con->outqueue_lock); - list_del(&e->list); - tipc_free_entry(e); - } - spin_unlock_bh(&con->outqueue_lock); -out: - return; - -send_err: - tipc_close_conn(con); -} - -static void tipc_recv_work(struct work_struct *work) -{ - struct tipc_conn *con = container_of(work, struct tipc_conn, rwork); - int count = 0; - - while (test_bit(CF_CONNECTED, &con->flags)) { - if (con->rx_action(con)) - break; - - /* Don't flood Rx machine */ - if (++count >= MAX_RECV_MSG_COUNT) { - cond_resched(); - count = 0; - } - } - conn_put(con); -} - -static void tipc_send_work(struct work_struct *work) -{ - struct tipc_conn *con = container_of(work, struct tipc_conn, swork); - - if (test_bit(CF_CONNECTED, &con->flags)) - tipc_send_to_sock(con); - - conn_put(con); -} - -static void tipc_work_stop(struct tipc_server *s) -{ - destroy_workqueue(s->rcv_wq); - destroy_workqueue(s->send_wq); -} - -static int tipc_work_start(struct tipc_server *s) -{ - s->rcv_wq = alloc_ordered_workqueue("tipc_rcv", 0); - if (!s->rcv_wq) { - pr_err("can't start tipc receive workqueue\n"); - return -ENOMEM; - } - - s->send_wq = alloc_ordered_workqueue("tipc_send", 0); - if (!s->send_wq) { - pr_err("can't start tipc send workqueue\n"); - destroy_workqueue(s->rcv_wq); - return -ENOMEM; - } - - return 0; -} - -int tipc_server_start(struct tipc_server *s) -{ - int ret; - - spin_lock_init(&s->idr_lock); - idr_init(&s->conn_idr); - s->idr_in_use = 0; - - s->rcvbuf_cache = kmem_cache_create(s->name, s->max_rcvbuf_size, - 0, SLAB_HWCACHE_ALIGN, NULL); - if (!s->rcvbuf_cache) - return -ENOMEM; - - ret = tipc_work_start(s); - if (ret < 0) { - kmem_cache_destroy(s->rcvbuf_cache); - return ret; - } - ret = tipc_open_listening_sock(s); - if (ret < 0) { - tipc_work_stop(s); - kmem_cache_destroy(s->rcvbuf_cache); - return ret; - } - return ret; -} - -void tipc_server_stop(struct tipc_server *s) -{ - struct tipc_conn *con; - int id; - - spin_lock_bh(&s->idr_lock); - for (id = 0; s->idr_in_use; id++) { - con = idr_find(&s->conn_idr, id); - if (con) { - spin_unlock_bh(&s->idr_lock); - tipc_close_conn(con); - spin_lock_bh(&s->idr_lock); - } - } - spin_unlock_bh(&s->idr_lock); - - tipc_work_stop(s); - kmem_cache_destroy(s->rcvbuf_cache); - idr_destroy(&s->conn_idr); -} diff --git a/net/tipc/socket.c b/net/tipc/socket.c index b0323ec7971e..f93477187a90 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -665,7 +665,7 @@ exit: * a completely predictable manner). */ static int tipc_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr; struct sock *sk = sock->sk; @@ -684,13 +684,12 @@ static int tipc_getname(struct socket *sock, struct sockaddr *uaddr, addr->addr.id.node = tn->own_addr; } - *uaddr_len = sizeof(*addr); addr->addrtype = TIPC_ADDR_ID; addr->family = AF_TIPC; addr->scope = 0; addr->addr.name.domain = 0; - return 0; + return sizeof(*addr); } /** diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index 68e26470c516..6925a989569b 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -1,7 +1,7 @@ /* * net/tipc/subscr.c: TIPC network topology service * - * Copyright (c) 2000-2006, Ericsson AB + * Copyright (c) 2000-2017, Ericsson AB * Copyright (c) 2005-2007, 2010-2013, Wind River Systems * All rights reserved. * @@ -38,61 +38,30 @@ #include "name_table.h" #include "subscr.h" -/** - * struct tipc_subscriber - TIPC network topology subscriber - * @kref: reference counter to tipc_subscription object - * @conid: connection identifier to server connecting to subscriber - * @lock: control access to subscriber - * @subscrp_list: list of subscription objects for this subscriber - */ -struct tipc_subscriber { - struct kref kref; - int conid; - spinlock_t lock; - struct list_head subscrp_list; -}; - -static void tipc_subscrb_put(struct tipc_subscriber *subscriber); - -/** - * htohl - convert value to endianness used by destination - * @in: value to convert - * @swap: non-zero if endianness must be reversed - * - * Returns converted value - */ -static u32 htohl(u32 in, int swap) -{ - return swap ? swab32(in) : in; -} - -static void tipc_subscrp_send_event(struct tipc_subscription *sub, - u32 found_lower, u32 found_upper, - u32 event, u32 port_ref, u32 node) +static void tipc_sub_send_event(struct tipc_subscription *sub, + u32 found_lower, u32 found_upper, + u32 event, u32 port, u32 node) { - struct tipc_net *tn = net_generic(sub->net, tipc_net_id); - struct tipc_subscriber *subscriber = sub->subscriber; - struct kvec msg_sect; + struct tipc_event *evt = &sub->evt; - msg_sect.iov_base = (void *)&sub->evt; - msg_sect.iov_len = sizeof(struct tipc_event); - sub->evt.event = htohl(event, sub->swap); - sub->evt.found_lower = htohl(found_lower, sub->swap); - sub->evt.found_upper = htohl(found_upper, sub->swap); - sub->evt.port.ref = htohl(port_ref, sub->swap); - sub->evt.port.node = htohl(node, sub->swap); - tipc_conn_sendmsg(tn->topsrv, subscriber->conid, NULL, - msg_sect.iov_base, msg_sect.iov_len); + if (sub->inactive) + return; + tipc_evt_write(evt, event, event); + tipc_evt_write(evt, found_lower, found_lower); + tipc_evt_write(evt, found_upper, found_upper); + tipc_evt_write(evt, port.ref, port); + tipc_evt_write(evt, port.node, node); + tipc_topsrv_queue_evt(sub->net, sub->conid, event, evt); } /** - * tipc_subscrp_check_overlap - test for subscription overlap with the + * tipc_sub_check_overlap - test for subscription overlap with the * given values * * Returns 1 if there is overlap, otherwise 0. */ -int tipc_subscrp_check_overlap(struct tipc_name_seq *seq, u32 found_lower, - u32 found_upper) +int tipc_sub_check_overlap(struct tipc_name_seq *seq, u32 found_lower, + u32 found_upper) { if (found_lower < seq->lower) found_lower = seq->lower; @@ -103,298 +72,98 @@ int tipc_subscrp_check_overlap(struct tipc_name_seq *seq, u32 found_lower, return 1; } -u32 tipc_subscrp_convert_seq_type(u32 type, int swap) -{ - return htohl(type, swap); -} - -void tipc_subscrp_convert_seq(struct tipc_name_seq *in, int swap, - struct tipc_name_seq *out) -{ - out->type = htohl(in->type, swap); - out->lower = htohl(in->lower, swap); - out->upper = htohl(in->upper, swap); -} - -void tipc_subscrp_report_overlap(struct tipc_subscription *sub, u32 found_lower, - u32 found_upper, u32 event, u32 port_ref, - u32 node, u32 scope, int must) +void tipc_sub_report_overlap(struct tipc_subscription *sub, + u32 found_lower, u32 found_upper, + u32 event, u32 port, u32 node, + u32 scope, int must) { - u32 filter = htohl(sub->evt.s.filter, sub->swap); + struct tipc_subscr *s = &sub->evt.s; + u32 filter = tipc_sub_read(s, filter); struct tipc_name_seq seq; - tipc_subscrp_convert_seq(&sub->evt.s.seq, sub->swap, &seq); - if (!tipc_subscrp_check_overlap(&seq, found_lower, found_upper)) + seq.type = tipc_sub_read(s, seq.type); + seq.lower = tipc_sub_read(s, seq.lower); + seq.upper = tipc_sub_read(s, seq.upper); + + if (!tipc_sub_check_overlap(&seq, found_lower, found_upper)) return; + if (!must && !(filter & TIPC_SUB_PORTS)) return; if (filter & TIPC_SUB_CLUSTER_SCOPE && scope == TIPC_NODE_SCOPE) return; if (filter & TIPC_SUB_NODE_SCOPE && scope != TIPC_NODE_SCOPE) return; - - tipc_subscrp_send_event(sub, found_lower, found_upper, event, port_ref, - node); + spin_lock(&sub->lock); + tipc_sub_send_event(sub, found_lower, found_upper, + event, port, node); + spin_unlock(&sub->lock); } -static void tipc_subscrp_timeout(struct timer_list *t) +static void tipc_sub_timeout(struct timer_list *t) { struct tipc_subscription *sub = from_timer(sub, t, timer); - struct tipc_subscriber *subscriber = sub->subscriber; - - spin_lock_bh(&subscriber->lock); - tipc_nametbl_unsubscribe(sub); - list_del(&sub->subscrp_list); - spin_unlock_bh(&subscriber->lock); - - /* Notify subscriber of timeout */ - tipc_subscrp_send_event(sub, sub->evt.s.seq.lower, sub->evt.s.seq.upper, - TIPC_SUBSCR_TIMEOUT, 0, 0); - - tipc_subscrp_put(sub); -} - -static void tipc_subscrb_kref_release(struct kref *kref) -{ - kfree(container_of(kref,struct tipc_subscriber, kref)); -} - -static void tipc_subscrb_put(struct tipc_subscriber *subscriber) -{ - kref_put(&subscriber->kref, tipc_subscrb_kref_release); -} + struct tipc_subscr *s = &sub->evt.s; -static void tipc_subscrb_get(struct tipc_subscriber *subscriber) -{ - kref_get(&subscriber->kref); + spin_lock(&sub->lock); + tipc_sub_send_event(sub, s->seq.lower, s->seq.upper, + TIPC_SUBSCR_TIMEOUT, 0, 0); + sub->inactive = true; + spin_unlock(&sub->lock); } -static void tipc_subscrp_kref_release(struct kref *kref) +static void tipc_sub_kref_release(struct kref *kref) { - struct tipc_subscription *sub = container_of(kref, - struct tipc_subscription, - kref); - struct tipc_net *tn = net_generic(sub->net, tipc_net_id); - struct tipc_subscriber *subscriber = sub->subscriber; - - atomic_dec(&tn->subscription_count); - kfree(sub); - tipc_subscrb_put(subscriber); + kfree(container_of(kref, struct tipc_subscription, kref)); } -void tipc_subscrp_put(struct tipc_subscription *subscription) +void tipc_sub_put(struct tipc_subscription *subscription) { - kref_put(&subscription->kref, tipc_subscrp_kref_release); + kref_put(&subscription->kref, tipc_sub_kref_release); } -void tipc_subscrp_get(struct tipc_subscription *subscription) +void tipc_sub_get(struct tipc_subscription *subscription) { kref_get(&subscription->kref); } -/* tipc_subscrb_subscrp_delete - delete a specific subscription or all - * subscriptions for a given subscriber. - */ -static void tipc_subscrb_subscrp_delete(struct tipc_subscriber *subscriber, - struct tipc_subscr *s) -{ - struct list_head *subscription_list = &subscriber->subscrp_list; - struct tipc_subscription *sub, *temp; - u32 timeout; - - spin_lock_bh(&subscriber->lock); - list_for_each_entry_safe(sub, temp, subscription_list, subscrp_list) { - if (s && memcmp(s, &sub->evt.s, sizeof(struct tipc_subscr))) - continue; - - timeout = htohl(sub->evt.s.timeout, sub->swap); - if (timeout == TIPC_WAIT_FOREVER || del_timer(&sub->timer)) { - tipc_nametbl_unsubscribe(sub); - list_del(&sub->subscrp_list); - tipc_subscrp_put(sub); - } - - if (s) - break; - } - spin_unlock_bh(&subscriber->lock); -} - -static struct tipc_subscriber *tipc_subscrb_create(int conid) -{ - struct tipc_subscriber *subscriber; - - subscriber = kzalloc(sizeof(*subscriber), GFP_ATOMIC); - if (!subscriber) { - pr_warn("Subscriber rejected, no memory\n"); - return NULL; - } - INIT_LIST_HEAD(&subscriber->subscrp_list); - kref_init(&subscriber->kref); - subscriber->conid = conid; - spin_lock_init(&subscriber->lock); - - return subscriber; -} - -static void tipc_subscrb_delete(struct tipc_subscriber *subscriber) -{ - tipc_subscrb_subscrp_delete(subscriber, NULL); - tipc_subscrb_put(subscriber); -} - -static void tipc_subscrp_cancel(struct tipc_subscr *s, - struct tipc_subscriber *subscriber) -{ - tipc_subscrb_get(subscriber); - tipc_subscrb_subscrp_delete(subscriber, s); - tipc_subscrb_put(subscriber); -} - -static struct tipc_subscription *tipc_subscrp_create(struct net *net, - struct tipc_subscr *s, - int swap) +struct tipc_subscription *tipc_sub_subscribe(struct net *net, + struct tipc_subscr *s, + int conid) { - struct tipc_net *tn = net_generic(net, tipc_net_id); + u32 filter = tipc_sub_read(s, filter); struct tipc_subscription *sub; - u32 filter = htohl(s->filter, swap); + u32 timeout; - /* Refuse subscription if global limit exceeded */ - if (atomic_read(&tn->subscription_count) >= TIPC_MAX_SUBSCRIPTIONS) { - pr_warn("Subscription rejected, limit reached (%u)\n", - TIPC_MAX_SUBSCRIPTIONS); + if ((filter & TIPC_SUB_PORTS && filter & TIPC_SUB_SERVICE) || + (tipc_sub_read(s, seq.lower) > tipc_sub_read(s, seq.upper))) { + pr_warn("Subscription rejected, illegal request\n"); return NULL; } - - /* Allocate subscription object */ sub = kmalloc(sizeof(*sub), GFP_ATOMIC); if (!sub) { pr_warn("Subscription rejected, no memory\n"); return NULL; } - - /* Initialize subscription object */ sub->net = net; - if (((filter & TIPC_SUB_PORTS) && (filter & TIPC_SUB_SERVICE)) || - (htohl(s->seq.lower, swap) > htohl(s->seq.upper, swap))) { - pr_warn("Subscription rejected, illegal request\n"); - kfree(sub); - return NULL; - } - - sub->swap = swap; + sub->conid = conid; + sub->inactive = false; memcpy(&sub->evt.s, s, sizeof(*s)); - atomic_inc(&tn->subscription_count); + spin_lock_init(&sub->lock); kref_init(&sub->kref); - return sub; -} - -static int tipc_subscrp_subscribe(struct net *net, struct tipc_subscr *s, - struct tipc_subscriber *subscriber, int swap, - bool status) -{ - struct tipc_subscription *sub = NULL; - u32 timeout; - - sub = tipc_subscrp_create(net, s, swap); - if (!sub) - return -1; - - spin_lock_bh(&subscriber->lock); - list_add(&sub->subscrp_list, &subscriber->subscrp_list); - sub->subscriber = subscriber; - tipc_nametbl_subscribe(sub, status); - tipc_subscrb_get(subscriber); - spin_unlock_bh(&subscriber->lock); - - timer_setup(&sub->timer, tipc_subscrp_timeout, 0); - timeout = htohl(sub->evt.s.timeout, swap); - + tipc_nametbl_subscribe(sub); + timer_setup(&sub->timer, tipc_sub_timeout, 0); + timeout = tipc_sub_read(&sub->evt.s, timeout); if (timeout != TIPC_WAIT_FOREVER) mod_timer(&sub->timer, jiffies + msecs_to_jiffies(timeout)); - return 0; -} - -/* Handle one termination request for the subscriber */ -static void tipc_subscrb_release_cb(int conid, void *usr_data) -{ - tipc_subscrb_delete((struct tipc_subscriber *)usr_data); -} - -/* Handle one request to create a new subscription for the subscriber */ -static int tipc_subscrb_rcv_cb(struct net *net, int conid, - struct sockaddr_tipc *addr, void *usr_data, - void *buf, size_t len) -{ - struct tipc_subscriber *subscriber = usr_data; - struct tipc_subscr *s = (struct tipc_subscr *)buf; - bool status; - int swap; - - /* Determine subscriber's endianness */ - swap = !(s->filter & (TIPC_SUB_PORTS | TIPC_SUB_SERVICE | - TIPC_SUB_CANCEL)); - - /* Detect & process a subscription cancellation request */ - if (s->filter & htohl(TIPC_SUB_CANCEL, swap)) { - s->filter &= ~htohl(TIPC_SUB_CANCEL, swap); - tipc_subscrp_cancel(s, subscriber); - return 0; - } - status = !(s->filter & htohl(TIPC_SUB_NO_STATUS, swap)); - return tipc_subscrp_subscribe(net, s, subscriber, swap, status); -} - -/* Handle one request to establish a new subscriber */ -static void *tipc_subscrb_connect_cb(int conid) -{ - return (void *)tipc_subscrb_create(conid); -} - -int tipc_topsrv_start(struct net *net) -{ - struct tipc_net *tn = net_generic(net, tipc_net_id); - const char name[] = "topology_server"; - struct tipc_server *topsrv; - struct sockaddr_tipc *saddr; - - saddr = kzalloc(sizeof(*saddr), GFP_ATOMIC); - if (!saddr) - return -ENOMEM; - saddr->family = AF_TIPC; - saddr->addrtype = TIPC_ADDR_NAMESEQ; - saddr->addr.nameseq.type = TIPC_TOP_SRV; - saddr->addr.nameseq.lower = TIPC_TOP_SRV; - saddr->addr.nameseq.upper = TIPC_TOP_SRV; - saddr->scope = TIPC_NODE_SCOPE; - - topsrv = kzalloc(sizeof(*topsrv), GFP_ATOMIC); - if (!topsrv) { - kfree(saddr); - return -ENOMEM; - } - topsrv->net = net; - topsrv->saddr = saddr; - topsrv->imp = TIPC_CRITICAL_IMPORTANCE; - topsrv->type = SOCK_SEQPACKET; - topsrv->max_rcvbuf_size = sizeof(struct tipc_subscr); - topsrv->tipc_conn_recvmsg = tipc_subscrb_rcv_cb; - topsrv->tipc_conn_new = tipc_subscrb_connect_cb; - topsrv->tipc_conn_release = tipc_subscrb_release_cb; - - strncpy(topsrv->name, name, strlen(name) + 1); - tn->topsrv = topsrv; - atomic_set(&tn->subscription_count, 0); - - return tipc_server_start(topsrv); + return sub; } -void tipc_topsrv_stop(struct net *net) +void tipc_sub_unsubscribe(struct tipc_subscription *sub) { - struct tipc_net *tn = net_generic(net, tipc_net_id); - struct tipc_server *topsrv = tn->topsrv; - - tipc_server_stop(topsrv); - kfree(topsrv->saddr); - kfree(topsrv); + tipc_nametbl_unsubscribe(sub); + if (sub->evt.s.timeout != TIPC_WAIT_FOREVER) + del_timer_sync(&sub->timer); + list_del(&sub->sub_list); + tipc_sub_put(sub); } diff --git a/net/tipc/subscr.h b/net/tipc/subscr.h index f3edca775d9f..8b2d22b18f22 100644 --- a/net/tipc/subscr.h +++ b/net/tipc/subscr.h @@ -1,7 +1,7 @@ /* * net/tipc/subscr.h: Include file for TIPC network topology service * - * Copyright (c) 2003-2006, Ericsson AB + * Copyright (c) 2003-2017, Ericsson AB * Copyright (c) 2005-2007, 2012-2013, Wind River Systems * All rights reserved. * @@ -37,48 +37,72 @@ #ifndef _TIPC_SUBSCR_H #define _TIPC_SUBSCR_H -#include "server.h" +#include "topsrv.h" -#define TIPC_MAX_SUBSCRIPTIONS 65535 -#define TIPC_MAX_PUBLICATIONS 65535 +#define TIPC_MAX_SUBSCR 65535 +#define TIPC_MAX_PUBLICATIONS 65535 struct tipc_subscription; -struct tipc_subscriber; +struct tipc_conn; /** * struct tipc_subscription - TIPC network topology subscription object * @subscriber: pointer to its subscriber * @seq: name sequence associated with subscription - * @net: point to network namespace * @timer: timer governing subscription duration (optional) * @nameseq_list: adjacent subscriptions in name sequence's subscription list - * @subscrp_list: adjacent subscriptions in subscriber's subscription list - * @swap: indicates if subscriber uses opposite endianness in its messages + * @sub_list: adjacent subscriptions in subscriber's subscription list * @evt: template for events generated by subscription */ struct tipc_subscription { struct kref kref; - struct tipc_subscriber *subscriber; struct net *net; struct timer_list timer; struct list_head nameseq_list; - struct list_head subscrp_list; - int swap; + struct list_head sub_list; struct tipc_event evt; + int conid; + bool inactive; + spinlock_t lock; /* serialize up/down and timer events */ }; -int tipc_subscrp_check_overlap(struct tipc_name_seq *seq, u32 found_lower, - u32 found_upper); -void tipc_subscrp_report_overlap(struct tipc_subscription *sub, - u32 found_lower, u32 found_upper, u32 event, - u32 port_ref, u32 node, u32 scope, int must); -void tipc_subscrp_convert_seq(struct tipc_name_seq *in, int swap, - struct tipc_name_seq *out); -u32 tipc_subscrp_convert_seq_type(u32 type, int swap); +struct tipc_subscription *tipc_sub_subscribe(struct net *net, + struct tipc_subscr *s, + int conid); +void tipc_sub_unsubscribe(struct tipc_subscription *sub); + +int tipc_sub_check_overlap(struct tipc_name_seq *seq, u32 found_lower, + u32 found_upper); +void tipc_sub_report_overlap(struct tipc_subscription *sub, + u32 found_lower, u32 found_upper, + u32 event, u32 port, u32 node, + u32 scope, int must); int tipc_topsrv_start(struct net *net); void tipc_topsrv_stop(struct net *net); -void tipc_subscrp_put(struct tipc_subscription *subscription); -void tipc_subscrp_get(struct tipc_subscription *subscription); +void tipc_sub_put(struct tipc_subscription *subscription); +void tipc_sub_get(struct tipc_subscription *subscription); + +#define TIPC_FILTER_MASK (TIPC_SUB_PORTS | TIPC_SUB_SERVICE | TIPC_SUB_CANCEL) + +/* tipc_sub_read - return field_ of struct sub_ in host endian format + */ +#define tipc_sub_read(sub_, field_) \ + ({ \ + struct tipc_subscr *sub__ = sub_; \ + u32 val__ = (sub__)->field_; \ + int swap_ = !((sub__)->filter & TIPC_FILTER_MASK); \ + (swap_ ? swab32(val__) : val__); \ + }) + +/* tipc_evt_write - write val_ to field_ of struct evt_ in user endian format + */ +#define tipc_evt_write(evt_, field_, val_) \ + ({ \ + struct tipc_event *evt__ = evt_; \ + u32 val__ = val_; \ + int swap_ = !((evt__)->s.filter & (TIPC_FILTER_MASK)); \ + (evt__)->field_ = swap_ ? swab32(val__) : val__; \ + }) #endif diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c new file mode 100644 index 000000000000..c8e34ef22c30 --- /dev/null +++ b/net/tipc/topsrv.c @@ -0,0 +1,703 @@ +/* + * net/tipc/server.c: TIPC server infrastructure + * + * Copyright (c) 2012-2013, Wind River Systems + * Copyright (c) 2017-2018, Ericsson AB + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include "subscr.h" +#include "topsrv.h" +#include "core.h" +#include "socket.h" +#include "addr.h" +#include "msg.h" +#include <net/sock.h> +#include <linux/module.h> + +/* Number of messages to send before rescheduling */ +#define MAX_SEND_MSG_COUNT 25 +#define MAX_RECV_MSG_COUNT 25 +#define CF_CONNECTED 1 +#define CF_SERVER 2 + +#define TIPC_SERVER_NAME_LEN 32 + +/** + * struct tipc_topsrv - TIPC server structure + * @conn_idr: identifier set of connection + * @idr_lock: protect the connection identifier set + * @idr_in_use: amount of allocated identifier entry + * @net: network namspace instance + * @rcvbuf_cache: memory cache of server receive buffer + * @rcv_wq: receive workqueue + * @send_wq: send workqueue + * @max_rcvbuf_size: maximum permitted receive message length + * @tipc_conn_new: callback will be called when new connection is incoming + * @tipc_conn_release: callback will be called before releasing the connection + * @tipc_conn_recvmsg: callback will be called when message arrives + * @name: server name + * @imp: message importance + * @type: socket type + */ +struct tipc_topsrv { + struct idr conn_idr; + spinlock_t idr_lock; /* for idr list */ + int idr_in_use; + struct net *net; + struct work_struct awork; + struct workqueue_struct *rcv_wq; + struct workqueue_struct *send_wq; + int max_rcvbuf_size; + struct socket *listener; + char name[TIPC_SERVER_NAME_LEN]; +}; + +/** + * struct tipc_conn - TIPC connection structure + * @kref: reference counter to connection object + * @conid: connection identifier + * @sock: socket handler associated with connection + * @flags: indicates connection state + * @server: pointer to connected server + * @sub_list: lsit to all pertaing subscriptions + * @sub_lock: lock protecting the subscription list + * @outqueue_lock: control access to the outqueue + * @rwork: receive work item + * @rx_action: what to do when connection socket is active + * @outqueue: pointer to first outbound message in queue + * @outqueue_lock: control access to the outqueue + * @swork: send work item + */ +struct tipc_conn { + struct kref kref; + int conid; + struct socket *sock; + unsigned long flags; + struct tipc_topsrv *server; + struct list_head sub_list; + spinlock_t sub_lock; /* for subscription list */ + struct work_struct rwork; + struct list_head outqueue; + spinlock_t outqueue_lock; /* for outqueue */ + struct work_struct swork; +}; + +/* An entry waiting to be sent */ +struct outqueue_entry { + bool inactive; + struct tipc_event evt; + struct list_head list; +}; + +static void tipc_conn_recv_work(struct work_struct *work); +static void tipc_conn_send_work(struct work_struct *work); +static void tipc_topsrv_kern_evt(struct net *net, struct tipc_event *evt); +static void tipc_conn_delete_sub(struct tipc_conn *con, struct tipc_subscr *s); + +static bool connected(struct tipc_conn *con) +{ + return con && test_bit(CF_CONNECTED, &con->flags); +} + +static void tipc_conn_kref_release(struct kref *kref) +{ + struct tipc_conn *con = container_of(kref, struct tipc_conn, kref); + struct tipc_topsrv *s = con->server; + struct outqueue_entry *e, *safe; + + spin_lock_bh(&s->idr_lock); + idr_remove(&s->conn_idr, con->conid); + s->idr_in_use--; + spin_unlock_bh(&s->idr_lock); + if (con->sock) + sock_release(con->sock); + + spin_lock_bh(&con->outqueue_lock); + list_for_each_entry_safe(e, safe, &con->outqueue, list) { + list_del(&e->list); + kfree(e); + } + spin_unlock_bh(&con->outqueue_lock); + kfree(con); +} + +static void conn_put(struct tipc_conn *con) +{ + kref_put(&con->kref, tipc_conn_kref_release); +} + +static void conn_get(struct tipc_conn *con) +{ + kref_get(&con->kref); +} + +static void tipc_conn_close(struct tipc_conn *con) +{ + struct sock *sk = con->sock->sk; + bool disconnect = false; + + write_lock_bh(&sk->sk_callback_lock); + disconnect = test_and_clear_bit(CF_CONNECTED, &con->flags); + + if (disconnect) { + sk->sk_user_data = NULL; + tipc_conn_delete_sub(con, NULL); + } + write_unlock_bh(&sk->sk_callback_lock); + + /* Handle concurrent calls from sending and receiving threads */ + if (!disconnect) + return; + + /* Don't flush pending works, -just let them expire */ + kernel_sock_shutdown(con->sock, SHUT_RDWR); + + conn_put(con); +} + +static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s) +{ + struct tipc_conn *con; + int ret; + + con = kzalloc(sizeof(*con), GFP_ATOMIC); + if (!con) + return ERR_PTR(-ENOMEM); + + kref_init(&con->kref); + INIT_LIST_HEAD(&con->outqueue); + INIT_LIST_HEAD(&con->sub_list); + spin_lock_init(&con->outqueue_lock); + spin_lock_init(&con->sub_lock); + INIT_WORK(&con->swork, tipc_conn_send_work); + INIT_WORK(&con->rwork, tipc_conn_recv_work); + + spin_lock_bh(&s->idr_lock); + ret = idr_alloc(&s->conn_idr, con, 0, 0, GFP_ATOMIC); + if (ret < 0) { + kfree(con); + spin_unlock_bh(&s->idr_lock); + return ERR_PTR(-ENOMEM); + } + con->conid = ret; + s->idr_in_use++; + spin_unlock_bh(&s->idr_lock); + + set_bit(CF_CONNECTED, &con->flags); + con->server = s; + + return con; +} + +static struct tipc_conn *tipc_conn_lookup(struct tipc_topsrv *s, int conid) +{ + struct tipc_conn *con; + + spin_lock_bh(&s->idr_lock); + con = idr_find(&s->conn_idr, conid); + if (!connected(con) || !kref_get_unless_zero(&con->kref)) + con = NULL; + spin_unlock_bh(&s->idr_lock); + return con; +} + +/* tipc_conn_delete_sub - delete a specific or all subscriptions + * for a given subscriber + */ +static void tipc_conn_delete_sub(struct tipc_conn *con, struct tipc_subscr *s) +{ + struct tipc_net *tn = tipc_net(con->server->net); + struct list_head *sub_list = &con->sub_list; + struct tipc_subscription *sub, *tmp; + + spin_lock_bh(&con->sub_lock); + list_for_each_entry_safe(sub, tmp, sub_list, sub_list) { + if (!s || !memcmp(s, &sub->evt.s, sizeof(*s))) { + tipc_sub_unsubscribe(sub); + atomic_dec(&tn->subscription_count); + } else if (s) { + break; + } + } + spin_unlock_bh(&con->sub_lock); +} + +static void tipc_conn_send_to_sock(struct tipc_conn *con) +{ + struct list_head *queue = &con->outqueue; + struct tipc_topsrv *srv = con->server; + struct outqueue_entry *e; + struct tipc_event *evt; + struct msghdr msg; + struct kvec iov; + int count = 0; + int ret; + + spin_lock_bh(&con->outqueue_lock); + + while (!list_empty(queue)) { + e = list_first_entry(queue, struct outqueue_entry, list); + evt = &e->evt; + spin_unlock_bh(&con->outqueue_lock); + + if (e->inactive) + tipc_conn_delete_sub(con, &evt->s); + + memset(&msg, 0, sizeof(msg)); + msg.msg_flags = MSG_DONTWAIT; + iov.iov_base = evt; + iov.iov_len = sizeof(*evt); + msg.msg_name = NULL; + + if (con->sock) { + ret = kernel_sendmsg(con->sock, &msg, &iov, + 1, sizeof(*evt)); + if (ret == -EWOULDBLOCK || ret == 0) { + cond_resched(); + return; + } else if (ret < 0) { + return tipc_conn_close(con); + } + } else { + tipc_topsrv_kern_evt(srv->net, evt); + } + + /* Don't starve users filling buffers */ + if (++count >= MAX_SEND_MSG_COUNT) { + cond_resched(); + count = 0; + } + spin_lock_bh(&con->outqueue_lock); + list_del(&e->list); + kfree(e); + } + spin_unlock_bh(&con->outqueue_lock); +} + +static void tipc_conn_send_work(struct work_struct *work) +{ + struct tipc_conn *con = container_of(work, struct tipc_conn, swork); + + if (connected(con)) + tipc_conn_send_to_sock(con); + + conn_put(con); +} + +/* tipc_conn_queue_evt() - interrupt level call from a subscription instance + * The queued work is launched into tipc_send_work()->tipc_send_to_sock() + */ +void tipc_topsrv_queue_evt(struct net *net, int conid, + u32 event, struct tipc_event *evt) +{ + struct tipc_topsrv *srv = tipc_topsrv(net); + struct outqueue_entry *e; + struct tipc_conn *con; + + con = tipc_conn_lookup(srv, conid); + if (!con) + return; + + if (!connected(con)) + goto err; + + e = kmalloc(sizeof(*e), GFP_ATOMIC); + if (!e) + goto err; + e->inactive = (event == TIPC_SUBSCR_TIMEOUT); + memcpy(&e->evt, evt, sizeof(*evt)); + spin_lock_bh(&con->outqueue_lock); + list_add_tail(&e->list, &con->outqueue); + spin_unlock_bh(&con->outqueue_lock); + + if (queue_work(srv->send_wq, &con->swork)) + return; +err: + conn_put(con); +} + +/* tipc_conn_write_space - interrupt callback after a sendmsg EAGAIN + * Indicates that there now is more space in the send buffer + * The queued work is launched into tipc_send_work()->tipc_conn_send_to_sock() + */ +static void tipc_conn_write_space(struct sock *sk) +{ + struct tipc_conn *con; + + read_lock_bh(&sk->sk_callback_lock); + con = sk->sk_user_data; + if (connected(con)) { + conn_get(con); + if (!queue_work(con->server->send_wq, &con->swork)) + conn_put(con); + } + read_unlock_bh(&sk->sk_callback_lock); +} + +static int tipc_conn_rcv_sub(struct tipc_topsrv *srv, + struct tipc_conn *con, + struct tipc_subscr *s) +{ + struct tipc_net *tn = tipc_net(srv->net); + struct tipc_subscription *sub; + + if (tipc_sub_read(s, filter) & TIPC_SUB_CANCEL) { + tipc_conn_delete_sub(con, s); + return 0; + } + if (atomic_read(&tn->subscription_count) >= TIPC_MAX_SUBSCR) { + pr_warn("Subscription rejected, max (%u)\n", TIPC_MAX_SUBSCR); + return -1; + } + sub = tipc_sub_subscribe(srv->net, s, con->conid); + if (!sub) + return -1; + atomic_inc(&tn->subscription_count); + spin_lock_bh(&con->sub_lock); + list_add(&sub->sub_list, &con->sub_list); + spin_unlock_bh(&con->sub_lock); + return 0; +} + +static int tipc_conn_rcv_from_sock(struct tipc_conn *con) +{ + struct tipc_topsrv *srv = con->server; + struct sock *sk = con->sock->sk; + struct msghdr msg = {}; + struct tipc_subscr s; + struct kvec iov; + int ret; + + iov.iov_base = &s; + iov.iov_len = sizeof(s); + msg.msg_name = NULL; + iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, iov.iov_len); + ret = sock_recvmsg(con->sock, &msg, MSG_DONTWAIT); + if (ret == -EWOULDBLOCK) + return -EWOULDBLOCK; + if (ret > 0) { + read_lock_bh(&sk->sk_callback_lock); + ret = tipc_conn_rcv_sub(srv, con, &s); + read_unlock_bh(&sk->sk_callback_lock); + } + if (ret < 0) + tipc_conn_close(con); + + return ret; +} + +static void tipc_conn_recv_work(struct work_struct *work) +{ + struct tipc_conn *con = container_of(work, struct tipc_conn, rwork); + int count = 0; + + while (connected(con)) { + if (tipc_conn_rcv_from_sock(con)) + break; + + /* Don't flood Rx machine */ + if (++count >= MAX_RECV_MSG_COUNT) { + cond_resched(); + count = 0; + } + } + conn_put(con); +} + +/* tipc_conn_data_ready - interrupt callback indicating the socket has data + * The queued work is launched into tipc_recv_work()->tipc_conn_rcv_from_sock() + */ +static void tipc_conn_data_ready(struct sock *sk) +{ + struct tipc_conn *con; + + read_lock_bh(&sk->sk_callback_lock); + con = sk->sk_user_data; + if (connected(con)) { + conn_get(con); + if (!queue_work(con->server->rcv_wq, &con->rwork)) + conn_put(con); + } + read_unlock_bh(&sk->sk_callback_lock); +} + +static void tipc_topsrv_accept(struct work_struct *work) +{ + struct tipc_topsrv *srv = container_of(work, struct tipc_topsrv, awork); + struct socket *lsock = srv->listener; + struct socket *newsock; + struct tipc_conn *con; + struct sock *newsk; + int ret; + + while (1) { + ret = kernel_accept(lsock, &newsock, O_NONBLOCK); + if (ret < 0) + return; + con = tipc_conn_alloc(srv); + if (IS_ERR(con)) { + ret = PTR_ERR(con); + sock_release(newsock); + return; + } + /* Register callbacks */ + newsk = newsock->sk; + write_lock_bh(&newsk->sk_callback_lock); + newsk->sk_data_ready = tipc_conn_data_ready; + newsk->sk_write_space = tipc_conn_write_space; + newsk->sk_user_data = con; + con->sock = newsock; + write_unlock_bh(&newsk->sk_callback_lock); + + /* Wake up receive process in case of 'SYN+' message */ + newsk->sk_data_ready(newsk); + } +} + +/* tipc_toprsv_listener_data_ready - interrupt callback with connection request + * The queued job is launched into tipc_topsrv_accept() + */ +static void tipc_topsrv_listener_data_ready(struct sock *sk) +{ + struct tipc_topsrv *srv; + + read_lock_bh(&sk->sk_callback_lock); + srv = sk->sk_user_data; + if (srv->listener) + queue_work(srv->rcv_wq, &srv->awork); + read_unlock_bh(&sk->sk_callback_lock); +} + +static int tipc_topsrv_create_listener(struct tipc_topsrv *srv) +{ + int imp = TIPC_CRITICAL_IMPORTANCE; + struct socket *lsock = NULL; + struct sockaddr_tipc saddr; + struct sock *sk; + int rc; + + rc = sock_create_kern(srv->net, AF_TIPC, SOCK_SEQPACKET, 0, &lsock); + if (rc < 0) + return rc; + + srv->listener = lsock; + sk = lsock->sk; + write_lock_bh(&sk->sk_callback_lock); + sk->sk_data_ready = tipc_topsrv_listener_data_ready; + sk->sk_user_data = srv; + write_unlock_bh(&sk->sk_callback_lock); + + rc = kernel_setsockopt(lsock, SOL_TIPC, TIPC_IMPORTANCE, + (char *)&imp, sizeof(imp)); + if (rc < 0) + goto err; + + saddr.family = AF_TIPC; + saddr.addrtype = TIPC_ADDR_NAMESEQ; + saddr.addr.nameseq.type = TIPC_TOP_SRV; + saddr.addr.nameseq.lower = TIPC_TOP_SRV; + saddr.addr.nameseq.upper = TIPC_TOP_SRV; + saddr.scope = TIPC_NODE_SCOPE; + + rc = kernel_bind(lsock, (struct sockaddr *)&saddr, sizeof(saddr)); + if (rc < 0) + goto err; + rc = kernel_listen(lsock, 0); + if (rc < 0) + goto err; + + /* As server's listening socket owner and creator is the same module, + * we have to decrease TIPC module reference count to guarantee that + * it remains zero after the server socket is created, otherwise, + * executing "rmmod" command is unable to make TIPC module deleted + * after TIPC module is inserted successfully. + * + * However, the reference count is ever increased twice in + * sock_create_kern(): one is to increase the reference count of owner + * of TIPC socket's proto_ops struct; another is to increment the + * reference count of owner of TIPC proto struct. Therefore, we must + * decrement the module reference count twice to ensure that it keeps + * zero after server's listening socket is created. Of course, we + * must bump the module reference count twice as well before the socket + * is closed. + */ + module_put(lsock->ops->owner); + module_put(sk->sk_prot_creator->owner); + + return 0; +err: + sock_release(lsock); + return -EINVAL; +} + +bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type, u32 lower, + u32 upper, u32 filter, int *conid) +{ + struct tipc_subscr sub; + struct tipc_conn *con; + int rc; + + sub.seq.type = type; + sub.seq.lower = lower; + sub.seq.upper = upper; + sub.timeout = TIPC_WAIT_FOREVER; + sub.filter = filter; + *(u32 *)&sub.usr_handle = port; + + con = tipc_conn_alloc(tipc_topsrv(net)); + if (IS_ERR(con)) + return false; + + *conid = con->conid; + con->sock = NULL; + rc = tipc_conn_rcv_sub(tipc_topsrv(net), con, &sub); + if (rc >= 0) + return true; + conn_put(con); + return false; +} + +void tipc_topsrv_kern_unsubscr(struct net *net, int conid) +{ + struct tipc_conn *con; + + con = tipc_conn_lookup(tipc_topsrv(net), conid); + if (!con) + return; + + test_and_clear_bit(CF_CONNECTED, &con->flags); + tipc_conn_delete_sub(con, NULL); + conn_put(con); + conn_put(con); +} + +static void tipc_topsrv_kern_evt(struct net *net, struct tipc_event *evt) +{ + u32 port = *(u32 *)&evt->s.usr_handle; + u32 self = tipc_own_addr(net); + struct sk_buff_head evtq; + struct sk_buff *skb; + + skb = tipc_msg_create(TOP_SRV, 0, INT_H_SIZE, sizeof(*evt), + self, self, port, port, 0); + if (!skb) + return; + msg_set_dest_droppable(buf_msg(skb), true); + memcpy(msg_data(buf_msg(skb)), evt, sizeof(*evt)); + skb_queue_head_init(&evtq); + __skb_queue_tail(&evtq, skb); + tipc_sk_rcv(net, &evtq); +} + +static int tipc_topsrv_work_start(struct tipc_topsrv *s) +{ + s->rcv_wq = alloc_ordered_workqueue("tipc_rcv", 0); + if (!s->rcv_wq) { + pr_err("can't start tipc receive workqueue\n"); + return -ENOMEM; + } + + s->send_wq = alloc_ordered_workqueue("tipc_send", 0); + if (!s->send_wq) { + pr_err("can't start tipc send workqueue\n"); + destroy_workqueue(s->rcv_wq); + return -ENOMEM; + } + + return 0; +} + +static void tipc_topsrv_work_stop(struct tipc_topsrv *s) +{ + destroy_workqueue(s->rcv_wq); + destroy_workqueue(s->send_wq); +} + +int tipc_topsrv_start(struct net *net) +{ + struct tipc_net *tn = tipc_net(net); + const char name[] = "topology_server"; + struct tipc_topsrv *srv; + int ret; + + srv = kzalloc(sizeof(*srv), GFP_ATOMIC); + if (!srv) + return -ENOMEM; + + srv->net = net; + srv->max_rcvbuf_size = sizeof(struct tipc_subscr); + INIT_WORK(&srv->awork, tipc_topsrv_accept); + + strncpy(srv->name, name, strlen(name) + 1); + tn->topsrv = srv; + atomic_set(&tn->subscription_count, 0); + + spin_lock_init(&srv->idr_lock); + idr_init(&srv->conn_idr); + srv->idr_in_use = 0; + + ret = tipc_topsrv_work_start(srv); + if (ret < 0) + return ret; + + ret = tipc_topsrv_create_listener(srv); + if (ret < 0) + tipc_topsrv_work_stop(srv); + + return ret; +} + +void tipc_topsrv_stop(struct net *net) +{ + struct tipc_topsrv *srv = tipc_topsrv(net); + struct socket *lsock = srv->listener; + struct tipc_conn *con; + int id; + + spin_lock_bh(&srv->idr_lock); + for (id = 0; srv->idr_in_use; id++) { + con = idr_find(&srv->conn_idr, id); + if (con) { + spin_unlock_bh(&srv->idr_lock); + tipc_conn_close(con); + spin_lock_bh(&srv->idr_lock); + } + } + __module_get(lsock->ops->owner); + __module_get(lsock->sk->sk_prot_creator->owner); + srv->listener = NULL; + spin_unlock_bh(&srv->idr_lock); + sock_release(lsock); + tipc_topsrv_work_stop(srv); + idr_destroy(&srv->conn_idr); + kfree(srv); +} diff --git a/net/tipc/server.h b/net/tipc/topsrv.h index 64df7513cd70..c7ea71293748 100644 --- a/net/tipc/server.h +++ b/net/tipc/topsrv.h @@ -2,6 +2,7 @@ * net/tipc/server.h: Include file for TIPC server code * * Copyright (c) 2012-2013, Wind River Systems + * Copyright (c) 2017, Ericsson AB * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -36,68 +37,18 @@ #ifndef _TIPC_SERVER_H #define _TIPC_SERVER_H -#include <linux/idr.h> -#include <linux/tipc.h> -#include <net/net_namespace.h> +#include "core.h" #define TIPC_SERVER_NAME_LEN 32 #define TIPC_SUB_CLUSTER_SCOPE 0x20 #define TIPC_SUB_NODE_SCOPE 0x40 #define TIPC_SUB_NO_STATUS 0x80 -/** - * struct tipc_server - TIPC server structure - * @conn_idr: identifier set of connection - * @idr_lock: protect the connection identifier set - * @idr_in_use: amount of allocated identifier entry - * @net: network namspace instance - * @rcvbuf_cache: memory cache of server receive buffer - * @rcv_wq: receive workqueue - * @send_wq: send workqueue - * @max_rcvbuf_size: maximum permitted receive message length - * @tipc_conn_new: callback will be called when new connection is incoming - * @tipc_conn_release: callback will be called before releasing the connection - * @tipc_conn_recvmsg: callback will be called when message arrives - * @saddr: TIPC server address - * @name: server name - * @imp: message importance - * @type: socket type - */ -struct tipc_server { - struct idr conn_idr; - spinlock_t idr_lock; - int idr_in_use; - struct net *net; - struct kmem_cache *rcvbuf_cache; - struct workqueue_struct *rcv_wq; - struct workqueue_struct *send_wq; - int max_rcvbuf_size; - void *(*tipc_conn_new)(int conid); - void (*tipc_conn_release)(int conid, void *usr_data); - int (*tipc_conn_recvmsg)(struct net *net, int conid, - struct sockaddr_tipc *addr, void *usr_data, - void *buf, size_t len); - struct sockaddr_tipc *saddr; - char name[TIPC_SERVER_NAME_LEN]; - int imp; - int type; -}; - -int tipc_conn_sendmsg(struct tipc_server *s, int conid, - struct sockaddr_tipc *addr, void *data, size_t len); +void tipc_topsrv_queue_evt(struct net *net, int conid, + u32 event, struct tipc_event *evt); bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type, u32 lower, u32 upper, u32 filter, int *conid); void tipc_topsrv_kern_unsubscr(struct net *net, int conid); -/** - * tipc_conn_terminate - terminate connection with server - * - * Note: Must call it in process context since it might sleep - */ -void tipc_conn_terminate(struct tipc_server *s, int conid); -int tipc_server_start(struct tipc_server *s); - -void tipc_server_stop(struct tipc_server *s); - #endif diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index b0d5fcea47e7..e9b4b53ab53e 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -308,8 +308,11 @@ static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval, goto out; } lock_sock(sk); - memcpy(crypto_info_aes_gcm_128->iv, ctx->iv, + memcpy(crypto_info_aes_gcm_128->iv, + ctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, TLS_CIPHER_AES_GCM_128_IV_SIZE); + memcpy(crypto_info_aes_gcm_128->rec_seq, ctx->rec_seq, + TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE); release_sock(sk); if (copy_to_user(optval, crypto_info_aes_gcm_128, @@ -375,7 +378,7 @@ static int do_tls_setsockopt_tx(struct sock *sk, char __user *optval, rc = copy_from_user(crypto_info, optval, sizeof(*crypto_info)); if (rc) { rc = -EFAULT; - goto out; + goto err_crypto_info; } /* check version */ diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index d545e1d0dea2..bc2970a8e7f3 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -637,7 +637,7 @@ static int unix_stream_connect(struct socket *, struct sockaddr *, int addr_len, int flags); static int unix_socketpair(struct socket *, struct socket *); static int unix_accept(struct socket *, struct socket *, int, bool); -static int unix_getname(struct socket *, struct sockaddr *, int *, int); +static int unix_getname(struct socket *, struct sockaddr *, int); static __poll_t unix_poll(struct file *, struct socket *, poll_table *); static __poll_t unix_dgram_poll(struct file *, struct socket *, poll_table *); @@ -1453,7 +1453,7 @@ out: } -static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int *uaddr_len, int peer) +static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct sock *sk = sock->sk; struct unix_sock *u; @@ -1476,12 +1476,12 @@ static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int *uaddr_ if (!u->addr) { sunaddr->sun_family = AF_UNIX; sunaddr->sun_path[0] = 0; - *uaddr_len = sizeof(short); + err = sizeof(short); } else { struct unix_address *addr = u->addr; - *uaddr_len = addr->len; - memcpy(sunaddr, addr->name, *uaddr_len); + err = addr->len; + memcpy(sunaddr, addr->name, addr->len); } unix_state_unlock(sk); sock_put(sk); @@ -1825,7 +1825,7 @@ out: } /* We use paged skbs for stream sockets, and limit occupancy to 32768 - * bytes, and a minimun of a full page. + * bytes, and a minimum of a full page. */ #define UNIX_SKB_FRAGS_SZ (PAGE_SIZE << get_order(32768)) @@ -2913,6 +2913,7 @@ static void __net_exit unix_net_exit(struct net *net) static struct pernet_operations unix_net_ops = { .init = unix_net_init, .exit = unix_net_exit, + .async = true, }; static int __init af_unix_init(void) diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index e0fc84daed94..aac9b8f6552e 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -759,7 +759,7 @@ vsock_bind(struct socket *sock, struct sockaddr *addr, int addr_len) } static int vsock_getname(struct socket *sock, - struct sockaddr *addr, int *addr_len, int peer) + struct sockaddr *addr, int peer) { int err; struct sock *sk; @@ -794,7 +794,7 @@ static int vsock_getname(struct socket *sock, */ BUILD_BUG_ON(sizeof(*vm_addr) > 128); memcpy(addr, vm_addr, sizeof(*vm_addr)); - *addr_len = sizeof(*vm_addr); + err = sizeof(*vm_addr); out: release_sock(sk); diff --git a/net/wireless/core.c b/net/wireless/core.c index a6f3cac8c640..670aa229168a 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1340,6 +1340,7 @@ static void __net_exit cfg80211_pernet_exit(struct net *net) static struct pernet_operations cfg80211_pernet_ops = { .exit = cfg80211_pernet_exit, + .async = true, }; static int __init cfg80211_init(void) diff --git a/net/wireless/mesh.c b/net/wireless/mesh.c index 51aa55618ef7..b12da6ef3c12 100644 --- a/net/wireless/mesh.c +++ b/net/wireless/mesh.c @@ -170,9 +170,28 @@ int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev, enum nl80211_bss_scan_width scan_width; struct ieee80211_supported_band *sband = rdev->wiphy.bands[setup->chandef.chan->band]; - scan_width = cfg80211_chandef_to_scan_width(&setup->chandef); - setup->basic_rates = ieee80211_mandatory_rates(sband, - scan_width); + + if (setup->chandef.chan->band == NL80211_BAND_2GHZ) { + int i; + + /* + * Older versions selected the mandatory rates for + * 2.4 GHz as well, but were broken in that only + * 1 Mbps was regarded as a mandatory rate. Keep + * using just 1 Mbps as the default basic rate for + * mesh to be interoperable with older versions. + */ + for (i = 0; i < sband->n_bitrates; i++) { + if (sband->bitrates[i].bitrate == 10) { + setup->basic_rates = BIT(i); + break; + } + } + } else { + scan_width = cfg80211_chandef_to_scan_width(&setup->chandef); + setup->basic_rates = ieee80211_mandatory_rates(sband, + scan_width); + } } err = cfg80211_chandef_dfs_required(&rdev->wiphy, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 9c0dcc8324b0..a910150f8169 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -421,6 +421,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_FILS_CACHE_ID] = { .len = 2 }, [NL80211_ATTR_PMK] = { .type = NLA_BINARY, .len = PMK_MAX_LEN }, [NL80211_ATTR_SCHED_SCAN_MULTI] = { .type = NLA_FLAG }, + [NL80211_ATTR_EXTERNAL_AUTH_SUPPORT] = { .type = NLA_FLAG }, }; /* policy for the key attributes */ @@ -3923,9 +3924,10 @@ static bool nl80211_valid_auth_type(struct cfg80211_registered_device *rdev, return false; return true; case NL80211_CMD_CONNECT: - /* SAE not supported yet */ - if (auth_type == NL80211_AUTHTYPE_SAE) + if (!(rdev->wiphy.features & NL80211_FEATURE_SAE) && + auth_type == NL80211_AUTHTYPE_SAE) return false; + /* FILS with SK PFS or PK not supported yet */ if (auth_type == NL80211_AUTHTYPE_FILS_SK_PFS || auth_type == NL80211_AUTHTYPE_FILS_PK) @@ -4487,6 +4489,7 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid, PUT_SINFO_U64(RX_DROP_MISC, rx_dropped_misc); PUT_SINFO_U64(BEACON_RX, rx_beacon); PUT_SINFO(BEACON_SIGNAL_AVG, rx_beacon_signal_avg, u8); + PUT_SINFO(ACK_SIGNAL, ack_signal, u8); #undef PUT_SINFO #undef PUT_SINFO_U64 @@ -5848,7 +5851,6 @@ static int nl80211_get_mesh_config(struct sk_buff *skb, return genlmsg_reply(msg, info); nla_put_failure: - genlmsg_cancel(msg, hdr); out: nlmsg_free(msg); return -ENOBUFS; @@ -6329,7 +6331,6 @@ static int nl80211_get_reg_do(struct sk_buff *skb, struct genl_info *info) nla_put_failure_rcu: rcu_read_unlock(); nla_put_failure: - genlmsg_cancel(msg, hdr); put_failure: nlmsg_free(msg); return -EMSGSIZE; @@ -6718,8 +6719,17 @@ nl80211_check_scan_flags(struct wiphy *wiphy, struct wireless_dev *wdev, *flags = nla_get_u32(attrs[NL80211_ATTR_SCAN_FLAGS]); - if ((*flags & NL80211_SCAN_FLAG_LOW_PRIORITY) && - !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) + if (((*flags & NL80211_SCAN_FLAG_LOW_PRIORITY) && + !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) || + ((*flags & NL80211_SCAN_FLAG_LOW_SPAN) && + !wiphy_ext_feature_isset(wiphy, + NL80211_EXT_FEATURE_LOW_SPAN_SCAN)) || + ((*flags & NL80211_SCAN_FLAG_LOW_POWER) && + !wiphy_ext_feature_isset(wiphy, + NL80211_EXT_FEATURE_LOW_POWER_SCAN)) || + ((*flags & NL80211_SCAN_FLAG_HIGH_ACCURACY) && + !wiphy_ext_feature_isset(wiphy, + NL80211_EXT_FEATURE_HIGH_ACCURACY_SCAN))) return -EOPNOTSUPP; if (*flags & NL80211_SCAN_FLAG_RANDOM_ADDR) { @@ -9155,6 +9165,15 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) return -EINVAL; } + if (nla_get_flag(info->attrs[NL80211_ATTR_EXTERNAL_AUTH_SUPPORT])) { + if (!info->attrs[NL80211_ATTR_SOCKET_OWNER]) { + GENL_SET_ERR_MSG(info, + "external auth requires connection ownership"); + return -EINVAL; + } + connect.flags |= CONNECT_REQ_EXTERNAL_AUTH_SUPPORT; + } + wdev_lock(dev->ieee80211_ptr); err = cfg80211_connect(rdev, dev, &connect, connkeys, @@ -12463,6 +12482,41 @@ static int nl80211_del_pmk(struct sk_buff *skb, struct genl_info *info) return ret; } +static int nl80211_external_auth(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + struct cfg80211_external_auth_params params; + + if (!rdev->ops->external_auth) + return -EOPNOTSUPP; + + if (!info->attrs[NL80211_ATTR_SSID]) + return -EINVAL; + + if (!info->attrs[NL80211_ATTR_BSSID]) + return -EINVAL; + + if (!info->attrs[NL80211_ATTR_STATUS_CODE]) + return -EINVAL; + + memset(¶ms, 0, sizeof(params)); + + params.ssid.ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]); + if (params.ssid.ssid_len == 0 || + params.ssid.ssid_len > IEEE80211_MAX_SSID_LEN) + return -EINVAL; + memcpy(params.ssid.ssid, nla_data(info->attrs[NL80211_ATTR_SSID]), + params.ssid.ssid_len); + + memcpy(params.bssid, nla_data(info->attrs[NL80211_ATTR_BSSID]), + ETH_ALEN); + + params.status = nla_get_u16(info->attrs[NL80211_ATTR_STATUS_CODE]); + + return rdev_external_auth(rdev, dev, ¶ms); +} + #define NL80211_FLAG_NEED_WIPHY 0x01 #define NL80211_FLAG_NEED_NETDEV 0x02 #define NL80211_FLAG_NEED_RTNL 0x04 @@ -13358,6 +13412,14 @@ static const struct genl_ops nl80211_ops[] = { .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, + { + .cmd = NL80211_CMD_EXTERNAL_AUTH, + .doit = nl80211_external_auth, + .policy = nl80211_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_NEED_RTNL, + }, }; @@ -13672,7 +13734,6 @@ void nl80211_common_reg_change_event(enum nl80211_commands cmd_id, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } @@ -13720,7 +13781,6 @@ static void nl80211_send_mlme_event(struct cfg80211_registered_device *rdev, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } @@ -13808,7 +13868,6 @@ static void nl80211_send_mlme_timeout(struct cfg80211_registered_device *rdev, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } @@ -13884,7 +13943,6 @@ void nl80211_send_connect_result(struct cfg80211_registered_device *rdev, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } @@ -13924,7 +13982,6 @@ void nl80211_send_roamed(struct cfg80211_registered_device *rdev, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } @@ -13954,7 +14011,6 @@ void nl80211_send_port_authorized(struct cfg80211_registered_device *rdev, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } @@ -13991,7 +14047,6 @@ void nl80211_send_disconnected(struct cfg80211_registered_device *rdev, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } @@ -14024,7 +14079,6 @@ void nl80211_send_ibss_bssid(struct cfg80211_registered_device *rdev, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } @@ -14065,7 +14119,6 @@ void cfg80211_notify_new_peer_candidate(struct net_device *dev, const u8 *addr, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } EXPORT_SYMBOL(cfg80211_notify_new_peer_candidate); @@ -14104,7 +14157,6 @@ void nl80211_michael_mic_failure(struct cfg80211_registered_device *rdev, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } @@ -14159,7 +14211,6 @@ void nl80211_send_beacon_hint_event(struct wiphy *wiphy, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } @@ -14205,7 +14256,6 @@ static void nl80211_send_remain_on_chan_event( return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } @@ -14319,7 +14369,6 @@ void cfg80211_conn_failed(struct net_device *dev, const u8 *mac_addr, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } EXPORT_SYMBOL(cfg80211_conn_failed); @@ -14356,7 +14405,6 @@ static bool __nl80211_unexpected_frame(struct net_device *dev, u8 cmd, return true; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); return true; } @@ -14440,7 +14488,6 @@ int nl80211_send_mgmt(struct cfg80211_registered_device *rdev, return genlmsg_unicast(wiphy_net(&rdev->wiphy), msg, nlportid); nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); return -ENOBUFS; } @@ -14484,7 +14531,6 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } EXPORT_SYMBOL(cfg80211_mgmt_tx_status); @@ -14693,7 +14739,6 @@ static void nl80211_gtk_rekey_notify(struct cfg80211_registered_device *rdev, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } @@ -14751,7 +14796,6 @@ nl80211_pmksa_candidate_notify(struct cfg80211_registered_device *rdev, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } @@ -14804,7 +14848,6 @@ static void nl80211_ch_switch_notify(struct cfg80211_registered_device *rdev, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } @@ -14886,12 +14929,67 @@ nl80211_radar_notify(struct cfg80211_registered_device *rdev, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } +void cfg80211_sta_opmode_change_notify(struct net_device *dev, const u8 *mac, + struct sta_opmode_info *sta_opmode, + gfp_t gfp) +{ + struct sk_buff *msg; + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); + void *hdr; + + if (WARN_ON(!mac)) + return; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp); + if (!msg) + return; + + hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_STA_OPMODE_CHANGED); + if (!hdr) { + nlmsg_free(msg); + return; + } + + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx)) + goto nla_put_failure; + + if (nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex)) + goto nla_put_failure; + + if (nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, mac)) + goto nla_put_failure; + + if ((sta_opmode->changed & STA_OPMODE_SMPS_MODE_CHANGED) && + nla_put_u8(msg, NL80211_ATTR_SMPS_MODE, sta_opmode->smps_mode)) + goto nla_put_failure; + + if ((sta_opmode->changed & STA_OPMODE_MAX_BW_CHANGED) && + nla_put_u8(msg, NL80211_ATTR_CHANNEL_WIDTH, sta_opmode->bw)) + goto nla_put_failure; + + if ((sta_opmode->changed & STA_OPMODE_N_SS_CHANGED) && + nla_put_u8(msg, NL80211_ATTR_NSS, sta_opmode->rx_nss)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + + genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0, + NL80211_MCGRP_MLME, gfp); + + return; + +nla_put_failure: + nlmsg_free(msg); +} +EXPORT_SYMBOL(cfg80211_sta_opmode_change_notify); + void cfg80211_probe_status(struct net_device *dev, const u8 *addr, - u64 cookie, bool acked, gfp_t gfp) + u64 cookie, bool acked, s32 ack_signal, + bool is_valid_ack_signal, gfp_t gfp) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); @@ -14916,7 +15014,9 @@ void cfg80211_probe_status(struct net_device *dev, const u8 *addr, nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, addr) || nla_put_u64_64bit(msg, NL80211_ATTR_COOKIE, cookie, NL80211_ATTR_PAD) || - (acked && nla_put_flag(msg, NL80211_ATTR_ACK))) + (acked && nla_put_flag(msg, NL80211_ATTR_ACK)) || + (is_valid_ack_signal && nla_put_s32(msg, NL80211_ATTR_ACK_SIGNAL, + ack_signal))) goto nla_put_failure; genlmsg_end(msg, hdr); @@ -14926,7 +15026,6 @@ void cfg80211_probe_status(struct net_device *dev, const u8 *addr, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } EXPORT_SYMBOL(cfg80211_probe_status); @@ -14971,8 +15070,6 @@ void cfg80211_report_obss_beacon(struct wiphy *wiphy, nla_put_failure: spin_unlock_bh(&rdev->beacon_registrations_lock); - if (hdr) - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } EXPORT_SYMBOL(cfg80211_report_obss_beacon); @@ -15188,7 +15285,6 @@ void cfg80211_tdls_oper_request(struct net_device *dev, const u8 *peer, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } EXPORT_SYMBOL(cfg80211_tdls_oper_request); @@ -15333,8 +15429,6 @@ void cfg80211_crit_proto_stopped(struct wireless_dev *wdev, gfp_t gfp) return; nla_put_failure: - if (hdr) - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } EXPORT_SYMBOL(cfg80211_crit_proto_stopped); @@ -15369,6 +15463,47 @@ void nl80211_send_ap_stopped(struct wireless_dev *wdev) nlmsg_free(msg); } +int cfg80211_external_auth_request(struct net_device *dev, + struct cfg80211_external_auth_params *params, + gfp_t gfp) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); + struct sk_buff *msg; + void *hdr; + + if (!wdev->conn_owner_nlportid) + return -EINVAL; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp); + if (!msg) + return -ENOMEM; + + hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_EXTERNAL_AUTH); + if (!hdr) + goto nla_put_failure; + + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || + nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) || + nla_put_u32(msg, NL80211_ATTR_AKM_SUITES, params->key_mgmt_suite) || + nla_put_u32(msg, NL80211_ATTR_EXTERNAL_AUTH_ACTION, + params->action) || + nla_put(msg, NL80211_ATTR_BSSID, ETH_ALEN, params->bssid) || + nla_put(msg, NL80211_ATTR_SSID, params->ssid.ssid_len, + params->ssid.ssid)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + genlmsg_unicast(wiphy_net(&rdev->wiphy), msg, + wdev->conn_owner_nlportid); + return 0; + + nla_put_failure: + nlmsg_free(msg); + return -ENOBUFS; +} +EXPORT_SYMBOL(cfg80211_external_auth_request); + /* initialisation/exit functions */ int __init nl80211_init(void) diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index 0c06240d25af..84f23ae015fc 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -1190,4 +1190,19 @@ static inline int rdev_del_pmk(struct cfg80211_registered_device *rdev, trace_rdev_return_int(&rdev->wiphy, ret); return ret; } + +static inline int +rdev_external_auth(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_external_auth_params *params) +{ + int ret = -EOPNOTSUPP; + + trace_rdev_external_auth(&rdev->wiphy, dev, params); + if (rdev->ops->external_auth) + ret = rdev->ops->external_auth(&rdev->wiphy, dev, params); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + #endif /* __CFG80211_RDEV_OPS */ diff --git a/net/wireless/sme.c b/net/wireless/sme.c index fdb3646274a5..701cfd7acc1b 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -1032,6 +1032,8 @@ void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, wdev->current_bss = NULL; wdev->ssid_len = 0; wdev->conn_owner_nlportid = 0; + kzfree(wdev->connect_keys); + wdev->connect_keys = NULL; nl80211_send_disconnected(rdev, dev, reason, ie, ie_len, from_ap); diff --git a/net/wireless/trace.h b/net/wireless/trace.h index bcfedd39e7a3..5152938b358d 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -2319,6 +2319,29 @@ TRACE_EVENT(rdev_del_pmk, WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(aa)) ); +TRACE_EVENT(rdev_external_auth, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct cfg80211_external_auth_params *params), + TP_ARGS(wiphy, netdev, params), + TP_STRUCT__entry(WIPHY_ENTRY + NETDEV_ENTRY + MAC_ENTRY(bssid) + __array(u8, ssid, IEEE80211_MAX_SSID_LEN + 1) + __field(u16, status) + ), + TP_fast_assign(WIPHY_ASSIGN; + NETDEV_ASSIGN; + MAC_ASSIGN(bssid, params->bssid); + memset(__entry->ssid, 0, IEEE80211_MAX_SSID_LEN + 1); + memcpy(__entry->ssid, params->ssid.ssid, + params->ssid.ssid_len); + __entry->status = params->status; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", bssid: " MAC_PR_FMT + ", ssid: %s, status: %u", WIPHY_PR_ARG, NETDEV_PR_ARG, + __entry->bssid, __entry->ssid, __entry->status) +); + /************************************************************* * cfg80211 exported functions traces * *************************************************************/ diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c index 9efbfc753347..bc7064486b15 100644 --- a/net/wireless/wext-core.c +++ b/net/wireless/wext-core.c @@ -390,6 +390,7 @@ static void __net_exit wext_pernet_exit(struct net *net) static struct pernet_operations wext_pernet_ops = { .init = wext_pernet_init, .exit = wext_pernet_exit, + .async = true, }; static int __init wireless_nlevent_init(void) diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 562cc11131f6..d49aa79b7997 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -896,7 +896,7 @@ out: } static int x25_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { struct sockaddr_x25 *sx25 = (struct sockaddr_x25 *)uaddr; struct sock *sk = sock->sk; @@ -913,7 +913,7 @@ static int x25_getname(struct socket *sock, struct sockaddr *uaddr, sx25->sx25_addr = x25->source_addr; sx25->sx25_family = AF_X25; - *uaddr_len = sizeof(*sx25); + rc = sizeof(*sx25); out: return rc; diff --git a/net/x25/x25_subr.c b/net/x25/x25_subr.c index db0b1315d577..9c214ec681ac 100644 --- a/net/x25/x25_subr.c +++ b/net/x25/x25_subr.c @@ -335,8 +335,7 @@ int x25_decode(struct sock *sk, struct sk_buff *skb, int *ns, int *nr, int *q, } } - pr_debug("invalid PLP frame %02X %02X %02X\n", - frame[0], frame[1], frame[2]); + pr_debug("invalid PLP frame %3ph\n", frame); return X25_ILLEGAL; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 7a23078132cf..77d9d1ab05ce 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2982,6 +2982,7 @@ static void __net_exit xfrm_net_exit(struct net *net) static struct pernet_operations __net_initdata xfrm_net_ops = { .init = xfrm_net_init, .exit = xfrm_net_exit, + .async = true, }; void __init xfrm_init(void) diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index ec3fc8d88e87..2c2a587e0942 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -43,6 +43,7 @@ hostprogs-y += xdp_redirect_cpu hostprogs-y += xdp_monitor hostprogs-y += xdp_rxq_info hostprogs-y += syscall_tp +hostprogs-y += cpustat # Libbpf dependencies LIBBPF := ../../tools/lib/bpf/bpf.o ../../tools/lib/bpf/nlattr.o @@ -93,6 +94,7 @@ xdp_redirect_cpu-objs := bpf_load.o $(LIBBPF) xdp_redirect_cpu_user.o xdp_monitor-objs := bpf_load.o $(LIBBPF) xdp_monitor_user.o xdp_rxq_info-objs := bpf_load.o $(LIBBPF) xdp_rxq_info_user.o syscall_tp-objs := bpf_load.o $(LIBBPF) syscall_tp_user.o +cpustat-objs := bpf_load.o $(LIBBPF) cpustat_user.o # Tell kbuild to always build the programs always := $(hostprogs-y) @@ -144,6 +146,7 @@ always += xdp_monitor_kern.o always += xdp_rxq_info_kern.o always += xdp2skb_meta_kern.o always += syscall_tp_kern.o +always += cpustat_kern.o HOSTCFLAGS += -I$(objtree)/usr/include HOSTCFLAGS += -I$(srctree)/tools/lib/ @@ -188,6 +191,7 @@ HOSTLOADLIBES_xdp_redirect_cpu += -lelf HOSTLOADLIBES_xdp_monitor += -lelf HOSTLOADLIBES_xdp_rxq_info += -lelf HOSTLOADLIBES_syscall_tp += -lelf +HOSTLOADLIBES_cpustat += -lelf # Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline: # make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang diff --git a/samples/bpf/cpustat_kern.c b/samples/bpf/cpustat_kern.c new file mode 100644 index 000000000000..68c84da065b1 --- /dev/null +++ b/samples/bpf/cpustat_kern.c @@ -0,0 +1,281 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/version.h> +#include <linux/ptrace.h> +#include <uapi/linux/bpf.h> +#include "bpf_helpers.h" + +/* + * The CPU number, cstate number and pstate number are based + * on 96boards Hikey with octa CA53 CPUs. + * + * Every CPU have three idle states for cstate: + * WFI, CPU_OFF, CLUSTER_OFF + * + * Every CPU have 5 operating points: + * 208MHz, 432MHz, 729MHz, 960MHz, 1200MHz + * + * This code is based on these assumption and other platforms + * need to adjust these definitions. + */ +#define MAX_CPU 8 +#define MAX_PSTATE_ENTRIES 5 +#define MAX_CSTATE_ENTRIES 3 + +static int cpu_opps[] = { 208000, 432000, 729000, 960000, 1200000 }; + +/* + * my_map structure is used to record cstate and pstate index and + * timestamp (Idx, Ts), when new event incoming we need to update + * combination for new state index and timestamp (Idx`, Ts`). + * + * Based on (Idx, Ts) and (Idx`, Ts`) we can calculate the time + * interval for the previous state: Duration(Idx) = Ts` - Ts. + * + * Every CPU has one below array for recording state index and + * timestamp, and record for cstate and pstate saperately: + * + * +--------------------------+ + * | cstate timestamp | + * +--------------------------+ + * | cstate index | + * +--------------------------+ + * | pstate timestamp | + * +--------------------------+ + * | pstate index | + * +--------------------------+ + */ +#define MAP_OFF_CSTATE_TIME 0 +#define MAP_OFF_CSTATE_IDX 1 +#define MAP_OFF_PSTATE_TIME 2 +#define MAP_OFF_PSTATE_IDX 3 +#define MAP_OFF_NUM 4 + +struct bpf_map_def SEC("maps") my_map = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(u64), + .max_entries = MAX_CPU * MAP_OFF_NUM, +}; + +/* cstate_duration records duration time for every idle state per CPU */ +struct bpf_map_def SEC("maps") cstate_duration = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(u64), + .max_entries = MAX_CPU * MAX_CSTATE_ENTRIES, +}; + +/* pstate_duration records duration time for every operating point per CPU */ +struct bpf_map_def SEC("maps") pstate_duration = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(u64), + .max_entries = MAX_CPU * MAX_PSTATE_ENTRIES, +}; + +/* + * The trace events for cpu_idle and cpu_frequency are taken from: + * /sys/kernel/debug/tracing/events/power/cpu_idle/format + * /sys/kernel/debug/tracing/events/power/cpu_frequency/format + * + * These two events have same format, so define one common structure. + */ +struct cpu_args { + u64 pad; + u32 state; + u32 cpu_id; +}; + +/* calculate pstate index, returns MAX_PSTATE_ENTRIES for failure */ +static u32 find_cpu_pstate_idx(u32 frequency) +{ + u32 i; + + for (i = 0; i < sizeof(cpu_opps) / sizeof(u32); i++) { + if (frequency == cpu_opps[i]) + return i; + } + + return i; +} + +SEC("tracepoint/power/cpu_idle") +int bpf_prog1(struct cpu_args *ctx) +{ + u64 *cts, *pts, *cstate, *pstate, prev_state, cur_ts, delta; + u32 key, cpu, pstate_idx; + u64 *val; + + if (ctx->cpu_id > MAX_CPU) + return 0; + + cpu = ctx->cpu_id; + + key = cpu * MAP_OFF_NUM + MAP_OFF_CSTATE_TIME; + cts = bpf_map_lookup_elem(&my_map, &key); + if (!cts) + return 0; + + key = cpu * MAP_OFF_NUM + MAP_OFF_CSTATE_IDX; + cstate = bpf_map_lookup_elem(&my_map, &key); + if (!cstate) + return 0; + + key = cpu * MAP_OFF_NUM + MAP_OFF_PSTATE_TIME; + pts = bpf_map_lookup_elem(&my_map, &key); + if (!pts) + return 0; + + key = cpu * MAP_OFF_NUM + MAP_OFF_PSTATE_IDX; + pstate = bpf_map_lookup_elem(&my_map, &key); + if (!pstate) + return 0; + + prev_state = *cstate; + *cstate = ctx->state; + + if (!*cts) { + *cts = bpf_ktime_get_ns(); + return 0; + } + + cur_ts = bpf_ktime_get_ns(); + delta = cur_ts - *cts; + *cts = cur_ts; + + /* + * When state doesn't equal to (u32)-1, the cpu will enter + * one idle state; for this case we need to record interval + * for the pstate. + * + * OPP2 + * +---------------------+ + * OPP1 | | + * ---------+ | + * | Idle state + * +--------------- + * + * |<- pstate duration ->| + * ^ ^ + * pts cur_ts + */ + if (ctx->state != (u32)-1) { + + /* record pstate after have first cpu_frequency event */ + if (!*pts) + return 0; + + delta = cur_ts - *pts; + + pstate_idx = find_cpu_pstate_idx(*pstate); + if (pstate_idx >= MAX_PSTATE_ENTRIES) + return 0; + + key = cpu * MAX_PSTATE_ENTRIES + pstate_idx; + val = bpf_map_lookup_elem(&pstate_duration, &key); + if (val) + __sync_fetch_and_add((long *)val, delta); + + /* + * When state equal to (u32)-1, the cpu just exits from one + * specific idle state; for this case we need to record + * interval for the pstate. + * + * OPP2 + * -----------+ + * | OPP1 + * | +----------- + * | Idle state | + * +---------------------+ + * + * |<- cstate duration ->| + * ^ ^ + * cts cur_ts + */ + } else { + + key = cpu * MAX_CSTATE_ENTRIES + prev_state; + val = bpf_map_lookup_elem(&cstate_duration, &key); + if (val) + __sync_fetch_and_add((long *)val, delta); + } + + /* Update timestamp for pstate as new start time */ + if (*pts) + *pts = cur_ts; + + return 0; +} + +SEC("tracepoint/power/cpu_frequency") +int bpf_prog2(struct cpu_args *ctx) +{ + u64 *pts, *cstate, *pstate, prev_state, cur_ts, delta; + u32 key, cpu, pstate_idx; + u64 *val; + + cpu = ctx->cpu_id; + + key = cpu * MAP_OFF_NUM + MAP_OFF_PSTATE_TIME; + pts = bpf_map_lookup_elem(&my_map, &key); + if (!pts) + return 0; + + key = cpu * MAP_OFF_NUM + MAP_OFF_PSTATE_IDX; + pstate = bpf_map_lookup_elem(&my_map, &key); + if (!pstate) + return 0; + + key = cpu * MAP_OFF_NUM + MAP_OFF_CSTATE_IDX; + cstate = bpf_map_lookup_elem(&my_map, &key); + if (!cstate) + return 0; + + prev_state = *pstate; + *pstate = ctx->state; + + if (!*pts) { + *pts = bpf_ktime_get_ns(); + return 0; + } + + cur_ts = bpf_ktime_get_ns(); + delta = cur_ts - *pts; + *pts = cur_ts; + + /* When CPU is in idle, bail out to skip pstate statistics */ + if (*cstate != (u32)(-1)) + return 0; + + /* + * The cpu changes to another different OPP (in below diagram + * change frequency from OPP3 to OPP1), need recording interval + * for previous frequency OPP3 and update timestamp as start + * time for new frequency OPP1. + * + * OPP3 + * +---------------------+ + * OPP2 | | + * ---------+ | + * | OPP1 + * +--------------- + * + * |<- pstate duration ->| + * ^ ^ + * pts cur_ts + */ + pstate_idx = find_cpu_pstate_idx(*pstate); + if (pstate_idx >= MAX_PSTATE_ENTRIES) + return 0; + + key = cpu * MAX_PSTATE_ENTRIES + pstate_idx; + val = bpf_map_lookup_elem(&pstate_duration, &key); + if (val) + __sync_fetch_and_add((long *)val, delta); + + return 0; +} + +char _license[] SEC("license") = "GPL"; +u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/cpustat_user.c b/samples/bpf/cpustat_user.c new file mode 100644 index 000000000000..2b4cd1ae57c5 --- /dev/null +++ b/samples/bpf/cpustat_user.c @@ -0,0 +1,219 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <signal.h> +#include <sched.h> +#include <string.h> +#include <unistd.h> +#include <fcntl.h> +#include <linux/bpf.h> +#include <locale.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <sys/time.h> +#include <sys/resource.h> +#include <sys/wait.h> + +#include "libbpf.h" +#include "bpf_load.h" + +#define MAX_CPU 8 +#define MAX_PSTATE_ENTRIES 5 +#define MAX_CSTATE_ENTRIES 3 +#define MAX_STARS 40 + +#define CPUFREQ_MAX_SYSFS_PATH "/sys/devices/system/cpu/cpu0/cpufreq/scaling_max_freq" +#define CPUFREQ_LOWEST_FREQ "208000" +#define CPUFREQ_HIGHEST_FREQ "12000000" + +struct cpu_stat_data { + unsigned long cstate[MAX_CSTATE_ENTRIES]; + unsigned long pstate[MAX_PSTATE_ENTRIES]; +}; + +static struct cpu_stat_data stat_data[MAX_CPU]; + +static void cpu_stat_print(void) +{ + int i, j; + char state_str[sizeof("cstate-9")]; + struct cpu_stat_data *data; + + /* Clear screen */ + printf("\033[2J"); + + /* Header */ + printf("\nCPU states statistics:\n"); + printf("%-10s ", "state(ms)"); + + for (i = 0; i < MAX_CSTATE_ENTRIES; i++) { + sprintf(state_str, "cstate-%d", i); + printf("%-11s ", state_str); + } + + for (i = 0; i < MAX_PSTATE_ENTRIES; i++) { + sprintf(state_str, "pstate-%d", i); + printf("%-11s ", state_str); + } + + printf("\n"); + + for (j = 0; j < MAX_CPU; j++) { + data = &stat_data[j]; + + printf("CPU-%-6d ", j); + for (i = 0; i < MAX_CSTATE_ENTRIES; i++) + printf("%-11ld ", data->cstate[i] / 1000000); + + for (i = 0; i < MAX_PSTATE_ENTRIES; i++) + printf("%-11ld ", data->pstate[i] / 1000000); + + printf("\n"); + } +} + +static void cpu_stat_update(int cstate_fd, int pstate_fd) +{ + unsigned long key, value; + int c, i; + + for (c = 0; c < MAX_CPU; c++) { + for (i = 0; i < MAX_CSTATE_ENTRIES; i++) { + key = c * MAX_CSTATE_ENTRIES + i; + bpf_map_lookup_elem(cstate_fd, &key, &value); + stat_data[c].cstate[i] = value; + } + + for (i = 0; i < MAX_PSTATE_ENTRIES; i++) { + key = c * MAX_PSTATE_ENTRIES + i; + bpf_map_lookup_elem(pstate_fd, &key, &value); + stat_data[c].pstate[i] = value; + } + } +} + +/* + * This function is copied from 'idlestat' tool function + * idlestat_wake_all() in idlestate.c. + * + * It sets the self running task affinity to cpus one by one so can wake up + * the specific CPU to handle scheduling; this results in all cpus can be + * waken up once and produce ftrace event 'trace_cpu_idle'. + */ +static int cpu_stat_inject_cpu_idle_event(void) +{ + int rcpu, i, ret; + cpu_set_t cpumask; + cpu_set_t original_cpumask; + + ret = sysconf(_SC_NPROCESSORS_CONF); + if (ret < 0) + return -1; + + rcpu = sched_getcpu(); + if (rcpu < 0) + return -1; + + /* Keep track of the CPUs we will run on */ + sched_getaffinity(0, sizeof(original_cpumask), &original_cpumask); + + for (i = 0; i < ret; i++) { + + /* Pointless to wake up ourself */ + if (i == rcpu) + continue; + + /* Pointless to wake CPUs we will not run on */ + if (!CPU_ISSET(i, &original_cpumask)) + continue; + + CPU_ZERO(&cpumask); + CPU_SET(i, &cpumask); + + sched_setaffinity(0, sizeof(cpumask), &cpumask); + } + + /* Enable all the CPUs of the original mask */ + sched_setaffinity(0, sizeof(original_cpumask), &original_cpumask); + return 0; +} + +/* + * It's possible to have no any frequency change for long time and cannot + * get ftrace event 'trace_cpu_frequency' for long period, this introduces + * big deviation for pstate statistics. + * + * To solve this issue, below code forces to set 'scaling_max_freq' to 208MHz + * for triggering ftrace event 'trace_cpu_frequency' and then recovery back to + * the maximum frequency value 1.2GHz. + */ +static int cpu_stat_inject_cpu_frequency_event(void) +{ + int len, fd; + + fd = open(CPUFREQ_MAX_SYSFS_PATH, O_WRONLY); + if (fd < 0) { + printf("failed to open scaling_max_freq, errno=%d\n", errno); + return fd; + } + + len = write(fd, CPUFREQ_LOWEST_FREQ, strlen(CPUFREQ_LOWEST_FREQ)); + if (len < 0) { + printf("failed to open scaling_max_freq, errno=%d\n", errno); + goto err; + } + + len = write(fd, CPUFREQ_HIGHEST_FREQ, strlen(CPUFREQ_HIGHEST_FREQ)); + if (len < 0) { + printf("failed to open scaling_max_freq, errno=%d\n", errno); + goto err; + } + +err: + close(fd); + return len; +} + +static void int_exit(int sig) +{ + cpu_stat_inject_cpu_idle_event(); + cpu_stat_inject_cpu_frequency_event(); + cpu_stat_update(map_fd[1], map_fd[2]); + cpu_stat_print(); + exit(0); +} + +int main(int argc, char **argv) +{ + char filename[256]; + int ret; + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + + if (load_bpf_file(filename)) { + printf("%s", bpf_log_buf); + return 1; + } + + ret = cpu_stat_inject_cpu_idle_event(); + if (ret < 0) + return 1; + + ret = cpu_stat_inject_cpu_frequency_event(); + if (ret < 0) + return 1; + + signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); + + while (1) { + cpu_stat_update(map_fd[1], map_fd[2]); + cpu_stat_print(); + sleep(5); + } + + return 0; +} diff --git a/samples/bpf/xdp_redirect_user.c b/samples/bpf/xdp_redirect_user.c index d54e91eb6cbf..b701b5c21342 100644 --- a/samples/bpf/xdp_redirect_user.c +++ b/samples/bpf/xdp_redirect_user.c @@ -20,6 +20,7 @@ #include <string.h> #include <unistd.h> #include <libgen.h> +#include <sys/resource.h> #include "bpf_load.h" #include "bpf_util.h" @@ -75,6 +76,7 @@ static void usage(const char *prog) int main(int argc, char **argv) { + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; const char *optstr = "SN"; char filename[256]; int ret, opt, key = 0; @@ -98,6 +100,11 @@ int main(int argc, char **argv) return 1; } + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK)"); + return 1; + } + ifindex_in = strtoul(argv[optind], NULL, 0); ifindex_out = strtoul(argv[optind + 1], NULL, 0); printf("input: %d output: %d\n", ifindex_in, ifindex_out); diff --git a/samples/sockmap/Makefile b/samples/sockmap/Makefile index 73f1da4d116c..9bf2881bd11b 100644 --- a/samples/sockmap/Makefile +++ b/samples/sockmap/Makefile @@ -2,7 +2,7 @@ hostprogs-y := sockmap # Libbpf dependencies -LIBBPF := ../../tools/lib/bpf/bpf.o +LIBBPF := ../../tools/lib/bpf/bpf.o ../../tools/lib/bpf/nlattr.o HOSTCFLAGS += -I$(objtree)/usr/include HOSTCFLAGS += -I$(srctree)/tools/lib/ diff --git a/samples/sockmap/sockmap_user.c b/samples/sockmap/sockmap_user.c index 7c25c0c112bc..95a54a89a532 100644 --- a/samples/sockmap/sockmap_user.c +++ b/samples/sockmap/sockmap_user.c @@ -566,6 +566,7 @@ run: else fprintf(stderr, "unknown test\n"); out: + bpf_prog_detach2(prog_fd[2], cg_fd, BPF_CGROUP_SOCK_OPS); close(s1); close(s2); close(p1); diff --git a/security/integrity/digsig.c b/security/integrity/digsig.c index 6f9e4ce568cd..9bb0a7f2863e 100644 --- a/security/integrity/digsig.c +++ b/security/integrity/digsig.c @@ -18,6 +18,7 @@ #include <linux/cred.h> #include <linux/key-type.h> #include <linux/digsig.h> +#include <linux/vmalloc.h> #include <crypto/public_key.h> #include <keys/system_keyring.h> diff --git a/security/keys/big_key.c b/security/keys/big_key.c index 929e14978c42..fa728f662a6f 100644 --- a/security/keys/big_key.c +++ b/security/keys/big_key.c @@ -22,6 +22,13 @@ #include <keys/big_key-type.h> #include <crypto/aead.h> +struct big_key_buf { + unsigned int nr_pages; + void *virt; + struct scatterlist *sg; + struct page *pages[]; +}; + /* * Layout of key payload words. */ @@ -91,10 +98,9 @@ static DEFINE_MUTEX(big_key_aead_lock); /* * Encrypt/decrypt big_key data */ -static int big_key_crypt(enum big_key_op op, u8 *data, size_t datalen, u8 *key) +static int big_key_crypt(enum big_key_op op, struct big_key_buf *buf, size_t datalen, u8 *key) { int ret; - struct scatterlist sgio; struct aead_request *aead_req; /* We always use a zero nonce. The reason we can get away with this is * because we're using a different randomly generated key for every @@ -109,8 +115,7 @@ static int big_key_crypt(enum big_key_op op, u8 *data, size_t datalen, u8 *key) return -ENOMEM; memset(zero_nonce, 0, sizeof(zero_nonce)); - sg_init_one(&sgio, data, datalen + (op == BIG_KEY_ENC ? ENC_AUTHTAG_SIZE : 0)); - aead_request_set_crypt(aead_req, &sgio, &sgio, datalen, zero_nonce); + aead_request_set_crypt(aead_req, buf->sg, buf->sg, datalen, zero_nonce); aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL); aead_request_set_ad(aead_req, 0); @@ -130,21 +135,81 @@ error: } /* + * Free up the buffer. + */ +static void big_key_free_buffer(struct big_key_buf *buf) +{ + unsigned int i; + + if (buf->virt) { + memset(buf->virt, 0, buf->nr_pages * PAGE_SIZE); + vunmap(buf->virt); + } + + for (i = 0; i < buf->nr_pages; i++) + if (buf->pages[i]) + __free_page(buf->pages[i]); + + kfree(buf); +} + +/* + * Allocate a buffer consisting of a set of pages with a virtual mapping + * applied over them. + */ +static void *big_key_alloc_buffer(size_t len) +{ + struct big_key_buf *buf; + unsigned int npg = (len + PAGE_SIZE - 1) >> PAGE_SHIFT; + unsigned int i, l; + + buf = kzalloc(sizeof(struct big_key_buf) + + sizeof(struct page) * npg + + sizeof(struct scatterlist) * npg, + GFP_KERNEL); + if (!buf) + return NULL; + + buf->nr_pages = npg; + buf->sg = (void *)(buf->pages + npg); + sg_init_table(buf->sg, npg); + + for (i = 0; i < buf->nr_pages; i++) { + buf->pages[i] = alloc_page(GFP_KERNEL); + if (!buf->pages[i]) + goto nomem; + + l = min_t(size_t, len, PAGE_SIZE); + sg_set_page(&buf->sg[i], buf->pages[i], l, 0); + len -= l; + } + + buf->virt = vmap(buf->pages, buf->nr_pages, VM_MAP, PAGE_KERNEL); + if (!buf->virt) + goto nomem; + + return buf; + +nomem: + big_key_free_buffer(buf); + return NULL; +} + +/* * Preparse a big key */ int big_key_preparse(struct key_preparsed_payload *prep) { + struct big_key_buf *buf; struct path *path = (struct path *)&prep->payload.data[big_key_path]; struct file *file; u8 *enckey; - u8 *data = NULL; ssize_t written; - size_t datalen = prep->datalen; + size_t datalen = prep->datalen, enclen = datalen + ENC_AUTHTAG_SIZE; int ret; - ret = -EINVAL; if (datalen <= 0 || datalen > 1024 * 1024 || !prep->data) - goto error; + return -EINVAL; /* Set an arbitrary quota */ prep->quotalen = 16; @@ -157,13 +222,12 @@ int big_key_preparse(struct key_preparsed_payload *prep) * * File content is stored encrypted with randomly generated key. */ - size_t enclen = datalen + ENC_AUTHTAG_SIZE; loff_t pos = 0; - data = kmalloc(enclen, GFP_KERNEL); - if (!data) + buf = big_key_alloc_buffer(enclen); + if (!buf) return -ENOMEM; - memcpy(data, prep->data, datalen); + memcpy(buf->virt, prep->data, datalen); /* generate random key */ enckey = kmalloc(ENC_KEY_SIZE, GFP_KERNEL); @@ -176,7 +240,7 @@ int big_key_preparse(struct key_preparsed_payload *prep) goto err_enckey; /* encrypt aligned data */ - ret = big_key_crypt(BIG_KEY_ENC, data, datalen, enckey); + ret = big_key_crypt(BIG_KEY_ENC, buf, datalen, enckey); if (ret) goto err_enckey; @@ -187,7 +251,7 @@ int big_key_preparse(struct key_preparsed_payload *prep) goto err_enckey; } - written = kernel_write(file, data, enclen, &pos); + written = kernel_write(file, buf->virt, enclen, &pos); if (written != enclen) { ret = written; if (written >= 0) @@ -202,7 +266,7 @@ int big_key_preparse(struct key_preparsed_payload *prep) *path = file->f_path; path_get(path); fput(file); - kzfree(data); + big_key_free_buffer(buf); } else { /* Just store the data in a buffer */ void *data = kmalloc(datalen, GFP_KERNEL); @@ -220,7 +284,7 @@ err_fput: err_enckey: kzfree(enckey); error: - kzfree(data); + big_key_free_buffer(buf); return ret; } @@ -298,15 +362,15 @@ long big_key_read(const struct key *key, char __user *buffer, size_t buflen) return datalen; if (datalen > BIG_KEY_FILE_THRESHOLD) { + struct big_key_buf *buf; struct path *path = (struct path *)&key->payload.data[big_key_path]; struct file *file; - u8 *data; u8 *enckey = (u8 *)key->payload.data[big_key_data]; size_t enclen = datalen + ENC_AUTHTAG_SIZE; loff_t pos = 0; - data = kmalloc(enclen, GFP_KERNEL); - if (!data) + buf = big_key_alloc_buffer(enclen); + if (!buf) return -ENOMEM; file = dentry_open(path, O_RDONLY, current_cred()); @@ -316,26 +380,26 @@ long big_key_read(const struct key *key, char __user *buffer, size_t buflen) } /* read file to kernel and decrypt */ - ret = kernel_read(file, data, enclen, &pos); + ret = kernel_read(file, buf->virt, enclen, &pos); if (ret >= 0 && ret != enclen) { ret = -EIO; goto err_fput; } - ret = big_key_crypt(BIG_KEY_DEC, data, enclen, enckey); + ret = big_key_crypt(BIG_KEY_DEC, buf, enclen, enckey); if (ret) goto err_fput; ret = datalen; /* copy decrypted data to user */ - if (copy_to_user(buffer, data, datalen) != 0) + if (copy_to_user(buffer, buf->virt, datalen) != 0) ret = -EFAULT; err_fput: fput(file); error: - kzfree(data); + big_key_free_buffer(buf); } else { ret = datalen; if (copy_to_user(buffer, key->payload.data[big_key_data], diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 8644d864e3c1..b4d7b6242a40 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -6743,6 +6743,7 @@ static void __net_exit selinux_nf_unregister(struct net *net) static struct pernet_operations selinux_net_ops = { .init = selinux_nf_register, .exit = selinux_nf_unregister, + .async = true, }; static int __init selinux_nf_ip_init(void) diff --git a/security/smack/smack_netfilter.c b/security/smack/smack_netfilter.c index e36d17835d4f..3f29c03162ca 100644 --- a/security/smack/smack_netfilter.c +++ b/security/smack/smack_netfilter.c @@ -89,6 +89,7 @@ static void __net_exit smack_nf_unregister(struct net *net) static struct pernet_operations smack_net_ops = { .init = smack_nf_register, .exit = smack_nf_unregister, + .async = true, }; static int __init smack_nf_ip_init(void) diff --git a/security/tomoyo/network.c b/security/tomoyo/network.c index cd6932e5225c..9094f4b3b367 100644 --- a/security/tomoyo/network.c +++ b/security/tomoyo/network.c @@ -655,10 +655,11 @@ int tomoyo_socket_listen_permission(struct socket *sock) return 0; { const int error = sock->ops->getname(sock, (struct sockaddr *) - &addr, &addr_len, 0); + &addr, 0); - if (error) + if (error < 0) return error; + addr_len = error; } address.protocol = type; address.operation = TOMOYO_NETWORK_LISTEN; diff --git a/sound/ac97/Kconfig b/sound/ac97/Kconfig index f8a64e15e5bf..baa5f8ef89d2 100644 --- a/sound/ac97/Kconfig +++ b/sound/ac97/Kconfig @@ -5,7 +5,6 @@ config AC97_BUS_NEW tristate - select AC97 help This is the new AC97 bus type, successor of AC97_BUS. The ported drivers which benefit from the AC97 automatic probing should "select" diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 60db32785f62..04d4db44fae5 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -1003,7 +1003,7 @@ static ssize_t snd_seq_write(struct file *file, const char __user *buf, { struct snd_seq_client *client = file->private_data; int written = 0, len; - int err = -EINVAL; + int err; struct snd_seq_event event; if (!(snd_seq_file_flags(file) & SNDRV_SEQ_LFLG_OUTPUT)) @@ -1018,11 +1018,15 @@ static ssize_t snd_seq_write(struct file *file, const char __user *buf, /* allocate the pool now if the pool is not allocated yet */ if (client->pool->size > 0 && !snd_seq_write_pool_allocated(client)) { - if (snd_seq_pool_init(client->pool) < 0) + mutex_lock(&client->ioctl_mutex); + err = snd_seq_pool_init(client->pool); + mutex_unlock(&client->ioctl_mutex); + if (err < 0) return -ENOMEM; } /* only process whole events */ + err = -EINVAL; while (count >= sizeof(struct snd_seq_event)) { /* Read in the event header from the user */ len = sizeof(event); diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 23475888192b..ce28f7ce64e6 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -3465,6 +3465,19 @@ static void alc269_fixup_pincfg_no_hp_to_lineout(struct hda_codec *codec, spec->parse_flags = HDA_PINCFG_NO_HP_FIXUP; } +static void alc269_fixup_pincfg_U7x7_headset_mic(struct hda_codec *codec, + const struct hda_fixup *fix, + int action) +{ + unsigned int cfg_headphone = snd_hda_codec_get_pincfg(codec, 0x21); + unsigned int cfg_headset_mic = snd_hda_codec_get_pincfg(codec, 0x19); + + if (cfg_headphone && cfg_headset_mic == 0x411111f0) + snd_hda_codec_set_pincfg(codec, 0x19, + (cfg_headphone & ~AC_DEFCFG_DEVICE) | + (AC_JACK_MIC_IN << AC_DEFCFG_DEVICE_SHIFT)); +} + static void alc269_fixup_hweq(struct hda_codec *codec, const struct hda_fixup *fix, int action) { @@ -4972,6 +4985,28 @@ static void alc_fixup_tpt440_dock(struct hda_codec *codec, } } +static void alc_fixup_tpt470_dock(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + static const struct hda_pintbl pincfgs[] = { + { 0x17, 0x21211010 }, /* dock headphone */ + { 0x19, 0x21a11010 }, /* dock mic */ + { } + }; + struct alc_spec *spec = codec->spec; + + if (action == HDA_FIXUP_ACT_PRE_PROBE) { + spec->parse_flags = HDA_PINCFG_NO_HP_FIXUP; + /* Enable DOCK device */ + snd_hda_codec_write(codec, 0x17, 0, + AC_VERB_SET_CONFIG_DEFAULT_BYTES_3, 0); + /* Enable DOCK device */ + snd_hda_codec_write(codec, 0x19, 0, + AC_VERB_SET_CONFIG_DEFAULT_BYTES_3, 0); + snd_hda_apply_pincfgs(codec, pincfgs); + } +} + static void alc_shutup_dell_xps13(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; @@ -5351,6 +5386,7 @@ enum { ALC269_FIXUP_LIFEBOOK_EXTMIC, ALC269_FIXUP_LIFEBOOK_HP_PIN, ALC269_FIXUP_LIFEBOOK_NO_HP_TO_LINEOUT, + ALC255_FIXUP_LIFEBOOK_U7x7_HEADSET_MIC, ALC269_FIXUP_AMIC, ALC269_FIXUP_DMIC, ALC269VB_FIXUP_AMIC, @@ -5446,6 +5482,7 @@ enum { ALC700_FIXUP_INTEL_REFERENCE, ALC274_FIXUP_DELL_BIND_DACS, ALC274_FIXUP_DELL_AIO_LINEOUT_VERB, + ALC298_FIXUP_TPT470_DOCK, }; static const struct hda_fixup alc269_fixups[] = { @@ -5556,6 +5593,10 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc269_fixup_pincfg_no_hp_to_lineout, }, + [ALC255_FIXUP_LIFEBOOK_U7x7_HEADSET_MIC] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc269_fixup_pincfg_U7x7_headset_mic, + }, [ALC269_FIXUP_AMIC] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -6271,6 +6312,12 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC274_FIXUP_DELL_BIND_DACS }, + [ALC298_FIXUP_TPT470_DOCK] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_tpt470_dock, + .chained = true, + .chain_id = ALC293_FIXUP_LENOVO_SPK_NOISE + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -6321,6 +6368,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x075d, "Dell AIO", ALC298_FIXUP_SPK_VOLUME), SND_PCI_QUIRK(0x1028, 0x0798, "Dell Inspiron 17 7000 Gaming", ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER), SND_PCI_QUIRK(0x1028, 0x082a, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE), + SND_PCI_QUIRK(0x1028, 0x084b, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB), + SND_PCI_QUIRK(0x1028, 0x084e, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB), SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2), @@ -6422,6 +6471,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x10cf, 0x159f, "Lifebook E780", ALC269_FIXUP_LIFEBOOK_NO_HP_TO_LINEOUT), SND_PCI_QUIRK(0x10cf, 0x15dc, "Lifebook T731", ALC269_FIXUP_LIFEBOOK_HP_PIN), SND_PCI_QUIRK(0x10cf, 0x1757, "Lifebook E752", ALC269_FIXUP_LIFEBOOK_HP_PIN), + SND_PCI_QUIRK(0x10cf, 0x1629, "Lifebook U7x7", ALC255_FIXUP_LIFEBOOK_U7x7_HEADSET_MIC), SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC), SND_PCI_QUIRK(0x10ec, 0x10f2, "Intel Reference board", ALC700_FIXUP_INTEL_REFERENCE), SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC), @@ -6450,8 +6500,16 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x2218, "Thinkpad X1 Carbon 2nd", ALC292_FIXUP_TPT440_DOCK), SND_PCI_QUIRK(0x17aa, 0x2223, "ThinkPad T550", ALC292_FIXUP_TPT440_DOCK), SND_PCI_QUIRK(0x17aa, 0x2226, "ThinkPad X250", ALC292_FIXUP_TPT440_DOCK), + SND_PCI_QUIRK(0x17aa, 0x222d, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), + SND_PCI_QUIRK(0x17aa, 0x222e, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x2231, "Thinkpad T560", ALC292_FIXUP_TPT460), SND_PCI_QUIRK(0x17aa, 0x2233, "Thinkpad", ALC292_FIXUP_TPT460), + SND_PCI_QUIRK(0x17aa, 0x2245, "Thinkpad T470", ALC298_FIXUP_TPT470_DOCK), + SND_PCI_QUIRK(0x17aa, 0x2246, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), + SND_PCI_QUIRK(0x17aa, 0x2247, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), + SND_PCI_QUIRK(0x17aa, 0x224b, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), + SND_PCI_QUIRK(0x17aa, 0x224c, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), + SND_PCI_QUIRK(0x17aa, 0x224d, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x310c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION), @@ -6472,7 +6530,12 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x5050, "Thinkpad T560p", ALC292_FIXUP_TPT460), SND_PCI_QUIRK(0x17aa, 0x5051, "Thinkpad L460", ALC292_FIXUP_TPT460), SND_PCI_QUIRK(0x17aa, 0x5053, "Thinkpad T460", ALC292_FIXUP_TPT460), + SND_PCI_QUIRK(0x17aa, 0x505d, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), + SND_PCI_QUIRK(0x17aa, 0x505f, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), + SND_PCI_QUIRK(0x17aa, 0x5062, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x5109, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), + SND_PCI_QUIRK(0x17aa, 0x511e, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), + SND_PCI_QUIRK(0x17aa, 0x511f, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x3bf8, "Quanta FL1", ALC269_FIXUP_PCM_44K), SND_PCI_QUIRK(0x17aa, 0x9e54, "LENOVO NB", ALC269_FIXUP_LENOVO_EAPD), SND_PCI_QUIRK(0x1b7d, 0xa831, "Ordissimo EVE2 ", ALC269VB_FIXUP_ORDISSIMO_EVE2), /* Also known as Malata PC-B1303 */ @@ -6735,6 +6798,11 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x14, 0x90170110}, {0x21, 0x02211020}), SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, + {0x12, 0x90a60130}, + {0x14, 0x90170110}, + {0x14, 0x01011020}, + {0x21, 0x0221101f}), + SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, ALC256_STANDARD_PINS), SND_HDA_PIN_QUIRK(0x10ec0256, 0x1043, "ASUS", ALC256_FIXUP_ASUS_MIC, {0x14, 0x90170110}, @@ -6803,6 +6871,10 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x12, 0x90a60120}, {0x14, 0x90170110}, {0x21, 0x0321101f}), + SND_HDA_PIN_QUIRK(0x10ec0289, 0x1028, "Dell", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, + {0x12, 0xb7a60130}, + {0x14, 0x90170110}, + {0x21, 0x04211020}), SND_HDA_PIN_QUIRK(0x10ec0290, 0x103c, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1, ALC290_STANDARD_PINS, {0x15, 0x04211040}, diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 9afb8ab524c7..06b22624ab7a 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -347,17 +347,20 @@ static int get_ctl_value_v2(struct usb_mixer_elem_info *cval, int request, int validx, int *value_ret) { struct snd_usb_audio *chip = cval->head.mixer->chip; - unsigned char buf[4 + 3 * sizeof(__u32)]; /* enough space for one range */ + /* enough space for one range */ + unsigned char buf[sizeof(__u16) + 3 * sizeof(__u32)]; unsigned char *val; - int idx = 0, ret, size; + int idx = 0, ret, val_size, size; __u8 bRequest; + val_size = uac2_ctl_value_size(cval->val_type); + if (request == UAC_GET_CUR) { bRequest = UAC2_CS_CUR; - size = uac2_ctl_value_size(cval->val_type); + size = val_size; } else { bRequest = UAC2_CS_RANGE; - size = sizeof(buf); + size = sizeof(__u16) + 3 * val_size; } memset(buf, 0, sizeof(buf)); @@ -390,16 +393,17 @@ error: val = buf + sizeof(__u16); break; case UAC_GET_MAX: - val = buf + sizeof(__u16) * 2; + val = buf + sizeof(__u16) + val_size; break; case UAC_GET_RES: - val = buf + sizeof(__u16) * 3; + val = buf + sizeof(__u16) + val_size * 2; break; default: return -EINVAL; } - *value_ret = convert_signed_value(cval, snd_usb_combine_bytes(val, sizeof(__u16))); + *value_ret = convert_signed_value(cval, + snd_usb_combine_bytes(val, val_size)); return 0; } diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index b9c9a19f9588..3cbfae6604f9 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -357,6 +357,15 @@ static int set_sync_ep_implicit_fb_quirk(struct snd_usb_substream *subs, alts = &iface->altsetting[1]; goto add_sync_ep; + case USB_ID(0x1397, 0x0002): + ep = 0x81; + iface = usb_ifnum_to_if(dev, 1); + + if (!iface || iface->num_altsetting == 0) + return -EINVAL; + + alts = &iface->altsetting[1]; + goto add_sync_ep; } if (attr == USB_ENDPOINT_SYNC_ASYNC && diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index a66ef5777887..ea8f3de92fa4 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1363,8 +1363,11 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip, return SNDRV_PCM_FMTBIT_DSD_U32_BE; break; - /* Amanero Combo384 USB interface with native DSD support */ - case USB_ID(0x16d0, 0x071a): + /* Amanero Combo384 USB based DACs with native DSD support */ + case USB_ID(0x16d0, 0x071a): /* Amanero - Combo384 */ + case USB_ID(0x2ab6, 0x0004): /* T+A DAC8DSD-V2.0, MP1000E-V2.0, MP2000R-V2.0, MP2500R-V2.0, MP3100HV-V2.0 */ + case USB_ID(0x2ab6, 0x0005): /* T+A USB HD Audio 1 */ + case USB_ID(0x2ab6, 0x0006): /* T+A USB HD Audio 2 */ if (fp->altsetting == 2) { switch (le16_to_cpu(chip->dev->descriptor.bcdDevice)) { case 0x199: diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h index 637b7263cb86..833ed9a16adf 100644 --- a/tools/arch/powerpc/include/uapi/asm/kvm.h +++ b/tools/arch/powerpc/include/uapi/asm/kvm.h @@ -632,6 +632,8 @@ struct kvm_ppc_cpu_char { #define KVM_REG_PPC_TIDR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbc) #define KVM_REG_PPC_PSSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbd) +#define KVM_REG_PPC_DEC_EXPIRY (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbe) + /* Transactional Memory checkpointed state: * This is all GPRs, all VSX regs and a subset of SPRs */ diff --git a/tools/arch/s390/include/uapi/asm/unistd.h b/tools/arch/s390/include/uapi/asm/unistd.h deleted file mode 100644 index 725120939051..000000000000 --- a/tools/arch/s390/include/uapi/asm/unistd.h +++ /dev/null @@ -1,412 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* - * S390 version - * - * Derived from "include/asm-i386/unistd.h" - */ - -#ifndef _UAPI_ASM_S390_UNISTD_H_ -#define _UAPI_ASM_S390_UNISTD_H_ - -/* - * This file contains the system call numbers. - */ - -#define __NR_exit 1 -#define __NR_fork 2 -#define __NR_read 3 -#define __NR_write 4 -#define __NR_open 5 -#define __NR_close 6 -#define __NR_restart_syscall 7 -#define __NR_creat 8 -#define __NR_link 9 -#define __NR_unlink 10 -#define __NR_execve 11 -#define __NR_chdir 12 -#define __NR_mknod 14 -#define __NR_chmod 15 -#define __NR_lseek 19 -#define __NR_getpid 20 -#define __NR_mount 21 -#define __NR_umount 22 -#define __NR_ptrace 26 -#define __NR_alarm 27 -#define __NR_pause 29 -#define __NR_utime 30 -#define __NR_access 33 -#define __NR_nice 34 -#define __NR_sync 36 -#define __NR_kill 37 -#define __NR_rename 38 -#define __NR_mkdir 39 -#define __NR_rmdir 40 -#define __NR_dup 41 -#define __NR_pipe 42 -#define __NR_times 43 -#define __NR_brk 45 -#define __NR_signal 48 -#define __NR_acct 51 -#define __NR_umount2 52 -#define __NR_ioctl 54 -#define __NR_fcntl 55 -#define __NR_setpgid 57 -#define __NR_umask 60 -#define __NR_chroot 61 -#define __NR_ustat 62 -#define __NR_dup2 63 -#define __NR_getppid 64 -#define __NR_getpgrp 65 -#define __NR_setsid 66 -#define __NR_sigaction 67 -#define __NR_sigsuspend 72 -#define __NR_sigpending 73 -#define __NR_sethostname 74 -#define __NR_setrlimit 75 -#define __NR_getrusage 77 -#define __NR_gettimeofday 78 -#define __NR_settimeofday 79 -#define __NR_symlink 83 -#define __NR_readlink 85 -#define __NR_uselib 86 -#define __NR_swapon 87 -#define __NR_reboot 88 -#define __NR_readdir 89 -#define __NR_mmap 90 -#define __NR_munmap 91 -#define __NR_truncate 92 -#define __NR_ftruncate 93 -#define __NR_fchmod 94 -#define __NR_getpriority 96 -#define __NR_setpriority 97 -#define __NR_statfs 99 -#define __NR_fstatfs 100 -#define __NR_socketcall 102 -#define __NR_syslog 103 -#define __NR_setitimer 104 -#define __NR_getitimer 105 -#define __NR_stat 106 -#define __NR_lstat 107 -#define __NR_fstat 108 -#define __NR_lookup_dcookie 110 -#define __NR_vhangup 111 -#define __NR_idle 112 -#define __NR_wait4 114 -#define __NR_swapoff 115 -#define __NR_sysinfo 116 -#define __NR_ipc 117 -#define __NR_fsync 118 -#define __NR_sigreturn 119 -#define __NR_clone 120 -#define __NR_setdomainname 121 -#define __NR_uname 122 -#define __NR_adjtimex 124 -#define __NR_mprotect 125 -#define __NR_sigprocmask 126 -#define __NR_create_module 127 -#define __NR_init_module 128 -#define __NR_delete_module 129 -#define __NR_get_kernel_syms 130 -#define __NR_quotactl 131 -#define __NR_getpgid 132 -#define __NR_fchdir 133 -#define __NR_bdflush 134 -#define __NR_sysfs 135 -#define __NR_personality 136 -#define __NR_afs_syscall 137 /* Syscall for Andrew File System */ -#define __NR_getdents 141 -#define __NR_flock 143 -#define __NR_msync 144 -#define __NR_readv 145 -#define __NR_writev 146 -#define __NR_getsid 147 -#define __NR_fdatasync 148 -#define __NR__sysctl 149 -#define __NR_mlock 150 -#define __NR_munlock 151 -#define __NR_mlockall 152 -#define __NR_munlockall 153 -#define __NR_sched_setparam 154 -#define __NR_sched_getparam 155 -#define __NR_sched_setscheduler 156 -#define __NR_sched_getscheduler 157 -#define __NR_sched_yield 158 -#define __NR_sched_get_priority_max 159 -#define __NR_sched_get_priority_min 160 -#define __NR_sched_rr_get_interval 161 -#define __NR_nanosleep 162 -#define __NR_mremap 163 -#define __NR_query_module 167 -#define __NR_poll 168 -#define __NR_nfsservctl 169 -#define __NR_prctl 172 -#define __NR_rt_sigreturn 173 -#define __NR_rt_sigaction 174 -#define __NR_rt_sigprocmask 175 -#define __NR_rt_sigpending 176 -#define __NR_rt_sigtimedwait 177 -#define __NR_rt_sigqueueinfo 178 -#define __NR_rt_sigsuspend 179 -#define __NR_pread64 180 -#define __NR_pwrite64 181 -#define __NR_getcwd 183 -#define __NR_capget 184 -#define __NR_capset 185 -#define __NR_sigaltstack 186 -#define __NR_sendfile 187 -#define __NR_getpmsg 188 -#define __NR_putpmsg 189 -#define __NR_vfork 190 -#define __NR_pivot_root 217 -#define __NR_mincore 218 -#define __NR_madvise 219 -#define __NR_getdents64 220 -#define __NR_readahead 222 -#define __NR_setxattr 224 -#define __NR_lsetxattr 225 -#define __NR_fsetxattr 226 -#define __NR_getxattr 227 -#define __NR_lgetxattr 228 -#define __NR_fgetxattr 229 -#define __NR_listxattr 230 -#define __NR_llistxattr 231 -#define __NR_flistxattr 232 -#define __NR_removexattr 233 -#define __NR_lremovexattr 234 -#define __NR_fremovexattr 235 -#define __NR_gettid 236 -#define __NR_tkill 237 -#define __NR_futex 238 -#define __NR_sched_setaffinity 239 -#define __NR_sched_getaffinity 240 -#define __NR_tgkill 241 -/* Number 242 is reserved for tux */ -#define __NR_io_setup 243 -#define __NR_io_destroy 244 -#define __NR_io_getevents 245 -#define __NR_io_submit 246 -#define __NR_io_cancel 247 -#define __NR_exit_group 248 -#define __NR_epoll_create 249 -#define __NR_epoll_ctl 250 -#define __NR_epoll_wait 251 -#define __NR_set_tid_address 252 -#define __NR_fadvise64 253 -#define __NR_timer_create 254 -#define __NR_timer_settime 255 -#define __NR_timer_gettime 256 -#define __NR_timer_getoverrun 257 -#define __NR_timer_delete 258 -#define __NR_clock_settime 259 -#define __NR_clock_gettime 260 -#define __NR_clock_getres 261 -#define __NR_clock_nanosleep 262 -/* Number 263 is reserved for vserver */ -#define __NR_statfs64 265 -#define __NR_fstatfs64 266 -#define __NR_remap_file_pages 267 -#define __NR_mbind 268 -#define __NR_get_mempolicy 269 -#define __NR_set_mempolicy 270 -#define __NR_mq_open 271 -#define __NR_mq_unlink 272 -#define __NR_mq_timedsend 273 -#define __NR_mq_timedreceive 274 -#define __NR_mq_notify 275 -#define __NR_mq_getsetattr 276 -#define __NR_kexec_load 277 -#define __NR_add_key 278 -#define __NR_request_key 279 -#define __NR_keyctl 280 -#define __NR_waitid 281 -#define __NR_ioprio_set 282 -#define __NR_ioprio_get 283 -#define __NR_inotify_init 284 -#define __NR_inotify_add_watch 285 -#define __NR_inotify_rm_watch 286 -#define __NR_migrate_pages 287 -#define __NR_openat 288 -#define __NR_mkdirat 289 -#define __NR_mknodat 290 -#define __NR_fchownat 291 -#define __NR_futimesat 292 -#define __NR_unlinkat 294 -#define __NR_renameat 295 -#define __NR_linkat 296 -#define __NR_symlinkat 297 -#define __NR_readlinkat 298 -#define __NR_fchmodat 299 -#define __NR_faccessat 300 -#define __NR_pselect6 301 -#define __NR_ppoll 302 -#define __NR_unshare 303 -#define __NR_set_robust_list 304 -#define __NR_get_robust_list 305 -#define __NR_splice 306 -#define __NR_sync_file_range 307 -#define __NR_tee 308 -#define __NR_vmsplice 309 -#define __NR_move_pages 310 -#define __NR_getcpu 311 -#define __NR_epoll_pwait 312 -#define __NR_utimes 313 -#define __NR_fallocate 314 -#define __NR_utimensat 315 -#define __NR_signalfd 316 -#define __NR_timerfd 317 -#define __NR_eventfd 318 -#define __NR_timerfd_create 319 -#define __NR_timerfd_settime 320 -#define __NR_timerfd_gettime 321 -#define __NR_signalfd4 322 -#define __NR_eventfd2 323 -#define __NR_inotify_init1 324 -#define __NR_pipe2 325 -#define __NR_dup3 326 -#define __NR_epoll_create1 327 -#define __NR_preadv 328 -#define __NR_pwritev 329 -#define __NR_rt_tgsigqueueinfo 330 -#define __NR_perf_event_open 331 -#define __NR_fanotify_init 332 -#define __NR_fanotify_mark 333 -#define __NR_prlimit64 334 -#define __NR_name_to_handle_at 335 -#define __NR_open_by_handle_at 336 -#define __NR_clock_adjtime 337 -#define __NR_syncfs 338 -#define __NR_setns 339 -#define __NR_process_vm_readv 340 -#define __NR_process_vm_writev 341 -#define __NR_s390_runtime_instr 342 -#define __NR_kcmp 343 -#define __NR_finit_module 344 -#define __NR_sched_setattr 345 -#define __NR_sched_getattr 346 -#define __NR_renameat2 347 -#define __NR_seccomp 348 -#define __NR_getrandom 349 -#define __NR_memfd_create 350 -#define __NR_bpf 351 -#define __NR_s390_pci_mmio_write 352 -#define __NR_s390_pci_mmio_read 353 -#define __NR_execveat 354 -#define __NR_userfaultfd 355 -#define __NR_membarrier 356 -#define __NR_recvmmsg 357 -#define __NR_sendmmsg 358 -#define __NR_socket 359 -#define __NR_socketpair 360 -#define __NR_bind 361 -#define __NR_connect 362 -#define __NR_listen 363 -#define __NR_accept4 364 -#define __NR_getsockopt 365 -#define __NR_setsockopt 366 -#define __NR_getsockname 367 -#define __NR_getpeername 368 -#define __NR_sendto 369 -#define __NR_sendmsg 370 -#define __NR_recvfrom 371 -#define __NR_recvmsg 372 -#define __NR_shutdown 373 -#define __NR_mlock2 374 -#define __NR_copy_file_range 375 -#define __NR_preadv2 376 -#define __NR_pwritev2 377 -#define __NR_s390_guarded_storage 378 -#define __NR_statx 379 -#define __NR_s390_sthyi 380 -#define NR_syscalls 381 - -/* - * There are some system calls that are not present on 64 bit, some - * have a different name although they do the same (e.g. __NR_chown32 - * is __NR_chown on 64 bit). - */ -#ifndef __s390x__ - -#define __NR_time 13 -#define __NR_lchown 16 -#define __NR_setuid 23 -#define __NR_getuid 24 -#define __NR_stime 25 -#define __NR_setgid 46 -#define __NR_getgid 47 -#define __NR_geteuid 49 -#define __NR_getegid 50 -#define __NR_setreuid 70 -#define __NR_setregid 71 -#define __NR_getrlimit 76 -#define __NR_getgroups 80 -#define __NR_setgroups 81 -#define __NR_fchown 95 -#define __NR_ioperm 101 -#define __NR_setfsuid 138 -#define __NR_setfsgid 139 -#define __NR__llseek 140 -#define __NR__newselect 142 -#define __NR_setresuid 164 -#define __NR_getresuid 165 -#define __NR_setresgid 170 -#define __NR_getresgid 171 -#define __NR_chown 182 -#define __NR_ugetrlimit 191 /* SuS compliant getrlimit */ -#define __NR_mmap2 192 -#define __NR_truncate64 193 -#define __NR_ftruncate64 194 -#define __NR_stat64 195 -#define __NR_lstat64 196 -#define __NR_fstat64 197 -#define __NR_lchown32 198 -#define __NR_getuid32 199 -#define __NR_getgid32 200 -#define __NR_geteuid32 201 -#define __NR_getegid32 202 -#define __NR_setreuid32 203 -#define __NR_setregid32 204 -#define __NR_getgroups32 205 -#define __NR_setgroups32 206 -#define __NR_fchown32 207 -#define __NR_setresuid32 208 -#define __NR_getresuid32 209 -#define __NR_setresgid32 210 -#define __NR_getresgid32 211 -#define __NR_chown32 212 -#define __NR_setuid32 213 -#define __NR_setgid32 214 -#define __NR_setfsuid32 215 -#define __NR_setfsgid32 216 -#define __NR_fcntl64 221 -#define __NR_sendfile64 223 -#define __NR_fadvise64_64 264 -#define __NR_fstatat64 293 - -#else - -#define __NR_select 142 -#define __NR_getrlimit 191 /* SuS compliant getrlimit */ -#define __NR_lchown 198 -#define __NR_getuid 199 -#define __NR_getgid 200 -#define __NR_geteuid 201 -#define __NR_getegid 202 -#define __NR_setreuid 203 -#define __NR_setregid 204 -#define __NR_getgroups 205 -#define __NR_setgroups 206 -#define __NR_fchown 207 -#define __NR_setresuid 208 -#define __NR_getresuid 209 -#define __NR_setresgid 210 -#define __NR_getresgid 211 -#define __NR_chown 212 -#define __NR_setuid 213 -#define __NR_setgid 214 -#define __NR_setfsuid 215 -#define __NR_setfsgid 216 -#define __NR_newfstatat 293 - -#endif - -#endif /* _UAPI_ASM_S390_UNISTD_H_ */ diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 1d9199e1c2ad..0dfe4d3f74e2 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -210,6 +210,7 @@ #define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ #define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */ +#define X86_FEATURE_SEV ( 7*32+20) /* AMD Secure Encrypted Virtualization */ #define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index 3a0396d87c42..185acfa229b5 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -244,7 +244,7 @@ static int do_batch(int argc, char **argv) } if (errno && errno != ENOENT) { - perror("reading batch file failed"); + p_err("reading batch file failed: %s", strerror(errno)); err = -1; } else { p_info("processed %d lines", lines); diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index e8e2baaf93c2..e549e329be82 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -774,6 +774,9 @@ static int do_dump(int argc, char **argv) n < 0 ? strerror(errno) : "short write"); goto err_free; } + + if (json_output) + jsonw_null(json_wtr); } else { if (member_len == &info.jited_prog_len) { const char *name = NULL; diff --git a/tools/cgroup/Makefile b/tools/cgroup/Makefile index 860fa151640a..ffca068e4a76 100644 --- a/tools/cgroup/Makefile +++ b/tools/cgroup/Makefile @@ -1,7 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for cgroup tools -CC = $(CROSS_COMPILE)gcc CFLAGS = -Wall -Wextra all: cgroup_event_listener diff --git a/tools/gpio/Makefile b/tools/gpio/Makefile index 805a2c0cf4cd..240eda014b37 100644 --- a/tools/gpio/Makefile +++ b/tools/gpio/Makefile @@ -12,8 +12,6 @@ endif # (this improves performance and avoids hard-to-debug behaviour); MAKEFLAGS += -r -CC = $(CROSS_COMPILE)gcc -LD = $(CROSS_COMPILE)ld CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include ALL_TARGETS := lsgpio gpio-hammer gpio-event-mon diff --git a/tools/hv/Makefile b/tools/hv/Makefile index 1139d71fa0cf..5db5e62cebda 100644 --- a/tools/hv/Makefile +++ b/tools/hv/Makefile @@ -1,7 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for Hyper-V tools -CC = $(CROSS_COMPILE)gcc WARNINGS = -Wall -Wextra CFLAGS = $(WARNINGS) -g $(shell getconf LFS_CFLAGS) diff --git a/tools/iio/Makefile b/tools/iio/Makefile index a08e7a47d6a3..332ed2f6c2c2 100644 --- a/tools/iio/Makefile +++ b/tools/iio/Makefile @@ -12,8 +12,6 @@ endif # (this improves performance and avoids hard-to-debug behaviour); MAKEFLAGS += -r -CC = $(CROSS_COMPILE)gcc -LD = $(CROSS_COMPILE)ld CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include ALL_TARGETS := iio_event_monitor lsiio iio_generic_buffer diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index ac3c6503ca27..536ee4febd74 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -86,6 +86,62 @@ enum i915_mocs_table_index { I915_MOCS_CACHED, }; +/* + * Different engines serve different roles, and there may be more than one + * engine serving each role. enum drm_i915_gem_engine_class provides a + * classification of the role of the engine, which may be used when requesting + * operations to be performed on a certain subset of engines, or for providing + * information about that group. + */ +enum drm_i915_gem_engine_class { + I915_ENGINE_CLASS_RENDER = 0, + I915_ENGINE_CLASS_COPY = 1, + I915_ENGINE_CLASS_VIDEO = 2, + I915_ENGINE_CLASS_VIDEO_ENHANCE = 3, + + I915_ENGINE_CLASS_INVALID = -1 +}; + +/** + * DOC: perf_events exposed by i915 through /sys/bus/event_sources/drivers/i915 + * + */ + +enum drm_i915_pmu_engine_sample { + I915_SAMPLE_BUSY = 0, + I915_SAMPLE_WAIT = 1, + I915_SAMPLE_SEMA = 2 +}; + +#define I915_PMU_SAMPLE_BITS (4) +#define I915_PMU_SAMPLE_MASK (0xf) +#define I915_PMU_SAMPLE_INSTANCE_BITS (8) +#define I915_PMU_CLASS_SHIFT \ + (I915_PMU_SAMPLE_BITS + I915_PMU_SAMPLE_INSTANCE_BITS) + +#define __I915_PMU_ENGINE(class, instance, sample) \ + ((class) << I915_PMU_CLASS_SHIFT | \ + (instance) << I915_PMU_SAMPLE_BITS | \ + (sample)) + +#define I915_PMU_ENGINE_BUSY(class, instance) \ + __I915_PMU_ENGINE(class, instance, I915_SAMPLE_BUSY) + +#define I915_PMU_ENGINE_WAIT(class, instance) \ + __I915_PMU_ENGINE(class, instance, I915_SAMPLE_WAIT) + +#define I915_PMU_ENGINE_SEMA(class, instance) \ + __I915_PMU_ENGINE(class, instance, I915_SAMPLE_SEMA) + +#define __I915_PMU_OTHER(x) (__I915_PMU_ENGINE(0xff, 0xff, 0xf) + 1 + (x)) + +#define I915_PMU_ACTUAL_FREQUENCY __I915_PMU_OTHER(0) +#define I915_PMU_REQUESTED_FREQUENCY __I915_PMU_OTHER(1) +#define I915_PMU_INTERRUPTS __I915_PMU_OTHER(2) +#define I915_PMU_RC6_RESIDENCY __I915_PMU_OTHER(3) + +#define I915_PMU_LAST I915_PMU_RC6_RESIDENCY + /* Each region is a minimum of 16k, and there are at most 255 of them. */ #define I915_NR_TEX_REGIONS 255 /* table size 2k - maximum due to use @@ -450,6 +506,27 @@ typedef struct drm_i915_irq_wait { */ #define I915_PARAM_HAS_EXEC_FENCE_ARRAY 49 +/* + * Query whether every context (both per-file default and user created) is + * isolated (insofar as HW supports). If this parameter is not true, then + * freshly created contexts may inherit values from an existing context, + * rather than default HW values. If true, it also ensures (insofar as HW + * supports) that all state set by this context will not leak to any other + * context. + * + * As not every engine across every gen support contexts, the returned + * value reports the support of context isolation for individual engines by + * returning a bitmask of each engine class set to true if that class supports + * isolation. + */ +#define I915_PARAM_HAS_CONTEXT_ISOLATION 50 + +/* Frequency of the command streamer timestamps given by the *_TIMESTAMP + * registers. This used to be fixed per platform but from CNL onwards, this + * might vary depending on the parts. + */ +#define I915_PARAM_CS_TIMESTAMP_FREQUENCY 51 + typedef struct drm_i915_getparam { __s32 param; /* diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index 8616131e2c61..6d9447700e18 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -163,6 +163,7 @@ enum { IFLA_IF_NETNSID, IFLA_CARRIER_UP_COUNT, IFLA_CARRIER_DOWN_COUNT, + IFLA_NEW_IFINDEX, __IFLA_MAX }; diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 8fb90a0819c3..0fb5ef939732 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -1362,6 +1362,96 @@ struct kvm_s390_ucas_mapping { /* Available with KVM_CAP_S390_CMMA_MIGRATION */ #define KVM_S390_GET_CMMA_BITS _IOWR(KVMIO, 0xb8, struct kvm_s390_cmma_log) #define KVM_S390_SET_CMMA_BITS _IOW(KVMIO, 0xb9, struct kvm_s390_cmma_log) +/* Memory Encryption Commands */ +#define KVM_MEMORY_ENCRYPT_OP _IOWR(KVMIO, 0xba, unsigned long) + +struct kvm_enc_region { + __u64 addr; + __u64 size; +}; + +#define KVM_MEMORY_ENCRYPT_REG_REGION _IOR(KVMIO, 0xbb, struct kvm_enc_region) +#define KVM_MEMORY_ENCRYPT_UNREG_REGION _IOR(KVMIO, 0xbc, struct kvm_enc_region) + +/* Secure Encrypted Virtualization command */ +enum sev_cmd_id { + /* Guest initialization commands */ + KVM_SEV_INIT = 0, + KVM_SEV_ES_INIT, + /* Guest launch commands */ + KVM_SEV_LAUNCH_START, + KVM_SEV_LAUNCH_UPDATE_DATA, + KVM_SEV_LAUNCH_UPDATE_VMSA, + KVM_SEV_LAUNCH_SECRET, + KVM_SEV_LAUNCH_MEASURE, + KVM_SEV_LAUNCH_FINISH, + /* Guest migration commands (outgoing) */ + KVM_SEV_SEND_START, + KVM_SEV_SEND_UPDATE_DATA, + KVM_SEV_SEND_UPDATE_VMSA, + KVM_SEV_SEND_FINISH, + /* Guest migration commands (incoming) */ + KVM_SEV_RECEIVE_START, + KVM_SEV_RECEIVE_UPDATE_DATA, + KVM_SEV_RECEIVE_UPDATE_VMSA, + KVM_SEV_RECEIVE_FINISH, + /* Guest status and debug commands */ + KVM_SEV_GUEST_STATUS, + KVM_SEV_DBG_DECRYPT, + KVM_SEV_DBG_ENCRYPT, + /* Guest certificates commands */ + KVM_SEV_CERT_EXPORT, + + KVM_SEV_NR_MAX, +}; + +struct kvm_sev_cmd { + __u32 id; + __u64 data; + __u32 error; + __u32 sev_fd; +}; + +struct kvm_sev_launch_start { + __u32 handle; + __u32 policy; + __u64 dh_uaddr; + __u32 dh_len; + __u64 session_uaddr; + __u32 session_len; +}; + +struct kvm_sev_launch_update_data { + __u64 uaddr; + __u32 len; +}; + + +struct kvm_sev_launch_secret { + __u64 hdr_uaddr; + __u32 hdr_len; + __u64 guest_uaddr; + __u32 guest_len; + __u64 trans_uaddr; + __u32 trans_len; +}; + +struct kvm_sev_launch_measure { + __u64 uaddr; + __u32 len; +}; + +struct kvm_sev_guest_status { + __u32 handle; + __u32 policy; + __u32 state; +}; + +struct kvm_sev_dbg { + __u64 src_uaddr; + __u64 dst_uaddr; + __u32 len; +}; #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) #define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1) diff --git a/tools/laptop/freefall/Makefile b/tools/laptop/freefall/Makefile index 5f758c489a20..b572d94255f6 100644 --- a/tools/laptop/freefall/Makefile +++ b/tools/laptop/freefall/Makefile @@ -2,7 +2,6 @@ PREFIX ?= /usr SBINDIR ?= sbin INSTALL ?= install -CC = $(CROSS_COMPILE)gcc TARGET = freefall diff --git a/tools/leds/Makefile b/tools/leds/Makefile index c379af003807..7b6bed13daaa 100644 --- a/tools/leds/Makefile +++ b/tools/leds/Makefile @@ -1,7 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for LEDs tools -CC = $(CROSS_COMPILE)gcc CFLAGS = -Wall -Wextra -g -I../../include/uapi all: uledmon led_hw_brightness_mon diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 97073d649c1a..5bbbf285af74 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -1060,11 +1060,12 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj, prog->insns = new_insn; prog->main_prog_cnt = prog->insns_cnt; prog->insns_cnt = new_cnt; + pr_debug("added %zd insn from %s to prog %s\n", + text->insns_cnt, text->section_name, + prog->section_name); } insn = &prog->insns[relo->insn_idx]; insn->imm += prog->main_prog_cnt - relo->insn_idx; - pr_debug("added %zd insn from %s to prog %s\n", - text->insns_cnt, text->section_name, prog->section_name); return 0; } diff --git a/tools/objtool/check.c b/tools/objtool/check.c index b00b1896547e..a8cb69a26576 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -852,8 +852,14 @@ static int add_switch_table(struct objtool_file *file, struct symbol *func, * This is a fairly uncommon pattern which is new for GCC 6. As of this * writing, there are 11 occurrences of it in the allmodconfig kernel. * + * As of GCC 7 there are quite a few more of these and the 'in between' code + * is significant. Esp. with KASAN enabled some of the code between the mov + * and jmpq uses .rodata itself, which can confuse things. + * * TODO: Once we have DWARF CFI and smarter instruction decoding logic, * ensure the same register is used in the mov and jump instructions. + * + * NOTE: RETPOLINE made it harder still to decode dynamic jumps. */ static struct rela *find_switch_table(struct objtool_file *file, struct symbol *func, @@ -875,12 +881,25 @@ static struct rela *find_switch_table(struct objtool_file *file, text_rela->addend + 4); if (!rodata_rela) return NULL; + file->ignore_unreachables = true; return rodata_rela; } /* case 3 */ - func_for_each_insn_continue_reverse(file, func, insn) { + /* + * Backward search using the @first_jump_src links, these help avoid + * much of the 'in between' code. Which avoids us getting confused by + * it. + */ + for (insn = list_prev_entry(insn, list); + + &insn->list != &file->insn_list && + insn->sec == func->sec && + insn->offset >= func->offset; + + insn = insn->first_jump_src ?: list_prev_entry(insn, list)) { + if (insn->type == INSN_JUMP_DYNAMIC) break; @@ -910,14 +929,32 @@ static struct rela *find_switch_table(struct objtool_file *file, return NULL; } + static int add_func_switch_tables(struct objtool_file *file, struct symbol *func) { - struct instruction *insn, *prev_jump = NULL; + struct instruction *insn, *last = NULL, *prev_jump = NULL; struct rela *rela, *prev_rela = NULL; int ret; func_for_each_insn(file, func, insn) { + if (!last) + last = insn; + + /* + * Store back-pointers for unconditional forward jumps such + * that find_switch_table() can back-track using those and + * avoid some potentially confusing code. + */ + if (insn->type == INSN_JUMP_UNCONDITIONAL && insn->jump_dest && + insn->offset > last->offset && + insn->jump_dest->offset > insn->offset && + !insn->jump_dest->first_jump_src) { + + insn->jump_dest->first_jump_src = insn; + last = insn->jump_dest; + } + if (insn->type != INSN_JUMP_DYNAMIC) continue; @@ -1899,13 +1936,19 @@ static bool ignore_unreachable_insn(struct instruction *insn) if (is_kasan_insn(insn) || is_ubsan_insn(insn)) return true; - if (insn->type == INSN_JUMP_UNCONDITIONAL && insn->jump_dest) { - insn = insn->jump_dest; - continue; + if (insn->type == INSN_JUMP_UNCONDITIONAL) { + if (insn->jump_dest && + insn->jump_dest->func == insn->func) { + insn = insn->jump_dest; + continue; + } + + break; } if (insn->offset + insn->len >= insn->func->offset + insn->func->len) break; + insn = list_next_entry(insn, list); } diff --git a/tools/objtool/check.h b/tools/objtool/check.h index dbadb304a410..23a1d065cae1 100644 --- a/tools/objtool/check.h +++ b/tools/objtool/check.h @@ -47,6 +47,7 @@ struct instruction { bool alt_group, visited, dead_end, ignore, hint, save, restore, ignore_alts; struct symbol *call_dest; struct instruction *jump_dest; + struct instruction *first_jump_src; struct list_head alts; struct symbol *func; struct stack_op stack_op; diff --git a/tools/perf/Documentation/perf-data.txt b/tools/perf/Documentation/perf-data.txt index f0796a47dfa3..90bb4aabe4f8 100644 --- a/tools/perf/Documentation/perf-data.txt +++ b/tools/perf/Documentation/perf-data.txt @@ -30,6 +30,10 @@ OPTIONS for 'convert' -i:: Specify input perf data file path. +-f:: +--force:: + Don't complain, do it. + -v:: --verbose:: Be more verbose (show counter open errors, etc). diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 9b0351d3ce34..012328038594 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -146,12 +146,6 @@ define allow-override $(eval $(1) = $(2))) endef -# Allow setting CC and AR and LD, or setting CROSS_COMPILE as a prefix. -$(call allow-override,CC,$(CROSS_COMPILE)gcc) -$(call allow-override,AR,$(CROSS_COMPILE)ar) -$(call allow-override,LD,$(CROSS_COMPILE)ld) -$(call allow-override,CXX,$(CROSS_COMPILE)g++) - LD += $(EXTRA_LDFLAGS) HOSTCC ?= gcc diff --git a/tools/perf/arch/s390/Makefile b/tools/perf/arch/s390/Makefile index 48228de415d0..dfa6e3103437 100644 --- a/tools/perf/arch/s390/Makefile +++ b/tools/perf/arch/s390/Makefile @@ -10,15 +10,19 @@ PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1 out := $(OUTPUT)arch/s390/include/generated/asm header := $(out)/syscalls_64.c -sysdef := $(srctree)/tools/arch/s390/include/uapi/asm/unistd.h -sysprf := $(srctree)/tools/perf/arch/s390/entry/syscalls/ +syskrn := $(srctree)/arch/s390/kernel/syscalls/syscall.tbl +sysprf := $(srctree)/tools/perf/arch/s390/entry/syscalls +sysdef := $(sysprf)/syscall.tbl systbl := $(sysprf)/mksyscalltbl # Create output directory if not already present _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') $(header): $(sysdef) $(systbl) - $(Q)$(SHELL) '$(systbl)' '$(CC)' $(sysdef) > $@ + @(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \ + (diff -B $(sysdef) $(syskrn) >/dev/null) \ + || echo "Warning: Kernel ABI header at '$(sysdef)' differs from latest version at '$(syskrn)'" >&2 )) || true + $(Q)$(SHELL) '$(systbl)' $(sysdef) > $@ clean:: $(call QUIET_CLEAN, s390) $(RM) $(header) diff --git a/tools/perf/arch/s390/entry/syscalls/mksyscalltbl b/tools/perf/arch/s390/entry/syscalls/mksyscalltbl index 7fa0d0abd419..72ecbb676370 100755 --- a/tools/perf/arch/s390/entry/syscalls/mksyscalltbl +++ b/tools/perf/arch/s390/entry/syscalls/mksyscalltbl @@ -3,25 +3,23 @@ # # Generate system call table for perf # -# -# Copyright IBM Corp. 2017 +# Copyright IBM Corp. 2017, 2018 # Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> # -gcc=$1 -input=$2 +SYSCALL_TBL=$1 -if ! test -r $input; then +if ! test -r $SYSCALL_TBL; then echo "Could not read input file" >&2 exit 1 fi create_table() { - local max_nr + local max_nr nr abi sc discard echo 'static const char *syscalltbl_s390_64[] = {' - while read sc nr; do + while read nr abi sc discard; do printf '\t[%d] = "%s",\n' $nr $sc max_nr=$nr done @@ -29,8 +27,6 @@ create_table() echo "#define SYSCALLTBL_S390_64_MAX_ID $max_nr" } - -$gcc -m64 -E -dM -x c $input \ - |sed -ne 's/^#define __NR_//p' \ - |sort -t' ' -k2 -nu \ +grep -E "^[[:digit:]]+[[:space:]]+(common|64)" $SYSCALL_TBL \ + |sort -k1 -n \ |create_table diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl new file mode 100644 index 000000000000..b38d48464368 --- /dev/null +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -0,0 +1,390 @@ +# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note +# +# System call table for s390 +# +# Format: +# +# <nr> <abi> <syscall> <entry-64bit> <compat-entry> +# +# where <abi> can be common, 64, or 32 + +1 common exit sys_exit sys_exit +2 common fork sys_fork sys_fork +3 common read sys_read compat_sys_s390_read +4 common write sys_write compat_sys_s390_write +5 common open sys_open compat_sys_open +6 common close sys_close sys_close +7 common restart_syscall sys_restart_syscall sys_restart_syscall +8 common creat sys_creat compat_sys_creat +9 common link sys_link compat_sys_link +10 common unlink sys_unlink compat_sys_unlink +11 common execve sys_execve compat_sys_execve +12 common chdir sys_chdir compat_sys_chdir +13 32 time - compat_sys_time +14 common mknod sys_mknod compat_sys_mknod +15 common chmod sys_chmod compat_sys_chmod +16 32 lchown - compat_sys_s390_lchown16 +19 common lseek sys_lseek compat_sys_lseek +20 common getpid sys_getpid sys_getpid +21 common mount sys_mount compat_sys_mount +22 common umount sys_oldumount compat_sys_oldumount +23 32 setuid - compat_sys_s390_setuid16 +24 32 getuid - compat_sys_s390_getuid16 +25 32 stime - compat_sys_stime +26 common ptrace sys_ptrace compat_sys_ptrace +27 common alarm sys_alarm sys_alarm +29 common pause sys_pause sys_pause +30 common utime sys_utime compat_sys_utime +33 common access sys_access compat_sys_access +34 common nice sys_nice sys_nice +36 common sync sys_sync sys_sync +37 common kill sys_kill sys_kill +38 common rename sys_rename compat_sys_rename +39 common mkdir sys_mkdir compat_sys_mkdir +40 common rmdir sys_rmdir compat_sys_rmdir +41 common dup sys_dup sys_dup +42 common pipe sys_pipe compat_sys_pipe +43 common times sys_times compat_sys_times +45 common brk sys_brk compat_sys_brk +46 32 setgid - compat_sys_s390_setgid16 +47 32 getgid - compat_sys_s390_getgid16 +48 common signal sys_signal compat_sys_signal +49 32 geteuid - compat_sys_s390_geteuid16 +50 32 getegid - compat_sys_s390_getegid16 +51 common acct sys_acct compat_sys_acct +52 common umount2 sys_umount compat_sys_umount +54 common ioctl sys_ioctl compat_sys_ioctl +55 common fcntl sys_fcntl compat_sys_fcntl +57 common setpgid sys_setpgid sys_setpgid +60 common umask sys_umask sys_umask +61 common chroot sys_chroot compat_sys_chroot +62 common ustat sys_ustat compat_sys_ustat +63 common dup2 sys_dup2 sys_dup2 +64 common getppid sys_getppid sys_getppid +65 common getpgrp sys_getpgrp sys_getpgrp +66 common setsid sys_setsid sys_setsid +67 common sigaction sys_sigaction compat_sys_sigaction +70 32 setreuid - compat_sys_s390_setreuid16 +71 32 setregid - compat_sys_s390_setregid16 +72 common sigsuspend sys_sigsuspend compat_sys_sigsuspend +73 common sigpending sys_sigpending compat_sys_sigpending +74 common sethostname sys_sethostname compat_sys_sethostname +75 common setrlimit sys_setrlimit compat_sys_setrlimit +76 32 getrlimit - compat_sys_old_getrlimit +77 common getrusage sys_getrusage compat_sys_getrusage +78 common gettimeofday sys_gettimeofday compat_sys_gettimeofday +79 common settimeofday sys_settimeofday compat_sys_settimeofday +80 32 getgroups - compat_sys_s390_getgroups16 +81 32 setgroups - compat_sys_s390_setgroups16 +83 common symlink sys_symlink compat_sys_symlink +85 common readlink sys_readlink compat_sys_readlink +86 common uselib sys_uselib compat_sys_uselib +87 common swapon sys_swapon compat_sys_swapon +88 common reboot sys_reboot compat_sys_reboot +89 common readdir - compat_sys_old_readdir +90 common mmap sys_old_mmap compat_sys_s390_old_mmap +91 common munmap sys_munmap compat_sys_munmap +92 common truncate sys_truncate compat_sys_truncate +93 common ftruncate sys_ftruncate compat_sys_ftruncate +94 common fchmod sys_fchmod sys_fchmod +95 32 fchown - compat_sys_s390_fchown16 +96 common getpriority sys_getpriority sys_getpriority +97 common setpriority sys_setpriority sys_setpriority +99 common statfs sys_statfs compat_sys_statfs +100 common fstatfs sys_fstatfs compat_sys_fstatfs +101 32 ioperm - - +102 common socketcall sys_socketcall compat_sys_socketcall +103 common syslog sys_syslog compat_sys_syslog +104 common setitimer sys_setitimer compat_sys_setitimer +105 common getitimer sys_getitimer compat_sys_getitimer +106 common stat sys_newstat compat_sys_newstat +107 common lstat sys_newlstat compat_sys_newlstat +108 common fstat sys_newfstat compat_sys_newfstat +110 common lookup_dcookie sys_lookup_dcookie compat_sys_lookup_dcookie +111 common vhangup sys_vhangup sys_vhangup +112 common idle - - +114 common wait4 sys_wait4 compat_sys_wait4 +115 common swapoff sys_swapoff compat_sys_swapoff +116 common sysinfo sys_sysinfo compat_sys_sysinfo +117 common ipc sys_s390_ipc compat_sys_s390_ipc +118 common fsync sys_fsync sys_fsync +119 common sigreturn sys_sigreturn compat_sys_sigreturn +120 common clone sys_clone compat_sys_clone +121 common setdomainname sys_setdomainname compat_sys_setdomainname +122 common uname sys_newuname compat_sys_newuname +124 common adjtimex sys_adjtimex compat_sys_adjtimex +125 common mprotect sys_mprotect compat_sys_mprotect +126 common sigprocmask sys_sigprocmask compat_sys_sigprocmask +127 common create_module - - +128 common init_module sys_init_module compat_sys_init_module +129 common delete_module sys_delete_module compat_sys_delete_module +130 common get_kernel_syms - - +131 common quotactl sys_quotactl compat_sys_quotactl +132 common getpgid sys_getpgid sys_getpgid +133 common fchdir sys_fchdir sys_fchdir +134 common bdflush sys_bdflush compat_sys_bdflush +135 common sysfs sys_sysfs compat_sys_sysfs +136 common personality sys_s390_personality sys_s390_personality +137 common afs_syscall - - +138 32 setfsuid - compat_sys_s390_setfsuid16 +139 32 setfsgid - compat_sys_s390_setfsgid16 +140 32 _llseek - compat_sys_llseek +141 common getdents sys_getdents compat_sys_getdents +142 32 _newselect - compat_sys_select +142 64 select sys_select - +143 common flock sys_flock sys_flock +144 common msync sys_msync compat_sys_msync +145 common readv sys_readv compat_sys_readv +146 common writev sys_writev compat_sys_writev +147 common getsid sys_getsid sys_getsid +148 common fdatasync sys_fdatasync sys_fdatasync +149 common _sysctl sys_sysctl compat_sys_sysctl +150 common mlock sys_mlock compat_sys_mlock +151 common munlock sys_munlock compat_sys_munlock +152 common mlockall sys_mlockall sys_mlockall +153 common munlockall sys_munlockall sys_munlockall +154 common sched_setparam sys_sched_setparam compat_sys_sched_setparam +155 common sched_getparam sys_sched_getparam compat_sys_sched_getparam +156 common sched_setscheduler sys_sched_setscheduler compat_sys_sched_setscheduler +157 common sched_getscheduler sys_sched_getscheduler sys_sched_getscheduler +158 common sched_yield sys_sched_yield sys_sched_yield +159 common sched_get_priority_max sys_sched_get_priority_max sys_sched_get_priority_max +160 common sched_get_priority_min sys_sched_get_priority_min sys_sched_get_priority_min +161 common sched_rr_get_interval sys_sched_rr_get_interval compat_sys_sched_rr_get_interval +162 common nanosleep sys_nanosleep compat_sys_nanosleep +163 common mremap sys_mremap compat_sys_mremap +164 32 setresuid - compat_sys_s390_setresuid16 +165 32 getresuid - compat_sys_s390_getresuid16 +167 common query_module - - +168 common poll sys_poll compat_sys_poll +169 common nfsservctl - - +170 32 setresgid - compat_sys_s390_setresgid16 +171 32 getresgid - compat_sys_s390_getresgid16 +172 common prctl sys_prctl compat_sys_prctl +173 common rt_sigreturn sys_rt_sigreturn compat_sys_rt_sigreturn +174 common rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction +175 common rt_sigprocmask sys_rt_sigprocmask compat_sys_rt_sigprocmask +176 common rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending +177 common rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait +178 common rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo +179 common rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend +180 common pread64 sys_pread64 compat_sys_s390_pread64 +181 common pwrite64 sys_pwrite64 compat_sys_s390_pwrite64 +182 32 chown - compat_sys_s390_chown16 +183 common getcwd sys_getcwd compat_sys_getcwd +184 common capget sys_capget compat_sys_capget +185 common capset sys_capset compat_sys_capset +186 common sigaltstack sys_sigaltstack compat_sys_sigaltstack +187 common sendfile sys_sendfile64 compat_sys_sendfile +188 common getpmsg - - +189 common putpmsg - - +190 common vfork sys_vfork sys_vfork +191 32 ugetrlimit - compat_sys_getrlimit +191 64 getrlimit sys_getrlimit - +192 32 mmap2 - compat_sys_s390_mmap2 +193 32 truncate64 - compat_sys_s390_truncate64 +194 32 ftruncate64 - compat_sys_s390_ftruncate64 +195 32 stat64 - compat_sys_s390_stat64 +196 32 lstat64 - compat_sys_s390_lstat64 +197 32 fstat64 - compat_sys_s390_fstat64 +198 32 lchown32 - compat_sys_lchown +198 64 lchown sys_lchown - +199 32 getuid32 - sys_getuid +199 64 getuid sys_getuid - +200 32 getgid32 - sys_getgid +200 64 getgid sys_getgid - +201 32 geteuid32 - sys_geteuid +201 64 geteuid sys_geteuid - +202 32 getegid32 - sys_getegid +202 64 getegid sys_getegid - +203 32 setreuid32 - sys_setreuid +203 64 setreuid sys_setreuid - +204 32 setregid32 - sys_setregid +204 64 setregid sys_setregid - +205 32 getgroups32 - compat_sys_getgroups +205 64 getgroups sys_getgroups - +206 32 setgroups32 - compat_sys_setgroups +206 64 setgroups sys_setgroups - +207 32 fchown32 - sys_fchown +207 64 fchown sys_fchown - +208 32 setresuid32 - sys_setresuid +208 64 setresuid sys_setresuid - +209 32 getresuid32 - compat_sys_getresuid +209 64 getresuid sys_getresuid - +210 32 setresgid32 - sys_setresgid +210 64 setresgid sys_setresgid - +211 32 getresgid32 - compat_sys_getresgid +211 64 getresgid sys_getresgid - +212 32 chown32 - compat_sys_chown +212 64 chown sys_chown - +213 32 setuid32 - sys_setuid +213 64 setuid sys_setuid - +214 32 setgid32 - sys_setgid +214 64 setgid sys_setgid - +215 32 setfsuid32 - sys_setfsuid +215 64 setfsuid sys_setfsuid - +216 32 setfsgid32 - sys_setfsgid +216 64 setfsgid sys_setfsgid - +217 common pivot_root sys_pivot_root compat_sys_pivot_root +218 common mincore sys_mincore compat_sys_mincore +219 common madvise sys_madvise compat_sys_madvise +220 common getdents64 sys_getdents64 compat_sys_getdents64 +221 32 fcntl64 - compat_sys_fcntl64 +222 common readahead sys_readahead compat_sys_s390_readahead +223 32 sendfile64 - compat_sys_sendfile64 +224 common setxattr sys_setxattr compat_sys_setxattr +225 common lsetxattr sys_lsetxattr compat_sys_lsetxattr +226 common fsetxattr sys_fsetxattr compat_sys_fsetxattr +227 common getxattr sys_getxattr compat_sys_getxattr +228 common lgetxattr sys_lgetxattr compat_sys_lgetxattr +229 common fgetxattr sys_fgetxattr compat_sys_fgetxattr +230 common listxattr sys_listxattr compat_sys_listxattr +231 common llistxattr sys_llistxattr compat_sys_llistxattr +232 common flistxattr sys_flistxattr compat_sys_flistxattr +233 common removexattr sys_removexattr compat_sys_removexattr +234 common lremovexattr sys_lremovexattr compat_sys_lremovexattr +235 common fremovexattr sys_fremovexattr compat_sys_fremovexattr +236 common gettid sys_gettid sys_gettid +237 common tkill sys_tkill sys_tkill +238 common futex sys_futex compat_sys_futex +239 common sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity +240 common sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity +241 common tgkill sys_tgkill sys_tgkill +243 common io_setup sys_io_setup compat_sys_io_setup +244 common io_destroy sys_io_destroy compat_sys_io_destroy +245 common io_getevents sys_io_getevents compat_sys_io_getevents +246 common io_submit sys_io_submit compat_sys_io_submit +247 common io_cancel sys_io_cancel compat_sys_io_cancel +248 common exit_group sys_exit_group sys_exit_group +249 common epoll_create sys_epoll_create sys_epoll_create +250 common epoll_ctl sys_epoll_ctl compat_sys_epoll_ctl +251 common epoll_wait sys_epoll_wait compat_sys_epoll_wait +252 common set_tid_address sys_set_tid_address compat_sys_set_tid_address +253 common fadvise64 sys_fadvise64_64 compat_sys_s390_fadvise64 +254 common timer_create sys_timer_create compat_sys_timer_create +255 common timer_settime sys_timer_settime compat_sys_timer_settime +256 common timer_gettime sys_timer_gettime compat_sys_timer_gettime +257 common timer_getoverrun sys_timer_getoverrun sys_timer_getoverrun +258 common timer_delete sys_timer_delete sys_timer_delete +259 common clock_settime sys_clock_settime compat_sys_clock_settime +260 common clock_gettime sys_clock_gettime compat_sys_clock_gettime +261 common clock_getres sys_clock_getres compat_sys_clock_getres +262 common clock_nanosleep sys_clock_nanosleep compat_sys_clock_nanosleep +264 32 fadvise64_64 - compat_sys_s390_fadvise64_64 +265 common statfs64 sys_statfs64 compat_sys_statfs64 +266 common fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 +267 common remap_file_pages sys_remap_file_pages compat_sys_remap_file_pages +268 common mbind sys_mbind compat_sys_mbind +269 common get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy +270 common set_mempolicy sys_set_mempolicy compat_sys_set_mempolicy +271 common mq_open sys_mq_open compat_sys_mq_open +272 common mq_unlink sys_mq_unlink compat_sys_mq_unlink +273 common mq_timedsend sys_mq_timedsend compat_sys_mq_timedsend +274 common mq_timedreceive sys_mq_timedreceive compat_sys_mq_timedreceive +275 common mq_notify sys_mq_notify compat_sys_mq_notify +276 common mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr +277 common kexec_load sys_kexec_load compat_sys_kexec_load +278 common add_key sys_add_key compat_sys_add_key +279 common request_key sys_request_key compat_sys_request_key +280 common keyctl sys_keyctl compat_sys_keyctl +281 common waitid sys_waitid compat_sys_waitid +282 common ioprio_set sys_ioprio_set sys_ioprio_set +283 common ioprio_get sys_ioprio_get sys_ioprio_get +284 common inotify_init sys_inotify_init sys_inotify_init +285 common inotify_add_watch sys_inotify_add_watch compat_sys_inotify_add_watch +286 common inotify_rm_watch sys_inotify_rm_watch sys_inotify_rm_watch +287 common migrate_pages sys_migrate_pages compat_sys_migrate_pages +288 common openat sys_openat compat_sys_openat +289 common mkdirat sys_mkdirat compat_sys_mkdirat +290 common mknodat sys_mknodat compat_sys_mknodat +291 common fchownat sys_fchownat compat_sys_fchownat +292 common futimesat sys_futimesat compat_sys_futimesat +293 32 fstatat64 - compat_sys_s390_fstatat64 +293 64 newfstatat sys_newfstatat - +294 common unlinkat sys_unlinkat compat_sys_unlinkat +295 common renameat sys_renameat compat_sys_renameat +296 common linkat sys_linkat compat_sys_linkat +297 common symlinkat sys_symlinkat compat_sys_symlinkat +298 common readlinkat sys_readlinkat compat_sys_readlinkat +299 common fchmodat sys_fchmodat compat_sys_fchmodat +300 common faccessat sys_faccessat compat_sys_faccessat +301 common pselect6 sys_pselect6 compat_sys_pselect6 +302 common ppoll sys_ppoll compat_sys_ppoll +303 common unshare sys_unshare compat_sys_unshare +304 common set_robust_list sys_set_robust_list compat_sys_set_robust_list +305 common get_robust_list sys_get_robust_list compat_sys_get_robust_list +306 common splice sys_splice compat_sys_splice +307 common sync_file_range sys_sync_file_range compat_sys_s390_sync_file_range +308 common tee sys_tee compat_sys_tee +309 common vmsplice sys_vmsplice compat_sys_vmsplice +310 common move_pages sys_move_pages compat_sys_move_pages +311 common getcpu sys_getcpu compat_sys_getcpu +312 common epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait +313 common utimes sys_utimes compat_sys_utimes +314 common fallocate sys_fallocate compat_sys_s390_fallocate +315 common utimensat sys_utimensat compat_sys_utimensat +316 common signalfd sys_signalfd compat_sys_signalfd +317 common timerfd - - +318 common eventfd sys_eventfd sys_eventfd +319 common timerfd_create sys_timerfd_create sys_timerfd_create +320 common timerfd_settime sys_timerfd_settime compat_sys_timerfd_settime +321 common timerfd_gettime sys_timerfd_gettime compat_sys_timerfd_gettime +322 common signalfd4 sys_signalfd4 compat_sys_signalfd4 +323 common eventfd2 sys_eventfd2 sys_eventfd2 +324 common inotify_init1 sys_inotify_init1 sys_inotify_init1 +325 common pipe2 sys_pipe2 compat_sys_pipe2 +326 common dup3 sys_dup3 sys_dup3 +327 common epoll_create1 sys_epoll_create1 sys_epoll_create1 +328 common preadv sys_preadv compat_sys_preadv +329 common pwritev sys_pwritev compat_sys_pwritev +330 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo +331 common perf_event_open sys_perf_event_open compat_sys_perf_event_open +332 common fanotify_init sys_fanotify_init sys_fanotify_init +333 common fanotify_mark sys_fanotify_mark compat_sys_fanotify_mark +334 common prlimit64 sys_prlimit64 compat_sys_prlimit64 +335 common name_to_handle_at sys_name_to_handle_at compat_sys_name_to_handle_at +336 common open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at +337 common clock_adjtime sys_clock_adjtime compat_sys_clock_adjtime +338 common syncfs sys_syncfs sys_syncfs +339 common setns sys_setns sys_setns +340 common process_vm_readv sys_process_vm_readv compat_sys_process_vm_readv +341 common process_vm_writev sys_process_vm_writev compat_sys_process_vm_writev +342 common s390_runtime_instr sys_s390_runtime_instr sys_s390_runtime_instr +343 common kcmp sys_kcmp compat_sys_kcmp +344 common finit_module sys_finit_module compat_sys_finit_module +345 common sched_setattr sys_sched_setattr compat_sys_sched_setattr +346 common sched_getattr sys_sched_getattr compat_sys_sched_getattr +347 common renameat2 sys_renameat2 compat_sys_renameat2 +348 common seccomp sys_seccomp compat_sys_seccomp +349 common getrandom sys_getrandom compat_sys_getrandom +350 common memfd_create sys_memfd_create compat_sys_memfd_create +351 common bpf sys_bpf compat_sys_bpf +352 common s390_pci_mmio_write sys_s390_pci_mmio_write compat_sys_s390_pci_mmio_write +353 common s390_pci_mmio_read sys_s390_pci_mmio_read compat_sys_s390_pci_mmio_read +354 common execveat sys_execveat compat_sys_execveat +355 common userfaultfd sys_userfaultfd sys_userfaultfd +356 common membarrier sys_membarrier sys_membarrier +357 common recvmmsg sys_recvmmsg compat_sys_recvmmsg +358 common sendmmsg sys_sendmmsg compat_sys_sendmmsg +359 common socket sys_socket sys_socket +360 common socketpair sys_socketpair compat_sys_socketpair +361 common bind sys_bind compat_sys_bind +362 common connect sys_connect compat_sys_connect +363 common listen sys_listen sys_listen +364 common accept4 sys_accept4 compat_sys_accept4 +365 common getsockopt sys_getsockopt compat_sys_getsockopt +366 common setsockopt sys_setsockopt compat_sys_setsockopt +367 common getsockname sys_getsockname compat_sys_getsockname +368 common getpeername sys_getpeername compat_sys_getpeername +369 common sendto sys_sendto compat_sys_sendto +370 common sendmsg sys_sendmsg compat_sys_sendmsg +371 common recvfrom sys_recvfrom compat_sys_recvfrom +372 common recvmsg sys_recvmsg compat_sys_recvmsg +373 common shutdown sys_shutdown sys_shutdown +374 common mlock2 sys_mlock2 compat_sys_mlock2 +375 common copy_file_range sys_copy_file_range compat_sys_copy_file_range +376 common preadv2 sys_preadv2 compat_sys_preadv2 +377 common pwritev2 sys_pwritev2 compat_sys_pwritev2 +378 common s390_guarded_storage sys_s390_guarded_storage compat_sys_s390_guarded_storage +379 common statx sys_statx compat_sys_statx +380 common s390_sthyi sys_s390_sthyi compat_sys_s390_sthyi diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index c0815a37fdb5..539c3d460158 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -2245,7 +2245,7 @@ static int perf_c2c__browse_cacheline(struct hist_entry *he) c2c_browser__update_nr_entries(browser); while (1) { - key = hist_browser__run(browser, "? - help"); + key = hist_browser__run(browser, "? - help", true); switch (key) { case 's': @@ -2314,7 +2314,7 @@ static int perf_c2c__hists_browse(struct hists *hists) c2c_browser__update_nr_entries(browser); while (1) { - key = hist_browser__run(browser, "? - help"); + key = hist_browser__run(browser, "? - help", true); switch (key) { case 'q': diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 42a52dcc41cd..4ad5dc649716 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -530,7 +530,8 @@ static int report__browse_hists(struct report *rep) case 1: ret = perf_evlist__tui_browse_hists(evlist, help, NULL, rep->min_percent, - &session->header.env); + &session->header.env, + true); /* * Usually "ret" is the last pressed key, and we only * care if the key notifies us to switch data file. diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index c6ccda52117d..b7c823ba8374 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -283,8 +283,9 @@ static void perf_top__print_sym_table(struct perf_top *top) printf("%-*.*s\n", win_width, win_width, graph_dotted_line); - if (hists->stats.nr_lost_warned != - hists->stats.nr_events[PERF_RECORD_LOST]) { + if (!top->record_opts.overwrite && + (hists->stats.nr_lost_warned != + hists->stats.nr_events[PERF_RECORD_LOST])) { hists->stats.nr_lost_warned = hists->stats.nr_events[PERF_RECORD_LOST]; color_fprintf(stdout, PERF_COLOR_RED, @@ -611,7 +612,8 @@ static void *display_thread_tui(void *arg) perf_evlist__tui_browse_hists(top->evlist, help, &hbt, top->min_percent, - &top->session->header.env); + &top->session->header.env, + !top->record_opts.overwrite); done = 1; return NULL; @@ -807,15 +809,23 @@ static void perf_event__process_sample(struct perf_tool *tool, static void perf_top__mmap_read_idx(struct perf_top *top, int idx) { + struct record_opts *opts = &top->record_opts; + struct perf_evlist *evlist = top->evlist; struct perf_sample sample; struct perf_evsel *evsel; + struct perf_mmap *md; struct perf_session *session = top->session; union perf_event *event; struct machine *machine; + u64 end, start; int ret; - while ((event = perf_evlist__mmap_read(top->evlist, idx)) != NULL) { - ret = perf_evlist__parse_sample(top->evlist, event, &sample); + md = opts->overwrite ? &evlist->overwrite_mmap[idx] : &evlist->mmap[idx]; + if (perf_mmap__read_init(md, opts->overwrite, &start, &end) < 0) + return; + + while ((event = perf_mmap__read_event(md, opts->overwrite, &start, end)) != NULL) { + ret = perf_evlist__parse_sample(evlist, event, &sample); if (ret) { pr_err("Can't parse sample, err = %d\n", ret); goto next_event; @@ -869,16 +879,120 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) } else ++session->evlist->stats.nr_unknown_events; next_event: - perf_evlist__mmap_consume(top->evlist, idx); + perf_mmap__consume(md, opts->overwrite); } + + perf_mmap__read_done(md); } static void perf_top__mmap_read(struct perf_top *top) { + bool overwrite = top->record_opts.overwrite; + struct perf_evlist *evlist = top->evlist; + unsigned long long start, end; int i; + start = rdclock(); + if (overwrite) + perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_DATA_PENDING); + for (i = 0; i < top->evlist->nr_mmaps; i++) perf_top__mmap_read_idx(top, i); + + if (overwrite) { + perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY); + perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING); + } + end = rdclock(); + + if ((end - start) > (unsigned long long)top->delay_secs * NSEC_PER_SEC) + ui__warning("Too slow to read ring buffer.\n" + "Please try increasing the period (-c) or\n" + "decreasing the freq (-F) or\n" + "limiting the number of CPUs (-C)\n"); +} + +/* + * Check per-event overwrite term. + * perf top should support consistent term for all events. + * - All events don't have per-event term + * E.g. "cpu/cpu-cycles/,cpu/instructions/" + * Nothing change, return 0. + * - All events have same per-event term + * E.g. "cpu/cpu-cycles,no-overwrite/,cpu/instructions,no-overwrite/ + * Using the per-event setting to replace the opts->overwrite if + * they are different, then return 0. + * - Events have different per-event term + * E.g. "cpu/cpu-cycles,overwrite/,cpu/instructions,no-overwrite/" + * Return -1 + * - Some of the event set per-event term, but some not. + * E.g. "cpu/cpu-cycles/,cpu/instructions,no-overwrite/" + * Return -1 + */ +static int perf_top__overwrite_check(struct perf_top *top) +{ + struct record_opts *opts = &top->record_opts; + struct perf_evlist *evlist = top->evlist; + struct perf_evsel_config_term *term; + struct list_head *config_terms; + struct perf_evsel *evsel; + int set, overwrite = -1; + + evlist__for_each_entry(evlist, evsel) { + set = -1; + config_terms = &evsel->config_terms; + list_for_each_entry(term, config_terms, list) { + if (term->type == PERF_EVSEL__CONFIG_TERM_OVERWRITE) + set = term->val.overwrite ? 1 : 0; + } + + /* no term for current and previous event (likely) */ + if ((overwrite < 0) && (set < 0)) + continue; + + /* has term for both current and previous event, compare */ + if ((overwrite >= 0) && (set >= 0) && (overwrite != set)) + return -1; + + /* no term for current event but has term for previous one */ + if ((overwrite >= 0) && (set < 0)) + return -1; + + /* has term for current event */ + if ((overwrite < 0) && (set >= 0)) { + /* if it's first event, set overwrite */ + if (evsel == perf_evlist__first(evlist)) + overwrite = set; + else + return -1; + } + } + + if ((overwrite >= 0) && (opts->overwrite != overwrite)) + opts->overwrite = overwrite; + + return 0; +} + +static int perf_top_overwrite_fallback(struct perf_top *top, + struct perf_evsel *evsel) +{ + struct record_opts *opts = &top->record_opts; + struct perf_evlist *evlist = top->evlist; + struct perf_evsel *counter; + + if (!opts->overwrite) + return 0; + + /* only fall back when first event fails */ + if (evsel != perf_evlist__first(evlist)) + return 0; + + evlist__for_each_entry(evlist, counter) + counter->attr.write_backward = false; + opts->overwrite = false; + ui__warning("fall back to non-overwrite mode\n"); + return 1; } static int perf_top__start_counters(struct perf_top *top) @@ -888,12 +1002,33 @@ static int perf_top__start_counters(struct perf_top *top) struct perf_evlist *evlist = top->evlist; struct record_opts *opts = &top->record_opts; + if (perf_top__overwrite_check(top)) { + ui__error("perf top only support consistent per-event " + "overwrite setting for all events\n"); + goto out_err; + } + perf_evlist__config(evlist, opts, &callchain_param); evlist__for_each_entry(evlist, counter) { try_again: if (perf_evsel__open(counter, top->evlist->cpus, top->evlist->threads) < 0) { + + /* + * Specially handle overwrite fall back. + * Because perf top is the only tool which has + * overwrite mode by default, support + * both overwrite and non-overwrite mode, and + * require consistent mode for all events. + * + * May move it to generic code with more tools + * have similar attribute. + */ + if (perf_missing_features.write_backward && + perf_top_overwrite_fallback(top, counter)) + goto try_again; + if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) { if (verbose > 0) ui__warning("%s\n", msg); @@ -1033,7 +1168,7 @@ static int __cmd_top(struct perf_top *top) perf_top__mmap_read(top); - if (hits == top->samples) + if (opts->overwrite || (hits == top->samples)) ret = perf_evlist__poll(top->evlist, 100); if (resize) { @@ -1127,6 +1262,7 @@ int cmd_top(int argc, const char **argv) .uses_mmap = true, }, .proc_map_timeout = 500, + .overwrite = 1, }, .max_stack = sysctl_perf_event_max_stack, .sym_pcnt_filter = 5, diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 51abdb0a4047..790ec25919a0 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -33,7 +33,6 @@ arch/s390/include/uapi/asm/kvm.h arch/s390/include/uapi/asm/kvm_perf.h arch/s390/include/uapi/asm/ptrace.h arch/s390/include/uapi/asm/sie.h -arch/s390/include/uapi/asm/unistd.h arch/arm/include/uapi/asm/kvm.h arch/arm64/include/uapi/asm/kvm.h arch/alpha/include/uapi/asm/errno.h diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/branch.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/branch.json new file mode 100644 index 000000000000..3b6208763e50 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/cortex-a53/branch.json @@ -0,0 +1,27 @@ +[ + {, + "EventCode": "0x7A", + "EventName": "BR_INDIRECT_SPEC", + "BriefDescription": "Branch speculatively executed - Indirect branch" + }, + {, + "EventCode": "0xC9", + "EventName": "BR_COND", + "BriefDescription": "Conditional branch executed" + }, + {, + "EventCode": "0xCA", + "EventName": "BR_INDIRECT_MISPRED", + "BriefDescription": "Indirect branch mispredicted" + }, + {, + "EventCode": "0xCB", + "EventName": "BR_INDIRECT_MISPRED_ADDR", + "BriefDescription": "Indirect branch mispredicted because of address miscompare" + }, + {, + "EventCode": "0xCC", + "EventName": "BR_COND_MISPRED", + "BriefDescription": "Conditional branch mispredicted" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/bus.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/bus.json new file mode 100644 index 000000000000..480d9f7460ab --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/cortex-a53/bus.json @@ -0,0 +1,22 @@ +[ + {, + "EventCode": "0x60", + "EventName": "BUS_ACCESS_LD", + "BriefDescription": "Bus access - Read" + }, + {, + "EventCode": "0x61", + "EventName": "BUS_ACCESS_ST", + "BriefDescription": "Bus access - Write" + }, + {, + "EventCode": "0xC0", + "EventName": "EXT_MEM_REQ", + "BriefDescription": "External memory request" + }, + {, + "EventCode": "0xC1", + "EventName": "EXT_MEM_REQ_NC", + "BriefDescription": "Non-cacheable external memory request" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/cache.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/cache.json new file mode 100644 index 000000000000..11baad6344b9 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/cortex-a53/cache.json @@ -0,0 +1,27 @@ +[ + {, + "EventCode": "0xC2", + "EventName": "PREFETCH_LINEFILL", + "BriefDescription": "Linefill because of prefetch" + }, + {, + "EventCode": "0xC3", + "EventName": "PREFETCH_LINEFILL_DROP", + "BriefDescription": "Instruction Cache Throttle occurred" + }, + {, + "EventCode": "0xC4", + "EventName": "READ_ALLOC_ENTER", + "BriefDescription": "Entering read allocate mode" + }, + {, + "EventCode": "0xC5", + "EventName": "READ_ALLOC", + "BriefDescription": "Read allocate mode" + }, + {, + "EventCode": "0xC8", + "EventName": "EXT_SNOOP", + "BriefDescription": "SCU Snooped data from another CPU for this CPU" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/memory.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/memory.json new file mode 100644 index 000000000000..480d9f7460ab --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/cortex-a53/memory.json @@ -0,0 +1,22 @@ +[ + {, + "EventCode": "0x60", + "EventName": "BUS_ACCESS_LD", + "BriefDescription": "Bus access - Read" + }, + {, + "EventCode": "0x61", + "EventName": "BUS_ACCESS_ST", + "BriefDescription": "Bus access - Write" + }, + {, + "EventCode": "0xC0", + "EventName": "EXT_MEM_REQ", + "BriefDescription": "External memory request" + }, + {, + "EventCode": "0xC1", + "EventName": "EXT_MEM_REQ_NC", + "BriefDescription": "Non-cacheable external memory request" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/other.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/other.json new file mode 100644 index 000000000000..73a22402d003 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/cortex-a53/other.json @@ -0,0 +1,32 @@ +[ + {, + "EventCode": "0x86", + "EventName": "EXC_IRQ", + "BriefDescription": "Exception taken, IRQ" + }, + {, + "EventCode": "0x87", + "EventName": "EXC_FIQ", + "BriefDescription": "Exception taken, FIQ" + }, + {, + "EventCode": "0xC6", + "EventName": "PRE_DECODE_ERR", + "BriefDescription": "Pre-decode error" + }, + {, + "EventCode": "0xD0", + "EventName": "L1I_CACHE_ERR", + "BriefDescription": "L1 Instruction Cache (data or tag) memory error" + }, + {, + "EventCode": "0xD1", + "EventName": "L1D_CACHE_ERR", + "BriefDescription": "L1 Data Cache (data, tag or dirty) memory error, correctable or non-correctable" + }, + {, + "EventCode": "0xD2", + "EventName": "TLB_ERR", + "BriefDescription": "TLB memory error" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/pipeline.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/pipeline.json new file mode 100644 index 000000000000..3149fb90555a --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/cortex-a53/pipeline.json @@ -0,0 +1,52 @@ +[ + {, + "EventCode": "0xC7", + "EventName": "STALL_SB_FULL", + "BriefDescription": "Data Write operation that stalls the pipeline because the store buffer is full" + }, + {, + "EventCode": "0xE0", + "EventName": "OTHER_IQ_DEP_STALL", + "BriefDescription": "Cycles that the DPU IQ is empty and that is not because of a recent micro-TLB miss, instruction cache miss or pre-decode error" + }, + {, + "EventCode": "0xE1", + "EventName": "IC_DEP_STALL", + "BriefDescription": "Cycles the DPU IQ is empty and there is an instruction cache miss being processed" + }, + {, + "EventCode": "0xE2", + "EventName": "IUTLB_DEP_STALL", + "BriefDescription": "Cycles the DPU IQ is empty and there is an instruction micro-TLB miss being processed" + }, + {, + "EventCode": "0xE3", + "EventName": "DECODE_DEP_STALL", + "BriefDescription": "Cycles the DPU IQ is empty and there is a pre-decode error being processed" + }, + {, + "EventCode": "0xE4", + "EventName": "OTHER_INTERLOCK_STALL", + "BriefDescription": "Cycles there is an interlock other than Advanced SIMD/Floating-point instructions or load/store instruction" + }, + {, + "EventCode": "0xE5", + "EventName": "AGU_DEP_STALL", + "BriefDescription": "Cycles there is an interlock for a load/store instruction waiting for data to calculate the address in the AGU" + }, + {, + "EventCode": "0xE6", + "EventName": "SIMD_DEP_STALL", + "BriefDescription": "Cycles there is an interlock for an Advanced SIMD/Floating-point operation." + }, + {, + "EventCode": "0xE7", + "EventName": "LD_DEP_STALL", + "BriefDescription": "Cycles there is a stall in the Wr stage because of a load miss" + }, + {, + "EventCode": "0xE8", + "EventName": "ST_DEP_STALL", + "BriefDescription": "Cycles there is a stall in the Wr stage because of a store" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/mapfile.csv b/tools/perf/pmu-events/arch/arm64/mapfile.csv index 219d6756134e..e61c9ca6cf9e 100644 --- a/tools/perf/pmu-events/arch/arm64/mapfile.csv +++ b/tools/perf/pmu-events/arch/arm64/mapfile.csv @@ -13,3 +13,4 @@ # #Family-model,Version,Filename,EventType 0x00000000420f5160,v1,cavium,core +0x00000000410fd03[[:xdigit:]],v1,cortex-a53,core diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c index 4035d43523c3..e0b1b414d466 100644 --- a/tools/perf/tests/backward-ring-buffer.c +++ b/tools/perf/tests/backward-ring-buffer.c @@ -31,10 +31,12 @@ static int count_samples(struct perf_evlist *evlist, int *sample_count, int i; for (i = 0; i < evlist->nr_mmaps; i++) { + struct perf_mmap *map = &evlist->overwrite_mmap[i]; union perf_event *event; + u64 start, end; - perf_mmap__read_catchup(&evlist->overwrite_mmap[i]); - while ((event = perf_mmap__read_backward(&evlist->overwrite_mmap[i])) != NULL) { + perf_mmap__read_init(map, true, &start, &end); + while ((event = perf_mmap__read_event(map, true, &start, end)) != NULL) { const u32 type = event->header.type; switch (type) { @@ -49,6 +51,7 @@ static int count_samples(struct perf_evlist *evlist, int *sample_count, return TEST_FAIL; } } + perf_mmap__read_done(map); } return TEST_OK; } diff --git a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh index 8b3da21a08f1..c446c894b297 100755 --- a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh +++ b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh @@ -22,10 +22,23 @@ trace_libc_inet_pton_backtrace() { expected[4]="rtt min.*" expected[5]="[0-9]+\.[0-9]+[[:space:]]+probe_libc:inet_pton:\([[:xdigit:]]+\)" expected[6]=".*inet_pton[[:space:]]\($libc\)$" - expected[7]="getaddrinfo[[:space:]]\($libc\)$" - expected[8]=".*\(.*/bin/ping.*\)$" - - perf trace --no-syscalls -e probe_libc:inet_pton/max-stack=3/ ping -6 -c 1 ::1 2>&1 | grep -v ^$ | while read line ; do + case "$(uname -m)" in + s390x) + eventattr='call-graph=dwarf' + expected[7]="gaih_inet[[:space:]]\(inlined\)$" + expected[8]="__GI_getaddrinfo[[:space:]]\(inlined\)$" + expected[9]="main[[:space:]]\(.*/bin/ping.*\)$" + expected[10]="__libc_start_main[[:space:]]\($libc\)$" + expected[11]="_start[[:space:]]\(.*/bin/ping.*\)$" + ;; + *) + eventattr='max-stack=3' + expected[7]="getaddrinfo[[:space:]]\($libc\)$" + expected[8]=".*\(.*/bin/ping.*\)$" + ;; + esac + + perf trace --no-syscalls -e probe_libc:inet_pton/$eventattr/ ping -6 -c 1 ::1 2>&1 | grep -v ^$ | while read line ; do echo $line echo "$line" | egrep -q "${expected[$idx]}" if [ $? -ne 0 ] ; then @@ -33,7 +46,7 @@ trace_libc_inet_pton_backtrace() { exit 1 fi let idx+=1 - [ $idx -eq 9 ] && break + [ -z "${expected[$idx]}" ] && break done } diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 68146f4620a5..6495ee55d9c3 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -608,7 +608,8 @@ static int hist_browser__title(struct hist_browser *browser, char *bf, size_t si return browser->title ? browser->title(browser, bf, size) : 0; } -int hist_browser__run(struct hist_browser *browser, const char *help) +int hist_browser__run(struct hist_browser *browser, const char *help, + bool warn_lost_event) { int key; char title[160]; @@ -638,8 +639,9 @@ int hist_browser__run(struct hist_browser *browser, const char *help) nr_entries = hist_browser__nr_entries(browser); ui_browser__update_nr_entries(&browser->b, nr_entries); - if (browser->hists->stats.nr_lost_warned != - browser->hists->stats.nr_events[PERF_RECORD_LOST]) { + if (warn_lost_event && + (browser->hists->stats.nr_lost_warned != + browser->hists->stats.nr_events[PERF_RECORD_LOST])) { browser->hists->stats.nr_lost_warned = browser->hists->stats.nr_events[PERF_RECORD_LOST]; ui_browser__warn_lost_events(&browser->b); @@ -2763,7 +2765,8 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, bool left_exits, struct hist_browser_timer *hbt, float min_pcnt, - struct perf_env *env) + struct perf_env *env, + bool warn_lost_event) { struct hists *hists = evsel__hists(evsel); struct hist_browser *browser = perf_evsel_browser__new(evsel, hbt, env); @@ -2844,7 +2847,8 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, nr_options = 0; - key = hist_browser__run(browser, helpline); + key = hist_browser__run(browser, helpline, + warn_lost_event); if (browser->he_selection != NULL) { thread = hist_browser__selected_thread(browser); @@ -3184,7 +3188,8 @@ static void perf_evsel_menu__write(struct ui_browser *browser, static int perf_evsel_menu__run(struct perf_evsel_menu *menu, int nr_events, const char *help, - struct hist_browser_timer *hbt) + struct hist_browser_timer *hbt, + bool warn_lost_event) { struct perf_evlist *evlist = menu->b.priv; struct perf_evsel *pos; @@ -3203,7 +3208,9 @@ static int perf_evsel_menu__run(struct perf_evsel_menu *menu, case K_TIMER: hbt->timer(hbt->arg); - if (!menu->lost_events_warned && menu->lost_events) { + if (!menu->lost_events_warned && + menu->lost_events && + warn_lost_event) { ui_browser__warn_lost_events(&menu->b); menu->lost_events_warned = true; } @@ -3224,7 +3231,8 @@ browse_hists: key = perf_evsel__hists_browse(pos, nr_events, help, true, hbt, menu->min_pcnt, - menu->env); + menu->env, + warn_lost_event); ui_browser__show_title(&menu->b, title); switch (key) { case K_TAB: @@ -3282,7 +3290,8 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist, int nr_entries, const char *help, struct hist_browser_timer *hbt, float min_pcnt, - struct perf_env *env) + struct perf_env *env, + bool warn_lost_event) { struct perf_evsel *pos; struct perf_evsel_menu menu = { @@ -3309,13 +3318,15 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist, menu.b.width = line_len; } - return perf_evsel_menu__run(&menu, nr_entries, help, hbt); + return perf_evsel_menu__run(&menu, nr_entries, help, + hbt, warn_lost_event); } int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, struct hist_browser_timer *hbt, float min_pcnt, - struct perf_env *env) + struct perf_env *env, + bool warn_lost_event) { int nr_entries = evlist->nr_entries; @@ -3325,7 +3336,7 @@ single_entry: return perf_evsel__hists_browse(first, nr_entries, help, false, hbt, min_pcnt, - env); + env, warn_lost_event); } if (symbol_conf.event_group) { @@ -3342,5 +3353,6 @@ single_entry: } return __perf_evlist__tui_browse_hists(evlist, nr_entries, help, - hbt, min_pcnt, env); + hbt, min_pcnt, env, + warn_lost_event); } diff --git a/tools/perf/ui/browsers/hists.h b/tools/perf/ui/browsers/hists.h index ba431777f559..9428bee076f2 100644 --- a/tools/perf/ui/browsers/hists.h +++ b/tools/perf/ui/browsers/hists.h @@ -28,7 +28,8 @@ struct hist_browser { struct hist_browser *hist_browser__new(struct hists *hists); void hist_browser__delete(struct hist_browser *browser); -int hist_browser__run(struct hist_browser *browser, const char *help); +int hist_browser__run(struct hist_browser *browser, const char *help, + bool warn_lost_event); void hist_browser__init(struct hist_browser *browser, struct hists *hists); #endif /* _PERF_UI_BROWSER_HISTS_H_ */ diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index ac35cd214feb..e5fc14e53c05 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -715,28 +715,11 @@ union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist, int return perf_mmap__read_forward(md); } -union perf_event *perf_evlist__mmap_read_backward(struct perf_evlist *evlist, int idx) -{ - struct perf_mmap *md = &evlist->mmap[idx]; - - /* - * No need to check messup for backward ring buffer: - * We can always read arbitrary long data from a backward - * ring buffer unless we forget to pause it before reading. - */ - return perf_mmap__read_backward(md); -} - union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) { return perf_evlist__mmap_read_forward(evlist, idx); } -void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx) -{ - perf_mmap__read_catchup(&evlist->mmap[idx]); -} - void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx) { perf_mmap__consume(&evlist->mmap[idx], false); diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 75f8e0ad5d76..336b838e6957 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -133,10 +133,6 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx); union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist, int idx); -union perf_event *perf_evlist__mmap_read_backward(struct perf_evlist *evlist, - int idx); -void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx); - void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx); int perf_evlist__open(struct perf_evlist *evlist); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index ff359c9ece2e..ef351688b797 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -41,17 +41,7 @@ #include "sane_ctype.h" -static struct { - bool sample_id_all; - bool exclude_guest; - bool mmap2; - bool cloexec; - bool clockid; - bool clockid_wrong; - bool lbr_flags; - bool write_backward; - bool group_read; -} perf_missing_features; +struct perf_missing_features perf_missing_features; static clockid_t clockid; diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 846e41644525..a7487c6d1866 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -149,6 +149,20 @@ union u64_swap { u32 val32[2]; }; +struct perf_missing_features { + bool sample_id_all; + bool exclude_guest; + bool mmap2; + bool cloexec; + bool clockid; + bool clockid_wrong; + bool lbr_flags; + bool write_backward; + bool group_read; +}; + +extern struct perf_missing_features perf_missing_features; + struct cpu_map; struct target; struct thread_map; diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index f6630cb95eff..02721b579746 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -430,7 +430,8 @@ int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel, int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, struct hist_browser_timer *hbt, float min_pcnt, - struct perf_env *env); + struct perf_env *env, + bool warn_lost_event); int script_browse(const char *script_opt); #else static inline @@ -438,7 +439,8 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused, const char *help __maybe_unused, struct hist_browser_timer *hbt __maybe_unused, float min_pcnt __maybe_unused, - struct perf_env *env __maybe_unused) + struct perf_env *env __maybe_unused, + bool warn_lost_event __maybe_unused) { return 0; } diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c index 05076e683938..91531a7c8fbf 100644 --- a/tools/perf/util/mmap.c +++ b/tools/perf/util/mmap.c @@ -22,29 +22,27 @@ size_t perf_mmap__mmap_len(struct perf_mmap *map) /* When check_messup is true, 'end' must points to a good entry */ static union perf_event *perf_mmap__read(struct perf_mmap *map, - u64 start, u64 end, u64 *prev) + u64 *startp, u64 end) { unsigned char *data = map->base + page_size; union perf_event *event = NULL; - int diff = end - start; + int diff = end - *startp; if (diff >= (int)sizeof(event->header)) { size_t size; - event = (union perf_event *)&data[start & map->mask]; + event = (union perf_event *)&data[*startp & map->mask]; size = event->header.size; - if (size < sizeof(event->header) || diff < (int)size) { - event = NULL; - goto broken_event; - } + if (size < sizeof(event->header) || diff < (int)size) + return NULL; /* * Event straddles the mmap boundary -- header should always * be inside due to u64 alignment of output. */ - if ((start & map->mask) + size != ((start + size) & map->mask)) { - unsigned int offset = start; + if ((*startp & map->mask) + size != ((*startp + size) & map->mask)) { + unsigned int offset = *startp; unsigned int len = min(sizeof(*event), size), cpy; void *dst = map->event_copy; @@ -59,20 +57,19 @@ static union perf_event *perf_mmap__read(struct perf_mmap *map, event = (union perf_event *)map->event_copy; } - start += size; + *startp += size; } -broken_event: - if (prev) - *prev = start; - return event; } +/* + * legacy interface for mmap read. + * Don't use it. Use perf_mmap__read_event(). + */ union perf_event *perf_mmap__read_forward(struct perf_mmap *map) { u64 head; - u64 old = map->prev; /* * Check if event was unmapped due to a POLLHUP/POLLERR. @@ -82,13 +79,26 @@ union perf_event *perf_mmap__read_forward(struct perf_mmap *map) head = perf_mmap__read_head(map); - return perf_mmap__read(map, old, head, &map->prev); + return perf_mmap__read(map, &map->prev, head); } -union perf_event *perf_mmap__read_backward(struct perf_mmap *map) +/* + * Read event from ring buffer one by one. + * Return one event for each call. + * + * Usage: + * perf_mmap__read_init() + * while(event = perf_mmap__read_event()) { + * //process the event + * perf_mmap__consume() + * } + * perf_mmap__read_done() + */ +union perf_event *perf_mmap__read_event(struct perf_mmap *map, + bool overwrite, + u64 *startp, u64 end) { - u64 head, end; - u64 start = map->prev; + union perf_event *event; /* * Check if event was unmapped due to a POLLHUP/POLLERR. @@ -96,40 +106,19 @@ union perf_event *perf_mmap__read_backward(struct perf_mmap *map) if (!refcount_read(&map->refcnt)) return NULL; - head = perf_mmap__read_head(map); - if (!head) + if (startp == NULL) return NULL; - /* - * 'head' pointer starts from 0. Kernel minus sizeof(record) form - * it each time when kernel writes to it, so in fact 'head' is - * negative. 'end' pointer is made manually by adding the size of - * the ring buffer to 'head' pointer, means the validate data can - * read is the whole ring buffer. If 'end' is positive, the ring - * buffer has not fully filled, so we must adjust 'end' to 0. - * - * However, since both 'head' and 'end' is unsigned, we can't - * simply compare 'end' against 0. Here we compare '-head' and - * the size of the ring buffer, where -head is the number of bytes - * kernel write to the ring buffer. - */ - if (-head < (u64)(map->mask + 1)) - end = 0; - else - end = head + map->mask + 1; - - return perf_mmap__read(map, start, end, &map->prev); -} + /* non-overwirte doesn't pause the ringbuffer */ + if (!overwrite) + end = perf_mmap__read_head(map); -void perf_mmap__read_catchup(struct perf_mmap *map) -{ - u64 head; + event = perf_mmap__read(map, startp, end); - if (!refcount_read(&map->refcnt)) - return; + if (!overwrite) + map->prev = *startp; - head = perf_mmap__read_head(map); - map->prev = head; + return event; } static bool perf_mmap__empty(struct perf_mmap *map) @@ -267,41 +256,60 @@ static int overwrite_rb_find_range(void *buf, int mask, u64 head, u64 *start, u6 return -1; } -int perf_mmap__push(struct perf_mmap *md, bool overwrite, - void *to, int push(void *to, void *buf, size_t size)) +/* + * Report the start and end of the available data in ringbuffer + */ +int perf_mmap__read_init(struct perf_mmap *md, bool overwrite, + u64 *startp, u64 *endp) { u64 head = perf_mmap__read_head(md); u64 old = md->prev; - u64 end = head, start = old; unsigned char *data = md->base + page_size; unsigned long size; - void *buf; - int rc = 0; - start = overwrite ? head : old; - end = overwrite ? old : head; + *startp = overwrite ? head : old; + *endp = overwrite ? old : head; - if (start == end) - return 0; + if (*startp == *endp) + return -EAGAIN; - size = end - start; + size = *endp - *startp; if (size > (unsigned long)(md->mask) + 1) { if (!overwrite) { WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n"); md->prev = head; perf_mmap__consume(md, overwrite); - return 0; + return -EAGAIN; } /* * Backward ring buffer is full. We still have a chance to read * most of data from it. */ - if (overwrite_rb_find_range(data, md->mask, head, &start, &end)) - return -1; + if (overwrite_rb_find_range(data, md->mask, head, startp, endp)) + return -EINVAL; } + return 0; +} + +int perf_mmap__push(struct perf_mmap *md, bool overwrite, + void *to, int push(void *to, void *buf, size_t size)) +{ + u64 head = perf_mmap__read_head(md); + u64 end, start; + unsigned char *data = md->base + page_size; + unsigned long size; + void *buf; + int rc = 0; + + rc = perf_mmap__read_init(md, overwrite, &start, &end); + if (rc < 0) + return (rc == -EAGAIN) ? 0 : -1; + + size = end - start; + if ((start & md->mask) + size != (end & md->mask)) { buf = &data[start & md->mask]; size = md->mask + 1 - (start & md->mask); @@ -327,3 +335,14 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite, out: return rc; } + +/* + * Mandatory for overwrite mode + * The direction of overwrite mode is backward. + * The last perf_mmap__read() will set tail to map->prev. + * Need to correct the map->prev to head which is the end of next read. + */ +void perf_mmap__read_done(struct perf_mmap *map) +{ + map->prev = perf_mmap__read_head(map); +} diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h index e43d7b55a55f..ec7d3a24e276 100644 --- a/tools/perf/util/mmap.h +++ b/tools/perf/util/mmap.h @@ -65,8 +65,6 @@ void perf_mmap__put(struct perf_mmap *map); void perf_mmap__consume(struct perf_mmap *map, bool overwrite); -void perf_mmap__read_catchup(struct perf_mmap *md); - static inline u64 perf_mmap__read_head(struct perf_mmap *mm) { struct perf_event_mmap_page *pc = mm->base; @@ -87,11 +85,17 @@ static inline void perf_mmap__write_tail(struct perf_mmap *md, u64 tail) } union perf_event *perf_mmap__read_forward(struct perf_mmap *map); -union perf_event *perf_mmap__read_backward(struct perf_mmap *map); + +union perf_event *perf_mmap__read_event(struct perf_mmap *map, + bool overwrite, + u64 *startp, u64 end); int perf_mmap__push(struct perf_mmap *md, bool backward, void *to, int push(void *to, void *buf, size_t size)); size_t perf_mmap__mmap_len(struct perf_mmap *map); +int perf_mmap__read_init(struct perf_mmap *md, bool overwrite, + u64 *startp, u64 *endp); +void perf_mmap__read_done(struct perf_mmap *map); #endif /*__PERF_MMAP_H */ diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 443892dabedb..1019bbc5dbd8 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -340,35 +340,15 @@ size_t hex_width(u64 v) return n; } -static int hex(char ch) -{ - if ((ch >= '0') && (ch <= '9')) - return ch - '0'; - if ((ch >= 'a') && (ch <= 'f')) - return ch - 'a' + 10; - if ((ch >= 'A') && (ch <= 'F')) - return ch - 'A' + 10; - return -1; -} - /* * While we find nice hex chars, build a long_val. * Return number of chars processed. */ int hex2u64(const char *ptr, u64 *long_val) { - const char *p = ptr; - *long_val = 0; - - while (*p) { - const int hex_val = hex(*p); + char *p; - if (hex_val < 0) - break; - - *long_val = (*long_val << 4) | hex_val; - p++; - } + *long_val = strtoull(ptr, &p, 16); return p - ptr; } diff --git a/tools/power/acpi/Makefile.config b/tools/power/acpi/Makefile.config index a1883bbb0144..2cccbba64418 100644 --- a/tools/power/acpi/Makefile.config +++ b/tools/power/acpi/Makefile.config @@ -56,9 +56,6 @@ INSTALL_SCRIPT = ${INSTALL_PROGRAM} # to compile vs uClibc, that can be done here as well. CROSS = #/usr/i386-linux-uclibc/usr/bin/i386-uclibc- CROSS_COMPILE ?= $(CROSS) -CC = $(CROSS_COMPILE)gcc -LD = $(CROSS_COMPILE)gcc -STRIP = $(CROSS_COMPILE)strip HOSTCC = gcc # check if compiler option is supported diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include index fcb3ed0be5f8..dd614463d4d6 100644 --- a/tools/scripts/Makefile.include +++ b/tools/scripts/Makefile.include @@ -42,6 +42,24 @@ EXTRA_WARNINGS += -Wformat CC_NO_CLANG := $(shell $(CC) -dM -E -x c /dev/null | grep -Fq "__clang__"; echo $$?) +# Makefiles suck: This macro sets a default value of $(2) for the +# variable named by $(1), unless the variable has been set by +# environment or command line. This is necessary for CC and AR +# because make sets default values, so the simpler ?= approach +# won't work as expected. +define allow-override + $(if $(or $(findstring environment,$(origin $(1))),\ + $(findstring command line,$(origin $(1)))),,\ + $(eval $(1) = $(2))) +endef + +# Allow setting various cross-compile vars or setting CROSS_COMPILE as a prefix. +$(call allow-override,CC,$(CROSS_COMPILE)gcc) +$(call allow-override,AR,$(CROSS_COMPILE)ar) +$(call allow-override,LD,$(CROSS_COMPILE)ld) +$(call allow-override,CXX,$(CROSS_COMPILE)g++) +$(call allow-override,STRIP,$(CROSS_COMPILE)strip) + ifeq ($(CC_NO_CLANG), 1) EXTRA_WARNINGS += -Wstrict-aliasing=3 endif diff --git a/tools/spi/Makefile b/tools/spi/Makefile index 90615e10c79a..815d15589177 100644 --- a/tools/spi/Makefile +++ b/tools/spi/Makefile @@ -11,8 +11,6 @@ endif # (this improves performance and avoids hard-to-debug behaviour); MAKEFLAGS += -r -CC = $(CROSS_COMPILE)gcc -LD = $(CROSS_COMPILE)ld CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include ALL_TARGETS := spidev_test spidev_fdx diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index cc15af2e54fe..9cf83f895d98 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -11,3 +11,4 @@ test_progs test_tcpbpf_user test_verifier_log feature +test_libbpf_open diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 5c43c187f27c..8567a858b789 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -35,12 +35,14 @@ TEST_GEN_PROGS_EXTENDED = test_libbpf_open include ../lib.mk -BPFOBJ := $(OUTPUT)/libbpf.a cgroup_helpers.c +BPFOBJ := $(OUTPUT)/libbpf.a $(TEST_GEN_PROGS): $(BPFOBJ) $(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/libbpf.a +$(OUTPUT)/test_dev_cgroup: cgroup_helpers.c + .PHONY: force # force a rebuild of BPFOBJ when its dependencies are updated diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 436c4c72414f..9e03a4c356a4 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -126,6 +126,8 @@ static void test_hashmap_sizes(int task, void *data) fd = bpf_create_map(BPF_MAP_TYPE_HASH, i, j, 2, map_flags); if (fd < 0) { + if (errno == ENOMEM) + return; printf("Failed to create hashmap key=%d value=%d '%s'\n", i, j, strerror(errno)); exit(1); diff --git a/tools/testing/selftests/bpf/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/test_tcpbpf_kern.c index 57119ad57a3f..3e645ee41ed5 100644 --- a/tools/testing/selftests/bpf/test_tcpbpf_kern.c +++ b/tools/testing/selftests/bpf/test_tcpbpf_kern.c @@ -5,7 +5,6 @@ #include <linux/if_ether.h> #include <linux/if_packet.h> #include <linux/ip.h> -#include <linux/in6.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/tcp.h> diff --git a/tools/testing/selftests/bpf/test_tcpbpf_user.c b/tools/testing/selftests/bpf/test_tcpbpf_user.c index 95a370f3d378..5d73db416460 100644 --- a/tools/testing/selftests/bpf/test_tcpbpf_user.c +++ b/tools/testing/selftests/bpf/test_tcpbpf_user.c @@ -11,6 +11,8 @@ #include <linux/ptrace.h> #include <linux/bpf.h> #include <sys/ioctl.h> +#include <sys/time.h> +#include <sys/resource.h> #include <sys/types.h> #include <sys/stat.h> #include <fcntl.h> @@ -42,6 +44,7 @@ static int bpf_find_map(const char *test, struct bpf_object *obj, int main(int argc, char **argv) { + struct rlimit limit = { RLIM_INFINITY, RLIM_INFINITY }; const char *file = "test_tcpbpf_kern.o"; struct tcpbpf_globals g = {0}; int cg_fd, prog_fd, map_fd; @@ -54,6 +57,9 @@ int main(int argc, char **argv) int pid; int rv; + if (setrlimit(RLIMIT_MEMLOCK, &limit) < 0) + perror("Unable to lift memlock rlimit"); + if (argc > 1 && strcmp(argv[1], "-d") == 0) debug_flag = true; diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index c0f16e93f9bd..2164d218322e 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -57,6 +57,9 @@ #define F_NEEDS_EFFICIENT_UNALIGNED_ACCESS (1 << 0) #define F_LOAD_WITH_STRICT_ALIGNMENT (1 << 1) +#define UNPRIV_SYSCTL "kernel/unprivileged_bpf_disabled" +static bool unpriv_disabled = false; + struct bpf_test { const char *descr; struct bpf_insn insns[MAX_INSNS]; @@ -2587,6 +2590,32 @@ static struct bpf_test tests[] = { .result = ACCEPT, }, { + "runtime/jit: pass negative index to tail_call", + .insns = { + BPF_MOV64_IMM(BPF_REG_3, -1), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_tail_call), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_prog = { 1 }, + .result = ACCEPT, + }, + { + "runtime/jit: pass > 32bit index to tail_call", + .insns = { + BPF_LD_IMM64(BPF_REG_3, 0x100000000ULL), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_tail_call), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_prog = { 2 }, + .result = ACCEPT, + }, + { "stack pointer arithmetic", .insns = { BPF_MOV64_IMM(BPF_REG_1, 4), @@ -11137,6 +11166,95 @@ static struct bpf_test tests[] = { .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, + { + "jit: lsh, rsh, arsh by 1", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_MOV64_IMM(BPF_REG_1, 0xff), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 1), + BPF_ALU32_IMM(BPF_LSH, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0x3fc, 1), + BPF_EXIT_INSN(), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 1), + BPF_ALU32_IMM(BPF_RSH, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0xff, 1), + BPF_EXIT_INSN(), + BPF_ALU64_IMM(BPF_ARSH, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0x7f, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 2, + }, + { + "jit: mov32 for ldimm64, 1", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_LD_IMM64(BPF_REG_1, 0xfeffffffffffffffULL), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 32), + BPF_LD_IMM64(BPF_REG_2, 0xfeffffffULL), + BPF_JMP_REG(BPF_JEQ, BPF_REG_1, BPF_REG_2, 1), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 2, + }, + { + "jit: mov32 for ldimm64, 2", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_IMM64(BPF_REG_1, 0x1ffffffffULL), + BPF_LD_IMM64(BPF_REG_2, 0xffffffffULL), + BPF_JMP_REG(BPF_JEQ, BPF_REG_1, BPF_REG_2, 1), + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 2, + }, + { + "jit: various mul tests", + .insns = { + BPF_LD_IMM64(BPF_REG_2, 0xeeff0d413122ULL), + BPF_LD_IMM64(BPF_REG_0, 0xfefefeULL), + BPF_LD_IMM64(BPF_REG_1, 0xefefefULL), + BPF_ALU64_REG(BPF_MUL, BPF_REG_0, BPF_REG_1), + BPF_JMP_REG(BPF_JEQ, BPF_REG_0, BPF_REG_2, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_LD_IMM64(BPF_REG_3, 0xfefefeULL), + BPF_ALU64_REG(BPF_MUL, BPF_REG_3, BPF_REG_1), + BPF_JMP_REG(BPF_JEQ, BPF_REG_3, BPF_REG_2, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_MOV32_REG(BPF_REG_2, BPF_REG_2), + BPF_LD_IMM64(BPF_REG_0, 0xfefefeULL), + BPF_ALU32_REG(BPF_MUL, BPF_REG_0, BPF_REG_1), + BPF_JMP_REG(BPF_JEQ, BPF_REG_0, BPF_REG_2, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_LD_IMM64(BPF_REG_3, 0xfefefeULL), + BPF_ALU32_REG(BPF_MUL, BPF_REG_3, BPF_REG_1), + BPF_JMP_REG(BPF_JEQ, BPF_REG_3, BPF_REG_2, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_LD_IMM64(BPF_REG_0, 0x952a7bbcULL), + BPF_LD_IMM64(BPF_REG_1, 0xfefefeULL), + BPF_LD_IMM64(BPF_REG_2, 0xeeff0d413122ULL), + BPF_ALU32_REG(BPF_MUL, BPF_REG_2, BPF_REG_1), + BPF_JMP_REG(BPF_JEQ, BPF_REG_2, BPF_REG_0, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 2, + }, + }; static int probe_filter_length(const struct bpf_insn *fp) @@ -11291,7 +11409,8 @@ static void do_test_single(struct bpf_test *test, bool unpriv, goto fail_log; } if (!strstr(bpf_vlog, expected_err) && !reject_from_alignment) { - printf("FAIL\nUnexpected error message!\n"); + printf("FAIL\nUnexpected error message!\n\tEXP: %s\n\tRES: %s\n", + expected_err, bpf_vlog); goto fail_log; } } @@ -11375,9 +11494,20 @@ out: return ret; } +static void get_unpriv_disabled() +{ + char buf[2]; + FILE *fd; + + fd = fopen("/proc/sys/"UNPRIV_SYSCTL, "r"); + if (fgets(buf, 2, fd) == buf && atoi(buf)) + unpriv_disabled = true; + fclose(fd); +} + static int do_test(bool unpriv, unsigned int from, unsigned int to) { - int i, passes = 0, errors = 0; + int i, passes = 0, errors = 0, skips = 0; for (i = from; i < to; i++) { struct bpf_test *test = &tests[i]; @@ -11385,7 +11515,10 @@ static int do_test(bool unpriv, unsigned int from, unsigned int to) /* Program types that are not supported by non-root we * skip right away. */ - if (!test->prog_type) { + if (!test->prog_type && unpriv_disabled) { + printf("#%d/u %s SKIP\n", i, test->descr); + skips++; + } else if (!test->prog_type) { if (!unpriv) set_admin(false); printf("#%d/u %s ", i, test->descr); @@ -11394,13 +11527,17 @@ static int do_test(bool unpriv, unsigned int from, unsigned int to) set_admin(true); } - if (!unpriv) { + if (unpriv) { + printf("#%d/p %s SKIP\n", i, test->descr); + skips++; + } else { printf("#%d/p %s ", i, test->descr); do_test_single(test, false, &passes, &errors); } } - printf("Summary: %d PASSED, %d FAILED\n", passes, errors); + printf("Summary: %d PASSED, %d SKIPPED, %d FAILED\n", passes, + skips, errors); return errors ? EXIT_FAILURE : EXIT_SUCCESS; } @@ -11428,6 +11565,13 @@ int main(int argc, char **argv) } } + get_unpriv_disabled(); + if (unpriv && unpriv_disabled) { + printf("Cannot run as unprivileged user with sysctl %s.\n", + UNPRIV_SYSCTL); + return EXIT_FAILURE; + } + setrlimit(RLIMIT_MEMLOCK, unpriv ? &rlim : &rinf); return do_test(unpriv, from, to); } diff --git a/tools/testing/selftests/memfd/Makefile b/tools/testing/selftests/memfd/Makefile index a5276a91dfbf..0862e6f47a38 100644 --- a/tools/testing/selftests/memfd/Makefile +++ b/tools/testing/selftests/memfd/Makefile @@ -5,6 +5,7 @@ CFLAGS += -I../../../../include/ CFLAGS += -I../../../../usr/include/ TEST_PROGS := run_tests.sh +TEST_FILES := run_fuse_test.sh TEST_GEN_FILES := memfd_test fuse_mnt fuse_test fuse_mnt.o: CFLAGS += $(shell pkg-config fuse --cflags) diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index d7c30d366935..229a038966e3 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -5,7 +5,7 @@ CFLAGS = -Wall -Wl,--no-as-needed -O2 -g CFLAGS += -I../../../../usr/include/ TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh -TEST_PROGS += fib_tests.sh +TEST_PROGS += fib_tests.sh fib-onlink-tests.sh TEST_GEN_FILES = socket TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa diff --git a/tools/testing/selftests/net/fib-onlink-tests.sh b/tools/testing/selftests/net/fib-onlink-tests.sh new file mode 100755 index 000000000000..06b1d7cc12cc --- /dev/null +++ b/tools/testing/selftests/net/fib-onlink-tests.sh @@ -0,0 +1,375 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# IPv4 and IPv6 onlink tests + +PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no} + +# Network interfaces +# - odd in current namespace; even in peer ns +declare -A NETIFS +# default VRF +NETIFS[p1]=veth1 +NETIFS[p2]=veth2 +NETIFS[p3]=veth3 +NETIFS[p4]=veth4 +# VRF +NETIFS[p5]=veth5 +NETIFS[p6]=veth6 +NETIFS[p7]=veth7 +NETIFS[p8]=veth8 + +# /24 network +declare -A V4ADDRS +V4ADDRS[p1]=169.254.1.1 +V4ADDRS[p2]=169.254.1.2 +V4ADDRS[p3]=169.254.3.1 +V4ADDRS[p4]=169.254.3.2 +V4ADDRS[p5]=169.254.5.1 +V4ADDRS[p6]=169.254.5.2 +V4ADDRS[p7]=169.254.7.1 +V4ADDRS[p8]=169.254.7.2 + +# /64 network +declare -A V6ADDRS +V6ADDRS[p1]=2001:db8:101::1 +V6ADDRS[p2]=2001:db8:101::2 +V6ADDRS[p3]=2001:db8:301::1 +V6ADDRS[p4]=2001:db8:301::2 +V6ADDRS[p5]=2001:db8:501::1 +V6ADDRS[p6]=2001:db8:501::2 +V6ADDRS[p7]=2001:db8:701::1 +V6ADDRS[p8]=2001:db8:701::2 + +# Test networks: +# [1] = default table +# [2] = VRF +# +# /32 host routes +declare -A TEST_NET4 +TEST_NET4[1]=169.254.101 +TEST_NET4[2]=169.254.102 +# /128 host routes +declare -A TEST_NET6 +TEST_NET6[1]=2001:db8:101 +TEST_NET6[2]=2001:db8:102 + +# connected gateway +CONGW[1]=169.254.1.254 +CONGW[2]=169.254.5.254 + +# recursive gateway +RECGW4[1]=169.254.11.254 +RECGW4[2]=169.254.12.254 +RECGW6[1]=2001:db8:11::64 +RECGW6[2]=2001:db8:12::64 + +# for v4 mapped to v6 +declare -A TEST_NET4IN6IN6 +TEST_NET4IN6[1]=10.1.1.254 +TEST_NET4IN6[2]=10.2.1.254 + +# mcast address +MCAST6=ff02::1 + + +PEER_NS=bart +PEER_CMD="ip netns exec ${PEER_NS}" +VRF=lisa +VRF_TABLE=1101 +PBR_TABLE=101 + +################################################################################ +# utilities + +log_test() +{ + local rc=$1 + local expected=$2 + local msg="$3" + + if [ ${rc} -eq ${expected} ]; then + nsuccess=$((nsuccess+1)) + printf "\n TEST: %-50s [ OK ]\n" "${msg}" + else + nfail=$((nfail+1)) + printf "\n TEST: %-50s [FAIL]\n" "${msg}" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + fi +} + +log_section() +{ + echo + echo "######################################################################" + echo "TEST SECTION: $*" + echo "######################################################################" +} + +log_subsection() +{ + echo + echo "#########################################" + echo "TEST SUBSECTION: $*" +} + +run_cmd() +{ + echo + echo "COMMAND: $*" + eval $* +} + +get_linklocal() +{ + local dev=$1 + local pfx + local addr + + addr=$(${pfx} ip -6 -br addr show dev ${dev} | \ + awk '{ + for (i = 3; i <= NF; ++i) { + if ($i ~ /^fe80/) + print $i + } + }' + ) + addr=${addr/\/*} + + [ -z "$addr" ] && return 1 + + echo $addr + + return 0 +} + +################################################################################ +# + +setup() +{ + echo + echo "########################################" + echo "Configuring interfaces" + + set -e + + # create namespace + ip netns add ${PEER_NS} + ip -netns ${PEER_NS} li set lo up + + # add vrf table + ip li add ${VRF} type vrf table ${VRF_TABLE} + ip li set ${VRF} up + ip ro add table ${VRF_TABLE} unreachable default + ip -6 ro add table ${VRF_TABLE} unreachable default + + # create test interfaces + ip li add ${NETIFS[p1]} type veth peer name ${NETIFS[p2]} + ip li add ${NETIFS[p3]} type veth peer name ${NETIFS[p4]} + ip li add ${NETIFS[p5]} type veth peer name ${NETIFS[p6]} + ip li add ${NETIFS[p7]} type veth peer name ${NETIFS[p8]} + + # enslave vrf interfaces + for n in 5 7; do + ip li set ${NETIFS[p${n}]} vrf ${VRF} + done + + # add addresses + for n in 1 3 5 7; do + ip li set ${NETIFS[p${n}]} up + ip addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]} + ip addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} + done + + # move peer interfaces to namespace and add addresses + for n in 2 4 6 8; do + ip li set ${NETIFS[p${n}]} netns ${PEER_NS} up + ip -netns ${PEER_NS} addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]} + ip -netns ${PEER_NS} addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} + done + + set +e + + # let DAD complete - assume default of 1 probe + sleep 1 +} + +cleanup() +{ + # make sure we start from a clean slate + ip netns del ${PEER_NS} 2>/dev/null + for n in 1 3 5 7; do + ip link del ${NETIFS[p${n}]} 2>/dev/null + done + ip link del ${VRF} 2>/dev/null + ip ro flush table ${VRF_TABLE} + ip -6 ro flush table ${VRF_TABLE} +} + +################################################################################ +# IPv4 tests +# + +run_ip() +{ + local table="$1" + local prefix="$2" + local gw="$3" + local dev="$4" + local exp_rc="$5" + local desc="$6" + + # dev arg may be empty + [ -n "${dev}" ] && dev="dev ${dev}" + + run_cmd ip ro add table "${table}" "${prefix}"/32 via "${gw}" "${dev}" onlink + log_test $? ${exp_rc} "${desc}" +} + +valid_onlink_ipv4() +{ + # - unicast connected, unicast recursive + # + log_subsection "default VRF - main table" + + run_ip 254 ${TEST_NET4[1]}.1 ${CONGW[1]} ${NETIFS[p1]} 0 "unicast connected" + run_ip 254 ${TEST_NET4[1]}.2 ${RECGW4[1]} ${NETIFS[p1]} 0 "unicast recursive" + + log_subsection "VRF ${VRF}" + + run_ip ${VRF_TABLE} ${TEST_NET4[2]}.1 ${CONGW[2]} ${NETIFS[p5]} 0 "unicast connected" + run_ip ${VRF_TABLE} ${TEST_NET4[2]}.2 ${RECGW4[2]} ${NETIFS[p5]} 0 "unicast recursive" + + log_subsection "VRF device, PBR table" + + run_ip ${PBR_TABLE} ${TEST_NET4[2]}.3 ${CONGW[2]} ${NETIFS[p5]} 0 "unicast connected" + run_ip ${PBR_TABLE} ${TEST_NET4[2]}.4 ${RECGW4[2]} ${NETIFS[p5]} 0 "unicast recursive" +} + +invalid_onlink_ipv4() +{ + run_ip 254 ${TEST_NET4[1]}.11 ${V4ADDRS[p1]} ${NETIFS[p1]} 2 \ + "Invalid gw - local unicast address" + + run_ip ${VRF_TABLE} ${TEST_NET4[2]}.11 ${V4ADDRS[p5]} ${NETIFS[p5]} 2 \ + "Invalid gw - local unicast address, VRF" + + run_ip 254 ${TEST_NET4[1]}.101 ${V4ADDRS[p1]} "" 2 "No nexthop device given" + + run_ip 254 ${TEST_NET4[1]}.102 ${V4ADDRS[p3]} ${NETIFS[p1]} 2 \ + "Gateway resolves to wrong nexthop device" + + run_ip ${VRF_TABLE} ${TEST_NET4[2]}.103 ${V4ADDRS[p7]} ${NETIFS[p5]} 2 \ + "Gateway resolves to wrong nexthop device - VRF" +} + +################################################################################ +# IPv6 tests +# + +run_ip6() +{ + local table="$1" + local prefix="$2" + local gw="$3" + local dev="$4" + local exp_rc="$5" + local desc="$6" + + # dev arg may be empty + [ -n "${dev}" ] && dev="dev ${dev}" + + run_cmd ip -6 ro add table "${table}" "${prefix}"/128 via "${gw}" "${dev}" onlink + log_test $? ${exp_rc} "${desc}" +} + +valid_onlink_ipv6() +{ + # - unicast connected, unicast recursive, v4-mapped + # + log_subsection "default VRF - main table" + + run_ip6 254 ${TEST_NET6[1]}::1 ${V6ADDRS[p1]/::*}::64 ${NETIFS[p1]} 0 "unicast connected" + run_ip6 254 ${TEST_NET6[1]}::2 ${RECGW6[1]} ${NETIFS[p1]} 0 "unicast recursive" + run_ip6 254 ${TEST_NET6[1]}::3 ::ffff:${TEST_NET4IN6[1]} ${NETIFS[p1]} 0 "v4-mapped" + + log_subsection "VRF ${VRF}" + + run_ip6 ${VRF_TABLE} ${TEST_NET6[2]}::1 ${V6ADDRS[p5]/::*}::64 ${NETIFS[p5]} 0 "unicast connected" + run_ip6 ${VRF_TABLE} ${TEST_NET6[2]}::2 ${RECGW6[2]} ${NETIFS[p5]} 0 "unicast recursive" + run_ip6 ${VRF_TABLE} ${TEST_NET6[2]}::3 ::ffff:${TEST_NET4IN6[2]} ${NETIFS[p5]} 0 "v4-mapped" + + log_subsection "VRF device, PBR table" + + run_ip6 ${PBR_TABLE} ${TEST_NET6[2]}::4 ${V6ADDRS[p5]/::*}::64 ${NETIFS[p5]} 0 "unicast connected" + run_ip6 ${PBR_TABLE} ${TEST_NET6[2]}::5 ${RECGW6[2]} ${NETIFS[p5]} 0 "unicast recursive" + run_ip6 ${PBR_TABLE} ${TEST_NET6[2]}::6 ::ffff:${TEST_NET4IN6[2]} ${NETIFS[p5]} 0 "v4-mapped" +} + +invalid_onlink_ipv6() +{ + local lladdr + + lladdr=$(get_linklocal ${NETIFS[p1]}) || return 1 + + run_ip6 254 ${TEST_NET6[1]}::11 ${V6ADDRS[p1]} ${NETIFS[p1]} 2 \ + "Invalid gw - local unicast address" + run_ip6 254 ${TEST_NET6[1]}::12 ${lladdr} ${NETIFS[p1]} 2 \ + "Invalid gw - local linklocal address" + run_ip6 254 ${TEST_NET6[1]}::12 ${MCAST6} ${NETIFS[p1]} 2 \ + "Invalid gw - multicast address" + + lladdr=$(get_linklocal ${NETIFS[p5]}) || return 1 + run_ip6 ${VRF_TABLE} ${TEST_NET6[2]}::11 ${V6ADDRS[p5]} ${NETIFS[p5]} 2 \ + "Invalid gw - local unicast address, VRF" + run_ip6 ${VRF_TABLE} ${TEST_NET6[2]}::12 ${lladdr} ${NETIFS[p5]} 2 \ + "Invalid gw - local linklocal address, VRF" + run_ip6 ${VRF_TABLE} ${TEST_NET6[2]}::12 ${MCAST6} ${NETIFS[p5]} 2 \ + "Invalid gw - multicast address, VRF" + + run_ip6 254 ${TEST_NET6[1]}::101 ${V6ADDRS[p1]} "" 2 \ + "No nexthop device given" + + # default VRF validation is done against LOCAL table + # run_ip6 254 ${TEST_NET6[1]}::102 ${V6ADDRS[p3]/::[0-9]/::64} ${NETIFS[p1]} 2 \ + # "Gateway resolves to wrong nexthop device" + + run_ip6 ${VRF_TABLE} ${TEST_NET6[2]}::103 ${V6ADDRS[p7]/::[0-9]/::64} ${NETIFS[p5]} 2 \ + "Gateway resolves to wrong nexthop device - VRF" +} + +run_onlink_tests() +{ + log_section "IPv4 onlink" + log_subsection "Valid onlink commands" + valid_onlink_ipv4 + log_subsection "Invalid onlink commands" + invalid_onlink_ipv4 + + log_section "IPv6 onlink" + log_subsection "Valid onlink commands" + valid_onlink_ipv6 + invalid_onlink_ipv6 +} + +################################################################################ +# main + +nsuccess=0 +nfail=0 + +cleanup +setup +run_onlink_tests +cleanup + +if [ "$TESTS" != "none" ]; then + printf "\nTests passed: %3d\n" ${nsuccess} + printf "Tests failed: %3d\n" ${nfail} +fi diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index a9154eefb2e2..b617985ecdc1 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -6,154 +6,155 @@ ret=0 -check_err() -{ - if [ $ret -eq 0 ]; then - ret=$1 - fi -} +PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no} -check_fail() +log_test() { - if [ $1 -eq 0 ]; then + local rc=$1 + local expected=$2 + local msg="$3" + + if [ ${rc} -eq ${expected} ]; then + printf " %-60s [ OK ]\n" "${msg}" + else ret=1 + printf " %-60s [FAIL]\n" "${msg}" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi fi } -netns_create() +setup() { - local testns=$1 + set -e + ip netns add testns + ip -netns testns link set dev lo up + + ip -netns testns link add dummy0 type dummy + ip -netns testns link set dev dummy0 up + ip -netns testns address add 198.51.100.1/24 dev dummy0 + ip -netns testns -6 address add 2001:db8:1::1/64 dev dummy0 + set +e - ip netns add $testns - ip netns exec $testns ip link set dev lo up } -fib_unreg_unicast_test() +cleanup() { - ret=0 - - netns_create "testns" - - ip netns exec testns ip link add dummy0 type dummy - ip netns exec testns ip link set dev dummy0 up + ip -netns testns link del dev dummy0 &> /dev/null + ip netns del testns +} - ip netns exec testns ip address add 198.51.100.1/24 dev dummy0 - ip netns exec testns ip -6 address add 2001:db8:1::1/64 dev dummy0 +fib_unreg_unicast_test() +{ + echo + echo "Single path route test" - ip netns exec testns ip route get fibmatch 198.51.100.2 &> /dev/null - check_err $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:1::2 &> /dev/null - check_err $? + setup - ip netns exec testns ip link del dev dummy0 - check_err $? + echo " Start point" + ip -netns testns route get fibmatch 198.51.100.2 &> /dev/null + log_test $? 0 "IPv4 fibmatch" + ip -netns testns -6 route get fibmatch 2001:db8:1::2 &> /dev/null + log_test $? 0 "IPv6 fibmatch" - ip netns exec testns ip route get fibmatch 198.51.100.2 &> /dev/null - check_fail $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:1::2 &> /dev/null - check_fail $? + set -e + ip -netns testns link del dev dummy0 + set +e - ip netns del testns + echo " Nexthop device deleted" + ip -netns testns route get fibmatch 198.51.100.2 &> /dev/null + log_test $? 2 "IPv4 fibmatch - no route" + ip -netns testns -6 route get fibmatch 2001:db8:1::2 &> /dev/null + log_test $? 2 "IPv6 fibmatch - no route" - if [ $ret -ne 0 ]; then - echo "FAIL: unicast route test" - return 1 - fi - echo "PASS: unicast route test" + cleanup } fib_unreg_multipath_test() { - ret=0 - - netns_create "testns" - ip netns exec testns ip link add dummy0 type dummy - ip netns exec testns ip link set dev dummy0 up + echo + echo "Multipath route test" - ip netns exec testns ip link add dummy1 type dummy - ip netns exec testns ip link set dev dummy1 up + setup - ip netns exec testns ip address add 198.51.100.1/24 dev dummy0 - ip netns exec testns ip -6 address add 2001:db8:1::1/64 dev dummy0 + set -e + ip -netns testns link add dummy1 type dummy + ip -netns testns link set dev dummy1 up + ip -netns testns address add 192.0.2.1/24 dev dummy1 + ip -netns testns -6 address add 2001:db8:2::1/64 dev dummy1 - ip netns exec testns ip address add 192.0.2.1/24 dev dummy1 - ip netns exec testns ip -6 address add 2001:db8:2::1/64 dev dummy1 - - ip netns exec testns ip route add 203.0.113.0/24 \ + ip -netns testns route add 203.0.113.0/24 \ nexthop via 198.51.100.2 dev dummy0 \ nexthop via 192.0.2.2 dev dummy1 - ip netns exec testns ip -6 route add 2001:db8:3::/64 \ + ip -netns testns -6 route add 2001:db8:3::/64 \ nexthop via 2001:db8:1::2 dev dummy0 \ nexthop via 2001:db8:2::2 dev dummy1 + set +e + + echo " Start point" + ip -netns testns route get fibmatch 203.0.113.1 &> /dev/null + log_test $? 0 "IPv4 fibmatch" + ip -netns testns -6 route get fibmatch 2001:db8:3::1 &> /dev/null + log_test $? 0 "IPv6 fibmatch" - ip netns exec testns ip route get fibmatch 203.0.113.1 &> /dev/null - check_err $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:3::1 &> /dev/null - check_err $? + set -e + ip -netns testns link del dev dummy0 + set +e - ip netns exec testns ip link del dev dummy0 - check_err $? + echo " One nexthop device deleted" + ip -netns testns route get fibmatch 203.0.113.1 &> /dev/null + log_test $? 2 "IPv4 - multipath route removed on delete" - ip netns exec testns ip route get fibmatch 203.0.113.1 &> /dev/null - check_fail $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:3::1 &> /dev/null + ip -netns testns -6 route get fibmatch 2001:db8:3::1 &> /dev/null # In IPv6 we do not flush the entire multipath route. - check_err $? + log_test $? 0 "IPv6 - multipath down to single path" - ip netns exec testns ip link del dev dummy1 + set -e + ip -netns testns link del dev dummy1 + set +e - ip netns del testns + echo " Second nexthop device deleted" + ip -netns testns -6 route get fibmatch 2001:db8:3::1 &> /dev/null + log_test $? 2 "IPv6 - no route" - if [ $ret -ne 0 ]; then - echo "FAIL: multipath route test" - return 1 - fi - echo "PASS: multipath route test" + cleanup } fib_unreg_test() { - echo "Running netdev unregister tests" - fib_unreg_unicast_test fib_unreg_multipath_test } fib_down_unicast_test() { - ret=0 - - netns_create "testns" - - ip netns exec testns ip link add dummy0 type dummy - ip netns exec testns ip link set dev dummy0 up - - ip netns exec testns ip address add 198.51.100.1/24 dev dummy0 - ip netns exec testns ip -6 address add 2001:db8:1::1/64 dev dummy0 + echo + echo "Single path, admin down" - ip netns exec testns ip route get fibmatch 198.51.100.2 &> /dev/null - check_err $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:1::2 &> /dev/null - check_err $? + setup - ip netns exec testns ip link set dev dummy0 down - check_err $? + echo " Start point" + ip -netns testns route get fibmatch 198.51.100.2 &> /dev/null + log_test $? 0 "IPv4 fibmatch" + ip -netns testns -6 route get fibmatch 2001:db8:1::2 &> /dev/null + log_test $? 0 "IPv6 fibmatch" - ip netns exec testns ip route get fibmatch 198.51.100.2 &> /dev/null - check_fail $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:1::2 &> /dev/null - check_fail $? + set -e + ip -netns testns link set dev dummy0 down + set +e - ip netns exec testns ip link del dev dummy0 + echo " Route deleted on down" + ip -netns testns route get fibmatch 198.51.100.2 &> /dev/null + log_test $? 2 "IPv4 fibmatch" + ip -netns testns -6 route get fibmatch 2001:db8:1::2 &> /dev/null + log_test $? 2 "IPv6 fibmatch" - ip netns del testns - - if [ $ret -ne 0 ]; then - echo "FAIL: unicast route test" - return 1 - fi - echo "PASS: unicast route test" + cleanup } fib_down_multipath_test_do() @@ -161,242 +162,229 @@ fib_down_multipath_test_do() local down_dev=$1 local up_dev=$2 - ip netns exec testns ip route get fibmatch 203.0.113.1 \ + ip -netns testns route get fibmatch 203.0.113.1 \ oif $down_dev &> /dev/null - check_fail $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:3::1 \ + log_test $? 2 "IPv4 fibmatch on down device" + ip -netns testns -6 route get fibmatch 2001:db8:3::1 \ oif $down_dev &> /dev/null - check_fail $? + log_test $? 2 "IPv6 fibmatch on down device" - ip netns exec testns ip route get fibmatch 203.0.113.1 \ + ip -netns testns route get fibmatch 203.0.113.1 \ oif $up_dev &> /dev/null - check_err $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:3::1 \ + log_test $? 0 "IPv4 fibmatch on up device" + ip -netns testns -6 route get fibmatch 2001:db8:3::1 \ oif $up_dev &> /dev/null - check_err $? + log_test $? 0 "IPv6 fibmatch on up device" - ip netns exec testns ip route get fibmatch 203.0.113.1 | \ + ip -netns testns route get fibmatch 203.0.113.1 | \ grep $down_dev | grep -q "dead linkdown" - check_err $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:3::1 | \ + log_test $? 0 "IPv4 flags on down device" + ip -netns testns -6 route get fibmatch 2001:db8:3::1 | \ grep $down_dev | grep -q "dead linkdown" - check_err $? + log_test $? 0 "IPv6 flags on down device" - ip netns exec testns ip route get fibmatch 203.0.113.1 | \ + ip -netns testns route get fibmatch 203.0.113.1 | \ grep $up_dev | grep -q "dead linkdown" - check_fail $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:3::1 | \ + log_test $? 1 "IPv4 flags on up device" + ip -netns testns -6 route get fibmatch 2001:db8:3::1 | \ grep $up_dev | grep -q "dead linkdown" - check_fail $? + log_test $? 1 "IPv6 flags on up device" } fib_down_multipath_test() { - ret=0 + echo + echo "Admin down multipath" - netns_create "testns" + setup - ip netns exec testns ip link add dummy0 type dummy - ip netns exec testns ip link set dev dummy0 up + set -e + ip -netns testns link add dummy1 type dummy + ip -netns testns link set dev dummy1 up - ip netns exec testns ip link add dummy1 type dummy - ip netns exec testns ip link set dev dummy1 up + ip -netns testns address add 192.0.2.1/24 dev dummy1 + ip -netns testns -6 address add 2001:db8:2::1/64 dev dummy1 - ip netns exec testns ip address add 198.51.100.1/24 dev dummy0 - ip netns exec testns ip -6 address add 2001:db8:1::1/64 dev dummy0 - - ip netns exec testns ip address add 192.0.2.1/24 dev dummy1 - ip netns exec testns ip -6 address add 2001:db8:2::1/64 dev dummy1 - - ip netns exec testns ip route add 203.0.113.0/24 \ + ip -netns testns route add 203.0.113.0/24 \ nexthop via 198.51.100.2 dev dummy0 \ nexthop via 192.0.2.2 dev dummy1 - ip netns exec testns ip -6 route add 2001:db8:3::/64 \ + ip -netns testns -6 route add 2001:db8:3::/64 \ nexthop via 2001:db8:1::2 dev dummy0 \ nexthop via 2001:db8:2::2 dev dummy1 + set +e + + echo " Verify start point" + ip -netns testns route get fibmatch 203.0.113.1 &> /dev/null + log_test $? 0 "IPv4 fibmatch" - ip netns exec testns ip route get fibmatch 203.0.113.1 &> /dev/null - check_err $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:3::1 &> /dev/null - check_err $? + ip -netns testns -6 route get fibmatch 2001:db8:3::1 &> /dev/null + log_test $? 0 "IPv6 fibmatch" - ip netns exec testns ip link set dev dummy0 down - check_err $? + set -e + ip -netns testns link set dev dummy0 down + set +e + echo " One device down, one up" fib_down_multipath_test_do "dummy0" "dummy1" - ip netns exec testns ip link set dev dummy0 up - check_err $? - ip netns exec testns ip link set dev dummy1 down - check_err $? + set -e + ip -netns testns link set dev dummy0 up + ip -netns testns link set dev dummy1 down + set +e + echo " Other device down and up" fib_down_multipath_test_do "dummy1" "dummy0" - ip netns exec testns ip link set dev dummy0 down - check_err $? + set -e + ip -netns testns link set dev dummy0 down + set +e - ip netns exec testns ip route get fibmatch 203.0.113.1 &> /dev/null - check_fail $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:3::1 &> /dev/null - check_fail $? + echo " Both devices down" + ip -netns testns route get fibmatch 203.0.113.1 &> /dev/null + log_test $? 2 "IPv4 fibmatch" + ip -netns testns -6 route get fibmatch 2001:db8:3::1 &> /dev/null + log_test $? 2 "IPv6 fibmatch" - ip netns exec testns ip link del dev dummy1 - ip netns exec testns ip link del dev dummy0 - - ip netns del testns - - if [ $ret -ne 0 ]; then - echo "FAIL: multipath route test" - return 1 - fi - echo "PASS: multipath route test" + ip -netns testns link del dev dummy1 + cleanup } fib_down_test() { - echo "Running netdev down tests" - fib_down_unicast_test fib_down_multipath_test } +# Local routes should not be affected when carrier changes. fib_carrier_local_test() { - ret=0 + echo + echo "Local carrier tests - single path" - # Local routes should not be affected when carrier changes. - netns_create "testns" + setup - ip netns exec testns ip link add dummy0 type dummy - ip netns exec testns ip link set dev dummy0 up + set -e + ip -netns testns link set dev dummy0 carrier on + set +e - ip netns exec testns ip link set dev dummy0 carrier on + echo " Start point" + ip -netns testns route get fibmatch 198.51.100.1 &> /dev/null + log_test $? 0 "IPv4 fibmatch" + ip -netns testns -6 route get fibmatch 2001:db8:1::1 &> /dev/null + log_test $? 0 "IPv6 fibmatch" - ip netns exec testns ip address add 198.51.100.1/24 dev dummy0 - ip netns exec testns ip -6 address add 2001:db8:1::1/64 dev dummy0 - - ip netns exec testns ip route get fibmatch 198.51.100.1 &> /dev/null - check_err $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:1::1 &> /dev/null - check_err $? - - ip netns exec testns ip route get fibmatch 198.51.100.1 | \ + ip -netns testns route get fibmatch 198.51.100.1 | \ grep -q "linkdown" - check_fail $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:1::1 | \ + log_test $? 1 "IPv4 - no linkdown flag" + ip -netns testns -6 route get fibmatch 2001:db8:1::1 | \ grep -q "linkdown" - check_fail $? + log_test $? 1 "IPv6 - no linkdown flag" - ip netns exec testns ip link set dev dummy0 carrier off + set -e + ip -netns testns link set dev dummy0 carrier off + sleep 1 + set +e - ip netns exec testns ip route get fibmatch 198.51.100.1 &> /dev/null - check_err $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:1::1 &> /dev/null - check_err $? + echo " Carrier off on nexthop" + ip -netns testns route get fibmatch 198.51.100.1 &> /dev/null + log_test $? 0 "IPv4 fibmatch" + ip -netns testns -6 route get fibmatch 2001:db8:1::1 &> /dev/null + log_test $? 0 "IPv6 fibmatch" - ip netns exec testns ip route get fibmatch 198.51.100.1 | \ + ip -netns testns route get fibmatch 198.51.100.1 | \ grep -q "linkdown" - check_fail $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:1::1 | \ + log_test $? 1 "IPv4 - linkdown flag set" + ip -netns testns -6 route get fibmatch 2001:db8:1::1 | \ grep -q "linkdown" - check_fail $? + log_test $? 1 "IPv6 - linkdown flag set" - ip netns exec testns ip address add 192.0.2.1/24 dev dummy0 - ip netns exec testns ip -6 address add 2001:db8:2::1/64 dev dummy0 + set -e + ip -netns testns address add 192.0.2.1/24 dev dummy0 + ip -netns testns -6 address add 2001:db8:2::1/64 dev dummy0 + set +e - ip netns exec testns ip route get fibmatch 192.0.2.1 &> /dev/null - check_err $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:2::1 &> /dev/null - check_err $? + echo " Route to local address with carrier down" + ip -netns testns route get fibmatch 192.0.2.1 &> /dev/null + log_test $? 0 "IPv4 fibmatch" + ip -netns testns -6 route get fibmatch 2001:db8:2::1 &> /dev/null + log_test $? 0 "IPv6 fibmatch" - ip netns exec testns ip route get fibmatch 192.0.2.1 | \ + ip -netns testns route get fibmatch 192.0.2.1 | \ grep -q "linkdown" - check_fail $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:2::1 | \ + log_test $? 1 "IPv4 linkdown flag set" + ip -netns testns -6 route get fibmatch 2001:db8:2::1 | \ grep -q "linkdown" - check_fail $? + log_test $? 1 "IPv6 linkdown flag set" - ip netns exec testns ip link del dev dummy0 - - ip netns del testns - - if [ $ret -ne 0 ]; then - echo "FAIL: local route carrier test" - return 1 - fi - echo "PASS: local route carrier test" + cleanup } fib_carrier_unicast_test() { ret=0 - netns_create "testns" - - ip netns exec testns ip link add dummy0 type dummy - ip netns exec testns ip link set dev dummy0 up + echo + echo "Single path route carrier test" - ip netns exec testns ip link set dev dummy0 carrier on + setup - ip netns exec testns ip address add 198.51.100.1/24 dev dummy0 - ip netns exec testns ip -6 address add 2001:db8:1::1/64 dev dummy0 + set -e + ip -netns testns link set dev dummy0 carrier on + set +e - ip netns exec testns ip route get fibmatch 198.51.100.2 &> /dev/null - check_err $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:1::2 &> /dev/null - check_err $? + echo " Start point" + ip -netns testns route get fibmatch 198.51.100.2 &> /dev/null + log_test $? 0 "IPv4 fibmatch" + ip -netns testns -6 route get fibmatch 2001:db8:1::2 &> /dev/null + log_test $? 0 "IPv6 fibmatch" - ip netns exec testns ip route get fibmatch 198.51.100.2 | \ + ip -netns testns route get fibmatch 198.51.100.2 | \ grep -q "linkdown" - check_fail $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:1::2 | \ + log_test $? 1 "IPv4 no linkdown flag" + ip -netns testns -6 route get fibmatch 2001:db8:1::2 | \ grep -q "linkdown" - check_fail $? + log_test $? 1 "IPv6 no linkdown flag" - ip netns exec testns ip link set dev dummy0 carrier off + set -e + ip -netns testns link set dev dummy0 carrier off + set +e - ip netns exec testns ip route get fibmatch 198.51.100.2 &> /dev/null - check_err $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:1::2 &> /dev/null - check_err $? + echo " Carrier down" + ip -netns testns route get fibmatch 198.51.100.2 &> /dev/null + log_test $? 0 "IPv4 fibmatch" + ip -netns testns -6 route get fibmatch 2001:db8:1::2 &> /dev/null + log_test $? 0 "IPv6 fibmatch" - ip netns exec testns ip route get fibmatch 198.51.100.2 | \ + ip -netns testns route get fibmatch 198.51.100.2 | \ grep -q "linkdown" - check_err $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:1::2 | \ + log_test $? 0 "IPv4 linkdown flag set" + ip -netns testns -6 route get fibmatch 2001:db8:1::2 | \ grep -q "linkdown" - check_err $? + log_test $? 0 "IPv6 linkdown flag set" - ip netns exec testns ip address add 192.0.2.1/24 dev dummy0 - ip netns exec testns ip -6 address add 2001:db8:2::1/64 dev dummy0 + set -e + ip -netns testns address add 192.0.2.1/24 dev dummy0 + ip -netns testns -6 address add 2001:db8:2::1/64 dev dummy0 + set +e - ip netns exec testns ip route get fibmatch 192.0.2.2 &> /dev/null - check_err $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:2::2 &> /dev/null - check_err $? + echo " Second address added with carrier down" + ip -netns testns route get fibmatch 192.0.2.2 &> /dev/null + log_test $? 0 "IPv4 fibmatch" + ip -netns testns -6 route get fibmatch 2001:db8:2::2 &> /dev/null + log_test $? 0 "IPv6 fibmatch" - ip netns exec testns ip route get fibmatch 192.0.2.2 | \ + ip -netns testns route get fibmatch 192.0.2.2 | \ grep -q "linkdown" - check_err $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:2::2 | \ + log_test $? 0 "IPv4 linkdown flag set" + ip -netns testns -6 route get fibmatch 2001:db8:2::2 | \ grep -q "linkdown" - check_err $? + log_test $? 0 "IPv6 linkdown flag set" - ip netns exec testns ip link del dev dummy0 - - ip netns del testns - - if [ $ret -ne 0 ]; then - echo "FAIL: unicast route carrier test" - return 1 - fi - echo "PASS: unicast route carrier test" + cleanup } fib_carrier_test() { - echo "Running netdev carrier change tests" - fib_carrier_local_test fib_carrier_unicast_test } @@ -424,6 +412,9 @@ if [ $? -ne 0 ]; then exit 0 fi +# start clean +cleanup &> /dev/null + fib_test exit $ret diff --git a/tools/testing/selftests/net/in_netns.sh b/tools/testing/selftests/net/in_netns.sh new file mode 100755 index 000000000000..f57a2eaad069 --- /dev/null +++ b/tools/testing/selftests/net/in_netns.sh @@ -0,0 +1,23 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# Execute a subprocess in a network namespace + +set -e + +readonly NETNS="ns-$(mktemp -u XXXXXX)" + +setup() { + ip netns add "${NETNS}" + ip -netns "${NETNS}" link set lo up +} + +cleanup() { + ip netns del "${NETNS}" +} + +trap cleanup EXIT +setup + +"$@" +exit "$?" diff --git a/tools/testing/selftests/net/msg_zerocopy.c b/tools/testing/selftests/net/msg_zerocopy.c index e11fe84de0fd..406cc70c571d 100644 --- a/tools/testing/selftests/net/msg_zerocopy.c +++ b/tools/testing/selftests/net/msg_zerocopy.c @@ -14,6 +14,9 @@ * - SOCK_DGRAM * - SOCK_RAW * + * PF_RDS + * - SOCK_SEQPACKET + * * Start this program on two connected hosts, one in send mode and * the other with option '-r' to put it in receiver mode. * @@ -53,6 +56,7 @@ #include <sys/types.h> #include <sys/wait.h> #include <unistd.h> +#include <linux/rds.h> #ifndef SO_EE_ORIGIN_ZEROCOPY #define SO_EE_ORIGIN_ZEROCOPY 5 @@ -164,17 +168,39 @@ static int do_accept(int fd) return fd; } -static bool do_sendmsg(int fd, struct msghdr *msg, bool do_zerocopy) +static void add_zcopy_cookie(struct msghdr *msg, uint32_t cookie) +{ + struct cmsghdr *cm; + + if (!msg->msg_control) + error(1, errno, "NULL cookie"); + cm = (void *)msg->msg_control; + cm->cmsg_len = CMSG_LEN(sizeof(cookie)); + cm->cmsg_level = SOL_RDS; + cm->cmsg_type = RDS_CMSG_ZCOPY_COOKIE; + memcpy(CMSG_DATA(cm), &cookie, sizeof(cookie)); +} + +static bool do_sendmsg(int fd, struct msghdr *msg, bool do_zerocopy, int domain) { int ret, len, i, flags; + static uint32_t cookie; + char ckbuf[CMSG_SPACE(sizeof(cookie))]; len = 0; for (i = 0; i < msg->msg_iovlen; i++) len += msg->msg_iov[i].iov_len; flags = MSG_DONTWAIT; - if (do_zerocopy) + if (do_zerocopy) { flags |= MSG_ZEROCOPY; + if (domain == PF_RDS) { + memset(&msg->msg_control, 0, sizeof(msg->msg_control)); + msg->msg_controllen = CMSG_SPACE(sizeof(cookie)); + msg->msg_control = (struct cmsghdr *)ckbuf; + add_zcopy_cookie(msg, ++cookie); + } + } ret = sendmsg(fd, msg, flags); if (ret == -1 && errno == EAGAIN) @@ -190,6 +216,10 @@ static bool do_sendmsg(int fd, struct msghdr *msg, bool do_zerocopy) if (do_zerocopy && ret) expected_completions++; } + if (do_zerocopy && domain == PF_RDS) { + msg->msg_control = NULL; + msg->msg_controllen = 0; + } return true; } @@ -216,7 +246,9 @@ static void do_sendmsg_corked(int fd, struct msghdr *msg) msg->msg_iov[0].iov_len = payload_len + extra_len; extra_len = 0; - do_sendmsg(fd, msg, do_zerocopy); + do_sendmsg(fd, msg, do_zerocopy, + (cfg_dst_addr.ss_family == AF_INET ? + PF_INET : PF_INET6)); } do_setsockopt(fd, IPPROTO_UDP, UDP_CORK, 0); @@ -300,14 +332,65 @@ static int do_setup_tx(int domain, int type, int protocol) if (cfg_zerocopy) do_setsockopt(fd, SOL_SOCKET, SO_ZEROCOPY, 1); - if (domain != PF_PACKET) + if (domain != PF_PACKET && domain != PF_RDS) if (connect(fd, (void *) &cfg_dst_addr, cfg_alen)) error(1, errno, "connect"); + if (domain == PF_RDS) { + if (bind(fd, (void *) &cfg_src_addr, cfg_alen)) + error(1, errno, "bind"); + } + return fd; } -static bool do_recv_completion(int fd) +static uint32_t do_process_zerocopy_cookies(struct rds_zcopy_cookies *ck) +{ + int i; + + if (ck->num > RDS_MAX_ZCOOKIES) + error(1, 0, "Returned %d cookies, max expected %d\n", + ck->num, RDS_MAX_ZCOOKIES); + for (i = 0; i < ck->num; i++) + if (cfg_verbose >= 2) + fprintf(stderr, "%d\n", ck->cookies[i]); + return ck->num; +} + +static bool do_recvmsg_completion(int fd) +{ + char cmsgbuf[CMSG_SPACE(sizeof(struct rds_zcopy_cookies))]; + struct rds_zcopy_cookies *ck; + struct cmsghdr *cmsg; + struct msghdr msg; + bool ret = false; + + memset(&msg, 0, sizeof(msg)); + msg.msg_control = cmsgbuf; + msg.msg_controllen = sizeof(cmsgbuf); + + if (recvmsg(fd, &msg, MSG_DONTWAIT)) + return ret; + + if (msg.msg_flags & MSG_CTRUNC) + error(1, errno, "recvmsg notification: truncated"); + + for (cmsg = CMSG_FIRSTHDR(&msg); cmsg; cmsg = CMSG_NXTHDR(&msg, cmsg)) { + if (cmsg->cmsg_level == SOL_RDS && + cmsg->cmsg_type == RDS_CMSG_ZCOPY_COMPLETION) { + + ck = (struct rds_zcopy_cookies *)CMSG_DATA(cmsg); + completions += do_process_zerocopy_cookies(ck); + ret = true; + break; + } + error(0, 0, "ignoring cmsg at level %d type %d\n", + cmsg->cmsg_level, cmsg->cmsg_type); + } + return ret; +} + +static bool do_recv_completion(int fd, int domain) { struct sock_extended_err *serr; struct msghdr msg = {}; @@ -316,6 +399,9 @@ static bool do_recv_completion(int fd) int ret, zerocopy; char control[100]; + if (domain == PF_RDS) + return do_recvmsg_completion(fd); + msg.msg_control = control; msg.msg_controllen = sizeof(control); @@ -337,6 +423,7 @@ static bool do_recv_completion(int fd) cm->cmsg_level, cm->cmsg_type); serr = (void *) CMSG_DATA(cm); + if (serr->ee_origin != SO_EE_ORIGIN_ZEROCOPY) error(1, 0, "serr: wrong origin: %u", serr->ee_origin); if (serr->ee_errno != 0) @@ -371,20 +458,20 @@ static bool do_recv_completion(int fd) } /* Read all outstanding messages on the errqueue */ -static void do_recv_completions(int fd) +static void do_recv_completions(int fd, int domain) { - while (do_recv_completion(fd)) {} + while (do_recv_completion(fd, domain)) {} } /* Wait for all remaining completions on the errqueue */ -static void do_recv_remaining_completions(int fd) +static void do_recv_remaining_completions(int fd, int domain) { int64_t tstop = gettimeofday_ms() + cfg_waittime_ms; while (completions < expected_completions && gettimeofday_ms() < tstop) { - if (do_poll(fd, POLLERR)) - do_recv_completions(fd); + if (do_poll(fd, domain == PF_RDS ? POLLIN : POLLERR)) + do_recv_completions(fd, domain); } if (completions < expected_completions) @@ -444,6 +531,13 @@ static void do_tx(int domain, int type, int protocol) msg.msg_iovlen++; } + if (domain == PF_RDS) { + msg.msg_name = &cfg_dst_addr; + msg.msg_namelen = (cfg_dst_addr.ss_family == AF_INET ? + sizeof(struct sockaddr_in) : + sizeof(struct sockaddr_in6)); + } + iov[2].iov_base = payload; iov[2].iov_len = cfg_payload_len; msg.msg_iovlen++; @@ -454,17 +548,17 @@ static void do_tx(int domain, int type, int protocol) if (cfg_cork) do_sendmsg_corked(fd, &msg); else - do_sendmsg(fd, &msg, cfg_zerocopy); + do_sendmsg(fd, &msg, cfg_zerocopy, domain); while (!do_poll(fd, POLLOUT)) { if (cfg_zerocopy) - do_recv_completions(fd); + do_recv_completions(fd, domain); } } while (gettimeofday_ms() < tstop); if (cfg_zerocopy) - do_recv_remaining_completions(fd); + do_recv_remaining_completions(fd, domain); if (close(fd)) error(1, errno, "close"); @@ -610,6 +704,7 @@ static void parse_opts(int argc, char **argv) 40 /* max tcp options */; int c; char *daddr = NULL, *saddr = NULL; + char *cfg_test; cfg_payload_len = max_payload_len; @@ -667,6 +762,14 @@ static void parse_opts(int argc, char **argv) break; } } + + cfg_test = argv[argc - 1]; + if (strcmp(cfg_test, "rds") == 0) { + if (!daddr) + error(1, 0, "-D <server addr> required for PF_RDS\n"); + if (!cfg_rx && !saddr) + error(1, 0, "-S <client addr> required for PF_RDS\n"); + } setup_sockaddr(cfg_family, daddr, &cfg_dst_addr); setup_sockaddr(cfg_family, saddr, &cfg_src_addr); @@ -699,6 +802,8 @@ int main(int argc, char **argv) do_test(cfg_family, SOCK_STREAM, 0); else if (!strcmp(cfg_test, "udp")) do_test(cfg_family, SOCK_DGRAM, 0); + else if (!strcmp(cfg_test, "rds")) + do_test(PF_RDS, SOCK_SEQPACKET, 0); else error(1, 0, "unknown cfg_test %s", cfg_test); diff --git a/tools/testing/selftests/net/psock_fanout.c b/tools/testing/selftests/net/psock_fanout.c index 989f917068d1..bd9b9632c72b 100644 --- a/tools/testing/selftests/net/psock_fanout.c +++ b/tools/testing/selftests/net/psock_fanout.c @@ -50,6 +50,7 @@ #include <linux/filter.h> #include <linux/bpf.h> #include <linux/if_packet.h> +#include <net/if.h> #include <net/ethernet.h> #include <netinet/ip.h> #include <netinet/udp.h> @@ -73,14 +74,29 @@ * @return -1 if mode is bad, a valid socket otherwise */ static int sock_fanout_open(uint16_t typeflags, uint16_t group_id) { + struct sockaddr_ll addr = {0}; int fd, val; - fd = socket(PF_PACKET, SOCK_RAW, htons(ETH_P_IP)); + fd = socket(PF_PACKET, SOCK_RAW, 0); if (fd < 0) { perror("socket packet"); exit(1); } + pair_udp_setfilter(fd); + + addr.sll_family = AF_PACKET; + addr.sll_protocol = htons(ETH_P_IP); + addr.sll_ifindex = if_nametoindex("lo"); + if (addr.sll_ifindex == 0) { + perror("if_nametoindex"); + exit(1); + } + if (bind(fd, (void *) &addr, sizeof(addr))) { + perror("bind packet"); + exit(1); + } + val = (((int) typeflags) << 16) | group_id; if (setsockopt(fd, SOL_PACKET, PACKET_FANOUT, &val, sizeof(val))) { if (close(fd)) { @@ -90,7 +106,6 @@ static int sock_fanout_open(uint16_t typeflags, uint16_t group_id) return -1; } - pair_udp_setfilter(fd); return fd; } @@ -128,6 +143,8 @@ static void sock_fanout_getopts(int fd, uint16_t *typeflags, uint16_t *group_id) static void sock_fanout_set_ebpf(int fd) { + static char log_buf[65536]; + const int len_off = __builtin_offsetof(struct __sk_buff, len); struct bpf_insn prog[] = { { BPF_ALU64 | BPF_MOV | BPF_X, 6, 1, 0, 0 }, @@ -140,7 +157,6 @@ static void sock_fanout_set_ebpf(int fd) { BPF_ALU | BPF_MOV | BPF_K, 0, 0, 0, 0 }, { BPF_JMP | BPF_EXIT, 0, 0, 0, 0 } }; - char log_buf[512]; union bpf_attr attr; int pfd; @@ -228,7 +244,7 @@ static int sock_fanout_read(int fds[], char *rings[], const int expect[]) if ((!(ret[0] == expect[0] && ret[1] == expect[1])) && (!(ret[0] == expect[1] && ret[1] == expect[0]))) { - fprintf(stderr, "ERROR: incorrect queue lengths\n"); + fprintf(stderr, "warning: incorrect queue lengths\n"); return 1; } @@ -347,7 +363,8 @@ static int test_datapath(uint16_t typeflags, int port_off, uint8_t type = typeflags & 0xFF; int fds[2], fds_udp[2][2], ret; - fprintf(stderr, "test: datapath 0x%hx\n", typeflags); + fprintf(stderr, "\ntest: datapath 0x%hx ports %hu,%hu\n", + typeflags, PORT_BASE, PORT_BASE + port_off); fds[0] = sock_fanout_open(typeflags, 0); fds[1] = sock_fanout_open(typeflags, 0); @@ -418,7 +435,7 @@ int main(int argc, char **argv) const int expect_cpu1[2][2] = { { 0, 20 }, { 0, 20 } }; const int expect_bpf[2][2] = { { 15, 5 }, { 15, 20 } }; const int expect_uniqueid[2][2] = { { 20, 20}, { 20, 20 } }; - int port_off = 2, tries = 5, ret; + int port_off = 2, tries = 20, ret; test_control_single(); test_control_group(); @@ -427,10 +444,14 @@ int main(int argc, char **argv) /* find a set of ports that do not collide onto the same socket */ ret = test_datapath(PACKET_FANOUT_HASH, port_off, expect_hash[0], expect_hash[1]); - while (ret && tries--) { + while (ret) { fprintf(stderr, "info: trying alternate ports (%d)\n", tries); ret = test_datapath(PACKET_FANOUT_HASH, ++port_off, expect_hash[0], expect_hash[1]); + if (!--tries) { + fprintf(stderr, "too many collisions\n"); + return 1; + } } ret |= test_datapath(PACKET_FANOUT_HASH | PACKET_FANOUT_FLAG_ROLLOVER, diff --git a/tools/testing/selftests/net/run_afpackettests b/tools/testing/selftests/net/run_afpackettests index 21fe149e3de1..bea079edc278 100755 --- a/tools/testing/selftests/net/run_afpackettests +++ b/tools/testing/selftests/net/run_afpackettests @@ -9,7 +9,7 @@ fi echo "--------------------" echo "running psock_fanout test" echo "--------------------" -./psock_fanout +./in_netns.sh ./psock_fanout if [ $? -ne 0 ]; then echo "[FAIL]" else @@ -19,7 +19,7 @@ fi echo "--------------------" echo "running psock_tpacket test" echo "--------------------" -./psock_tpacket +./in_netns.sh ./psock_tpacket if [ $? -ne 0 ]; then echo "[FAIL]" else diff --git a/tools/testing/selftests/powerpc/alignment/alignment_handler.c b/tools/testing/selftests/powerpc/alignment/alignment_handler.c index 39fd362415cf..0f2698f9fd6d 100644 --- a/tools/testing/selftests/powerpc/alignment/alignment_handler.c +++ b/tools/testing/selftests/powerpc/alignment/alignment_handler.c @@ -57,7 +57,7 @@ volatile int gotsig; void sighandler(int sig, siginfo_t *info, void *ctx) { - struct ucontext *ucp = ctx; + ucontext_t *ucp = ctx; if (!testing) { signal(sig, SIG_DFL); diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 0b457e8e0f0c..5df609950a66 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -141,6 +141,15 @@ struct seccomp_data { #define SECCOMP_FILTER_FLAG_LOG 2 #endif +#ifndef PTRACE_SECCOMP_GET_METADATA +#define PTRACE_SECCOMP_GET_METADATA 0x420d + +struct seccomp_metadata { + __u64 filter_off; /* Input: which filter */ + __u64 flags; /* Output: filter's flags */ +}; +#endif + #ifndef seccomp int seccomp(unsigned int op, unsigned int flags, void *args) { @@ -2845,6 +2854,58 @@ TEST(get_action_avail) EXPECT_EQ(errno, EOPNOTSUPP); } +TEST(get_metadata) +{ + pid_t pid; + int pipefd[2]; + char buf; + struct seccomp_metadata md; + + ASSERT_EQ(0, pipe(pipefd)); + + pid = fork(); + ASSERT_GE(pid, 0); + if (pid == 0) { + struct sock_filter filter[] = { + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), + }; + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + + /* one with log, one without */ + ASSERT_EQ(0, seccomp(SECCOMP_SET_MODE_FILTER, + SECCOMP_FILTER_FLAG_LOG, &prog)); + ASSERT_EQ(0, seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog)); + + ASSERT_EQ(0, close(pipefd[0])); + ASSERT_EQ(1, write(pipefd[1], "1", 1)); + ASSERT_EQ(0, close(pipefd[1])); + + while (1) + sleep(100); + } + + ASSERT_EQ(0, close(pipefd[1])); + ASSERT_EQ(1, read(pipefd[0], &buf, 1)); + + ASSERT_EQ(0, ptrace(PTRACE_ATTACH, pid)); + ASSERT_EQ(pid, waitpid(pid, NULL, 0)); + + md.filter_off = 0; + ASSERT_EQ(sizeof(md), ptrace(PTRACE_SECCOMP_GET_METADATA, pid, sizeof(md), &md)); + EXPECT_EQ(md.flags, SECCOMP_FILTER_FLAG_LOG); + EXPECT_EQ(md.filter_off, 0); + + md.filter_off = 1; + ASSERT_EQ(sizeof(md), ptrace(PTRACE_SECCOMP_GET_METADATA, pid, sizeof(md), &md)); + EXPECT_EQ(md.flags, 0); + EXPECT_EQ(md.filter_off, 1); + + ASSERT_EQ(0, kill(pid, SIGKILL)); +} + /* * TODO: * - add microbenchmarks diff --git a/tools/testing/selftests/tc-testing/README b/tools/testing/selftests/tc-testing/README index 970ff294fec8..3a0336782d2d 100644 --- a/tools/testing/selftests/tc-testing/README +++ b/tools/testing/selftests/tc-testing/README @@ -14,11 +14,11 @@ REQUIREMENTS * The kernel must have network namespace support -* The kernel must have veth support available, as a veth pair is created +* The kernel must have veth support available, as a veth pair is created prior to running the tests. -* All tc-related features must be built in or available as modules. - To check what is required in current setup run: +* All tc-related features being tested must be built in or available as + modules. To check what is required in current setup run: ./tdc.py -c Note: @@ -44,10 +44,13 @@ using the -p option when running tdc: RUNNING TDC ----------- -To use tdc, root privileges are required. tdc will not run otherwise. +To use tdc, root privileges are required. This is because the +commands being tested must be run as root. The code that enforces +execution by root uid has been moved into a plugin (see PLUGIN +ARCHITECTURE, below). -All tests are executed inside a network namespace to prevent conflicts -within the host. +If nsPlugin is linked, all tests are executed inside a network +namespace to prevent conflicts within the host. Running tdc without any arguments will run all tests. Refer to the section on command line arguments for more information, or run: @@ -59,6 +62,33 @@ output captured from the failing test will be printed immediately following the failed test in the TAP output. +OVERVIEW OF TDC EXECUTION +------------------------- + +One run of tests is considered a "test suite" (this will be refined in the +future). A test suite has one or more test cases in it. + +A test case has four stages: + + - setup + - execute + - verify + - teardown + +The setup and teardown stages can run zero or more commands. The setup +stage does some setup if the test needs it. The teardown stage undoes +the setup and returns the system to a "neutral" state so any other test +can be run next. These two stages require any commands run to return +success, but do not otherwise verify the results. + +The execute and verify stages each run one command. The execute stage +tests the return code against one or more acceptable values. The +verify stage checks the return code for success, and also compares +the stdout with a regular expression. + +Each of the commands in any stage will run in a shell instance. + + USER-DEFINED CONSTANTS ---------------------- @@ -70,23 +100,132 @@ executed as part of the test. More will be added as test cases require. Example: $TC qdisc add dev $DEV1 ingress +The NAMES values are used to substitute into the commands in the test cases. + COMMAND LINE ARGUMENTS ---------------------- Run tdc.py -h to see the full list of available arguments. --p PATH Specify the tc executable located at PATH to be used on this - test run --c Show the available test case categories in this test file --c CATEGORY Run only tests that belong to CATEGORY --f FILE Read test cases from the JSON file named FILE --l [CATEGORY] List all test cases in the JSON file. If CATEGORY is - specified, list test cases matching that category. --s ID Show the test case matching ID --e ID Execute the test case identified by ID --i Generate unique ID numbers for test cases with no existing - ID number +usage: tdc.py [-h] [-p PATH] [-D DIR [DIR ...]] [-f FILE [FILE ...]] + [-c [CATG [CATG ...]]] [-e ID [ID ...]] [-l] [-s] [-i] [-v] + [-d DEVICE] [-n NS] [-V] + +Linux TC unit tests + +optional arguments: + -h, --help show this help message and exit + -p PATH, --path PATH The full path to the tc executable to use + -v, --verbose Show the commands that are being run + -d DEVICE, --device DEVICE + Execute the test case in flower category + +selection: + select which test cases: files plus directories; filtered by categories + plus testids + + -D DIR [DIR ...], --directory DIR [DIR ...] + Collect tests from the specified directory(ies) + (default [tc-tests]) + -f FILE [FILE ...], --file FILE [FILE ...] + Run tests from the specified file(s) + -c [CATG [CATG ...]], --category [CATG [CATG ...]] + Run tests only from the specified category/ies, or if + no category/ies is/are specified, list known + categories. + -e ID [ID ...], --execute ID [ID ...] + Execute the specified test cases with specified IDs + +action: + select action to perform on selected test cases + + -l, --list List all test cases, or those only within the + specified category + -s, --show Display the selected test cases + -i, --id Generate ID numbers for new test cases + +netns: + options for nsPlugin(run commands in net namespace) + + -n NS, --namespace NS + Run commands in namespace NS + +valgrind: + options for valgrindPlugin (run command under test under Valgrind) + + -V, --valgrind Run commands under valgrind + + +PLUGIN ARCHITECTURE +------------------- + +There is now a plugin architecture, and some of the functionality that +was in the tdc.py script has been moved into the plugins. + +The plugins are in the directory plugin-lib. The are executed from +directory plugins. Put symbolic links from plugins to plugin-lib, +and name them according to the order you want them to run. + +Example: + +bjb@bee:~/work/tc-testing$ ls -l plugins +total 4 +lrwxrwxrwx 1 bjb bjb 27 Oct 4 16:12 10-rootPlugin.py -> ../plugin-lib/rootPlugin.py +lrwxrwxrwx 1 bjb bjb 25 Oct 12 17:55 20-nsPlugin.py -> ../plugin-lib/nsPlugin.py +-rwxr-xr-x 1 bjb bjb 0 Sep 29 15:56 __init__.py + +The plugins are a subclass of TdcPlugin, defined in TdcPlugin.py and +must be called "SubPlugin" so tdc can find them. They are +distinguished from each other in the python program by their module +name. + +This base class supplies "hooks" to run extra functions. These hooks are as follows: + +pre- and post-suite +pre- and post-case +pre- and post-execute stage +adjust-command (runs in all stages and receives the stage name) + +The pre-suite hook receives the number of tests and an array of test ids. +This allows you to dump out the list of skipped tests in the event of a +failure during setup or teardown stage. + +The pre-case hook receives the ordinal number and test id of the current test. + +The adjust-command hook receives the stage id (see list below) and the +full command to be executed. This allows for last-minute adjustment +of the command. + +The stages are identified by the following strings: + + - pre (pre-suite) + - setup + - command + - verify + - teardown + - post (post-suite) + + +To write a plugin, you need to inherit from TdcPlugin in +TdcPlugin.py. To use the plugin, you have to put the +implementation file in plugin-lib, and add a symbolic link to it from +plugins. It will be detected at run time and invoked at the +appropriate times. There are a few examples in the plugin-lib +directory: + + - rootPlugin.py: + implements the enforcement of running as root + - nsPlugin.py: + sets up a network namespace and runs all commands in that namespace + - valgrindPlugin.py + runs each command in the execute stage under valgrind, + and checks for leaks. + This plugin will output an extra test for each test in the test file, + one is the existing output as to whether the test passed or failed, + and the other is a test whether the command leaked memory or not. + (This one is a preliminary version, it may not work quite right yet, + but the overall template is there and it should only need tweaks.) ACKNOWLEDGEMENTS diff --git a/tools/testing/selftests/tc-testing/TODO.txt b/tools/testing/selftests/tc-testing/TODO.txt index 6a266d811a78..c40698557e2f 100644 --- a/tools/testing/selftests/tc-testing/TODO.txt +++ b/tools/testing/selftests/tc-testing/TODO.txt @@ -5,6 +5,27 @@ tc Testing Suite To-Do list: - Add support for multiple versions of tc to run successively -- Improve error messages when tdc aborts its run +- Improve error messages when tdc aborts its run. Partially done - still + need to better handle problems in pre- and post-suite. -- Allow tdc to write its results to file +- Use python logger module for debug/verbose output + +- Allow tdc to write its results to file. + Maybe use python logger module for this too. + +- A better implementation of the "hooks". Currently, every plugin + will attempt to run a function at every hook point. Could be + changed so that plugin __init__ methods will register functions to + be run in the various predefined times. Then if a plugin does not + require action at a specific point, no penalty will be paid for + trying to run a function that will do nothing. + +- Proper exception handling - make an exception class and use it + +- a TestCase class, for easier testcase handling, searching, comparison + +- a TestSuite class + and a way to configure a test suite, + to automate running multiple "test suites" with different requirements + +- super simple test case example using ls, touch, etc diff --git a/tools/testing/selftests/tc-testing/TdcPlugin.py b/tools/testing/selftests/tc-testing/TdcPlugin.py new file mode 100644 index 000000000000..3ee9a6dacb52 --- /dev/null +++ b/tools/testing/selftests/tc-testing/TdcPlugin.py @@ -0,0 +1,74 @@ +#!/usr/bin/env python3 + +class TdcPlugin: + def __init__(self): + super().__init__() + print(' -- {}.__init__'.format(self.sub_class)) + + def pre_suite(self, testcount, testidlist): + '''run commands before test_runner goes into a test loop''' + self.testcount = testcount + self.testidlist = testidlist + if self.args.verbose > 1: + print(' -- {}.pre_suite'.format(self.sub_class)) + + def post_suite(self, index): + '''run commands after test_runner completes the test loop + index is the last ordinal number of test that was attempted''' + if self.args.verbose > 1: + print(' -- {}.post_suite'.format(self.sub_class)) + + def pre_case(self, test_ordinal, testid): + '''run commands before test_runner does one test''' + if self.args.verbose > 1: + print(' -- {}.pre_case'.format(self.sub_class)) + self.args.testid = testid + self.args.test_ordinal = test_ordinal + + def post_case(self): + '''run commands after test_runner does one test''' + if self.args.verbose > 1: + print(' -- {}.post_case'.format(self.sub_class)) + + def pre_execute(self): + '''run command before test-runner does the execute step''' + if self.args.verbose > 1: + print(' -- {}.pre_execute'.format(self.sub_class)) + + def post_execute(self): + '''run command after test-runner does the execute step''' + if self.args.verbose > 1: + print(' -- {}.post_execute'.format(self.sub_class)) + + def adjust_command(self, stage, command): + '''adjust the command''' + if self.args.verbose > 1: + print(' -- {}.adjust_command {}'.format(self.sub_class, stage)) + + # if stage == 'pre': + # pass + # elif stage == 'setup': + # pass + # elif stage == 'execute': + # pass + # elif stage == 'verify': + # pass + # elif stage == 'teardown': + # pass + # elif stage == 'post': + # pass + # else: + # pass + + return command + + def add_args(self, parser): + '''Get the plugin args from the command line''' + self.argparser = parser + return self.argparser + + def check_args(self, args, remaining): + '''Check that the args are set correctly''' + self.args = args + if self.args.verbose > 1: + print(' -- {}.check_args'.format(self.sub_class)) diff --git a/tools/testing/selftests/tc-testing/creating-plugins/AddingPlugins.txt b/tools/testing/selftests/tc-testing/creating-plugins/AddingPlugins.txt new file mode 100644 index 000000000000..c18f88d09360 --- /dev/null +++ b/tools/testing/selftests/tc-testing/creating-plugins/AddingPlugins.txt @@ -0,0 +1,104 @@ +tdc - Adding plugins for tdc + +Author: Brenda J. Butler - bjb@mojatatu.com + +ADDING PLUGINS +-------------- + +A new plugin should be written in python as a class that inherits from TdcPlugin. +There are some examples in plugin-lib. + +The plugin can be used to add functionality to the test framework, +such as: + +- adding commands to be run before and/or after the test suite +- adding commands to be run before and/or after the test cases +- adding commands to be run before and/or after the execute phase of the test cases +- ability to alter the command to be run in any phase: + pre (the pre-suite stage) + prepare + execute + verify + teardown + post (the post-suite stage) +- ability to add to the command line args, and use them at run time + + +The functions in the class should follow the following interfaces: + + def __init__(self) + def pre_suite(self, testcount, testidlist) # see "PRE_SUITE" below + def post_suite(self, ordinal) # see "SKIPPING" below + def pre_case(self, test_ordinal, testid) # see "PRE_CASE" below + def post_case(self) + def pre_execute(self) + def post_execute(self) + def adjust_command(self, stage, command) # see "ADJUST" below + def add_args(self, parser) # see "ADD_ARGS" below + def check_args(self, args, remaining) # see "CHECK_ARGS" below + + +PRE_SUITE + +This method takes a testcount (number of tests to be run) and +testidlist (array of test ids for tests that will be run). This is +useful for various things, including when an exception occurs and the +rest of the tests must be skipped. The info is stored in the object, +and the post_suite method can refer to it when dumping the "skipped" +TAP output. The tdc.py script will do that for the test suite as +defined in the test case, but if the plugin is being used to run extra +tests on each test (eg, check for memory leaks on associated +co-processes) then that other tap output can be generated in the +post-suite method using this info passed in to the pre_suite method. + + +SKIPPING + +The post_suite method will receive the ordinal number of the last +test to be attempted. It can use this info when outputting +the TAP output for the extra test cases. + + +PRE_CASE + +The pre_case method will receive the ordinal number of the test +and the test id. Useful for outputing the extra test results. + + +ADJUST + +The adjust_command method receives a string representing +the execution stage and a string which is the actual command to be +executed. The plugin can adjust the command, based on the stage of +execution. + +The stages are represented by the following strings: + + 'pre' + 'setup' + 'command' + 'verify' + 'teardown' + 'post' + +The adjust_command method must return the adjusted command so tdc +can use it. + + +ADD_ARGS + +The add_args method receives the argparser object and can add +arguments to it. Care should be taken that the new arguments do not +conflict with any from tdc.py or from other plugins that will be used +concurrently. + +The add_args method should return the argparser object. + + +CHECK_ARGS + +The check_args method is so that the plugin can do validation on +the args, if needed. If there is a problem, and Exception should +be raised, with a string that explains the problem. + +eg: raise Exception('plugin xxx, arg -y is wrong, fix it') diff --git a/tools/testing/selftests/tc-testing/creating-testcases/AddingTestCases.txt b/tools/testing/selftests/tc-testing/creating-testcases/AddingTestCases.txt index 00438331ba47..17b267dedbd9 100644 --- a/tools/testing/selftests/tc-testing/creating-testcases/AddingTestCases.txt +++ b/tools/testing/selftests/tc-testing/creating-testcases/AddingTestCases.txt @@ -12,14 +12,18 @@ template.json for the required JSON format for test cases. Include the 'id' field, but do not assign a value. Running tdc with the -i option will generate a unique ID for that test case. -tdc will recursively search the 'tc' subdirectory for .json files. Any -test case files you create in these directories will automatically be included. -If you wish to store your custom test cases elsewhere, be sure to run tdc -with the -f argument and the path to your file. +tdc will recursively search the 'tc-tests' subdirectory (or the +directories named with the -D option) for .json files. Any test case +files you create in these directories will automatically be included. +If you wish to store your custom test cases elsewhere, be sure to run +tdc with the -f argument and the path to your file, or the -D argument +and the path to your directory(ies). -Be aware of required escape characters in the JSON data - particularly when -defining the match pattern. Refer to the tctests.json file for examples when -in doubt. +Be aware of required escape characters in the JSON data - particularly +when defining the match pattern. Refer to the supplied json test files +for examples when in doubt. The match pattern is written in json, and +will be used by python. So the match pattern will be a python regular +expression, but should be written using json syntax. TEST CASE STRUCTURE @@ -69,7 +73,8 @@ SETUP/TEARDOWN ERRORS If an error is detected during the setup/teardown process, execution of the tests will immediately stop with an error message and the namespace in which the tests are run will be destroyed. This is to prevent inaccurate results -in the test cases. +in the test cases. tdc will output a series of TAP results for the skipped +tests. Repeated failures of the setup/teardown may indicate a problem with the test case, or possibly even a bug in one of the commands that are not being tested. @@ -79,3 +84,17 @@ so that it doesn't halt the script for an error that doesn't matter. Turn the individual command into a list, with the command being first, followed by all acceptable exit codes for the command. +Example: + +A pair of setup commands. The first can have exit code 0, 1 or 255, the +second must have exit code 0. + + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ], + "$TC actions add action reclassify index 65536" + ], diff --git a/tools/testing/selftests/tc-testing/plugin-lib/README-PLUGINS b/tools/testing/selftests/tc-testing/plugin-lib/README-PLUGINS new file mode 100644 index 000000000000..aa8a2669702b --- /dev/null +++ b/tools/testing/selftests/tc-testing/plugin-lib/README-PLUGINS @@ -0,0 +1,27 @@ +tdc.py will look for plugins in a directory plugins off the cwd. +Make a set of numbered symbolic links from there to the actual plugins. +Eg: + +tdc.py +plugin-lib/ +plugins/ + __init__.py + 10-rootPlugin.py -> ../plugin-lib/rootPlugin.py + 20-valgrindPlugin.py -> ../plugin-lib/valgrindPlugin.py + 30-nsPlugin.py -> ../plugin-lib/nsPlugin.py + + +tdc.py will find them and use them. + + +rootPlugin + Check if the uid is root. If not, bail out. + +valgrindPlugin + Run the command under test with valgrind, and produce an extra set of TAP results for the memory tests. + This plugin will write files to the cwd, called vgnd-xxx.log. These will contain + the valgrind output for test xxx. Any file matching the glob 'vgnd-*.log' will be + deleted at the end of the run. + +nsPlugin + Run all the commands in a network namespace. diff --git a/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py b/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py new file mode 100644 index 000000000000..a194b1af2b30 --- /dev/null +++ b/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py @@ -0,0 +1,141 @@ +import os +import signal +from string import Template +import subprocess +import time +from TdcPlugin import TdcPlugin + +from tdc_config import * + +class SubPlugin(TdcPlugin): + def __init__(self): + self.sub_class = 'ns/SubPlugin' + super().__init__() + + def pre_suite(self, testcount, testidlist): + '''run commands before test_runner goes into a test loop''' + super().pre_suite(testcount, testidlist) + + if self.args.namespace: + self._ns_create() + + def post_suite(self, index): + '''run commands after test_runner goes into a test loop''' + super().post_suite(index) + if self.args.verbose: + print('{}.post_suite'.format(self.sub_class)) + + if self.args.namespace: + self._ns_destroy() + + def add_args(self, parser): + super().add_args(parser) + self.argparser_group = self.argparser.add_argument_group( + 'netns', + 'options for nsPlugin(run commands in net namespace)') + self.argparser_group.add_argument( + '-n', '--namespace', action='store_true', + help='Run commands in namespace') + return self.argparser + + def adjust_command(self, stage, command): + super().adjust_command(stage, command) + cmdform = 'list' + cmdlist = list() + + if not self.args.namespace: + return command + + if self.args.verbose: + print('{}.adjust_command'.format(self.sub_class)) + + if not isinstance(command, list): + cmdform = 'str' + cmdlist = command.split() + else: + cmdlist = command + if stage == 'setup' or stage == 'execute' or stage == 'verify' or stage == 'teardown': + if self.args.verbose: + print('adjust_command: stage is {}; inserting netns stuff in command [{}] list [{}]'.format(stage, command, cmdlist)) + cmdlist.insert(0, self.args.NAMES['NS']) + cmdlist.insert(0, 'exec') + cmdlist.insert(0, 'netns') + cmdlist.insert(0, 'ip') + else: + pass + + if cmdform == 'str': + command = ' '.join(cmdlist) + else: + command = cmdlist + + if self.args.verbose: + print('adjust_command: return command [{}]'.format(command)) + return command + + def _ns_create(self): + ''' + Create the network namespace in which the tests will be run and set up + the required network devices for it. + ''' + if self.args.namespace: + cmd = 'ip netns add {}'.format(self.args.NAMES['NS']) + self._exec_cmd('pre', cmd) + cmd = 'ip link add $DEV0 type veth peer name $DEV1' + self._exec_cmd('pre', cmd) + cmd = 'ip link set $DEV1 netns {}'.format(self.args.NAMES['NS']) + self._exec_cmd('pre', cmd) + cmd = 'ip link set $DEV0 up' + self._exec_cmd('pre', cmd) + cmd = 'ip -n {} link set $DEV1 up'.format(self.args.NAMES['NS']) + self._exec_cmd('pre', cmd) + if self.args.device: + cmd = 'ip link set $DEV2 netns {}'.format(self.args.NAMES['NS']) + self._exec_cmd('pre', cmd) + cmd = 'ip -n {} link set $DEV2 up'.format(self.args.NAMES['NS']) + self._exec_cmd('pre', cmd) + + def _ns_destroy(self): + ''' + Destroy the network namespace for testing (and any associated network + devices as well) + ''' + if self.args.namespace: + cmd = 'ip netns delete {}'.format(self.args.NAMES['NS']) + self._exec_cmd('post', cmd) + + def _exec_cmd(self, stage, command): + ''' + Perform any required modifications on an executable command, then run + it in a subprocess and return the results. + ''' + if '$' in command: + command = self._replace_keywords(command) + + self.adjust_command(stage, command) + if self.args.verbose: + print('_exec_cmd: command "{}"'.format(command)) + proc = subprocess.Popen(command, + shell=True, + stdout=subprocess.PIPE, + stderr=subprocess.PIPE, + env=ENVIR) + (rawout, serr) = proc.communicate() + + if proc.returncode != 0 and len(serr) > 0: + foutput = serr.decode("utf-8") + else: + foutput = rawout.decode("utf-8") + + proc.stdout.close() + proc.stderr.close() + return proc, foutput + + def _replace_keywords(self, cmd): + """ + For a given executable command, substitute any known + variables contained within NAMES with the correct values + """ + tcmd = Template(cmd) + subcmd = tcmd.safe_substitute(self.args.NAMES) + return subcmd diff --git a/tools/testing/selftests/tc-testing/plugin-lib/rootPlugin.py b/tools/testing/selftests/tc-testing/plugin-lib/rootPlugin.py new file mode 100644 index 000000000000..e36775bd4d12 --- /dev/null +++ b/tools/testing/selftests/tc-testing/plugin-lib/rootPlugin.py @@ -0,0 +1,19 @@ +import os +import sys +from TdcPlugin import TdcPlugin + +from tdc_config import * + + +class SubPlugin(TdcPlugin): + def __init__(self): + self.sub_class = 'root/SubPlugin' + super().__init__() + + def pre_suite(self, testcount, testidlist): + # run commands before test_runner goes into a test loop + super().pre_suite(testcount, testidlist) + + if os.geteuid(): + print('This script must be run with root privileges', file=sys.stderr) + exit(1) diff --git a/tools/testing/selftests/tc-testing/plugin-lib/valgrindPlugin.py b/tools/testing/selftests/tc-testing/plugin-lib/valgrindPlugin.py new file mode 100644 index 000000000000..477a7bd7d7fb --- /dev/null +++ b/tools/testing/selftests/tc-testing/plugin-lib/valgrindPlugin.py @@ -0,0 +1,142 @@ +''' +run the command under test, under valgrind and collect memory leak info +as a separate test. +''' + + +import os +import re +import signal +from string import Template +import subprocess +import time +from TdcPlugin import TdcPlugin + +from tdc_config import * + +def vp_extract_num_from_string(num_as_string_maybe_with_commas): + return int(num_as_string_maybe_with_commas.replace(',','')) + +class SubPlugin(TdcPlugin): + def __init__(self): + self.sub_class = 'valgrind/SubPlugin' + self.tap = '' + super().__init__() + + def pre_suite(self, testcount, testidlist): + '''run commands before test_runner goes into a test loop''' + super().pre_suite(testcount, testidlist) + if self.args.verbose > 1: + print('{}.pre_suite'.format(self.sub_class)) + if self.args.valgrind: + self._add_to_tap('1..{}\n'.format(self.testcount)) + + def post_suite(self, index): + '''run commands after test_runner goes into a test loop''' + super().post_suite(index) + self._add_to_tap('\n|---\n') + if self.args.verbose > 1: + print('{}.post_suite'.format(self.sub_class)) + print('{}'.format(self.tap)) + if self.args.verbose < 4: + subprocess.check_output('rm -f vgnd-*.log', shell=True) + + def add_args(self, parser): + super().add_args(parser) + self.argparser_group = self.argparser.add_argument_group( + 'valgrind', + 'options for valgrindPlugin (run command under test under Valgrind)') + + self.argparser_group.add_argument( + '-V', '--valgrind', action='store_true', + help='Run commands under valgrind') + + return self.argparser + + def adjust_command(self, stage, command): + super().adjust_command(stage, command) + cmdform = 'list' + cmdlist = list() + + if not self.args.valgrind: + return command + + if self.args.verbose > 1: + print('{}.adjust_command'.format(self.sub_class)) + + if not isinstance(command, list): + cmdform = 'str' + cmdlist = command.split() + else: + cmdlist = command + + if stage == 'execute': + if self.args.verbose > 1: + print('adjust_command: stage is {}; inserting valgrind stuff in command [{}] list [{}]'. + format(stage, command, cmdlist)) + cmdlist.insert(0, '--track-origins=yes') + cmdlist.insert(0, '--show-leak-kinds=definite,indirect') + cmdlist.insert(0, '--leak-check=full') + cmdlist.insert(0, '--log-file=vgnd-{}.log'.format(self.args.testid)) + cmdlist.insert(0, '-v') # ask for summary of non-leak errors + cmdlist.insert(0, ENVIR['VALGRIND_BIN']) + else: + pass + + if cmdform == 'str': + command = ' '.join(cmdlist) + else: + command = cmdlist + + if self.args.verbose > 1: + print('adjust_command: return command [{}]'.format(command)) + return command + + def post_execute(self): + if not self.args.valgrind: + return + + self.definitely_lost_re = re.compile( + r'definitely lost:\s+([,0-9]+)\s+bytes in\s+([,0-9]+)\sblocks', re.MULTILINE | re.DOTALL) + self.indirectly_lost_re = re.compile( + r'indirectly lost:\s+([,0-9]+)\s+bytes in\s+([,0-9]+)\s+blocks', re.MULTILINE | re.DOTALL) + self.possibly_lost_re = re.compile( + r'possibly lost:\s+([,0-9]+)bytes in\s+([,0-9]+)\s+blocks', re.MULTILINE | re.DOTALL) + self.non_leak_error_re = re.compile( + r'ERROR SUMMARY:\s+([,0-9]+) errors from\s+([,0-9]+)\s+contexts', re.MULTILINE | re.DOTALL) + + def_num = 0 + ind_num = 0 + pos_num = 0 + nle_num = 0 + + # what about concurrent test runs? Maybe force them to be in different directories? + with open('vgnd-{}.log'.format(self.args.testid)) as vfd: + content = vfd.read() + def_mo = self.definitely_lost_re.search(content) + ind_mo = self.indirectly_lost_re.search(content) + pos_mo = self.possibly_lost_re.search(content) + nle_mo = self.non_leak_error_re.search(content) + + if def_mo: + def_num = int(def_mo.group(2)) + if ind_mo: + ind_num = int(ind_mo.group(2)) + if pos_mo: + pos_num = int(pos_mo.group(2)) + if nle_mo: + nle_num = int(nle_mo.group(1)) + + mem_results = '' + if (def_num > 0) or (ind_num > 0) or (pos_num > 0) or (nle_num > 0): + mem_results += 'not ' + + mem_results += 'ok {} - {}-mem # {}\n'.format( + self.args.test_ordinal, self.args.testid, 'memory leak check') + self._add_to_tap(mem_results) + if mem_results.startswith('not '): + print('{}'.format(content)) + self._add_to_tap(content) + + def _add_to_tap(self, more_tap_output): + self.tap += more_tap_output diff --git a/tools/testing/selftests/tc-testing/plugins/__init__.py b/tools/testing/selftests/tc-testing/plugins/__init__.py new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/testing/selftests/tc-testing/plugins/__init__.py diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py index fc373fdf2bdc..7b50775abaf6 100755 --- a/tools/testing/selftests/tc-testing/tdc.py +++ b/tools/testing/selftests/tc-testing/tdc.py @@ -11,16 +11,96 @@ import re import os import sys import argparse +import importlib import json import subprocess +import time +import traceback from collections import OrderedDict from string import Template from tdc_config import * from tdc_helper import * - -USE_NS = True +import TdcPlugin + + +class PluginMgrTestFail(Exception): + def __init__(self, stage, output, message): + self.stage = stage + self.output = output + self.message = message + +class PluginMgr: + def __init__(self, argparser): + super().__init__() + self.plugins = {} + self.plugin_instances = [] + self.args = [] + self.argparser = argparser + + # TODO, put plugins in order + plugindir = os.getenv('TDC_PLUGIN_DIR', './plugins') + for dirpath, dirnames, filenames in os.walk(plugindir): + for fn in filenames: + if (fn.endswith('.py') and + not fn == '__init__.py' and + not fn.startswith('#') and + not fn.startswith('.#')): + mn = fn[0:-3] + foo = importlib.import_module('plugins.' + mn) + self.plugins[mn] = foo + self.plugin_instances.append(foo.SubPlugin()) + + def call_pre_suite(self, testcount, testidlist): + for pgn_inst in self.plugin_instances: + pgn_inst.pre_suite(testcount, testidlist) + + def call_post_suite(self, index): + for pgn_inst in reversed(self.plugin_instances): + pgn_inst.post_suite(index) + + def call_pre_case(self, test_ordinal, testid): + for pgn_inst in self.plugin_instances: + try: + pgn_inst.pre_case(test_ordinal, testid) + except Exception as ee: + print('exception {} in call to pre_case for {} plugin'. + format(ee, pgn_inst.__class__)) + print('test_ordinal is {}'.format(test_ordinal)) + print('testid is {}'.format(testid)) + raise + + def call_post_case(self): + for pgn_inst in reversed(self.plugin_instances): + pgn_inst.post_case() + + def call_pre_execute(self): + for pgn_inst in self.plugin_instances: + pgn_inst.pre_execute() + + def call_post_execute(self): + for pgn_inst in reversed(self.plugin_instances): + pgn_inst.post_execute() + + def call_add_args(self, parser): + for pgn_inst in self.plugin_instances: + parser = pgn_inst.add_args(parser) + return parser + + def call_check_args(self, args, remaining): + for pgn_inst in self.plugin_instances: + pgn_inst.check_args(args, remaining) + + def call_adjust_command(self, stage, command): + for pgn_inst in self.plugin_instances: + command = pgn_inst.adjust_command(stage, command) + return command + + @staticmethod + def _make_argparser(args): + self.argparser = argparse.ArgumentParser( + description='Linux TC unit tests') def replace_keywords(cmd): @@ -33,21 +113,24 @@ def replace_keywords(cmd): return subcmd -def exec_cmd(command, nsonly=True): +def exec_cmd(args, pm, stage, command): """ Perform any required modifications on an executable command, then run it in a subprocess and return the results. """ - if (USE_NS and nsonly): - command = 'ip netns exec $NS ' + command - + if len(command.strip()) == 0: + return None, None if '$' in command: command = replace_keywords(command) + command = pm.call_adjust_command(stage, command) + if args.verbose > 0: + print('command "{}"'.format(command)) proc = subprocess.Popen(command, shell=True, stdout=subprocess.PIPE, - stderr=subprocess.PIPE) + stderr=subprocess.PIPE, + env=ENVIR) (rawout, serr) = proc.communicate() if proc.returncode != 0 and len(serr) > 0: @@ -60,36 +143,93 @@ def exec_cmd(command, nsonly=True): return proc, foutput -def prepare_env(cmdlist): +def prepare_env(args, pm, stage, prefix, cmdlist, output = None): """ - Execute the setup/teardown commands for a test case. Optionally - terminate test execution if the command fails. + Execute the setup/teardown commands for a test case. + Optionally terminate test execution if the command fails. """ + if args.verbose > 0: + print('{}'.format(prefix)) for cmdinfo in cmdlist: - if (type(cmdinfo) == list): + if isinstance(cmdinfo, list): exit_codes = cmdinfo[1:] cmd = cmdinfo[0] else: exit_codes = [0] cmd = cmdinfo - if (len(cmd) == 0): + if not cmd: continue - (proc, foutput) = exec_cmd(cmd) + (proc, foutput) = exec_cmd(args, pm, stage, cmd) + + if proc and (proc.returncode not in exit_codes): + print('', file=sys.stderr) + print("{} *** Could not execute: \"{}\"".format(prefix, cmd), + file=sys.stderr) + print("\n{} *** Error message: \"{}\"".format(prefix, foutput), + file=sys.stderr) + print("\n{} *** Aborting test run.".format(prefix), file=sys.stderr) + print("\n\n{} *** stdout ***".format(proc.stdout), file=sys.stderr) + print("\n\n{} *** stderr ***".format(proc.stderr), file=sys.stderr) + raise PluginMgrTestFail( + stage, output, + '"{}" did not complete successfully'.format(prefix)) + +def run_one_test(pm, args, index, tidx): + result = True + tresult = "" + tap = "" + if args.verbose > 0: + print("\t====================\n=====> ", end="") + print("Test " + tidx["id"] + ": " + tidx["name"]) + + pm.call_pre_case(index, tidx['id']) + prepare_env(args, pm, 'setup', "-----> prepare stage", tidx["setup"]) + + if (args.verbose > 0): + print('-----> execute stage') + pm.call_pre_execute() + (p, procout) = exec_cmd(args, pm, 'execute', tidx["cmdUnderTest"]) + exit_code = p.returncode + pm.call_post_execute() + + if (exit_code != int(tidx["expExitCode"])): + result = False + print("exit:", exit_code, int(tidx["expExitCode"])) + print(procout) + else: + if args.verbose > 0: + print('-----> verify stage') + match_pattern = re.compile( + str(tidx["matchPattern"]), re.DOTALL | re.MULTILINE) + (p, procout) = exec_cmd(args, pm, 'verify', tidx["verifyCmd"]) + if procout: + match_index = re.findall(match_pattern, procout) + if len(match_index) != int(tidx["matchCount"]): + result = False + elif int(tidx["matchCount"]) != 0: + result = False - if proc.returncode not in exit_codes: - print - print("Could not execute:") - print(cmd) - print("\nError message:") - print(foutput) - print("\nAborting test run.") - ns_destroy() - exit(1) + if not result: + tresult += 'not ' + tresult += 'ok {} - {} # {}\n'.format(str(index), tidx['id'], tidx['name']) + tap += tresult + if result == False: + if procout: + tap += procout + else: + tap += 'No output!\n' -def test_runner(filtered_tests, args): + prepare_env(args, pm, 'teardown', '-----> teardown stage', tidx['teardown'], procout) + pm.call_post_case() + + index += 1 + + return tap + +def test_runner(pm, args, filtered_tests): """ Driver function for the unit tests. @@ -102,74 +242,79 @@ def test_runner(filtered_tests, args): tcount = len(testlist) index = 1 tap = str(index) + ".." + str(tcount) + "\n" + badtest = None + stage = None + emergency_exit = False + emergency_exit_message = '' + try: + pm.call_pre_suite(tcount, [tidx['id'] for tidx in testlist]) + except Exception as ee: + ex_type, ex, ex_tb = sys.exc_info() + print('Exception {} {} (caught in pre_suite).'. + format(ex_type, ex)) + # when the extra print statements are uncommented, + # the traceback does not appear between them + # (it appears way earlier in the tdc.py output) + # so don't bother ... + # print('--------------------(') + # print('traceback') + traceback.print_tb(ex_tb) + # print('--------------------)') + emergency_exit_message = 'EMERGENCY EXIT, call_pre_suite failed with exception {} {}\n'.format(ex_type, ex) + emergency_exit = True + stage = 'pre-SUITE' + + if emergency_exit: + pm.call_post_suite(index) + return emergency_exit_message + if args.verbose > 1: + print('give test rig 2 seconds to stabilize') + time.sleep(2) for tidx in testlist: - result = True - tresult = "" if "flower" in tidx["category"] and args.device == None: + if args.verbose > 1: + print('Not executing test {} {} because DEV2 not defined'. + format(tidx['id'], tidx['name'])) continue - print("Test " + tidx["id"] + ": " + tidx["name"]) - prepare_env(tidx["setup"]) - (p, procout) = exec_cmd(tidx["cmdUnderTest"]) - exit_code = p.returncode - - if (exit_code != int(tidx["expExitCode"])): - result = False - print("exit:", exit_code, int(tidx["expExitCode"])) - print(procout) - else: - match_pattern = re.compile(str(tidx["matchPattern"]), re.DOTALL) - (p, procout) = exec_cmd(tidx["verifyCmd"]) - match_index = re.findall(match_pattern, procout) - if len(match_index) != int(tidx["matchCount"]): - result = False - - if result == True: - tresult += "ok " - else: - tresult += "not ok " - tap += tresult + str(index) + " " + tidx["id"] + " " + tidx["name"] + "\n" - - if result == False: - tap += procout - - prepare_env(tidx["teardown"]) + try: + badtest = tidx # in case it goes bad + tap += run_one_test(pm, args, index, tidx) + except PluginMgrTestFail as pmtf: + ex_type, ex, ex_tb = sys.exc_info() + stage = pmtf.stage + message = pmtf.message + output = pmtf.output + print(message) + print('Exception {} {} (caught in test_runner, running test {} {} {} stage {})'. + format(ex_type, ex, index, tidx['id'], tidx['name'], stage)) + print('---------------') + print('traceback') + traceback.print_tb(ex_tb) + print('---------------') + if stage == 'teardown': + print('accumulated output for this test:') + if pmtf.output: + print(pmtf.output) + print('---------------') + break index += 1 - return tap + # if we failed in setup or teardown, + # fill in the remaining tests with ok-skipped + count = index + tap += 'about to flush the tap output if tests need to be skipped\n' + if tcount + 1 != index: + for tidx in testlist[index - 1:]: + msg = 'skipped - previous {} failed'.format(stage) + tap += 'ok {} - {} # {} {} {}\n'.format( + count, tidx['id'], msg, index, badtest.get('id', '--Unknown--')) + count += 1 + tap += 'done flushing skipped test tap output\n' + pm.call_post_suite(index) -def ns_create(): - """ - Create the network namespace in which the tests will be run and set up - the required network devices for it. - """ - if (USE_NS): - cmd = 'ip netns add $NS' - exec_cmd(cmd, False) - cmd = 'ip link add $DEV0 type veth peer name $DEV1' - exec_cmd(cmd, False) - cmd = 'ip link set $DEV1 netns $NS' - exec_cmd(cmd, False) - cmd = 'ip link set $DEV0 up' - exec_cmd(cmd, False) - cmd = 'ip -n $NS link set $DEV1 up' - exec_cmd(cmd, False) - cmd = 'ip link set $DEV2 netns $NS' - exec_cmd(cmd, False) - cmd = 'ip -n $NS link set $DEV2 up' - exec_cmd(cmd, False) - - -def ns_destroy(): - """ - Destroy the network namespace for testing (and any associated network - devices as well) - """ - if (USE_NS): - cmd = 'ip netns delete $NS' - exec_cmd(cmd, False) - + return tap def has_blank_ids(idlist): """ @@ -209,41 +354,64 @@ def set_args(parser): """ Set the command line arguments for tdc. """ - parser.add_argument('-p', '--path', type=str, - help='The full path to the tc executable to use') - parser.add_argument('-c', '--category', type=str, nargs='?', const='+c', - help='Run tests only from the specified category, or if no category is specified, list known categories.') - parser.add_argument('-f', '--file', type=str, - help='Run tests from the specified file') - parser.add_argument('-l', '--list', type=str, nargs='?', const="++", metavar='CATEGORY', - help='List all test cases, or those only within the specified category') - parser.add_argument('-s', '--show', type=str, nargs=1, metavar='ID', dest='showID', - help='Display the test case with specified id') - parser.add_argument('-e', '--execute', type=str, nargs=1, metavar='ID', - help='Execute the single test case with specified ID') - parser.add_argument('-i', '--id', action='store_true', dest='gen_id', - help='Generate ID numbers for new test cases') + parser.add_argument( + '-p', '--path', type=str, + help='The full path to the tc executable to use') + sg = parser.add_argument_group( + 'selection', 'select which test cases: ' + + 'files plus directories; filtered by categories plus testids') + ag = parser.add_argument_group( + 'action', 'select action to perform on selected test cases') + + sg.add_argument( + '-D', '--directory', nargs='+', metavar='DIR', + help='Collect tests from the specified directory(ies) ' + + '(default [tc-tests])') + sg.add_argument( + '-f', '--file', nargs='+', metavar='FILE', + help='Run tests from the specified file(s)') + sg.add_argument( + '-c', '--category', nargs='*', metavar='CATG', default=['+c'], + help='Run tests only from the specified category/ies, ' + + 'or if no category/ies is/are specified, list known categories.') + sg.add_argument( + '-e', '--execute', nargs='+', metavar='ID', + help='Execute the specified test cases with specified IDs') + ag.add_argument( + '-l', '--list', action='store_true', + help='List all test cases, or those only within the specified category') + ag.add_argument( + '-s', '--show', action='store_true', dest='showID', + help='Display the selected test cases') + ag.add_argument( + '-i', '--id', action='store_true', dest='gen_id', + help='Generate ID numbers for new test cases') + parser.add_argument( + '-v', '--verbose', action='count', default=0, + help='Show the commands that are being run') parser.add_argument('-d', '--device', help='Execute the test case in flower category') return parser -def check_default_settings(args): +def check_default_settings(args, remaining, pm): """ - Process any arguments overriding the default settings, and ensure the - settings are correct. + Process any arguments overriding the default settings, + and ensure the settings are correct. """ # Allow for overriding specific settings global NAMES if args.path != None: - NAMES['TC'] = args.path + NAMES['TC'] = args.path if args.device != None: - NAMES['DEV2'] = args.device + NAMES['DEV2'] = args.device if not os.path.isfile(NAMES['TC']): print("The specified tc path " + NAMES['TC'] + " does not exist.") exit(1) + pm.call_check_args(args, remaining) + def get_id_list(alltests): """ @@ -277,7 +445,7 @@ def generate_case_ids(alltests): for c in alltests: if (c["id"] == ""): while True: - newid = str('%04x' % random.randrange(16**4)) + newid = str('{:04x}'.format(random.randrange(16**4))) if (does_id_exist(alltests, newid)): continue else: @@ -300,40 +468,107 @@ def generate_case_ids(alltests): json.dump(testlist, outfile, indent=4) outfile.close() +def filter_tests_by_id(args, testlist): + ''' + Remove tests from testlist that are not in the named id list. + If id list is empty, return empty list. + ''' + newlist = list() + if testlist and args.execute: + target_ids = args.execute + + if isinstance(target_ids, list) and (len(target_ids) > 0): + newlist = list(filter(lambda x: x['id'] in target_ids, testlist)) + return newlist + +def filter_tests_by_category(args, testlist): + ''' + Remove tests from testlist that are not in a named category. + ''' + answer = list() + if args.category and testlist: + test_ids = list() + for catg in set(args.category): + if catg == '+c': + continue + print('considering category {}'.format(catg)) + for tc in testlist: + if catg in tc['category'] and tc['id'] not in test_ids: + answer.append(tc) + test_ids.append(tc['id']) + + return answer def get_test_cases(args): """ If a test case file is specified, retrieve tests from that file. Otherwise, glob for all json files in subdirectories and load from each one. + Also, if requested, filter by category, and add tests matching + certain ids. """ import fnmatch - if args.file != None: - if not os.path.isfile(args.file): - print("The specified test case file " + args.file + " does not exist.") - exit(1) - flist = [args.file] - else: - flist = [] - for root, dirnames, filenames in os.walk('tc-tests'): + + flist = [] + testdirs = ['tc-tests'] + + if args.file: + # at least one file was specified - remove the default directory + testdirs = [] + + for ff in args.file: + if not os.path.isfile(ff): + print("IGNORING file " + ff + "\n\tBECAUSE does not exist.") + else: + flist.append(os.path.abspath(ff)) + + if args.directory: + testdirs = args.directory + + for testdir in testdirs: + for root, dirnames, filenames in os.walk(testdir): for filename in fnmatch.filter(filenames, '*.json'): - flist.append(os.path.join(root, filename)) - alltests = list() + candidate = os.path.abspath(os.path.join(root, filename)) + if candidate not in testdirs: + flist.append(candidate) + + alltestcases = list() for casefile in flist: - alltests = alltests + (load_from_file(casefile)) - return alltests + alltestcases = alltestcases + (load_from_file(casefile)) + + allcatlist = get_test_categories(alltestcases) + allidlist = get_id_list(alltestcases) + testcases_by_cats = get_categorized_testlist(alltestcases, allcatlist) + idtestcases = filter_tests_by_id(args, alltestcases) + cattestcases = filter_tests_by_category(args, alltestcases) -def set_operation_mode(args): + cat_ids = [x['id'] for x in cattestcases] + if args.execute: + if args.category: + alltestcases = cattestcases + [x for x in idtestcases if x['id'] not in cat_ids] + else: + alltestcases = idtestcases + else: + if cat_ids: + alltestcases = cattestcases + else: + # just accept the existing value of alltestcases, + # which has been filtered by file/directory + pass + + return allcatlist, allidlist, testcases_by_cats, alltestcases + + +def set_operation_mode(pm, args): """ Load the test case data and process remaining arguments to determine what the script should do for this run, and call the appropriate function. """ - alltests = get_test_cases(args) + ucat, idlist, testcases, alltests = get_test_cases(args) if args.gen_id: - idlist = get_id_list(alltests) if (has_blank_ids(idlist)): alltests = generate_case_ids(alltests) else: @@ -347,70 +582,26 @@ def set_operation_mode(args): print("Please correct them before continuing.") exit(1) - ucat = get_test_categories(alltests) - if args.showID: - show_test_case_by_id(alltests, args.showID[0]) + for atest in alltests: + print_test_case(atest) exit(0) - if args.execute: - target_id = args.execute[0] - else: - target_id = "" - - if args.category: - if (args.category == '+c'): - print("Available categories:") - print_sll(ucat) - exit(0) - else: - target_category = args.category - else: - target_category = "" - - - testcases = get_categorized_testlist(alltests, ucat) + if isinstance(args.category, list) and (len(args.category) == 0): + print("Available categories:") + print_sll(ucat) + exit(0) if args.list: - if (args.list == "++"): + if args.list: list_test_cases(alltests) exit(0) - elif(len(args.list) > 0): - if (args.list not in ucat): - print("Unknown category " + args.list) - print("Available categories:") - print_sll(ucat) - exit(1) - list_test_cases(testcases[args.list]) - exit(0) - - if (os.geteuid() != 0): - print("This script must be run with root privileges.\n") - exit(1) - - ns_create() - - if (len(target_category) == 0): - if (len(target_id) > 0): - alltests = list(filter(lambda x: target_id in x['id'], alltests)) - if (len(alltests) == 0): - print("Cannot find a test case with ID matching " + target_id) - exit(1) - catresults = test_runner(alltests, args) - print("All test results: " + "\n\n" + catresults) - elif (len(target_category) > 0): - if (target_category == "flower") and args.device == None: - print("Please specify a NIC device (-d) to run category flower") - exit(1) - if (target_category not in ucat): - print("Specified category is not present in this file.") - exit(1) - else: - catresults = test_runner(testcases[target_category], args) - print("Category " + target_category + "\n\n" + catresults) - - ns_destroy() + if len(alltests): + catresults = test_runner(pm, args, alltests) + else: + catresults = 'No tests found\n' + print('All test results: \n\n{}'.format(catresults)) def main(): """ @@ -419,10 +610,15 @@ def main(): """ parser = args_parse() parser = set_args(parser) + pm = PluginMgr(parser) + parser = pm.call_add_args(parser) (args, remaining) = parser.parse_known_args() - check_default_settings(args) + args.NAMES = NAMES + check_default_settings(args, remaining, pm) + if args.verbose > 2: + print('args is {}'.format(args)) - set_operation_mode(args) + set_operation_mode(pm, args) exit(0) diff --git a/tools/testing/selftests/tc-testing/tdc_batch.py b/tools/testing/selftests/tc-testing/tdc_batch.py index 707c6bfef689..52fa539dc662 100755 --- a/tools/testing/selftests/tc-testing/tdc_batch.py +++ b/tools/testing/selftests/tc-testing/tdc_batch.py @@ -49,13 +49,13 @@ index = 0 for i in range(0x100): for j in range(0x100): for k in range(0x100): - mac = ("%02x:%02x:%02x" % (i, j, k)) + mac = ("{:02x}:{:02x}:{:02x}".format(i, j, k)) src_mac = "e4:11:00:" + mac dst_mac = "e4:12:00:" + mac - cmd = ("filter add dev %s %s protocol ip parent ffff: flower %s " - "src_mac %s dst_mac %s action drop %s" % + cmd = ("filter add dev {} {} protocol ip parent ffff: flower {} " + "src_mac {} dst_mac {} action drop {}".format (device, prio, skip, src_mac, dst_mac, share_action)) - file.write("%s\n" % cmd) + file.write("{}\n".format(cmd)) index += 1 if index >= number: file.close() diff --git a/tools/testing/selftests/tc-testing/tdc_helper.py b/tools/testing/selftests/tc-testing/tdc_helper.py index db381120a566..9f35c96c88a0 100644 --- a/tools/testing/selftests/tc-testing/tdc_helper.py +++ b/tools/testing/selftests/tc-testing/tdc_helper.py @@ -57,20 +57,11 @@ def print_sll(items): def print_test_case(tcase): """ Pretty-printing of a given test case. """ + print('\n==============\nTest {}\t{}\n'.format(tcase['id'], tcase['name'])) for k in tcase.keys(): if (isinstance(tcase[k], list)): print(k + ":") print_list(tcase[k]) else: - print(k + ": " + tcase[k]) - - -def show_test_case_by_id(testlist, caseID): - """ Find the specified test case to pretty-print. """ - if not any(d.get('id', None) == caseID for d in testlist): - print("That ID does not exist.") - exit(1) - else: - print_test_case(next((d for d in testlist if d['id'] == caseID))) - - + if not ((k == 'id') or (k == 'name')): + print(k + ": " + str(tcase[k])) diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index 10ca46df1449..d744991c0f4f 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -5,16 +5,26 @@ include ../lib.mk .PHONY: all all_32 all_64 warn_32bit_failure clean -TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_syscall test_mremap_vdso \ - check_initial_reg_state sigreturn ldt_gdt iopl mpx-mini-test ioperm \ +UNAME_M := $(shell uname -m) +CAN_BUILD_I386 := $(shell ./check_cc.sh $(CC) trivial_32bit_program.c -m32) +CAN_BUILD_X86_64 := $(shell ./check_cc.sh $(CC) trivial_64bit_program.c) + +TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt test_mremap_vdso \ + check_initial_reg_state sigreturn iopl mpx-mini-test ioperm \ protection_keys test_vdso test_vsyscall TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \ test_FCMOV test_FCOMI test_FISTTP \ vdso_restorer -TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip 5lvl +TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip +# Some selftests require 32bit support enabled also on 64bit systems +TARGETS_C_32BIT_NEEDED := ldt_gdt ptrace_syscall -TARGETS_C_32BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_32BIT_ONLY) +TARGETS_C_32BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_32BIT_ONLY) $(TARGETS_C_32BIT_NEEDED) TARGETS_C_64BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_64BIT_ONLY) +ifeq ($(CAN_BUILD_I386)$(CAN_BUILD_X86_64),11) +TARGETS_C_64BIT_ALL += $(TARGETS_C_32BIT_NEEDED) +endif + BINARIES_32 := $(TARGETS_C_32BIT_ALL:%=%_32) BINARIES_64 := $(TARGETS_C_64BIT_ALL:%=%_64) @@ -23,10 +33,6 @@ BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64)) CFLAGS := -O2 -g -std=gnu99 -pthread -Wall -no-pie -UNAME_M := $(shell uname -m) -CAN_BUILD_I386 := $(shell ./check_cc.sh $(CC) trivial_32bit_program.c -m32) -CAN_BUILD_X86_64 := $(shell ./check_cc.sh $(CC) trivial_64bit_program.c) - define gen-target-rule-32 $(1) $(1)_32: $(OUTPUT)/$(1)_32 .PHONY: $(1) $(1)_32 @@ -40,12 +46,14 @@ endef ifeq ($(CAN_BUILD_I386),1) all: all_32 TEST_PROGS += $(BINARIES_32) +EXTRA_CFLAGS += -DCAN_BUILD_32 $(foreach t,$(TARGETS_C_32BIT_ALL),$(eval $(call gen-target-rule-32,$(t)))) endif ifeq ($(CAN_BUILD_X86_64),1) all: all_64 TEST_PROGS += $(BINARIES_64) +EXTRA_CFLAGS += -DCAN_BUILD_64 $(foreach t,$(TARGETS_C_64BIT_ALL),$(eval $(call gen-target-rule-64,$(t)))) endif diff --git a/tools/testing/selftests/x86/mpx-mini-test.c b/tools/testing/selftests/x86/mpx-mini-test.c index ec0f6b45ce8b..9c0325e1ea68 100644 --- a/tools/testing/selftests/x86/mpx-mini-test.c +++ b/tools/testing/selftests/x86/mpx-mini-test.c @@ -315,11 +315,39 @@ static inline void *__si_bounds_upper(siginfo_t *si) return si->si_upper; } #else + +/* + * This deals with old version of _sigfault in some distros: + * + +old _sigfault: + struct { + void *si_addr; + } _sigfault; + +new _sigfault: + struct { + void __user *_addr; + int _trapno; + short _addr_lsb; + union { + struct { + void __user *_lower; + void __user *_upper; + } _addr_bnd; + __u32 _pkey; + }; + } _sigfault; + * + */ + static inline void **__si_bounds_hack(siginfo_t *si) { void *sigfault = &si->_sifields._sigfault; void *end_sigfault = sigfault + sizeof(si->_sifields._sigfault); - void **__si_lower = end_sigfault; + int *trapno = (int*)end_sigfault; + /* skip _trapno and _addr_lsb */ + void **__si_lower = (void**)(trapno + 2); return __si_lower; } @@ -331,7 +359,7 @@ static inline void *__si_bounds_lower(siginfo_t *si) static inline void *__si_bounds_upper(siginfo_t *si) { - return (*__si_bounds_hack(si)) + sizeof(void *); + return *(__si_bounds_hack(si) + 1); } #endif diff --git a/tools/testing/selftests/x86/protection_keys.c b/tools/testing/selftests/x86/protection_keys.c index bc1b0735bb50..f15aa5a76fe3 100644 --- a/tools/testing/selftests/x86/protection_keys.c +++ b/tools/testing/selftests/x86/protection_keys.c @@ -393,34 +393,6 @@ pid_t fork_lazy_child(void) return forkret; } -void davecmp(void *_a, void *_b, int len) -{ - int i; - unsigned long *a = _a; - unsigned long *b = _b; - - for (i = 0; i < len / sizeof(*a); i++) { - if (a[i] == b[i]) - continue; - - dprintf3("[%3d]: a: %016lx b: %016lx\n", i, a[i], b[i]); - } -} - -void dumpit(char *f) -{ - int fd = open(f, O_RDONLY); - char buf[100]; - int nr_read; - - dprintf2("maps fd: %d\n", fd); - do { - nr_read = read(fd, &buf[0], sizeof(buf)); - write(1, buf, nr_read); - } while (nr_read > 0); - close(fd); -} - #define PKEY_DISABLE_ACCESS 0x1 #define PKEY_DISABLE_WRITE 0x2 diff --git a/tools/testing/selftests/x86/single_step_syscall.c b/tools/testing/selftests/x86/single_step_syscall.c index a48da95c18fd..ddfdd635de16 100644 --- a/tools/testing/selftests/x86/single_step_syscall.c +++ b/tools/testing/selftests/x86/single_step_syscall.c @@ -119,7 +119,9 @@ static void check_result(void) int main() { +#ifdef CAN_BUILD_32 int tmp; +#endif sethandler(SIGTRAP, sigtrap, 0); @@ -139,12 +141,13 @@ int main() : : "c" (post_nop) : "r11"); check_result(); #endif - +#ifdef CAN_BUILD_32 printf("[RUN]\tSet TF and check int80\n"); set_eflags(get_eflags() | X86_EFLAGS_TF); asm volatile ("int $0x80" : "=a" (tmp) : "a" (SYS_getpid) : INT80_CLOBBERS); check_result(); +#endif /* * This test is particularly interesting if fast syscalls use diff --git a/tools/testing/selftests/x86/test_mremap_vdso.c b/tools/testing/selftests/x86/test_mremap_vdso.c index bf0d687c7db7..64f11c8d9b76 100644 --- a/tools/testing/selftests/x86/test_mremap_vdso.c +++ b/tools/testing/selftests/x86/test_mremap_vdso.c @@ -90,8 +90,12 @@ int main(int argc, char **argv, char **envp) vdso_size += PAGE_SIZE; } +#ifdef __i386__ /* Glibc is likely to explode now - exit with raw syscall */ asm volatile ("int $0x80" : : "a" (__NR_exit), "b" (!!ret)); +#else /* __x86_64__ */ + syscall(SYS_exit, ret); +#endif } else { int status; diff --git a/tools/testing/selftests/x86/test_vdso.c b/tools/testing/selftests/x86/test_vdso.c index 29973cde06d3..235259011704 100644 --- a/tools/testing/selftests/x86/test_vdso.c +++ b/tools/testing/selftests/x86/test_vdso.c @@ -26,20 +26,59 @@ # endif #endif +/* max length of lines in /proc/self/maps - anything longer is skipped here */ +#define MAPS_LINE_LEN 128 + int nerrs = 0; +typedef long (*getcpu_t)(unsigned *, unsigned *, void *); + +getcpu_t vgetcpu; +getcpu_t vdso_getcpu; + +static void *vsyscall_getcpu(void) +{ #ifdef __x86_64__ -# define VSYS(x) (x) + FILE *maps; + char line[MAPS_LINE_LEN]; + bool found = false; + + maps = fopen("/proc/self/maps", "r"); + if (!maps) /* might still be present, but ignore it here, as we test vDSO not vsyscall */ + return NULL; + + while (fgets(line, MAPS_LINE_LEN, maps)) { + char r, x; + void *start, *end; + char name[MAPS_LINE_LEN]; + + /* sscanf() is safe here as strlen(name) >= strlen(line) */ + if (sscanf(line, "%p-%p %c-%cp %*x %*x:%*x %*u %s", + &start, &end, &r, &x, name) != 5) + continue; + + if (strcmp(name, "[vsyscall]")) + continue; + + /* assume entries are OK, as we test vDSO here not vsyscall */ + found = true; + break; + } + + fclose(maps); + + if (!found) { + printf("Warning: failed to find vsyscall getcpu\n"); + return NULL; + } + return (void *) (0xffffffffff600800); #else -# define VSYS(x) 0 + return NULL; #endif +} -typedef long (*getcpu_t)(unsigned *, unsigned *, void *); - -const getcpu_t vgetcpu = (getcpu_t)VSYS(0xffffffffff600800); -getcpu_t vdso_getcpu; -void fill_function_pointers() +static void fill_function_pointers() { void *vdso = dlopen("linux-vdso.so.1", RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD); @@ -54,6 +93,8 @@ void fill_function_pointers() vdso_getcpu = (getcpu_t)dlsym(vdso, "__vdso_getcpu"); if (!vdso_getcpu) printf("Warning: failed to find getcpu in vDSO\n"); + + vgetcpu = (getcpu_t) vsyscall_getcpu(); } static long sys_getcpu(unsigned * cpu, unsigned * node, diff --git a/tools/testing/selftests/x86/test_vsyscall.c b/tools/testing/selftests/x86/test_vsyscall.c index 7a744fa7b786..be81621446f0 100644 --- a/tools/testing/selftests/x86/test_vsyscall.c +++ b/tools/testing/selftests/x86/test_vsyscall.c @@ -33,6 +33,9 @@ # endif #endif +/* max length of lines in /proc/self/maps - anything longer is skipped here */ +#define MAPS_LINE_LEN 128 + static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), int flags) { @@ -98,7 +101,7 @@ static int init_vsys(void) #ifdef __x86_64__ int nerrs = 0; FILE *maps; - char line[128]; + char line[MAPS_LINE_LEN]; bool found = false; maps = fopen("/proc/self/maps", "r"); @@ -108,10 +111,12 @@ static int init_vsys(void) return 0; } - while (fgets(line, sizeof(line), maps)) { + while (fgets(line, MAPS_LINE_LEN, maps)) { char r, x; void *start, *end; - char name[128]; + char name[MAPS_LINE_LEN]; + + /* sscanf() is safe here as strlen(name) >= strlen(line) */ if (sscanf(line, "%p-%p %c-%cp %*x %*x:%*x %*u %s", &start, &end, &r, &x, name) != 5) continue; diff --git a/tools/usb/Makefile b/tools/usb/Makefile index 4e6506078494..01d758d73b6d 100644 --- a/tools/usb/Makefile +++ b/tools/usb/Makefile @@ -1,7 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for USB tools -CC = $(CROSS_COMPILE)gcc PTHREAD_LIBS = -lpthread WARNINGS = -Wall -Wextra CFLAGS = $(WARNINGS) -g -I../include diff --git a/tools/vm/Makefile b/tools/vm/Makefile index be320b905ea7..20f6cf04377f 100644 --- a/tools/vm/Makefile +++ b/tools/vm/Makefile @@ -6,7 +6,6 @@ TARGETS=page-types slabinfo page_owner_sort LIB_DIR = ../lib/api LIBS = $(LIB_DIR)/libapi.a -CC = $(CROSS_COMPILE)gcc CFLAGS = -Wall -Wextra -I../lib/ LDFLAGS = $(LIBS) diff --git a/tools/wmi/Makefile b/tools/wmi/Makefile index e664f1167388..e0e87239126b 100644 --- a/tools/wmi/Makefile +++ b/tools/wmi/Makefile @@ -2,7 +2,6 @@ PREFIX ?= /usr SBINDIR ?= sbin INSTALL ?= install CFLAGS += -D__EXPORTED_HEADERS__ -I../../include/uapi -I../../include -CC = $(CROSS_COMPILE)gcc TARGET = dell-smbios-example |