From 5930cb3511dfb4392de1180c892b353316ef29ec Mon Sep 17 00:00:00 2001 From: Baruch Siach Date: Thu, 18 Dec 2014 21:45:24 +0200 Subject: serial: driver for Conexant Digicolor USART Signed-off-by: Baruch Siach Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/serial_core.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h index c17218094f18..9124e837c181 100644 --- a/include/uapi/linux/serial_core.h +++ b/include/uapi/linux/serial_core.h @@ -248,4 +248,7 @@ /* MESON */ #define PORT_MESON 109 +/* Conexant Digicolor */ +#define PORT_DIGICOLOR 110 + #endif /* _UAPILINUX_SERIAL_CORE_H */ -- cgit v1.2.3 From fddceb8b5399083bcc042266f188116cc779fc80 Mon Sep 17 00:00:00 2001 From: Vijay Rai Date: Mon, 5 Jan 2015 21:14:42 +0530 Subject: tty: 8250: Add 64byte UART support for FSL platforms Some of FSL SoCs like T1040 has new version of UART controller which can support 64byte FiFo. To enable 64 byte support, following needs to be done: -FCR[EN64] needs to be programmed to 1 to enable it. -Also, when FCR[EN64]==1, RTL bits to be used as below to define various Receive Trigger Levels: -FCR[RTL] = 00 1 byte -FCR[RTL] = 01 16 bytes -FCR[RTL] = 10 32 bytes -FCR[RTL] = 11 56 bytes -tx_loadsz is set to 63-bytes instead of 64-bytes to implement workaround of errata A-008006 which states that tx_loadsz should be configured less than Maximum supported fifo bytes Signed-off-by: Vijay Rai Signed-off-by: Priyanka Jain Signed-off-by: Poonam Aggrwal Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_core.c | 23 ++++++++++++++++++++++- include/uapi/linux/serial_core.h | 3 ++- include/uapi/linux/serial_reg.h | 3 ++- 3 files changed, 26 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c index 3bfcfdb57d05..689169c11f0f 100644 --- a/drivers/tty/serial/8250/8250_core.c +++ b/drivers/tty/serial/8250/8250_core.c @@ -329,6 +329,17 @@ static const struct serial8250_config uart_config[] = { .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .flags = UART_CAP_FIFO | UART_CAP_AFE, }, +/* tx_loadsz is set to 63-bytes instead of 64-bytes to implement +workaround of errata A-008006 which states that tx_loadsz should be +configured less than Maximum supported fifo bytes */ + [PORT_16550A_FSL64] = { + .name = "16550A_FSL64", + .fifo_size = 64, + .tx_loadsz = 63, + .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10 | + UART_FCR7_64BYTE, + .flags = UART_CAP_FIFO, + }, }; /* Uart divisor latch read */ @@ -956,7 +967,17 @@ static void autoconfig_16550a(struct uart_8250_port *up) up->port.type = PORT_16650; up->capabilities |= UART_CAP_EFR | UART_CAP_SLEEP; } else { - DEBUG_AUTOCONF("Motorola 8xxx DUART "); + serial_out(up, UART_LCR, 0); + serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO | + UART_FCR7_64BYTE); + status1 = serial_in(up, UART_IIR) >> 5; + serial_out(up, UART_FCR, 0); + serial_out(up, UART_LCR, 0); + + if (status1 == 7) + up->port.type = PORT_16550A_FSL64; + else + DEBUG_AUTOCONF("Motorola 8xxx DUART "); } serial_out(up, UART_EFR, 0); return; diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h index 9124e837c181..ee628c489e47 100644 --- a/include/uapi/linux/serial_core.h +++ b/include/uapi/linux/serial_core.h @@ -55,7 +55,8 @@ #define PORT_ALTR_16550_F64 27 /* Altera 16550 UART with 64 FIFOs */ #define PORT_ALTR_16550_F128 28 /* Altera 16550 UART with 128 FIFOs */ #define PORT_RT2880 29 /* Ralink RT2880 internal UART */ -#define PORT_MAX_8250 29 /* max port ID */ +#define PORT_16550A_FSL64 30 /* Freescale 16550 UART with 64 FIFOs */ +#define PORT_MAX_8250 30 /* max port ID */ /* * ARM specific type numbers. These are not currently guaranteed diff --git a/include/uapi/linux/serial_reg.h b/include/uapi/linux/serial_reg.h index 53af3b790129..00adb01fa5f3 100644 --- a/include/uapi/linux/serial_reg.h +++ b/include/uapi/linux/serial_reg.h @@ -86,7 +86,8 @@ #define UART_FCR6_T_TRIGGER_8 0x10 /* Mask for transmit trigger set at 8 */ #define UART_FCR6_T_TRIGGER_24 0x20 /* Mask for transmit trigger set at 24 */ #define UART_FCR6_T_TRIGGER_30 0x30 /* Mask for transmit trigger set at 30 */ -#define UART_FCR7_64BYTE 0x20 /* Go into 64 byte mode (TI16C750) */ +#define UART_FCR7_64BYTE 0x20 /* Go into 64 byte mode (TI16C750 and + some Freescale UARTs) */ #define UART_FCR_R_TRIG_SHIFT 6 #define UART_FCR_R_TRIG_BITS(x) \ -- cgit v1.2.3 From a0675c25d6392c2197b796a60c4a2a0138c86355 Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Sat, 7 Jun 2014 00:54:51 +0200 Subject: arm/arm64: KVM: add virtual GICv3 distributor emulation With everything separated and prepared, we implement a model of a GICv3 distributor and redistributors by using the existing framework to provide handler functions for each register group. Currently we limit the emulation to a model enforcing a single security state, with SRE==1 (forcing system register access) and ARE==1 (allowing more than 8 VCPUs). We share some of the functions provided for GICv2 emulation, but take the different ways of addressing (v)CPUs into account. Save and restore is currently not implemented. Similar to the split-off of the GICv2 specific code, the new emulation code goes into a new file (vgic-v3-emul.c). Signed-off-by: Andre Przywara Signed-off-by: Christoffer Dall --- arch/arm64/kvm/Makefile | 1 + include/kvm/arm_vgic.h | 9 +- include/linux/irqchip/arm-gic-v3.h | 32 ++ include/linux/kvm_host.h | 1 + include/uapi/linux/kvm.h | 2 + virt/kvm/arm/vgic-v3-emul.c | 922 +++++++++++++++++++++++++++++++++++++ virt/kvm/arm/vgic.c | 11 +- virt/kvm/arm/vgic.h | 3 + 8 files changed, 978 insertions(+), 3 deletions(-) create mode 100644 virt/kvm/arm/vgic-v3-emul.c (limited to 'include/uapi/linux') diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index d9573533a873..4e6e09ee4033 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -24,5 +24,6 @@ kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v2.o kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v2-emul.o kvm-$(CONFIG_KVM_ARM_VGIC) += vgic-v2-switch.o kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v3.o +kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v3-emul.o kvm-$(CONFIG_KVM_ARM_VGIC) += vgic-v3-switch.o kvm-$(CONFIG_KVM_ARM_TIMER) += $(KVM)/arm/arch_timer.o diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index ff04afd0d901..98c30168bce4 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -162,7 +162,11 @@ struct vgic_dist { /* Distributor and vcpu interface mapping in the guest */ phys_addr_t vgic_dist_base; - phys_addr_t vgic_cpu_base; + /* GICv2 and GICv3 use different mapped register blocks */ + union { + phys_addr_t vgic_cpu_base; + phys_addr_t vgic_redist_base; + }; /* Distributor enabled */ u32 enabled; @@ -224,6 +228,9 @@ struct vgic_dist { */ struct vgic_bitmap *irq_spi_target; + /* Target MPIDR for each IRQ (needed for GICv3 IROUTERn) only */ + u32 *irq_spi_mpidr; + /* Bitmap indicating which CPU has something pending */ unsigned long *irq_pending_on_cpu; diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 1e8b0cf30792..3fb4d8588a26 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -33,6 +33,7 @@ #define GICD_SETSPI_SR 0x0050 #define GICD_CLRSPI_SR 0x0058 #define GICD_SEIR 0x0068 +#define GICD_IGROUPR 0x0080 #define GICD_ISENABLER 0x0100 #define GICD_ICENABLER 0x0180 #define GICD_ISPENDR 0x0200 @@ -41,14 +42,37 @@ #define GICD_ICACTIVER 0x0380 #define GICD_IPRIORITYR 0x0400 #define GICD_ICFGR 0x0C00 +#define GICD_IGRPMODR 0x0D00 +#define GICD_NSACR 0x0E00 #define GICD_IROUTER 0x6000 +#define GICD_IDREGS 0xFFD0 #define GICD_PIDR2 0xFFE8 +/* + * Those registers are actually from GICv2, but the spec demands that they + * are implemented as RES0 if ARE is 1 (which we do in KVM's emulated GICv3). + */ +#define GICD_ITARGETSR 0x0800 +#define GICD_SGIR 0x0F00 +#define GICD_CPENDSGIR 0x0F10 +#define GICD_SPENDSGIR 0x0F20 + #define GICD_CTLR_RWP (1U << 31) +#define GICD_CTLR_DS (1U << 6) #define GICD_CTLR_ARE_NS (1U << 4) #define GICD_CTLR_ENABLE_G1A (1U << 1) #define GICD_CTLR_ENABLE_G1 (1U << 0) +/* + * In systems with a single security state (what we emulate in KVM) + * the meaning of the interrupt group enable bits is slightly different + */ +#define GICD_CTLR_ENABLE_SS_G1 (1U << 1) +#define GICD_CTLR_ENABLE_SS_G0 (1U << 0) + +#define GICD_TYPER_LPIS (1U << 17) +#define GICD_TYPER_MBIS (1U << 16) + #define GICD_TYPER_ID_BITS(typer) ((((typer) >> 19) & 0x1f) + 1) #define GICD_TYPER_IRQS(typer) ((((typer) & 0x1f) + 1) * 32) #define GICD_TYPER_LPIS (1U << 17) @@ -60,6 +84,8 @@ #define GIC_PIDR2_ARCH_GICv3 0x30 #define GIC_PIDR2_ARCH_GICv4 0x40 +#define GIC_V3_DIST_SIZE 0x10000 + /* * Re-Distributor registers, offsets from RD_base */ @@ -78,6 +104,7 @@ #define GICR_SYNCR 0x00C0 #define GICR_MOVLPIR 0x0100 #define GICR_MOVALLR 0x0110 +#define GICR_IDREGS GICD_IDREGS #define GICR_PIDR2 GICD_PIDR2 #define GICR_CTLR_ENABLE_LPIS (1UL << 0) @@ -104,6 +131,7 @@ /* * Re-Distributor registers, offsets from SGI_base */ +#define GICR_IGROUPR0 GICD_IGROUPR #define GICR_ISENABLER0 GICD_ISENABLER #define GICR_ICENABLER0 GICD_ICENABLER #define GICR_ISPENDR0 GICD_ISPENDR @@ -112,11 +140,15 @@ #define GICR_ICACTIVER0 GICD_ICACTIVER #define GICR_IPRIORITYR0 GICD_IPRIORITYR #define GICR_ICFGR0 GICD_ICFGR +#define GICR_IGRPMODR0 GICD_IGRPMODR +#define GICR_NSACR GICD_NSACR #define GICR_TYPER_PLPIS (1U << 0) #define GICR_TYPER_VLPIS (1U << 1) #define GICR_TYPER_LAST (1U << 4) +#define GIC_V3_REDIST_SIZE 0x20000 + #define LPI_PROP_GROUP1 (1 << 1) #define LPI_PROP_ENABLED (1 << 0) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 25d7ce31a5d4..0ef2daa199d8 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1052,6 +1052,7 @@ void kvm_unregister_device_ops(u32 type); extern struct kvm_device_ops kvm_mpic_ops; extern struct kvm_device_ops kvm_xics_ops; extern struct kvm_device_ops kvm_arm_vgic_v2_ops; +extern struct kvm_device_ops kvm_arm_vgic_v3_ops; #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index a37fd1224f36..b4e6f1e70f03 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -952,6 +952,8 @@ enum kvm_device_type { #define KVM_DEV_TYPE_ARM_VGIC_V2 KVM_DEV_TYPE_ARM_VGIC_V2 KVM_DEV_TYPE_FLIC, #define KVM_DEV_TYPE_FLIC KVM_DEV_TYPE_FLIC + KVM_DEV_TYPE_ARM_VGIC_V3, +#define KVM_DEV_TYPE_ARM_VGIC_V3 KVM_DEV_TYPE_ARM_VGIC_V3 KVM_DEV_TYPE_MAX, }; diff --git a/virt/kvm/arm/vgic-v3-emul.c b/virt/kvm/arm/vgic-v3-emul.c new file mode 100644 index 000000000000..8db1db597223 --- /dev/null +++ b/virt/kvm/arm/vgic-v3-emul.c @@ -0,0 +1,922 @@ +/* + * GICv3 distributor and redistributor emulation + * + * GICv3 emulation is currently only supported on a GICv3 host (because + * we rely on the hardware's CPU interface virtualization support), but + * supports both hardware with or without the optional GICv2 backwards + * compatibility features. + * + * Limitations of the emulation: + * (RAZ/WI: read as zero, write ignore, RAO/WI: read as one, write ignore) + * - We do not support LPIs (yet). TYPER.LPIS is reported as 0 and is RAZ/WI. + * - We do not support the message based interrupts (MBIs) triggered by + * writes to the GICD_{SET,CLR}SPI_* registers. TYPER.MBIS is reported as 0. + * - We do not support the (optional) backwards compatibility feature. + * GICD_CTLR.ARE resets to 1 and is RAO/WI. If the _host_ GIC supports + * the compatiblity feature, you can use a GICv2 in the guest, though. + * - We only support a single security state. GICD_CTLR.DS is 1 and is RAO/WI. + * - Priorities are not emulated (same as the GICv2 emulation). Linux + * as a guest is fine with this, because it does not use priorities. + * - We only support Group1 interrupts. Again Linux uses only those. + * + * Copyright (C) 2014 ARM Ltd. + * Author: Andre Przywara + * + * 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. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ + +#include +#include +#include +#include + +#include +#include + +#include +#include +#include + +#include "vgic.h" + +static bool handle_mmio_rao_wi(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, phys_addr_t offset) +{ + u32 reg = 0xffffffff; + + vgic_reg_access(mmio, ®, offset, + ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED); + + return false; +} + +static bool handle_mmio_ctlr(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, phys_addr_t offset) +{ + u32 reg = 0; + + /* + * Force ARE and DS to 1, the guest cannot change this. + * For the time being we only support Group1 interrupts. + */ + if (vcpu->kvm->arch.vgic.enabled) + reg = GICD_CTLR_ENABLE_SS_G1; + reg |= GICD_CTLR_ARE_NS | GICD_CTLR_DS; + + vgic_reg_access(mmio, ®, offset, + ACCESS_READ_VALUE | ACCESS_WRITE_VALUE); + if (mmio->is_write) { + if (reg & GICD_CTLR_ENABLE_SS_G0) + kvm_info("guest tried to enable unsupported Group0 interrupts\n"); + vcpu->kvm->arch.vgic.enabled = !!(reg & GICD_CTLR_ENABLE_SS_G1); + vgic_update_state(vcpu->kvm); + return true; + } + return false; +} + +/* + * As this implementation does not provide compatibility + * with GICv2 (ARE==1), we report zero CPUs in bits [5..7]. + * Also LPIs and MBIs are not supported, so we set the respective bits to 0. + * Also we report at most 2**10=1024 interrupt IDs (to match 1024 SPIs). + */ +#define INTERRUPT_ID_BITS 10 +static bool handle_mmio_typer(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, phys_addr_t offset) +{ + u32 reg; + + reg = (min(vcpu->kvm->arch.vgic.nr_irqs, 1024) >> 5) - 1; + + reg |= (INTERRUPT_ID_BITS - 1) << 19; + + vgic_reg_access(mmio, ®, offset, + ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED); + + return false; +} + +static bool handle_mmio_iidr(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, phys_addr_t offset) +{ + u32 reg; + + reg = (PRODUCT_ID_KVM << 24) | (IMPLEMENTER_ARM << 0); + vgic_reg_access(mmio, ®, offset, + ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED); + + return false; +} + +static bool handle_mmio_set_enable_reg_dist(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + if (likely(offset >= VGIC_NR_PRIVATE_IRQS / 8)) + return vgic_handle_enable_reg(vcpu->kvm, mmio, offset, + vcpu->vcpu_id, + ACCESS_WRITE_SETBIT); + + vgic_reg_access(mmio, NULL, offset, + ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED); + return false; +} + +static bool handle_mmio_clear_enable_reg_dist(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + if (likely(offset >= VGIC_NR_PRIVATE_IRQS / 8)) + return vgic_handle_enable_reg(vcpu->kvm, mmio, offset, + vcpu->vcpu_id, + ACCESS_WRITE_CLEARBIT); + + vgic_reg_access(mmio, NULL, offset, + ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED); + return false; +} + +static bool handle_mmio_set_pending_reg_dist(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + if (likely(offset >= VGIC_NR_PRIVATE_IRQS / 8)) + return vgic_handle_set_pending_reg(vcpu->kvm, mmio, offset, + vcpu->vcpu_id); + + vgic_reg_access(mmio, NULL, offset, + ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED); + return false; +} + +static bool handle_mmio_clear_pending_reg_dist(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + if (likely(offset >= VGIC_NR_PRIVATE_IRQS / 8)) + return vgic_handle_clear_pending_reg(vcpu->kvm, mmio, offset, + vcpu->vcpu_id); + + vgic_reg_access(mmio, NULL, offset, + ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED); + return false; +} + +static bool handle_mmio_priority_reg_dist(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + u32 *reg; + + if (unlikely(offset < VGIC_NR_PRIVATE_IRQS)) { + vgic_reg_access(mmio, NULL, offset, + ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED); + return false; + } + + reg = vgic_bytemap_get_reg(&vcpu->kvm->arch.vgic.irq_priority, + vcpu->vcpu_id, offset); + vgic_reg_access(mmio, reg, offset, + ACCESS_READ_VALUE | ACCESS_WRITE_VALUE); + return false; +} + +static bool handle_mmio_cfg_reg_dist(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + u32 *reg; + + if (unlikely(offset < VGIC_NR_PRIVATE_IRQS / 4)) { + vgic_reg_access(mmio, NULL, offset, + ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED); + return false; + } + + reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_cfg, + vcpu->vcpu_id, offset >> 1); + + return vgic_handle_cfg_reg(reg, mmio, offset); +} + +/* + * We use a compressed version of the MPIDR (all 32 bits in one 32-bit word) + * when we store the target MPIDR written by the guest. + */ +static u32 compress_mpidr(unsigned long mpidr) +{ + u32 ret; + + ret = MPIDR_AFFINITY_LEVEL(mpidr, 0); + ret |= MPIDR_AFFINITY_LEVEL(mpidr, 1) << 8; + ret |= MPIDR_AFFINITY_LEVEL(mpidr, 2) << 16; + ret |= MPIDR_AFFINITY_LEVEL(mpidr, 3) << 24; + + return ret; +} + +static unsigned long uncompress_mpidr(u32 value) +{ + unsigned long mpidr; + + mpidr = ((value >> 0) & 0xFF) << MPIDR_LEVEL_SHIFT(0); + mpidr |= ((value >> 8) & 0xFF) << MPIDR_LEVEL_SHIFT(1); + mpidr |= ((value >> 16) & 0xFF) << MPIDR_LEVEL_SHIFT(2); + mpidr |= (u64)((value >> 24) & 0xFF) << MPIDR_LEVEL_SHIFT(3); + + return mpidr; +} + +/* + * Lookup the given MPIDR value to get the vcpu_id (if there is one) + * and store that in the irq_spi_cpu[] array. + * This limits the number of VCPUs to 255 for now, extending the data + * type (or storing kvm_vcpu pointers) should lift the limit. + * Store the original MPIDR value in an extra array to support read-as-written. + * Unallocated MPIDRs are translated to a special value and caught + * before any array accesses. + */ +static bool handle_mmio_route_reg(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + struct kvm *kvm = vcpu->kvm; + struct vgic_dist *dist = &kvm->arch.vgic; + int spi; + u32 reg; + int vcpu_id; + unsigned long *bmap, mpidr; + + /* + * The upper 32 bits of each 64 bit register are zero, + * as we don't support Aff3. + */ + if ((offset & 4)) { + vgic_reg_access(mmio, NULL, offset, + ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED); + return false; + } + + /* This region only covers SPIs, so no handling of private IRQs here. */ + spi = offset / 8; + + /* get the stored MPIDR for this IRQ */ + mpidr = uncompress_mpidr(dist->irq_spi_mpidr[spi]); + reg = mpidr; + + vgic_reg_access(mmio, ®, offset, + ACCESS_READ_VALUE | ACCESS_WRITE_VALUE); + + if (!mmio->is_write) + return false; + + /* + * Now clear the currently assigned vCPU from the map, making room + * for the new one to be written below + */ + vcpu = kvm_mpidr_to_vcpu(kvm, mpidr); + if (likely(vcpu)) { + vcpu_id = vcpu->vcpu_id; + bmap = vgic_bitmap_get_shared_map(&dist->irq_spi_target[vcpu_id]); + __clear_bit(spi, bmap); + } + + dist->irq_spi_mpidr[spi] = compress_mpidr(reg); + vcpu = kvm_mpidr_to_vcpu(kvm, reg & MPIDR_HWID_BITMASK); + + /* + * The spec says that non-existent MPIDR values should not be + * forwarded to any existent (v)CPU, but should be able to become + * pending anyway. We simply keep the irq_spi_target[] array empty, so + * the interrupt will never be injected. + * irq_spi_cpu[irq] gets a magic value in this case. + */ + if (likely(vcpu)) { + vcpu_id = vcpu->vcpu_id; + dist->irq_spi_cpu[spi] = vcpu_id; + bmap = vgic_bitmap_get_shared_map(&dist->irq_spi_target[vcpu_id]); + __set_bit(spi, bmap); + } else { + dist->irq_spi_cpu[spi] = VCPU_NOT_ALLOCATED; + } + + vgic_update_state(kvm); + + return true; +} + +/* + * We should be careful about promising too much when a guest reads + * this register. Don't claim to be like any hardware implementation, + * but just report the GIC as version 3 - which is what a Linux guest + * would check. + */ +static bool handle_mmio_idregs(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + u32 reg = 0; + + switch (offset + GICD_IDREGS) { + case GICD_PIDR2: + reg = 0x3b; + break; + } + + vgic_reg_access(mmio, ®, offset, + ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED); + + return false; +} + +static const struct kvm_mmio_range vgic_v3_dist_ranges[] = { + { + .base = GICD_CTLR, + .len = 0x04, + .bits_per_irq = 0, + .handle_mmio = handle_mmio_ctlr, + }, + { + .base = GICD_TYPER, + .len = 0x04, + .bits_per_irq = 0, + .handle_mmio = handle_mmio_typer, + }, + { + .base = GICD_IIDR, + .len = 0x04, + .bits_per_irq = 0, + .handle_mmio = handle_mmio_iidr, + }, + { + /* this register is optional, it is RAZ/WI if not implemented */ + .base = GICD_STATUSR, + .len = 0x04, + .bits_per_irq = 0, + .handle_mmio = handle_mmio_raz_wi, + }, + { + /* this write only register is WI when TYPER.MBIS=0 */ + .base = GICD_SETSPI_NSR, + .len = 0x04, + .bits_per_irq = 0, + .handle_mmio = handle_mmio_raz_wi, + }, + { + /* this write only register is WI when TYPER.MBIS=0 */ + .base = GICD_CLRSPI_NSR, + .len = 0x04, + .bits_per_irq = 0, + .handle_mmio = handle_mmio_raz_wi, + }, + { + /* this is RAZ/WI when DS=1 */ + .base = GICD_SETSPI_SR, + .len = 0x04, + .bits_per_irq = 0, + .handle_mmio = handle_mmio_raz_wi, + }, + { + /* this is RAZ/WI when DS=1 */ + .base = GICD_CLRSPI_SR, + .len = 0x04, + .bits_per_irq = 0, + .handle_mmio = handle_mmio_raz_wi, + }, + { + .base = GICD_IGROUPR, + .len = 0x80, + .bits_per_irq = 1, + .handle_mmio = handle_mmio_rao_wi, + }, + { + .base = GICD_ISENABLER, + .len = 0x80, + .bits_per_irq = 1, + .handle_mmio = handle_mmio_set_enable_reg_dist, + }, + { + .base = GICD_ICENABLER, + .len = 0x80, + .bits_per_irq = 1, + .handle_mmio = handle_mmio_clear_enable_reg_dist, + }, + { + .base = GICD_ISPENDR, + .len = 0x80, + .bits_per_irq = 1, + .handle_mmio = handle_mmio_set_pending_reg_dist, + }, + { + .base = GICD_ICPENDR, + .len = 0x80, + .bits_per_irq = 1, + .handle_mmio = handle_mmio_clear_pending_reg_dist, + }, + { + .base = GICD_ISACTIVER, + .len = 0x80, + .bits_per_irq = 1, + .handle_mmio = handle_mmio_raz_wi, + }, + { + .base = GICD_ICACTIVER, + .len = 0x80, + .bits_per_irq = 1, + .handle_mmio = handle_mmio_raz_wi, + }, + { + .base = GICD_IPRIORITYR, + .len = 0x400, + .bits_per_irq = 8, + .handle_mmio = handle_mmio_priority_reg_dist, + }, + { + /* TARGETSRn is RES0 when ARE=1 */ + .base = GICD_ITARGETSR, + .len = 0x400, + .bits_per_irq = 8, + .handle_mmio = handle_mmio_raz_wi, + }, + { + .base = GICD_ICFGR, + .len = 0x100, + .bits_per_irq = 2, + .handle_mmio = handle_mmio_cfg_reg_dist, + }, + { + /* this is RAZ/WI when DS=1 */ + .base = GICD_IGRPMODR, + .len = 0x80, + .bits_per_irq = 1, + .handle_mmio = handle_mmio_raz_wi, + }, + { + /* this is RAZ/WI when DS=1 */ + .base = GICD_NSACR, + .len = 0x100, + .bits_per_irq = 2, + .handle_mmio = handle_mmio_raz_wi, + }, + { + /* this is RAZ/WI when ARE=1 */ + .base = GICD_SGIR, + .len = 0x04, + .handle_mmio = handle_mmio_raz_wi, + }, + { + /* this is RAZ/WI when ARE=1 */ + .base = GICD_CPENDSGIR, + .len = 0x10, + .handle_mmio = handle_mmio_raz_wi, + }, + { + /* this is RAZ/WI when ARE=1 */ + .base = GICD_SPENDSGIR, + .len = 0x10, + .handle_mmio = handle_mmio_raz_wi, + }, + { + .base = GICD_IROUTER + 0x100, + .len = 0x1ee0, + .bits_per_irq = 64, + .handle_mmio = handle_mmio_route_reg, + }, + { + .base = GICD_IDREGS, + .len = 0x30, + .bits_per_irq = 0, + .handle_mmio = handle_mmio_idregs, + }, + {}, +}; + +static bool handle_mmio_set_enable_reg_redist(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + struct kvm_vcpu *redist_vcpu = mmio->private; + + return vgic_handle_enable_reg(vcpu->kvm, mmio, offset, + redist_vcpu->vcpu_id, + ACCESS_WRITE_SETBIT); +} + +static bool handle_mmio_clear_enable_reg_redist(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + struct kvm_vcpu *redist_vcpu = mmio->private; + + return vgic_handle_enable_reg(vcpu->kvm, mmio, offset, + redist_vcpu->vcpu_id, + ACCESS_WRITE_CLEARBIT); +} + +static bool handle_mmio_set_pending_reg_redist(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + struct kvm_vcpu *redist_vcpu = mmio->private; + + return vgic_handle_set_pending_reg(vcpu->kvm, mmio, offset, + redist_vcpu->vcpu_id); +} + +static bool handle_mmio_clear_pending_reg_redist(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + struct kvm_vcpu *redist_vcpu = mmio->private; + + return vgic_handle_clear_pending_reg(vcpu->kvm, mmio, offset, + redist_vcpu->vcpu_id); +} + +static bool handle_mmio_priority_reg_redist(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + struct kvm_vcpu *redist_vcpu = mmio->private; + u32 *reg; + + reg = vgic_bytemap_get_reg(&vcpu->kvm->arch.vgic.irq_priority, + redist_vcpu->vcpu_id, offset); + vgic_reg_access(mmio, reg, offset, + ACCESS_READ_VALUE | ACCESS_WRITE_VALUE); + return false; +} + +static bool handle_mmio_cfg_reg_redist(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + struct kvm_vcpu *redist_vcpu = mmio->private; + + u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_cfg, + redist_vcpu->vcpu_id, offset >> 1); + + return vgic_handle_cfg_reg(reg, mmio, offset); +} + +static const struct kvm_mmio_range vgic_redist_sgi_ranges[] = { + { + .base = GICR_IGROUPR0, + .len = 0x04, + .bits_per_irq = 1, + .handle_mmio = handle_mmio_rao_wi, + }, + { + .base = GICR_ISENABLER0, + .len = 0x04, + .bits_per_irq = 1, + .handle_mmio = handle_mmio_set_enable_reg_redist, + }, + { + .base = GICR_ICENABLER0, + .len = 0x04, + .bits_per_irq = 1, + .handle_mmio = handle_mmio_clear_enable_reg_redist, + }, + { + .base = GICR_ISPENDR0, + .len = 0x04, + .bits_per_irq = 1, + .handle_mmio = handle_mmio_set_pending_reg_redist, + }, + { + .base = GICR_ICPENDR0, + .len = 0x04, + .bits_per_irq = 1, + .handle_mmio = handle_mmio_clear_pending_reg_redist, + }, + { + .base = GICR_ISACTIVER0, + .len = 0x04, + .bits_per_irq = 1, + .handle_mmio = handle_mmio_raz_wi, + }, + { + .base = GICR_ICACTIVER0, + .len = 0x04, + .bits_per_irq = 1, + .handle_mmio = handle_mmio_raz_wi, + }, + { + .base = GICR_IPRIORITYR0, + .len = 0x20, + .bits_per_irq = 8, + .handle_mmio = handle_mmio_priority_reg_redist, + }, + { + .base = GICR_ICFGR0, + .len = 0x08, + .bits_per_irq = 2, + .handle_mmio = handle_mmio_cfg_reg_redist, + }, + { + .base = GICR_IGRPMODR0, + .len = 0x04, + .bits_per_irq = 1, + .handle_mmio = handle_mmio_raz_wi, + }, + { + .base = GICR_NSACR, + .len = 0x04, + .handle_mmio = handle_mmio_raz_wi, + }, + {}, +}; + +static bool handle_mmio_ctlr_redist(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + /* since we don't support LPIs, this register is zero for now */ + vgic_reg_access(mmio, NULL, offset, + ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED); + return false; +} + +static bool handle_mmio_typer_redist(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + u32 reg; + u64 mpidr; + struct kvm_vcpu *redist_vcpu = mmio->private; + int target_vcpu_id = redist_vcpu->vcpu_id; + + /* the upper 32 bits contain the affinity value */ + if ((offset & ~3) == 4) { + mpidr = kvm_vcpu_get_mpidr_aff(redist_vcpu); + reg = compress_mpidr(mpidr); + + vgic_reg_access(mmio, ®, offset, + ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED); + return false; + } + + reg = redist_vcpu->vcpu_id << 8; + if (target_vcpu_id == atomic_read(&vcpu->kvm->online_vcpus) - 1) + reg |= GICR_TYPER_LAST; + vgic_reg_access(mmio, ®, offset, + ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED); + return false; +} + +static const struct kvm_mmio_range vgic_redist_ranges[] = { + { + .base = GICR_CTLR, + .len = 0x04, + .bits_per_irq = 0, + .handle_mmio = handle_mmio_ctlr_redist, + }, + { + .base = GICR_TYPER, + .len = 0x08, + .bits_per_irq = 0, + .handle_mmio = handle_mmio_typer_redist, + }, + { + .base = GICR_IIDR, + .len = 0x04, + .bits_per_irq = 0, + .handle_mmio = handle_mmio_iidr, + }, + { + .base = GICR_WAKER, + .len = 0x04, + .bits_per_irq = 0, + .handle_mmio = handle_mmio_raz_wi, + }, + { + .base = GICR_IDREGS, + .len = 0x30, + .bits_per_irq = 0, + .handle_mmio = handle_mmio_idregs, + }, + {}, +}; + +/* + * This function splits accesses between the distributor and the two + * redistributor parts (private/SPI). As each redistributor is accessible + * from any CPU, we have to determine the affected VCPU by taking the faulting + * address into account. We then pass this VCPU to the handler function via + * the private parameter. + */ +#define SGI_BASE_OFFSET SZ_64K +static bool vgic_v3_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run, + struct kvm_exit_mmio *mmio) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + unsigned long dbase = dist->vgic_dist_base; + unsigned long rdbase = dist->vgic_redist_base; + int nrcpus = atomic_read(&vcpu->kvm->online_vcpus); + int vcpu_id; + const struct kvm_mmio_range *mmio_range; + + if (is_in_range(mmio->phys_addr, mmio->len, dbase, GIC_V3_DIST_SIZE)) { + return vgic_handle_mmio_range(vcpu, run, mmio, + vgic_v3_dist_ranges, dbase); + } + + if (!is_in_range(mmio->phys_addr, mmio->len, rdbase, + GIC_V3_REDIST_SIZE * nrcpus)) + return false; + + vcpu_id = (mmio->phys_addr - rdbase) / GIC_V3_REDIST_SIZE; + rdbase += (vcpu_id * GIC_V3_REDIST_SIZE); + mmio->private = kvm_get_vcpu(vcpu->kvm, vcpu_id); + + if (mmio->phys_addr >= rdbase + SGI_BASE_OFFSET) { + rdbase += SGI_BASE_OFFSET; + mmio_range = vgic_redist_sgi_ranges; + } else { + mmio_range = vgic_redist_ranges; + } + return vgic_handle_mmio_range(vcpu, run, mmio, mmio_range, rdbase); +} + +static bool vgic_v3_queue_sgi(struct kvm_vcpu *vcpu, int irq) +{ + if (vgic_queue_irq(vcpu, 0, irq)) { + vgic_dist_irq_clear_pending(vcpu, irq); + vgic_cpu_irq_clear(vcpu, irq); + return true; + } + + return false; +} + +static int vgic_v3_map_resources(struct kvm *kvm, + const struct vgic_params *params) +{ + int ret = 0; + struct vgic_dist *dist = &kvm->arch.vgic; + + if (!irqchip_in_kernel(kvm)) + return 0; + + mutex_lock(&kvm->lock); + + if (vgic_ready(kvm)) + goto out; + + if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base) || + IS_VGIC_ADDR_UNDEF(dist->vgic_redist_base)) { + kvm_err("Need to set vgic distributor addresses first\n"); + ret = -ENXIO; + goto out; + } + + /* + * For a VGICv3 we require the userland to explicitly initialize + * the VGIC before we need to use it. + */ + if (!vgic_initialized(kvm)) { + ret = -EBUSY; + goto out; + } + + kvm->arch.vgic.ready = true; +out: + if (ret) + kvm_vgic_destroy(kvm); + mutex_unlock(&kvm->lock); + return ret; +} + +static int vgic_v3_init_model(struct kvm *kvm) +{ + int i; + u32 mpidr; + struct vgic_dist *dist = &kvm->arch.vgic; + int nr_spis = dist->nr_irqs - VGIC_NR_PRIVATE_IRQS; + + dist->irq_spi_mpidr = kcalloc(nr_spis, sizeof(dist->irq_spi_mpidr[0]), + GFP_KERNEL); + + if (!dist->irq_spi_mpidr) + return -ENOMEM; + + /* Initialize the target VCPUs for each IRQ to VCPU 0 */ + mpidr = compress_mpidr(kvm_vcpu_get_mpidr_aff(kvm_get_vcpu(kvm, 0))); + for (i = VGIC_NR_PRIVATE_IRQS; i < dist->nr_irqs; i++) { + dist->irq_spi_cpu[i - VGIC_NR_PRIVATE_IRQS] = 0; + dist->irq_spi_mpidr[i - VGIC_NR_PRIVATE_IRQS] = mpidr; + vgic_bitmap_set_irq_val(dist->irq_spi_target, 0, i, 1); + } + + return 0; +} + +/* GICv3 does not keep track of SGI sources anymore. */ +static void vgic_v3_add_sgi_source(struct kvm_vcpu *vcpu, int irq, int source) +{ +} + +void vgic_v3_init_emulation(struct kvm *kvm) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + + dist->vm_ops.handle_mmio = vgic_v3_handle_mmio; + dist->vm_ops.queue_sgi = vgic_v3_queue_sgi; + dist->vm_ops.add_sgi_source = vgic_v3_add_sgi_source; + dist->vm_ops.init_model = vgic_v3_init_model; + dist->vm_ops.map_resources = vgic_v3_map_resources; + + kvm->arch.max_vcpus = KVM_MAX_VCPUS; +} + +static int vgic_v3_create(struct kvm_device *dev, u32 type) +{ + return kvm_vgic_create(dev->kvm, type); +} + +static void vgic_v3_destroy(struct kvm_device *dev) +{ + kfree(dev); +} + +static int vgic_v3_set_attr(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + int ret; + + ret = vgic_set_common_attr(dev, attr); + if (ret != -ENXIO) + return ret; + + switch (attr->group) { + case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: + case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: + return -ENXIO; + } + + return -ENXIO; +} + +static int vgic_v3_get_attr(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + int ret; + + ret = vgic_get_common_attr(dev, attr); + if (ret != -ENXIO) + return ret; + + switch (attr->group) { + case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: + case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: + return -ENXIO; + } + + return -ENXIO; +} + +static int vgic_v3_has_attr(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + switch (attr->group) { + case KVM_DEV_ARM_VGIC_GRP_ADDR: + switch (attr->attr) { + case KVM_VGIC_V2_ADDR_TYPE_DIST: + case KVM_VGIC_V2_ADDR_TYPE_CPU: + return -ENXIO; + } + break; + case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: + case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: + return -ENXIO; + case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: + return 0; + case KVM_DEV_ARM_VGIC_GRP_CTRL: + switch (attr->attr) { + case KVM_DEV_ARM_VGIC_CTRL_INIT: + return 0; + } + } + return -ENXIO; +} + +struct kvm_device_ops kvm_arm_vgic_v3_ops = { + .name = "kvm-arm-vgic-v3", + .create = vgic_v3_create, + .destroy = vgic_v3_destroy, + .set_attr = vgic_v3_set_attr, + .get_attr = vgic_v3_get_attr, + .has_attr = vgic_v3_has_attr, +}; diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c index b6e17c886ce2..6d23e57c3561 100644 --- a/virt/kvm/arm/vgic.c +++ b/virt/kvm/arm/vgic.c @@ -1249,7 +1249,7 @@ static int vgic_update_irq_pending(struct kvm *kvm, int cpuid, struct kvm_vcpu *vcpu; int edge_triggered, level_triggered; int enabled; - bool ret = true; + bool ret = true, can_inject = true; spin_lock(&dist->lock); @@ -1264,6 +1264,11 @@ static int vgic_update_irq_pending(struct kvm *kvm, int cpuid, if (irq_num >= VGIC_NR_PRIVATE_IRQS) { cpuid = dist->irq_spi_cpu[irq_num - VGIC_NR_PRIVATE_IRQS]; + if (cpuid == VCPU_NOT_ALLOCATED) { + /* Pretend we use CPU0, and prevent injection */ + cpuid = 0; + can_inject = false; + } vcpu = kvm_get_vcpu(kvm, cpuid); } @@ -1286,7 +1291,7 @@ static int vgic_update_irq_pending(struct kvm *kvm, int cpuid, enabled = vgic_irq_is_enabled(vcpu, irq_num); - if (!enabled) { + if (!enabled || !can_inject) { ret = false; goto out; } @@ -1439,6 +1444,7 @@ void kvm_vgic_destroy(struct kvm *kvm) } kfree(dist->irq_sgi_sources); kfree(dist->irq_spi_cpu); + kfree(dist->irq_spi_mpidr); kfree(dist->irq_spi_target); kfree(dist->irq_pending_on_cpu); dist->irq_sgi_sources = NULL; @@ -1594,6 +1600,7 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) kvm->arch.vgic.vctrl_base = vgic->vctrl_base; kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF; kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF; + kvm->arch.vgic.vgic_redist_base = VGIC_ADDR_UNDEF; out_unlock: for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) { diff --git a/virt/kvm/arm/vgic.h b/virt/kvm/arm/vgic.h index e363b9341873..1e83bdf5f499 100644 --- a/virt/kvm/arm/vgic.h +++ b/virt/kvm/arm/vgic.h @@ -35,6 +35,8 @@ #define ACCESS_WRITE_VALUE (3 << 1) #define ACCESS_WRITE_MASK(x) ((x) & (3 << 1)) +#define VCPU_NOT_ALLOCATED ((u8)-1) + unsigned long *vgic_bitmap_get_shared_map(struct vgic_bitmap *x); void vgic_update_state(struct kvm *kvm); @@ -116,5 +118,6 @@ int vgic_get_common_attr(struct kvm_device *dev, struct kvm_device_attr *attr); int vgic_init(struct kvm *kvm); void vgic_v2_init_emulation(struct kvm *kvm); +void vgic_v3_init_emulation(struct kvm *kvm); #endif -- cgit v1.2.3 From 2822545f9fe264ec62d4abc69c17ae759eafe4ce Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Wed, 15 Oct 2014 16:48:16 +0200 Subject: KVM: s390: new parameter for SIGP STOP irqs In order to get rid of the action_flags and to properly migrate pending SIGP STOP irqs triggered e.g. by SIGP STOP AND STORE STATUS, we need to remember whether to store the status when stopping. For this reason, a new parameter (flags) for the SIGP STOP irq is introduced. These flags further define details of the requested STOP and can be easily migrated. Reviewed-by: Thomas Huth Acked-by: Cornelia Huck Signed-off-by: David Hildenbrand Signed-off-by: Christian Borntraeger --- Documentation/virtual/kvm/api.txt | 2 +- arch/s390/include/asm/kvm_host.h | 2 ++ arch/s390/kvm/interrupt.c | 18 +++++++++++++++++- include/uapi/linux/kvm.h | 6 ++++++ 4 files changed, 26 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 0007fef4ed81..3ca6e0e9a769 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -2312,7 +2312,7 @@ struct kvm_s390_interrupt { type can be one of the following: -KVM_S390_SIGP_STOP (vcpu) - sigp restart +KVM_S390_SIGP_STOP (vcpu) - sigp stop; optional flags in parm KVM_S390_PROGRAM_INT (vcpu) - program check; code in parm KVM_S390_SIGP_SET_PREFIX (vcpu) - sigp set prefix; prefix address in parm KVM_S390_RESTART (vcpu) - restart diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 9cba74d5d853..5eafe84a7b3d 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -378,6 +378,7 @@ struct kvm_s390_interrupt_info { struct kvm_s390_emerg_info emerg; struct kvm_s390_extcall_info extcall; struct kvm_s390_prefix_info prefix; + struct kvm_s390_stop_info stop; struct kvm_s390_mchk_info mchk; }; }; @@ -393,6 +394,7 @@ struct kvm_s390_irq_payload { struct kvm_s390_emerg_info emerg; struct kvm_s390_extcall_info extcall; struct kvm_s390_prefix_info prefix; + struct kvm_s390_stop_info stop; struct kvm_s390_mchk_info mchk; }; diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 7fbbcbcea6ac..73bafc3d0f41 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -394,13 +394,20 @@ static int __must_check __deliver_restart(struct kvm_vcpu *vcpu) static int __must_check __deliver_stop(struct kvm_vcpu *vcpu) { + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + struct kvm_s390_stop_info *stop = &li->irq.stop; + + spin_lock(&li->lock); + stop->flags = 0; + clear_bit(IRQ_PEND_SIGP_STOP, &li->pending_irqs); + spin_unlock(&li->lock); + VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu stop"); vcpu->stat.deliver_stop_signal++; trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_SIGP_STOP, 0, 0); __set_cpuflag(vcpu, CPUSTAT_STOP_INT); - clear_bit(IRQ_PEND_SIGP_STOP, &vcpu->arch.local_int.pending_irqs); return 0; } @@ -1031,13 +1038,19 @@ static int __inject_set_prefix(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) return 0; } +#define KVM_S390_STOP_SUPP_FLAGS 0 static int __inject_sigp_stop(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + struct kvm_s390_stop_info *stop = &li->irq.stop; trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_SIGP_STOP, 0, 0, 2); + if (irq->u.stop.flags & ~KVM_S390_STOP_SUPP_FLAGS) + return -EINVAL; + li->action_bits |= ACTION_STOP_ON_STOP; + stop->flags = irq->u.stop.flags; set_bit(IRQ_PEND_SIGP_STOP, &li->pending_irqs); return 0; } @@ -1306,6 +1319,9 @@ int s390int_to_s390irq(struct kvm_s390_interrupt *s390int, case KVM_S390_SIGP_SET_PREFIX: irq->u.prefix.address = s390int->parm; break; + case KVM_S390_SIGP_STOP: + irq->u.stop.flags = s390int->parm; + break; case KVM_S390_INT_EXTERNAL_CALL: if (irq->u.extcall.code & 0xffff0000) return -EINVAL; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index a37fd1224f36..adc24a3fd23e 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -491,6 +491,11 @@ struct kvm_s390_emerg_info { __u16 code; }; +#define KVM_S390_STOP_FLAG_STORE_STATUS 0x01 +struct kvm_s390_stop_info { + __u32 flags; +}; + struct kvm_s390_mchk_info { __u64 cr14; __u64 mcic; @@ -509,6 +514,7 @@ struct kvm_s390_irq { struct kvm_s390_emerg_info emerg; struct kvm_s390_extcall_info extcall; struct kvm_s390_prefix_info prefix; + struct kvm_s390_stop_info stop; struct kvm_s390_mchk_info mchk; char reserved[64]; } u; -- cgit v1.2.3 From 2444b352c3acf54897b0e2803a7c4e66699f9f43 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 9 Oct 2014 14:10:13 +0200 Subject: KVM: s390: forward most SIGP orders to user space Most SIGP orders are handled partially in kernel and partially in user space. In order to: - Get a correct SIGP SET PREFIX handler that informs user space - Avoid race conditions between concurrently executed SIGP orders - Serialize SIGP orders per VCPU We need to handle all "slow" SIGP orders in user space. The remaining ones to be handled completely in kernel are: - SENSE - SENSE RUNNING - EXTERNAL CALL - EMERGENCY SIGNAL - CONDITIONAL EMERGENCY SIGNAL According to the PoP, they have to be fast. They can be executed without conflicting to the actions of other pending/concurrently executing orders (e.g. STOP vs. START). This patch introduces a new capability that will - when enabled - forward all but the mentioned SIGP orders to user space. The instruction counters in the kernel are still updated. Reviewed-by: Cornelia Huck Signed-off-by: David Hildenbrand Signed-off-by: Christian Borntraeger --- Documentation/virtual/kvm/api.txt | 20 ++++++++++++++++ arch/s390/include/asm/kvm_host.h | 1 + arch/s390/kvm/kvm-s390.c | 5 ++++ arch/s390/kvm/sigp.c | 49 +++++++++++++++++++++++++++++++++++++++ include/uapi/linux/kvm.h | 1 + 5 files changed, 76 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 3ca6e0e9a769..df19837e94d4 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -3225,3 +3225,23 @@ userspace from doing that. If the hcall number specified is not one that has an in-kernel implementation, the KVM_ENABLE_CAP ioctl will fail with an EINVAL error. + +7.2 KVM_CAP_S390_USER_SIGP + +Architectures: s390 +Parameters: none + +This capability controls which SIGP orders will be handled completely in user +space. With this capability enabled, all fast orders will be handled completely +in the kernel: +- SENSE +- SENSE RUNNING +- EXTERNAL CALL +- EMERGENCY SIGNAL +- CONDITIONAL EMERGENCY SIGNAL + +All other orders will be handled completely in user space. + +Only privileged operation exceptions will be checked for in the kernel (or even +in the hardware prior to interception). If this capability is not enabled, the +old way of handling SIGP orders is used (partially in kernel and user space). diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index b6170520380b..a2dcd0e099f7 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -521,6 +521,7 @@ struct kvm_arch{ int use_irqchip; int use_cmma; int user_cpu_state_ctrl; + int user_sigp; struct s390_io_adapter *adapters[MAX_S390_IO_ADAPTERS]; wait_queue_head_t ipte_wq; int ipte_lock_count; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index bfb2b990da9b..3677b8ca647f 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -166,6 +166,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_IRQCHIP: case KVM_CAP_VM_ATTRIBUTES: case KVM_CAP_MP_STATE: + case KVM_CAP_S390_USER_SIGP: r = 1; break; case KVM_CAP_NR_VCPUS: @@ -254,6 +255,10 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) kvm->arch.use_irqchip = 1; r = 0; break; + case KVM_CAP_S390_USER_SIGP: + kvm->arch.user_sigp = 1; + r = 0; + break; default: r = -EINVAL; break; diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c index 1524be9120ad..23b1e86b2122 100644 --- a/arch/s390/kvm/sigp.c +++ b/arch/s390/kvm/sigp.c @@ -371,6 +371,53 @@ static int handle_sigp_dst(struct kvm_vcpu *vcpu, u8 order_code, return rc; } +static int handle_sigp_order_in_user_space(struct kvm_vcpu *vcpu, u8 order_code) +{ + if (!vcpu->kvm->arch.user_sigp) + return 0; + + switch (order_code) { + case SIGP_SENSE: + case SIGP_EXTERNAL_CALL: + case SIGP_EMERGENCY_SIGNAL: + case SIGP_COND_EMERGENCY_SIGNAL: + case SIGP_SENSE_RUNNING: + return 0; + /* update counters as we're directly dropping to user space */ + case SIGP_STOP: + vcpu->stat.instruction_sigp_stop++; + break; + case SIGP_STOP_AND_STORE_STATUS: + vcpu->stat.instruction_sigp_stop_store_status++; + break; + case SIGP_STORE_STATUS_AT_ADDRESS: + vcpu->stat.instruction_sigp_store_status++; + break; + case SIGP_SET_PREFIX: + vcpu->stat.instruction_sigp_prefix++; + break; + case SIGP_START: + vcpu->stat.instruction_sigp_start++; + break; + case SIGP_RESTART: + vcpu->stat.instruction_sigp_restart++; + break; + case SIGP_INITIAL_CPU_RESET: + vcpu->stat.instruction_sigp_init_cpu_reset++; + break; + case SIGP_CPU_RESET: + vcpu->stat.instruction_sigp_cpu_reset++; + break; + default: + vcpu->stat.instruction_sigp_unknown++; + } + + VCPU_EVENT(vcpu, 4, "sigp order %u: completely handled in user space", + order_code); + + return 1; +} + int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu) { int r1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4; @@ -385,6 +432,8 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); order_code = kvm_s390_get_base_disp_rs(vcpu); + if (handle_sigp_order_in_user_space(vcpu, order_code)) + return -EOPNOTSUPP; if (r1 % 2) parameter = vcpu->run->s.regs.gprs[r1]; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index adc24a3fd23e..37f71c3040c3 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -759,6 +759,7 @@ struct kvm_ppc_smmu_info { #define KVM_CAP_PPC_FIXUP_HCALL 103 #define KVM_CAP_PPC_ENABLE_HCALL 104 #define KVM_CAP_CHECK_EXTENSION_VM 105 +#define KVM_CAP_S390_USER_SIGP 106 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From 5e33f6fdf735cda1d4580fe6f1878da05718fe73 Mon Sep 17 00:00:00 2001 From: Robert Baldyga Date: Fri, 23 Jan 2015 13:41:01 +0100 Subject: usb: gadget: ffs: add eventfd notification about ffs events Add eventfd which notifies userspace about ep0 events and AIO completion events. It simplifies using of FunctionFS with event loop, because now we need to poll on single file (instead of polling on ep0 and eventfd's supplied to AIO layer). FunctionFS eventfd is not triggered if another eventfd is supplied to AIO layer (in AIO request). It can be useful, for example, when we want to handle AIO transations for chosen endpoint in separate thread. Signed-off-by: Robert Baldyga Acked-by: Michal Nazarewicz Signed-off-by: Felipe Balbi --- drivers/usb/gadget/function/f_fs.c | 29 ++++++++++++++++++++++++++++- drivers/usb/gadget/function/u_fs.h | 1 + include/uapi/linux/usb/functionfs.h | 1 + 3 files changed, 30 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 14e44d7083a1..af98b096af2f 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -31,6 +31,7 @@ #include #include #include +#include #include "u_fs.h" #include "u_f.h" @@ -153,6 +154,8 @@ struct ffs_io_data { struct usb_ep *ep; struct usb_request *req; + + struct ffs_data *ffs; }; struct ffs_desc_helper { @@ -674,6 +677,9 @@ static void ffs_user_copy_worker(struct work_struct *work) aio_complete(io_data->kiocb, ret, ret); + if (io_data->ffs->ffs_eventfd && !io_data->kiocb->ki_eventfd) + eventfd_signal(io_data->ffs->ffs_eventfd, 1); + usb_ep_free_request(io_data->ep, io_data->req); io_data->kiocb->private = NULL; @@ -827,6 +833,7 @@ static ssize_t ffs_epfile_io(struct file *file, struct ffs_io_data *io_data) io_data->buf = data; io_data->ep = ep->ep; io_data->req = req; + io_data->ffs = epfile->ffs; req->context = io_data; req->complete = ffs_epfile_async_io_complete; @@ -1510,6 +1517,9 @@ static void ffs_data_clear(struct ffs_data *ffs) if (ffs->epfiles) ffs_epfiles_destroy(ffs->epfiles, ffs->eps_count); + if (ffs->ffs_eventfd) + eventfd_ctx_put(ffs->ffs_eventfd); + kfree(ffs->raw_descs_data); kfree(ffs->raw_strings); kfree(ffs->stringtabs); @@ -2169,7 +2179,8 @@ static int __ffs_data_got_descs(struct ffs_data *ffs, FUNCTIONFS_HAS_HS_DESC | FUNCTIONFS_HAS_SS_DESC | FUNCTIONFS_HAS_MS_OS_DESC | - FUNCTIONFS_VIRTUAL_ADDR)) { + FUNCTIONFS_VIRTUAL_ADDR | + FUNCTIONFS_EVENTFD)) { ret = -ENOSYS; goto error; } @@ -2180,6 +2191,20 @@ static int __ffs_data_got_descs(struct ffs_data *ffs, goto error; } + if (flags & FUNCTIONFS_EVENTFD) { + if (len < 4) + goto error; + ffs->ffs_eventfd = + eventfd_ctx_fdget((int)get_unaligned_le32(data)); + if (IS_ERR(ffs->ffs_eventfd)) { + ret = PTR_ERR(ffs->ffs_eventfd); + ffs->ffs_eventfd = NULL; + goto error; + } + data += 4; + len -= 4; + } + /* Read fs_count, hs_count and ss_count (if present) */ for (i = 0; i < 3; ++i) { if (!(flags & (1 << i))) { @@ -2454,6 +2479,8 @@ static void __ffs_event_add(struct ffs_data *ffs, pr_vdebug("adding event %d\n", type); ffs->ev.types[ffs->ev.count++] = type; wake_up_locked(&ffs->ev.waitq); + if (ffs->ffs_eventfd) + eventfd_signal(ffs->ffs_eventfd, 1); } static void ffs_event_add(struct ffs_data *ffs, diff --git a/drivers/usb/gadget/function/u_fs.h b/drivers/usb/gadget/function/u_fs.h index 284a1f00a980..60139854e0b1 100644 --- a/drivers/usb/gadget/function/u_fs.h +++ b/drivers/usb/gadget/function/u_fs.h @@ -272,6 +272,7 @@ struct ffs_data { kgid_t gid; } file_perms; + struct eventfd_ctx *ffs_eventfd; bool no_disconnect; struct work_struct reset_work; diff --git a/include/uapi/linux/usb/functionfs.h b/include/uapi/linux/usb/functionfs.h index 295ba299e7bd..108dd7997014 100644 --- a/include/uapi/linux/usb/functionfs.h +++ b/include/uapi/linux/usb/functionfs.h @@ -20,6 +20,7 @@ enum functionfs_flags { FUNCTIONFS_HAS_SS_DESC = 4, FUNCTIONFS_HAS_MS_OS_DESC = 8, FUNCTIONFS_VIRTUAL_ADDR = 16, + FUNCTIONFS_EVENTFD = 32, }; /* Descriptor of an non-audio endpoint */ -- cgit v1.2.3 From 3f2cee73b650921b2e214bf487b2061a1c266504 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Thu, 29 Jan 2015 11:29:13 -0500 Subject: USB: usbfs: allow URBs to be reaped after disconnection The usbfs API has a peculiar hole: Users are not allowed to reap their URBs after the device has been disconnected. There doesn't seem to be any good reason for this; it is an ad-hoc inconsistency. The patch allows users to issue the USBDEVFS_REAPURB and USBDEVFS_REAPURBNDELAY ioctls (together with their 32-bit counterparts on 64-bit systems) even after the device is gone. If no URBs are pending for a disconnected device then the ioctls will return -ENODEV rather than -EAGAIN, because obviously no new URBs will ever be able to complete. The patch also adds a new capability flag for USBDEVFS_GET_CAPABILITIES to indicate that the reap-after-disconnect feature is supported. Signed-off-by: Alan Stern Tested-by: Chris Dickens Acked-by: Hans de Goede Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/devio.c | 63 +++++++++++++++++++++++---------------- include/uapi/linux/usbdevice_fs.h | 3 +- 2 files changed, 39 insertions(+), 27 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index 0b59731c3021..66abdbcfbfa5 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -1689,7 +1689,7 @@ static struct async *reap_as(struct usb_dev_state *ps) for (;;) { __set_current_state(TASK_INTERRUPTIBLE); as = async_getcompleted(ps); - if (as) + if (as || !connected(ps)) break; if (signal_pending(current)) break; @@ -1712,7 +1712,7 @@ static int proc_reapurb(struct usb_dev_state *ps, void __user *arg) } if (signal_pending(current)) return -EINTR; - return -EIO; + return -ENODEV; } static int proc_reapurbnonblock(struct usb_dev_state *ps, void __user *arg) @@ -1721,10 +1721,11 @@ static int proc_reapurbnonblock(struct usb_dev_state *ps, void __user *arg) struct async *as; as = async_getcompleted(ps); - retval = -EAGAIN; if (as) { retval = processcompl(as, (void __user * __user *)arg); free_async(as); + } else { + retval = (connected(ps) ? -EAGAIN : -ENODEV); } return retval; } @@ -1854,7 +1855,7 @@ static int proc_reapurb_compat(struct usb_dev_state *ps, void __user *arg) } if (signal_pending(current)) return -EINTR; - return -EIO; + return -ENODEV; } static int proc_reapurbnonblock_compat(struct usb_dev_state *ps, void __user *arg) @@ -1862,11 +1863,12 @@ static int proc_reapurbnonblock_compat(struct usb_dev_state *ps, void __user *ar int retval; struct async *as; - retval = -EAGAIN; as = async_getcompleted(ps); if (as) { retval = processcompl_compat(as, (void __user * __user *)arg); free_async(as); + } else { + retval = (connected(ps) ? -EAGAIN : -ENODEV); } return retval; } @@ -2038,7 +2040,8 @@ static int proc_get_capabilities(struct usb_dev_state *ps, void __user *arg) { __u32 caps; - caps = USBDEVFS_CAP_ZERO_PACKET | USBDEVFS_CAP_NO_PACKET_SIZE_LIM; + caps = USBDEVFS_CAP_ZERO_PACKET | USBDEVFS_CAP_NO_PACKET_SIZE_LIM | + USBDEVFS_CAP_REAP_AFTER_DISCONNECT; if (!ps->dev->bus->no_stop_on_short) caps |= USBDEVFS_CAP_BULK_CONTINUATION; if (ps->dev->bus->sg_tablesize) @@ -2138,6 +2141,32 @@ static long usbdev_do_ioctl(struct file *file, unsigned int cmd, return -EPERM; usb_lock_device(dev); + + /* Reap operations are allowed even after disconnection */ + switch (cmd) { + case USBDEVFS_REAPURB: + snoop(&dev->dev, "%s: REAPURB\n", __func__); + ret = proc_reapurb(ps, p); + goto done; + + case USBDEVFS_REAPURBNDELAY: + snoop(&dev->dev, "%s: REAPURBNDELAY\n", __func__); + ret = proc_reapurbnonblock(ps, p); + goto done; + +#ifdef CONFIG_COMPAT + case USBDEVFS_REAPURB32: + snoop(&dev->dev, "%s: REAPURB32\n", __func__); + ret = proc_reapurb_compat(ps, p); + goto done; + + case USBDEVFS_REAPURBNDELAY32: + snoop(&dev->dev, "%s: REAPURBNDELAY32\n", __func__); + ret = proc_reapurbnonblock_compat(ps, p); + goto done; +#endif + } + if (!connected(ps)) { usb_unlock_device(dev); return -ENODEV; @@ -2231,16 +2260,6 @@ static long usbdev_do_ioctl(struct file *file, unsigned int cmd, inode->i_mtime = CURRENT_TIME; break; - case USBDEVFS_REAPURB32: - snoop(&dev->dev, "%s: REAPURB32\n", __func__); - ret = proc_reapurb_compat(ps, p); - break; - - case USBDEVFS_REAPURBNDELAY32: - snoop(&dev->dev, "%s: REAPURBNDELAY32\n", __func__); - ret = proc_reapurbnonblock_compat(ps, p); - break; - case USBDEVFS_IOCTL32: snoop(&dev->dev, "%s: IOCTL32\n", __func__); ret = proc_ioctl_compat(ps, ptr_to_compat(p)); @@ -2252,16 +2271,6 @@ static long usbdev_do_ioctl(struct file *file, unsigned int cmd, ret = proc_unlinkurb(ps, p); break; - case USBDEVFS_REAPURB: - snoop(&dev->dev, "%s: REAPURB\n", __func__); - ret = proc_reapurb(ps, p); - break; - - case USBDEVFS_REAPURBNDELAY: - snoop(&dev->dev, "%s: REAPURBNDELAY\n", __func__); - ret = proc_reapurbnonblock(ps, p); - break; - case USBDEVFS_DISCSIGNAL: snoop(&dev->dev, "%s: DISCSIGNAL\n", __func__); ret = proc_disconnectsignal(ps, p); @@ -2304,6 +2313,8 @@ static long usbdev_do_ioctl(struct file *file, unsigned int cmd, ret = proc_free_streams(ps, p); break; } + + done: usb_unlock_device(dev); if (ret >= 0) inode->i_atime = CURRENT_TIME; diff --git a/include/uapi/linux/usbdevice_fs.h b/include/uapi/linux/usbdevice_fs.h index abe5f4bd4d82..019ba1e0799a 100644 --- a/include/uapi/linux/usbdevice_fs.h +++ b/include/uapi/linux/usbdevice_fs.h @@ -128,11 +128,12 @@ struct usbdevfs_hub_portinfo { char port [127]; /* e.g. port 3 connects to device 27 */ }; -/* Device capability flags */ +/* System and bus capability flags */ #define USBDEVFS_CAP_ZERO_PACKET 0x01 #define USBDEVFS_CAP_BULK_CONTINUATION 0x02 #define USBDEVFS_CAP_NO_PACKET_SIZE_LIM 0x04 #define USBDEVFS_CAP_BULK_SCATTER_GATHER 0x08 +#define USBDEVFS_CAP_REAP_AFTER_DISCONNECT 0x10 /* USBDEVFS_DISCONNECT_CLAIM flags & struct */ -- cgit v1.2.3 From 9cf514ccfacb301f3b1b4509a8ce25dffad55880 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 5 May 2014 13:11:59 +0200 Subject: nfsd: implement pNFS operations Add support for the GETDEVICEINFO, LAYOUTGET, LAYOUTCOMMIT and LAYOUTRETURN NFSv4.1 operations, as well as backing code to manage outstanding layouts and devices. Layout management is very straight forward, with a nfs4_layout_stateid structure that extends nfs4_stid to manage layout stateids as the top-level structure. It is linked into the nfs4_file and nfs4_client structures like the other stateids, and contains a linked list of layouts that hang of the stateid. The actual layout operations are implemented in layout drivers that are not part of this commit, but will be added later. The worst part of this commit is the management of the pNFS device IDs, which suffers from a specification that is not sanely implementable due to the fact that the device-IDs are global and not bound to an export, and have a small enough size so that we can't store the fsid portion of a file handle, and must never be reused. As we still do need perform all export authentication and validation checks on a device ID passed to GETDEVICEINFO we are caught between a rock and a hard place. To work around this issue we add a new hash that maps from a 64-bit integer to a fsid so that we can look up the export to authenticate against it, a 32-bit integer as a generation that we can bump when changing the device, and a currently unused 32-bit integer that could be used in the future to handle more than a single device per export. Entries in this hash table are never deleted as we can't reuse the ids anyway, and would have a severe lifetime problem anyway as Linux export structures are temporary structures that can go away under load. Parts of the XDR data, structures and marshaling/unmarshaling code, as well as many concepts are derived from the old pNFS server implementation from Andy Adamson, Benny Halevy, Dean Hildebrand, Marc Eshel, Fred Isaman, Mike Sager, Ricardo Labiaga and many others. Signed-off-by: Christoph Hellwig --- fs/nfsd/Kconfig | 10 + fs/nfsd/Makefile | 1 + fs/nfsd/export.c | 8 + fs/nfsd/export.h | 2 + fs/nfsd/nfs4layouts.c | 487 +++++++++++++++++++++++++++++++++++++++ fs/nfsd/nfs4proc.c | 302 ++++++++++++++++++++++++ fs/nfsd/nfs4state.c | 16 +- fs/nfsd/nfs4xdr.c | 312 +++++++++++++++++++++++++ fs/nfsd/nfsctl.c | 9 +- fs/nfsd/nfsd.h | 16 +- fs/nfsd/pnfs.h | 80 +++++++ fs/nfsd/state.h | 21 ++ fs/nfsd/xdr4.h | 59 +++++ include/linux/nfs4.h | 1 + include/uapi/linux/nfsd/debug.h | 1 + include/uapi/linux/nfsd/export.h | 4 +- 16 files changed, 1324 insertions(+), 5 deletions(-) create mode 100644 fs/nfsd/nfs4layouts.c create mode 100644 fs/nfsd/pnfs.h (limited to 'include/uapi/linux') diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig index 73395156bdb4..683bf718aead 100644 --- a/fs/nfsd/Kconfig +++ b/fs/nfsd/Kconfig @@ -82,6 +82,16 @@ config NFSD_V4 If unsure, say N. +config NFSD_PNFS + bool "NFSv4.1 server support for Parallel NFS (pNFS)" + depends on NFSD_V4 + help + This option enables support for the parallel NFS features of the + minor version 1 of the NFSv4 protocol (RFC5661) in the kernel's NFS + server. + + If unsure, say N. + config NFSD_V4_SECURITY_LABEL bool "Provide Security Label support for NFSv4 server" depends on NFSD_V4 && SECURITY diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile index af32ef06b4fe..5806270a8567 100644 --- a/fs/nfsd/Makefile +++ b/fs/nfsd/Makefile @@ -12,3 +12,4 @@ nfsd-$(CONFIG_NFSD_V3) += nfs3proc.o nfs3xdr.o nfsd-$(CONFIG_NFSD_V3_ACL) += nfs3acl.o nfsd-$(CONFIG_NFSD_V4) += nfs4proc.o nfs4xdr.o nfs4state.o nfs4idmap.o \ nfs4acl.o nfs4callback.o nfs4recover.o +nfsd-$(CONFIG_NFSD_PNFS) += nfs4layouts.o diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index 30a739d896ff..c3e3b6e55ae2 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -20,6 +20,7 @@ #include "nfsd.h" #include "nfsfh.h" #include "netns.h" +#include "pnfs.h" #define NFSDDBG_FACILITY NFSDDBG_EXPORT @@ -545,6 +546,7 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) exp.ex_client = dom; exp.cd = cd; + exp.ex_devid_map = NULL; /* expiry */ err = -EINVAL; @@ -621,6 +623,8 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) if (!gid_valid(exp.ex_anon_gid)) goto out4; err = 0; + + nfsd4_setup_layout_type(&exp); } expp = svc_export_lookup(&exp); @@ -703,6 +707,7 @@ static void svc_export_init(struct cache_head *cnew, struct cache_head *citem) new->ex_fslocs.locations = NULL; new->ex_fslocs.locations_count = 0; new->ex_fslocs.migrated = 0; + new->ex_layout_type = 0; new->ex_uuid = NULL; new->cd = item->cd; } @@ -717,6 +722,8 @@ static void export_update(struct cache_head *cnew, struct cache_head *citem) new->ex_anon_uid = item->ex_anon_uid; new->ex_anon_gid = item->ex_anon_gid; new->ex_fsid = item->ex_fsid; + new->ex_devid_map = item->ex_devid_map; + item->ex_devid_map = NULL; new->ex_uuid = item->ex_uuid; item->ex_uuid = NULL; new->ex_fslocs.locations = item->ex_fslocs.locations; @@ -725,6 +732,7 @@ static void export_update(struct cache_head *cnew, struct cache_head *citem) item->ex_fslocs.locations_count = 0; new->ex_fslocs.migrated = item->ex_fslocs.migrated; item->ex_fslocs.migrated = 0; + new->ex_layout_type = item->ex_layout_type; new->ex_nflavors = item->ex_nflavors; for (i = 0; i < MAX_SECINFO_LIST; i++) { new->ex_flavors[i] = item->ex_flavors[i]; diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h index 04dc8c167b0c..1f52bfcc436f 100644 --- a/fs/nfsd/export.h +++ b/fs/nfsd/export.h @@ -56,6 +56,8 @@ struct svc_export { struct nfsd4_fs_locations ex_fslocs; uint32_t ex_nflavors; struct exp_flavor_info ex_flavors[MAX_SECINFO_LIST]; + enum pnfs_layouttype ex_layout_type; + struct nfsd4_deviceid_map *ex_devid_map; struct cache_detail *cd; }; diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c new file mode 100644 index 000000000000..8273270418b1 --- /dev/null +++ b/fs/nfsd/nfs4layouts.c @@ -0,0 +1,487 @@ +/* + * Copyright (c) 2014 Christoph Hellwig. + */ +#include +#include + +#include "pnfs.h" +#include "netns.h" + +#define NFSDDBG_FACILITY NFSDDBG_PNFS + +struct nfs4_layout { + struct list_head lo_perstate; + struct nfs4_layout_stateid *lo_state; + struct nfsd4_layout_seg lo_seg; +}; + +static struct kmem_cache *nfs4_layout_cache; +static struct kmem_cache *nfs4_layout_stateid_cache; + +const struct nfsd4_layout_ops *nfsd4_layout_ops[LAYOUT_TYPE_MAX] = { +}; + +/* pNFS device ID to export fsid mapping */ +#define DEVID_HASH_BITS 8 +#define DEVID_HASH_SIZE (1 << DEVID_HASH_BITS) +#define DEVID_HASH_MASK (DEVID_HASH_SIZE - 1) +static u64 nfsd_devid_seq = 1; +static struct list_head nfsd_devid_hash[DEVID_HASH_SIZE]; +static DEFINE_SPINLOCK(nfsd_devid_lock); + +static inline u32 devid_hashfn(u64 idx) +{ + return jhash_2words(idx, idx >> 32, 0) & DEVID_HASH_MASK; +} + +static void +nfsd4_alloc_devid_map(const struct svc_fh *fhp) +{ + const struct knfsd_fh *fh = &fhp->fh_handle; + size_t fsid_len = key_len(fh->fh_fsid_type); + struct nfsd4_deviceid_map *map, *old; + int i; + + map = kzalloc(sizeof(*map) + fsid_len, GFP_KERNEL); + if (!map) + return; + + map->fsid_type = fh->fh_fsid_type; + memcpy(&map->fsid, fh->fh_fsid, fsid_len); + + spin_lock(&nfsd_devid_lock); + if (fhp->fh_export->ex_devid_map) + goto out_unlock; + + for (i = 0; i < DEVID_HASH_SIZE; i++) { + list_for_each_entry(old, &nfsd_devid_hash[i], hash) { + if (old->fsid_type != fh->fh_fsid_type) + continue; + if (memcmp(old->fsid, fh->fh_fsid, + key_len(old->fsid_type))) + continue; + + fhp->fh_export->ex_devid_map = old; + goto out_unlock; + } + } + + map->idx = nfsd_devid_seq++; + list_add_tail_rcu(&map->hash, &nfsd_devid_hash[devid_hashfn(map->idx)]); + fhp->fh_export->ex_devid_map = map; + map = NULL; + +out_unlock: + spin_unlock(&nfsd_devid_lock); + kfree(map); +} + +struct nfsd4_deviceid_map * +nfsd4_find_devid_map(int idx) +{ + struct nfsd4_deviceid_map *map, *ret = NULL; + + rcu_read_lock(); + list_for_each_entry_rcu(map, &nfsd_devid_hash[devid_hashfn(idx)], hash) + if (map->idx == idx) + ret = map; + rcu_read_unlock(); + + return ret; +} + +int +nfsd4_set_deviceid(struct nfsd4_deviceid *id, const struct svc_fh *fhp, + u32 device_generation) +{ + if (!fhp->fh_export->ex_devid_map) { + nfsd4_alloc_devid_map(fhp); + if (!fhp->fh_export->ex_devid_map) + return -ENOMEM; + } + + id->fsid_idx = fhp->fh_export->ex_devid_map->idx; + id->generation = device_generation; + id->pad = 0; + return 0; +} + +void nfsd4_setup_layout_type(struct svc_export *exp) +{ + if (exp->ex_flags & NFSEXP_NOPNFS) + return; +} + +static void +nfsd4_free_layout_stateid(struct nfs4_stid *stid) +{ + struct nfs4_layout_stateid *ls = layoutstateid(stid); + struct nfs4_client *clp = ls->ls_stid.sc_client; + struct nfs4_file *fp = ls->ls_stid.sc_file; + + spin_lock(&clp->cl_lock); + list_del_init(&ls->ls_perclnt); + spin_unlock(&clp->cl_lock); + + spin_lock(&fp->fi_lock); + list_del_init(&ls->ls_perfile); + spin_unlock(&fp->fi_lock); + + kmem_cache_free(nfs4_layout_stateid_cache, ls); +} + +static struct nfs4_layout_stateid * +nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate, + struct nfs4_stid *parent, u32 layout_type) +{ + struct nfs4_client *clp = cstate->clp; + struct nfs4_file *fp = parent->sc_file; + struct nfs4_layout_stateid *ls; + struct nfs4_stid *stp; + + stp = nfs4_alloc_stid(cstate->clp, nfs4_layout_stateid_cache); + if (!stp) + return NULL; + stp->sc_free = nfsd4_free_layout_stateid; + get_nfs4_file(fp); + stp->sc_file = fp; + + ls = layoutstateid(stp); + INIT_LIST_HEAD(&ls->ls_perclnt); + INIT_LIST_HEAD(&ls->ls_perfile); + spin_lock_init(&ls->ls_lock); + INIT_LIST_HEAD(&ls->ls_layouts); + ls->ls_layout_type = layout_type; + + spin_lock(&clp->cl_lock); + stp->sc_type = NFS4_LAYOUT_STID; + list_add(&ls->ls_perclnt, &clp->cl_lo_states); + spin_unlock(&clp->cl_lock); + + spin_lock(&fp->fi_lock); + list_add(&ls->ls_perfile, &fp->fi_lo_states); + spin_unlock(&fp->fi_lock); + + return ls; +} + +__be32 +nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, stateid_t *stateid, + bool create, u32 layout_type, struct nfs4_layout_stateid **lsp) +{ + struct nfs4_layout_stateid *ls; + struct nfs4_stid *stid; + unsigned char typemask = NFS4_LAYOUT_STID; + __be32 status; + + if (create) + typemask |= (NFS4_OPEN_STID | NFS4_LOCK_STID | NFS4_DELEG_STID); + + status = nfsd4_lookup_stateid(cstate, stateid, typemask, &stid, + net_generic(SVC_NET(rqstp), nfsd_net_id)); + if (status) + goto out; + + if (!fh_match(&cstate->current_fh.fh_handle, + &stid->sc_file->fi_fhandle)) { + status = nfserr_bad_stateid; + goto out_put_stid; + } + + if (stid->sc_type != NFS4_LAYOUT_STID) { + ls = nfsd4_alloc_layout_stateid(cstate, stid, layout_type); + nfs4_put_stid(stid); + + status = nfserr_jukebox; + if (!ls) + goto out; + } else { + ls = container_of(stid, struct nfs4_layout_stateid, ls_stid); + + status = nfserr_bad_stateid; + if (stateid->si_generation > stid->sc_stateid.si_generation) + goto out_put_stid; + if (layout_type != ls->ls_layout_type) + goto out_put_stid; + } + + *lsp = ls; + return 0; + +out_put_stid: + nfs4_put_stid(stid); +out: + return status; +} + +static inline u64 +layout_end(struct nfsd4_layout_seg *seg) +{ + u64 end = seg->offset + seg->length; + return end >= seg->offset ? end : NFS4_MAX_UINT64; +} + +static void +layout_update_len(struct nfsd4_layout_seg *lo, u64 end) +{ + if (end == NFS4_MAX_UINT64) + lo->length = NFS4_MAX_UINT64; + else + lo->length = end - lo->offset; +} + +static bool +layouts_overlapping(struct nfs4_layout *lo, struct nfsd4_layout_seg *s) +{ + if (s->iomode != IOMODE_ANY && s->iomode != lo->lo_seg.iomode) + return false; + if (layout_end(&lo->lo_seg) <= s->offset) + return false; + if (layout_end(s) <= lo->lo_seg.offset) + return false; + return true; +} + +static bool +layouts_try_merge(struct nfsd4_layout_seg *lo, struct nfsd4_layout_seg *new) +{ + if (lo->iomode != new->iomode) + return false; + if (layout_end(new) < lo->offset) + return false; + if (layout_end(lo) < new->offset) + return false; + + lo->offset = min(lo->offset, new->offset); + layout_update_len(lo, max(layout_end(lo), layout_end(new))); + return true; +} + +__be32 +nfsd4_insert_layout(struct nfsd4_layoutget *lgp, struct nfs4_layout_stateid *ls) +{ + struct nfsd4_layout_seg *seg = &lgp->lg_seg; + struct nfs4_layout *lp, *new = NULL; + + spin_lock(&ls->ls_lock); + list_for_each_entry(lp, &ls->ls_layouts, lo_perstate) { + if (layouts_try_merge(&lp->lo_seg, seg)) + goto done; + } + spin_unlock(&ls->ls_lock); + + new = kmem_cache_alloc(nfs4_layout_cache, GFP_KERNEL); + if (!new) + return nfserr_jukebox; + memcpy(&new->lo_seg, seg, sizeof(lp->lo_seg)); + new->lo_state = ls; + + spin_lock(&ls->ls_lock); + list_for_each_entry(lp, &ls->ls_layouts, lo_perstate) { + if (layouts_try_merge(&lp->lo_seg, seg)) + goto done; + } + + atomic_inc(&ls->ls_stid.sc_count); + list_add_tail(&new->lo_perstate, &ls->ls_layouts); + new = NULL; +done: + update_stateid(&ls->ls_stid.sc_stateid); + memcpy(&lgp->lg_sid, &ls->ls_stid.sc_stateid, sizeof(stateid_t)); + spin_unlock(&ls->ls_lock); + if (new) + kmem_cache_free(nfs4_layout_cache, new); + return nfs_ok; +} + +static void +nfsd4_free_layouts(struct list_head *reaplist) +{ + while (!list_empty(reaplist)) { + struct nfs4_layout *lp = list_first_entry(reaplist, + struct nfs4_layout, lo_perstate); + + list_del(&lp->lo_perstate); + nfs4_put_stid(&lp->lo_state->ls_stid); + kmem_cache_free(nfs4_layout_cache, lp); + } +} + +static void +nfsd4_return_file_layout(struct nfs4_layout *lp, struct nfsd4_layout_seg *seg, + struct list_head *reaplist) +{ + struct nfsd4_layout_seg *lo = &lp->lo_seg; + u64 end = layout_end(lo); + + if (seg->offset <= lo->offset) { + if (layout_end(seg) >= end) { + list_move_tail(&lp->lo_perstate, reaplist); + return; + } + end = seg->offset; + } else { + /* retain the whole layout segment on a split. */ + if (layout_end(seg) < end) { + dprintk("%s: split not supported\n", __func__); + return; + } + + lo->offset = layout_end(seg); + } + + layout_update_len(lo, end); +} + +__be32 +nfsd4_return_file_layouts(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + struct nfsd4_layoutreturn *lrp) +{ + struct nfs4_layout_stateid *ls; + struct nfs4_layout *lp, *n; + LIST_HEAD(reaplist); + __be32 nfserr; + int found = 0; + + nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, &lrp->lr_sid, + false, lrp->lr_layout_type, + &ls); + if (nfserr) + return nfserr; + + spin_lock(&ls->ls_lock); + list_for_each_entry_safe(lp, n, &ls->ls_layouts, lo_perstate) { + if (layouts_overlapping(lp, &lrp->lr_seg)) { + nfsd4_return_file_layout(lp, &lrp->lr_seg, &reaplist); + found++; + } + } + if (!list_empty(&ls->ls_layouts)) { + if (found) { + update_stateid(&ls->ls_stid.sc_stateid); + memcpy(&lrp->lr_sid, &ls->ls_stid.sc_stateid, + sizeof(stateid_t)); + } + lrp->lrs_present = 1; + } else { + nfs4_unhash_stid(&ls->ls_stid); + lrp->lrs_present = 0; + } + spin_unlock(&ls->ls_lock); + + nfs4_put_stid(&ls->ls_stid); + nfsd4_free_layouts(&reaplist); + return nfs_ok; +} + +__be32 +nfsd4_return_client_layouts(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + struct nfsd4_layoutreturn *lrp) +{ + struct nfs4_layout_stateid *ls, *n; + struct nfs4_client *clp = cstate->clp; + struct nfs4_layout *lp, *t; + LIST_HEAD(reaplist); + + lrp->lrs_present = 0; + + spin_lock(&clp->cl_lock); + list_for_each_entry_safe(ls, n, &clp->cl_lo_states, ls_perclnt) { + if (lrp->lr_return_type == RETURN_FSID && + !fh_fsid_match(&ls->ls_stid.sc_file->fi_fhandle, + &cstate->current_fh.fh_handle)) + continue; + + spin_lock(&ls->ls_lock); + list_for_each_entry_safe(lp, t, &ls->ls_layouts, lo_perstate) { + if (lrp->lr_seg.iomode == IOMODE_ANY || + lrp->lr_seg.iomode == lp->lo_seg.iomode) + list_move_tail(&lp->lo_perstate, &reaplist); + } + spin_unlock(&ls->ls_lock); + } + spin_unlock(&clp->cl_lock); + + nfsd4_free_layouts(&reaplist); + return 0; +} + +static void +nfsd4_return_all_layouts(struct nfs4_layout_stateid *ls, + struct list_head *reaplist) +{ + spin_lock(&ls->ls_lock); + list_splice_init(&ls->ls_layouts, reaplist); + spin_unlock(&ls->ls_lock); +} + +void +nfsd4_return_all_client_layouts(struct nfs4_client *clp) +{ + struct nfs4_layout_stateid *ls, *n; + LIST_HEAD(reaplist); + + spin_lock(&clp->cl_lock); + list_for_each_entry_safe(ls, n, &clp->cl_lo_states, ls_perclnt) + nfsd4_return_all_layouts(ls, &reaplist); + spin_unlock(&clp->cl_lock); + + nfsd4_free_layouts(&reaplist); +} + +void +nfsd4_return_all_file_layouts(struct nfs4_client *clp, struct nfs4_file *fp) +{ + struct nfs4_layout_stateid *ls, *n; + LIST_HEAD(reaplist); + + spin_lock(&fp->fi_lock); + list_for_each_entry_safe(ls, n, &fp->fi_lo_states, ls_perfile) { + if (ls->ls_stid.sc_client == clp) + nfsd4_return_all_layouts(ls, &reaplist); + } + spin_unlock(&fp->fi_lock); + + nfsd4_free_layouts(&reaplist); +} + +int +nfsd4_init_pnfs(void) +{ + int i; + + for (i = 0; i < DEVID_HASH_SIZE; i++) + INIT_LIST_HEAD(&nfsd_devid_hash[i]); + + nfs4_layout_cache = kmem_cache_create("nfs4_layout", + sizeof(struct nfs4_layout), 0, 0, NULL); + if (!nfs4_layout_cache) + return -ENOMEM; + + nfs4_layout_stateid_cache = kmem_cache_create("nfs4_layout_stateid", + sizeof(struct nfs4_layout_stateid), 0, 0, NULL); + if (!nfs4_layout_stateid_cache) { + kmem_cache_destroy(nfs4_layout_cache); + return -ENOMEM; + } + return 0; +} + +void +nfsd4_exit_pnfs(void) +{ + int i; + + kmem_cache_destroy(nfs4_layout_cache); + kmem_cache_destroy(nfs4_layout_stateid_cache); + + for (i = 0; i < DEVID_HASH_SIZE; i++) { + struct nfsd4_deviceid_map *map, *n; + + list_for_each_entry_safe(map, n, &nfsd_devid_hash[i], hash) + kfree(map); + } +} diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index ac71d13c69ef..2b91443497cc 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -43,6 +43,7 @@ #include "current_stateid.h" #include "netns.h" #include "acl.h" +#include "pnfs.h" #ifdef CONFIG_NFSD_V4_SECURITY_LABEL #include @@ -1178,6 +1179,252 @@ nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return status == nfserr_same ? nfs_ok : status; } +#ifdef CONFIG_NFSD_PNFS +static const struct nfsd4_layout_ops * +nfsd4_layout_verify(struct svc_export *exp, unsigned int layout_type) +{ + if (!exp->ex_layout_type) { + dprintk("%s: export does not support pNFS\n", __func__); + return NULL; + } + + if (exp->ex_layout_type != layout_type) { + dprintk("%s: layout type %d not supported\n", + __func__, layout_type); + return NULL; + } + + return nfsd4_layout_ops[layout_type]; +} + +static __be32 +nfsd4_getdeviceinfo(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + struct nfsd4_getdeviceinfo *gdp) +{ + const struct nfsd4_layout_ops *ops; + struct nfsd4_deviceid_map *map; + struct svc_export *exp; + __be32 nfserr; + + dprintk("%s: layout_type %u dev_id [0x%llx:0x%x] maxcnt %u\n", + __func__, + gdp->gd_layout_type, + gdp->gd_devid.fsid_idx, gdp->gd_devid.generation, + gdp->gd_maxcount); + + map = nfsd4_find_devid_map(gdp->gd_devid.fsid_idx); + if (!map) { + dprintk("%s: couldn't find device ID to export mapping!\n", + __func__); + return nfserr_noent; + } + + exp = rqst_exp_find(rqstp, map->fsid_type, map->fsid); + if (IS_ERR(exp)) { + dprintk("%s: could not find device id\n", __func__); + return nfserr_noent; + } + + nfserr = nfserr_layoutunavailable; + ops = nfsd4_layout_verify(exp, gdp->gd_layout_type); + if (!ops) + goto out; + + nfserr = nfs_ok; + if (gdp->gd_maxcount != 0) + nfserr = ops->proc_getdeviceinfo(exp->ex_path.mnt->mnt_sb, gdp); + + gdp->gd_notify_types &= ops->notify_types; + exp_put(exp); +out: + return nfserr; +} + +static __be32 +nfsd4_layoutget(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + struct nfsd4_layoutget *lgp) +{ + struct svc_fh *current_fh = &cstate->current_fh; + const struct nfsd4_layout_ops *ops; + struct nfs4_layout_stateid *ls; + __be32 nfserr; + int accmode; + + switch (lgp->lg_seg.iomode) { + case IOMODE_READ: + accmode = NFSD_MAY_READ; + break; + case IOMODE_RW: + accmode = NFSD_MAY_READ | NFSD_MAY_WRITE; + break; + default: + dprintk("%s: invalid iomode %d\n", + __func__, lgp->lg_seg.iomode); + nfserr = nfserr_badiomode; + goto out; + } + + nfserr = fh_verify(rqstp, current_fh, 0, accmode); + if (nfserr) + goto out; + + nfserr = nfserr_layoutunavailable; + ops = nfsd4_layout_verify(current_fh->fh_export, lgp->lg_layout_type); + if (!ops) + goto out; + + /* + * Verify minlength and range as per RFC5661: + * o If loga_length is less than loga_minlength, + * the metadata server MUST return NFS4ERR_INVAL. + * o If the sum of loga_offset and loga_minlength exceeds + * NFS4_UINT64_MAX, and loga_minlength is not + * NFS4_UINT64_MAX, the error NFS4ERR_INVAL MUST result. + * o If the sum of loga_offset and loga_length exceeds + * NFS4_UINT64_MAX, and loga_length is not NFS4_UINT64_MAX, + * the error NFS4ERR_INVAL MUST result. + */ + nfserr = nfserr_inval; + if (lgp->lg_seg.length < lgp->lg_minlength || + (lgp->lg_minlength != NFS4_MAX_UINT64 && + lgp->lg_minlength > NFS4_MAX_UINT64 - lgp->lg_seg.offset) || + (lgp->lg_seg.length != NFS4_MAX_UINT64 && + lgp->lg_seg.length > NFS4_MAX_UINT64 - lgp->lg_seg.offset)) + goto out; + if (lgp->lg_seg.length == 0) + goto out; + + nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, &lgp->lg_sid, + true, lgp->lg_layout_type, &ls); + if (nfserr) + goto out; + + nfserr = ops->proc_layoutget(current_fh->fh_dentry->d_inode, + current_fh, lgp); + if (nfserr) + goto out_put_stid; + + nfserr = nfsd4_insert_layout(lgp, ls); + +out_put_stid: + nfs4_put_stid(&ls->ls_stid); +out: + return nfserr; +} + +static __be32 +nfsd4_layoutcommit(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + struct nfsd4_layoutcommit *lcp) +{ + const struct nfsd4_layout_seg *seg = &lcp->lc_seg; + struct svc_fh *current_fh = &cstate->current_fh; + const struct nfsd4_layout_ops *ops; + loff_t new_size = lcp->lc_last_wr + 1; + struct inode *inode; + struct nfs4_layout_stateid *ls; + __be32 nfserr; + + nfserr = fh_verify(rqstp, current_fh, 0, NFSD_MAY_WRITE); + if (nfserr) + goto out; + + nfserr = nfserr_layoutunavailable; + ops = nfsd4_layout_verify(current_fh->fh_export, lcp->lc_layout_type); + if (!ops) + goto out; + inode = current_fh->fh_dentry->d_inode; + + nfserr = nfserr_inval; + if (new_size <= seg->offset) { + dprintk("pnfsd: last write before layout segment\n"); + goto out; + } + if (new_size > seg->offset + seg->length) { + dprintk("pnfsd: last write beyond layout segment\n"); + goto out; + } + if (!lcp->lc_newoffset && new_size > i_size_read(inode)) { + dprintk("pnfsd: layoutcommit beyond EOF\n"); + goto out; + } + + nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, &lcp->lc_sid, + false, lcp->lc_layout_type, + &ls); + if (nfserr) { + /* fixup error code as per RFC5661 */ + if (nfserr == nfserr_bad_stateid) + nfserr = nfserr_badlayout; + goto out; + } + + nfserr = ops->proc_layoutcommit(inode, lcp); + if (nfserr) + goto out_put_stid; + + if (new_size > i_size_read(inode)) { + lcp->lc_size_chg = 1; + lcp->lc_newsize = new_size; + } else { + lcp->lc_size_chg = 0; + } + +out_put_stid: + nfs4_put_stid(&ls->ls_stid); +out: + return nfserr; +} + +static __be32 +nfsd4_layoutreturn(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + struct nfsd4_layoutreturn *lrp) +{ + struct svc_fh *current_fh = &cstate->current_fh; + __be32 nfserr; + + nfserr = fh_verify(rqstp, current_fh, 0, NFSD_MAY_NOP); + if (nfserr) + goto out; + + nfserr = nfserr_layoutunavailable; + if (!nfsd4_layout_verify(current_fh->fh_export, lrp->lr_layout_type)) + goto out; + + switch (lrp->lr_seg.iomode) { + case IOMODE_READ: + case IOMODE_RW: + case IOMODE_ANY: + break; + default: + dprintk("%s: invalid iomode %d\n", __func__, + lrp->lr_seg.iomode); + nfserr = nfserr_inval; + goto out; + } + + switch (lrp->lr_return_type) { + case RETURN_FILE: + nfserr = nfsd4_return_file_layouts(rqstp, cstate, lrp); + break; + case RETURN_FSID: + case RETURN_ALL: + nfserr = nfsd4_return_client_layouts(rqstp, cstate, lrp); + break; + default: + dprintk("%s: invalid return_type %d\n", __func__, + lrp->lr_return_type); + nfserr = nfserr_inval; + break; + } +out: + return nfserr; +} +#endif /* CONFIG_NFSD_PNFS */ + /* * NULL call. */ @@ -1679,6 +1926,36 @@ static inline u32 nfsd4_create_session_rsize(struct svc_rqst *rqstp, struct nfsd op_encode_channel_attrs_maxsz) * sizeof(__be32); } +#ifdef CONFIG_NFSD_PNFS +/* + * At this stage we don't really know what layout driver will handle the request, + * so we need to define an arbitrary upper bound here. + */ +#define MAX_LAYOUT_SIZE 128 +static inline u32 nfsd4_layoutget_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +{ + return (op_encode_hdr_size + + 1 /* logr_return_on_close */ + + op_encode_stateid_maxsz + + 1 /* nr of layouts */ + + MAX_LAYOUT_SIZE) * sizeof(__be32); +} + +static inline u32 nfsd4_layoutcommit_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +{ + return (op_encode_hdr_size + + 1 /* locr_newsize */ + + 2 /* ns_size */) * sizeof(__be32); +} + +static inline u32 nfsd4_layoutreturn_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +{ + return (op_encode_hdr_size + + 1 /* lrs_stateid */ + + op_encode_stateid_maxsz) * sizeof(__be32); +} +#endif /* CONFIG_NFSD_PNFS */ + static struct nfsd4_operation nfsd4_ops[] = { [OP_ACCESS] = { .op_func = (nfsd4op_func)nfsd4_access, @@ -1966,6 +2243,31 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_get_currentstateid = (stateid_getter)nfsd4_get_freestateid, .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, }, +#ifdef CONFIG_NFSD_PNFS + [OP_GETDEVICEINFO] = { + .op_func = (nfsd4op_func)nfsd4_getdeviceinfo, + .op_flags = ALLOWED_WITHOUT_FH, + .op_name = "OP_GETDEVICEINFO", + }, + [OP_LAYOUTGET] = { + .op_func = (nfsd4op_func)nfsd4_layoutget, + .op_flags = OP_MODIFIES_SOMETHING, + .op_name = "OP_LAYOUTGET", + .op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutget_rsize, + }, + [OP_LAYOUTCOMMIT] = { + .op_func = (nfsd4op_func)nfsd4_layoutcommit, + .op_flags = OP_MODIFIES_SOMETHING, + .op_name = "OP_LAYOUTCOMMIT", + .op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutcommit_rsize, + }, + [OP_LAYOUTRETURN] = { + .op_func = (nfsd4op_func)nfsd4_layoutreturn, + .op_flags = OP_MODIFIES_SOMETHING, + .op_name = "OP_LAYOUTRETURN", + .op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutreturn_rsize, + }, +#endif /* CONFIG_NFSD_PNFS */ /* NFSv4.2 operations */ [OP_ALLOCATE] = { diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index eefd29ec43f2..c89f79dc69e2 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -48,6 +48,7 @@ #include "current_stateid.h" #include "netns.h" +#include "pnfs.h" #define NFSDDBG_FACILITY NFSDDBG_PROC @@ -1539,6 +1540,9 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name) INIT_LIST_HEAD(&clp->cl_lru); INIT_LIST_HEAD(&clp->cl_callbacks); INIT_LIST_HEAD(&clp->cl_revoked); +#ifdef CONFIG_NFSD_PNFS + INIT_LIST_HEAD(&clp->cl_lo_states); +#endif spin_lock_init(&clp->cl_lock); rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table"); return clp; @@ -1643,6 +1647,7 @@ __destroy_client(struct nfs4_client *clp) nfs4_get_stateowner(&oo->oo_owner); release_openowner(oo); } + nfsd4_return_all_client_layouts(clp); nfsd4_shutdown_callback(clp); if (clp->cl_cb_conn.cb_xprt) svc_xprt_put(clp->cl_cb_conn.cb_xprt); @@ -2126,8 +2131,11 @@ nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp, static void nfsd4_set_ex_flags(struct nfs4_client *new, struct nfsd4_exchange_id *clid) { - /* pNFS is not supported */ +#ifdef CONFIG_NFSD_PNFS + new->cl_exchange_flags |= EXCHGID4_FLAG_USE_PNFS_MDS; +#else new->cl_exchange_flags |= EXCHGID4_FLAG_USE_NON_PNFS; +#endif /* Referrals are supported, Migration is not. */ new->cl_exchange_flags |= EXCHGID4_FLAG_SUPP_MOVED_REFER; @@ -3055,6 +3063,9 @@ static void nfsd4_init_file(struct knfsd_fh *fh, unsigned int hashval, fp->fi_share_deny = 0; memset(fp->fi_fds, 0, sizeof(fp->fi_fds)); memset(fp->fi_access, 0, sizeof(fp->fi_access)); +#ifdef CONFIG_NFSD_PNFS + INIT_LIST_HEAD(&fp->fi_lo_states); +#endif hlist_add_head_rcu(&fp->fi_hash, &file_hashtbl[hashval]); } @@ -4841,6 +4852,9 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, update_stateid(&stp->st_stid.sc_stateid); memcpy(&close->cl_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t)); + nfsd4_return_all_file_layouts(stp->st_stateowner->so_client, + stp->st_stid.sc_file); + nfsd4_close_open_stateid(stp); /* put reference from nfs4_preprocess_seqid_op */ diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 974533e5a427..df5e66caf100 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -47,6 +47,7 @@ #include "state.h" #include "cache.h" #include "netns.h" +#include "pnfs.h" #ifdef CONFIG_NFSD_V4_SECURITY_LABEL #include @@ -1522,6 +1523,127 @@ static __be32 nfsd4_decode_reclaim_complete(struct nfsd4_compoundargs *argp, str DECODE_TAIL; } +#ifdef CONFIG_NFSD_PNFS +static __be32 +nfsd4_decode_getdeviceinfo(struct nfsd4_compoundargs *argp, + struct nfsd4_getdeviceinfo *gdev) +{ + DECODE_HEAD; + u32 num, i; + + READ_BUF(sizeof(struct nfsd4_deviceid) + 3 * 4); + COPYMEM(&gdev->gd_devid, sizeof(struct nfsd4_deviceid)); + gdev->gd_layout_type = be32_to_cpup(p++); + gdev->gd_maxcount = be32_to_cpup(p++); + num = be32_to_cpup(p++); + if (num) { + READ_BUF(4 * num); + gdev->gd_notify_types = be32_to_cpup(p++); + for (i = 1; i < num; i++) { + if (be32_to_cpup(p++)) { + status = nfserr_inval; + goto out; + } + } + } + DECODE_TAIL; +} + +static __be32 +nfsd4_decode_layoutget(struct nfsd4_compoundargs *argp, + struct nfsd4_layoutget *lgp) +{ + DECODE_HEAD; + + READ_BUF(36); + lgp->lg_signal = be32_to_cpup(p++); + lgp->lg_layout_type = be32_to_cpup(p++); + lgp->lg_seg.iomode = be32_to_cpup(p++); + p = xdr_decode_hyper(p, &lgp->lg_seg.offset); + p = xdr_decode_hyper(p, &lgp->lg_seg.length); + p = xdr_decode_hyper(p, &lgp->lg_minlength); + nfsd4_decode_stateid(argp, &lgp->lg_sid); + READ_BUF(4); + lgp->lg_maxcount = be32_to_cpup(p++); + + DECODE_TAIL; +} + +static __be32 +nfsd4_decode_layoutcommit(struct nfsd4_compoundargs *argp, + struct nfsd4_layoutcommit *lcp) +{ + DECODE_HEAD; + u32 timechange; + + READ_BUF(20); + p = xdr_decode_hyper(p, &lcp->lc_seg.offset); + p = xdr_decode_hyper(p, &lcp->lc_seg.length); + lcp->lc_reclaim = be32_to_cpup(p++); + nfsd4_decode_stateid(argp, &lcp->lc_sid); + READ_BUF(4); + lcp->lc_newoffset = be32_to_cpup(p++); + if (lcp->lc_newoffset) { + READ_BUF(8); + p = xdr_decode_hyper(p, &lcp->lc_last_wr); + } else + lcp->lc_last_wr = 0; + READ_BUF(4); + timechange = be32_to_cpup(p++); + if (timechange) { + status = nfsd4_decode_time(argp, &lcp->lc_mtime); + if (status) + return status; + } else { + lcp->lc_mtime.tv_nsec = UTIME_NOW; + } + READ_BUF(8); + lcp->lc_layout_type = be32_to_cpup(p++); + + /* + * Save the layout update in XDR format and let the layout driver deal + * with it later. + */ + lcp->lc_up_len = be32_to_cpup(p++); + if (lcp->lc_up_len > 0) { + READ_BUF(lcp->lc_up_len); + READMEM(lcp->lc_up_layout, lcp->lc_up_len); + } + + DECODE_TAIL; +} + +static __be32 +nfsd4_decode_layoutreturn(struct nfsd4_compoundargs *argp, + struct nfsd4_layoutreturn *lrp) +{ + DECODE_HEAD; + + READ_BUF(16); + lrp->lr_reclaim = be32_to_cpup(p++); + lrp->lr_layout_type = be32_to_cpup(p++); + lrp->lr_seg.iomode = be32_to_cpup(p++); + lrp->lr_return_type = be32_to_cpup(p++); + if (lrp->lr_return_type == RETURN_FILE) { + READ_BUF(16); + p = xdr_decode_hyper(p, &lrp->lr_seg.offset); + p = xdr_decode_hyper(p, &lrp->lr_seg.length); + nfsd4_decode_stateid(argp, &lrp->lr_sid); + READ_BUF(4); + lrp->lrf_body_len = be32_to_cpup(p++); + if (lrp->lrf_body_len > 0) { + READ_BUF(lrp->lrf_body_len); + READMEM(lrp->lrf_body, lrp->lrf_body_len); + } + } else { + lrp->lr_seg.offset = 0; + lrp->lr_seg.length = NFS4_MAX_UINT64; + } + + DECODE_TAIL; +} +#endif /* CONFIG_NFSD_PNFS */ + static __be32 nfsd4_decode_fallocate(struct nfsd4_compoundargs *argp, struct nfsd4_fallocate *fallocate) @@ -1616,11 +1738,19 @@ static nfsd4_dec nfsd4_dec_ops[] = { [OP_DESTROY_SESSION] = (nfsd4_dec)nfsd4_decode_destroy_session, [OP_FREE_STATEID] = (nfsd4_dec)nfsd4_decode_free_stateid, [OP_GET_DIR_DELEGATION] = (nfsd4_dec)nfsd4_decode_notsupp, +#ifdef CONFIG_NFSD_PNFS + [OP_GETDEVICEINFO] = (nfsd4_dec)nfsd4_decode_getdeviceinfo, + [OP_GETDEVICELIST] = (nfsd4_dec)nfsd4_decode_notsupp, + [OP_LAYOUTCOMMIT] = (nfsd4_dec)nfsd4_decode_layoutcommit, + [OP_LAYOUTGET] = (nfsd4_dec)nfsd4_decode_layoutget, + [OP_LAYOUTRETURN] = (nfsd4_dec)nfsd4_decode_layoutreturn, +#else [OP_GETDEVICEINFO] = (nfsd4_dec)nfsd4_decode_notsupp, [OP_GETDEVICELIST] = (nfsd4_dec)nfsd4_decode_notsupp, [OP_LAYOUTCOMMIT] = (nfsd4_dec)nfsd4_decode_notsupp, [OP_LAYOUTGET] = (nfsd4_dec)nfsd4_decode_notsupp, [OP_LAYOUTRETURN] = (nfsd4_dec)nfsd4_decode_notsupp, +#endif [OP_SECINFO_NO_NAME] = (nfsd4_dec)nfsd4_decode_secinfo_no_name, [OP_SEQUENCE] = (nfsd4_dec)nfsd4_decode_sequence, [OP_SET_SSV] = (nfsd4_dec)nfsd4_decode_notsupp, @@ -2548,6 +2678,30 @@ out_acl: get_parent_attributes(exp, &stat); p = xdr_encode_hyper(p, stat.ino); } +#ifdef CONFIG_NFSD_PNFS + if ((bmval1 & FATTR4_WORD1_FS_LAYOUT_TYPES) || + (bmval2 & FATTR4_WORD2_LAYOUT_TYPES)) { + if (exp->ex_layout_type) { + p = xdr_reserve_space(xdr, 8); + if (!p) + goto out_resource; + *p++ = cpu_to_be32(1); + *p++ = cpu_to_be32(exp->ex_layout_type); + } else { + p = xdr_reserve_space(xdr, 4); + if (!p) + goto out_resource; + *p++ = cpu_to_be32(0); + } + } + + if (bmval2 & FATTR4_WORD2_LAYOUT_BLKSIZE) { + p = xdr_reserve_space(xdr, 4); + if (!p) + goto out_resource; + *p++ = cpu_to_be32(stat.blksize); + } +#endif /* CONFIG_NFSD_PNFS */ if (bmval2 & FATTR4_WORD2_SECURITY_LABEL) { status = nfsd4_encode_security_label(xdr, rqstp, context, contextlen); @@ -3824,6 +3978,156 @@ nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, __be32 nfserr, return nfserr; } +#ifdef CONFIG_NFSD_PNFS +static __be32 +nfsd4_encode_getdeviceinfo(struct nfsd4_compoundres *resp, __be32 nfserr, + struct nfsd4_getdeviceinfo *gdev) +{ + struct xdr_stream *xdr = &resp->xdr; + const struct nfsd4_layout_ops *ops = + nfsd4_layout_ops[gdev->gd_layout_type]; + u32 starting_len = xdr->buf->len, needed_len; + __be32 *p; + + dprintk("%s: err %d\n", __func__, nfserr); + if (nfserr) + goto out; + + nfserr = nfserr_resource; + p = xdr_reserve_space(xdr, 4); + if (!p) + goto out; + + *p++ = cpu_to_be32(gdev->gd_layout_type); + + /* If maxcount is 0 then just update notifications */ + if (gdev->gd_maxcount != 0) { + nfserr = ops->encode_getdeviceinfo(xdr, gdev); + if (nfserr) { + /* + * We don't bother to burden the layout drivers with + * enforcing gd_maxcount, just tell the client to + * come back with a bigger buffer if it's not enough. + */ + if (xdr->buf->len + 4 > gdev->gd_maxcount) + goto toosmall; + goto out; + } + } + + nfserr = nfserr_resource; + if (gdev->gd_notify_types) { + p = xdr_reserve_space(xdr, 4 + 4); + if (!p) + goto out; + *p++ = cpu_to_be32(1); /* bitmap length */ + *p++ = cpu_to_be32(gdev->gd_notify_types); + } else { + p = xdr_reserve_space(xdr, 4); + if (!p) + goto out; + *p++ = 0; + } + + nfserr = 0; +out: + kfree(gdev->gd_device); + dprintk("%s: done: %d\n", __func__, be32_to_cpu(nfserr)); + return nfserr; + +toosmall: + dprintk("%s: maxcount too small\n", __func__); + needed_len = xdr->buf->len + 4 /* notifications */; + xdr_truncate_encode(xdr, starting_len); + p = xdr_reserve_space(xdr, 4); + if (!p) { + nfserr = nfserr_resource; + } else { + *p++ = cpu_to_be32(needed_len); + nfserr = nfserr_toosmall; + } + goto out; +} + +static __be32 +nfsd4_encode_layoutget(struct nfsd4_compoundres *resp, __be32 nfserr, + struct nfsd4_layoutget *lgp) +{ + struct xdr_stream *xdr = &resp->xdr; + const struct nfsd4_layout_ops *ops = + nfsd4_layout_ops[lgp->lg_layout_type]; + __be32 *p; + + dprintk("%s: err %d\n", __func__, nfserr); + if (nfserr) + goto out; + + nfserr = nfserr_resource; + p = xdr_reserve_space(xdr, 36 + sizeof(stateid_opaque_t)); + if (!p) + goto out; + + *p++ = cpu_to_be32(1); /* we always set return-on-close */ + *p++ = cpu_to_be32(lgp->lg_sid.si_generation); + p = xdr_encode_opaque_fixed(p, &lgp->lg_sid.si_opaque, + sizeof(stateid_opaque_t)); + + *p++ = cpu_to_be32(1); /* we always return a single layout */ + p = xdr_encode_hyper(p, lgp->lg_seg.offset); + p = xdr_encode_hyper(p, lgp->lg_seg.length); + *p++ = cpu_to_be32(lgp->lg_seg.iomode); + *p++ = cpu_to_be32(lgp->lg_layout_type); + + nfserr = ops->encode_layoutget(xdr, lgp); +out: + kfree(lgp->lg_content); + return nfserr; +} + +static __be32 +nfsd4_encode_layoutcommit(struct nfsd4_compoundres *resp, __be32 nfserr, + struct nfsd4_layoutcommit *lcp) +{ + struct xdr_stream *xdr = &resp->xdr; + __be32 *p; + + if (nfserr) + return nfserr; + + p = xdr_reserve_space(xdr, 4); + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(lcp->lc_size_chg); + if (lcp->lc_size_chg) { + p = xdr_reserve_space(xdr, 8); + if (!p) + return nfserr_resource; + p = xdr_encode_hyper(p, lcp->lc_newsize); + } + + return nfs_ok; +} + +static __be32 +nfsd4_encode_layoutreturn(struct nfsd4_compoundres *resp, __be32 nfserr, + struct nfsd4_layoutreturn *lrp) +{ + struct xdr_stream *xdr = &resp->xdr; + __be32 *p; + + if (nfserr) + return nfserr; + + p = xdr_reserve_space(xdr, 4); + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(lrp->lrs_present); + if (lrp->lrs_present) + nfsd4_encode_stateid(xdr, &lrp->lr_sid); + return nfs_ok; +} +#endif /* CONFIG_NFSD_PNFS */ + static __be32 nfsd4_encode_seek(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_seek *seek) @@ -3900,11 +4204,19 @@ static nfsd4_enc nfsd4_enc_ops[] = { [OP_DESTROY_SESSION] = (nfsd4_enc)nfsd4_encode_noop, [OP_FREE_STATEID] = (nfsd4_enc)nfsd4_encode_noop, [OP_GET_DIR_DELEGATION] = (nfsd4_enc)nfsd4_encode_noop, +#ifdef CONFIG_NFSD_PNFS + [OP_GETDEVICEINFO] = (nfsd4_enc)nfsd4_encode_getdeviceinfo, + [OP_GETDEVICELIST] = (nfsd4_enc)nfsd4_encode_noop, + [OP_LAYOUTCOMMIT] = (nfsd4_enc)nfsd4_encode_layoutcommit, + [OP_LAYOUTGET] = (nfsd4_enc)nfsd4_encode_layoutget, + [OP_LAYOUTRETURN] = (nfsd4_enc)nfsd4_encode_layoutreturn, +#else [OP_GETDEVICEINFO] = (nfsd4_enc)nfsd4_encode_noop, [OP_GETDEVICELIST] = (nfsd4_enc)nfsd4_encode_noop, [OP_LAYOUTCOMMIT] = (nfsd4_enc)nfsd4_encode_noop, [OP_LAYOUTGET] = (nfsd4_enc)nfsd4_encode_noop, [OP_LAYOUTRETURN] = (nfsd4_enc)nfsd4_encode_noop, +#endif [OP_SECINFO_NO_NAME] = (nfsd4_enc)nfsd4_encode_secinfo_no_name, [OP_SEQUENCE] = (nfsd4_enc)nfsd4_encode_sequence, [OP_SET_SSV] = (nfsd4_enc)nfsd4_encode_noop, diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 19ace74d35f6..aa47d75ddb26 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -21,6 +21,7 @@ #include "cache.h" #include "state.h" #include "netns.h" +#include "pnfs.h" /* * We have a single directory with several nodes in it. @@ -1258,9 +1259,12 @@ static int __init init_nfsd(void) retval = nfsd4_init_slabs(); if (retval) goto out_unregister_pernet; - retval = nfsd_fault_inject_init(); /* nfsd fault injection controls */ + retval = nfsd4_init_pnfs(); if (retval) goto out_free_slabs; + retval = nfsd_fault_inject_init(); /* nfsd fault injection controls */ + if (retval) + goto out_exit_pnfs; nfsd_stat_init(); /* Statistics */ retval = nfsd_reply_cache_init(); if (retval) @@ -1282,6 +1286,8 @@ out_free_lockd: out_free_stat: nfsd_stat_shutdown(); nfsd_fault_inject_cleanup(); +out_exit_pnfs: + nfsd4_exit_pnfs(); out_free_slabs: nfsd4_free_slabs(); out_unregister_pernet: @@ -1299,6 +1305,7 @@ static void __exit exit_nfsd(void) nfsd_stat_shutdown(); nfsd_lockd_shutdown(); nfsd4_free_slabs(); + nfsd4_exit_pnfs(); nfsd_fault_inject_cleanup(); unregister_filesystem(&nfsd_fs_type); unregister_pernet_subsys(&nfsd_net_ops); diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 33a46a8dfaf7..565c4da1a9eb 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -325,15 +325,27 @@ void nfsd_lockd_shutdown(void); #define NFSD4_SUPPORTED_ATTRS_WORD2 0 +/* 4.1 */ +#ifdef CONFIG_NFSD_PNFS +#define PNFSD_SUPPORTED_ATTRS_WORD1 FATTR4_WORD1_FS_LAYOUT_TYPES +#define PNFSD_SUPPORTED_ATTRS_WORD2 \ +(FATTR4_WORD2_LAYOUT_BLKSIZE | FATTR4_WORD2_LAYOUT_TYPES) +#else +#define PNFSD_SUPPORTED_ATTRS_WORD1 0 +#define PNFSD_SUPPORTED_ATTRS_WORD2 0 +#endif /* CONFIG_NFSD_PNFS */ + #define NFSD4_1_SUPPORTED_ATTRS_WORD0 \ NFSD4_SUPPORTED_ATTRS_WORD0 #define NFSD4_1_SUPPORTED_ATTRS_WORD1 \ - NFSD4_SUPPORTED_ATTRS_WORD1 + (NFSD4_SUPPORTED_ATTRS_WORD1 | PNFSD_SUPPORTED_ATTRS_WORD1) #define NFSD4_1_SUPPORTED_ATTRS_WORD2 \ - (NFSD4_SUPPORTED_ATTRS_WORD2 | FATTR4_WORD2_SUPPATTR_EXCLCREAT) + (NFSD4_SUPPORTED_ATTRS_WORD2 | PNFSD_SUPPORTED_ATTRS_WORD2 | \ + FATTR4_WORD2_SUPPATTR_EXCLCREAT) +/* 4.2 */ #ifdef CONFIG_NFSD_V4_SECURITY_LABEL #define NFSD4_2_SECURITY_ATTRS FATTR4_WORD2_SECURITY_LABEL #else diff --git a/fs/nfsd/pnfs.h b/fs/nfsd/pnfs.h new file mode 100644 index 000000000000..a9616a4e13cd --- /dev/null +++ b/fs/nfsd/pnfs.h @@ -0,0 +1,80 @@ +#ifndef _FS_NFSD_PNFS_H +#define _FS_NFSD_PNFS_H 1 + +#include +#include + +#include "state.h" +#include "xdr4.h" + +struct xdr_stream; + +struct nfsd4_deviceid_map { + struct list_head hash; + u64 idx; + int fsid_type; + u32 fsid[]; +}; + +struct nfsd4_layout_ops { + u32 notify_types; + + __be32 (*proc_getdeviceinfo)(struct super_block *sb, + struct nfsd4_getdeviceinfo *gdevp); + __be32 (*encode_getdeviceinfo)(struct xdr_stream *xdr, + struct nfsd4_getdeviceinfo *gdevp); + + __be32 (*proc_layoutget)(struct inode *, const struct svc_fh *fhp, + struct nfsd4_layoutget *lgp); + __be32 (*encode_layoutget)(struct xdr_stream *, + struct nfsd4_layoutget *lgp); + + __be32 (*proc_layoutcommit)(struct inode *inode, + struct nfsd4_layoutcommit *lcp); +}; + +extern const struct nfsd4_layout_ops *nfsd4_layout_ops[]; + +__be32 nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, stateid_t *stateid, + bool create, u32 layout_type, struct nfs4_layout_stateid **lsp); +__be32 nfsd4_insert_layout(struct nfsd4_layoutget *lgp, + struct nfs4_layout_stateid *ls); +__be32 nfsd4_return_file_layouts(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + struct nfsd4_layoutreturn *lrp); +__be32 nfsd4_return_client_layouts(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + struct nfsd4_layoutreturn *lrp); +int nfsd4_set_deviceid(struct nfsd4_deviceid *id, const struct svc_fh *fhp, + u32 device_generation); +struct nfsd4_deviceid_map *nfsd4_find_devid_map(int idx); + +#ifdef CONFIG_NFSD_PNFS +void nfsd4_setup_layout_type(struct svc_export *exp); +void nfsd4_return_all_client_layouts(struct nfs4_client *); +void nfsd4_return_all_file_layouts(struct nfs4_client *clp, + struct nfs4_file *fp); +int nfsd4_init_pnfs(void); +void nfsd4_exit_pnfs(void); +#else +static inline void nfsd4_setup_layout_type(struct svc_export *exp) +{ +} + +static inline void nfsd4_return_all_client_layouts(struct nfs4_client *clp) +{ +} +static inline void nfsd4_return_all_file_layouts(struct nfs4_client *clp, + struct nfs4_file *fp) +{ +} +static inline void nfsd4_exit_pnfs(void) +{ +} +static inline int nfsd4_init_pnfs(void) +{ + return 0; +} +#endif /* CONFIG_NFSD_PNFS */ +#endif /* _FS_NFSD_PNFS_H */ diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 38ebb1268b59..5f66b7fd0297 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -92,6 +92,7 @@ struct nfs4_stid { /* For a deleg stateid kept around only to process free_stateid's: */ #define NFS4_REVOKED_DELEG_STID 16 #define NFS4_CLOSED_DELEG_STID 32 +#define NFS4_LAYOUT_STID 64 unsigned char sc_type; stateid_t sc_stateid; struct nfs4_client *sc_client; @@ -297,6 +298,9 @@ struct nfs4_client { struct list_head cl_delegations; struct list_head cl_revoked; /* unacknowledged, revoked 4.1 state */ struct list_head cl_lru; /* tail queue */ +#ifdef CONFIG_NFSD_PNFS + struct list_head cl_lo_states; /* outstanding layout states */ +#endif struct xdr_netobj cl_name; /* id generated by client */ nfs4_verifier cl_verifier; /* generated by client */ time_t cl_time; /* time of last lease renewal */ @@ -496,6 +500,9 @@ struct nfs4_file { int fi_delegees; struct knfsd_fh fi_fhandle; bool fi_had_conflict; +#ifdef CONFIG_NFSD_PNFS + struct list_head fi_lo_states; +#endif }; /* @@ -528,6 +535,20 @@ static inline struct nfs4_ol_stateid *openlockstateid(struct nfs4_stid *s) return container_of(s, struct nfs4_ol_stateid, st_stid); } +struct nfs4_layout_stateid { + struct nfs4_stid ls_stid; + struct list_head ls_perclnt; + struct list_head ls_perfile; + spinlock_t ls_lock; + struct list_head ls_layouts; + u32 ls_layout_type; +}; + +static inline struct nfs4_layout_stateid *layoutstateid(struct nfs4_stid *s) +{ + return container_of(s, struct nfs4_layout_stateid, ls_stid); +} + /* flags for preprocess_seqid_op() */ #define RD_STATE 0x00000010 #define WR_STATE 0x00000020 diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 90a5925bd6ab..0bda93e58e1b 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -428,6 +428,61 @@ struct nfsd4_reclaim_complete { u32 rca_one_fs; }; +struct nfsd4_deviceid { + u64 fsid_idx; + u32 generation; + u32 pad; +}; + +struct nfsd4_layout_seg { + u32 iomode; + u64 offset; + u64 length; +}; + +struct nfsd4_getdeviceinfo { + struct nfsd4_deviceid gd_devid; /* request */ + u32 gd_layout_type; /* request */ + u32 gd_maxcount; /* request */ + u32 gd_notify_types;/* request - response */ + void *gd_device; /* response */ +}; + +struct nfsd4_layoutget { + u64 lg_minlength; /* request */ + u32 lg_signal; /* request */ + u32 lg_layout_type; /* request */ + u32 lg_maxcount; /* request */ + stateid_t lg_sid; /* request/response */ + struct nfsd4_layout_seg lg_seg; /* request/response */ + void *lg_content; /* response */ +}; + +struct nfsd4_layoutcommit { + stateid_t lc_sid; /* request */ + struct nfsd4_layout_seg lc_seg; /* request */ + u32 lc_reclaim; /* request */ + u32 lc_newoffset; /* request */ + u64 lc_last_wr; /* request */ + struct timespec lc_mtime; /* request */ + u32 lc_layout_type; /* request */ + u32 lc_up_len; /* layout length */ + void *lc_up_layout; /* decoded by callback */ + u32 lc_size_chg; /* boolean for response */ + u64 lc_newsize; /* response */ +}; + +struct nfsd4_layoutreturn { + u32 lr_return_type; /* request */ + u32 lr_layout_type; /* request */ + struct nfsd4_layout_seg lr_seg; /* request */ + u32 lr_reclaim; /* request */ + u32 lrf_body_len; /* request */ + void *lrf_body; /* request */ + stateid_t lr_sid; /* request/response */ + u32 lrs_present; /* response */ +}; + struct nfsd4_fallocate { /* request */ stateid_t falloc_stateid; @@ -491,6 +546,10 @@ struct nfsd4_op { struct nfsd4_reclaim_complete reclaim_complete; struct nfsd4_test_stateid test_stateid; struct nfsd4_free_stateid free_stateid; + struct nfsd4_getdeviceinfo getdeviceinfo; + struct nfsd4_layoutget layoutget; + struct nfsd4_layoutcommit layoutcommit; + struct nfsd4_layoutreturn layoutreturn; /* NFSv4.2 */ struct nfsd4_fallocate allocate; diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 8a3589c2542c..bc10d687f2ce 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -411,6 +411,7 @@ enum lock_type4 { #define FATTR4_WORD1_TIME_MODIFY_SET (1UL << 22) #define FATTR4_WORD1_MOUNTED_ON_FILEID (1UL << 23) #define FATTR4_WORD1_FS_LAYOUT_TYPES (1UL << 30) +#define FATTR4_WORD2_LAYOUT_TYPES (1UL << 0) #define FATTR4_WORD2_LAYOUT_BLKSIZE (1UL << 1) #define FATTR4_WORD2_MDSTHRESHOLD (1UL << 4) #define FATTR4_WORD2_SECURITY_LABEL (1UL << 16) diff --git a/include/uapi/linux/nfsd/debug.h b/include/uapi/linux/nfsd/debug.h index 1fdc95bb2375..0bf130a1c58d 100644 --- a/include/uapi/linux/nfsd/debug.h +++ b/include/uapi/linux/nfsd/debug.h @@ -32,6 +32,7 @@ #define NFSDDBG_REPCACHE 0x0080 #define NFSDDBG_XDR 0x0100 #define NFSDDBG_LOCKD 0x0200 +#define NFSDDBG_PNFS 0x0400 #define NFSDDBG_ALL 0x7FFF #define NFSDDBG_NOCHANGE 0xFFFF diff --git a/include/uapi/linux/nfsd/export.h b/include/uapi/linux/nfsd/export.h index 584b6ef3a5e8..4742f2cb42f2 100644 --- a/include/uapi/linux/nfsd/export.h +++ b/include/uapi/linux/nfsd/export.h @@ -47,8 +47,10 @@ * exported filesystem. */ #define NFSEXP_V4ROOT 0x10000 +#define NFSEXP_NOPNFS 0x20000 + /* All flags that we claim to support. (Note we don't support NOACL.) */ -#define NFSEXP_ALLFLAGS 0x1FE7F +#define NFSEXP_ALLFLAGS 0x3FE7F /* The flags that may vary depending on security flavor: */ #define NFSEXP_SECINFO_FLAGS (NFSEXP_READONLY | NFSEXP_ROOTSQUASH \ -- cgit v1.2.3 From b7396a38fb28db4ebbbf35da1057eb5206b4ad6c Mon Sep 17 00:00:00 2001 From: Chunyan Zhang Date: Wed, 28 Jan 2015 19:08:44 +0800 Subject: tty/serial: Add Spreadtrum sc9836-uart driver support Add a full sc9836-uart driver for SC9836 SoC which is based on the spreadtrum sharkl64 platform. This driver also support earlycon. Originally-by: Lanqing Liu Signed-off-by: Orson Zhai Signed-off-by: Chunyan Zhang Acked-by: Arnd Bergmann Reviewed-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/Kconfig | 18 + drivers/tty/serial/Makefile | 1 + drivers/tty/serial/sprd_serial.c | 793 +++++++++++++++++++++++++++++++++++++++ include/uapi/linux/serial_core.h | 3 + 4 files changed, 815 insertions(+) create mode 100644 drivers/tty/serial/sprd_serial.c (limited to 'include/uapi/linux') diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index c63317e87c33..ddcc0a4c659c 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -1583,6 +1583,24 @@ config SERIAL_MEN_Z135 This driver can also be build as a module. If so, the module will be called men_z135_uart.ko +config SERIAL_SPRD + tristate "Support for Spreadtrum serial" + depends on ARCH_SPRD + select SERIAL_CORE + help + This enables the driver for the Spreadtrum's serial. + +config SERIAL_SPRD_CONSOLE + bool "Spreadtrum UART console support" + depends on SERIAL_SPRD=y + select SERIAL_CORE_CONSOLE + select SERIAL_EARLYCON + help + Support for early debug console using Spreadtrum's serial. This enables + the console before standard serial driver is probed. This is enabled + with "earlycon" on the kernel command line. The console is + enabled when early_param is processed. + endmenu config SERIAL_MCTRL_GPIO diff --git a/drivers/tty/serial/Makefile b/drivers/tty/serial/Makefile index a1c1085ef75c..431879003ccd 100644 --- a/drivers/tty/serial/Makefile +++ b/drivers/tty/serial/Makefile @@ -93,6 +93,7 @@ obj-$(CONFIG_SERIAL_RP2) += rp2.o obj-$(CONFIG_SERIAL_FSL_LPUART) += fsl_lpuart.o obj-$(CONFIG_SERIAL_CONEXANT_DIGICOLOR) += digicolor-usart.o obj-$(CONFIG_SERIAL_MEN_Z135) += men_z135_uart.o +obj-$(CONFIG_SERIAL_SPRD) += sprd_serial.o # GPIOLIB helpers for modem control lines obj-$(CONFIG_SERIAL_MCTRL_GPIO) += serial_mctrl_gpio.o diff --git a/drivers/tty/serial/sprd_serial.c b/drivers/tty/serial/sprd_serial.c new file mode 100644 index 000000000000..594b63331ef4 --- /dev/null +++ b/drivers/tty/serial/sprd_serial.c @@ -0,0 +1,793 @@ +/* + * Copyright (C) 2012-2015 Spreadtrum Communications Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * 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. + */ + +#if defined(CONFIG_SERIAL_SPRD_CONSOLE) && defined(CONFIG_MAGIC_SYSRQ) +#define SUPPORT_SYSRQ +#endif + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* device name */ +#define UART_NR_MAX 8 +#define SPRD_TTY_NAME "ttyS" +#define SPRD_FIFO_SIZE 128 +#define SPRD_DEF_RATE 26000000 +#define SPRD_BAUD_IO_LIMIT 3000000 +#define SPRD_TIMEOUT 256 + +/* the offset of serial registers and BITs for them */ +/* data registers */ +#define SPRD_TXD 0x0000 +#define SPRD_RXD 0x0004 + +/* line status register and its BITs */ +#define SPRD_LSR 0x0008 +#define SPRD_LSR_OE BIT(4) +#define SPRD_LSR_FE BIT(3) +#define SPRD_LSR_PE BIT(2) +#define SPRD_LSR_BI BIT(7) +#define SPRD_LSR_TX_OVER BIT(15) + +/* data number in TX and RX fifo */ +#define SPRD_STS1 0x000C + +/* interrupt enable register and its BITs */ +#define SPRD_IEN 0x0010 +#define SPRD_IEN_RX_FULL BIT(0) +#define SPRD_IEN_TX_EMPTY BIT(1) +#define SPRD_IEN_BREAK_DETECT BIT(7) +#define SPRD_IEN_TIMEOUT BIT(13) + +/* interrupt clear register */ +#define SPRD_ICLR 0x0014 + +/* line control register */ +#define SPRD_LCR 0x0018 +#define SPRD_LCR_STOP_1BIT 0x10 +#define SPRD_LCR_STOP_2BIT 0x30 +#define SPRD_LCR_DATA_LEN (BIT(2) | BIT(3)) +#define SPRD_LCR_DATA_LEN5 0x0 +#define SPRD_LCR_DATA_LEN6 0x4 +#define SPRD_LCR_DATA_LEN7 0x8 +#define SPRD_LCR_DATA_LEN8 0xc +#define SPRD_LCR_PARITY (BIT(0) | BIT(1)) +#define SPRD_LCR_PARITY_EN 0x2 +#define SPRD_LCR_EVEN_PAR 0x0 +#define SPRD_LCR_ODD_PAR 0x1 + +/* control register 1 */ +#define SPRD_CTL1 0x001C +#define RX_HW_FLOW_CTL_THLD BIT(6) +#define RX_HW_FLOW_CTL_EN BIT(7) +#define TX_HW_FLOW_CTL_EN BIT(8) +#define RX_TOUT_THLD_DEF 0x3E00 +#define RX_HFC_THLD_DEF 0x40 + +/* fifo threshold register */ +#define SPRD_CTL2 0x0020 +#define THLD_TX_EMPTY 0x40 +#define THLD_RX_FULL 0x40 + +/* config baud rate register */ +#define SPRD_CLKD0 0x0024 +#define SPRD_CLKD1 0x0028 + +/* interrupt mask status register */ +#define SPRD_IMSR 0x002C +#define SPRD_IMSR_RX_FIFO_FULL BIT(0) +#define SPRD_IMSR_TX_FIFO_EMPTY BIT(1) +#define SPRD_IMSR_BREAK_DETECT BIT(7) +#define SPRD_IMSR_TIMEOUT BIT(13) + +struct reg_backup { + u32 ien; + u32 ctrl0; + u32 ctrl1; + u32 ctrl2; + u32 clkd0; + u32 clkd1; + u32 dspwait; +}; + +struct sprd_uart_port { + struct uart_port port; + struct reg_backup reg_bak; + char name[16]; +}; + +static struct sprd_uart_port *sprd_port[UART_NR_MAX]; +static int sprd_ports_num; + +static inline unsigned int serial_in(struct uart_port *port, int offset) +{ + return readl_relaxed(port->membase + offset); +} + +static inline void serial_out(struct uart_port *port, int offset, int value) +{ + writel_relaxed(value, port->membase + offset); +} + +static unsigned int sprd_tx_empty(struct uart_port *port) +{ + if (serial_in(port, SPRD_STS1) & 0xff00) + return 0; + else + return TIOCSER_TEMT; +} + +static unsigned int sprd_get_mctrl(struct uart_port *port) +{ + return TIOCM_DSR | TIOCM_CTS; +} + +static void sprd_set_mctrl(struct uart_port *port, unsigned int mctrl) +{ + /* nothing to do */ +} + +static void sprd_stop_tx(struct uart_port *port) +{ + unsigned int ien, iclr; + + iclr = serial_in(port, SPRD_ICLR); + ien = serial_in(port, SPRD_IEN); + + iclr |= SPRD_IEN_TX_EMPTY; + ien &= ~SPRD_IEN_TX_EMPTY; + + serial_out(port, SPRD_ICLR, iclr); + serial_out(port, SPRD_IEN, ien); +} + +static void sprd_start_tx(struct uart_port *port) +{ + unsigned int ien; + + ien = serial_in(port, SPRD_IEN); + if (!(ien & SPRD_IEN_TX_EMPTY)) { + ien |= SPRD_IEN_TX_EMPTY; + serial_out(port, SPRD_IEN, ien); + } +} + +static void sprd_stop_rx(struct uart_port *port) +{ + unsigned int ien, iclr; + + iclr = serial_in(port, SPRD_ICLR); + ien = serial_in(port, SPRD_IEN); + + ien &= ~(SPRD_IEN_RX_FULL | SPRD_IEN_BREAK_DETECT); + iclr |= SPRD_IEN_RX_FULL | SPRD_IEN_BREAK_DETECT; + + serial_out(port, SPRD_IEN, ien); + serial_out(port, SPRD_ICLR, iclr); +} + +/* The Sprd serial does not support this function. */ +static void sprd_break_ctl(struct uart_port *port, int break_state) +{ + /* nothing to do */ +} + +static int handle_lsr_errors(struct uart_port *port, + unsigned int *flag, + unsigned int *lsr) +{ + int ret = 0; + + /* statistics */ + if (*lsr & SPRD_LSR_BI) { + *lsr &= ~(SPRD_LSR_FE | SPRD_LSR_PE); + port->icount.brk++; + ret = uart_handle_break(port); + if (ret) + return ret; + } else if (*lsr & SPRD_LSR_PE) + port->icount.parity++; + else if (*lsr & SPRD_LSR_FE) + port->icount.frame++; + if (*lsr & SPRD_LSR_OE) + port->icount.overrun++; + + /* mask off conditions which should be ignored */ + *lsr &= port->read_status_mask; + if (*lsr & SPRD_LSR_BI) + *flag = TTY_BREAK; + else if (*lsr & SPRD_LSR_PE) + *flag = TTY_PARITY; + else if (*lsr & SPRD_LSR_FE) + *flag = TTY_FRAME; + + return ret; +} + +static inline void sprd_rx(struct uart_port *port) +{ + struct tty_port *tty = &port->state->port; + unsigned int ch, flag, lsr, max_count = SPRD_TIMEOUT; + + while ((serial_in(port, SPRD_STS1) & 0x00ff) && max_count--) { + lsr = serial_in(port, SPRD_LSR); + ch = serial_in(port, SPRD_RXD); + flag = TTY_NORMAL; + port->icount.rx++; + + if (lsr & (SPRD_LSR_BI | SPRD_LSR_PE | + SPRD_LSR_FE | SPRD_LSR_OE)) + if (handle_lsr_errors(port, &lsr, &flag)) + continue; + if (uart_handle_sysrq_char(port, ch)) + continue; + + uart_insert_char(port, lsr, SPRD_LSR_OE, ch, flag); + } + + tty_flip_buffer_push(tty); +} + +static inline void sprd_tx(struct uart_port *port) +{ + struct circ_buf *xmit = &port->state->xmit; + int count; + + if (port->x_char) { + serial_out(port, SPRD_TXD, port->x_char); + port->icount.tx++; + port->x_char = 0; + return; + } + + if (uart_circ_empty(xmit) || uart_tx_stopped(port)) { + sprd_stop_tx(port); + return; + } + + count = THLD_TX_EMPTY; + do { + serial_out(port, SPRD_TXD, xmit->buf[xmit->tail]); + xmit->tail = (xmit->tail + 1) & (UART_XMIT_SIZE - 1); + port->icount.tx++; + if (uart_circ_empty(xmit)) + break; + } while (--count > 0); + + if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS) + uart_write_wakeup(port); + + if (uart_circ_empty(xmit)) + sprd_stop_tx(port); +} + +/* this handles the interrupt from one port */ +static irqreturn_t sprd_handle_irq(int irq, void *dev_id) +{ + struct uart_port *port = dev_id; + unsigned int ims; + + spin_lock(&port->lock); + + ims = serial_in(port, SPRD_IMSR); + + if (!ims) + return IRQ_NONE; + + serial_out(port, SPRD_ICLR, ~0); + + if (ims & (SPRD_IMSR_RX_FIFO_FULL | + SPRD_IMSR_BREAK_DETECT | SPRD_IMSR_TIMEOUT)) + sprd_rx(port); + + if (ims & SPRD_IMSR_TX_FIFO_EMPTY) + sprd_tx(port); + + spin_unlock(&port->lock); + + return IRQ_HANDLED; +} + +static int sprd_startup(struct uart_port *port) +{ + int ret = 0; + unsigned int ien, fc; + unsigned int timeout; + struct sprd_uart_port *sp; + unsigned long flags; + + serial_out(port, SPRD_CTL2, ((THLD_TX_EMPTY << 8) | THLD_RX_FULL)); + + /* clear rx fifo */ + timeout = SPRD_TIMEOUT; + while (timeout-- && serial_in(port, SPRD_STS1) & 0x00ff) + serial_in(port, SPRD_RXD); + + /* clear tx fifo */ + timeout = SPRD_TIMEOUT; + while (timeout-- && serial_in(port, SPRD_STS1) & 0xff00) + cpu_relax(); + + /* clear interrupt */ + serial_out(port, SPRD_IEN, 0); + serial_out(port, SPRD_ICLR, ~0); + + /* allocate irq */ + sp = container_of(port, struct sprd_uart_port, port); + snprintf(sp->name, sizeof(sp->name), "sprd_serial%d", port->line); + ret = devm_request_irq(port->dev, port->irq, sprd_handle_irq, + IRQF_SHARED, sp->name, port); + if (ret) { + dev_err(port->dev, "fail to request serial irq %d, ret=%d\n", + port->irq, ret); + return ret; + } + fc = serial_in(port, SPRD_CTL1); + fc |= RX_TOUT_THLD_DEF | RX_HFC_THLD_DEF; + serial_out(port, SPRD_CTL1, fc); + + /* enable interrupt */ + spin_lock_irqsave(&port->lock, flags); + ien = serial_in(port, SPRD_IEN); + ien |= SPRD_IEN_RX_FULL | SPRD_IEN_BREAK_DETECT | SPRD_IEN_TIMEOUT; + serial_out(port, SPRD_IEN, ien); + spin_unlock_irqrestore(&port->lock, flags); + + return 0; +} + +static void sprd_shutdown(struct uart_port *port) +{ + serial_out(port, SPRD_IEN, 0); + serial_out(port, SPRD_ICLR, ~0); + devm_free_irq(port->dev, port->irq, port); +} + +static void sprd_set_termios(struct uart_port *port, + struct ktermios *termios, + struct ktermios *old) +{ + unsigned int baud, quot; + unsigned int lcr = 0, fc; + unsigned long flags; + + /* ask the core to calculate the divisor for us */ + baud = uart_get_baud_rate(port, termios, old, 0, SPRD_BAUD_IO_LIMIT); + + quot = (unsigned int)((port->uartclk + baud / 2) / baud); + + /* set data length */ + switch (termios->c_cflag & CSIZE) { + case CS5: + lcr |= SPRD_LCR_DATA_LEN5; + break; + case CS6: + lcr |= SPRD_LCR_DATA_LEN6; + break; + case CS7: + lcr |= SPRD_LCR_DATA_LEN7; + break; + case CS8: + default: + lcr |= SPRD_LCR_DATA_LEN8; + break; + } + + /* calculate stop bits */ + lcr &= ~(SPRD_LCR_STOP_1BIT | SPRD_LCR_STOP_2BIT); + if (termios->c_cflag & CSTOPB) + lcr |= SPRD_LCR_STOP_2BIT; + else + lcr |= SPRD_LCR_STOP_1BIT; + + /* calculate parity */ + lcr &= ~SPRD_LCR_PARITY; + termios->c_cflag &= ~CMSPAR; /* no support mark/space */ + if (termios->c_cflag & PARENB) { + lcr |= SPRD_LCR_PARITY_EN; + if (termios->c_cflag & PARODD) + lcr |= SPRD_LCR_ODD_PAR; + else + lcr |= SPRD_LCR_EVEN_PAR; + } + + spin_lock_irqsave(&port->lock, flags); + + /* update the per-port timeout */ + uart_update_timeout(port, termios->c_cflag, baud); + + port->read_status_mask = SPRD_LSR_OE; + if (termios->c_iflag & INPCK) + port->read_status_mask |= SPRD_LSR_FE | SPRD_LSR_PE; + if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK)) + port->read_status_mask |= SPRD_LSR_BI; + + /* characters to ignore */ + port->ignore_status_mask = 0; + if (termios->c_iflag & IGNPAR) + port->ignore_status_mask |= SPRD_LSR_PE | SPRD_LSR_FE; + if (termios->c_iflag & IGNBRK) { + port->ignore_status_mask |= SPRD_LSR_BI; + /* + * If we're ignoring parity and break indicators, + * ignore overruns too (for real raw support). + */ + if (termios->c_iflag & IGNPAR) + port->ignore_status_mask |= SPRD_LSR_OE; + } + + /* flow control */ + fc = serial_in(port, SPRD_CTL1); + fc &= ~(RX_HW_FLOW_CTL_THLD | RX_HW_FLOW_CTL_EN | TX_HW_FLOW_CTL_EN); + if (termios->c_cflag & CRTSCTS) { + fc |= RX_HW_FLOW_CTL_THLD; + fc |= RX_HW_FLOW_CTL_EN; + fc |= TX_HW_FLOW_CTL_EN; + } + + /* clock divider bit0~bit15 */ + serial_out(port, SPRD_CLKD0, quot & 0xffff); + + /* clock divider bit16~bit20 */ + serial_out(port, SPRD_CLKD1, (quot & 0x1f0000) >> 16); + serial_out(port, SPRD_LCR, lcr); + fc |= RX_TOUT_THLD_DEF | RX_HFC_THLD_DEF; + serial_out(port, SPRD_CTL1, fc); + + spin_unlock_irqrestore(&port->lock, flags); + + /* Don't rewrite B0 */ + if (tty_termios_baud_rate(termios)) + tty_termios_encode_baud_rate(termios, baud, baud); +} + +static const char *sprd_type(struct uart_port *port) +{ + return "SPX"; +} + +static void sprd_release_port(struct uart_port *port) +{ + /* nothing to do */ +} + +static int sprd_request_port(struct uart_port *port) +{ + return 0; +} + +static void sprd_config_port(struct uart_port *port, int flags) +{ + if (flags & UART_CONFIG_TYPE) + port->type = PORT_SPRD; +} + +static int sprd_verify_port(struct uart_port *port, + struct serial_struct *ser) +{ + if (ser->type != PORT_SPRD) + return -EINVAL; + if (port->irq != ser->irq) + return -EINVAL; + return 0; +} + +static struct uart_ops serial_sprd_ops = { + .tx_empty = sprd_tx_empty, + .get_mctrl = sprd_get_mctrl, + .set_mctrl = sprd_set_mctrl, + .stop_tx = sprd_stop_tx, + .start_tx = sprd_start_tx, + .stop_rx = sprd_stop_rx, + .break_ctl = sprd_break_ctl, + .startup = sprd_startup, + .shutdown = sprd_shutdown, + .set_termios = sprd_set_termios, + .type = sprd_type, + .release_port = sprd_release_port, + .request_port = sprd_request_port, + .config_port = sprd_config_port, + .verify_port = sprd_verify_port, +}; + +#ifdef CONFIG_SERIAL_SPRD_CONSOLE +static inline void wait_for_xmitr(struct uart_port *port) +{ + unsigned int status, tmout = 10000; + + /* wait up to 10ms for the character(s) to be sent */ + do { + status = serial_in(port, SPRD_STS1); + if (--tmout == 0) + break; + udelay(1); + } while (status & 0xff00); +} + +static void sprd_console_putchar(struct uart_port *port, int ch) +{ + wait_for_xmitr(port); + serial_out(port, SPRD_TXD, ch); +} + +static void sprd_console_write(struct console *co, const char *s, + unsigned int count) +{ + struct uart_port *port = &sprd_port[co->index]->port; + int locked = 1; + unsigned long flags; + + if (port->sysrq) + locked = 0; + else if (oops_in_progress) + locked = spin_trylock_irqsave(&port->lock, flags); + else + spin_lock_irqsave(&port->lock, flags); + + uart_console_write(port, s, count, sprd_console_putchar); + + /* wait for transmitter to become empty */ + wait_for_xmitr(port); + + if (locked) + spin_unlock_irqrestore(&port->lock, flags); +} + +static int __init sprd_console_setup(struct console *co, char *options) +{ + struct uart_port *port; + int baud = 115200; + int bits = 8; + int parity = 'n'; + int flow = 'n'; + + if (co->index >= UART_NR_MAX || co->index < 0) + co->index = 0; + + port = &sprd_port[co->index]->port; + if (port == NULL) { + pr_info("serial port %d not yet initialized\n", co->index); + return -ENODEV; + } + if (options) + uart_parse_options(options, &baud, &parity, &bits, &flow); + + return uart_set_options(port, co, baud, parity, bits, flow); +} + +static struct uart_driver sprd_uart_driver; +static struct console sprd_console = { + .name = SPRD_TTY_NAME, + .write = sprd_console_write, + .device = uart_console_device, + .setup = sprd_console_setup, + .flags = CON_PRINTBUFFER, + .index = -1, + .data = &sprd_uart_driver, +}; + +#define SPRD_CONSOLE (&sprd_console) + +/* Support for earlycon */ +static void sprd_putc(struct uart_port *port, int c) +{ + unsigned int timeout = SPRD_TIMEOUT; + + while (timeout-- && + !(readl(port->membase + SPRD_LSR) & SPRD_LSR_TX_OVER)) + cpu_relax(); + + writeb(c, port->membase + SPRD_TXD); +} + +static void sprd_early_write(struct console *con, const char *s, + unsigned n) +{ + struct earlycon_device *dev = con->data; + + uart_console_write(&dev->port, s, n, sprd_putc); +} + +static int __init sprd_early_console_setup( + struct earlycon_device *device, + const char *opt) +{ + if (!device->port.membase) + return -ENODEV; + + device->con->write = sprd_early_write; + return 0; +} + +EARLYCON_DECLARE(sprd_serial, sprd_early_console_setup); +OF_EARLYCON_DECLARE(sprd_serial, "sprd,sc9836-uart", + sprd_early_console_setup); + +#else /* !CONFIG_SERIAL_SPRD_CONSOLE */ +#define SPRD_CONSOLE NULL +#endif + +static struct uart_driver sprd_uart_driver = { + .owner = THIS_MODULE, + .driver_name = "sprd_serial", + .dev_name = SPRD_TTY_NAME, + .major = 0, + .minor = 0, + .nr = UART_NR_MAX, + .cons = SPRD_CONSOLE, +}; + +static int sprd_probe_dt_alias(int index, struct device *dev) +{ + struct device_node *np; + int ret = index; + + if (!IS_ENABLED(CONFIG_OF)) + return ret; + + np = dev->of_node; + if (!np) + return ret; + + ret = of_alias_get_id(np, "serial"); + if (IS_ERR_VALUE(ret)) + ret = index; + else if (ret >= ARRAY_SIZE(sprd_port) || sprd_port[ret] != NULL) { + dev_warn(dev, "requested serial port %d not available.\n", ret); + ret = index; + } + + return ret; +} + +static int sprd_remove(struct platform_device *dev) +{ + struct sprd_uart_port *sup = platform_get_drvdata(dev); + + if (sup) { + uart_remove_one_port(&sprd_uart_driver, &sup->port); + sprd_port[sup->port.line] = NULL; + sprd_ports_num--; + } + + if (!sprd_ports_num) + uart_unregister_driver(&sprd_uart_driver); + + return 0; +} + +static int sprd_probe(struct platform_device *pdev) +{ + struct resource *res; + struct uart_port *up; + struct clk *clk; + int irq; + int index; + int ret; + + for (index = 0; index < ARRAY_SIZE(sprd_port); index++) + if (sprd_port[index] == NULL) + break; + + if (index == ARRAY_SIZE(sprd_port)) + return -EBUSY; + + index = sprd_probe_dt_alias(index, &pdev->dev); + + sprd_port[index] = devm_kzalloc(&pdev->dev, + sizeof(*sprd_port[index]), GFP_KERNEL); + if (!sprd_port[index]) + return -ENOMEM; + + up = &sprd_port[index]->port; + up->dev = &pdev->dev; + up->line = index; + up->type = PORT_SPRD; + up->iotype = SERIAL_IO_PORT; + up->uartclk = SPRD_DEF_RATE; + up->fifosize = SPRD_FIFO_SIZE; + up->ops = &serial_sprd_ops; + up->flags = UPF_BOOT_AUTOCONF; + + clk = devm_clk_get(&pdev->dev, NULL); + if (!IS_ERR(clk)) + up->uartclk = clk_get_rate(clk); + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) { + dev_err(&pdev->dev, "not provide mem resource\n"); + return -ENODEV; + } + up->mapbase = res->start; + up->membase = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(up->membase)) + return PTR_ERR(up->membase); + + irq = platform_get_irq(pdev, 0); + if (irq < 0) { + dev_err(&pdev->dev, "not provide irq resource\n"); + return -ENODEV; + } + up->irq = irq; + + if (!sprd_ports_num) { + ret = uart_register_driver(&sprd_uart_driver); + if (ret < 0) { + pr_err("Failed to register SPRD-UART driver\n"); + return ret; + } + } + sprd_ports_num++; + + ret = uart_add_one_port(&sprd_uart_driver, up); + if (ret) { + sprd_port[index] = NULL; + sprd_remove(pdev); + } + + platform_set_drvdata(pdev, up); + + return ret; +} + +static int sprd_suspend(struct device *dev) +{ + struct sprd_uart_port *sup = dev_get_drvdata(dev); + + uart_suspend_port(&sprd_uart_driver, &sup->port); + + return 0; +} + +static int sprd_resume(struct device *dev) +{ + struct sprd_uart_port *sup = dev_get_drvdata(dev); + + uart_resume_port(&sprd_uart_driver, &sup->port); + + return 0; +} + +static SIMPLE_DEV_PM_OPS(sprd_pm_ops, sprd_suspend, sprd_resume); + +static const struct of_device_id serial_ids[] = { + {.compatible = "sprd,sc9836-uart",}, + {} +}; + +static struct platform_driver sprd_platform_driver = { + .probe = sprd_probe, + .remove = sprd_remove, + .driver = { + .name = "sprd_serial", + .of_match_table = of_match_ptr(serial_ids), + .pm = &sprd_pm_ops, + }, +}; + +module_platform_driver(sprd_platform_driver); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("Spreadtrum SoC serial driver series"); diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h index ee628c489e47..55da91e763bb 100644 --- a/include/uapi/linux/serial_core.h +++ b/include/uapi/linux/serial_core.h @@ -252,4 +252,7 @@ /* Conexant Digicolor */ #define PORT_DIGICOLOR 110 +/* SPRD SERIAL */ +#define PORT_SPRD 111 + #endif /* _UAPILINUX_SERIAL_CORE_H */ -- cgit v1.2.3 From 0ae45f63d4ef8d8eeec49c7d8b44a1775fff13e8 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Mon, 2 Feb 2015 00:37:00 -0500 Subject: vfs: add support for a lazytime mount option Add a new mount option which enables a new "lazytime" mode. This mode causes atime, mtime, and ctime updates to only be made to the in-memory version of the inode. The on-disk times will only get updated when (a) if the inode needs to be updated for some non-time related change, (b) if userspace calls fsync(), syncfs() or sync(), or (c) just before an undeleted inode is evicted from memory. This is OK according to POSIX because there are no guarantees after a crash unless userspace explicitly requests via a fsync(2) call. For workloads which feature a large number of random write to a preallocated file, the lazytime mount option significantly reduces writes to the inode table. The repeated 4k writes to a single block will result in undesirable stress on flash devices and SMR disk drives. Even on conventional HDD's, the repeated writes to the inode table block will trigger Adjacent Track Interference (ATI) remediation latencies, which very negatively impact long tail latencies --- which is a very big deal for web serving tiers (for example). Google-Bug-Id: 18297052 Signed-off-by: Theodore Ts'o Signed-off-by: Al Viro --- fs/ext4/inode.c | 6 ++++ fs/fs-writeback.c | 62 +++++++++++++++++++++++++++++++++------- fs/gfs2/file.c | 4 +-- fs/inode.c | 56 +++++++++++++++++++++++++----------- fs/jfs/file.c | 2 +- fs/libfs.c | 2 +- fs/proc_namespace.c | 1 + fs/sync.c | 8 ++++++ include/linux/backing-dev.h | 1 + include/linux/fs.h | 5 ++++ include/trace/events/writeback.h | 60 +++++++++++++++++++++++++++++++++++++- include/uapi/linux/fs.h | 4 ++- mm/backing-dev.c | 10 +++++-- 13 files changed, 186 insertions(+), 35 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 5653fa42930b..628df5ba44a6 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4840,11 +4840,17 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode) * If the inode is marked synchronous, we don't honour that here - doing * so would cause a commit on atime updates, which we don't bother doing. * We handle synchronous inodes at the highest possible level. + * + * If only the I_DIRTY_TIME flag is set, we can skip everything. If + * I_DIRTY_TIME and I_DIRTY_SYNC is set, the only inode fields we need + * to copy into the on-disk inode structure are the timestamp files. */ void ext4_dirty_inode(struct inode *inode, int flags) { handle_t *handle; + if (flags == I_DIRTY_TIME) + return; handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); if (IS_ERR(handle)) goto out; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 2d609a5fbfea..004686191354 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -247,14 +247,19 @@ static bool inode_dirtied_after(struct inode *inode, unsigned long t) return ret; } +#define EXPIRE_DIRTY_ATIME 0x0001 + /* * Move expired (dirtied before work->older_than_this) dirty inodes from * @delaying_queue to @dispatch_queue. */ static int move_expired_inodes(struct list_head *delaying_queue, struct list_head *dispatch_queue, + int flags, struct wb_writeback_work *work) { + unsigned long *older_than_this = NULL; + unsigned long expire_time; LIST_HEAD(tmp); struct list_head *pos, *node; struct super_block *sb = NULL; @@ -262,13 +267,21 @@ static int move_expired_inodes(struct list_head *delaying_queue, int do_sb_sort = 0; int moved = 0; + if ((flags & EXPIRE_DIRTY_ATIME) == 0) + older_than_this = work->older_than_this; + else if ((work->reason == WB_REASON_SYNC) == 0) { + expire_time = jiffies - (HZ * 86400); + older_than_this = &expire_time; + } while (!list_empty(delaying_queue)) { inode = wb_inode(delaying_queue->prev); - if (work->older_than_this && - inode_dirtied_after(inode, *work->older_than_this)) + if (older_than_this && + inode_dirtied_after(inode, *older_than_this)) break; list_move(&inode->i_wb_list, &tmp); moved++; + if (flags & EXPIRE_DIRTY_ATIME) + set_bit(__I_DIRTY_TIME_EXPIRED, &inode->i_state); if (sb_is_blkdev_sb(inode->i_sb)) continue; if (sb && sb != inode->i_sb) @@ -309,9 +322,12 @@ out: static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work) { int moved; + assert_spin_locked(&wb->list_lock); list_splice_init(&wb->b_more_io, &wb->b_io); - moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, work); + moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, 0, work); + moved += move_expired_inodes(&wb->b_dirty_time, &wb->b_io, + EXPIRE_DIRTY_ATIME, work); trace_writeback_queue_io(wb, work, moved); } @@ -435,6 +451,8 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, * updates after data IO completion. */ redirty_tail(inode, wb); + } else if (inode->i_state & I_DIRTY_TIME) { + list_move(&inode->i_wb_list, &wb->b_dirty_time); } else { /* The inode is clean. Remove from writeback lists. */ list_del_init(&inode->i_wb_list); @@ -481,7 +499,13 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) spin_lock(&inode->i_lock); dirty = inode->i_state & I_DIRTY; - inode->i_state &= ~I_DIRTY; + if (((dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) && + (inode->i_state & I_DIRTY_TIME)) || + (inode->i_state & I_DIRTY_TIME_EXPIRED)) { + dirty |= I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED; + trace_writeback_lazytime(inode); + } + inode->i_state &= ~dirty; /* * Paired with smp_mb() in __mark_inode_dirty(). This allows @@ -501,8 +525,10 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) spin_unlock(&inode->i_lock); + if (dirty & I_DIRTY_TIME) + mark_inode_dirty_sync(inode); /* Don't write the inode if only I_DIRTY_PAGES was set */ - if (dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) { + if (dirty & ~I_DIRTY_PAGES) { int err = write_inode(inode, wbc); if (ret == 0) ret = err; @@ -550,7 +576,7 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb, * make sure inode is on some writeback list and leave it there unless * we have completely cleaned the inode. */ - if (!(inode->i_state & I_DIRTY) && + if (!(inode->i_state & I_DIRTY_ALL) && (wbc->sync_mode != WB_SYNC_ALL || !mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK))) goto out; @@ -565,7 +591,7 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb, * If inode is clean, remove it from writeback lists. Otherwise don't * touch it. See comment above for explanation. */ - if (!(inode->i_state & I_DIRTY)) + if (!(inode->i_state & I_DIRTY_ALL)) list_del_init(&inode->i_wb_list); spin_unlock(&wb->list_lock); inode_sync_complete(inode); @@ -707,7 +733,7 @@ static long writeback_sb_inodes(struct super_block *sb, wrote += write_chunk - wbc.nr_to_write; spin_lock(&wb->list_lock); spin_lock(&inode->i_lock); - if (!(inode->i_state & I_DIRTY)) + if (!(inode->i_state & I_DIRTY_ALL)) wrote++; requeue_inode(inode, wb, &wbc); inode_sync_complete(inode); @@ -1145,16 +1171,20 @@ static noinline void block_dump___mark_inode_dirty(struct inode *inode) * page->mapping->host, so the page-dirtying time is recorded in the internal * blockdev inode. */ +#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) void __mark_inode_dirty(struct inode *inode, int flags) { struct super_block *sb = inode->i_sb; struct backing_dev_info *bdi = NULL; + int dirtytime; + + trace_writeback_mark_inode_dirty(inode, flags); /* * Don't do this for I_DIRTY_PAGES - that doesn't actually * dirty the inode itself */ - if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) { + if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_TIME)) { trace_writeback_dirty_inode_start(inode, flags); if (sb->s_op->dirty_inode) @@ -1162,6 +1192,9 @@ void __mark_inode_dirty(struct inode *inode, int flags) trace_writeback_dirty_inode(inode, flags); } + if (flags & I_DIRTY_INODE) + flags &= ~I_DIRTY_TIME; + dirtytime = flags & I_DIRTY_TIME; /* * Paired with smp_mb() in __writeback_single_inode() for the @@ -1169,16 +1202,21 @@ void __mark_inode_dirty(struct inode *inode, int flags) */ smp_mb(); - if ((inode->i_state & flags) == flags) + if (((inode->i_state & flags) == flags) || + (dirtytime && (inode->i_state & I_DIRTY_INODE))) return; if (unlikely(block_dump)) block_dump___mark_inode_dirty(inode); spin_lock(&inode->i_lock); + if (dirtytime && (inode->i_state & I_DIRTY_INODE)) + goto out_unlock_inode; if ((inode->i_state & flags) != flags) { const int was_dirty = inode->i_state & I_DIRTY; + if (flags & I_DIRTY_INODE) + inode->i_state &= ~I_DIRTY_TIME; inode->i_state |= flags; /* @@ -1225,8 +1263,10 @@ void __mark_inode_dirty(struct inode *inode, int flags) } inode->dirtied_when = jiffies; - list_move(&inode->i_wb_list, &bdi->wb.b_dirty); + list_move(&inode->i_wb_list, dirtytime ? + &bdi->wb.b_dirty_time : &bdi->wb.b_dirty); spin_unlock(&bdi->wb.list_lock); + trace_writeback_dirty_inode_enqueue(inode); if (wakeup_bdi) bdi_wakeup_thread_delayed(bdi); diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 6e600abf694a..15c44cf457cc 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -655,7 +655,7 @@ static int gfs2_fsync(struct file *file, loff_t start, loff_t end, { struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; - int sync_state = inode->i_state & I_DIRTY; + int sync_state = inode->i_state & I_DIRTY_ALL; struct gfs2_inode *ip = GFS2_I(inode); int ret = 0, ret1 = 0; @@ -668,7 +668,7 @@ static int gfs2_fsync(struct file *file, loff_t start, loff_t end, if (!gfs2_is_jdata(ip)) sync_state &= ~I_DIRTY_PAGES; if (datasync) - sync_state &= ~I_DIRTY_SYNC; + sync_state &= ~(I_DIRTY_SYNC | I_DIRTY_TIME); if (sync_state) { ret = sync_inode_metadata(inode, 1); diff --git a/fs/inode.c b/fs/inode.c index aa149e7262ac..4feb85cc125f 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -18,6 +18,7 @@ #include /* for inode_has_buffers */ #include #include +#include #include "internal.h" /* @@ -30,7 +31,7 @@ * inode_sb_list_lock protects: * sb->s_inodes, inode->i_sb_list * bdi->wb.list_lock protects: - * bdi->wb.b_{dirty,io,more_io}, inode->i_wb_list + * bdi->wb.b_{dirty,io,more_io,dirty_time}, inode->i_wb_list * inode_hash_lock protects: * inode_hashtable, inode->i_hash * @@ -416,7 +417,8 @@ static void inode_lru_list_add(struct inode *inode) */ void inode_add_lru(struct inode *inode) { - if (!(inode->i_state & (I_DIRTY | I_SYNC | I_FREEING | I_WILL_FREE)) && + if (!(inode->i_state & (I_DIRTY_ALL | I_SYNC | + I_FREEING | I_WILL_FREE)) && !atomic_read(&inode->i_count) && inode->i_sb->s_flags & MS_ACTIVE) inode_lru_list_add(inode); } @@ -647,7 +649,7 @@ int invalidate_inodes(struct super_block *sb, bool kill_dirty) spin_unlock(&inode->i_lock); continue; } - if (inode->i_state & I_DIRTY && !kill_dirty) { + if (inode->i_state & I_DIRTY_ALL && !kill_dirty) { spin_unlock(&inode->i_lock); busy = 1; continue; @@ -1432,11 +1434,20 @@ static void iput_final(struct inode *inode) */ void iput(struct inode *inode) { - if (inode) { - BUG_ON(inode->i_state & I_CLEAR); - - if (atomic_dec_and_lock(&inode->i_count, &inode->i_lock)) - iput_final(inode); + if (!inode) + return; + BUG_ON(inode->i_state & I_CLEAR); +retry: + if (atomic_dec_and_lock(&inode->i_count, &inode->i_lock)) { + if (inode->i_nlink && (inode->i_state & I_DIRTY_TIME)) { + atomic_inc(&inode->i_count); + inode->i_state &= ~I_DIRTY_TIME; + spin_unlock(&inode->i_lock); + trace_writeback_lazytime_iput(inode); + mark_inode_dirty_sync(inode); + goto retry; + } + iput_final(inode); } } EXPORT_SYMBOL(iput); @@ -1495,14 +1506,9 @@ static int relatime_need_update(struct vfsmount *mnt, struct inode *inode, return 0; } -/* - * This does the actual work of updating an inodes time or version. Must have - * had called mnt_want_write() before calling this. - */ -static int update_time(struct inode *inode, struct timespec *time, int flags) +int generic_update_time(struct inode *inode, struct timespec *time, int flags) { - if (inode->i_op->update_time) - return inode->i_op->update_time(inode, time, flags); + int iflags = I_DIRTY_TIME; if (flags & S_ATIME) inode->i_atime = *time; @@ -1512,9 +1518,27 @@ static int update_time(struct inode *inode, struct timespec *time, int flags) inode->i_ctime = *time; if (flags & S_MTIME) inode->i_mtime = *time; - mark_inode_dirty_sync(inode); + + if (!(inode->i_sb->s_flags & MS_LAZYTIME) || (flags & S_VERSION)) + iflags |= I_DIRTY_SYNC; + __mark_inode_dirty(inode, iflags); return 0; } +EXPORT_SYMBOL(generic_update_time); + +/* + * This does the actual work of updating an inodes time or version. Must have + * had called mnt_want_write() before calling this. + */ +static int update_time(struct inode *inode, struct timespec *time, int flags) +{ + int (*update_time)(struct inode *, struct timespec *, int); + + update_time = inode->i_op->update_time ? inode->i_op->update_time : + generic_update_time; + + return update_time(inode, time, flags); +} /** * touch_atime - update the access time diff --git a/fs/jfs/file.c b/fs/jfs/file.c index 33aa0cc1f8b8..10815f8dfd8b 100644 --- a/fs/jfs/file.c +++ b/fs/jfs/file.c @@ -39,7 +39,7 @@ int jfs_fsync(struct file *file, loff_t start, loff_t end, int datasync) return rc; mutex_lock(&inode->i_mutex); - if (!(inode->i_state & I_DIRTY) || + if (!(inode->i_state & I_DIRTY_ALL) || (datasync && !(inode->i_state & I_DIRTY_DATASYNC))) { /* Make sure committed changes hit the disk */ jfs_flush_journal(JFS_SBI(inode->i_sb)->log, 1); diff --git a/fs/libfs.c b/fs/libfs.c index 005843ce5dbd..b2ffdb045be4 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -948,7 +948,7 @@ int __generic_file_fsync(struct file *file, loff_t start, loff_t end, mutex_lock(&inode->i_mutex); ret = sync_mapping_buffers(inode->i_mapping); - if (!(inode->i_state & I_DIRTY)) + if (!(inode->i_state & I_DIRTY_ALL)) goto out; if (datasync && !(inode->i_state & I_DIRTY_DATASYNC)) goto out; diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c index 0f96f71ab32b..8db932da4009 100644 --- a/fs/proc_namespace.c +++ b/fs/proc_namespace.c @@ -44,6 +44,7 @@ static int show_sb_opts(struct seq_file *m, struct super_block *sb) { MS_SYNCHRONOUS, ",sync" }, { MS_DIRSYNC, ",dirsync" }, { MS_MANDLOCK, ",mand" }, + { MS_LAZYTIME, ",lazytime" }, { 0, NULL } }; const struct proc_fs_info *fs_infop; diff --git a/fs/sync.c b/fs/sync.c index 01d9f18a70b5..fbc98ee62044 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -177,8 +177,16 @@ SYSCALL_DEFINE1(syncfs, int, fd) */ int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync) { + struct inode *inode = file->f_mapping->host; + if (!file->f_op->fsync) return -EINVAL; + if (!datasync && (inode->i_state & I_DIRTY_TIME)) { + spin_lock(&inode->i_lock); + inode->i_state &= ~I_DIRTY_TIME; + spin_unlock(&inode->i_lock); + mark_inode_dirty_sync(inode); + } return file->f_op->fsync(file, start, end, datasync); } EXPORT_SYMBOL(vfs_fsync_range); diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 5da6012b7a14..4cdf7336f64a 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -55,6 +55,7 @@ struct bdi_writeback { struct list_head b_dirty; /* dirty inodes */ struct list_head b_io; /* parked for writeback */ struct list_head b_more_io; /* parked for more writeback */ + struct list_head b_dirty_time; /* time stamps are dirty */ spinlock_t list_lock; /* protects the b_* lists */ }; diff --git a/include/linux/fs.h b/include/linux/fs.h index 42efe13077b6..cd027ce2c705 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1746,8 +1746,12 @@ struct super_operations { #define __I_DIO_WAKEUP 9 #define I_DIO_WAKEUP (1 << I_DIO_WAKEUP) #define I_LINKABLE (1 << 10) +#define I_DIRTY_TIME (1 << 11) +#define __I_DIRTY_TIME_EXPIRED 12 +#define I_DIRTY_TIME_EXPIRED (1 << __I_DIRTY_TIME_EXPIRED) #define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES) +#define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME) extern void __mark_inode_dirty(struct inode *, int); static inline void mark_inode_dirty(struct inode *inode) @@ -1910,6 +1914,7 @@ extern int current_umask(void); extern void ihold(struct inode * inode); extern void iput(struct inode *); +extern int generic_update_time(struct inode *, struct timespec *, int); static inline struct inode *file_inode(const struct file *f) { diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index cee02d65ab3f..5ecb4c234625 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -18,6 +18,8 @@ {I_FREEING, "I_FREEING"}, \ {I_CLEAR, "I_CLEAR"}, \ {I_SYNC, "I_SYNC"}, \ + {I_DIRTY_TIME, "I_DIRTY_TIME"}, \ + {I_DIRTY_TIME_EXPIRED, "I_DIRTY_TIME_EXPIRED"}, \ {I_REFERENCED, "I_REFERENCED"} \ ) @@ -68,6 +70,7 @@ DECLARE_EVENT_CLASS(writeback_dirty_inode_template, TP_STRUCT__entry ( __array(char, name, 32) __field(unsigned long, ino) + __field(unsigned long, state) __field(unsigned long, flags) ), @@ -78,16 +81,25 @@ DECLARE_EVENT_CLASS(writeback_dirty_inode_template, strncpy(__entry->name, bdi->dev ? dev_name(bdi->dev) : "(unknown)", 32); __entry->ino = inode->i_ino; + __entry->state = inode->i_state; __entry->flags = flags; ), - TP_printk("bdi %s: ino=%lu flags=%s", + TP_printk("bdi %s: ino=%lu state=%s flags=%s", __entry->name, __entry->ino, + show_inode_state(__entry->state), show_inode_state(__entry->flags) ) ); +DEFINE_EVENT(writeback_dirty_inode_template, writeback_mark_inode_dirty, + + TP_PROTO(struct inode *inode, int flags), + + TP_ARGS(inode, flags) +); + DEFINE_EVENT(writeback_dirty_inode_template, writeback_dirty_inode_start, TP_PROTO(struct inode *inode, int flags), @@ -598,6 +610,52 @@ DEFINE_EVENT(writeback_single_inode_template, writeback_single_inode, TP_ARGS(inode, wbc, nr_to_write) ); +DECLARE_EVENT_CLASS(writeback_lazytime_template, + TP_PROTO(struct inode *inode), + + TP_ARGS(inode), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field(unsigned long, ino ) + __field(unsigned long, state ) + __field( __u16, mode ) + __field(unsigned long, dirtied_when ) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->state = inode->i_state; + __entry->mode = inode->i_mode; + __entry->dirtied_when = inode->dirtied_when; + ), + + TP_printk("dev %d,%d ino %lu dirtied %lu state %s mode 0%o", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->ino, __entry->dirtied_when, + show_inode_state(__entry->state), __entry->mode) +); + +DEFINE_EVENT(writeback_lazytime_template, writeback_lazytime, + TP_PROTO(struct inode *inode), + + TP_ARGS(inode) +); + +DEFINE_EVENT(writeback_lazytime_template, writeback_lazytime_iput, + TP_PROTO(struct inode *inode), + + TP_ARGS(inode) +); + +DEFINE_EVENT(writeback_lazytime_template, writeback_dirty_inode_enqueue, + + TP_PROTO(struct inode *inode), + + TP_ARGS(inode) +); + #endif /* _TRACE_WRITEBACK_H */ /* This part must be outside protection */ diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 3735fa0a6784..9b964a5920af 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -90,6 +90,7 @@ struct inodes_stat_t { #define MS_KERNMOUNT (1<<22) /* this is a kern_mount call */ #define MS_I_VERSION (1<<23) /* Update inode I_version field */ #define MS_STRICTATIME (1<<24) /* Always perform atime updates */ +#define MS_LAZYTIME (1<<25) /* Update the on-disk [acm]times lazily */ /* These sb flags are internal to the kernel */ #define MS_NOSEC (1<<28) @@ -100,7 +101,8 @@ struct inodes_stat_t { /* * Superblock flags that can be altered by MS_REMOUNT */ -#define MS_RMT_MASK (MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_I_VERSION) +#define MS_RMT_MASK (MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_I_VERSION|\ + MS_LAZYTIME) /* * Old magic mount flag and mask diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 0ae0df55000b..915feea94c66 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -69,10 +69,10 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v) unsigned long background_thresh; unsigned long dirty_thresh; unsigned long bdi_thresh; - unsigned long nr_dirty, nr_io, nr_more_io; + unsigned long nr_dirty, nr_io, nr_more_io, nr_dirty_time; struct inode *inode; - nr_dirty = nr_io = nr_more_io = 0; + nr_dirty = nr_io = nr_more_io = nr_dirty_time = 0; spin_lock(&wb->list_lock); list_for_each_entry(inode, &wb->b_dirty, i_wb_list) nr_dirty++; @@ -80,6 +80,9 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v) nr_io++; list_for_each_entry(inode, &wb->b_more_io, i_wb_list) nr_more_io++; + list_for_each_entry(inode, &wb->b_dirty_time, i_wb_list) + if (inode->i_state & I_DIRTY_TIME) + nr_dirty_time++; spin_unlock(&wb->list_lock); global_dirty_limits(&background_thresh, &dirty_thresh); @@ -98,6 +101,7 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v) "b_dirty: %10lu\n" "b_io: %10lu\n" "b_more_io: %10lu\n" + "b_dirty_time: %10lu\n" "bdi_list: %10u\n" "state: %10lx\n", (unsigned long) K(bdi_stat(bdi, BDI_WRITEBACK)), @@ -111,6 +115,7 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v) nr_dirty, nr_io, nr_more_io, + nr_dirty_time, !list_empty(&bdi->bdi_list), bdi->state); #undef K @@ -418,6 +423,7 @@ static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi) INIT_LIST_HEAD(&wb->b_dirty); INIT_LIST_HEAD(&wb->b_io); INIT_LIST_HEAD(&wb->b_more_io); + INIT_LIST_HEAD(&wb->b_dirty_time); spin_lock_init(&wb->list_lock); INIT_DELAYED_WORK(&wb->dwork, bdi_writeback_workfn); } -- cgit v1.2.3 From 692132b5b1c5ce97076915d4aed0c61513e18b03 Mon Sep 17 00:00:00 2001 From: Niklas Cassel Date: Mon, 2 Feb 2015 23:19:20 +0100 Subject: serial: driver for ETRAX FS UART This is the last missing piece to get a kernel booting to a prompt in qemu-cris. Signed-off-by: Niklas Cassel Acked-by: Jesper Nilsson Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/Kconfig | 10 + drivers/tty/serial/Makefile | 1 + drivers/tty/serial/etraxfs-uart.c | 996 ++++++++++++++++++++++++++++++++++++++ include/uapi/linux/serial_core.h | 3 + 4 files changed, 1010 insertions(+) create mode 100644 drivers/tty/serial/etraxfs-uart.c (limited to 'include/uapi/linux') diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index ddcc0a4c659c..5d916c7a216b 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -1085,6 +1085,16 @@ config SERIAL_VT8500_CONSOLE depends on SERIAL_VT8500=y select SERIAL_CORE_CONSOLE +config SERIAL_ETRAXFS + bool "ETRAX FS serial port support" + depends on ETRAX_ARCH_V32 && OF + select SERIAL_CORE + +config SERIAL_ETRAXFS_CONSOLE + bool "ETRAX FS serial console support" + depends on SERIAL_ETRAXFS + select SERIAL_CORE_CONSOLE + config SERIAL_NETX tristate "NetX serial port support" depends on ARCH_NETX diff --git a/drivers/tty/serial/Makefile b/drivers/tty/serial/Makefile index 431879003ccd..599be4b05a26 100644 --- a/drivers/tty/serial/Makefile +++ b/drivers/tty/serial/Makefile @@ -51,6 +51,7 @@ obj-$(CONFIG_SERIAL_MPSC) += mpsc.o obj-$(CONFIG_SERIAL_MESON) += meson_uart.o obj-$(CONFIG_SERIAL_SB1250_DUART) += sb1250-duart.o obj-$(CONFIG_ETRAX_SERIAL) += crisv10.o +obj-$(CONFIG_SERIAL_ETRAXFS) += etraxfs-uart.o obj-$(CONFIG_SERIAL_SCCNXP) += sccnxp.o obj-$(CONFIG_SERIAL_SC16IS7XX) += sc16is7xx.o obj-$(CONFIG_SERIAL_JSM) += jsm/ diff --git a/drivers/tty/serial/etraxfs-uart.c b/drivers/tty/serial/etraxfs-uart.c new file mode 100644 index 000000000000..a57301a6fe42 --- /dev/null +++ b/drivers/tty/serial/etraxfs-uart.c @@ -0,0 +1,996 @@ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define DRV_NAME "etraxfs-uart" +#define UART_NR CONFIG_ETRAX_SERIAL_PORTS + +#define MODIFY_REG(instance, reg, var) \ + do { \ + if (REG_RD_INT(ser, instance, reg) != \ + REG_TYPE_CONV(int, reg_ser_##reg, var)) \ + REG_WR(ser, instance, reg, var); \ + } while (0) + +struct uart_cris_port { + struct uart_port port; + + int initialized; + int irq; + + void __iomem *regi_ser; + + struct gpio_desc *dtr_pin; + struct gpio_desc *dsr_pin; + struct gpio_desc *ri_pin; + struct gpio_desc *cd_pin; + + int write_ongoing; +}; + +static struct uart_driver etraxfs_uart_driver; +static struct uart_port *console_port; +static int console_baud = 115200; +static struct uart_cris_port *etraxfs_uart_ports[UART_NR]; + +static void cris_serial_port_init(struct uart_port *port, int line); +static void etraxfs_uart_stop_rx(struct uart_port *port); +static inline void etraxfs_uart_start_tx_bottom(struct uart_port *port); + +#ifdef CONFIG_SERIAL_ETRAXFS_CONSOLE +static void +cris_console_write(struct console *co, const char *s, unsigned int count) +{ + struct uart_cris_port *up; + int i; + reg_ser_r_stat_din stat; + reg_ser_rw_tr_dma_en tr_dma_en, old; + + up = etraxfs_uart_ports[co->index]; + + if (!up) + return; + + /* Switch to manual mode. */ + tr_dma_en = old = REG_RD(ser, up->regi_ser, rw_tr_dma_en); + if (tr_dma_en.en == regk_ser_yes) { + tr_dma_en.en = regk_ser_no; + REG_WR(ser, up->regi_ser, rw_tr_dma_en, tr_dma_en); + } + + /* Send data. */ + for (i = 0; i < count; i++) { + /* LF -> CRLF */ + if (s[i] == '\n') { + do { + stat = REG_RD(ser, up->regi_ser, r_stat_din); + } while (!stat.tr_rdy); + REG_WR_INT(ser, up->regi_ser, rw_dout, '\r'); + } + /* Wait until transmitter is ready and send. */ + do { + stat = REG_RD(ser, up->regi_ser, r_stat_din); + } while (!stat.tr_rdy); + REG_WR_INT(ser, up->regi_ser, rw_dout, s[i]); + } + + /* Restore mode. */ + if (tr_dma_en.en != old.en) + REG_WR(ser, up->regi_ser, rw_tr_dma_en, old); +} + +static int __init +cris_console_setup(struct console *co, char *options) +{ + struct uart_port *port; + int baud = 115200; + int bits = 8; + int parity = 'n'; + int flow = 'n'; + + if (co->index < 0 || co->index >= UART_NR) + co->index = 0; + port = &etraxfs_uart_ports[co->index]->port; + console_port = port; + + co->flags |= CON_CONSDEV; + + if (options) + uart_parse_options(options, &baud, &parity, &bits, &flow); + console_baud = baud; + cris_serial_port_init(port, co->index); + uart_set_options(port, co, baud, parity, bits, flow); + + return 0; +} + +static struct tty_driver *cris_console_device(struct console *co, int *index) +{ + struct uart_driver *p = co->data; + *index = co->index; + return p->tty_driver; +} + +static struct console cris_console = { + .name = "ttyS", + .write = cris_console_write, + .device = cris_console_device, + .setup = cris_console_setup, + .flags = CON_PRINTBUFFER, + .index = -1, + .data = &etraxfs_uart_driver, +}; +#endif /* CONFIG_SERIAL_ETRAXFS_CONSOLE */ + +static struct uart_driver etraxfs_uart_driver = { + .owner = THIS_MODULE, + .driver_name = "serial", + .dev_name = "ttyS", + .major = TTY_MAJOR, + .minor = 64, + .nr = UART_NR, +#ifdef CONFIG_SERIAL_ETRAXFS_CONSOLE + .cons = &cris_console, +#endif /* CONFIG_SERIAL_ETRAXFS_CONSOLE */ +}; + +static inline int crisv32_serial_get_rts(struct uart_cris_port *up) +{ + void __iomem *regi_ser = up->regi_ser; + /* + * Return what the user has controlled rts to or + * what the pin is? (if auto_rts is used it differs during tx) + */ + reg_ser_r_stat_din rstat = REG_RD(ser, regi_ser, r_stat_din); + + return !(rstat.rts_n == regk_ser_active); +} + +/* + * A set = 0 means 3.3V on the pin, bitvalue: 0=active, 1=inactive + * 0=0V , 1=3.3V + */ +static inline void crisv32_serial_set_rts(struct uart_cris_port *up, + int set, int force) +{ + void __iomem *regi_ser = up->regi_ser; + + unsigned long flags; + reg_ser_rw_rec_ctrl rec_ctrl; + + local_irq_save(flags); + rec_ctrl = REG_RD(ser, regi_ser, rw_rec_ctrl); + + if (set) + rec_ctrl.rts_n = regk_ser_active; + else + rec_ctrl.rts_n = regk_ser_inactive; + REG_WR(ser, regi_ser, rw_rec_ctrl, rec_ctrl); + local_irq_restore(flags); +} + +static inline int crisv32_serial_get_cts(struct uart_cris_port *up) +{ + void __iomem *regi_ser = up->regi_ser; + reg_ser_r_stat_din rstat = REG_RD(ser, regi_ser, r_stat_din); + + return (rstat.cts_n == regk_ser_active); +} + +/* + * Send a single character for XON/XOFF purposes. We do it in this separate + * function instead of the alternative support port.x_char, in the ...start_tx + * function, so we don't mix up this case with possibly enabling transmission + * of queued-up data (in case that's disabled after *receiving* an XOFF or + * negative CTS). This function is used for both DMA and non-DMA case; see HW + * docs specifically blessing sending characters manually when DMA for + * transmission is enabled and running. We may be asked to transmit despite + * the transmitter being disabled by a ..._stop_tx call so we need to enable + * it temporarily but restore the state afterwards. + */ +static void etraxfs_uart_send_xchar(struct uart_port *port, char ch) +{ + struct uart_cris_port *up = (struct uart_cris_port *)port; + reg_ser_rw_dout dout = { .data = ch }; + reg_ser_rw_ack_intr ack_intr = { .tr_rdy = regk_ser_yes }; + reg_ser_r_stat_din rstat; + reg_ser_rw_tr_ctrl prev_tr_ctrl, tr_ctrl; + void __iomem *regi_ser = up->regi_ser; + unsigned long flags; + + /* + * Wait for tr_rdy in case a character is already being output. Make + * sure we have integrity between the register reads and the writes + * below, but don't busy-wait with interrupts off and the port lock + * taken. + */ + spin_lock_irqsave(&port->lock, flags); + do { + spin_unlock_irqrestore(&port->lock, flags); + spin_lock_irqsave(&port->lock, flags); + prev_tr_ctrl = tr_ctrl = REG_RD(ser, regi_ser, rw_tr_ctrl); + rstat = REG_RD(ser, regi_ser, r_stat_din); + } while (!rstat.tr_rdy); + + /* + * Ack an interrupt if one was just issued for the previous character + * that was output. This is required for non-DMA as the interrupt is + * used as the only indicator that the transmitter is ready and it + * isn't while this x_char is being transmitted. + */ + REG_WR(ser, regi_ser, rw_ack_intr, ack_intr); + + /* Enable the transmitter in case it was disabled. */ + tr_ctrl.stop = 0; + REG_WR(ser, regi_ser, rw_tr_ctrl, tr_ctrl); + + /* + * Finally, send the blessed character; nothing should stop it now, + * except for an xoff-detected state, which we'll handle below. + */ + REG_WR(ser, regi_ser, rw_dout, dout); + up->port.icount.tx++; + + /* There might be an xoff state to clear. */ + rstat = REG_RD(ser, up->regi_ser, r_stat_din); + + /* + * Clear any xoff state that *may* have been there to + * inhibit transmission of the character. + */ + if (rstat.xoff_detect) { + reg_ser_rw_xoff_clr xoff_clr = { .clr = 1 }; + reg_ser_rw_tr_dma_en tr_dma_en; + + REG_WR(ser, regi_ser, rw_xoff_clr, xoff_clr); + tr_dma_en = REG_RD(ser, regi_ser, rw_tr_dma_en); + + /* + * If we had an xoff state but cleared it, instead sneak in a + * disabled state for the transmitter, after the character we + * sent. Thus we keep the port disabled, just as if the xoff + * state was still in effect (or actually, as if stop_tx had + * been called, as we stop DMA too). + */ + prev_tr_ctrl.stop = 1; + + tr_dma_en.en = 0; + REG_WR(ser, regi_ser, rw_tr_dma_en, tr_dma_en); + } + + /* Restore "previous" enabled/disabled state of the transmitter. */ + REG_WR(ser, regi_ser, rw_tr_ctrl, prev_tr_ctrl); + + spin_unlock_irqrestore(&port->lock, flags); +} + +/* + * Do not spin_lock_irqsave or disable interrupts by other means here; it's + * already done by the caller. + */ +static void etraxfs_uart_start_tx(struct uart_port *port) +{ + struct uart_cris_port *up = (struct uart_cris_port *)port; + + /* we have already done below if a write is ongoing */ + if (up->write_ongoing) + return; + + /* Signal that write is ongoing */ + up->write_ongoing = 1; + + etraxfs_uart_start_tx_bottom(port); +} + +static inline void etraxfs_uart_start_tx_bottom(struct uart_port *port) +{ + struct uart_cris_port *up = (struct uart_cris_port *)port; + void __iomem *regi_ser = up->regi_ser; + reg_ser_rw_tr_ctrl tr_ctrl; + reg_ser_rw_intr_mask intr_mask; + + tr_ctrl = REG_RD(ser, regi_ser, rw_tr_ctrl); + tr_ctrl.stop = regk_ser_no; + REG_WR(ser, regi_ser, rw_tr_ctrl, tr_ctrl); + intr_mask = REG_RD(ser, regi_ser, rw_intr_mask); + intr_mask.tr_rdy = regk_ser_yes; + REG_WR(ser, regi_ser, rw_intr_mask, intr_mask); +} + +/* + * This function handles both the DMA and non-DMA case by ordering the + * transmitter to stop of after the current character. We don't need to wait + * for any such character to be completely transmitted; we do that where it + * matters, like in etraxfs_uart_set_termios. Don't busy-wait here; see + * Documentation/serial/driver: this function is called within + * spin_lock_irq{,save} and thus separate ones would be disastrous (when SMP). + * There's no documented need to set the txd pin to any particular value; + * break setting is controlled solely by etraxfs_uart_break_ctl. + */ +static void etraxfs_uart_stop_tx(struct uart_port *port) +{ + struct uart_cris_port *up = (struct uart_cris_port *)port; + void __iomem *regi_ser = up->regi_ser; + reg_ser_rw_tr_ctrl tr_ctrl; + reg_ser_rw_intr_mask intr_mask; + reg_ser_rw_tr_dma_en tr_dma_en = {0}; + reg_ser_rw_xoff_clr xoff_clr = {0}; + + /* + * For the non-DMA case, we'd get a tr_rdy interrupt that we're not + * interested in as we're not transmitting any characters. For the + * DMA case, that interrupt is already turned off, but no reason to + * waste code on conditionals here. + */ + intr_mask = REG_RD(ser, regi_ser, rw_intr_mask); + intr_mask.tr_rdy = regk_ser_no; + REG_WR(ser, regi_ser, rw_intr_mask, intr_mask); + + tr_ctrl = REG_RD(ser, regi_ser, rw_tr_ctrl); + tr_ctrl.stop = 1; + REG_WR(ser, regi_ser, rw_tr_ctrl, tr_ctrl); + + /* + * Always clear possible hardware xoff-detected state here, no need to + * unnecessary consider mctrl settings and when they change. We clear + * it here rather than in start_tx: both functions are called as the + * effect of XOFF processing, but start_tx is also called when upper + * levels tell the driver that there are more characters to send, so + * avoid adding code there. + */ + xoff_clr.clr = 1; + REG_WR(ser, regi_ser, rw_xoff_clr, xoff_clr); + + /* + * Disable transmitter DMA, so that if we're in XON/XOFF, we can send + * those single characters without also giving go-ahead for queued up + * DMA data. + */ + tr_dma_en.en = 0; + REG_WR(ser, regi_ser, rw_tr_dma_en, tr_dma_en); + + /* + * Make sure that write_ongoing is reset when stopping tx. + */ + up->write_ongoing = 0; +} + +static void etraxfs_uart_stop_rx(struct uart_port *port) +{ + struct uart_cris_port *up = (struct uart_cris_port *)port; + void __iomem *regi_ser = up->regi_ser; + reg_ser_rw_rec_ctrl rec_ctrl = REG_RD(ser, regi_ser, rw_rec_ctrl); + + rec_ctrl.en = regk_ser_no; + REG_WR(ser, regi_ser, rw_rec_ctrl, rec_ctrl); +} + +static void etraxfs_uart_enable_ms(struct uart_port *port) +{ +} + +static void check_modem_status(struct uart_cris_port *up) +{ +} + +static unsigned int etraxfs_uart_tx_empty(struct uart_port *port) +{ + struct uart_cris_port *up = (struct uart_cris_port *)port; + unsigned long flags; + unsigned int ret; + reg_ser_r_stat_din rstat = {0}; + + spin_lock_irqsave(&up->port.lock, flags); + + rstat = REG_RD(ser, up->regi_ser, r_stat_din); + ret = rstat.tr_empty ? TIOCSER_TEMT : 0; + + spin_unlock_irqrestore(&up->port.lock, flags); + return ret; +} +static unsigned int etraxfs_uart_get_mctrl(struct uart_port *port) +{ + struct uart_cris_port *up = (struct uart_cris_port *)port; + unsigned int ret; + + ret = 0; + if (crisv32_serial_get_rts(up)) + ret |= TIOCM_RTS; + /* DTR is active low */ + if (up->dtr_pin && !gpiod_get_raw_value(up->dtr_pin)) + ret |= TIOCM_DTR; + /* CD is active low */ + if (up->cd_pin && !gpiod_get_raw_value(up->cd_pin)) + ret |= TIOCM_CD; + /* RI is active low */ + if (up->ri_pin && !gpiod_get_raw_value(up->ri_pin)) + ret |= TIOCM_RI; + /* DSR is active low */ + if (up->dsr_pin && !gpiod_get_raw_value(up->dsr_pin)) + ret |= TIOCM_DSR; + if (crisv32_serial_get_cts(up)) + ret |= TIOCM_CTS; + return ret; +} + +static void etraxfs_uart_set_mctrl(struct uart_port *port, unsigned int mctrl) +{ + struct uart_cris_port *up = (struct uart_cris_port *)port; + + crisv32_serial_set_rts(up, mctrl & TIOCM_RTS ? 1 : 0, 0); + /* DTR is active low */ + if (up->dtr_pin) + gpiod_set_raw_value(up->dtr_pin, mctrl & TIOCM_DTR ? 0 : 1); + /* RI is active low */ + if (up->ri_pin) + gpiod_set_raw_value(up->ri_pin, mctrl & TIOCM_RNG ? 0 : 1); + /* CD is active low */ + if (up->cd_pin) + gpiod_set_raw_value(up->cd_pin, mctrl & TIOCM_CD ? 0 : 1); +} + +static void etraxfs_uart_break_ctl(struct uart_port *port, int break_state) +{ + struct uart_cris_port *up = (struct uart_cris_port *)port; + unsigned long flags; + reg_ser_rw_tr_ctrl tr_ctrl; + reg_ser_rw_tr_dma_en tr_dma_en; + reg_ser_rw_intr_mask intr_mask; + + spin_lock_irqsave(&up->port.lock, flags); + tr_ctrl = REG_RD(ser, up->regi_ser, rw_tr_ctrl); + tr_dma_en = REG_RD(ser, up->regi_ser, rw_tr_dma_en); + intr_mask = REG_RD(ser, up->regi_ser, rw_intr_mask); + + if (break_state != 0) { /* Send break */ + /* + * We need to disable DMA (if used) or tr_rdy interrupts if no + * DMA. No need to make this conditional on use of DMA; + * disabling will be a no-op for the other mode. + */ + intr_mask.tr_rdy = regk_ser_no; + tr_dma_en.en = 0; + + /* + * Stop transmission and set the txd pin to 0 after the + * current character. The txd setting will take effect after + * any current transmission has completed. + */ + tr_ctrl.stop = 1; + tr_ctrl.txd = 0; + } else { + /* Re-enable the serial interrupt. */ + intr_mask.tr_rdy = regk_ser_yes; + + tr_ctrl.stop = 0; + tr_ctrl.txd = 1; + } + REG_WR(ser, up->regi_ser, rw_tr_ctrl, tr_ctrl); + REG_WR(ser, up->regi_ser, rw_tr_dma_en, tr_dma_en); + REG_WR(ser, up->regi_ser, rw_intr_mask, intr_mask); + + spin_unlock_irqrestore(&up->port.lock, flags); +} + +static void +transmit_chars_no_dma(struct uart_cris_port *up) +{ + int max_count; + struct circ_buf *xmit = &up->port.state->xmit; + + void __iomem *regi_ser = up->regi_ser; + reg_ser_r_stat_din rstat; + reg_ser_rw_ack_intr ack_intr = { .tr_rdy = regk_ser_yes }; + + if (uart_circ_empty(xmit) || uart_tx_stopped(&up->port)) { + /* No more to send, so disable the interrupt. */ + reg_ser_rw_intr_mask intr_mask; + + intr_mask = REG_RD(ser, regi_ser, rw_intr_mask); + intr_mask.tr_rdy = 0; + intr_mask.tr_empty = 0; + REG_WR(ser, regi_ser, rw_intr_mask, intr_mask); + up->write_ongoing = 0; + return; + } + + /* If the serport is fast, we send up to max_count bytes before + exiting the loop. */ + max_count = 64; + do { + reg_ser_rw_dout dout = { .data = xmit->buf[xmit->tail] }; + + REG_WR(ser, regi_ser, rw_dout, dout); + REG_WR(ser, regi_ser, rw_ack_intr, ack_intr); + xmit->tail = (xmit->tail + 1) & (UART_XMIT_SIZE-1); + up->port.icount.tx++; + if (xmit->head == xmit->tail) + break; + rstat = REG_RD(ser, regi_ser, r_stat_din); + } while ((--max_count > 0) && rstat.tr_rdy); + + if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS) + uart_write_wakeup(&up->port); +} + +static void receive_chars_no_dma(struct uart_cris_port *up) +{ + reg_ser_rs_stat_din stat_din; + reg_ser_r_stat_din rstat; + struct tty_port *port; + struct uart_icount *icount; + int max_count = 16; + char flag; + reg_ser_rw_ack_intr ack_intr = { 0 }; + + rstat = REG_RD(ser, up->regi_ser, r_stat_din); + icount = &up->port.icount; + port = &up->port.state->port; + + do { + stat_din = REG_RD(ser, up->regi_ser, rs_stat_din); + + flag = TTY_NORMAL; + ack_intr.dav = 1; + REG_WR(ser, up->regi_ser, rw_ack_intr, ack_intr); + icount->rx++; + + if (stat_din.framing_err | stat_din.par_err | stat_din.orun) { + if (stat_din.data == 0x00 && + stat_din.framing_err) { + /* Most likely a break. */ + flag = TTY_BREAK; + icount->brk++; + } else if (stat_din.par_err) { + flag = TTY_PARITY; + icount->parity++; + } else if (stat_din.orun) { + flag = TTY_OVERRUN; + icount->overrun++; + } else if (stat_din.framing_err) { + flag = TTY_FRAME; + icount->frame++; + } + } + + /* + * If this becomes important, we probably *could* handle this + * gracefully by keeping track of the unhandled character. + */ + if (!tty_insert_flip_char(port, stat_din.data, flag)) + panic("%s: No tty buffer space", __func__); + rstat = REG_RD(ser, up->regi_ser, r_stat_din); + } while (rstat.dav && (max_count-- > 0)); + spin_unlock(&up->port.lock); + tty_flip_buffer_push(port); + spin_lock(&up->port.lock); +} + +static irqreturn_t +ser_interrupt(int irq, void *dev_id) +{ + struct uart_cris_port *up = (struct uart_cris_port *)dev_id; + void __iomem *regi_ser; + int handled = 0; + + spin_lock(&up->port.lock); + + regi_ser = up->regi_ser; + + if (regi_ser) { + reg_ser_r_masked_intr masked_intr; + + masked_intr = REG_RD(ser, regi_ser, r_masked_intr); + /* + * Check what interrupts are active before taking + * actions. If DMA is used the interrupt shouldn't + * be enabled. + */ + if (masked_intr.dav) { + receive_chars_no_dma(up); + handled = 1; + } + check_modem_status(up); + + if (masked_intr.tr_rdy) { + transmit_chars_no_dma(up); + handled = 1; + } + } + spin_unlock(&up->port.lock); + return IRQ_RETVAL(handled); +} + +#ifdef CONFIG_CONSOLE_POLL +static int etraxfs_uart_get_poll_char(struct uart_port *port) +{ + reg_ser_rs_stat_din stat; + reg_ser_rw_ack_intr ack_intr = { 0 }; + struct uart_cris_port *up = (struct uart_cris_port *)port; + + do { + stat = REG_RD(ser, up->regi_ser, rs_stat_din); + } while (!stat.dav); + + /* Ack the data_avail interrupt. */ + ack_intr.dav = 1; + REG_WR(ser, up->regi_ser, rw_ack_intr, ack_intr); + + return stat.data; +} + +static void etraxfs_uart_put_poll_char(struct uart_port *port, + unsigned char c) +{ + reg_ser_r_stat_din stat; + struct uart_cris_port *up = (struct uart_cris_port *)port; + + do { + stat = REG_RD(ser, up->regi_ser, r_stat_din); + } while (!stat.tr_rdy); + REG_WR_INT(ser, up->regi_ser, rw_dout, c); +} +#endif /* CONFIG_CONSOLE_POLL */ + +static int etraxfs_uart_startup(struct uart_port *port) +{ + struct uart_cris_port *up = (struct uart_cris_port *)port; + unsigned long flags; + reg_ser_rw_intr_mask ser_intr_mask = {0}; + + ser_intr_mask.dav = regk_ser_yes; + + if (request_irq(etraxfs_uart_ports[port->line]->irq, ser_interrupt, + 0, DRV_NAME, etraxfs_uart_ports[port->line])) + panic("irq ser%d", port->line); + + spin_lock_irqsave(&up->port.lock, flags); + + REG_WR(ser, up->regi_ser, rw_intr_mask, ser_intr_mask); + + etraxfs_uart_set_mctrl(&up->port, up->port.mctrl); + + spin_unlock_irqrestore(&up->port.lock, flags); + + return 0; +} + +static void etraxfs_uart_shutdown(struct uart_port *port) +{ + struct uart_cris_port *up = (struct uart_cris_port *)port; + unsigned long flags; + + spin_lock_irqsave(&up->port.lock, flags); + + etraxfs_uart_stop_tx(port); + etraxfs_uart_stop_rx(port); + + free_irq(etraxfs_uart_ports[port->line]->irq, + etraxfs_uart_ports[port->line]); + + etraxfs_uart_set_mctrl(&up->port, up->port.mctrl); + + spin_unlock_irqrestore(&up->port.lock, flags); + +} + +static void +etraxfs_uart_set_termios(struct uart_port *port, struct ktermios *termios, + struct ktermios *old) +{ + struct uart_cris_port *up = (struct uart_cris_port *)port; + unsigned long flags; + reg_ser_rw_xoff xoff; + reg_ser_rw_xoff_clr xoff_clr = {0}; + reg_ser_rw_tr_ctrl tx_ctrl = {0}; + reg_ser_rw_tr_dma_en tx_dma_en = {0}; + reg_ser_rw_rec_ctrl rx_ctrl = {0}; + reg_ser_rw_tr_baud_div tx_baud_div = {0}; + reg_ser_rw_rec_baud_div rx_baud_div = {0}; + int baud; + + if (old && + termios->c_cflag == old->c_cflag && + termios->c_iflag == old->c_iflag) + return; + + /* Tx: 8 bit, no/even parity, 1 stop bit, no cts. */ + tx_ctrl.base_freq = regk_ser_f29_493; + tx_ctrl.en = 0; + tx_ctrl.stop = 0; + tx_ctrl.auto_rts = regk_ser_no; + tx_ctrl.txd = 1; + tx_ctrl.auto_cts = 0; + /* Rx: 8 bit, no/even parity. */ + rx_ctrl.dma_err = regk_ser_stop; + rx_ctrl.sampling = regk_ser_majority; + rx_ctrl.timeout = 1; + + rx_ctrl.rts_n = regk_ser_inactive; + + /* Common for tx and rx: 8N1. */ + tx_ctrl.data_bits = regk_ser_bits8; + rx_ctrl.data_bits = regk_ser_bits8; + tx_ctrl.par = regk_ser_even; + rx_ctrl.par = regk_ser_even; + tx_ctrl.par_en = regk_ser_no; + rx_ctrl.par_en = regk_ser_no; + + tx_ctrl.stop_bits = regk_ser_bits1; + + /* + * Change baud-rate and write it to the hardware. + * + * baud_clock = base_freq / (divisor*8) + * divisor = base_freq / (baud_clock * 8) + * base_freq is either: + * off, ext, 29.493MHz, 32.000 MHz, 32.768 MHz or 100 MHz + * 20.493MHz is used for standard baudrates + */ + + /* + * For the console port we keep the original baudrate here. Not very + * beautiful. + */ + if ((port != console_port) || old) + baud = uart_get_baud_rate(port, termios, old, 0, + port->uartclk / 8); + else + baud = console_baud; + + tx_baud_div.div = 29493000 / (8 * baud); + /* Rx uses same as tx. */ + rx_baud_div.div = tx_baud_div.div; + rx_ctrl.base_freq = tx_ctrl.base_freq; + + if ((termios->c_cflag & CSIZE) == CS7) { + /* Set 7 bit mode. */ + tx_ctrl.data_bits = regk_ser_bits7; + rx_ctrl.data_bits = regk_ser_bits7; + } + + if (termios->c_cflag & CSTOPB) { + /* Set 2 stop bit mode. */ + tx_ctrl.stop_bits = regk_ser_bits2; + } + + if (termios->c_cflag & PARENB) { + /* Enable parity. */ + tx_ctrl.par_en = regk_ser_yes; + rx_ctrl.par_en = regk_ser_yes; + } + + if (termios->c_cflag & CMSPAR) { + if (termios->c_cflag & PARODD) { + /* Set mark parity if PARODD and CMSPAR. */ + tx_ctrl.par = regk_ser_mark; + rx_ctrl.par = regk_ser_mark; + } else { + tx_ctrl.par = regk_ser_space; + rx_ctrl.par = regk_ser_space; + } + } else { + if (termios->c_cflag & PARODD) { + /* Set odd parity. */ + tx_ctrl.par = regk_ser_odd; + rx_ctrl.par = regk_ser_odd; + } + } + + if (termios->c_cflag & CRTSCTS) { + /* Enable automatic CTS handling. */ + tx_ctrl.auto_cts = regk_ser_yes; + } + + /* Make sure the tx and rx are enabled. */ + tx_ctrl.en = regk_ser_yes; + rx_ctrl.en = regk_ser_yes; + + spin_lock_irqsave(&port->lock, flags); + + tx_dma_en.en = 0; + REG_WR(ser, up->regi_ser, rw_tr_dma_en, tx_dma_en); + + /* Actually write the control regs (if modified) to the hardware. */ + uart_update_timeout(port, termios->c_cflag, port->uartclk/8); + MODIFY_REG(up->regi_ser, rw_rec_baud_div, rx_baud_div); + MODIFY_REG(up->regi_ser, rw_rec_ctrl, rx_ctrl); + + MODIFY_REG(up->regi_ser, rw_tr_baud_div, tx_baud_div); + MODIFY_REG(up->regi_ser, rw_tr_ctrl, tx_ctrl); + + tx_dma_en.en = 0; + REG_WR(ser, up->regi_ser, rw_tr_dma_en, tx_dma_en); + + xoff = REG_RD(ser, up->regi_ser, rw_xoff); + + if (up->port.state && up->port.state->port.tty && + (up->port.state->port.tty->termios.c_iflag & IXON)) { + xoff.chr = STOP_CHAR(up->port.state->port.tty); + xoff.automatic = regk_ser_yes; + } else + xoff.automatic = regk_ser_no; + + MODIFY_REG(up->regi_ser, rw_xoff, xoff); + + /* + * Make sure we don't start in an automatically shut-off state due to + * a previous early exit. + */ + xoff_clr.clr = 1; + REG_WR(ser, up->regi_ser, rw_xoff_clr, xoff_clr); + + etraxfs_uart_set_mctrl(&up->port, up->port.mctrl); + spin_unlock_irqrestore(&up->port.lock, flags); +} + +static const char * +etraxfs_uart_type(struct uart_port *port) +{ + return "CRISv32"; +} + +static void etraxfs_uart_release_port(struct uart_port *port) +{ +} + +static int etraxfs_uart_request_port(struct uart_port *port) +{ + return 0; +} + +static void etraxfs_uart_config_port(struct uart_port *port, int flags) +{ + struct uart_cris_port *up = (struct uart_cris_port *)port; + + up->port.type = PORT_CRIS; +} + +static const struct uart_ops etraxfs_uart_pops = { + .tx_empty = etraxfs_uart_tx_empty, + .set_mctrl = etraxfs_uart_set_mctrl, + .get_mctrl = etraxfs_uart_get_mctrl, + .stop_tx = etraxfs_uart_stop_tx, + .start_tx = etraxfs_uart_start_tx, + .send_xchar = etraxfs_uart_send_xchar, + .stop_rx = etraxfs_uart_stop_rx, + .enable_ms = etraxfs_uart_enable_ms, + .break_ctl = etraxfs_uart_break_ctl, + .startup = etraxfs_uart_startup, + .shutdown = etraxfs_uart_shutdown, + .set_termios = etraxfs_uart_set_termios, + .type = etraxfs_uart_type, + .release_port = etraxfs_uart_release_port, + .request_port = etraxfs_uart_request_port, + .config_port = etraxfs_uart_config_port, +#ifdef CONFIG_CONSOLE_POLL + .poll_get_char = etraxfs_uart_get_poll_char, + .poll_put_char = etraxfs_uart_put_poll_char, +#endif +}; + +static void cris_serial_port_init(struct uart_port *port, int line) +{ + struct uart_cris_port *up = (struct uart_cris_port *)port; + + if (up->initialized) + return; + up->initialized = 1; + port->line = line; + spin_lock_init(&port->lock); + port->ops = &etraxfs_uart_pops; + port->irq = up->irq; + port->iobase = (unsigned long) up->regi_ser; + port->uartclk = 29493000; + + /* + * We can't fit any more than 255 here (unsigned char), though + * actually UART_XMIT_SIZE characters could be pending output. + * At time of this writing, the definition of "fifosize" is here the + * amount of characters that can be pending output after a start_tx call + * until tx_empty returns 1: see serial_core.c:uart_wait_until_sent. + * This matters for timeout calculations unfortunately, but keeping + * larger amounts at the DMA wouldn't win much so let's just play nice. + */ + port->fifosize = 255; + port->flags = UPF_BOOT_AUTOCONF; +} + +static int etraxfs_uart_probe(struct platform_device *pdev) +{ + struct device_node *np = pdev->dev.of_node; + struct uart_cris_port *up; + int dev_id; + + if (!np) + return -ENODEV; + + dev_id = of_alias_get_id(np, "serial"); + if (dev_id < 0) + dev_id = 0; + + if (dev_id >= UART_NR) + return -EINVAL; + + if (etraxfs_uart_ports[dev_id]) + return -EBUSY; + + up = devm_kzalloc(&pdev->dev, sizeof(struct uart_cris_port), + GFP_KERNEL); + if (!up) + return -ENOMEM; + + up->irq = irq_of_parse_and_map(np, 0); + up->regi_ser = of_iomap(np, 0); + up->dtr_pin = devm_gpiod_get_optional(&pdev->dev, "dtr"); + up->dsr_pin = devm_gpiod_get_optional(&pdev->dev, "dsr"); + up->ri_pin = devm_gpiod_get_optional(&pdev->dev, "ri"); + up->cd_pin = devm_gpiod_get_optional(&pdev->dev, "cd"); + up->port.dev = &pdev->dev; + cris_serial_port_init(&up->port, dev_id); + + etraxfs_uart_ports[dev_id] = up; + platform_set_drvdata(pdev, &up->port); + uart_add_one_port(&etraxfs_uart_driver, &up->port); + + return 0; +} + +static int etraxfs_uart_remove(struct platform_device *pdev) +{ + struct uart_port *port; + + port = platform_get_drvdata(pdev); + uart_remove_one_port(&etraxfs_uart_driver, port); + etraxfs_uart_ports[pdev->id] = NULL; + + return 0; +} + +static const struct of_device_id etraxfs_uart_dt_ids[] = { + { .compatible = "axis,etraxfs-uart" }, + { /* sentinel */ } +}; + +MODULE_DEVICE_TABLE(of, etraxfs_uart_dt_ids); + +static struct platform_driver etraxfs_uart_platform_driver = { + .driver = { + .name = DRV_NAME, + .of_match_table = of_match_ptr(etraxfs_uart_dt_ids), + }, + .probe = etraxfs_uart_probe, + .remove = etraxfs_uart_remove, +}; + +static int __init etraxfs_uart_init(void) +{ + int ret; + + ret = uart_register_driver(&etraxfs_uart_driver); + if (ret) + return ret; + + ret = platform_driver_register(&etraxfs_uart_platform_driver); + if (ret) + uart_unregister_driver(&etraxfs_uart_driver); + + return ret; +} + +static void __exit etraxfs_uart_exit(void) +{ + platform_driver_unregister(&etraxfs_uart_platform_driver); + uart_unregister_driver(&etraxfs_uart_driver); +} + +module_init(etraxfs_uart_init); +module_exit(etraxfs_uart_exit); diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h index 55da91e763bb..b2122813f18a 100644 --- a/include/uapi/linux/serial_core.h +++ b/include/uapi/linux/serial_core.h @@ -255,4 +255,7 @@ /* SPRD SERIAL */ #define PORT_SPRD 111 +/* Cris v10 / v32 SoC */ +#define PORT_CRIS 112 + #endif /* _UAPILINUX_SERIAL_CORE_H */ -- cgit v1.2.3 From e5863d9ad754926e7d3f38b43ac8bd48ef73b097 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Wed, 17 Dec 2014 21:08:12 -0500 Subject: dm: allocate requests in target when stacking on blk-mq devices For blk-mq request-based DM the responsibility of allocating a cloned request is transfered from DM core to the target type. Doing so enables the cloned request to be allocated from the appropriate blk-mq request_queue's pool (only the DM target, e.g. multipath, can know which block device to send a given cloned request to). Care was taken to preserve compatibility with old-style block request completion that requires request-based DM _not_ acquire the clone request's queue lock in the completion path. As such, there are now 2 different request-based DM target_type interfaces: 1) the original .map_rq() interface will continue to be used for non-blk-mq devices -- the preallocated clone request is passed in from DM core. 2) a new .clone_and_map_rq() and .release_clone_rq() will be used for blk-mq devices -- blk_get_request() and blk_put_request() are used respectively from these hooks. dm_table_set_type() was updated to detect if the request-based target is being stacked on blk-mq devices, if so DM_TYPE_MQ_REQUEST_BASED is set. DM core disallows switching the DM table's type after it is set. This means that there is no mixing of non-blk-mq and blk-mq devices within the same request-based DM table. [This patch was started by Keith and later heavily modified by Mike] Tested-by: Bart Van Assche Signed-off-by: Keith Busch Signed-off-by: Mike Snitzer --- drivers/md/dm-mpath.c | 51 ++++++++++++++++--- drivers/md/dm-table.c | 34 +++++++++++-- drivers/md/dm-target.c | 15 +++++- drivers/md/dm.c | 114 +++++++++++++++++++++++++++++++----------- drivers/md/dm.h | 8 +-- include/linux/device-mapper.h | 7 +++ include/uapi/linux/dm-ioctl.h | 4 +- 7 files changed, 185 insertions(+), 48 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 2552b88f8953..863fc8c1ac06 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -11,6 +11,7 @@ #include "dm-path-selector.h" #include "dm-uevent.h" +#include #include #include #include @@ -378,12 +379,13 @@ static int __must_push_back(struct multipath *m) /* * Map cloned requests */ -static int multipath_map(struct dm_target *ti, struct request *clone, - union map_info *map_context) +static int __multipath_map(struct dm_target *ti, struct request *clone, + union map_info *map_context, + struct request *rq, struct request **__clone) { struct multipath *m = (struct multipath *) ti->private; int r = DM_MAPIO_REQUEUE; - size_t nr_bytes = blk_rq_bytes(clone); + size_t nr_bytes = clone ? blk_rq_bytes(clone) : blk_rq_bytes(rq); struct pgpath *pgpath; struct block_device *bdev; struct dm_mpath_io *mpio; @@ -416,12 +418,25 @@ static int multipath_map(struct dm_target *ti, struct request *clone, bdev = pgpath->path.dev->bdev; - clone->q = bdev_get_queue(bdev); - clone->rq_disk = bdev->bd_disk; - clone->cmd_flags |= REQ_FAILFAST_TRANSPORT; - spin_unlock_irq(&m->lock); + if (clone) { + /* Old request-based interface: allocated clone is passed in */ + clone->q = bdev_get_queue(bdev); + clone->rq_disk = bdev->bd_disk; + clone->cmd_flags |= REQ_FAILFAST_TRANSPORT; + } else { + /* blk-mq request-based interface */ + *__clone = blk_get_request(bdev_get_queue(bdev), + rq_data_dir(rq), GFP_KERNEL); + if (IS_ERR(*__clone)) + /* ENOMEM, requeue */ + return r; + (*__clone)->bio = (*__clone)->biotail = NULL; + (*__clone)->rq_disk = bdev->bd_disk; + (*__clone)->cmd_flags |= REQ_FAILFAST_TRANSPORT; + } + if (pgpath->pg->ps.type->start_io) pgpath->pg->ps.type->start_io(&pgpath->pg->ps, &pgpath->path, @@ -434,6 +449,24 @@ out_unlock: return r; } +static int multipath_map(struct dm_target *ti, struct request *clone, + union map_info *map_context) +{ + return __multipath_map(ti, clone, map_context, NULL, NULL); +} + +static int multipath_clone_and_map(struct dm_target *ti, struct request *rq, + union map_info *map_context, + struct request **clone) +{ + return __multipath_map(ti, NULL, map_context, rq, clone); +} + +static void multipath_release_clone(struct request *clone) +{ + blk_put_request(clone); +} + /* * If we run out of usable paths, should we queue I/O or error it? */ @@ -1670,11 +1703,13 @@ out: *---------------------------------------------------------------*/ static struct target_type multipath_target = { .name = "multipath", - .version = {1, 7, 0}, + .version = {1, 8, 0}, .module = THIS_MODULE, .ctr = multipath_ctr, .dtr = multipath_dtr, .map_rq = multipath_map, + .clone_and_map_rq = multipath_clone_and_map, + .release_clone_rq = multipath_release_clone, .rq_end_io = multipath_end_io, .presuspend = multipath_presuspend, .postsuspend = multipath_postsuspend, diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 3afae9e062f8..2d7e373955f3 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -827,6 +827,7 @@ static int dm_table_set_type(struct dm_table *t) { unsigned i; unsigned bio_based = 0, request_based = 0, hybrid = 0; + bool use_blk_mq = false; struct dm_target *tgt; struct dm_dev_internal *dd; struct list_head *devices; @@ -872,11 +873,26 @@ static int dm_table_set_type(struct dm_table *t) /* Non-request-stackable devices can't be used for request-based dm */ devices = dm_table_get_devices(t); list_for_each_entry(dd, devices, list) { - if (!blk_queue_stackable(bdev_get_queue(dd->dm_dev->bdev))) { - DMWARN("table load rejected: including" - " non-request-stackable devices"); + struct request_queue *q = bdev_get_queue(dd->dm_dev->bdev); + + if (!blk_queue_stackable(q)) { + DMERR("table load rejected: including" + " non-request-stackable devices"); return -EINVAL; } + + if (q->mq_ops) + use_blk_mq = true; + } + + if (use_blk_mq) { + /* verify _all_ devices in the table are blk-mq devices */ + list_for_each_entry(dd, devices, list) + if (!bdev_get_queue(dd->dm_dev->bdev)->mq_ops) { + DMERR("table load rejected: not all devices" + " are blk-mq request-stackable"); + return -EINVAL; + } } /* @@ -890,7 +906,7 @@ static int dm_table_set_type(struct dm_table *t) return -EINVAL; } - t->type = DM_TYPE_REQUEST_BASED; + t->type = !use_blk_mq ? DM_TYPE_REQUEST_BASED : DM_TYPE_MQ_REQUEST_BASED; return 0; } @@ -907,7 +923,15 @@ struct target_type *dm_table_get_immutable_target_type(struct dm_table *t) bool dm_table_request_based(struct dm_table *t) { - return dm_table_get_type(t) == DM_TYPE_REQUEST_BASED; + unsigned table_type = dm_table_get_type(t); + + return (table_type == DM_TYPE_REQUEST_BASED || + table_type == DM_TYPE_MQ_REQUEST_BASED); +} + +bool dm_table_mq_request_based(struct dm_table *t) +{ + return dm_table_get_type(t) == DM_TYPE_MQ_REQUEST_BASED; } static int dm_table_alloc_md_mempools(struct dm_table *t) diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c index 242e3cec397a..925ec1b15e75 100644 --- a/drivers/md/dm-target.c +++ b/drivers/md/dm-target.c @@ -137,13 +137,26 @@ static int io_err_map_rq(struct dm_target *ti, struct request *clone, return -EIO; } +static int io_err_clone_and_map_rq(struct dm_target *ti, struct request *rq, + union map_info *map_context, + struct request **clone) +{ + return -EIO; +} + +static void io_err_release_clone_rq(struct request *clone) +{ +} + static struct target_type error_target = { .name = "error", - .version = {1, 2, 0}, + .version = {1, 3, 0}, .ctr = io_err_ctr, .dtr = io_err_dtr, .map = io_err_map, .map_rq = io_err_map_rq, + .clone_and_map_rq = io_err_clone_and_map_rq, + .release_clone_rq = io_err_release_clone_rq, }; int __init dm_target_init(void) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index ae1219893948..549b815999a1 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1044,7 +1044,10 @@ static void free_rq_clone(struct request *clone) struct dm_rq_target_io *tio = clone->end_io_data; blk_rq_unprep_clone(clone); - free_clone_request(tio->md, clone); + if (clone->q && clone->q->mq_ops) + tio->ti->type->release_clone_rq(clone); + else + free_clone_request(tio->md, clone); free_rq_tio(tio); } @@ -1086,7 +1089,8 @@ static void dm_unprep_request(struct request *rq) rq->special = NULL; rq->cmd_flags &= ~REQ_DONTPREP; - free_rq_clone(clone); + if (clone) + free_rq_clone(clone); } /* @@ -1185,6 +1189,13 @@ static void dm_softirq_done(struct request *rq) struct dm_rq_target_io *tio = rq->special; struct request *clone = tio->clone; + if (!clone) { + blk_end_request_all(rq, tio->error); + rq_completed(tio->md, rq_data_dir(rq), false); + free_rq_tio(tio); + return; + } + if (rq->cmd_flags & REQ_FAILED) mapped = false; @@ -1207,7 +1218,7 @@ static void dm_complete_request(struct request *rq, int error) * Complete the not-mapped clone and the original request with the error status * through softirq context. * Target's rq_end_io() function isn't called. - * This may be used when the target's map_rq() function fails. + * This may be used when the target's map_rq() or clone_and_map_rq() functions fail. */ static void dm_kill_unmapped_request(struct request *rq, int error) { @@ -1222,13 +1233,15 @@ static void end_clone_request(struct request *clone, int error) { struct dm_rq_target_io *tio = clone->end_io_data; - /* - * For just cleaning up the information of the queue in which - * the clone was dispatched. - * The clone is *NOT* freed actually here because it is alloced from - * dm own mempool and REQ_ALLOCED isn't set in clone->cmd_flags. - */ - __blk_put_request(clone->q, clone); + if (!clone->q->mq_ops) { + /* + * For just cleaning up the information of the queue in which + * the clone was dispatched. + * The clone is *NOT* freed actually here because it is alloced + * from dm own mempool (REQ_ALLOCED isn't set). + */ + __blk_put_request(clone->q, clone); + } /* * Actual request completion is done in a softirq context which doesn't @@ -1789,6 +1802,8 @@ static struct dm_rq_target_io *prep_tio(struct request *rq, struct mapped_device *md, gfp_t gfp_mask) { struct dm_rq_target_io *tio; + int srcu_idx; + struct dm_table *table; tio = alloc_rq_tio(md, gfp_mask); if (!tio) @@ -1802,10 +1817,15 @@ static struct dm_rq_target_io *prep_tio(struct request *rq, memset(&tio->info, 0, sizeof(tio->info)); init_kthread_work(&tio->work, map_tio_request); - if (!clone_rq(rq, md, tio, gfp_mask)) { - free_rq_tio(tio); - return NULL; + table = dm_get_live_table(md, &srcu_idx); + if (!dm_table_mq_request_based(table)) { + if (!clone_rq(rq, md, tio, gfp_mask)) { + dm_put_live_table(md, srcu_idx); + free_rq_tio(tio); + return NULL; + } } + dm_put_live_table(md, srcu_idx); return tio; } @@ -1835,17 +1855,36 @@ static int dm_prep_fn(struct request_queue *q, struct request *rq) /* * Returns: - * 0 : the request has been processed (not requeued) - * !0 : the request has been requeued + * 0 : the request has been processed + * DM_MAPIO_REQUEUE : the original request needs to be requeued + * < 0 : the request was completed due to failure */ static int map_request(struct dm_target *ti, struct request *rq, struct mapped_device *md) { - int r, requeued = 0; + int r; struct dm_rq_target_io *tio = rq->special; - struct request *clone = tio->clone; + struct request *clone = NULL; + + if (tio->clone) { + clone = tio->clone; + r = ti->type->map_rq(ti, clone, &tio->info); + } else { + r = ti->type->clone_and_map_rq(ti, rq, &tio->info, &clone); + if (r < 0) { + /* The target wants to complete the I/O */ + dm_kill_unmapped_request(rq, r); + return r; + } + if (IS_ERR(clone)) + return DM_MAPIO_REQUEUE; + if (setup_clone(clone, rq, tio, GFP_KERNEL)) { + /* -ENOMEM */ + ti->type->release_clone_rq(clone); + return DM_MAPIO_REQUEUE; + } + } - r = ti->type->map_rq(ti, clone, &tio->info); switch (r) { case DM_MAPIO_SUBMITTED: /* The target has taken the I/O to submit by itself later */ @@ -1859,7 +1898,6 @@ static int map_request(struct dm_target *ti, struct request *rq, case DM_MAPIO_REQUEUE: /* The target wants to requeue the I/O */ dm_requeue_unmapped_request(clone); - requeued = 1; break; default: if (r > 0) { @@ -1869,17 +1907,20 @@ static int map_request(struct dm_target *ti, struct request *rq, /* The target wants to complete the I/O */ dm_kill_unmapped_request(rq, r); - break; + return r; } - return requeued; + return 0; } static void map_tio_request(struct kthread_work *work) { struct dm_rq_target_io *tio = container_of(work, struct dm_rq_target_io, work); + struct request *rq = tio->orig; + struct mapped_device *md = tio->md; - map_request(tio->ti, tio->orig, tio->md); + if (map_request(tio->ti, rq, md) == DM_MAPIO_REQUEUE) + dm_requeue_unmapped_original_request(md, rq); } static void dm_start_request(struct mapped_device *md, struct request *orig) @@ -2459,6 +2500,14 @@ unsigned dm_get_md_type(struct mapped_device *md) return md->type; } +static bool dm_md_type_request_based(struct mapped_device *md) +{ + unsigned table_type = dm_get_md_type(md); + + return (table_type == DM_TYPE_REQUEST_BASED || + table_type == DM_TYPE_MQ_REQUEST_BASED); +} + struct target_type *dm_get_immutable_target_type(struct mapped_device *md) { return md->immutable_target_type; @@ -2511,8 +2560,7 @@ static int dm_init_request_based_queue(struct mapped_device *md) */ int dm_setup_md_queue(struct mapped_device *md) { - if ((dm_get_md_type(md) == DM_TYPE_REQUEST_BASED) && - !dm_init_request_based_queue(md)) { + if (dm_md_type_request_based(md) && !dm_init_request_based_queue(md)) { DMWARN("Cannot initialize queue for request-based mapped device"); return -EINVAL; } @@ -3184,27 +3232,35 @@ struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity, u { struct dm_md_mempools *pools = kzalloc(sizeof(*pools), GFP_KERNEL); struct kmem_cache *cachep; - unsigned int pool_size; + unsigned int pool_size = 0; unsigned int front_pad; if (!pools) return NULL; - if (type == DM_TYPE_BIO_BASED) { + switch (type) { + case DM_TYPE_BIO_BASED: cachep = _io_cache; pool_size = dm_get_reserved_bio_based_ios(); front_pad = roundup(per_bio_data_size, __alignof__(struct dm_target_io)) + offsetof(struct dm_target_io, clone); - } else if (type == DM_TYPE_REQUEST_BASED) { - cachep = _rq_tio_cache; + break; + case DM_TYPE_REQUEST_BASED: pool_size = dm_get_reserved_rq_based_ios(); pools->rq_pool = mempool_create_slab_pool(pool_size, _rq_cache); if (!pools->rq_pool) goto out; + /* fall through to setup remaining rq-based pools */ + case DM_TYPE_MQ_REQUEST_BASED: + cachep = _rq_tio_cache; + if (!pool_size) + pool_size = dm_get_reserved_rq_based_ios(); front_pad = offsetof(struct dm_rq_clone_bio_info, clone); /* per_bio_data_size is not used. See __bind_mempools(). */ WARN_ON(per_bio_data_size != 0); - } else + break; + default: goto out; + } pools->io_pool = mempool_create_slab_pool(pool_size, cachep); if (!pools->io_pool) diff --git a/drivers/md/dm.h b/drivers/md/dm.h index 84b0f9e4ba6c..84d79784b866 100644 --- a/drivers/md/dm.h +++ b/drivers/md/dm.h @@ -34,9 +34,10 @@ /* * Type of table and mapped_device's mempool */ -#define DM_TYPE_NONE 0 -#define DM_TYPE_BIO_BASED 1 -#define DM_TYPE_REQUEST_BASED 2 +#define DM_TYPE_NONE 0 +#define DM_TYPE_BIO_BASED 1 +#define DM_TYPE_REQUEST_BASED 2 +#define DM_TYPE_MQ_REQUEST_BASED 3 /* * List of devices that a metadevice uses and should open/close. @@ -73,6 +74,7 @@ int dm_table_any_busy_target(struct dm_table *t); unsigned dm_table_get_type(struct dm_table *t); struct target_type *dm_table_get_immutable_target_type(struct dm_table *t); bool dm_table_request_based(struct dm_table *t); +bool dm_table_mq_request_based(struct dm_table *t); void dm_table_free_md_mempools(struct dm_table *t); struct dm_md_mempools *dm_table_get_md_mempools(struct dm_table *t); diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 19296fba58e8..2646aed1d3fe 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -48,6 +48,11 @@ typedef void (*dm_dtr_fn) (struct dm_target *ti); typedef int (*dm_map_fn) (struct dm_target *ti, struct bio *bio); typedef int (*dm_map_request_fn) (struct dm_target *ti, struct request *clone, union map_info *map_context); +typedef int (*dm_clone_and_map_request_fn) (struct dm_target *ti, + struct request *rq, + union map_info *map_context, + struct request **clone); +typedef void (*dm_release_clone_request_fn) (struct request *clone); /* * Returns: @@ -143,6 +148,8 @@ struct target_type { dm_dtr_fn dtr; dm_map_fn map; dm_map_request_fn map_rq; + dm_clone_and_map_request_fn clone_and_map_rq; + dm_release_clone_request_fn release_clone_rq; dm_endio_fn end_io; dm_request_endio_fn rq_end_io; dm_presuspend_fn presuspend; diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h index a570d7b5796c..889f3a5b7b18 100644 --- a/include/uapi/linux/dm-ioctl.h +++ b/include/uapi/linux/dm-ioctl.h @@ -267,9 +267,9 @@ enum { #define DM_DEV_SET_GEOMETRY _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl) #define DM_VERSION_MAJOR 4 -#define DM_VERSION_MINOR 29 +#define DM_VERSION_MINOR 30 #define DM_VERSION_PATCHLEVEL 0 -#define DM_VERSION_EXTRA "-ioctl (2014-10-28)" +#define DM_VERSION_EXTRA "-ioctl (2014-12-22)" /* Status bits */ #define DM_READONLY_FLAG (1 << 0) /* In/Out */ -- cgit v1.2.3 From 0ace2ca89cbd6bcdf2b9d2df1fa0fa24ea9d1653 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Tue, 10 Feb 2015 16:30:32 -0800 Subject: vxlan: Use checksum partial with remote checksum offload Change remote checksum handling to set checksum partial as default behavior. Added an iflink parameter to configure not using checksum partial (calling csum_partial to update checksum). Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 25 +++++++++++++++++++------ include/net/vxlan.h | 4 +++- include/uapi/linux/if_link.h | 1 + 3 files changed, 23 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 4f04443cfd33..1e0a775ea882 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -555,7 +555,8 @@ static int vxlan_fdb_append(struct vxlan_fdb *f, static struct vxlanhdr *vxlan_gro_remcsum(struct sk_buff *skb, unsigned int off, struct vxlanhdr *vh, size_t hdrlen, - u32 data, struct gro_remcsum *grc) + u32 data, struct gro_remcsum *grc, + bool nopartial) { size_t start, offset, plen; @@ -580,7 +581,7 @@ static struct vxlanhdr *vxlan_gro_remcsum(struct sk_buff *skb, } skb_gro_remcsum_process(skb, (void *)vh + hdrlen, - start, offset, grc, true); + start, offset, grc, nopartial); skb->remcsum_offload = 1; @@ -618,7 +619,9 @@ static struct sk_buff **vxlan_gro_receive(struct sk_buff **head, if ((flags & VXLAN_HF_RCO) && (vs->flags & VXLAN_F_REMCSUM_RX)) { vh = vxlan_gro_remcsum(skb, off_vx, vh, sizeof(struct vxlanhdr), - ntohl(vh->vx_vni), &grc); + ntohl(vh->vx_vni), &grc, + !!(vs->flags & + VXLAN_F_REMCSUM_NOPARTIAL)); if (!vh) goto out; @@ -1155,7 +1158,7 @@ static void vxlan_igmp_leave(struct work_struct *work) } static struct vxlanhdr *vxlan_remcsum(struct sk_buff *skb, struct vxlanhdr *vh, - size_t hdrlen, u32 data) + size_t hdrlen, u32 data, bool nopartial) { size_t start, offset, plen; @@ -1171,7 +1174,8 @@ static struct vxlanhdr *vxlan_remcsum(struct sk_buff *skb, struct vxlanhdr *vh, vh = (struct vxlanhdr *)(udp_hdr(skb) + 1); - skb_remcsum_process(skb, (void *)vh + hdrlen, start, offset, true); + skb_remcsum_process(skb, (void *)vh + hdrlen, start, offset, + nopartial); return vh; } @@ -1208,7 +1212,8 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) goto drop; if ((flags & VXLAN_HF_RCO) && (vs->flags & VXLAN_F_REMCSUM_RX)) { - vxh = vxlan_remcsum(skb, vxh, sizeof(struct vxlanhdr), vni); + vxh = vxlan_remcsum(skb, vxh, sizeof(struct vxlanhdr), vni, + !!(vs->flags & VXLAN_F_REMCSUM_NOPARTIAL)); if (!vxh) goto drop; @@ -2437,6 +2442,7 @@ static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = { [IFLA_VXLAN_REMCSUM_TX] = { .type = NLA_U8 }, [IFLA_VXLAN_REMCSUM_RX] = { .type = NLA_U8 }, [IFLA_VXLAN_GBP] = { .type = NLA_FLAG, }, + [IFLA_VXLAN_REMCSUM_NOPARTIAL] = { .type = NLA_FLAG }, }; static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[]) @@ -2760,6 +2766,9 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev, if (data[IFLA_VXLAN_GBP]) vxlan->flags |= VXLAN_F_GBP; + if (data[IFLA_VXLAN_REMCSUM_NOPARTIAL]) + vxlan->flags |= VXLAN_F_REMCSUM_NOPARTIAL; + if (vxlan_find_vni(src_net, vni, use_ipv6 ? AF_INET6 : AF_INET, vxlan->dst_port, vxlan->flags)) { pr_info("duplicate VNI %u\n", vni); @@ -2909,6 +2918,10 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev) nla_put_flag(skb, IFLA_VXLAN_GBP)) goto nla_put_failure; + if (vxlan->flags & VXLAN_F_REMCSUM_NOPARTIAL && + nla_put_flag(skb, IFLA_VXLAN_REMCSUM_NOPARTIAL)) + goto nla_put_failure; + return 0; nla_put_failure: diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 2927d6244481..eabd3a038674 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -128,13 +128,15 @@ struct vxlan_sock { #define VXLAN_F_REMCSUM_TX 0x200 #define VXLAN_F_REMCSUM_RX 0x400 #define VXLAN_F_GBP 0x800 +#define VXLAN_F_REMCSUM_NOPARTIAL 0x1000 /* Flags that are used in the receive patch. These flags must match in * order for a socket to be shareable */ #define VXLAN_F_RCV_FLAGS (VXLAN_F_GBP | \ VXLAN_F_UDP_ZERO_CSUM6_RX | \ - VXLAN_F_REMCSUM_RX) + VXLAN_F_REMCSUM_RX | \ + VXLAN_F_REMCSUM_NOPARTIAL) struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port, vxlan_rcv_t *rcv, void *data, diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 0deee3eeddbf..dfd0bb22e554 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -374,6 +374,7 @@ enum { IFLA_VXLAN_REMCSUM_TX, IFLA_VXLAN_REMCSUM_RX, IFLA_VXLAN_GBP, + IFLA_VXLAN_REMCSUM_NOPARTIAL, __IFLA_VXLAN_MAX }; #define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1) -- cgit v1.2.3 From fe881ef11cf0220f118816181930494d484c4883 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Tue, 10 Feb 2015 16:30:33 -0800 Subject: gue: Use checksum partial with remote checksum offload Change remote checksum handling to set checksum partial as default behavior. Added an iflink parameter to configure not using checksum partial (calling csum_partial to update checksum). Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/uapi/linux/fou.h | 1 + net/ipv4/fou.c | 28 ++++++++++++++++++++++------ 2 files changed, 23 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/fou.h b/include/uapi/linux/fou.h index 8df06894da23..c303588bb767 100644 --- a/include/uapi/linux/fou.h +++ b/include/uapi/linux/fou.h @@ -14,6 +14,7 @@ enum { FOU_ATTR_AF, /* u8 */ FOU_ATTR_IPPROTO, /* u8 */ FOU_ATTR_TYPE, /* u8 */ + FOU_ATTR_REMCSUM_NOPARTIAL, /* flag */ __FOU_ATTR_MAX, }; diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index d320f575cc62..ff069f6597ac 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -22,14 +22,18 @@ static LIST_HEAD(fou_list); struct fou { struct socket *sock; u8 protocol; + u8 flags; u16 port; struct udp_offload udp_offloads; struct list_head list; }; +#define FOU_F_REMCSUM_NOPARTIAL BIT(0) + struct fou_cfg { u16 type; u8 protocol; + u8 flags; struct udp_port_cfg udp_config; }; @@ -64,7 +68,8 @@ static int fou_udp_recv(struct sock *sk, struct sk_buff *skb) } static struct guehdr *gue_remcsum(struct sk_buff *skb, struct guehdr *guehdr, - void *data, size_t hdrlen, u8 ipproto) + void *data, size_t hdrlen, u8 ipproto, + bool nopartial) { __be16 *pd = data; size_t start = ntohs(pd[0]); @@ -75,7 +80,8 @@ static struct guehdr *gue_remcsum(struct sk_buff *skb, struct guehdr *guehdr, return NULL; guehdr = (struct guehdr *)&udp_hdr(skb)[1]; - skb_remcsum_process(skb, (void *)guehdr + hdrlen, start, offset, true); + skb_remcsum_process(skb, (void *)guehdr + hdrlen, + start, offset, nopartial); return guehdr; } @@ -136,7 +142,9 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb) if (flags & GUE_PFLAG_REMCSUM) { guehdr = gue_remcsum(skb, guehdr, data + doffset, - hdrlen, guehdr->proto_ctype); + hdrlen, guehdr->proto_ctype, + !!(fou->flags & + FOU_F_REMCSUM_NOPARTIAL)); if (!guehdr) goto drop; @@ -209,7 +217,7 @@ out_unlock: static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off, struct guehdr *guehdr, void *data, size_t hdrlen, u8 ipproto, - struct gro_remcsum *grc) + struct gro_remcsum *grc, bool nopartial) { __be16 *pd = data; size_t start = ntohs(pd[0]); @@ -230,7 +238,7 @@ static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off, } skb_gro_remcsum_process(skb, (void *)guehdr + hdrlen, - start, offset, grc, true); + start, offset, grc, nopartial); skb->remcsum_offload = 1; @@ -250,6 +258,7 @@ static struct sk_buff **gue_gro_receive(struct sk_buff **head, void *data; u16 doffset = 0; int flush = 1; + struct fou *fou = container_of(uoff, struct fou, udp_offloads); struct gro_remcsum grc; skb_gro_remcsum_init(&grc); @@ -294,7 +303,9 @@ static struct sk_buff **gue_gro_receive(struct sk_buff **head, if (flags & GUE_PFLAG_REMCSUM) { guehdr = gue_gro_remcsum(skb, off, guehdr, data + doffset, hdrlen, - guehdr->proto_ctype, &grc); + guehdr->proto_ctype, &grc, + !!(fou->flags & + FOU_F_REMCSUM_NOPARTIAL)); if (!guehdr) goto out; @@ -455,6 +466,7 @@ static int fou_create(struct net *net, struct fou_cfg *cfg, sk = sock->sk; + fou->flags = cfg->flags; fou->port = cfg->udp_config.local_udp_port; /* Initial for fou type */ @@ -541,6 +553,7 @@ static struct nla_policy fou_nl_policy[FOU_ATTR_MAX + 1] = { [FOU_ATTR_AF] = { .type = NLA_U8, }, [FOU_ATTR_IPPROTO] = { .type = NLA_U8, }, [FOU_ATTR_TYPE] = { .type = NLA_U8, }, + [FOU_ATTR_REMCSUM_NOPARTIAL] = { .type = NLA_FLAG, }, }; static int parse_nl_config(struct genl_info *info, @@ -571,6 +584,9 @@ static int parse_nl_config(struct genl_info *info, if (info->attrs[FOU_ATTR_TYPE]) cfg->type = nla_get_u8(info->attrs[FOU_ATTR_TYPE]); + if (info->attrs[FOU_ATTR_REMCSUM_NOPARTIAL]) + cfg->flags |= FOU_F_REMCSUM_NOPARTIAL; + return 0; } -- cgit v1.2.3 From 8a0516ed8b90c95ffa1363b420caa37418149f21 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 12 Feb 2015 14:58:22 -0800 Subject: mm: convert p[te|md]_numa users to p[te|md]_protnone_numa Convert existing users of pte_numa and friends to the new helper. Note that the kernel is broken after this patch is applied until the other page table modifiers are also altered. This patch layout is to make review easier. Signed-off-by: Mel Gorman Acked-by: Linus Torvalds Acked-by: Aneesh Kumar Acked-by: Benjamin Herrenschmidt Tested-by: Sasha Levin Cc: Dave Jones Cc: Hugh Dickins Cc: Ingo Molnar Cc: Kirill Shutemov Cc: Paul Mackerras Cc: Rik van Riel Cc: Sasha Levin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/kvm/book3s_hv_rm_mmu.c | 2 +- arch/powerpc/mm/fault.c | 5 ----- arch/powerpc/mm/pgtable.c | 11 ++++++++--- arch/powerpc/mm/pgtable_64.c | 3 ++- arch/x86/mm/gup.c | 4 ++-- include/uapi/linux/mempolicy.h | 2 +- mm/gup.c | 10 +++++----- mm/huge_memory.c | 16 ++++++++-------- mm/memory.c | 4 ++-- mm/mprotect.c | 38 ++++++++++--------------------------- mm/pgtable-generic.c | 2 +- 11 files changed, 40 insertions(+), 57 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index 510bdfbc4073..625407e4d3b0 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -212,7 +212,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, /* Look up the Linux PTE for the backing page */ pte_size = psize; pte = lookup_linux_pte_and_update(pgdir, hva, writing, &pte_size); - if (pte_present(pte) && !pte_numa(pte)) { + if (pte_present(pte) && !pte_protnone(pte)) { if (writing && !pte_write(pte)) /* make the actual HPTE be read-only */ ptel = hpte_make_readonly(ptel); diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 6154b0a2b063..f38327b95f76 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -398,8 +398,6 @@ good_area: * processors use the same I/D cache coherency mechanism * as embedded. */ - if (error_code & DSISR_PROTFAULT) - goto bad_area; #endif /* CONFIG_PPC_STD_MMU */ /* @@ -423,9 +421,6 @@ good_area: flags |= FAULT_FLAG_WRITE; /* a read */ } else { - /* protection fault */ - if (error_code & 0x08000000) - goto bad_area; if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))) goto bad_area; } diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c index c90e602677c9..83dfcb55ffef 100644 --- a/arch/powerpc/mm/pgtable.c +++ b/arch/powerpc/mm/pgtable.c @@ -172,9 +172,14 @@ static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma, void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { -#ifdef CONFIG_DEBUG_VM - WARN_ON(pte_val(*ptep) & _PAGE_PRESENT); -#endif + /* + * When handling numa faults, we already have the pte marked + * _PAGE_PRESENT, but we can be sure that it is not in hpte. + * Hence we can use set_pte_at for them. + */ + VM_WARN_ON((pte_val(*ptep) & (_PAGE_PRESENT | _PAGE_USER)) == + (_PAGE_PRESENT | _PAGE_USER)); + /* Note: mm->context.id might not yet have been assigned as * this context might not have been activated yet when this * is called. diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 4fe5f64cc179..91bb8836825a 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -718,7 +718,8 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { #ifdef CONFIG_DEBUG_VM - WARN_ON(pmd_val(*pmdp) & _PAGE_PRESENT); + WARN_ON((pmd_val(*pmdp) & (_PAGE_PRESENT | _PAGE_USER)) == + (_PAGE_PRESENT | _PAGE_USER)); assert_spin_locked(&mm->page_table_lock); WARN_ON(!pmd_trans_huge(pmd)); #endif diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c index 89df70e0caa6..81bf3d2af3eb 100644 --- a/arch/x86/mm/gup.c +++ b/arch/x86/mm/gup.c @@ -84,7 +84,7 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, struct page *page; /* Similar to the PMD case, NUMA hinting must take slow path */ - if (pte_numa(pte)) { + if (pte_protnone(pte)) { pte_unmap(ptep); return 0; } @@ -178,7 +178,7 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, * slowpath for accounting purposes and so that they * can be serialised against THP migration. */ - if (pmd_numa(pmd)) + if (pmd_protnone(pmd)) return 0; if (!gup_huge_pmd(pmd, addr, next, write, pages, nr)) return 0; diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h index 0d11c3dcd3a1..9cd8b21dddbe 100644 --- a/include/uapi/linux/mempolicy.h +++ b/include/uapi/linux/mempolicy.h @@ -67,7 +67,7 @@ enum mpol_rebind_step { #define MPOL_F_LOCAL (1 << 1) /* preferred local allocation */ #define MPOL_F_REBINDING (1 << 2) /* identify policies in rebinding */ #define MPOL_F_MOF (1 << 3) /* this policy wants migrate on fault */ -#define MPOL_F_MORON (1 << 4) /* Migrate On pte_numa Reference On Node */ +#define MPOL_F_MORON (1 << 4) /* Migrate On protnone Reference On Node */ #endif /* _UAPI_LINUX_MEMPOLICY_H */ diff --git a/mm/gup.c b/mm/gup.c index c2da1163986a..51bf0b06ca7b 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -64,7 +64,7 @@ retry: migration_entry_wait(mm, pmd, address); goto retry; } - if ((flags & FOLL_NUMA) && pte_numa(pte)) + if ((flags & FOLL_NUMA) && pte_protnone(pte)) goto no_page; if ((flags & FOLL_WRITE) && !pte_write(pte)) { pte_unmap_unlock(ptep, ptl); @@ -184,7 +184,7 @@ struct page *follow_page_mask(struct vm_area_struct *vma, return page; return no_page_table(vma, flags); } - if ((flags & FOLL_NUMA) && pmd_numa(*pmd)) + if ((flags & FOLL_NUMA) && pmd_protnone(*pmd)) return no_page_table(vma, flags); if (pmd_trans_huge(*pmd)) { if (flags & FOLL_SPLIT) { @@ -906,10 +906,10 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, /* * Similar to the PMD case below, NUMA hinting must take slow - * path + * path using the pte_protnone check. */ if (!pte_present(pte) || pte_special(pte) || - pte_numa(pte) || (write && !pte_write(pte))) + pte_protnone(pte) || (write && !pte_write(pte))) goto pte_unmap; VM_BUG_ON(!pfn_valid(pte_pfn(pte))); @@ -1104,7 +1104,7 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, * slowpath for accounting purposes and so that they * can be serialised against THP migration. */ - if (pmd_numa(pmd)) + if (pmd_protnone(pmd)) return 0; if (!gup_huge_pmd(pmd, pmdp, addr, next, write, diff --git a/mm/huge_memory.c b/mm/huge_memory.c index c6921362c5fc..915941c45169 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1211,7 +1211,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, return ERR_PTR(-EFAULT); /* Full NUMA hinting faults to serialise migration in fault paths */ - if ((flags & FOLL_NUMA) && pmd_numa(*pmd)) + if ((flags & FOLL_NUMA) && pmd_protnone(*pmd)) goto out; page = pmd_page(*pmd); @@ -1342,7 +1342,7 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, /* * Migrate the THP to the requested node, returns with page unlocked - * and pmd_numa cleared. + * and access rights restored. */ spin_unlock(ptl); migrated = migrate_misplaced_transhuge_page(mm, vma, @@ -1357,7 +1357,7 @@ clear_pmdnuma: BUG_ON(!PageLocked(page)); pmd = pmd_mknonnuma(pmd); set_pmd_at(mm, haddr, pmdp, pmd); - VM_BUG_ON(pmd_numa(*pmdp)); + VM_BUG_ON(pmd_protnone(*pmdp)); update_mmu_cache_pmd(vma, addr, pmdp); unlock_page(page); out_unlock: @@ -1483,7 +1483,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, ret = 1; if (!prot_numa) { entry = pmdp_get_and_clear_notify(mm, addr, pmd); - if (pmd_numa(entry)) + if (pmd_protnone(entry)) entry = pmd_mknonnuma(entry); entry = pmd_modify(entry, newprot); ret = HPAGE_PMD_NR; @@ -1499,7 +1499,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, * local vs remote hits on the zero page. */ if (!is_huge_zero_page(page) && - !pmd_numa(*pmd)) { + !pmd_protnone(*pmd)) { pmdp_set_numa(mm, addr, pmd); ret = HPAGE_PMD_NR; } @@ -1767,9 +1767,9 @@ static int __split_huge_page_map(struct page *page, pte_t *pte, entry; BUG_ON(PageCompound(page+i)); /* - * Note that pmd_numa is not transferred deliberately - * to avoid any possibility that pte_numa leaks to - * a PROT_NONE VMA by accident. + * Note that NUMA hinting access restrictions are not + * transferred to avoid any possibility of altering + * permissions across VMAs. */ entry = mk_pte(page + i, vma->vm_page_prot); entry = maybe_mkwrite(pte_mkdirty(entry), vma); diff --git a/mm/memory.c b/mm/memory.c index bbe6a73a899d..92e6a6299e86 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3124,7 +3124,7 @@ static int handle_pte_fault(struct mm_struct *mm, pte, pmd, flags, entry); } - if (pte_numa(entry)) + if (pte_protnone(entry)) return do_numa_page(mm, vma, address, entry, pte, pmd); ptl = pte_lockptr(mm, pmd); @@ -3202,7 +3202,7 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (pmd_trans_splitting(orig_pmd)) return 0; - if (pmd_numa(orig_pmd)) + if (pmd_protnone(orig_pmd)) return do_huge_pmd_numa_page(mm, vma, address, orig_pmd, pmd); diff --git a/mm/mprotect.c b/mm/mprotect.c index 33121662f08b..44ffa698484d 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -75,36 +75,18 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, oldpte = *pte; if (pte_present(oldpte)) { pte_t ptent; - bool updated = false; - if (!prot_numa) { - ptent = ptep_modify_prot_start(mm, addr, pte); - if (pte_numa(ptent)) - ptent = pte_mknonnuma(ptent); - ptent = pte_modify(ptent, newprot); - /* - * Avoid taking write faults for pages we - * know to be dirty. - */ - if (dirty_accountable && pte_dirty(ptent) && - (pte_soft_dirty(ptent) || - !(vma->vm_flags & VM_SOFTDIRTY))) - ptent = pte_mkwrite(ptent); - ptep_modify_prot_commit(mm, addr, pte, ptent); - updated = true; - } else { - struct page *page; - - page = vm_normal_page(vma, addr, oldpte); - if (page && !PageKsm(page)) { - if (!pte_numa(oldpte)) { - ptep_set_numa(mm, addr, pte); - updated = true; - } - } + ptent = ptep_modify_prot_start(mm, addr, pte); + ptent = pte_modify(ptent, newprot); + + /* Avoid taking write faults for known dirty pages */ + if (dirty_accountable && pte_dirty(ptent) && + (pte_soft_dirty(ptent) || + !(vma->vm_flags & VM_SOFTDIRTY))) { + ptent = pte_mkwrite(ptent); } - if (updated) - pages++; + ptep_modify_prot_commit(mm, addr, pte, ptent); + pages++; } else if (IS_ENABLED(CONFIG_MIGRATION)) { swp_entry_t entry = pte_to_swp_entry(oldpte); diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index dfb79e028ecb..4b8ad760dde3 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -193,7 +193,7 @@ void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { pmd_t entry = *pmdp; - if (pmd_numa(entry)) + if (pmd_protnone(entry)) entry = pmd_mknonnuma(entry); set_pmd_at(vma->vm_mm, address, pmdp, pmd_mknotpresent(entry)); flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); -- cgit v1.2.3 From 35e88d5c22e1916c819b5a8756aed2f09a4aba18 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Tue, 17 Feb 2015 15:41:51 +0100 Subject: fs/binfmt_som: Drop kernel support for HP-UX SOM binaries The parisc arch has been the only user of HP-UX SOM binaries. Support for HP-UX executables was never finished and since we now drop support for the HP-UX compat layer anyway, it does not makes sense to keep the BINFMT_SOM support. Cc: linux-fsdevel@vger.kernel.org Cc: linux-parisc@vger.kernel.org Signed-off-by: Helge Deller --- fs/Kconfig.binfmt | 7 -- fs/Makefile | 1 - fs/binfmt_som.c | 299 ---------------------------------------------- include/uapi/linux/Kbuild | 1 - include/uapi/linux/som.h | 154 ------------------------ 5 files changed, 462 deletions(-) delete mode 100644 fs/binfmt_som.c delete mode 100644 include/uapi/linux/som.h (limited to 'include/uapi/linux') diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt index c055d56ec63d..270c48148f79 100644 --- a/fs/Kconfig.binfmt +++ b/fs/Kconfig.binfmt @@ -149,13 +149,6 @@ config BINFMT_EM86 later load the module when you want to use a Linux/Intel binary. The module will be called binfmt_em86. If unsure, say Y. -config BINFMT_SOM - tristate "Kernel support for SOM binaries" - depends on PARISC && HPUX - help - SOM is a binary executable format inherited from HP/UX. Say - Y here to be able to load and execute SOM binaries directly. - config BINFMT_MISC tristate "Kernel support for MISC binaries" ---help--- diff --git a/fs/Makefile b/fs/Makefile index bedff48e8fdc..b7e0cfe3af2f 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -37,7 +37,6 @@ obj-$(CONFIG_BINFMT_SCRIPT) += binfmt_script.o obj-$(CONFIG_BINFMT_ELF) += binfmt_elf.o obj-$(CONFIG_COMPAT_BINFMT_ELF) += compat_binfmt_elf.o obj-$(CONFIG_BINFMT_ELF_FDPIC) += binfmt_elf_fdpic.o -obj-$(CONFIG_BINFMT_SOM) += binfmt_som.o obj-$(CONFIG_BINFMT_FLAT) += binfmt_flat.o obj-$(CONFIG_FS_MBCACHE) += mbcache.o diff --git a/fs/binfmt_som.c b/fs/binfmt_som.c deleted file mode 100644 index 4e00ed68d4a6..000000000000 --- a/fs/binfmt_som.c +++ /dev/null @@ -1,299 +0,0 @@ -/* - * linux/fs/binfmt_som.c - * - * These are the functions used to load SOM format executables as used - * by HP-UX. - * - * Copyright 1999 Matthew Wilcox - * based on binfmt_elf which is - * Copyright 1993, 1994: Eric Youngdale (ericy@cais.com). - */ - -#include - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include - - -#include - -static int load_som_binary(struct linux_binprm * bprm); -static int load_som_library(struct file *); - -/* - * If we don't support core dumping, then supply a NULL so we - * don't even try. - */ -#if 0 -static int som_core_dump(struct coredump_params *cprm); -#else -#define som_core_dump NULL -#endif - -#define SOM_PAGESTART(_v) ((_v) & ~(unsigned long)(SOM_PAGESIZE-1)) -#define SOM_PAGEOFFSET(_v) ((_v) & (SOM_PAGESIZE-1)) -#define SOM_PAGEALIGN(_v) (((_v) + SOM_PAGESIZE - 1) & ~(SOM_PAGESIZE - 1)) - -static struct linux_binfmt som_format = { - .module = THIS_MODULE, - .load_binary = load_som_binary, - .load_shlib = load_som_library, - .core_dump = som_core_dump, - .min_coredump = SOM_PAGESIZE -}; - -/* - * create_som_tables() parses the env- and arg-strings in new user - * memory and creates the pointer tables from them, and puts their - * addresses on the "stack", returning the new stack pointer value. - */ -static void create_som_tables(struct linux_binprm *bprm) -{ - char **argv, **envp; - int argc = bprm->argc; - int envc = bprm->envc; - unsigned long p; - unsigned long *sp; - - /* Word-align the stack pointer */ - sp = (unsigned long *)((bprm->p + 3) & ~3); - - envp = (char **) sp; - sp += envc + 1; - argv = (char **) sp; - sp += argc + 1; - - __put_user((unsigned long) envp,++sp); - __put_user((unsigned long) argv,++sp); - - __put_user(argc, ++sp); - - bprm->p = (unsigned long) sp; - - p = current->mm->arg_start; - while (argc-- > 0) { - __put_user((char *)p,argv++); - p += strlen_user((char *)p); - } - __put_user(NULL, argv); - current->mm->arg_end = current->mm->env_start = p; - while (envc-- > 0) { - __put_user((char *)p,envp++); - p += strlen_user((char *)p); - } - __put_user(NULL, envp); - current->mm->env_end = p; -} - -static int check_som_header(struct som_hdr *som_ex) -{ - int *buf = (int *)som_ex; - int i, ck; - - if (som_ex->system_id != SOM_SID_PARISC_1_0 && - som_ex->system_id != SOM_SID_PARISC_1_1 && - som_ex->system_id != SOM_SID_PARISC_2_0) - return -ENOEXEC; - - if (som_ex->a_magic != SOM_EXEC_NONSHARE && - som_ex->a_magic != SOM_EXEC_SHARE && - som_ex->a_magic != SOM_EXEC_DEMAND) - return -ENOEXEC; - - if (som_ex->version_id != SOM_ID_OLD && - som_ex->version_id != SOM_ID_NEW) - return -ENOEXEC; - - ck = 0; - for (i=0; i<32; i++) - ck ^= buf[i]; - if (ck != 0) - return -ENOEXEC; - - return 0; -} - -static int map_som_binary(struct file *file, - const struct som_exec_auxhdr *hpuxhdr) -{ - unsigned long code_start, code_size, data_start, data_size; - unsigned long bss_start, som_brk; - int retval; - int prot = PROT_READ | PROT_EXEC; - int flags = MAP_FIXED|MAP_PRIVATE|MAP_DENYWRITE|MAP_EXECUTABLE; - - mm_segment_t old_fs = get_fs(); - set_fs(get_ds()); - - code_start = SOM_PAGESTART(hpuxhdr->exec_tmem); - code_size = SOM_PAGEALIGN(hpuxhdr->exec_tsize); - current->mm->start_code = code_start; - current->mm->end_code = code_start + code_size; - retval = vm_mmap(file, code_start, code_size, prot, - flags, SOM_PAGESTART(hpuxhdr->exec_tfile)); - if (retval < 0 && retval > -1024) - goto out; - - data_start = SOM_PAGESTART(hpuxhdr->exec_dmem); - data_size = SOM_PAGEALIGN(hpuxhdr->exec_dsize); - current->mm->start_data = data_start; - current->mm->end_data = bss_start = data_start + data_size; - retval = vm_mmap(file, data_start, data_size, - prot | PROT_WRITE, flags, - SOM_PAGESTART(hpuxhdr->exec_dfile)); - if (retval < 0 && retval > -1024) - goto out; - - som_brk = bss_start + SOM_PAGEALIGN(hpuxhdr->exec_bsize); - current->mm->start_brk = current->mm->brk = som_brk; - retval = vm_mmap(NULL, bss_start, som_brk - bss_start, - prot | PROT_WRITE, MAP_FIXED | MAP_PRIVATE, 0); - if (retval > 0 || retval < -1024) - retval = 0; -out: - set_fs(old_fs); - return retval; -} - - -/* - * These are the functions used to load SOM executables and shared - * libraries. There is no binary dependent code anywhere else. - */ - -static int -load_som_binary(struct linux_binprm * bprm) -{ - int retval; - unsigned int size; - unsigned long som_entry; - struct som_hdr *som_ex; - struct som_exec_auxhdr *hpuxhdr; - struct pt_regs *regs = current_pt_regs(); - - /* Get the exec-header */ - som_ex = (struct som_hdr *) bprm->buf; - - retval = check_som_header(som_ex); - if (retval != 0) - goto out; - - /* Now read in the auxiliary header information */ - - retval = -ENOMEM; - size = som_ex->aux_header_size; - if (size > SOM_PAGESIZE) - goto out; - hpuxhdr = kmalloc(size, GFP_KERNEL); - if (!hpuxhdr) - goto out; - - retval = kernel_read(bprm->file, som_ex->aux_header_location, - (char *) hpuxhdr, size); - if (retval != size) { - if (retval >= 0) - retval = -EIO; - goto out_free; - } - - /* Flush all traces of the currently running executable */ - retval = flush_old_exec(bprm); - if (retval) - goto out_free; - - /* OK, This is the point of no return */ - current->personality = PER_HPUX; - setup_new_exec(bprm); - - /* Set the task size for HP-UX processes such that - * the gateway page is outside the address space. - * This can be fixed later, but for now, this is much - * easier. - */ - - current->thread.task_size = 0xc0000000; - - /* Set map base to allow enough room for hp-ux heap growth */ - - current->thread.map_base = 0x80000000; - - retval = map_som_binary(bprm->file, hpuxhdr); - if (retval < 0) - goto out_free; - - som_entry = hpuxhdr->exec_entry; - kfree(hpuxhdr); - - set_binfmt(&som_format); - install_exec_creds(bprm); - setup_arg_pages(bprm, STACK_TOP, EXSTACK_DEFAULT); - - create_som_tables(bprm); - - current->mm->start_stack = bprm->p; - -#if 0 - printk("(start_brk) %08lx\n" , (unsigned long) current->mm->start_brk); - printk("(end_code) %08lx\n" , (unsigned long) current->mm->end_code); - printk("(start_code) %08lx\n" , (unsigned long) current->mm->start_code); - printk("(end_data) %08lx\n" , (unsigned long) current->mm->end_data); - printk("(start_stack) %08lx\n" , (unsigned long) current->mm->start_stack); - printk("(brk) %08lx\n" , (unsigned long) current->mm->brk); -#endif - - map_hpux_gateway_page(current,current->mm); - - start_thread_som(regs, som_entry, bprm->p); - return 0; - - /* error cleanup */ -out_free: - kfree(hpuxhdr); -out: - return retval; -} - -static int load_som_library(struct file *f) -{ -/* No lib support in SOM yet. gizza chance.. */ - return -ENOEXEC; -} - /* Install the SOM loader. - * N.B. We *rely* on the table being the right size with the - * right number of free slots... - */ - -static int __init init_som_binfmt(void) -{ - register_binfmt(&som_format); - return 0; -} - -static void __exit exit_som_binfmt(void) -{ - /* Remove the SOM loader. */ - unregister_binfmt(&som_format); -} - -core_initcall(init_som_binfmt); -module_exit(exit_som_binfmt); - -MODULE_LICENSE("GPL"); diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index 7b8141bf59a7..68ceb97c458c 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -370,7 +370,6 @@ header-y += snmp.h header-y += sock_diag.h header-y += socket.h header-y += sockios.h -header-y += som.h header-y += sonet.h header-y += sonypi.h header-y += soundcard.h diff --git a/include/uapi/linux/som.h b/include/uapi/linux/som.h deleted file mode 100644 index 166594e4e7be..000000000000 --- a/include/uapi/linux/som.h +++ /dev/null @@ -1,154 +0,0 @@ -#ifndef _LINUX_SOM_H -#define _LINUX_SOM_H - -/* File format definition for SOM executables / shared libraries */ - -/* we need struct timespec */ -#include - -#define SOM_PAGESIZE 4096 - -/* this is the SOM header */ -struct som_hdr { - short system_id; /* magic number - system */ - short a_magic; /* magic number - file type */ - unsigned int version_id; /* versiod ID: YYMMDDHH */ - struct timespec file_time; /* system clock */ - unsigned int entry_space; /* space for entry point */ - unsigned int entry_subspace; /* subspace for entry point */ - unsigned int entry_offset; /* offset of entry point */ - unsigned int aux_header_location; /* auxiliary header location */ - unsigned int aux_header_size; /* auxiliary header size */ - unsigned int som_length; /* length of entire SOM */ - unsigned int presumed_dp; /* compiler's DP value */ - unsigned int space_location; /* space dictionary location */ - unsigned int space_total; /* number of space entries */ - unsigned int subspace_location; /* subspace entries location */ - unsigned int subspace_total; /* number of subspace entries */ - unsigned int loader_fixup_location; /* MPE/iX loader fixup */ - unsigned int loader_fixup_total; /* number of fixup records */ - unsigned int space_strings_location; /* (sub)space names */ - unsigned int space_strings_size; /* size of strings area */ - unsigned int init_array_location; /* reserved */ - unsigned int init_array_total; /* reserved */ - unsigned int compiler_location; /* module dictionary */ - unsigned int compiler_total; /* number of modules */ - unsigned int symbol_location; /* symbol dictionary */ - unsigned int symbol_total; /* number of symbols */ - unsigned int fixup_request_location; /* fixup requests */ - unsigned int fixup_request_total; /* number of fixup requests */ - unsigned int symbol_strings_location;/* module & symbol names area */ - unsigned int symbol_strings_size; /* size of strings area */ - unsigned int unloadable_sp_location; /* unloadable spaces location */ - unsigned int unloadable_sp_size; /* size of data */ - unsigned int checksum; -}; - -/* values for system_id */ - -#define SOM_SID_PARISC_1_0 0x020b -#define SOM_SID_PARISC_1_1 0x0210 -#define SOM_SID_PARISC_2_0 0x0214 - -/* values for a_magic */ - -#define SOM_LIB_EXEC 0x0104 -#define SOM_RELOCATABLE 0x0106 -#define SOM_EXEC_NONSHARE 0x0107 -#define SOM_EXEC_SHARE 0x0108 -#define SOM_EXEC_DEMAND 0x010B -#define SOM_LIB_DYN 0x010D -#define SOM_LIB_SHARE 0x010E -#define SOM_LIB_RELOC 0x0619 - -/* values for version_id. Decimal not hex, yes. Grr. */ - -#define SOM_ID_OLD 85082112 -#define SOM_ID_NEW 87102412 - -struct aux_id { - unsigned int mandatory :1; /* the linker must understand this */ - unsigned int copy :1; /* Must be copied by the linker */ - unsigned int append :1; /* Must be merged by the linker */ - unsigned int ignore :1; /* Discard section if unknown */ - unsigned int reserved :12; - unsigned int type :16; /* Header type */ - unsigned int length; /* length of _following_ data */ -}; - -/* The Exec Auxiliary Header. Called The HP-UX Header within HP apparently. */ -struct som_exec_auxhdr { - struct aux_id som_auxhdr; - int exec_tsize; /* Text size in bytes */ - int exec_tmem; /* Address to load text at */ - int exec_tfile; /* Location of text in file */ - int exec_dsize; /* Data size in bytes */ - int exec_dmem; /* Address to load data at */ - int exec_dfile; /* Location of data in file */ - int exec_bsize; /* Uninitialised data (bss) */ - int exec_entry; /* Address to start executing */ - int exec_flags; /* loader flags */ - int exec_bfill; /* initialisation value for bss */ -}; - -/* Oh, the things people do to avoid casts. Shame it'll break with gcc's - * new aliasing rules really. - */ -union name_pt { - char * n_name; - unsigned int n_strx; -}; - -/* The Space Dictionary */ -struct space_dictionary_record { - union name_pt name; /* index to subspace name */ - unsigned int is_loadable :1; /* loadable */ - unsigned int is_defined :1; /* defined within file */ - unsigned int is_private :1; /* not sharable */ - unsigned int has_intermediate_code :1; /* contains intermediate code */ - unsigned int is_tspecific :1; /* thread specific */ - unsigned int reserved :11; /* for future expansion */ - unsigned int sort_key :8; /* for linker */ - unsigned int reserved2 :8; /* for future expansion */ - - int space_number; /* index */ - int subspace_index; /* index into subspace dict */ - unsigned int subspace_quantity; /* number of subspaces */ - int loader_fix_index; /* for loader */ - unsigned int loader_fix_quantity; /* for loader */ - int init_pointer_index; /* data pointer array index */ - unsigned int init_pointer_quantity; /* number of data pointers */ -}; - -/* The Subspace Dictionary */ -struct subspace_dictionary_record { - int space_index; - unsigned int access_control_bits :7; - unsigned int memory_resident :1; - unsigned int dup_common :1; - unsigned int is_common :1; - unsigned int quadrant :2; - unsigned int initially_frozen :1; - unsigned int is_first :1; - unsigned int code_only :1; - unsigned int sort_key :8; - unsigned int replicate_init :1; - unsigned int continuation :1; - unsigned int is_tspecific :1; - unsigned int is_comdat :1; - unsigned int reserved :4; - - int file_loc_init_value; - unsigned int initialization_length; - unsigned int subspace_start; - unsigned int subspace_length; - - unsigned int reserved2 :5; - unsigned int alignment :27; - - union name_pt name; - int fixup_request_index; - unsigned int fixup_request_quantity; -}; - -#endif /* _LINUX_SOM_H */ -- cgit v1.2.3 From 9dc5c05f45ca8101025046cda7f8aca8835204f2 Mon Sep 17 00:00:00 2001 From: Geoff Levand Date: Tue, 17 Feb 2015 13:45:50 -0800 Subject: kexec: Fix make headers_check Remove the unneded declaration for a kexec_load() routine. Fixes errors like these when running 'make headers_check': include/uapi/linux/kexec.h: userspace cannot reference function or variable defined in the kernel Paul said: : The kexec_load declaration isn't very useful for userspace, see the patch : I submitted in http://lkml.kernel.org/r/1389791824.17407.9.camel@x220 . : And After my attempt the export of that declaration has also been : discussed in : http://lkml.kernel.org/r/115373b6ac68ee7a305975896e1c4971e8e51d4c.1408731991.git.geoff@infradead.org : : In that last discussion no one has been able to point to an actual user of : it. So, as far as I can tell, no one actually uses it. Which makes : sense, because including this header by itself doesn't give one access to : a useful definition of kexec_load. So why bother with the declaration? Signed-off-by: Geoff Levand Acked-by: Paul Bolle Cc: H. Peter Anvin Cc: Vivek Goyal Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Maximilian Attems Cc: Michal Marek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/kexec.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kexec.h b/include/uapi/linux/kexec.h index 6925f5b42f89..99048e501b88 100644 --- a/include/uapi/linux/kexec.h +++ b/include/uapi/linux/kexec.h @@ -55,12 +55,6 @@ struct kexec_segment { size_t memsz; }; -/* Load a new kernel image as described by the kexec_segment array - * consisting of passed number of segments at the entry-point address. - * The flags allow different useage types. - */ -extern int kexec_load(void *, size_t, struct kexec_segment *, - unsigned long int); #endif /* __KERNEL__ */ #endif /* _UAPILINUX_KEXEC_H */ -- cgit v1.2.3