diff options
| author | David S. Miller <davem@davemloft.net> | 2014-07-22 00:44:59 -0700 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2014-07-22 00:44:59 -0700 |
| commit | 8fd90bb889635fa1e7f80a3950948cc2e74c1446 (patch) | |
| tree | 1490343b5ad9f88b9333e53fa9457c00cbf6c2d1 | |
| parent | 1bb4238b17b5de6cdc120970a9d00dd8a44f40df (diff) | |
| parent | 15ba2236f3556fc01b9ca91394465152b5ea74b6 (diff) | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Conflicts:
drivers/infiniband/hw/cxgb4/device.c
The cxgb4 conflict was simply overlapping changes.
Signed-off-by: David S. Miller <davem@davemloft.net>
189 files changed, 1904 insertions, 942 deletions
diff --git a/Documentation/acpi/enumeration.txt b/Documentation/acpi/enumeration.txt index fd786ea13a1..e182be5e3c8 100644 --- a/Documentation/acpi/enumeration.txt +++ b/Documentation/acpi/enumeration.txt @@ -60,12 +60,6 @@ If the driver needs to perform more complex initialization like getting and configuring GPIOs it can get its ACPI handle and extract this information from ACPI tables. -Currently the kernel is not able to automatically determine from which ACPI -device it should make the corresponding platform device so we need to add -the ACPI device explicitly to acpi_platform_device_ids list defined in -drivers/acpi/acpi_platform.c. This limitation is only for the platform -devices, SPI and I2C devices are created automatically as described below. - DMA support ~~~~~~~~~~~ DMA controllers enumerated via ACPI should be registered in the system to diff --git a/Documentation/devicetree/bindings/cpufreq/cpufreq-cpu0.txt b/Documentation/devicetree/bindings/cpufreq/cpufreq-cpu0.txt index f055515d2b6..366690cb86a 100644 --- a/Documentation/devicetree/bindings/cpufreq/cpufreq-cpu0.txt +++ b/Documentation/devicetree/bindings/cpufreq/cpufreq-cpu0.txt @@ -8,10 +8,12 @@ Both required and optional properties listed below must be defined under node /cpus/cpu@0. Required properties: -- operating-points: Refer to Documentation/devicetree/bindings/power/opp.txt - for details +- None Optional properties: +- operating-points: Refer to Documentation/devicetree/bindings/power/opp.txt for + details. OPPs *must* be supplied either via DT, i.e. this property, or + populated at runtime. - clock-latency: Specify the possible maximum transition latency for clock, in unit of nanoseconds. - voltage-tolerance: Specify the CPU voltage tolerance in percentage. diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index c1b9aa8c5a5..b7fa2f59945 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2790,6 +2790,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted. leaf rcu_node structure. Useful for very large systems. + rcutree.jiffies_till_sched_qs= [KNL] + Set required age in jiffies for a + given grace period before RCU starts + soliciting quiescent-state help from + rcu_note_context_switch(). + rcutree.jiffies_till_first_fqs= [KNL] Set delay from grace-period initialization to first attempt to force quiescent states. @@ -3526,7 +3532,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted. the allocated input device; If set to 0, video driver will only send out the event without touching backlight brightness level. - default: 0 + default: 1 virtio_mmio.device= [VMMIO] Memory mapped virtio (platform) device. diff --git a/MAINTAINERS b/MAINTAINERS index ae8cd00215b..78215a5dea2 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8010,6 +8010,16 @@ F: drivers/ata/ F: include/linux/ata.h F: include/linux/libata.h +SERIAL ATA AHCI PLATFORM devices support +M: Hans de Goede <hdegoede@redhat.com> +M: Tejun Heo <tj@kernel.org> +L: linux-ide@vger.kernel.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata.git +S: Supported +F: drivers/ata/ahci_platform.c +F: drivers/ata/libahci_platform.c +F: include/linux/ahci_platform.h + SERVER ENGINES 10Gbps iSCSI - BladeEngine 2 DRIVER M: Jayamohan Kallickal <jayamohan.kallickal@emulex.com> L: linux-scsi@vger.kernel.org @@ -1,7 +1,7 @@ VERSION = 3 PATCHLEVEL = 16 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc6 NAME = Shuffling Zombie Juror # *DOCUMENTATION* diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 245058b3b0e..88acf8bc149 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -6,6 +6,7 @@ config ARM select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_HAVE_CUSTOM_GPIO_H select ARCH_MIGHT_HAVE_PC_PARPORT + select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF select ARCH_WANT_IPC_PARSE_VERSION diff --git a/arch/arm/boot/dts/at91sam9n12.dtsi b/arch/arm/boot/dts/at91sam9n12.dtsi index 287795985e3..b84bac5bada 100644 --- a/arch/arm/boot/dts/at91sam9n12.dtsi +++ b/arch/arm/boot/dts/at91sam9n12.dtsi @@ -925,7 +925,7 @@ compatible = "atmel,at91rm9200-ohci", "usb-ohci"; reg = <0x00500000 0x00100000>; interrupts = <22 IRQ_TYPE_LEVEL_HIGH 2>; - clocks = <&usb>, <&uhphs_clk>, <&udphs_clk>, + clocks = <&usb>, <&uhphs_clk>, <&uhphs_clk>, <&uhpck>; clock-names = "usb_clk", "ohci_clk", "hclk", "uhpck"; status = "disabled"; diff --git a/arch/arm/boot/dts/at91sam9x5.dtsi b/arch/arm/boot/dts/at91sam9x5.dtsi index 2ebc42140ea..2c0d6ea3ab4 100644 --- a/arch/arm/boot/dts/at91sam9x5.dtsi +++ b/arch/arm/boot/dts/at91sam9x5.dtsi @@ -1124,6 +1124,7 @@ compatible = "atmel,at91sam9rl-pwm"; reg = <0xf8034000 0x300>; interrupts = <18 IRQ_TYPE_LEVEL_HIGH 4>; + clocks = <&pwm_clk>; #pwm-cells = <3>; status = "disabled"; }; @@ -1155,8 +1156,7 @@ compatible = "atmel,at91rm9200-ohci", "usb-ohci"; reg = <0x00600000 0x100000>; interrupts = <22 IRQ_TYPE_LEVEL_HIGH 2>; - clocks = <&usb>, <&uhphs_clk>, <&udphs_clk>, - <&uhpck>; + clocks = <&usb>, <&uhphs_clk>, <&uhphs_clk>, <&uhpck>; clock-names = "usb_clk", "ohci_clk", "hclk", "uhpck"; status = "disabled"; }; diff --git a/arch/arm/mach-exynos/hotplug.c b/arch/arm/mach-exynos/hotplug.c index 8a134d019cb..920a4baa53c 100644 --- a/arch/arm/mach-exynos/hotplug.c +++ b/arch/arm/mach-exynos/hotplug.c @@ -40,15 +40,17 @@ static inline void cpu_leave_lowpower(void) static inline void platform_do_lowpower(unsigned int cpu, int *spurious) { + u32 mpidr = cpu_logical_map(cpu); + u32 core_id = MPIDR_AFFINITY_LEVEL(mpidr, 0); + for (;;) { - /* make cpu1 to be turned off at next WFI command */ - if (cpu == 1) - exynos_cpu_power_down(cpu); + /* Turn the CPU off on next WFI instruction. */ + exynos_cpu_power_down(core_id); wfi(); - if (pen_release == cpu_logical_map(cpu)) { + if (pen_release == core_id) { /* * OK, proper wakeup, we're done */ diff --git a/arch/arm/mach-exynos/platsmp.c b/arch/arm/mach-exynos/platsmp.c index 1c8d31e3952..50b9aad5e27 100644 --- a/arch/arm/mach-exynos/platsmp.c +++ b/arch/arm/mach-exynos/platsmp.c @@ -90,7 +90,8 @@ static void exynos_secondary_init(unsigned int cpu) static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle) { unsigned long timeout; - unsigned long phys_cpu = cpu_logical_map(cpu); + u32 mpidr = cpu_logical_map(cpu); + u32 core_id = MPIDR_AFFINITY_LEVEL(mpidr, 0); int ret = -ENOSYS; /* @@ -104,17 +105,18 @@ static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle) * the holding pen - release it, then wait for it to flag * that it has been released by resetting pen_release. * - * Note that "pen_release" is the hardware CPU ID, whereas + * Note that "pen_release" is the hardware CPU core ID, whereas * "cpu" is Linux's internal ID. */ - write_pen_release(phys_cpu); + write_pen_release(core_id); - if (!exynos_cpu_power_state(cpu)) { - exynos_cpu_power_up(cpu); + if (!exynos_cpu_power_state(core_id)) { + exynos_cpu_power_up(core_id); timeout = 10; /* wait max 10 ms until cpu1 is on */ - while (exynos_cpu_power_state(cpu) != S5P_CORE_LOCAL_PWR_EN) { + while (exynos_cpu_power_state(core_id) + != S5P_CORE_LOCAL_PWR_EN) { if (timeout-- == 0) break; @@ -145,20 +147,20 @@ static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle) * Try to set boot address using firmware first * and fall back to boot register if it fails. */ - ret = call_firmware_op(set_cpu_boot_addr, phys_cpu, boot_addr); + ret = call_firmware_op(set_cpu_boot_addr, core_id, boot_addr); if (ret && ret != -ENOSYS) goto fail; if (ret == -ENOSYS) { - void __iomem *boot_reg = cpu_boot_reg(phys_cpu); + void __iomem *boot_reg = cpu_boot_reg(core_id); if (IS_ERR(boot_reg)) { ret = PTR_ERR(boot_reg); goto fail; } - __raw_writel(boot_addr, cpu_boot_reg(phys_cpu)); + __raw_writel(boot_addr, cpu_boot_reg(core_id)); } - call_firmware_op(cpu_boot, phys_cpu); + call_firmware_op(cpu_boot, core_id); arch_send_wakeup_ipi_mask(cpumask_of(cpu)); @@ -227,22 +229,24 @@ static void __init exynos_smp_prepare_cpus(unsigned int max_cpus) * boot register if it fails. */ for (i = 1; i < max_cpus; ++i) { - unsigned long phys_cpu; unsigned long boot_addr; + u32 mpidr; + u32 core_id; int ret; - phys_cpu = cpu_logical_map(i); + mpidr = cpu_logical_map(i); + core_id = MPIDR_AFFINITY_LEVEL(mpidr, 0); boot_addr = virt_to_phys(exynos4_secondary_startup); - ret = call_firmware_op(set_cpu_boot_addr, phys_cpu, boot_addr); + ret = call_firmware_op(set_cpu_boot_addr, core_id, boot_addr); if (ret && ret != -ENOSYS) break; if (ret == -ENOSYS) { - void __iomem *boot_reg = cpu_boot_reg(phys_cpu); + void __iomem *boot_reg = cpu_boot_reg(core_id); if (IS_ERR(boot_reg)) break; - __raw_writel(boot_addr, cpu_boot_reg(phys_cpu)); + __raw_writel(boot_addr, cpu_boot_reg(core_id)); } } } diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c index 8e795dea02e..8556c787e59 100644 --- a/arch/arm/mach-imx/clk-imx6q.c +++ b/arch/arm/mach-imx/clk-imx6q.c @@ -70,7 +70,7 @@ static const char *cko_sels[] = { "cko1", "cko2", }; static const char *lvds_sels[] = { "dummy", "dummy", "dummy", "dummy", "dummy", "dummy", "pll4_audio", "pll5_video", "pll8_mlb", "enet_ref", - "pcie_ref", "sata_ref", + "pcie_ref_125m", "sata_ref_100m", }; enum mx6q_clks { @@ -491,7 +491,7 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node) /* All existing boards with PCIe use LVDS1 */ if (IS_ENABLED(CONFIG_PCI_IMX6)) - clk_set_parent(clk[lvds1_sel], clk[sata_ref]); + clk_set_parent(clk[lvds1_sel], clk[sata_ref_100m]); /* Set initial power mode */ imx6q_set_lpm(WAIT_CLOCKED); diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c index 477202fd39c..2bdc3233abe 100644 --- a/arch/arm/mach-mvebu/coherency.c +++ b/arch/arm/mach-mvebu/coherency.c @@ -292,6 +292,10 @@ static struct notifier_block mvebu_hwcc_nb = { .notifier_call = mvebu_hwcc_notifier, }; +static struct notifier_block mvebu_hwcc_pci_nb = { + .notifier_call = mvebu_hwcc_notifier, +}; + static void __init armada_370_coherency_init(struct device_node *np) { struct resource res; @@ -427,7 +431,7 @@ static int __init coherency_pci_init(void) { if (coherency_available()) bus_register_notifier(&pci_bus_type, - &mvebu_hwcc_nb); + &mvebu_hwcc_pci_nb); return 0; } diff --git a/arch/arm/mach-mvebu/headsmp-a9.S b/arch/arm/mach-mvebu/headsmp-a9.S index 5925366bc03..da5bb292b91 100644 --- a/arch/arm/mach-mvebu/headsmp-a9.S +++ b/arch/arm/mach-mvebu/headsmp-a9.S @@ -15,6 +15,8 @@ #include <linux/linkage.h> #include <linux/init.h> +#include <asm/assembler.h> + __CPUINIT #define CPU_RESUME_ADDR_REG 0xf10182d4 @@ -22,13 +24,18 @@ .global armada_375_smp_cpu1_enable_code_end armada_375_smp_cpu1_enable_code_start: - ldr r0, [pc, #4] +ARM_BE8(setend be) + adr r0, 1f + ldr r0, [r0] ldr r1, [r0] +ARM_BE8(rev r1, r1) mov pc, r1 +1: .word CPU_RESUME_ADDR_REG armada_375_smp_cpu1_enable_code_end: ENTRY(mvebu_cortex_a9_secondary_startup) +ARM_BE8(setend be) bl v7_invalidate_l1 b secondary_startup ENDPROC(mvebu_cortex_a9_secondary_startup) diff --git a/arch/arm/mach-mvebu/pmsu.c b/arch/arm/mach-mvebu/pmsu.c index a1d407c0feb..25aa8237d66 100644 --- a/arch/arm/mach-mvebu/pmsu.c +++ b/arch/arm/mach-mvebu/pmsu.c @@ -201,12 +201,12 @@ static noinline int do_armada_370_xp_cpu_suspend(unsigned long deepidle) /* Test the CR_C bit and set it if it was cleared */ asm volatile( - "mrc p15, 0, %0, c1, c0, 0 \n\t" - "tst %0, #(1 << 2) \n\t" - "orreq %0, %0, #(1 << 2) \n\t" - "mcreq p15, 0, %0, c1, c0, 0 \n\t" + "mrc p15, 0, r0, c1, c0, 0 \n\t" + "tst r0, #(1 << 2) \n\t" + "orreq r0, r0, #(1 << 2) \n\t" + "mcreq p15, 0, r0, c1, c0, 0 \n\t" "isb " - : : "r" (0)); + : : : "r0"); pr_warn("Failed to suspend the system\n"); diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index a474de346be..839f48c26ef 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -4,6 +4,7 @@ config ARM64 select ARCH_HAS_OPP select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_USE_CMPXCHG_LOCKREF + select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_WANT_OPTIONAL_GPIOLIB select ARCH_WANT_COMPAT_IPC_PARSE_VERSION select ARCH_WANT_FRAME_POINTERS diff --git a/arch/arm64/kernel/efi-stub.c b/arch/arm64/kernel/efi-stub.c index 60e98a639ac..e786e6cdc40 100644 --- a/arch/arm64/kernel/efi-stub.c +++ b/arch/arm64/kernel/efi-stub.c @@ -12,8 +12,6 @@ #include <linux/efi.h> #include <linux/libfdt.h> #include <asm/sections.h> -#include <generated/compile.h> -#include <generated/utsrelease.h> /* * AArch64 requires the DTB to be 8-byte aligned in the first 512MiB from diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index fefe7c8bf05..80b94b0add1 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -145,6 +145,7 @@ config PPC select HAVE_IRQ_EXIT_ON_IRQ_STACK select ARCH_USE_CMPXCHG_LOCKREF if PPC64 select HAVE_ARCH_AUDITSYSCALL + select ARCH_SUPPORTS_ATOMIC_RMW config GENERIC_CSUM def_bool CPU_LITTLE_ENDIAN diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index fddb72b48ce..d645428a65a 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -198,8 +198,10 @@ static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r, return rb; } -static inline unsigned long hpte_page_size(unsigned long h, unsigned long l) +static inline unsigned long __hpte_page_size(unsigned long h, unsigned long l, + bool is_base_size) { + int size, a_psize; /* Look at the 8 bit LP value */ unsigned int lp = (l >> LP_SHIFT) & ((1 << LP_BITS) - 1); @@ -214,14 +216,27 @@ static inline unsigned long hpte_page_size(unsigned long h, unsigned long l) continue; a_psize = __hpte_actual_psize(lp, size); - if (a_psize != -1) + if (a_psize != -1) { + if (is_base_size) + return 1ul << mmu_psize_defs[size].shift; return 1ul << mmu_psize_defs[a_psize].shift; + } } } return 0; } +static inline unsigned long hpte_page_size(unsigned long h, unsigned long l) +{ + return __hpte_page_size(h, l, 0); +} + +static inline unsigned long hpte_base_page_size(unsigned long h, unsigned long l) +{ + return __hpte_page_size(h, l, 1); +} + static inline unsigned long hpte_rpn(unsigned long ptel, unsigned long psize) { return ((ptel & HPTE_R_RPN) & ~(psize - 1)) >> PAGE_SHIFT; diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index 9ea266eae33..7e461252854 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -277,6 +277,8 @@ n: .globl n; \ n: +#define _GLOBAL_TOC(name) _GLOBAL(name) + #define _KPROBE(n) \ .section ".kprobes.text","a"; \ .globl n; \ diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 80561074078..68468d695f1 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -1562,7 +1562,7 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf, goto out; } if (!rma_setup && is_vrma_hpte(v)) { - unsigned long psize = hpte_page_size(v, r); + unsigned long psize = hpte_base_page_size(v, r); unsigned long senc = slb_pgsize_encoding(psize); unsigned long lpcr; diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index 6e6224318c3..5a24d3c2b6b 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -814,13 +814,10 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v, r = hpte[i+1]; /* - * Check the HPTE again, including large page size - * Since we don't currently allow any MPSS (mixed - * page-size segment) page sizes, it is sufficient - * to check against the actual page size. + * Check the HPTE again, including base page size */ if ((v & valid) && (v & mask) == val && - hpte_page_size(v, r) == (1ul << pshift)) + hpte_base_page_size(v, r) == (1ul << pshift)) /* Return with the HPTE still locked */ return (hash << 3) + (i >> 1); diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 868347ef09f..558a67df812 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -48,7 +48,7 @@ * * LR = return address to continue at after eventually re-enabling MMU */ -_GLOBAL(kvmppc_hv_entry_trampoline) +_GLOBAL_TOC(kvmppc_hv_entry_trampoline) mflr r0 std r0, PPC_LR_STKOFF(r1) stdu r1, -112(r1) diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S index e2c29e381dc..d044b8b7c69 100644 --- a/arch/powerpc/kvm/book3s_interrupts.S +++ b/arch/powerpc/kvm/book3s_interrupts.S @@ -25,7 +25,11 @@ #include <asm/exception-64s.h> #if defined(CONFIG_PPC_BOOK3S_64) +#if defined(_CALL_ELF) && _CALL_ELF == 2 +#define FUNC(name) name +#else #define FUNC(name) GLUE(.,name) +#endif #define GET_SHADOW_VCPU(reg) addi reg, r13, PACA_SVCPU #elif defined(CONFIG_PPC_BOOK3S_32) diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S index 9eec675220e..16c4d88ba27 100644 --- a/arch/powerpc/kvm/book3s_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_rmhandlers.S @@ -36,7 +36,11 @@ #if defined(CONFIG_PPC_BOOK3S_64) +#if defined(_CALL_ELF) && _CALL_ELF == 2 +#define FUNC(name) name +#else #define FUNC(name) GLUE(.,name) +#endif #elif defined(CONFIG_PPC_BOOK3S_32) @@ -146,7 +150,7 @@ kvmppc_handler_skip_ins: * On entry, r4 contains the guest shadow MSR * MSR.EE has to be 0 when calling this function */ -_GLOBAL(kvmppc_entry_trampoline) +_GLOBAL_TOC(kvmppc_entry_trampoline) mfmsr r5 LOAD_REG_ADDR(r7, kvmppc_handler_trampoline_enter) toreal(r7) diff --git a/arch/powerpc/kvm/book3s_rtas.c b/arch/powerpc/kvm/book3s_rtas.c index edb14ba992b..ef27fbd5d9c 100644 --- a/arch/powerpc/kvm/book3s_rtas.c +++ b/arch/powerpc/kvm/book3s_rtas.c @@ -23,20 +23,20 @@ static void kvm_rtas_set_xive(struct kvm_vcpu *vcpu, struct rtas_args *args) u32 irq, server, priority; int rc; - if (args->nargs != 3 || args->nret != 1) { + if (be32_to_cpu(args->nargs) != 3 || be32_to_cpu(args->nret) != 1) { rc = -3; goto out; } - irq = args->args[0]; - server = args->args[1]; - priority = args->args[2]; + irq = be32_to_cpu(args->args[0]); + server = be32_to_cpu(args->args[1]); + priority = be32_to_cpu(args->args[2]); rc = kvmppc_xics_set_xive(vcpu->kvm, irq, server, priority); if (rc) rc = -3; out: - args->rets[0] = rc; + args->rets[0] = cpu_to_be32(rc); } static void kvm_rtas_get_xive(struct kvm_vcpu *vcpu, struct rtas_args *args) @@ -44,12 +44,12 @@ static void kvm_rtas_get_xive(struct kvm_vcpu *vcpu, struct rtas_args *args) u32 irq, server, priority; int rc; - if (args->nargs != 1 || args->nret != 3) { + if (be32_to_cpu(args->nargs) != 1 || be32_to_cpu(args->nret) != 3) { rc = -3; goto out; } - irq = args->args[0]; + irq = be32_to_cpu(args->args[0]); server = priority = 0; rc = kvmppc_xics_get_xive(vcpu->kvm, irq, &server, &priority); @@ -58,10 +58,10 @@ static void kvm_rtas_get_xive(struct kvm_vcpu *vcpu, struct rtas_args *args) goto out; } - args->rets[1] = server; - args->rets[2] = priority; + args->rets[1] = cpu_to_be32(server); + args->rets[2] = cpu_to_be32(priority); out: - args->rets[0] = rc; + args->rets[0] = cpu_to_be32(rc); } static void kvm_rtas_int_off(struct kvm_vcpu *vcpu, struct rtas_args *args) @@ -69,18 +69,18 @@ static void kvm_rtas_int_off(struct kvm_vcpu *vcpu, struct rtas_args *args) u32 irq; int rc; - if (args->nargs != 1 || args->nret != 1) { + if (be32_to_cpu(args->nargs) != 1 || be32_to_cpu(args->nret) != 1) { rc = -3; goto out; } - irq = args->args[0]; + irq = be32_to_cpu(args->args[0]); rc = kvmppc_xics_int_off(vcpu->kvm, irq); if (rc) rc = -3; out: - args->rets[0] = rc; + args->rets[0] = cpu_to_be32(rc); } static void kvm_rtas_int_on(struct kvm_vcpu *vcpu, struct rtas_args *args) @@ -88,18 +88,18 @@ static void kvm_rtas_int_on(struct kvm_vcpu *vcpu, struct rtas_args *args) u32 irq; int rc; - if (args->nargs != 1 || args->nret != 1) { + if (be32_to_cpu(args->nargs) != 1 || be32_to_cpu(args->nret) != 1) { rc = -3; goto out; } - irq = args->args[0]; + irq = be32_to_cpu(args->args[0]); rc = kvmppc_xics_int_on(vcpu->kvm, irq); if (rc) rc = -3; out: - args->rets[0] = rc; + args->rets[0] = cpu_to_be32(rc); } #endif /* CONFIG_KVM_XICS */ @@ -205,32 +205,6 @@ int kvm_vm_ioctl_rtas_define_token(struct kvm *kvm, void __user *argp) return rc; } -static void kvmppc_rtas_swap_endian_in(struct rtas_args *args) -{ -#ifdef __LITTLE_ENDIAN__ - int i; - - args->token = be32_to_cpu(args->token); - args->nargs = be32_to_cpu(args->nargs); - args->nret = be32_to_cpu(args->nret); - for (i = 0; i < args->nargs; i++) - args->args[i] = be32_to_cpu(args->args[i]); -#endif -} - -static void kvmppc_rtas_swap_endian_out(struct rtas_args *args) -{ -#ifdef __LITTLE_ENDIAN__ - int i; - - for (i = 0; i < args->nret; i++) - args->args[i] = cpu_to_be32(args->args[i]); - args->token = cpu_to_be32(args->token); - args->nargs = cpu_to_be32(args->nargs); - args->nret = cpu_to_be32(args->nret); -#endif -} - int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu) { struct rtas_token_definition *d; @@ -249,8 +223,6 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu) if (rc) goto fail; - kvmppc_rtas_swap_endian_in(&args); - /* * args->rets is a pointer into args->args. Now that we've * copied args we need to fix it up to point into our copy, @@ -258,13 +230,13 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu) * value so we can restore it on the way out. */ orig_rets = args.rets; - args.rets = &args.args[args.nargs]; + args.rets = &args.args[be32_to_cpu(args.nargs)]; mutex_lock(&vcpu->kvm->lock); rc = -ENOENT; list_for_each_entry(d, &vcpu->kvm->arch.rtas_tokens, list) { - if (d->token == args.token) { + if (d->token == be32_to_cpu(args.token)) { d->handler->handler(vcpu, &args); rc = 0; break; @@ -275,7 +247,6 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu) if (rc == 0) { args.rets = orig_rets; - kvmppc_rtas_swap_endian_out(&args); rc = kvm_write_guest(vcpu->kvm, args_phys, &args, sizeof(args)); if (rc) goto fail; diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index dd2cc03f406..86903d3f5a0 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -473,7 +473,8 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, if (printk_ratelimit()) pr_err("%s: pte not present: gfn %lx, pfn %lx\n", __func__, (long)gfn, pfn); - return -EINVAL; + ret = -EINVAL; + goto out; } kvmppc_e500_ref_setup(ref, gtlbe, pfn, wimg); diff --git a/arch/s390/include/asm/switch_to.h b/arch/s390/include/asm/switch_to.h index df38c70cd59..18ea9e3f814 100644 --- a/arch/s390/include/asm/switch_to.h +++ b/arch/s390/include/asm/switch_to.h @@ -51,8 +51,8 @@ static inline int restore_fp_ctl(u32 *fpc) return 0; asm volatile( - "0: lfpc %1\n" - " la %0,0\n" + " lfpc %1\n" + "0: la %0,0\n" "1:\n" EX_TABLE(0b,1b) : "=d" (rc) : "Q" (*fpc), "0" (-EINVAL)); diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S index 7ba7d678451..e88d35d7495 100644 --- a/arch/s390/kernel/head.S +++ b/arch/s390/kernel/head.S @@ -437,11 +437,11 @@ ENTRY(startup_kdump) #if defined(CONFIG_64BIT) #if defined(CONFIG_MARCH_ZEC12) - .long 3, 0xc100efea, 0xf46ce800, 0x00400000 + .long 3, 0xc100eff2, 0xf46ce800, 0x00400000 #elif defined(CONFIG_MARCH_Z196) - .long 2, 0xc100efea, 0xf46c0000 + .long 2, 0xc100eff2, 0xf46c0000 #elif defined(CONFIG_MARCH_Z10) - .long 2, 0xc100efea, 0xf0680000 + .long 2, 0xc100eff2, 0xf0680000 #elif defined(CONFIG_MARCH_Z9_109) .long 1, 0xc100efc2 #elif defined(CONFIG_MARCH_Z990) diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index 2d716734b5b..5dc7ad9e2fb 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -334,9 +334,14 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data) unsigned long mask = PSW_MASK_USER; mask |= is_ri_task(child) ? PSW_MASK_RI : 0; - if ((data & ~mask) != PSW_USER_BITS) + if ((data ^ PSW_USER_BITS) & ~mask) + /* Invalid psw mask. */ + return -EINVAL; + if ((data & PSW_MASK_ASC) == PSW_ASC_HOME) + /* Invalid address-space-control bits */ return -EINVAL; if ((data & PSW_MASK_EA) && !(data & PSW_MASK_BA)) + /* Invalid addressing mode bits */ return -EINVAL; } *(addr_t *)((addr_t) &task_pt_regs(child)->psw + addr) = data; @@ -672,9 +677,12 @@ static int __poke_user_compat(struct task_struct *child, mask |= is_ri_task(child) ? PSW32_MASK_RI : 0; /* Build a 64 bit psw mask from 31 bit mask. */ - if ((tmp & ~mask) != PSW32_USER_BITS) + if ((tmp ^ PSW32_USER_BITS) & ~mask) /* Invalid psw mask. */ return -EINVAL; + if ((data & PSW32_MASK_ASC) == PSW32_ASC_HOME) + /* Invalid address-space-control bits */ + return -EINVAL; regs->psw.mask = (regs->psw.mask & ~PSW_MASK_USER) | (regs->psw.mask & PSW_MASK_BA) | (__u64)(tmp & mask) << 32; diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 9ddc51eeb8d..30de42730b2 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -48,13 +48,10 @@ static LIST_HEAD(zpci_list); static DEFINE_SPINLOCK(zpci_list_lock); -static void zpci_enable_irq(struct irq_data *data); -static void zpci_disable_irq(struct irq_data *data); - static struct irq_chip zpci_irq_chip = { .name = "zPCI", - .irq_unmask = zpci_enable_irq, - .irq_mask = zpci_disable_irq, + .irq_unmask = unmask_msi_irq, + .irq_mask = mask_msi_irq, }; static DECLARE_BITMAP(zpci_domain, ZPCI_NR_DEVICES); @@ -244,43 +241,6 @@ static int zpci_cfg_store(struct zpci_dev *zdev, int offset, u32 val, u8 len) return rc; } -static int zpci_msi_set_mask_bits(struct msi_desc *msi, u32 mask, u32 flag) -{ - int offset, pos; - u32 mask_bits; - - if (msi->msi_attrib.is_msix) { - offset = msi->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE + - PCI_MSIX_ENTRY_VECTOR_CTRL; - msi->masked = readl(msi->mask_base + offset); - writel(flag, msi->mask_base + offset); - } else if (msi->msi_attrib.maskbit) { - pos = (long) msi->mask_base; - pci_read_config_dword(msi->dev, pos, &mask_bits); - mask_bits &= ~(mask); - mask_bits |= flag & mask; - pci_write_config_dword(msi->dev, pos, mask_bits); - } else - return 0; - - msi->msi_attrib.maskbit = !!flag; - return 1; -} - -static void zpci_enable_irq(struct irq_data *data) -{ - struct msi_desc *msi = irq_get_msi_desc(data->irq); - - zpci_msi_set_mask_bits(msi, 1, 0); -} - -static void zpci_disable_irq(struct irq_data *data) -{ - struct msi_desc *msi = irq_get_msi_desc(data->irq); - - zpci_msi_set_mask_bits(msi, 1, 1); -} - void pcibios_fixup_bus(struct pci_bus *bus) { } @@ -487,7 +447,10 @@ void arch_teardown_msi_irqs(struct pci_dev *pdev) /* Release MSI interrupts */ list_for_each_entry(msi, &pdev->msi_list, list) { - zpci_msi_set_mask_bits(msi, 1, 1); + if (msi->msi_attrib.is_msix) + default_msix_mask_irq(msi, 1); + else + default_msi_mask_irq(msi, 1, 1); irq_set_msi_desc(msi->irq, NULL); irq_free_desc(msi->irq); msi->msg.address_lo = 0; diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 29f2e988c56..407c87d9879 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -78,6 +78,7 @@ config SPARC64 select HAVE_C_RECORDMCOUNT select NO_BOOTMEM select HAVE_ARCH_AUDITSYSCALL + select ARCH_SUPPORTS_ATOMIC_RMW config ARCH_DEFCONFIG string diff --git a/arch/sparc/include/uapi/asm/unistd.h b/arch/sparc/include/uapi/asm/unistd.h index b73274fb961..42f2bca1d33 100644 --- a/arch/sparc/include/uapi/asm/unistd.h +++ b/arch/sparc/include/uapi/asm/unistd.h @@ -410,8 +410,9 @@ #define __NR_finit_module 342 #define __NR_sched_setattr 343 #define __NR_sched_getattr 344 +#define __NR_renameat2 345 -#define NR_syscalls 345 +#define NR_syscalls 346 /* Bitmask values returned from kern_features system call. */ #define KERN_FEATURE_MIXED_MODE_STACK 0x00000001 diff --git a/arch/sparc/kernel/sys32.S b/arch/sparc/kernel/sys32.S index d066eb18650..f834224208e 100644 --- a/arch/sparc/kernel/sys32.S +++ b/arch/sparc/kernel/sys32.S @@ -48,6 +48,7 @@ SIGN1(sys32_futex, compat_sys_futex, %o1) SIGN1(sys32_recvfrom, compat_sys_recvfrom, %o0) SIGN1(sys32_recvmsg, compat_sys_recvmsg, %o0) SIGN1(sys32_sendmsg, compat_sys_sendmsg, %o0) +SIGN2(sys32_renameat2, sys_renameat2, %o0, %o2) .globl sys32_mmap2 sys32_mmap2: diff --git a/arch/sparc/kernel/systbls_32.S b/arch/sparc/kernel/systbls_32.S index 151ace8766c..85fe9b1087c 100644 --- a/arch/sparc/kernel/systbls_32.S +++ b/arch/sparc/kernel/systbls_32.S @@ -86,3 +86,4 @@ sys_call_table: /*330*/ .long sys_fanotify_mark, sys_prlimit64, sys_name_to_handle_at, sys_open_by_handle_at, sys_clock_adjtime /*335*/ .long sys_syncfs, sys_sendmmsg, sys_setns, sys_process_vm_readv, sys_process_vm_writev /*340*/ .long sys_ni_syscall, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr +/*345*/ .long sys_renameat2 diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S index 4bd4e2bb26c..33ecba2826e 100644 --- a/arch/sparc/kernel/systbls_64.S +++ b/arch/sparc/kernel/systbls_64.S @@ -87,6 +87,7 @@ sys_call_table32: /*330*/ .word compat_sys_fanotify_mark, sys_prlimit64, sys_name_to_handle_at, compat_sys_open_by_handle_at, compat_sys_clock_adjtime .word sys_syncfs, compat_sys_sendmmsg, sys_setns, compat_sys_process_vm_readv, compat_sys_process_vm_writev /*340*/ .word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr + .word sys32_renameat2 #endif /* CONFIG_COMPAT */ @@ -165,3 +166,4 @@ sys_call_table: /*330*/ .word sys_fanotify_mark, sys_prlimit64, sys_name_to_handle_at, sys_open_by_handle_at, sys_clock_adjtime .word sys_syncfs, sys_sendmmsg, sys_setns, sys_process_vm_readv, sys_process_vm_writev /*340*/ .word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr + .word sys_renameat2 diff --git a/arch/um/kernel/tlb.c b/arch/um/kernel/tlb.c index 9472079471b..f1b3eb14b85 100644 --- a/arch/um/kernel/tlb.c +++ b/arch/um/kernel/tlb.c @@ -12,6 +12,7 @@ #include <mem_user.h> #include <os.h> #include <skas.h> +#include <kern_util.h> struct host_vm_change { struct host_vm_op { @@ -124,6 +125,9 @@ static int add_munmap(unsigned long addr, unsigned long len, struct host_vm_op *last; int ret = 0; + if ((addr >= STUB_START) && (addr < STUB_END)) + return -EINVAL; + if (hvc->index != 0) { last = &hvc->ops[hvc->index - 1]; if ((last->type == MUNMAP) && @@ -283,8 +287,11 @@ void fix_range_common(struct mm_struct *mm, unsigned long start_addr, /* This is not an else because ret is modified above */ if (ret) { printk(KERN_ERR "fix_range_common: failed, killing current " - "process\n"); + "process: %d\n", task_tgid_vnr(current)); + /* We are under mmap_sem, release it such that current can terminate */ + up_write(¤t->mm->mmap_sem); force_sig(SIGKILL, current); + do_signal(); } } diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index 974b87474a9..5678c3571e7 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -206,7 +206,7 @@ unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user, int is_write = FAULT_WRITE(fi); unsigned long address = FAULT_ADDRESS(fi); - if (regs) + if (!is_user && regs) current->thread.segv_regs = container_of(regs, struct pt_regs, regs); if (!is_user && (address >= start_vm) && (address < end_vm)) { diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c index d531879a461..908579f2b0a 100644 --- a/arch/um/os-Linux/skas/process.c +++ b/arch/um/os-Linux/skas/process.c @@ -54,7 +54,7 @@ static int ptrace_dump_regs(int pid) void wait_stub_done(int pid) { - int n, status, err, bad_stop = 0; + int n, status, err; while (1) { CATCH_EINTR(n = waitpid(pid, &status, WUNTRACED | __WALL)); @@ -74,8 +74,6 @@ void wait_stub_done(int pid) if (((1 << WSTOPSIG(status)) & STUB_DONE_MASK) != 0) return; - else - bad_stop = 1; bad_wait: err = ptrace_dump_regs(pid); @@ -85,10 +83,7 @@ bad_wait: printk(UM_KERN_ERR "wait_stub_done : failed to wait for SIGTRAP, " "pid = %d, n = %d, errno = %d, status = 0x%x\n", pid, n, errno, status); - if (bad_stop) - kill(pid, SIGKILL); - else - fatal_sigsegv(); + fatal_sigsegv(); } extern unsigned long current_stub_stack(void); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index a8f749ef0fd..d24887b645d 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -131,6 +131,7 @@ config X86 select HAVE_CC_STACKPROTECTOR select GENERIC_CPU_AUTOPROBE select HAVE_ARCH_AUDITSYSCALL + select ARCH_SUPPORTS_ATOMIC_RMW config INSTRUCTION_DECODER def_bool y diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index 84c223479e3..7a6d43a554d 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -91,10 +91,9 @@ bs_die: .section ".bsdata", "a" bugger_off_msg: - .ascii "Direct floppy boot is not supported. " - .ascii "Use a boot loader program instead.\r\n" + .ascii "Use a boot loader.\r\n" .ascii "\n" - .ascii "Remove disk and press any key to reboot ...\r\n" + .ascii "Remove disk and press any key to reboot...\r\n" .byte 0 #ifdef CONFIG_EFI_STUB @@ -108,7 +107,7 @@ coff_header: #else .word 0x8664 # x86-64 #endif - .word 3 # nr_sections + .word 4 # nr_sections .long 0 # TimeDateStamp .long 0 # PointerToSymbolTable .long 1 # NumberOfSymbols @@ -250,6 +249,25 @@ section_table: .word 0 # NumberOfLineNumbers .long 0x60500020 # Characteristics (section flags) + # + # The offset & size fields are filled in by build.c. + # + .ascii ".bss" + .byte 0 + .byte 0 + .byte 0 + .byte 0 + .long 0 + .long 0x0 + .long 0 # Size of initialized data + # on disk + .long 0x0 + .long 0 # PointerToRelocations + .long 0 # PointerToLineNumbers + .word 0 # NumberOfRelocations + .word 0 # NumberOfLineNumbers + .long 0xc8000080 # Characteristics (section flags) + #endif /* CONFIG_EFI_STUB */ # Kernel attributes; used by setup. This is part 1 of the diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index 1a2f2121cad..a7661c430cd 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -143,7 +143,7 @@ static void usage(void) #ifdef CONFIG_EFI_STUB -static void update_pecoff_section_header(char *section_name, u32 offset, u32 size) +static void update_pecoff_section_header_fields(char *section_name, u32 vma, u32 size, u32 datasz, u32 offset) { unsigned int pe_header; unsigned short num_sections; @@ -164,10 +164,10 @@ static void update_pecoff_section_header(char *section_name, u32 offset, u32 siz put_unaligned_le32(size, section + 0x8); /* section header vma field */ - put_unaligned_le32(offset, section + 0xc); + put_unaligned_le32(vma, section + 0xc); /* section header 'size of initialised data' field */ - put_unaligned_le32(size, section + 0x10); + put_unaligned_le32(datasz, section + 0x10); /* section header 'file offset' field */ put_unaligned_le32(offset, section + 0x14); @@ -179,6 +179,11 @@ static void update_pecoff_section_header(char *section_name, u32 offset, u32 siz } } +static void update_pecoff_section_header(char *section_name, u32 offset, u32 size) +{ + update_pecoff_section_header_fields(section_name, offset, size, size, offset); +} + static void update_pecoff_setup_and_reloc(unsigned int size) { u32 setup_offset = 0x200; @@ -203,9 +208,6 @@ static void update_pecoff_text(unsigned int text_start, unsigned int file_sz) pe_header = get_unaligned_le32(&buf[0x3c]); - /* Size of image */ - put_unaligned_le32(file_sz, &buf[pe_header + 0x50]); - /* * Size of code: Subtract the size of the first sector (512 bytes) * which includes the header. @@ -220,6 +222,22 @@ static void update_pecoff_text(unsigned int text_start, unsigned int file_sz) update_pecoff_section_header(".text", text_start, text_sz); } +static void update_pecoff_bss(unsigned int file_sz, unsigned int init_sz) +{ + unsigned int pe_header; + unsigned int bss_sz = init_sz - file_sz; + + pe_header = get_unaligned_le32(&buf[0x3c]); + + /* Size of uninitialized data */ + put_unaligned_le32(bss_sz, &buf[pe_header + 0x24]); + + /* Size of image */ + put_unaligned_le32(init_sz, &buf[pe_header + 0x50]); + + update_pecoff_section_header_fields(".bss", file_sz, bss_sz, 0, 0); +} + static int reserve_pecoff_reloc_section(int c) { /* Reserve 0x20 bytes for .reloc section */ @@ -259,6 +277,8 @@ static void efi_stub_entry_update(void) static inline void update_pecoff_setup_and_reloc(unsigned int size) {} static inline void update_pecoff_text(unsigned int text_start, unsigned int file_sz) {} +static inline void update_pecoff_bss(unsigned int file_sz, + unsigned int init_sz) {} static inline void efi_stub_defaults(void) {} static inline void efi_stub_entry_update(void) {} @@ -310,7 +330,7 @@ static void parse_zoffset(char *fname) int main(int argc, char ** argv) { - unsigned int i, sz, setup_sectors; + unsigned int i, sz, setup_sectors, init_sz; int c; u32 sys_size; struct stat sb; @@ -376,7 +396,9 @@ int main(int argc, char ** argv) buf[0x1f1] = setup_sectors-1; put_unaligned_le32(sys_size, &buf[0x1f4]); - update_pecoff_text(setup_sectors * 512, sz + i + ((sys_size * 16) - sz)); + update_pecoff_text(setup_sectors * 512, i + (sys_size * 16)); + init_sz = get_unaligned_le32(&buf[0x260]); + update_pecoff_bss(i + (sys_size * 16), init_sz); efi_stub_entry_update(); diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index f3a1f04ed4c..58487445141 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -841,7 +841,6 @@ static int apm_do_idle(void) u32 eax; u8 ret = 0; int idled = 0; - int polling; int err = 0; if (!need_resched()) { diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index 6afbb16e9b7..94d857fb103 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -175,7 +175,7 @@ void init_espfix_ap(void) if (!pud_present(pud)) { pmd_p = (pmd_t *)__get_free_page(PGALLOC_GFP); pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask)); - paravirt_alloc_pud(&init_mm, __pa(pmd_p) >> PAGE_SHIFT); + paravirt_alloc_pmd(&init_mm, __pa(pmd_p) >> PAGE_SHIFT); for (n = 0; n < ESPFIX_PUD_CLONES; n++) set_pud(&pud_p[n], pud); } @@ -185,7 +185,7 @@ void init_espfix_ap(void) if (!pmd_present(pmd)) { pte_p = (pte_t *)__get_free_page(PGALLOC_GFP); pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask)); - paravirt_alloc_pmd(&init_mm, __pa(pte_p) >> PAGE_SHIFT); + paravirt_alloc_pte(&init_mm, __pa(pte_p) >> PAGE_SHIFT); for (n = 0; n < ESPFIX_PMD_CLONES; n++) set_pmd(&pmd_p[n], pmd); } @@ -193,7 +193,6 @@ void init_espfix_ap(void) pte_p = pte_offset_kernel(&pmd, addr); stack_page = (void *)__get_free_page(GFP_KERNEL); pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask)); - paravirt_alloc_pte(&init_mm, __pa(stack_page) >> PAGE_SHIFT); for (n = 0; n < ESPFIX_PTE_CLONES; n++) set_pte(&pte_p[n*PTE_STRIDE], pte); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index f6449334ec4..ef432f891d3 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5887,6 +5887,18 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) kvm_x86_ops->set_nmi(vcpu); } } else if (kvm_cpu_has_injectable_intr(vcpu)) { + /* + * Because interrupts can be injected asynchronously, we are + * calling check_nested_events again here to avoid a race condition. + * See https://lkml.org/lkml/2014/7/2/60 for discussion about this + * proposal and current concerns. Perhaps we should be setting + * KVM_REQ_EVENT only on certain events and not unconditionally? + */ + if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) { + r = kvm_x86_ops->check_nested_events(vcpu, req_int_win); + if (r != 0) + return r; + } if (kvm_x86_ops->interrupt_allowed(vcpu)) { kvm_queue_interrupt(vcpu, kvm_cpu_get_interrupt(vcpu), false); diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index b9f4cc494ec..28d227c5ca7 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -872,6 +872,13 @@ void blkcg_drain_queue(struct request_queue *q) { lockdep_assert_held(q->queue_lock); + /* + * @q could be exiting and already have destroyed all blkgs as + * indicated by NULL root_blkg. If so, don't confuse policies. + */ + if (!q->root_blkg) + return; + blk_throtl_drain(q); } diff --git a/block/blk-tag.c b/block/blk-tag.c index 3f33d867226..a185b86741e 100644 --- a/block/blk-tag.c +++ b/block/blk-tag.c @@ -27,18 +27,15 @@ struct request *blk_queue_find_tag(struct request_queue *q, int tag) EXPORT_SYMBOL(blk_queue_find_tag); /** - * __blk_free_tags - release a given set of tag maintenance info + * blk_free_tags - release a given set of tag maintenance info * @bqt: the tag map to free * - * Tries to free the specified @bqt. Returns true if it was - * actually freed and false if there are still references using it + * Drop the reference count on @bqt and frees it when the last reference + * is dropped. */ -static int __blk_free_tags(struct blk_queue_tag *bqt) +void blk_free_tags(struct blk_queue_tag *bqt) { - int retval; - - retval = atomic_dec_and_test(&bqt->refcnt); - if (retval) { + if (atomic_dec_and_test(&bqt->refcnt)) { BUG_ON(find_first_bit(bqt->tag_map, bqt->max_depth) < bqt->max_depth); @@ -50,9 +47,8 @@ static int __blk_free_tags(struct blk_queue_tag *bqt) kfree(bqt); } - - return retval; } +EXPORT_SYMBOL(blk_free_tags); /** * __blk_queue_free_tags - release tag maintenance info @@ -69,28 +65,13 @@ void __blk_queue_free_tags(struct request_queue *q) if (!bqt) return; - __blk_free_tags(bqt); + blk_free_tags(bqt); q->queue_tags = NULL; queue_flag_clear_unlocked(QUEUE_FLAG_QUEUED, q); } /** - * blk_free_tags - release a given set of tag maintenance info - * @bqt: the tag map to free - * - * For externally managed @bqt frees the map. Callers of this - * function must guarantee to have released all the queues that - * might have been using this tag map. - */ -void blk_free_tags(struct blk_queue_tag *bqt) -{ - if (unlikely(!__blk_free_tags(bqt))) - BUG(); -} -EXPORT_SYMBOL(blk_free_tags); - -/** * blk_queue_free_tags - release tag maintenance info * @q: the request queue for the device * diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c index fbd5a67cb77..a0926a6094b 100644 --- a/block/compat_ioctl.c +++ b/block/compat_ioctl.c @@ -690,6 +690,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) case BLKROSET: case BLKDISCARD: case BLKSECDISCARD: + case BLKZEROOUT: /* * the ones below are implemented in blkdev_locked_ioctl, * but we call blkdev_ioctl, which gets the lock for us diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c index 071c1dfb93f..350d52a8f78 100644 --- a/drivers/acpi/video.c +++ b/drivers/acpi/video.c @@ -68,7 +68,7 @@ MODULE_AUTHOR("Bruno Ducrot"); MODULE_DESCRIPTION("ACPI Video Driver"); MODULE_LICENSE("GPL"); -static bool brightness_switch_enabled; +static bool brightness_switch_enabled = 1; module_param(brightness_switch_enabled, bool, 0644); /* @@ -581,6 +581,14 @@ static struct dmi_system_id video_dmi_table[] __initdata = { }, { .callback = video_set_use_native_backlight, + .ident = "HP ProBook 4540s", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_VERSION, "HP ProBook 4540s"), + }, + }, + { + .callback = video_set_use_native_backlight, .ident = "HP ProBook 2013 models", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index dae5607e111..4cd52a4541a 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -456,6 +456,7 @@ static const struct pci_device_id ahci_pci_tbl[] = { /* Promise */ { PCI_VDEVICE(PROMISE, 0x3f20), board_ahci }, /* PDC42819 */ + { PCI_VDEVICE(PROMISE, 0x3781), board_ahci }, /* FastTrak TX8660 ahci-mode */ /* Asmedia */ { PCI_VDEVICE(ASMEDIA, 0x0601), board_ahci }, /* ASM1060 */ diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 18d97d5c7d9..d19c37a7abc 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4787,6 +4787,10 @@ void swap_buf_le16(u16 *buf, unsigned int buf_words) * ata_qc_new - Request an available ATA command, for queueing * @ap: target port * + * Some ATA host controllers may implement a queue depth which is less + * than ATA_MAX_QUEUE. So we shouldn't allocate a tag which is beyond + * the hardware limitation. + * * LOCKING: * None. */ @@ -4794,14 +4798,16 @@ void swap_buf_le16(u16 *buf, unsigned int buf_words) static struct ata_queued_cmd *ata_qc_new(struct ata_port *ap) { struct ata_queued_cmd *qc = NULL; - unsigned int i, tag; + unsigned int i, tag, max_queue; + + max_queue = ap->scsi_host->can_queue; /* no command while frozen */ if (unlikely(ap->pflags & ATA_PFLAG_FROZEN)) return NULL; - for (i = 0; i < ATA_MAX_QUEUE; i++) { - tag = (i + ap->last_tag + 1) % ATA_MAX_QUEUE; + for (i = 0, tag = ap->last_tag + 1; i < max_queue; i++, tag++) { + tag = tag < max_queue ? tag : 0; /* the last tag is reserved for internal command. */ if (tag == ATA_TAG_INTERNAL) @@ -6169,6 +6175,16 @@ int ata_host_register(struct ata_host *host, struct scsi_host_template *sht) { int i, rc; + /* + * The max queue supported by hardware must not be greater than + * ATA_MAX_QUEUE. + */ + if (sht->can_queue > ATA_MAX_QUEUE) { + dev_err(host->dev, "BUG: the hardware max queue is too large\n"); + WARN_ON(1); + return -EINVAL; + } + /* host must have been started */ if (!(host->flags & ATA_HOST_STARTED)) { dev_err(host->dev, "BUG: trying to register unstarted host\n"); diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index 6760fc4e85b..dad83df555c 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -1811,7 +1811,7 @@ static unsigned int ata_eh_analyze_tf(struct ata_queued_cmd *qc, case ATA_DEV_ATA: if (err & ATA_ICRC) qc->err_mask |= AC_ERR_ATA_BUS; - if (err & ATA_UNC) + if (err & (ATA_UNC | ATA_AMNF)) qc->err_mask |= AC_ERR_MEDIA; if (err & ATA_IDNF) qc->err_mask |= AC_ERR_INVALID; @@ -2556,11 +2556,12 @@ static void ata_eh_link_report(struct ata_link *link) } if (cmd->command != ATA_CMD_PACKET && - (res->feature & (ATA_ICRC | ATA_UNC | ATA_IDNF | - ATA_ABORTED))) - ata_dev_err(qc->dev, "error: { %s%s%s%s}\n", + (res->feature & (ATA_ICRC | ATA_UNC | ATA_AMNF | + ATA_IDNF | ATA_ABORTED))) + ata_dev_err(qc->dev, "error: { %s%s%s%s%s}\n", res->feature & ATA_ICRC ? "ICRC " : "", res->feature & ATA_UNC ? "UNC " : "", + res->feature & ATA_AMNF ? "AMNF " : "", res->feature & ATA_IDNF ? "IDNF " : "", res->feature & ATA_ABORTED ? "ABRT " : ""); #endif diff --git a/drivers/ata/pata_ep93xx.c b/drivers/ata/pata_ep93xx.c index 6ad5c072ce3..4d37c5415fc 100644 --- a/drivers/ata/pata_ep93xx.c +++ b/drivers/ata/pata_ep93xx.c @@ -915,7 +915,7 @@ static int ep93xx_pata_probe(struct platform_device *pdev) struct ep93xx_pata_data *drv_data; struct ata_host *host; struct ata_port *ap; - unsigned int irq; + int irq; struct resource *mem_res; void __iomem *ide_base; int err; diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 9e9227e1762..eee48c49f5d 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -89,8 +89,13 @@ int platform_get_irq(struct platform_device *dev, unsigned int num) return dev->archdata.irqs[num]; #else struct resource *r; - if (IS_ENABLED(CONFIG_OF_IRQ) && dev->dev.of_node) - return of_irq_get(dev->dev.of_node, num); + if (IS_ENABLED(CONFIG_OF_IRQ) && dev->dev.of_node) { + int ret; + + ret = of_irq_get(dev->dev.of_node, num); + if (ret >= 0 || ret == -EPROBE_DEFER) + return ret; + } r = platform_get_resource(dev, IORESOURCE_IRQ, num); @@ -133,8 +138,13 @@ int platform_get_irq_byname(struct platform_device *dev, const char *name) { struct resource *r; - if (IS_ENABLED(CONFIG_OF_IRQ) && dev->dev.of_node) - return of_irq_get_byname(dev->dev.of_node, name); + if (IS_ENABLED(CONFIG_OF_IRQ) && dev->dev.of_node) { + int ret; + + ret = of_irq_get_byname(dev->dev.of_node, name); + if (ret >= 0 || ret == -EPROBE_DEFER) + return ret; + } r = platform_get_resource_byname(dev, IORESOURCE_IRQ, name); return r ? r->start : -ENXIO; diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index 1b35c45c92b..3f2e1673808 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -544,6 +544,12 @@ void conn_try_outdate_peer_async(struct drbd_connection *connection) struct task_struct *opa; kref_get(&connection->kref); + /* We may just have force_sig()'ed this thread + * to get it out of some blocking network function. + * Clear signals; otherwise kthread_run(), which internally uses + * wait_on_completion_killable(), will mistake our pending signal + * for a new fatal signal and fail. */ + flush_signals(current); opa = kthread_run(_try_outdate_peer_async, connection, "drbd_async_h"); if (IS_ERR(opa)) { drbd_err(connection, "out of mem, failed to invoke fence-peer helper\n"); diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c index 334601cc81c..c4419ea1ab0 100644 --- a/drivers/char/hw_random/core.c +++ b/drivers/char/hw_random/core.c @@ -55,16 +55,41 @@ static DEFINE_MUTEX(rng_mutex); static int data_avail; static u8 *rng_buffer; +static inline int rng_get_data(struct hwrng *rng, u8 *buffer, size_t size, + int wait); + static size_t rng_buffer_size(void) { return SMP_CACHE_BYTES < 32 ? 32 : SMP_CACHE_BYTES; } +static void add_early_randomness(struct hwrng *rng) +{ + unsigned char bytes[16]; + int bytes_read; + + /* + * Currently only virtio-rng cannot return data during device + * probe, and that's handled in virtio-rng.c itself. If there + * are more such devices, this call to rng_get_data can be + * made conditional here instead of doing it per-device. + */ + bytes_read = rng_get_data(rng, bytes, sizeof(bytes), 1); + if (bytes_read > 0) + add_device_randomness(bytes, bytes_read); +} + static inline int hwrng_init(struct hwrng *rng) { - if (!rng->init) - return 0; - return rng->init(rng); + if (rng->init) { + int ret; + + ret = rng->init(rng); + if (ret) + return ret; + } + add_early_randomness(rng); + return 0; } static inline void hwrng_cleanup(struct hwrng *rng) @@ -304,8 +329,6 @@ int hwrng_register(struct hwrng *rng) { int err = -EINVAL; struct hwrng *old_rng, *tmp; - unsigned char bytes[16]; - int bytes_read; if (rng->name == NULL || (rng->data_read == NULL && rng->read == NULL)) @@ -347,9 +370,17 @@ int hwrng_register(struct hwrng *rng) INIT_LIST_HEAD(&rng->list); list_add_tail(&rng->list, &rng_list); - bytes_read = rng_get_data(rng, bytes, sizeof(bytes), 1); - if (bytes_read > 0) - add_device_randomness(bytes, bytes_read); + if (old_rng && !rng->init) { + /* + * Use a new device's input to add some randomness to + * the system. If this rng device isn't going to be + * used right away, its init function hasn't been + * called yet; so only use the randomness from devices + * that don't need an init callback. + */ + add_early_randomness(rng); + } + out_unlock: mutex_unlock(&rng_mutex); out: diff --git a/drivers/char/hw_random/virtio-rng.c b/drivers/char/hw_random/virtio-rng.c index f3e71501de5..e9b15bc18b4 100644 --- a/drivers/char/hw_random/virtio-rng.c +++ b/drivers/char/hw_random/virtio-rng.c @@ -38,6 +38,8 @@ struct virtrng_info { int index; }; +static bool probe_done; + static void random_recv_done(struct virtqueue *vq) { struct virtrng_info *vi = vq->vdev->priv; @@ -67,6 +69,13 @@ static int virtio_read(struct hwrng *rng, void *buf, size_t size, bool wait) int ret; struct virtrng_info *vi = (struct virtrng_info *)rng->priv; + /* + * Don't ask host for data till we're setup. This call can + * happen during hwrng_register(), after commit d9e7972619. + */ + if (unlikely(!probe_done)) + return 0; + if (!vi->busy) { vi->busy = true; init_completion(&vi->have_data); @@ -137,6 +146,7 @@ static int probe_common(struct virtio_device *vdev) return err; } + probe_done = true; return 0; } diff --git a/drivers/char/random.c b/drivers/char/random.c index 0a7ac0a7b25..71529e196b8 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -641,7 +641,7 @@ retry: } while (unlikely(entropy_count < pool_size-2 && pnfrac)); } - if (entropy_count < 0) { + if (unlikely(entropy_count < 0)) { pr_warn("random: negative entropy/overflow: pool %s count %d\n", r->name, entropy_count); WARN_ON(1); @@ -981,7 +981,7 @@ static size_t account(struct entropy_store *r, size_t nbytes, int min, int reserved) { int entropy_count, orig; - size_t ibytes; + size_t ibytes, nfrac; BUG_ON(r->entropy_count > r->poolinfo->poolfracbits); @@ -999,7 +999,17 @@ retry: } if (ibytes < min) ibytes = 0; - if ((entropy_count -= ibytes << (ENTROPY_SHIFT + 3)) < 0) + + if (unlikely(entropy_count < 0)) { + pr_warn("random: negative entropy count: pool %s count %d\n", + r->name, entropy_count); + WARN_ON(1); + entropy_count = 0; + } + nfrac = ibytes << (ENTROPY_SHIFT + 3); + if ((size_t) entropy_count > nfrac) + entropy_count -= nfrac; + else entropy_count = 0; if (cmpxchg(&r->entropy_count, orig, entropy_count) != orig) @@ -1376,6 +1386,7 @@ urandom_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos) "with %d bits of entropy available\n", current->comm, nonblocking_pool.entropy_total); + nbytes = min_t(size_t, nbytes, INT_MAX >> (ENTROPY_SHIFT + 3)); ret = extract_entropy_user(&nonblocking_pool, buf, nbytes); trace_urandom_read(8 * nbytes, ENTROPY_BITS(&nonblocking_pool), diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index ebac6711500..7364a538e05 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -104,6 +104,7 @@ config ARM_IMX6Q_CPUFREQ tristate "Freescale i.MX6 cpufreq support" depends on ARCH_MXC depends on REGULATOR_ANATOP + select PM_OPP help This adds cpufreq driver support for Freescale i.MX6 series SoCs. @@ -118,7 +119,7 @@ config ARM_INTEGRATOR If in doubt, say Y. config ARM_KIRKWOOD_CPUFREQ - def_bool MACH_KIRKWOOD + def_bool ARCH_KIRKWOOD || MACH_KIRKWOOD help This adds the CPUFreq driver for Marvell Kirkwood SoCs. diff --git a/drivers/cpufreq/cpufreq-cpu0.c b/drivers/cpufreq/cpufreq-cpu0.c index ee1ae303a07..86beda9f950 100644 --- a/drivers/cpufreq/cpufreq-cpu0.c +++ b/drivers/cpufreq/cpufreq-cpu0.c @@ -152,11 +152,8 @@ static int cpu0_cpufreq_probe(struct platform_device *pdev) goto out_put_reg; } - ret = of_init_opp_table(cpu_dev); - if (ret) { - pr_err("failed to init OPP table: %d\n", ret); - goto out_put_clk; - } + /* OPPs might be populated at runtime, don't check for error here */ + of_init_opp_table(cpu_dev); ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table); if (ret) { diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 62259d27f03..6f024852c6f 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1153,10 +1153,12 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif) * the creation of a brand new one. So we need to perform this update * by invoking update_policy_cpu(). */ - if (recover_policy && cpu != policy->cpu) + if (recover_policy && cpu != policy->cpu) { update_policy_cpu(policy, cpu); - else + WARN_ON(kobject_move(&policy->kobj, &dev->kobj)); + } else { policy->cpu = cpu; + } cpumask_copy(policy->cpus, cpumask_of(cpu)); diff --git a/drivers/cpufreq/sa1110-cpufreq.c b/drivers/cpufreq/sa1110-cpufreq.c index 546376719d8..b5befc21117 100644 --- a/drivers/cpufreq/sa1110-cpufreq.c +++ b/drivers/cpufreq/sa1110-cpufreq.c @@ -349,7 +349,7 @@ static int __init sa1110_clk_init(void) name = "K4S641632D"; if (machine_is_h3100()) name = "KM416S4030CT"; - if (machine_is_jornada720()) + if (machine_is_jornada720() || machine_is_h3600()) name = "K4S281632B-1H"; if (machine_is_nanoengine()) name = "MT48LC8M16A2TG-75"; diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index eff1a2f22f0..dc79346689e 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -346,6 +346,7 @@ static __initdata struct { struct param_info { int verbose; + int found; void *params; }; @@ -362,16 +363,12 @@ static int __init fdt_find_uefi_params(unsigned long node, const char *uname, (strcmp(uname, "chosen") != 0 && strcmp(uname, "chosen@0") != 0)) return 0; - pr_info("Getting parameters from FDT:\n"); - for (i = 0; i < ARRAY_SIZE(dt_params); i++) { prop = of_get_flat_dt_prop(node, dt_params[i].propname, &len); - if (!prop) { - pr_err("Can't find %s in device tree!\n", - dt_params[i].name); + if (!prop) return 0; - } dest = info->params + dt_params[i].offset; + info->found++; val = of_read_number(prop, len / sizeof(u32)); @@ -390,10 +387,21 @@ static int __init fdt_find_uefi_params(unsigned long node, const char *uname, int __init efi_get_fdt_params(struct efi_fdt_params *params, int verbose) { struct param_info info; + int ret; + + pr_info("Getting EFI parameters from FDT:\n"); info.verbose = verbose; + info.found = 0; info.params = params; - return of_scan_flat_dt(fdt_find_uefi_params, &info); + ret = of_scan_flat_dt(fdt_find_uefi_params, &info); + if (!info.found) + pr_info("UEFI not found.\n"); + else if (!ret) + pr_err("Can't find '%s' in device tree!\n", + dt_params[info.found].name); + + return ret; } #endif /* CONFIG_EFI_PARAMS_FROM_FDT */ diff --git a/drivers/firmware/efi/fdt.c b/drivers/firmware/efi/fdt.c index 82d774161cc..507a3df46a5 100644 --- a/drivers/firmware/efi/fdt.c +++ b/drivers/firmware/efi/fdt.c @@ -23,16 +23,6 @@ static efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt, u32 fdt_val32; u64 fdt_val64; - /* - * Copy definition of linux_banner here. Since this code is - * built as part of the decompressor for ARM v7, pulling - * in version.c where linux_banner is defined for the - * kernel brings other kernel dependencies with it. - */ - const char linux_banner[] = - "Linux version " UTS_RELEASE " (" LINUX_COMPILE_BY "@" - LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION "\n"; - /* Do some checks on provided FDT, if it exists*/ if (orig_fdt) { if (fdt_check_header(orig_fdt)) { diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index e27e7804c0b..f0be855ddf4 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -11673,6 +11673,9 @@ static struct intel_quirk intel_quirks[] = { /* Toshiba CB35 Chromebook (Celeron 2955U) */ { 0x0a06, 0x1179, 0x0a88, quirk_backlight_present }, + + /* HP Chromebook 14 (Celeron 2955U) */ + { 0x0a06, 0x103c, 0x21ed, quirk_backlight_present }, }; static void intel_init_quirks(struct drm_device *dev) @@ -11911,6 +11914,7 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc) * ... */ plane = crtc->plane; crtc->plane = !plane; + crtc->primary_enabled = true; dev_priv->display.crtc_disable(&crtc->base); crtc->plane = plane; diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 075170d1844..8a1a4fbc06a 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -906,8 +906,8 @@ intel_dp_compute_config(struct intel_encoder *encoder, mode_rate = intel_dp_link_required(adjusted_mode->crtc_clock, bpp); - for (lane_count = min_lane_count; lane_count <= max_lane_count; lane_count <<= 1) { - for (clock = min_clock; clock <= max_clock; clock++) { + for (clock = min_clock; clock <= max_clock; clock++) { + for (lane_count = min_lane_count; lane_count <= max_lane_count; lane_count <<= 1) { link_clock = drm_dp_bw_code_to_link_rate(bws[clock]); link_avail = intel_dp_max_data_rate(link_clock, lane_count); diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index 23126023aeb..5e5a72fca5f 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -111,6 +111,13 @@ static void intel_lvds_get_config(struct intel_encoder *encoder, pipe_config->adjusted_mode.flags |= flags; + /* gen2/3 store dither state in pfit control, needs to match */ + if (INTEL_INFO(dev)->gen < 4) { + tmp = I915_READ(PFIT_CONTROL); + + pipe_config->gmch_pfit.control |= tmp & PANEL_8TO6_DITHER_ENABLE; + } + dotclock = pipe_config->port_clock; if (HAS_PCH_SPLIT(dev_priv->dev)) diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c index 628cd893827..12b02fe1d0a 100644 --- a/drivers/gpu/drm/i915/intel_panel.c +++ b/drivers/gpu/drm/i915/intel_panel.c @@ -361,16 +361,16 @@ void intel_gmch_panel_fitting(struct intel_crtc *intel_crtc, pfit_control |= ((intel_crtc->pipe << PFIT_PIPE_SHIFT) | PFIT_FILTER_FUZZY); - /* Make sure pre-965 set dither correctly for 18bpp panels. */ - if (INTEL_INFO(dev)->gen < 4 && pipe_config->pipe_bpp == 18) - pfit_control |= PANEL_8TO6_DITHER_ENABLE; - out: if ((pfit_control & PFIT_ENABLE) == 0) { pfit_control = 0; pfit_pgm_ratios = 0; } + /* Make sure pre-965 set dither correctly for 18bpp panels. */ + if (INTEL_INFO(dev)->gen < 4 && pipe_config->pipe_bpp == 18) + pfit_control |= PANEL_8TO6_DITHER_ENABLE; + pipe_config->gmch_pfit.control = pfit_control; pipe_config->gmch_pfit.pgm_ratios = pfit_pgm_ratios; pipe_config->gmch_pfit.lvds_border_bits = border; diff --git a/drivers/gpu/drm/nouveau/core/subdev/therm/temp.c b/drivers/gpu/drm/nouveau/core/subdev/therm/temp.c index cfde9eb44ad..6212537b90c 100644 --- a/drivers/gpu/drm/nouveau/core/subdev/therm/temp.c +++ b/drivers/gpu/drm/nouveau/core/subdev/therm/temp.c @@ -192,11 +192,11 @@ alarm_timer_callback(struct nouveau_alarm *alarm) nouveau_therm_threshold_hyst_polling(therm, &sensor->thrs_shutdown, NOUVEAU_THERM_THRS_SHUTDOWN); + spin_unlock_irqrestore(&priv->sensor.alarm_program_lock, flags); + /* schedule the next poll in one second */ if (therm->temp_get(therm) >= 0 && list_empty(&alarm->head)) - ptimer->alarm(ptimer, 1000 * 1000 * 1000, alarm); - - spin_unlock_irqrestore(&priv->sensor.alarm_program_lock, flags); + ptimer->alarm(ptimer, 1000000000ULL, alarm); } void diff --git a/drivers/gpu/drm/qxl/qxl_irq.c b/drivers/gpu/drm/qxl/qxl_irq.c index 34d6a85e902..0bf1e20c6e4 100644 --- a/drivers/gpu/drm/qxl/qxl_irq.c +++ b/drivers/gpu/drm/qxl/qxl_irq.c @@ -33,6 +33,9 @@ irqreturn_t qxl_irq_handler(int irq, void *arg) pending = xchg(&qdev->ram_header->int_pending, 0); + if (!pending) + return IRQ_NONE; + atomic_inc(&qdev->irq_received); if (pending & QXL_INTERRUPT_DISPLAY) { diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c index a03c73411a5..30d242b2507 100644 --- a/drivers/gpu/drm/radeon/atombios_crtc.c +++ b/drivers/gpu/drm/radeon/atombios_crtc.c @@ -1414,8 +1414,8 @@ static int dce4_crtc_do_set_base(struct drm_crtc *crtc, tmp &= ~EVERGREEN_GRPH_SURFACE_UPDATE_H_RETRACE_EN; WREG32(EVERGREEN_GRPH_FLIP_CONTROL + radeon_crtc->crtc_offset, tmp); - /* set pageflip to happen anywhere in vblank interval */ - WREG32(EVERGREEN_MASTER_UPDATE_MODE + radeon_crtc->crtc_offset, 0); + /* set pageflip to happen only at start of vblank interval (front porch) */ + WREG32(EVERGREEN_MASTER_UPDATE_MODE + radeon_crtc->crtc_offset, 3); if (!atomic && fb && fb != crtc->primary->fb) { radeon_fb = to_radeon_framebuffer(fb); @@ -1614,8 +1614,8 @@ static int avivo_crtc_do_set_base(struct drm_crtc *crtc, tmp &= ~AVIVO_D1GRPH_SURFACE_UPDATE_H_RETRACE_EN; WREG32(AVIVO_D1GRPH_FLIP_CONTROL + radeon_crtc->crtc_offset, tmp); - /* set pageflip to happen anywhere in vblank interval */ - WREG32(AVIVO_D1MODE_MASTER_UPDATE_MODE + radeon_crtc->crtc_offset, 0); + /* set pageflip to happen only at start of vblank interval (front porch) */ + WREG32(AVIVO_D1MODE_MASTER_UPDATE_MODE + radeon_crtc->crtc_offset, 3); if (!atomic && fb && fb != crtc->primary->fb) { radeon_fb = to_radeon_framebuffer(fb); diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c index 2b290844064..7d68203a373 100644 --- a/drivers/gpu/drm/radeon/atombios_encoders.c +++ b/drivers/gpu/drm/radeon/atombios_encoders.c @@ -183,7 +183,6 @@ void radeon_atom_backlight_init(struct radeon_encoder *radeon_encoder, struct backlight_properties props; struct radeon_backlight_privdata *pdata; struct radeon_encoder_atom_dig *dig; - u8 backlight_level; char bl_name[16]; /* Mac laptops with multiple GPUs use the gmux driver for backlight @@ -222,12 +221,17 @@ void radeon_atom_backlight_init(struct radeon_encoder *radeon_encoder, pdata->encoder = radeon_encoder; - backlight_level = radeon_atom_get_backlight_level_from_reg(rdev); - dig = radeon_encoder->enc_priv; dig->bl_dev = bd; bd->props.brightness = radeon_atom_backlight_get_brightness(bd); + /* Set a reasonable default here if the level is 0 otherwise + * fbdev will attempt to turn the backlight on after console + * unblanking and it will try and restore 0 which turns the backlight + * off again. + */ + if (bd->props.brightness == 0) + bd->props.brightness = RADEON_MAX_BL_LEVEL; bd->props.power = FB_BLANK_UNBLANK; backlight_update_status(bd); diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c index f7ece0ff431..250bac3935a 100644 --- a/drivers/gpu/drm/radeon/evergreen.c +++ b/drivers/gpu/drm/radeon/evergreen.c @@ -2642,8 +2642,9 @@ void evergreen_mc_resume(struct radeon_device *rdev, struct evergreen_mc_save *s for (i = 0; i < rdev->num_crtc; i++) { if (save->crtc_enabled[i]) { tmp = RREG32(EVERGREEN_MASTER_UPDATE_MODE + crtc_offsets[i]); - if ((tmp & 0x3) != 0) { - tmp &= ~0x3; + if ((tmp & 0x7) != 3) { + tmp &= ~0x7; + tmp |= 0x3; WREG32(EVERGREEN_MASTER_UPDATE_MODE + crtc_offsets[i], tmp); } tmp = RREG32(EVERGREEN_GRPH_UPDATE + crtc_offsets[i]); diff --git a/drivers/gpu/drm/radeon/evergreen_reg.h b/drivers/gpu/drm/radeon/evergreen_reg.h index 333d143fca2..23bff590fb6 100644 --- a/drivers/gpu/drm/radeon/evergreen_reg.h +++ b/drivers/gpu/drm/radeon/evergreen_reg.h @@ -239,7 +239,6 @@ # define EVERGREEN_CRTC_V_BLANK (1 << 0) #define EVERGREEN_CRTC_STATUS_POSITION 0x6e90 #define EVERGREEN_CRTC_STATUS_HV_COUNT 0x6ea0 -#define EVERGREEN_MASTER_UPDATE_MODE 0x6ef8 #define EVERGREEN_CRTC_UPDATE_LOCK 0x6ed4 #define EVERGREEN_MASTER_UPDATE_LOCK 0x6ef4 #define EVERGREEN_MASTER_UPDATE_MODE 0x6ef8 diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 29d9cc04c04..b7204500a9a 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -684,10 +684,9 @@ struct radeon_flip_work { struct work_struct unpin_work; struct radeon_device *rdev; int crtc_id; - struct drm_framebuffer *fb; + uint64_t base; struct drm_pending_vblank_event *event; struct radeon_bo *old_rbo; - struct radeon_bo *new_rbo; struct radeon_fence *fence; }; diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index 13896edcf0b..bf25061c8ac 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -366,7 +366,6 @@ void radeon_crtc_handle_flip(struct radeon_device *rdev, int crtc_id) spin_unlock_irqrestore(&rdev->ddev->event_lock, flags); drm_vblank_put(rdev->ddev, radeon_crtc->crtc_id); - radeon_fence_unref(&work->fence); radeon_irq_kms_pflip_irq_put(rdev, work->crtc_id); queue_work(radeon_crtc->flip_queue, &work->unpin_work); } @@ -386,51 +385,108 @@ static void radeon_flip_work_func(struct work_struct *__work) struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[work->crtc_id]; struct drm_crtc *crtc = &radeon_crtc->base; - struct drm_framebuffer *fb = work->fb; - - uint32_t tiling_flags, pitch_pixels; - uint64_t base; - unsigned long flags; int r; down_read(&rdev->exclusive_lock); - while (work->fence) { + if (work->fence) { r = radeon_fence_wait(work->fence, false); if (r == -EDEADLK) { up_read(&rdev->exclusive_lock); r = radeon_gpu_reset(rdev); down_read(&rdev->exclusive_lock); } + if (r) + DRM_ERROR("failed to wait on page flip fence (%d)!\n", r); - if (r) { - DRM_ERROR("failed to wait on page flip fence (%d)!\n", - r); - goto cleanup; - } else - radeon_fence_unref(&work->fence); + /* We continue with the page flip even if we failed to wait on + * the fence, otherwise the DRM core and userspace will be + * confused about which BO the CRTC is scanning out + */ + + radeon_fence_unref(&work->fence); } + /* We borrow the event spin lock for protecting flip_status */ + spin_lock_irqsave(&crtc->dev->event_lock, flags); + + /* set the proper interrupt */ + radeon_irq_kms_pflip_irq_get(rdev, radeon_crtc->crtc_id); + + /* do the flip (mmio) */ + radeon_page_flip(rdev, radeon_crtc->crtc_id, work->base); + + radeon_crtc->flip_status = RADEON_FLIP_SUBMITTED; + spin_unlock_irqrestore(&crtc->dev->event_lock, flags); + up_read(&rdev->exclusive_lock); +} + +static int radeon_crtc_page_flip(struct drm_crtc *crtc, + struct drm_framebuffer *fb, + struct drm_pending_vblank_event *event, + uint32_t page_flip_flags) +{ + struct drm_device *dev = crtc->dev; + struct radeon_device *rdev = dev->dev_private; + struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc); + struct radeon_framebuffer *old_radeon_fb; + struct radeon_framebuffer *new_radeon_fb; + struct drm_gem_object *obj; + struct radeon_flip_work *work; + struct radeon_bo *new_rbo; + uint32_t tiling_flags, pitch_pixels; + uint64_t base; + unsigned long flags; + int r; + + work = kzalloc(sizeof *work, GFP_KERNEL); + if (work == NULL) + return -ENOMEM; + + INIT_WORK(&work->flip_work, radeon_flip_work_func); + INIT_WORK(&work->unpin_work, radeon_unpin_work_func); + + work->rdev = rdev; + work->crtc_id = radeon_crtc->crtc_id; + work->event = event; + + /* schedule unpin of the old buffer */ + old_radeon_fb = to_radeon_framebuffer(crtc->primary->fb); + obj = old_radeon_fb->obj; + + /* take a reference to the old object */ + drm_gem_object_reference(obj); + work->old_rbo = gem_to_radeon_bo(obj); + + new_radeon_fb = to_radeon_framebuffer(fb); + obj = new_radeon_fb->obj; + new_rbo = gem_to_radeon_bo(obj); + + spin_lock(&new_rbo->tbo.bdev->fence_lock); + if (new_rbo->tbo.sync_obj) + work->fence = radeon_fence_ref(new_rbo->tbo.sync_obj); + spin_unlock(&new_rbo->tbo.bdev->fence_lock); + /* pin the new buffer */ - DRM_DEBUG_DRIVER("flip-ioctl() cur_fbo = %p, cur_bbo = %p\n", - work->old_rbo, work->new_rbo); + DRM_DEBUG_DRIVER("flip-ioctl() cur_rbo = %p, new_rbo = %p\n", + work->old_rbo, new_rbo); - r = radeon_bo_reserve(work->new_rbo, false); + r = radeon_bo_reserve(new_rbo, false); if (unlikely(r != 0)) { DRM_ERROR("failed to reserve new rbo buffer before flip\n"); goto cleanup; } /* Only 27 bit offset for legacy CRTC */ - r = radeon_bo_pin_restricted(work->new_rbo, RADEON_GEM_DOMAIN_VRAM, + r = radeon_bo_pin_restricted(new_rbo, RADEON_GEM_DOMAIN_VRAM, ASIC_IS_AVIVO(rdev) ? 0 : 1 << 27, &base); if (unlikely(r != 0)) { - radeon_bo_unreserve(work->new_rbo); + radeon_bo_unreserve(new_rbo); r = -EINVAL; DRM_ERROR("failed to pin new rbo buffer before flip\n"); goto cleanup; } - radeon_bo_get_tiling_flags(work->new_rbo, &tiling_flags, NULL); - radeon_bo_unreserve(work->new_rbo); + radeon_bo_get_tiling_flags(new_rbo, &tiling_flags, NULL); + radeon_bo_unreserve(new_rbo); if (!ASIC_IS_AVIVO(rdev)) { /* crtc offset is from display base addr not FB location */ @@ -467,6 +523,7 @@ static void radeon_flip_work_func(struct work_struct *__work) } base &= ~7; } + work->base = base; r = drm_vblank_get(crtc->dev, radeon_crtc->crtc_id); if (r) { @@ -477,100 +534,42 @@ static void radeon_flip_work_func(struct work_struct *__work) /* We borrow the event spin lock for protecting flip_work */ spin_lock_irqsave(&crtc->dev->event_lock, flags); - /* set the proper interrupt */ - radeon_irq_kms_pflip_irq_get(rdev, radeon_crtc->crtc_id); + if (radeon_crtc->flip_status != RADEON_FLIP_NONE) { + DRM_DEBUG_DRIVER("flip queue: crtc already busy\n"); + spin_unlock_irqrestore(&crtc->dev->event_lock, flags); + r = -EBUSY; + goto vblank_cleanup; + } + radeon_crtc->flip_status = RADEON_FLIP_PENDING; + radeon_crtc->flip_work = work; - /* do the flip (mmio) */ - radeon_page_flip(rdev, radeon_crtc->crtc_id, base); + /* update crtc fb */ + crtc->primary->fb = fb; - radeon_crtc->flip_status = RADEON_FLIP_SUBMITTED; spin_unlock_irqrestore(&crtc->dev->event_lock, flags); - up_read(&rdev->exclusive_lock); - return; + queue_work(radeon_crtc->flip_queue, &work->flip_work); + return 0; + +vblank_cleanup: + drm_vblank_put(crtc->dev, radeon_crtc->crtc_id); pflip_cleanup: - if (unlikely(radeon_bo_reserve(work->new_rbo, false) != 0)) { + if (unlikely(radeon_bo_reserve(new_rbo, false) != 0)) { DRM_ERROR("failed to reserve new rbo in error path\n"); goto cleanup; } - if (unlikely(radeon_bo_unpin(work->new_rbo) != 0)) { + if (unlikely(radeon_bo_unpin(new_rbo) != 0)) { DRM_ERROR("failed to unpin new rbo in error path\n"); } - radeon_bo_unreserve(work->new_rbo); + radeon_bo_unreserve(new_rbo); cleanup: drm_gem_object_unreference_unlocked(&work->old_rbo->gem_base); radeon_fence_unref(&work->fence); kfree(work); - up_read(&rdev->exclusive_lock); -} - -static int radeon_crtc_page_flip(struct drm_crtc *crtc, - struct drm_framebuffer *fb, - struct drm_pending_vblank_event *event, - uint32_t page_flip_flags) -{ - struct drm_device *dev = crtc->dev; - struct radeon_device *rdev = dev->dev_private; - struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc); - struct radeon_framebuffer *old_radeon_fb; - struct radeon_framebuffer *new_radeon_fb; - struct drm_gem_object *obj; - struct radeon_flip_work *work; - unsigned long flags; - - work = kzalloc(sizeof *work, GFP_KERNEL); - if (work == NULL) - return -ENOMEM; - - INIT_WORK(&work->flip_work, radeon_flip_work_func); - INIT_WORK(&work->unpin_work, radeon_unpin_work_func); - - work->rdev = rdev; - work->crtc_id = radeon_crtc->crtc_id; - work->fb = fb; - work->event = event; - - /* schedule unpin of the old buffer */ - old_radeon_fb = to_radeon_framebuffer(crtc->primary->fb); - obj = old_radeon_fb->obj; - - /* take a reference to the old object */ - drm_gem_object_reference(obj); - work->old_rbo = gem_to_radeon_bo(obj); - - new_radeon_fb = to_radeon_framebuffer(fb); - obj = new_radeon_fb->obj; - work->new_rbo = gem_to_radeon_bo(obj); - - spin_lock(&work->new_rbo->tbo.bdev->fence_lock); - if (work->new_rbo->tbo.sync_obj) - work->fence = radeon_fence_ref(work->new_rbo->tbo.sync_obj); - spin_unlock(&work->new_rbo->tbo.bdev->fence_lock); - - /* We borrow the event spin lock for protecting flip_work */ - spin_lock_irqsave(&crtc->dev->event_lock, flags); - if (radeon_crtc->flip_status != RADEON_FLIP_NONE) { - DRM_DEBUG_DRIVER("flip queue: crtc already busy\n"); - spin_unlock_irqrestore(&crtc->dev->event_lock, flags); - drm_gem_object_unreference_unlocked(&work->old_rbo->gem_base); - radeon_fence_unref(&work->fence); - kfree(work); - return -EBUSY; - } - radeon_crtc->flip_status = RADEON_FLIP_PENDING; - radeon_crtc->flip_work = work; - - /* update crtc fb */ - crtc->primary->fb = fb; - - spin_unlock_irqrestore(&crtc->dev->event_lock, flags); - - queue_work(radeon_crtc->flip_queue, &work->flip_work); - - return 0; + return r; } static int @@ -830,6 +829,10 @@ int radeon_ddc_get_modes(struct radeon_connector *radeon_connector) struct radeon_device *rdev = dev->dev_private; int ret = 0; + /* don't leak the edid if we already fetched it in detect() */ + if (radeon_connector->edid) + goto got_edid; + /* on hw with routers, select right port */ if (radeon_connector->router.ddc_valid) radeon_router_select_ddc_port(radeon_connector); @@ -868,6 +871,7 @@ int radeon_ddc_get_modes(struct radeon_connector *radeon_connector) radeon_connector->edid = radeon_bios_get_hardcoded_edid(rdev); } if (radeon_connector->edid) { +got_edid: drm_mode_connector_update_edid_property(&radeon_connector->base, radeon_connector->edid); ret = drm_add_edid_modes(&radeon_connector->base, radeon_connector->edid); drm_edid_to_eld(&radeon_connector->base, radeon_connector->edid); diff --git a/drivers/gpu/drm/radeon/rv515.c b/drivers/gpu/drm/radeon/rv515.c index 237dd29d9f1..3e21e869015 100644 --- a/drivers/gpu/drm/radeon/rv515.c +++ b/drivers/gpu/drm/radeon/rv515.c @@ -406,8 +406,9 @@ void rv515_mc_resume(struct radeon_device *rdev, struct rv515_mc_save *save) for (i = 0; i < rdev->num_crtc; i++) { if (save->crtc_enabled[i]) { tmp = RREG32(AVIVO_D1MODE_MASTER_UPDATE_MODE + crtc_offsets[i]); - if ((tmp & 0x3) != 0) { - tmp &= ~0x3; + if ((tmp & 0x7) != 3) { + tmp &= ~0x7; + tmp |= 0x3; WREG32(AVIVO_D1MODE_MASTER_UPDATE_MODE + crtc_offsets[i], tmp); } tmp = RREG32(AVIVO_D1GRPH_UPDATE + crtc_offsets[i]); diff --git a/drivers/hv/hv_fcopy.c b/drivers/hv/hv_fcopy.c index eaaa3d843b8..23b2ce294c4 100644 --- a/drivers/hv/hv_fcopy.c +++ b/drivers/hv/hv_fcopy.c @@ -246,8 +246,8 @@ void hv_fcopy_onchannelcallback(void *context) /* * Send the information to the user-level daemon. */ - fcopy_send_data(); schedule_delayed_work(&fcopy_work, 5*HZ); + fcopy_send_data(); return; } icmsghdr->icflags = ICMSGHDRFLAG_TRANSACTION | ICMSGHDRFLAG_RESPONSE; diff --git a/drivers/hwmon/adt7470.c b/drivers/hwmon/adt7470.c index 0f4dea5ccf1..9ee3913850d 100644 --- a/drivers/hwmon/adt7470.c +++ b/drivers/hwmon/adt7470.c @@ -515,7 +515,7 @@ static ssize_t set_temp_min(struct device *dev, return -EINVAL; temp = DIV_ROUND_CLOSEST(temp, 1000); - temp = clamp_val(temp, 0, 255); + temp = clamp_val(temp, -128, 127); mutex_lock(&data->lock); data->temp_min[attr->index] = temp; @@ -549,7 +549,7 @@ static ssize_t set_temp_max(struct device *dev, return -EINVAL; temp = DIV_ROUND_CLOSEST(temp, 1000); - temp = clamp_val(temp, 0, 255); + temp = clamp_val(temp, -128, 127); mutex_lock(&data->lock); data->temp_max[attr->index] = temp; @@ -826,7 +826,7 @@ static ssize_t set_pwm_tmin(struct device *dev, return -EINVAL; temp = DIV_ROUND_CLOSEST(temp, 1000); - temp = clamp_val(temp, 0, 255); + temp = clamp_val(temp, -128, 127); mutex_lock(&data->lock); data->pwm_tmin[attr->index] = temp; diff --git a/drivers/hwmon/da9052-hwmon.c b/drivers/hwmon/da9052-hwmon.c index afd31042b45..d14ab3c45da 100644 --- a/drivers/hwmon/da9052-hwmon.c +++ b/drivers/hwmon/da9052-hwmon.c @@ -194,7 +194,7 @@ static ssize_t da9052_hwmon_show_name(struct device *dev, struct device_attribute *devattr, char *buf) { - return sprintf(buf, "da9052-hwmon\n"); + return sprintf(buf, "da9052\n"); } static ssize_t show_label(struct device *dev, diff --git a/drivers/hwmon/da9055-hwmon.c b/drivers/hwmon/da9055-hwmon.c index 73b3865f120..35eb7738d71 100644 --- a/drivers/hwmon/da9055-hwmon.c +++ b/drivers/hwmon/da9055-hwmon.c @@ -204,7 +204,7 @@ static ssize_t da9055_hwmon_show_name(struct device *dev, struct device_attribute *devattr, char *buf) { - return sprintf(buf, "da9055-hwmon\n"); + return sprintf(buf, "da9055\n"); } static ssize_t show_label(struct device *dev, diff --git a/drivers/ide/Kconfig b/drivers/ide/Kconfig index 8fb46aab2d8..a04c49f2a01 100644 --- a/drivers/ide/Kconfig +++ b/drivers/ide/Kconfig @@ -416,6 +416,7 @@ config BLK_DEV_CY82C693 config BLK_DEV_CS5520 tristate "Cyrix CS5510/20 MediaGX chipset support (VERY EXPERIMENTAL)" + depends on X86_32 || COMPILE_TEST select BLK_DEV_IDEDMA_PCI help Include support for PIO tuning and virtual DMA on the Cyrix MediaGX @@ -426,6 +427,7 @@ config BLK_DEV_CS5520 config BLK_DEV_CS5530 tristate "Cyrix/National Semiconductor CS5530 MediaGX chipset support" + depends on X86_32 || COMPILE_TEST select BLK_DEV_IDEDMA_PCI help Include support for UDMA on the Cyrix MediaGX 5530 chipset. This @@ -435,7 +437,7 @@ config BLK_DEV_CS5530 config BLK_DEV_CS5535 tristate "AMD CS5535 chipset support" - depends on X86 && !X86_64 + depends on X86_32 select BLK_DEV_IDEDMA_PCI help Include support for UDMA on the NSC/AMD CS5535 companion chipset. @@ -486,6 +488,7 @@ config BLK_DEV_JMICRON config BLK_DEV_SC1200 tristate "National SCx200 chipset support" + depends on X86_32 || COMPILE_TEST select BLK_DEV_IDEDMA_PCI help This driver adds support for the on-board IDE controller on the diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c index 2a744a91370..a3d3b1733c4 100644 --- a/drivers/ide/ide-probe.c +++ b/drivers/ide/ide-probe.c @@ -853,8 +853,9 @@ static int init_irq (ide_hwif_t *hwif) if (irq_handler == NULL) irq_handler = ide_intr; - if (request_irq(hwif->irq, irq_handler, sa, hwif->name, hwif)) - goto out_up; + if (!host->get_lock) + if (request_irq(hwif->irq, irq_handler, sa, hwif->name, hwif)) + goto out_up; #if !defined(__mc68000__) printk(KERN_INFO "%s at 0x%03lx-0x%03lx,0x%03lx on irq %d", hwif->name, @@ -1533,7 +1534,8 @@ static void ide_unregister(ide_hwif_t *hwif) ide_proc_unregister_port(hwif); - free_irq(hwif->irq, hwif); + if (!hwif->host->get_lock) + free_irq(hwif->irq, hwif); device_unregister(hwif->portdev); device_unregister(&hwif->gendev); diff --git a/drivers/iio/accel/mma8452.c b/drivers/iio/accel/mma8452.c index 17aeea17056..2a5fa9a436e 100644 --- a/drivers/iio/accel/mma8452.c +++ b/drivers/iio/accel/mma8452.c @@ -111,8 +111,14 @@ static const int mma8452_samp_freq[8][2] = { {6, 250000}, {1, 560000} }; +/* + * Hardware has fullscale of -2G, -4G, -8G corresponding to raw value -2048 + * The userspace interface uses m/s^2 and we declare micro units + * So scale factor is given by: + * g * N * 1000000 / 2048 for N = 2, 4, 8 and g=9.80665 + */ static const int mma8452_scales[3][2] = { - {0, 977}, {0, 1953}, {0, 3906} + {0, 9577}, {0, 19154}, {0, 38307} }; static ssize_t mma8452_show_samp_freq_avail(struct device *dev, diff --git a/drivers/iio/industrialio-event.c b/drivers/iio/industrialio-event.c index 258a973a1fb..bfbf4d419f4 100644 --- a/drivers/iio/industrialio-event.c +++ b/drivers/iio/industrialio-event.c @@ -345,6 +345,9 @@ static int iio_device_add_event(struct iio_dev *indio_dev, &indio_dev->event_interface->dev_attr_list); kfree(postfix); + if ((ret == -EBUSY) && (shared_by != IIO_SEPARATE)) + continue; + if (ret) return ret; diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index 6d61a16d1f5..c2fb71c182a 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -433,8 +433,17 @@ static void arp_failure_discard(void *handle, struct sk_buff *skb) */ static void act_open_req_arp_failure(void *handle, struct sk_buff *skb) { + struct c4iw_ep *ep = handle; + printk(KERN_ERR MOD "ARP failure duing connect\n"); kfree_skb(skb); + connect_reply_upcall(ep, -EHOSTUNREACH); + state_set(&ep->com, DEAD); + remove_handle(ep->com.dev, &ep->com.dev->atid_idr, ep->atid); + cxgb4_free_atid(ep->com.dev->rdev.lldi.tids, ep->atid); + dst_release(ep->dst); + cxgb4_l2t_release(ep->l2t); + c4iw_put_ep(&ep->com); } /* @@ -660,7 +669,7 @@ static int send_connect(struct c4iw_ep *ep) opt2 |= T5_OPT_2_VALID; opt2 |= V_CONG_CNTRL(CONG_ALG_TAHOE); } - t4_set_arp_err_handler(skb, NULL, act_open_req_arp_failure); + t4_set_arp_err_handler(skb, ep, act_open_req_arp_failure); if (is_t4(ep->com.dev->rdev.lldi.adapter_type)) { if (ep->com.remote_addr.ss_family == AF_INET) { @@ -2219,7 +2228,6 @@ static void reject_cr(struct c4iw_dev *dev, u32 hwtid, struct sk_buff *skb) PDBG("%s c4iw_dev %p tid %u\n", __func__, dev, hwtid); BUG_ON(skb_cloned(skb)); skb_trim(skb, sizeof(struct cpl_tid_release)); - skb_get(skb); release_tid(&dev->rdev, hwtid, skb); return; } @@ -3969,7 +3977,7 @@ int __init c4iw_cm_init(void) return 0; } -void __exit c4iw_cm_term(void) +void c4iw_cm_term(void) { WARN_ON(!list_empty(&timeout_list)); flush_workqueue(workq); diff --git a/drivers/infiniband/hw/cxgb4/device.c b/drivers/infiniband/hw/cxgb4/device.c index bda94922363..f25df5276c2 100644 --- a/drivers/infiniband/hw/cxgb4/device.c +++ b/drivers/infiniband/hw/cxgb4/device.c @@ -844,6 +844,7 @@ static int c4iw_rdev_open(struct c4iw_rdev *rdev) pr_err(MOD "error allocating status page\n"); goto err4; } + if (c4iw_wr_log) { rdev->wr_log = kzalloc((1 << c4iw_wr_log_size_order) * sizeof(*rdev->wr_log), GFP_KERNEL); @@ -854,6 +855,9 @@ static int c4iw_rdev_open(struct c4iw_rdev *rdev) pr_err(MOD "error allocating wr_log. Logging disabled\n"); } } + + rdev->status_page->db_off = 0; + return 0; err4: c4iw_rqtpool_destroy(rdev); @@ -888,7 +892,6 @@ static void c4iw_dealloc(struct uld_ctx *ctx) if (ctx->dev->rdev.oc_mw_kva) iounmap(ctx->dev->rdev.oc_mw_kva); ib_dealloc_device(&ctx->dev->ibdev); - iwpm_exit(RDMA_NL_C4IW); ctx->dev = NULL; } @@ -1007,12 +1010,6 @@ static struct c4iw_dev *c4iw_alloc(const struct cxgb4_lld_info *infop) setup_debugfs(devp); } - ret = iwpm_init(RDMA_NL_C4IW); - if (ret) { - pr_err("port mapper initialization failed with %d\n", ret); - ib_dealloc_device(&devp->ibdev); - return ERR_PTR(ret); - } return devp; } @@ -1513,6 +1510,15 @@ static int __init c4iw_init_module(void) pr_err("%s[%u]: Failed to add netlink callback\n" , __func__, __LINE__); + err = iwpm_init(RDMA_NL_C4IW); + if (err) { + pr_err("port mapper initialization failed with %d\n", err); + ibnl_remove_client(RDMA_NL_C4IW); + c4iw_cm_term(); + debugfs_remove_recursive(c4iw_debugfs_root); + return err; + } + cxgb4_register_uld(CXGB4_ULD_RDMA, &c4iw_uld_info); return 0; @@ -1530,6 +1536,7 @@ static void __exit c4iw_exit_module(void) } mutex_unlock(&dev_mutex); cxgb4_unregister_uld(CXGB4_ULD_RDMA); + iwpm_exit(RDMA_NL_C4IW); ibnl_remove_client(RDMA_NL_C4IW); c4iw_cm_term(); debugfs_remove_recursive(c4iw_debugfs_root); diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h index c378fd25ee0..b5678ac9739 100644 --- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h +++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h @@ -943,7 +943,7 @@ int c4iw_destroy_ctrl_qp(struct c4iw_rdev *rdev); int c4iw_register_device(struct c4iw_dev *dev); void c4iw_unregister_device(struct c4iw_dev *dev); int __init c4iw_cm_init(void); -void __exit c4iw_cm_term(void); +void c4iw_cm_term(void); void c4iw_release_dev_ucontext(struct c4iw_rdev *rdev, struct c4iw_dev_ucontext *uctx); void c4iw_init_dev_ucontext(struct c4iw_rdev *rdev, diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index d13ddf1c003..bbbcf389272 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -675,7 +675,7 @@ static int create_kernel_qp(struct mlx5_ib_dev *dev, int err; uuari = &dev->mdev.priv.uuari; - if (init_attr->create_flags & ~IB_QP_CREATE_SIGNATURE_EN) + if (init_attr->create_flags & ~(IB_QP_CREATE_SIGNATURE_EN | IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK)) return -EINVAL; if (init_attr->qp_type == MLX5_IB_QPT_REG_UMR) diff --git a/drivers/iommu/fsl_pamu.c b/drivers/iommu/fsl_pamu.c index b99dd88e31b..bb446d742a2 100644 --- a/drivers/iommu/fsl_pamu.c +++ b/drivers/iommu/fsl_pamu.c @@ -170,10 +170,10 @@ int pamu_disable_liodn(int liodn) static unsigned int map_addrspace_size_to_wse(phys_addr_t addrspace_size) { /* Bug if not a power of 2 */ - BUG_ON(!is_power_of_2(addrspace_size)); + BUG_ON((addrspace_size & (addrspace_size - 1))); /* window size is 2^(WSE+1) bytes */ - return __ffs(addrspace_size) - 1; + return fls64(addrspace_size) - 2; } /* Derive the PAACE window count encoding for the subwindow count */ @@ -351,7 +351,7 @@ int pamu_config_ppaace(int liodn, phys_addr_t win_addr, phys_addr_t win_size, struct paace *ppaace; unsigned long fspi; - if (!is_power_of_2(win_size) || win_size < PAMU_PAGE_SIZE) { + if ((win_size & (win_size - 1)) || win_size < PAMU_PAGE_SIZE) { pr_debug("window size too small or not a power of two %llx\n", win_size); return -EINVAL; } @@ -464,7 +464,7 @@ int pamu_config_spaace(int liodn, u32 subwin_cnt, u32 subwin, return -ENOENT; } - if (!is_power_of_2(subwin_size) || subwin_size < PAMU_PAGE_SIZE) { + if ((subwin_size & (subwin_size - 1)) || subwin_size < PAMU_PAGE_SIZE) { pr_debug("subwindow size out of range, or not a power of 2\n"); return -EINVAL; } diff --git a/drivers/iommu/fsl_pamu_domain.c b/drivers/iommu/fsl_pamu_domain.c index 93072ba44b1..af47648301a 100644 --- a/drivers/iommu/fsl_pamu_domain.c +++ b/drivers/iommu/fsl_pamu_domain.c @@ -301,7 +301,7 @@ static int check_size(u64 size, dma_addr_t iova) * Size must be a power of two and at least be equal * to PAMU page size. */ - if (!is_power_of_2(size) || size < PAMU_PAGE_SIZE) { + if ((size & (size - 1)) || size < PAMU_PAGE_SIZE) { pr_debug("%s: size too small or not a power of two\n", __func__); return -EINVAL; } @@ -335,11 +335,6 @@ static struct fsl_dma_domain *iommu_alloc_dma_domain(void) return domain; } -static inline struct device_domain_info *find_domain(struct device *dev) -{ - return dev->archdata.iommu_domain; -} - static void remove_device_ref(struct device_domain_info *info, u32 win_cnt) { unsigned long flags; @@ -380,7 +375,7 @@ static void attach_device(struct fsl_dma_domain *dma_domain, int liodn, struct d * Check here if the device is already attached to domain or not. * If the device is already attached to a domain detach it. */ - old_domain_info = find_domain(dev); + old_domain_info = dev->archdata.iommu_domain; if (old_domain_info && old_domain_info->domain != dma_domain) { spin_unlock_irqrestore(&device_domain_lock, flags); detach_device(dev, old_domain_info->domain); @@ -399,7 +394,7 @@ static void attach_device(struct fsl_dma_domain *dma_domain, int liodn, struct d * the info for the first LIODN as all * LIODNs share the same domain */ - if (!old_domain_info) + if (!dev->archdata.iommu_domain) dev->archdata.iommu_domain = info; spin_unlock_irqrestore(&device_domain_lock, flags); @@ -1042,12 +1037,15 @@ root_bus: group = get_shared_pci_device_group(pdev); } + if (!group) + group = ERR_PTR(-ENODEV); + return group; } static int fsl_pamu_add_device(struct device *dev) { - struct iommu_group *group = NULL; + struct iommu_group *group = ERR_PTR(-ENODEV); struct pci_dev *pdev; const u32 *prop; int ret, len; @@ -1070,7 +1068,7 @@ static int fsl_pamu_add_device(struct device *dev) group = get_device_iommu_group(dev); } - if (!group || IS_ERR(group)) + if (IS_ERR(group)) return PTR_ERR(group); ret = iommu_group_add_device(group, dev); diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c index 7e11c9d6ae8..7c131cf7cc1 100644 --- a/drivers/irqchip/irq-gic.c +++ b/drivers/irqchip/irq-gic.c @@ -42,6 +42,7 @@ #include <linux/irqchip/chained_irq.h> #include <linux/irqchip/arm-gic.h> +#include <asm/cputype.h> #include <asm/irq.h> #include <asm/exception.h> #include <asm/smp_plat.h> @@ -954,7 +955,9 @@ void __init gic_init_bases(unsigned int gic_nr, int irq_start, } for_each_possible_cpu(cpu) { - unsigned long offset = percpu_offset * cpu_logical_map(cpu); + u32 mpidr = cpu_logical_map(cpu); + u32 core_id = MPIDR_AFFINITY_LEVEL(mpidr, 0); + unsigned long offset = percpu_offset * core_id; *per_cpu_ptr(gic->dist_base.percpu_base, cpu) = dist_base + offset; *per_cpu_ptr(gic->cpu_base.percpu_base, cpu) = cpu_base + offset; } @@ -1071,8 +1074,10 @@ gic_of_init(struct device_node *node, struct device_node *parent) gic_cnt++; return 0; } +IRQCHIP_DECLARE(gic_400, "arm,gic-400", gic_of_init); IRQCHIP_DECLARE(cortex_a15_gic, "arm,cortex-a15-gic", gic_of_init); IRQCHIP_DECLARE(cortex_a9_gic, "arm,cortex-a9-gic", gic_of_init); +IRQCHIP_DECLARE(cortex_a7_gic, "arm,cortex-a7-gic", gic_of_init); IRQCHIP_DECLARE(msm_8660_qgic, "qcom,msm-8660-qgic", gic_of_init); IRQCHIP_DECLARE(msm_qgic2, "qcom,msm-qgic2", gic_of_init); diff --git a/drivers/isdn/i4l/isdn_ppp.c b/drivers/isdn/i4l/isdn_ppp.c index a333b7f798d..62f0688d45a 100644 --- a/drivers/isdn/i4l/isdn_ppp.c +++ b/drivers/isdn/i4l/isdn_ppp.c @@ -638,9 +638,15 @@ isdn_ppp_ioctl(int min, struct file *file, unsigned int cmd, unsigned long arg) fprog.len = len; fprog.filter = code; - if (is->pass_filter) + if (is->pass_filter) { sk_unattached_filter_destroy(is->pass_filter); - err = sk_unattached_filter_create(&is->pass_filter, &fprog); + is->pass_filter = NULL; + } + if (fprog.filter != NULL) + err = sk_unattached_filter_create(&is->pass_filter, + &fprog); + else + err = 0; kfree(code); return err; @@ -657,9 +663,15 @@ isdn_ppp_ioctl(int min, struct file *file, unsigned int cmd, unsigned long arg) fprog.len = len; fprog.filter = code; - if (is->active_filter) + if (is->active_filter) { sk_unattached_filter_destroy(is->active_filter); - err = sk_unattached_filter_create(&is->active_filter, &fprog); + is->active_filter = NULL; + } + if (fprog.filter != NULL) + err = sk_unattached_filter_create(&is->active_filter, + &fprog); + else + err = 0; kfree(code); return err; diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index 4ead4ba6065..d2899e7eb3a 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -425,6 +425,15 @@ static int __open_metadata(struct dm_cache_metadata *cmd) disk_super = dm_block_data(sblock); + /* Verify the data block size hasn't changed */ + if (le32_to_cpu(disk_super->data_block_size) != cmd->data_block_size) { + DMERR("changing the data block size (from %u to %llu) is not supported", + le32_to_cpu(disk_super->data_block_size), + (unsigned long long)cmd->data_block_size); + r = -EINVAL; + goto bad; + } + r = __check_incompat_features(disk_super, cmd); if (r < 0) goto bad; diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index b086a945edc..e9d33ad59df 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -613,6 +613,15 @@ static int __open_metadata(struct dm_pool_metadata *pmd) disk_super = dm_block_data(sblock); + /* Verify the data block size hasn't changed */ + if (le32_to_cpu(disk_super->data_block_size) != pmd->data_block_size) { + DMERR("changing the data block size (from %u to %llu) is not supported", + le32_to_cpu(disk_super->data_block_size), + (unsigned long long)pmd->data_block_size); + r = -EINVAL; + goto bad_unlock_sblock; + } + r = __check_incompat_features(disk_super, pmd); if (r < 0) goto bad_unlock_sblock; diff --git a/drivers/media/dvb-frontends/si2168.c b/drivers/media/dvb-frontends/si2168.c index 8637d2ed762..2e3cdcfa0a6 100644 --- a/drivers/media/dvb-frontends/si2168.c +++ b/drivers/media/dvb-frontends/si2168.c @@ -60,7 +60,7 @@ static int si2168_cmd_execute(struct si2168 *s, struct si2168_cmd *cmd) jiffies_to_msecs(jiffies) - (jiffies_to_msecs(timeout) - TIMEOUT)); - if (!(cmd->args[0] >> 7) & 0x01) { + if (!((cmd->args[0] >> 7) & 0x01)) { ret = -ETIMEDOUT; goto err_mutex_unlock; } @@ -485,20 +485,6 @@ static int si2168_init(struct dvb_frontend *fe) if (ret) goto err; - cmd.args[0] = 0x05; - cmd.args[1] = 0x00; - cmd.args[2] = 0xaa; - cmd.args[3] = 0x4d; - cmd.args[4] = 0x56; - cmd.args[5] = 0x40; - cmd.args[6] = 0x00; - cmd.args[7] = 0x00; - cmd.wlen = 8; - cmd.rlen = 1; - ret = si2168_cmd_execute(s, &cmd); - if (ret) - goto err; - /* cold state - try to download firmware */ dev_info(&s->client->dev, "%s: found a '%s' in cold state\n", KBUILD_MODNAME, si2168_ops.info.name); diff --git a/drivers/media/dvb-frontends/si2168_priv.h b/drivers/media/dvb-frontends/si2168_priv.h index 2a343e896f4..53f7f06ae34 100644 --- a/drivers/media/dvb-frontends/si2168_priv.h +++ b/drivers/media/dvb-frontends/si2168_priv.h @@ -22,7 +22,7 @@ #include <linux/firmware.h> #include <linux/i2c-mux.h> -#define SI2168_FIRMWARE "dvb-demod-si2168-01.fw" +#define SI2168_FIRMWARE "dvb-demod-si2168-02.fw" /* state struct */ struct si2168 { diff --git a/drivers/media/dvb-frontends/tda10071.c b/drivers/media/dvb-frontends/tda10071.c index 522fe00f5ee..9619be5d482 100644 --- a/drivers/media/dvb-frontends/tda10071.c +++ b/drivers/media/dvb-frontends/tda10071.c @@ -668,6 +668,7 @@ static int tda10071_set_frontend(struct dvb_frontend *fe) struct dtv_frontend_properties *c = &fe->dtv_property_cache; int ret, i; u8 mode, rolloff, pilot, inversion, div; + fe_modulation_t modulation; dev_dbg(&priv->i2c->dev, "%s: delivery_system=%d modulation=%d frequency=%d symbol_rate=%d inversion=%d pilot=%d rolloff=%d\n", @@ -702,10 +703,13 @@ static int tda10071_set_frontend(struct dvb_frontend *fe) switch (c->delivery_system) { case SYS_DVBS: + modulation = QPSK; rolloff = 0; pilot = 2; break; case SYS_DVBS2: + modulation = c->modulation; + switch (c->rolloff) { case ROLLOFF_20: rolloff = 2; @@ -750,7 +754,7 @@ static int tda10071_set_frontend(struct dvb_frontend *fe) for (i = 0, mode = 0xff; i < ARRAY_SIZE(TDA10071_MODCOD); i++) { if (c->delivery_system == TDA10071_MODCOD[i].delivery_system && - c->modulation == TDA10071_MODCOD[i].modulation && + modulation == TDA10071_MODCOD[i].modulation && c->fec_inner == TDA10071_MODCOD[i].fec) { mode = TDA10071_MODCOD[i].val; dev_dbg(&priv->i2c->dev, "%s: mode found=%02x\n", @@ -834,10 +838,10 @@ static int tda10071_get_frontend(struct dvb_frontend *fe) switch ((buf[1] >> 0) & 0x01) { case 0: - c->inversion = INVERSION_OFF; + c->inversion = INVERSION_ON; break; case 1: - c->inversion = INVERSION_ON; + c->inversion = INVERSION_OFF; break; } @@ -856,7 +860,7 @@ static int tda10071_get_frontend(struct dvb_frontend *fe) if (ret) goto error; - c->symbol_rate = (buf[0] << 16) | (buf[1] << 8) | (buf[2] << 0); + c->symbol_rate = ((buf[0] << 16) | (buf[1] << 8) | (buf[2] << 0)) * 1000; return ret; error: diff --git a/drivers/media/dvb-frontends/tda10071_priv.h b/drivers/media/dvb-frontends/tda10071_priv.h index 4baf14bfb65..42048619273 100644 --- a/drivers/media/dvb-frontends/tda10071_priv.h +++ b/drivers/media/dvb-frontends/tda10071_priv.h @@ -55,6 +55,7 @@ static struct tda10071_modcod { { SYS_DVBS2, QPSK, FEC_8_9, 0x0a }, { SYS_DVBS2, QPSK, FEC_9_10, 0x0b }, /* 8PSK */ + { SYS_DVBS2, PSK_8, FEC_AUTO, 0x00 }, { SYS_DVBS2, PSK_8, FEC_3_5, 0x0c }, { SYS_DVBS2, PSK_8, FEC_2_3, 0x0d }, { SYS_DVBS2, PSK_8, FEC_3_4, 0x0e }, diff --git a/drivers/media/pci/saa7134/saa7134-empress.c b/drivers/media/pci/saa7134/saa7134-empress.c index e65c760e4e8..0006d6bf8c1 100644 --- a/drivers/media/pci/saa7134/saa7134-empress.c +++ b/drivers/media/pci/saa7134/saa7134-empress.c @@ -179,7 +179,7 @@ static const struct v4l2_file_operations ts_fops = .read = vb2_fop_read, .poll = vb2_fop_poll, .mmap = vb2_fop_mmap, - .ioctl = video_ioctl2, + .unlocked_ioctl = video_ioctl2, }; static const struct v4l2_ioctl_ops ts_ioctl_ops = { diff --git a/drivers/media/platform/davinci/vpif_capture.c b/drivers/media/platform/davinci/vpif_capture.c index a7ed1649790..1e4ec697fb1 100644 --- a/drivers/media/platform/davinci/vpif_capture.c +++ b/drivers/media/platform/davinci/vpif_capture.c @@ -269,6 +269,7 @@ err: list_del(&buf->list); vb2_buffer_done(&buf->vb, VB2_BUF_STATE_QUEUED); } + spin_unlock_irqrestore(&common->irqlock, flags); return ret; } diff --git a/drivers/media/platform/davinci/vpif_display.c b/drivers/media/platform/davinci/vpif_display.c index 5bb085b19bc..b431b58f39e 100644 --- a/drivers/media/platform/davinci/vpif_display.c +++ b/drivers/media/platform/davinci/vpif_display.c @@ -233,6 +233,7 @@ err: list_del(&buf->list); vb2_buffer_done(&buf->vb, VB2_BUF_STATE_QUEUED); } + spin_unlock_irqrestore(&common->irqlock, flags); return ret; } diff --git a/drivers/media/tuners/si2157.c b/drivers/media/tuners/si2157.c index 271a752cee5..fa4cc7b880a 100644 --- a/drivers/media/tuners/si2157.c +++ b/drivers/media/tuners/si2157.c @@ -57,7 +57,7 @@ static int si2157_cmd_execute(struct si2157 *s, struct si2157_cmd *cmd) jiffies_to_msecs(jiffies) - (jiffies_to_msecs(timeout) - TIMEOUT)); - if (!(buf[0] >> 7) & 0x01) { + if (!((buf[0] >> 7) & 0x01)) { ret = -ETIMEDOUT; goto err_mutex_unlock; } else { diff --git a/drivers/media/usb/dvb-usb-v2/af9035.c b/drivers/media/usb/dvb-usb-v2/af9035.c index 021e4d35e4d..7b9b75f6077 100644 --- a/drivers/media/usb/dvb-usb-v2/af9035.c +++ b/drivers/media/usb/dvb-usb-v2/af9035.c @@ -704,15 +704,41 @@ static int af9035_read_config(struct dvb_usb_device *d) if (ret < 0) goto err; - if (tmp == 0x00) - dev_dbg(&d->udev->dev, - "%s: [%d]tuner not set, using default\n", - __func__, i); - else + dev_dbg(&d->udev->dev, "%s: [%d]tuner=%02x\n", + __func__, i, tmp); + + /* tuner sanity check */ + if (state->chip_type == 0x9135) { + if (state->chip_version == 0x02) { + /* IT9135 BX (v2) */ + switch (tmp) { + case AF9033_TUNER_IT9135_60: + case AF9033_TUNER_IT9135_61: + case AF9033_TUNER_IT9135_62: + state->af9033_config[i].tuner = tmp; + break; + } + } else { + /* IT9135 AX (v1) */ + switch (tmp) { + case AF9033_TUNER_IT9135_38: + case AF9033_TUNER_IT9135_51: + case AF9033_TUNER_IT9135_52: + state->af9033_config[i].tuner = tmp; + break; + } + } + } else { + /* AF9035 */ state->af9033_config[i].tuner = tmp; + } - dev_dbg(&d->udev->dev, "%s: [%d]tuner=%02x\n", - __func__, i, state->af9033_config[i].tuner); + if (state->af9033_config[i].tuner != tmp) { + dev_info(&d->udev->dev, + "%s: [%d] overriding tuner from %02x to %02x\n", + KBUILD_MODNAME, i, tmp, + state->af9033_config[i].tuner); + } switch (state->af9033_config[i].tuner) { case AF9033_TUNER_TUA9001: diff --git a/drivers/media/usb/gspca/pac7302.c b/drivers/media/usb/gspca/pac7302.c index 2fd1c5e31a0..339adce7c7a 100644 --- a/drivers/media/usb/gspca/pac7302.c +++ b/drivers/media/usb/gspca/pac7302.c @@ -928,6 +928,7 @@ static const struct usb_device_id device_table[] = { {USB_DEVICE(0x093a, 0x2620)}, {USB_DEVICE(0x093a, 0x2621)}, {USB_DEVICE(0x093a, 0x2622), .driver_info = FL_VFLIP}, + {USB_DEVICE(0x093a, 0x2623), .driver_info = FL_VFLIP}, {USB_DEVICE(0x093a, 0x2624), .driver_info = FL_VFLIP}, {USB_DEVICE(0x093a, 0x2625)}, {USB_DEVICE(0x093a, 0x2626)}, diff --git a/drivers/media/usb/hdpvr/hdpvr-video.c b/drivers/media/usb/hdpvr/hdpvr-video.c index 0500c4175d5..6bce01a674f 100644 --- a/drivers/media/usb/hdpvr/hdpvr-video.c +++ b/drivers/media/usb/hdpvr/hdpvr-video.c @@ -82,7 +82,7 @@ static void hdpvr_read_bulk_callback(struct urb *urb) } /*=========================================================================*/ -/* bufffer bits */ +/* buffer bits */ /* function expects dev->io_mutex to be hold by caller */ int hdpvr_cancel_queue(struct hdpvr_device *dev) @@ -926,7 +926,7 @@ static int hdpvr_s_ctrl(struct v4l2_ctrl *ctrl) case V4L2_CID_MPEG_AUDIO_ENCODING: if (dev->flags & HDPVR_FLAG_AC3_CAP) { opt->audio_codec = ctrl->val; - return hdpvr_set_audio(dev, opt->audio_input, + return hdpvr_set_audio(dev, opt->audio_input + 1, opt->audio_codec); } return 0; @@ -1198,7 +1198,7 @@ int hdpvr_register_videodev(struct hdpvr_device *dev, struct device *parent, v4l2_ctrl_new_std_menu(hdl, &hdpvr_ctrl_ops, V4L2_CID_MPEG_AUDIO_ENCODING, ac3 ? V4L2_MPEG_AUDIO_ENCODING_AC3 : V4L2_MPEG_AUDIO_ENCODING_AAC, - 0x7, V4L2_MPEG_AUDIO_ENCODING_AAC); + 0x7, ac3 ? dev->options.audio_codec : V4L2_MPEG_AUDIO_ENCODING_AAC); v4l2_ctrl_new_std_menu(hdl, &hdpvr_ctrl_ops, V4L2_CID_MPEG_VIDEO_ENCODING, V4L2_MPEG_VIDEO_ENCODING_MPEG_4_AVC, 0x3, diff --git a/drivers/media/v4l2-core/v4l2-dv-timings.c b/drivers/media/v4l2-core/v4l2-dv-timings.c index 4ae54caadd0..ce1c9f5d9de 100644 --- a/drivers/media/v4l2-core/v4l2-dv-timings.c +++ b/drivers/media/v4l2-core/v4l2-dv-timings.c @@ -610,10 +610,10 @@ struct v4l2_fract v4l2_calc_aspect_ratio(u8 hor_landscape, u8 vert_portrait) aspect.denominator = 9; } else if (ratio == 34) { aspect.numerator = 4; - aspect.numerator = 3; + aspect.denominator = 3; } else if (ratio == 68) { aspect.numerator = 15; - aspect.numerator = 9; + aspect.denominator = 9; } else { aspect.numerator = hor_landscape + 99; aspect.denominator = 100; diff --git a/drivers/mtd/ubi/fastmap.c b/drivers/mtd/ubi/fastmap.c index b04e7d05988..0431b46d9fd 100644 --- a/drivers/mtd/ubi/fastmap.c +++ b/drivers/mtd/ubi/fastmap.c @@ -125,7 +125,7 @@ static struct ubi_ainf_volume *add_vol(struct ubi_attach_info *ai, int vol_id, parent = *p; av = rb_entry(parent, struct ubi_ainf_volume, rb); - if (vol_id < av->vol_id) + if (vol_id > av->vol_id) p = &(*p)->rb_left; else p = &(*p)->rb_right; @@ -423,7 +423,7 @@ static int scan_pool(struct ubi_device *ubi, struct ubi_attach_info *ai, pnum, err); ret = err > 0 ? UBI_BAD_FASTMAP : err; goto out; - } else if (ret == UBI_IO_BITFLIPS) + } else if (err == UBI_IO_BITFLIPS) scrub = 1; /* diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c index 14c00048bbe..82322b1c841 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c @@ -129,14 +129,15 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq, name); } - cq->irq_desc = - irq_to_desc(mlx4_eq_get_irq(mdev->dev, - cq->vector)); } } else { cq->vector = (cq->ring + 1 + priv->port) % mdev->dev->caps.num_comp_vectors; } + + cq->irq_desc = + irq_to_desc(mlx4_eq_get_irq(mdev->dev, + cq->vector)); } else { /* For TX we use the same irq per ring we assigned for the RX */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c index ba0401d4af5..184c3615f47 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c @@ -94,6 +94,11 @@ int mlx5_core_create_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr, write_lock_irq(&table->lock); err = radix_tree_insert(&table->tree, mlx5_base_mkey(mr->key), mr); write_unlock_irq(&table->lock); + if (err) { + mlx5_core_warn(dev, "failed radix tree insert of mr 0x%x, %d\n", + mlx5_base_mkey(mr->key), err); + mlx5_core_destroy_mkey(dev, mr); + } return err; } @@ -104,12 +109,22 @@ int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr) struct mlx5_mr_table *table = &dev->priv.mr_table; struct mlx5_destroy_mkey_mbox_in in; struct mlx5_destroy_mkey_mbox_out out; + struct mlx5_core_mr *deleted_mr; unsigned long flags; int err; memset(&in, 0, sizeof(in)); memset(&out, 0, sizeof(out)); + write_lock_irqsave(&table->lock, flags); + deleted_mr = radix_tree_delete(&table->tree, mlx5_base_mkey(mr->key)); + write_unlock_irqrestore(&table->lock, flags); + if (!deleted_mr) { + mlx5_core_warn(dev, "failed radix tree delete of mr 0x%x\n", + mlx5_base_mkey(mr->key)); + return -ENOENT; + } + in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_DESTROY_MKEY); in.mkey = cpu_to_be32(mlx5_mkey_to_idx(mr->key)); err = mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out)); @@ -119,10 +134,6 @@ int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr) if (out.hdr.status) return mlx5_cmd_status_to_err(&out.hdr); - write_lock_irqsave(&table->lock, flags); - radix_tree_delete(&table->tree, mlx5_base_mkey(mr->key)); - write_unlock_irqrestore(&table->lock, flags); - return err; } EXPORT_SYMBOL(mlx5_core_destroy_mkey); diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 6175bd59190..9887bcb45b8 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -4226,6 +4226,8 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp) RTL_W32(RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST); break; case RTL_GIGA_MAC_VER_40: + RTL_W32(RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST | RX_EARLY_OFF); + break; case RTL_GIGA_MAC_VER_41: case RTL_GIGA_MAC_VER_42: case RTL_GIGA_MAC_VER_43: diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c index 1c24a8f368b..fd411d6e19a 100644 --- a/drivers/net/ethernet/sun/sunvnet.c +++ b/drivers/net/ethernet/sun/sunvnet.c @@ -1083,6 +1083,24 @@ static struct vnet *vnet_find_or_create(const u64 *local_mac) return vp; } +static void vnet_cleanup(void) +{ + struct vnet *vp; + struct net_device *dev; + + mutex_lock(&vnet_list_mutex); + while (!list_empty(&vnet_list)) { + vp = list_first_entry(&vnet_list, struct vnet, list); + list_del(&vp->list); + dev = vp->dev; + /* vio_unregister_driver() should have cleaned up port_list */ + BUG_ON(!list_empty(&vp->port_list)); + unregister_netdev(dev); + free_netdev(dev); + } + mutex_unlock(&vnet_list_mutex); +} + static const char *local_mac_prop = "local-mac-address"; static struct vnet *vnet_find_parent(struct mdesc_handle *hp, @@ -1240,7 +1258,6 @@ static int vnet_port_remove(struct vio_dev *vdev) kfree(port); - unregister_netdev(vp->dev); } return 0; } @@ -1268,6 +1285,7 @@ static int __init vnet_init(void) static void __exit vnet_exit(void) { vio_unregister_driver(&vnet_port_driver); + vnet_cleanup(); } module_init(vnet_init); diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 2031ce4051d..765248b42a0 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -761,10 +761,15 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) }; ppp_lock(ppp); - if (ppp->pass_filter) + if (ppp->pass_filter) { sk_unattached_filter_destroy(ppp->pass_filter); - err = sk_unattached_filter_create(&ppp->pass_filter, - &fprog); + ppp->pass_filter = NULL; + } + if (fprog.filter != NULL) + err = sk_unattached_filter_create(&ppp->pass_filter, + &fprog); + else + err = 0; kfree(code); ppp_unlock(ppp); } @@ -782,10 +787,15 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) }; ppp_lock(ppp); - if (ppp->active_filter) + if (ppp->active_filter) { sk_unattached_filter_destroy(ppp->active_filter); - err = sk_unattached_filter_create(&ppp->active_filter, - &fprog); + ppp->active_filter = NULL; + } + if (fprog.filter != NULL) + err = sk_unattached_filter_create(&ppp->active_filter, + &fprog); + else + err = 0; kfree(code); ppp_unlock(ppp); } diff --git a/drivers/net/usb/huawei_cdc_ncm.c b/drivers/net/usb/huawei_cdc_ncm.c index 5d95a13dbe2..735f7dadb9a 100644 --- a/drivers/net/usb/huawei_cdc_ncm.c +++ b/drivers/net/usb/huawei_cdc_ncm.c @@ -194,6 +194,9 @@ static const struct usb_device_id huawei_cdc_ncm_devs[] = { { USB_VENDOR_AND_INTERFACE_INFO(0x12d1, 0xff, 0x02, 0x76), .driver_info = (unsigned long)&huawei_cdc_ncm_info, }, + { USB_VENDOR_AND_INTERFACE_INFO(0x12d1, 0xff, 0x03, 0x16), + .driver_info = (unsigned long)&huawei_cdc_ncm_info, + }, /* Terminating entry */ { diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index c4638c67f6b..22756db53dc 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -667,6 +667,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x05c6, 0x9084, 4)}, {QMI_FIXED_INTF(0x05c6, 0x920d, 0)}, {QMI_FIXED_INTF(0x05c6, 0x920d, 5)}, + {QMI_FIXED_INTF(0x0846, 0x68a2, 8)}, {QMI_FIXED_INTF(0x12d1, 0x140c, 1)}, /* Huawei E173 */ {QMI_FIXED_INTF(0x12d1, 0x14ac, 1)}, /* Huawei E1820 */ {QMI_FIXED_INTF(0x16d8, 0x6003, 0)}, /* CMOTech 6003 */ @@ -757,6 +758,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1199, 0x9054, 8)}, /* Sierra Wireless Modem */ {QMI_FIXED_INTF(0x1199, 0x9055, 8)}, /* Netgear AirCard 341U */ {QMI_FIXED_INTF(0x1199, 0x9056, 8)}, /* Sierra Wireless Modem */ + {QMI_FIXED_INTF(0x1199, 0x9057, 8)}, {QMI_FIXED_INTF(0x1199, 0x9061, 8)}, /* Sierra Wireless Modem */ {QMI_FIXED_INTF(0x1bbb, 0x011e, 4)}, /* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */ {QMI_FIXED_INTF(0x1bbb, 0x0203, 2)}, /* Alcatel L800MA */ diff --git a/drivers/net/wan/x25_asy.c b/drivers/net/wan/x25_asy.c index df6c0735755..5c47b011a9d 100644 --- a/drivers/net/wan/x25_asy.c +++ b/drivers/net/wan/x25_asy.c @@ -122,8 +122,12 @@ static int x25_asy_change_mtu(struct net_device *dev, int newmtu) { struct x25_asy *sl = netdev_priv(dev); unsigned char *xbuff, *rbuff; - int len = 2 * newmtu; + int len; + if (newmtu > 65534) + return -EINVAL; + + len = 2 * newmtu; xbuff = kmalloc(len + 4, GFP_ATOMIC); rbuff = kmalloc(len + 4, GFP_ATOMIC); diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 77127ca08ca..769e553d3f4 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -1030,14 +1030,21 @@ static int xenvif_tx_check_gop(struct xenvif_queue *queue, { struct gnttab_map_grant_ref *gop_map = *gopp_map; u16 pending_idx = XENVIF_TX_CB(skb)->pending_idx; + /* This always points to the shinfo of the skb being checked, which + * could be either the first or the one on the frag_list + */ struct skb_shared_info *shinfo = skb_shinfo(skb); + /* If this is non-NULL, we are currently checking the frag_list skb, and + * this points to the shinfo of the first one + */ + struct skb_shared_info *first_shinfo = NULL; int nr_frags = shinfo->nr_frags; + const bool sharedslot = nr_frags && + frag_get_pending_idx(&shinfo->frags[0]) == pending_idx; int i, err; - struct sk_buff *first_skb = NULL; /* Check status of header. */ err = (*gopp_copy)->status; - (*gopp_copy)++; if (unlikely(err)) { if (net_ratelimit()) netdev_dbg(queue->vif->dev, @@ -1045,8 +1052,12 @@ static int xenvif_tx_check_gop(struct xenvif_queue *queue, (*gopp_copy)->status, pending_idx, (*gopp_copy)->source.u.ref); - xenvif_idx_release(queue, pending_idx, XEN_NETIF_RSP_ERROR); + /* The first frag might still have this slot mapped */ + if (!sharedslot) + xenvif_idx_release(queue, pending_idx, + XEN_NETIF_RSP_ERROR); } + (*gopp_copy)++; check_frags: for (i = 0; i < nr_frags; i++, gop_map++) { @@ -1062,8 +1073,19 @@ check_frags: pending_idx, gop_map->handle); /* Had a previous error? Invalidate this fragment. */ - if (unlikely(err)) + if (unlikely(err)) { xenvif_idx_unmap(queue, pending_idx); + /* If the mapping of the first frag was OK, but + * the header's copy failed, and they are + * sharing a slot, send an error + */ + if (i == 0 && sharedslot) + xenvif_idx_release(queue, pending_idx, + XEN_NETIF_RSP_ERROR); + else + xenvif_idx_release(queue, pending_idx, + XEN_NETIF_RSP_OKAY); + } continue; } @@ -1075,42 +1097,53 @@ check_frags: gop_map->status, pending_idx, gop_map->ref); + xenvif_idx_release(queue, pending_idx, XEN_NETIF_RSP_ERROR); /* Not the first error? Preceding frags already invalidated. */ if (err) continue; - /* First error: invalidate preceding fragments. */ + + /* First error: if the header haven't shared a slot with the + * first frag, release it as well. + */ + if (!sharedslot) + xenvif_idx_release(queue, + XENVIF_TX_CB(skb)->pending_idx, + XEN_NETIF_RSP_OKAY); + + /* Invalidate preceding fragments of this skb. */ for (j = 0; j < i; j++) { pending_idx = frag_get_pending_idx(&shinfo->frags[j]); xenvif_idx_unmap(queue, pending_idx); + xenvif_idx_release(queue, pending_idx, + XEN_NETIF_RSP_OKAY); + } + + /* And if we found the error while checking the frag_list, unmap + * the first skb's frags + */ + if (first_shinfo) { + for (j = 0; j < first_shinfo->nr_frags; j++) { + pending_idx = frag_get_pending_idx(&first_shinfo->frags[j]); + xenvif_idx_unmap(queue, pending_idx); + xenvif_idx_release(queue, pending_idx, + XEN_NETIF_RSP_OKAY); + } } /* Remember the error: invalidate all subsequent fragments. */ err = newerr; } - if (skb_has_frag_list(skb)) { - first_skb = skb; - skb = shinfo->frag_list; - shinfo = skb_shinfo(skb); + if (skb_has_frag_list(skb) && !first_shinfo) { + first_shinfo = skb_shinfo(skb); + shinfo = skb_shinfo(skb_shinfo(skb)->frag_list); nr_frags = shinfo->nr_frags; goto check_frags; } - /* There was a mapping error in the frag_list skb. We have to unmap - * the first skb's frags - */ - if (first_skb && err) { - int j; - shinfo = skb_shinfo(first_skb); - for (j = 0; j < shinfo->nr_frags; j++) { - pending_idx = frag_get_pending_idx(&shinfo->frags[j]); - xenvif_idx_unmap(queue, pending_idx); - } - } - *gopp_map = gop_map; return err; } @@ -1518,7 +1551,16 @@ static int xenvif_tx_submit(struct xenvif_queue *queue) /* Check the remap error code. */ if (unlikely(xenvif_tx_check_gop(queue, skb, &gop_map, &gop_copy))) { + /* If there was an error, xenvif_tx_check_gop is + * expected to release all the frags which were mapped, + * so kfree_skb shouldn't do it again + */ skb_shinfo(skb)->nr_frags = 0; + if (skb_has_frag_list(skb)) { + struct sk_buff *nskb = + skb_shinfo(skb)->frag_list; + skb_shinfo(nskb)->nr_frags = 0; + } kfree_skb(skb); continue; } @@ -1822,8 +1864,6 @@ void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx) tx_unmap_op.status); BUG(); } - - xenvif_idx_release(queue, pending_idx, XEN_NETIF_RSP_OKAY); } static inline int rx_work_todo(struct xenvif_queue *queue) diff --git a/drivers/s390/char/raw3270.c b/drivers/s390/char/raw3270.c index 15b3459f865..220acb4cbee 100644 --- a/drivers/s390/char/raw3270.c +++ b/drivers/s390/char/raw3270.c @@ -633,7 +633,6 @@ raw3270_reset_device_cb(struct raw3270_request *rq, void *data) } else raw3270_writesf_readpart(rp); memset(&rp->init_reset, 0, sizeof(rp->init_reset)); - memset(&rp->init_data, 0, sizeof(rp->init_data)); } static int diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 69ef4f8cfac..4038437ff03 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -901,10 +901,15 @@ static int ap_device_probe(struct device *dev) int rc; ap_dev->drv = ap_drv; + + spin_lock_bh(&ap_device_list_lock); + list_add(&ap_dev->list, &ap_device_list); + spin_unlock_bh(&ap_device_list_lock); + rc = ap_drv->probe ? ap_drv->probe(ap_dev) : -ENODEV; - if (!rc) { + if (rc) { spin_lock_bh(&ap_device_list_lock); - list_add(&ap_dev->list, &ap_device_list); + list_del_init(&ap_dev->list); spin_unlock_bh(&ap_device_list_lock); } return rc; diff --git a/drivers/staging/media/omap4iss/Kconfig b/drivers/staging/media/omap4iss/Kconfig index 78b0fba7047..8afc6fee40c 100644 --- a/drivers/staging/media/omap4iss/Kconfig +++ b/drivers/staging/media/omap4iss/Kconfig @@ -1,6 +1,6 @@ config VIDEO_OMAP4 bool "OMAP 4 Camera support" - depends on VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API && I2C && ARCH_OMAP4 + depends on VIDEO_V4L2=y && VIDEO_V4L2_SUBDEV_API && I2C=y && ARCH_OMAP4 select VIDEOBUF2_DMA_CONTIG ---help--- Driver for an OMAP 4 ISS controller. diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c index 9d2b673f90e..b8125aa64ad 100644 --- a/drivers/usb/chipidea/udc.c +++ b/drivers/usb/chipidea/udc.c @@ -1169,8 +1169,8 @@ static int ep_enable(struct usb_ep *ep, if (hwep->type == USB_ENDPOINT_XFER_CONTROL) cap |= QH_IOS; - if (hwep->num) - cap |= QH_ZLT; + + cap |= QH_ZLT; cap |= (hwep->ep.maxpacket << __ffs(QH_MAX_PKT)) & QH_MAX_PKT; /* * For ISO-TX, we set mult at QH as the largest value, and use diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 21b99b4b408..0e950ad8cb2 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -889,6 +889,25 @@ static int hub_usb3_port_disable(struct usb_hub *hub, int port1) if (!hub_is_superspeed(hub->hdev)) return -EINVAL; + ret = hub_port_status(hub, port1, &portstatus, &portchange); + if (ret < 0) + return ret; + + /* + * USB controller Advanced Micro Devices, Inc. [AMD] FCH USB XHCI + * Controller [1022:7814] will have spurious result making the following + * usb 3.0 device hotplugging route to the 2.0 root hub and recognized + * as high-speed device if we set the usb 3.0 port link state to + * Disabled. Since it's already in USB_SS_PORT_LS_RX_DETECT state, we + * check the state here to avoid the bug. + */ + if ((portstatus & USB_PORT_STAT_LINK_STATE) == + USB_SS_PORT_LS_RX_DETECT) { + dev_dbg(&hub->ports[port1 - 1]->dev, + "Not disabling port; link state is RxDetect\n"); + return ret; + } + ret = hub_set_port_link_state(hub, port1, USB_SS_PORT_LS_SS_DISABLED); if (ret) return ret; diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index b7a506f2bb1..5c660c77f03 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -426,20 +426,18 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp) * p2m are consistent. */ if (!xen_feature(XENFEAT_auto_translated_physmap)) { - unsigned long p; - struct page *scratch_page = get_balloon_scratch_page(); - if (!PageHighMem(page)) { + struct page *scratch_page = get_balloon_scratch_page(); + ret = HYPERVISOR_update_va_mapping( (unsigned long)__va(pfn << PAGE_SHIFT), pfn_pte(page_to_pfn(scratch_page), PAGE_KERNEL_RO), 0); BUG_ON(ret); - } - p = page_to_pfn(scratch_page); - __set_phys_to_machine(pfn, pfn_to_mfn(p)); - put_balloon_scratch_page(); + put_balloon_scratch_page(); + } + __set_phys_to_machine(pfn, INVALID_P2M_ENTRY); } #endif diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c index c3667b202f2..5f1e1f3cd18 100644 --- a/drivers/xen/manage.c +++ b/drivers/xen/manage.c @@ -88,7 +88,6 @@ static int xen_suspend(void *data) if (!si->cancelled) { xen_irq_resume(); - xen_console_resume(); xen_timer_resume(); } @@ -135,6 +134,10 @@ static void do_suspend(void) err = stop_machine(xen_suspend, &si, cpumask_of(0)); + /* Resume console as early as possible. */ + if (!si.cancelled) + xen_console_resume(); + raw_notifier_call_chain(&xen_resume_notifier, 0, NULL); dpm_resume_start(si.cancelled ? PMSG_THAW : PMSG_RESTORE); diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index e12441c7cf1..7187b14faa6 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -484,8 +484,19 @@ void btrfs_wait_logged_extents(struct btrfs_root *log, u64 transid) log_list); list_del_init(&ordered->log_list); spin_unlock_irq(&log->log_extents_lock[index]); + + if (!test_bit(BTRFS_ORDERED_IO_DONE, &ordered->flags) && + !test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags)) { + struct inode *inode = ordered->inode; + u64 start = ordered->file_offset; + u64 end = ordered->file_offset + ordered->len - 1; + + WARN_ON(!inode); + filemap_fdatawrite_range(inode->i_mapping, start, end); + } wait_event(ordered->wait, test_bit(BTRFS_ORDERED_IO_DONE, &ordered->flags)); + btrfs_put_ordered_extent(ordered); spin_lock_irq(&log->log_extents_lock[index]); } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 6104676857f..6cb82f62cb7 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1680,11 +1680,11 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path) if (device->bdev == root->fs_info->fs_devices->latest_bdev) root->fs_info->fs_devices->latest_bdev = next_device->bdev; - if (device->bdev) + if (device->bdev) { device->fs_devices->open_devices--; - - /* remove sysfs entry */ - btrfs_kobj_rm_device(root->fs_info, device); + /* remove sysfs entry */ + btrfs_kobj_rm_device(root->fs_info, device); + } call_rcu(&device->rcu, free_device); diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 4fc3a304617..26b3f952e6b 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -981,7 +981,7 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl) int error = 0; state = (fl->fl_type == F_WRLCK) ? LM_ST_EXCLUSIVE : LM_ST_SHARED; - flags = (IS_SETLKW(cmd) ? 0 : LM_FLAG_TRY) | GL_EXACT | GL_NOCACHE; + flags = (IS_SETLKW(cmd) ? 0 : LM_FLAG_TRY) | GL_EXACT; mutex_lock(&fp->f_fl_mutex); @@ -991,7 +991,7 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl) goto out; flock_lock_file_wait(file, &(struct file_lock){.fl_type = F_UNLCK}); - gfs2_glock_dq_wait(fl_gh); + gfs2_glock_dq(fl_gh); gfs2_holder_reinit(state, flags, fl_gh); } else { error = gfs2_glock_get(GFS2_SB(&ip->i_inode), ip->i_no_addr, diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index c355f7320e4..ee4e04fe60f 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -731,14 +731,14 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, cachep = gfs2_glock_aspace_cachep; else cachep = gfs2_glock_cachep; - gl = kmem_cache_alloc(cachep, GFP_KERNEL); + gl = kmem_cache_alloc(cachep, GFP_NOFS); if (!gl) return -ENOMEM; memset(&gl->gl_lksb, 0, sizeof(struct dlm_lksb)); if (glops->go_flags & GLOF_LVB) { - gl->gl_lksb.sb_lvbptr = kzalloc(GFS2_MIN_LVB_SIZE, GFP_KERNEL); + gl->gl_lksb.sb_lvbptr = kzalloc(GFS2_MIN_LVB_SIZE, GFP_NOFS); if (!gl->gl_lksb.sb_lvbptr) { kmem_cache_free(cachep, gl); return -ENOMEM; @@ -1404,12 +1404,16 @@ __acquires(&lru_lock) gl = list_entry(list->next, struct gfs2_glock, gl_lru); list_del_init(&gl->gl_lru); if (!spin_trylock(&gl->gl_spin)) { +add_back_to_lru: list_add(&gl->gl_lru, &lru_list); atomic_inc(&lru_count); continue; } + if (test_and_set_bit(GLF_LOCK, &gl->gl_flags)) { + spin_unlock(&gl->gl_spin); + goto add_back_to_lru; + } clear_bit(GLF_LRU, &gl->gl_flags); - spin_unlock(&lru_lock); gl->gl_lockref.count++; if (demote_ok(gl)) handle_callback(gl, LM_ST_UNLOCKED, 0, false); @@ -1417,7 +1421,7 @@ __acquires(&lru_lock) if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) gl->gl_lockref.count--; spin_unlock(&gl->gl_spin); - spin_lock(&lru_lock); + cond_resched_lock(&lru_lock); } } @@ -1442,7 +1446,7 @@ static long gfs2_scan_glock_lru(int nr) gl = list_entry(lru_list.next, struct gfs2_glock, gl_lru); /* Test for being demotable */ - if (!test_and_set_bit(GLF_LOCK, &gl->gl_flags)) { + if (!test_bit(GLF_LOCK, &gl->gl_flags)) { list_move(&gl->gl_lru, &dispose); atomic_dec(&lru_count); freed++; diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index fc1100781bb..2ffc67dce87 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -234,8 +234,8 @@ static void inode_go_sync(struct gfs2_glock *gl) * inode_go_inval - prepare a inode glock to be released * @gl: the glock * @flags: - * - * Normally we invlidate everything, but if we are moving into + * + * Normally we invalidate everything, but if we are moving into * LM_ST_DEFERRED from LM_ST_SHARED or LM_ST_EXCLUSIVE then we * can keep hold of the metadata, since it won't have changed. * diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c index 91f274de124..4fafea1c9ec 100644 --- a/fs/gfs2/lock_dlm.c +++ b/fs/gfs2/lock_dlm.c @@ -1036,8 +1036,8 @@ static int set_recover_size(struct gfs2_sbd *sdp, struct dlm_slot *slots, new_size = old_size + RECOVER_SIZE_INC; - submit = kzalloc(new_size * sizeof(uint32_t), GFP_NOFS); - result = kzalloc(new_size * sizeof(uint32_t), GFP_NOFS); + submit = kcalloc(new_size, sizeof(uint32_t), GFP_NOFS); + result = kcalloc(new_size, sizeof(uint32_t), GFP_NOFS); if (!submit || !result) { kfree(submit); kfree(result); diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index db629d1bd1b..f4cb9c0d6bb 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -337,7 +337,7 @@ static bool gfs2_unaligned_extlen(struct gfs2_rbm *rbm, u32 n_unaligned, u32 *le /** * gfs2_free_extlen - Return extent length of free blocks - * @rbm: Starting position + * @rrbm: Starting position * @len: Max length to check * * Starting at the block specified by the rbm, see how many free blocks @@ -2522,7 +2522,7 @@ void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, unsigned int state) /** * gfs2_rlist_free - free a resource group list - * @list: the list of resource groups + * @rlist: the list of resource groups * */ diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 8f98138cbc4..f11b9eed0de 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -756,7 +756,6 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr) spin_unlock(&dreq->lock); while (!list_empty(&hdr->pages)) { - bool do_destroy = true; req = nfs_list_entry(hdr->pages.next); nfs_list_remove_request(req); @@ -765,7 +764,6 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr) case NFS_IOHDR_NEED_COMMIT: kref_get(&req->wb_kref); nfs_mark_request_commit(req, hdr->lseg, &cinfo); - do_destroy = false; } nfs_unlock_and_release_request(req); } diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 82ddbf46660..f415cbf9f6c 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -244,6 +244,7 @@ void nfs_pgio_data_release(struct nfs_pgio_data *); int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *); int nfs_initiate_pgio(struct rpc_clnt *, struct nfs_pgio_data *, const struct rpc_call_ops *, int, int); +void nfs_free_request(struct nfs_page *req); static inline void nfs_iocounter_init(struct nfs_io_counter *c) { diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c index 871d6eda8db..8f854dde415 100644 --- a/fs/nfs/nfs3acl.c +++ b/fs/nfs/nfs3acl.c @@ -247,3 +247,46 @@ const struct xattr_handler *nfs3_xattr_handlers[] = { &posix_acl_default_xattr_handler, NULL, }; + +static int +nfs3_list_one_acl(struct inode *inode, int type, const char *name, void *data, + size_t size, ssize_t *result) +{ + struct posix_acl *acl; + char *p = data + *result; + + acl = get_acl(inode, type); + if (!acl) + return 0; + + posix_acl_release(acl); + + *result += strlen(name); + *result += 1; + if (!size) + return 0; + if (*result > size) + return -ERANGE; + + strcpy(p, name); + return 0; +} + +ssize_t +nfs3_listxattr(struct dentry *dentry, char *data, size_t size) +{ + struct inode *inode = dentry->d_inode; + ssize_t result = 0; + int error; + + error = nfs3_list_one_acl(inode, ACL_TYPE_ACCESS, + POSIX_ACL_XATTR_ACCESS, data, size, &result); + if (error) + return error; + + error = nfs3_list_one_acl(inode, ACL_TYPE_DEFAULT, + POSIX_ACL_XATTR_DEFAULT, data, size, &result); + if (error) + return error; + return result; +} diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index e7daa42bbc8..f0afa291fd5 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -885,7 +885,7 @@ static const struct inode_operations nfs3_dir_inode_operations = { .getattr = nfs_getattr, .setattr = nfs_setattr, #ifdef CONFIG_NFS_V3_ACL - .listxattr = generic_listxattr, + .listxattr = nfs3_listxattr, .getxattr = generic_getxattr, .setxattr = generic_setxattr, .removexattr = generic_removexattr, @@ -899,7 +899,7 @@ static const struct inode_operations nfs3_file_inode_operations = { .getattr = nfs_getattr, .setattr = nfs_setattr, #ifdef CONFIG_NFS_V3_ACL - .listxattr = generic_listxattr, + .listxattr = nfs3_listxattr, .getxattr = generic_getxattr, .setxattr = generic_setxattr, .removexattr = generic_removexattr, diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index b6ee3a6ee96..17fab89f635 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -29,8 +29,6 @@ static struct kmem_cache *nfs_page_cachep; static const struct rpc_call_ops nfs_pgio_common_ops; -static void nfs_free_request(struct nfs_page *); - static bool nfs_pgarray_set(struct nfs_page_array *p, unsigned int pagecount) { p->npages = pagecount; @@ -239,20 +237,28 @@ nfs_page_group_init(struct nfs_page *req, struct nfs_page *prev) WARN_ON_ONCE(prev == req); if (!prev) { + /* a head request */ req->wb_head = req; req->wb_this_page = req; } else { + /* a subrequest */ WARN_ON_ONCE(prev->wb_this_page != prev->wb_head); WARN_ON_ONCE(!test_bit(PG_HEADLOCK, &prev->wb_head->wb_flags)); req->wb_head = prev->wb_head; req->wb_this_page = prev->wb_this_page; prev->wb_this_page = req; + /* All subrequests take a ref on the head request until + * nfs_page_group_destroy is called */ + kref_get(&req->wb_head->wb_kref); + /* grab extra ref if head request has extra ref from * the write/commit path to handle handoff between write * and commit lists */ - if (test_bit(PG_INODE_REF, &prev->wb_head->wb_flags)) + if (test_bit(PG_INODE_REF, &prev->wb_head->wb_flags)) { + set_bit(PG_INODE_REF, &req->wb_flags); kref_get(&req->wb_kref); + } } } @@ -269,6 +275,10 @@ nfs_page_group_destroy(struct kref *kref) struct nfs_page *req = container_of(kref, struct nfs_page, wb_kref); struct nfs_page *tmp, *next; + /* subrequests must release the ref on the head request */ + if (req->wb_head != req) + nfs_release_request(req->wb_head); + if (!nfs_page_group_sync_on_bit(req, PG_TEARDOWN)) return; @@ -394,7 +404,7 @@ static void nfs_clear_request(struct nfs_page *req) * * Note: Should never be called with the spinlock held! */ -static void nfs_free_request(struct nfs_page *req) +void nfs_free_request(struct nfs_page *req) { WARN_ON_ONCE(req->wb_this_page != req); @@ -925,7 +935,6 @@ static int __nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, nfs_pageio_doio(desc); if (desc->pg_error < 0) return 0; - desc->pg_moreio = 0; if (desc->pg_recoalesce) return 0; /* retry add_request for this subreq */ @@ -972,6 +981,7 @@ static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc) desc->pg_count = 0; desc->pg_base = 0; desc->pg_recoalesce = 0; + desc->pg_moreio = 0; while (!list_empty(&head)) { struct nfs_page *req; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 98ff061ccaf..5e2f1030454 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -46,6 +46,7 @@ static const struct rpc_call_ops nfs_commit_ops; static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops; static const struct nfs_commit_completion_ops nfs_commit_completion_ops; static const struct nfs_rw_ops nfs_rw_write_ops; +static void nfs_clear_request_commit(struct nfs_page *req); static struct kmem_cache *nfs_wdata_cachep; static mempool_t *nfs_wdata_mempool; @@ -91,8 +92,15 @@ static void nfs_context_set_write_error(struct nfs_open_context *ctx, int error) set_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags); } +/* + * nfs_page_find_head_request_locked - find head request associated with @page + * + * must be called while holding the inode lock. + * + * returns matching head request with reference held, or NULL if not found. + */ static struct nfs_page * -nfs_page_find_request_locked(struct nfs_inode *nfsi, struct page *page) +nfs_page_find_head_request_locked(struct nfs_inode *nfsi, struct page *page) { struct nfs_page *req = NULL; @@ -104,25 +112,33 @@ nfs_page_find_request_locked(struct nfs_inode *nfsi, struct page *page) /* Linearly search the commit list for the correct req */ list_for_each_entry_safe(freq, t, &nfsi->commit_info.list, wb_list) { if (freq->wb_page == page) { - req = freq; + req = freq->wb_head; break; } } } - if (req) + if (req) { + WARN_ON_ONCE(req->wb_head != req); + kref_get(&req->wb_kref); + } return req; } -static struct nfs_page *nfs_page_find_request(struct page *page) +/* + * nfs_page_find_head_request - find head request associated with @page + * + * returns matching head request with reference held, or NULL if not found. + */ +static struct nfs_page *nfs_page_find_head_request(struct page *page) { struct inode *inode = page_file_mapping(page)->host; struct nfs_page *req = NULL; spin_lock(&inode->i_lock); - req = nfs_page_find_request_locked(NFS_I(inode), page); + req = nfs_page_find_head_request_locked(NFS_I(inode), page); spin_unlock(&inode->i_lock); return req; } @@ -274,36 +290,246 @@ static void nfs_end_page_writeback(struct nfs_page *req) clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC); } -static struct nfs_page *nfs_find_and_lock_request(struct page *page, bool nonblock) + +/* nfs_page_group_clear_bits + * @req - an nfs request + * clears all page group related bits from @req + */ +static void +nfs_page_group_clear_bits(struct nfs_page *req) +{ + clear_bit(PG_TEARDOWN, &req->wb_flags); + clear_bit(PG_UNLOCKPAGE, &req->wb_flags); + clear_bit(PG_UPTODATE, &req->wb_flags); + clear_bit(PG_WB_END, &req->wb_flags); + clear_bit(PG_REMOVE, &req->wb_flags); +} + + +/* + * nfs_unroll_locks_and_wait - unlock all newly locked reqs and wait on @req + * + * this is a helper function for nfs_lock_and_join_requests + * + * @inode - inode associated with request page group, must be holding inode lock + * @head - head request of page group, must be holding head lock + * @req - request that couldn't lock and needs to wait on the req bit lock + * @nonblock - if true, don't actually wait + * + * NOTE: this must be called holding page_group bit lock and inode spin lock + * and BOTH will be released before returning. + * + * returns 0 on success, < 0 on error. + */ +static int +nfs_unroll_locks_and_wait(struct inode *inode, struct nfs_page *head, + struct nfs_page *req, bool nonblock) + __releases(&inode->i_lock) +{ + struct nfs_page *tmp; + int ret; + + /* relinquish all the locks successfully grabbed this run */ + for (tmp = head ; tmp != req; tmp = tmp->wb_this_page) + nfs_unlock_request(tmp); + + WARN_ON_ONCE(test_bit(PG_TEARDOWN, &req->wb_flags)); + + /* grab a ref on the request that will be waited on */ + kref_get(&req->wb_kref); + + nfs_page_group_unlock(head); + spin_unlock(&inode->i_lock); + + /* release ref from nfs_page_find_head_request_locked */ + nfs_release_request(head); + + if (!nonblock) + ret = nfs_wait_on_request(req); + else + ret = -EAGAIN; + nfs_release_request(req); + + return ret; +} + +/* + * nfs_destroy_unlinked_subrequests - destroy recently unlinked subrequests + * + * @destroy_list - request list (using wb_this_page) terminated by @old_head + * @old_head - the old head of the list + * + * All subrequests must be locked and removed from all lists, so at this point + * they are only "active" in this function, and possibly in nfs_wait_on_request + * with a reference held by some other context. + */ +static void +nfs_destroy_unlinked_subrequests(struct nfs_page *destroy_list, + struct nfs_page *old_head) +{ + while (destroy_list) { + struct nfs_page *subreq = destroy_list; + + destroy_list = (subreq->wb_this_page == old_head) ? + NULL : subreq->wb_this_page; + + WARN_ON_ONCE(old_head != subreq->wb_head); + + /* make sure old group is not used */ + subreq->wb_head = subreq; + subreq->wb_this_page = subreq; + + nfs_clear_request_commit(subreq); + + /* subreq is now totally disconnected from page group or any + * write / commit lists. last chance to wake any waiters */ + nfs_unlock_request(subreq); + + if (!test_bit(PG_TEARDOWN, &subreq->wb_flags)) { + /* release ref on old head request */ + nfs_release_request(old_head); + + nfs_page_group_clear_bits(subreq); + + /* release the PG_INODE_REF reference */ + if (test_and_clear_bit(PG_INODE_REF, &subreq->wb_flags)) + nfs_release_request(subreq); + else + WARN_ON_ONCE(1); + } else { + WARN_ON_ONCE(test_bit(PG_CLEAN, &subreq->wb_flags)); + /* zombie requests have already released the last + * reference and were waiting on the rest of the + * group to complete. Since it's no longer part of a + * group, simply free the request */ + nfs_page_group_clear_bits(subreq); + nfs_free_request(subreq); + } + } +} + +/* + * nfs_lock_and_join_requests - join all subreqs to the head req and return + * a locked reference, cancelling any pending + * operations for this page. + * + * @page - the page used to lookup the "page group" of nfs_page structures + * @nonblock - if true, don't block waiting for request locks + * + * This function joins all sub requests to the head request by first + * locking all requests in the group, cancelling any pending operations + * and finally updating the head request to cover the whole range covered by + * the (former) group. All subrequests are removed from any write or commit + * lists, unlinked from the group and destroyed. + * + * Returns a locked, referenced pointer to the head request - which after + * this call is guaranteed to be the only request associated with the page. + * Returns NULL if no requests are found for @page, or a ERR_PTR if an + * error was encountered. + */ +static struct nfs_page * +nfs_lock_and_join_requests(struct page *page, bool nonblock) { struct inode *inode = page_file_mapping(page)->host; - struct nfs_page *req; + struct nfs_page *head, *subreq; + struct nfs_page *destroy_list = NULL; + unsigned int total_bytes; int ret; +try_again: + total_bytes = 0; + + WARN_ON_ONCE(destroy_list); + spin_lock(&inode->i_lock); - for (;;) { - req = nfs_page_find_request_locked(NFS_I(inode), page); - if (req == NULL) - break; - if (nfs_lock_request(req)) - break; - /* Note: If we hold the page lock, as is the case in nfs_writepage, - * then the call to nfs_lock_request() will always - * succeed provided that someone hasn't already marked the - * request as dirty (in which case we don't care). - */ + + /* + * A reference is taken only on the head request which acts as a + * reference to the whole page group - the group will not be destroyed + * until the head reference is released. + */ + head = nfs_page_find_head_request_locked(NFS_I(inode), page); + + if (!head) { spin_unlock(&inode->i_lock); - if (!nonblock) - ret = nfs_wait_on_request(req); - else - ret = -EAGAIN; - nfs_release_request(req); - if (ret != 0) + return NULL; + } + + /* lock each request in the page group */ + nfs_page_group_lock(head); + subreq = head; + do { + /* + * Subrequests are always contiguous, non overlapping + * and in order. If not, it's a programming error. + */ + WARN_ON_ONCE(subreq->wb_offset != + (head->wb_offset + total_bytes)); + + /* keep track of how many bytes this group covers */ + total_bytes += subreq->wb_bytes; + + if (!nfs_lock_request(subreq)) { + /* releases page group bit lock and + * inode spin lock and all references */ + ret = nfs_unroll_locks_and_wait(inode, head, + subreq, nonblock); + + if (ret == 0) + goto try_again; + return ERR_PTR(ret); - spin_lock(&inode->i_lock); + } + + subreq = subreq->wb_this_page; + } while (subreq != head); + + /* Now that all requests are locked, make sure they aren't on any list. + * Commit list removal accounting is done after locks are dropped */ + subreq = head; + do { + nfs_list_remove_request(subreq); + subreq = subreq->wb_this_page; + } while (subreq != head); + + /* unlink subrequests from head, destroy them later */ + if (head->wb_this_page != head) { + /* destroy list will be terminated by head */ + destroy_list = head->wb_this_page; + head->wb_this_page = head; + + /* change head request to cover whole range that + * the former page group covered */ + head->wb_bytes = total_bytes; } + + /* + * prepare head request to be added to new pgio descriptor + */ + nfs_page_group_clear_bits(head); + + /* + * some part of the group was still on the inode list - otherwise + * the group wouldn't be involved in async write. + * grab a reference for the head request, iff it needs one. + */ + if (!test_and_set_bit(PG_INODE_REF, &head->wb_flags)) + kref_get(&head->wb_kref); + + nfs_page_group_unlock(head); + + /* drop lock to clear_request_commit the head req and clean up + * requests on destroy list */ spin_unlock(&inode->i_lock); - return req; + + nfs_destroy_unlinked_subrequests(destroy_list, head); + + /* clean up commit list state */ + nfs_clear_request_commit(head); + + /* still holds ref on head from nfs_page_find_head_request_locked + * and still has lock on head from lock loop */ + return head; } /* @@ -316,7 +542,7 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, struct nfs_page *req; int ret = 0; - req = nfs_find_and_lock_request(page, nonblock); + req = nfs_lock_and_join_requests(page, nonblock); if (!req) goto out; ret = PTR_ERR(req); @@ -448,7 +674,9 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req) set_page_private(req->wb_page, (unsigned long)req); } nfsi->npages++; - set_bit(PG_INODE_REF, &req->wb_flags); + /* this a head request for a page group - mark it as having an + * extra reference so sub groups can follow suit */ + WARN_ON(test_and_set_bit(PG_INODE_REF, &req->wb_flags)); kref_get(&req->wb_kref); spin_unlock(&inode->i_lock); } @@ -474,7 +702,9 @@ static void nfs_inode_remove_request(struct nfs_page *req) nfsi->npages--; spin_unlock(&inode->i_lock); } - nfs_release_request(req); + + if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags)) + nfs_release_request(req); } static void @@ -638,7 +868,6 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr) { struct nfs_commit_info cinfo; unsigned long bytes = 0; - bool do_destroy; if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) goto out; @@ -668,7 +897,6 @@ remove_req: next: nfs_unlock_request(req); nfs_end_page_writeback(req); - do_destroy = !test_bit(NFS_IOHDR_NEED_COMMIT, &hdr->flags); nfs_release_request(req); } out: @@ -769,7 +997,7 @@ static struct nfs_page *nfs_try_to_update_request(struct inode *inode, spin_lock(&inode->i_lock); for (;;) { - req = nfs_page_find_request_locked(NFS_I(inode), page); + req = nfs_page_find_head_request_locked(NFS_I(inode), page); if (req == NULL) goto out_unlock; @@ -877,7 +1105,7 @@ int nfs_flush_incompatible(struct file *file, struct page *page) * dropped page. */ do { - req = nfs_page_find_request(page); + req = nfs_page_find_head_request(page); if (req == NULL) return 0; l_ctx = req->wb_lock_context; @@ -1569,27 +1797,28 @@ int nfs_wb_page_cancel(struct inode *inode, struct page *page) struct nfs_page *req; int ret = 0; - for (;;) { - wait_on_page_writeback(page); - req = nfs_page_find_request(page); - if (req == NULL) - break; - if (nfs_lock_request(req)) { - nfs_clear_request_commit(req); - nfs_inode_remove_request(req); - /* - * In case nfs_inode_remove_request has marked the - * page as being dirty - */ - cancel_dirty_page(page, PAGE_CACHE_SIZE); - nfs_unlock_and_release_request(req); - break; - } - ret = nfs_wait_on_request(req); - nfs_release_request(req); - if (ret < 0) - break; + wait_on_page_writeback(page); + + /* blocking call to cancel all requests and join to a single (head) + * request */ + req = nfs_lock_and_join_requests(page, false); + + if (IS_ERR(req)) { + ret = PTR_ERR(req); + } else if (req) { + /* all requests from this page have been cancelled by + * nfs_lock_and_join_requests, so just remove the head + * request from the inode / page_private pointer and + * release it */ + nfs_inode_remove_request(req); + /* + * In case nfs_inode_remove_request has marked the + * page as being dirty + */ + cancel_dirty_page(page, PAGE_CACHE_SIZE); + nfs_unlock_and_release_request(req); } + return ret; } diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c index 96175df211b..75c3fe5f3d9 100644 --- a/fs/xfs/xfs_bmap.c +++ b/fs/xfs/xfs_bmap.c @@ -4298,8 +4298,8 @@ xfs_bmapi_delay( } -int -__xfs_bmapi_allocate( +static int +xfs_bmapi_allocate( struct xfs_bmalloca *bma) { struct xfs_mount *mp = bma->ip->i_mount; @@ -4578,9 +4578,6 @@ xfs_bmapi_write( bma.flist = flist; bma.firstblock = firstblock; - if (flags & XFS_BMAPI_STACK_SWITCH) - bma.stack_switch = 1; - while (bno < end && n < *nmap) { inhole = eof || bma.got.br_startoff > bno; wasdelay = !inhole && isnullstartblock(bma.got.br_startblock); diff --git a/fs/xfs/xfs_bmap.h b/fs/xfs/xfs_bmap.h index 38ba36e9b2f..b879ca56a64 100644 --- a/fs/xfs/xfs_bmap.h +++ b/fs/xfs/xfs_bmap.h @@ -77,7 +77,6 @@ typedef struct xfs_bmap_free * from written to unwritten, otherwise convert from unwritten to written. */ #define XFS_BMAPI_CONVERT 0x040 -#define XFS_BMAPI_STACK_SWITCH 0x080 #define XFS_BMAPI_FLAGS \ { XFS_BMAPI_ENTIRE, "ENTIRE" }, \ @@ -86,8 +85,7 @@ typedef struct xfs_bmap_free { XFS_BMAPI_PREALLOC, "PREALLOC" }, \ { XFS_BMAPI_IGSTATE, "IGSTATE" }, \ { XFS_BMAPI_CONTIG, "CONTIG" }, \ - { XFS_BMAPI_CONVERT, "CONVERT" }, \ - { XFS_BMAPI_STACK_SWITCH, "STACK_SWITCH" } + { XFS_BMAPI_CONVERT, "CONVERT" } static inline int xfs_bmapi_aflag(int w) diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 703b3ec1796..64731ef3324 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -249,59 +249,6 @@ xfs_bmap_rtalloc( } /* - * Stack switching interfaces for allocation - */ -static void -xfs_bmapi_allocate_worker( - struct work_struct *work) -{ - struct xfs_bmalloca *args = container_of(work, - struct xfs_bmalloca, work); - unsigned long pflags; - unsigned long new_pflags = PF_FSTRANS; - - /* - * we are in a transaction context here, but may also be doing work - * in kswapd context, and hence we may need to inherit that state - * temporarily to ensure that we don't block waiting for memory reclaim - * in any way. - */ - if (args->kswapd) - new_pflags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD; - - current_set_flags_nested(&pflags, new_pflags); - - args->result = __xfs_bmapi_allocate(args); - complete(args->done); - - current_restore_flags_nested(&pflags, new_pflags); -} - -/* - * Some allocation requests often come in with little stack to work on. Push - * them off to a worker thread so there is lots of stack to use. Otherwise just - * call directly to avoid the context switch overhead here. - */ -int -xfs_bmapi_allocate( - struct xfs_bmalloca *args) -{ - DECLARE_COMPLETION_ONSTACK(done); - - if (!args->stack_switch) - return __xfs_bmapi_allocate(args); - - - args->done = &done; - args->kswapd = current_is_kswapd(); - INIT_WORK_ONSTACK(&args->work, xfs_bmapi_allocate_worker); - queue_work(xfs_alloc_wq, &args->work); - wait_for_completion(&done); - destroy_work_on_stack(&args->work); - return args->result; -} - -/* * Check if the endoff is outside the last extent. If so the caller will grow * the allocation to a stripe unit boundary. All offsets are considered outside * the end of file for an empty fork, so 1 is returned in *eof in that case. diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h index 075f72232a6..2fdb72d2c90 100644 --- a/fs/xfs/xfs_bmap_util.h +++ b/fs/xfs/xfs_bmap_util.h @@ -55,8 +55,6 @@ struct xfs_bmalloca { bool userdata;/* set if is user data */ bool aeof; /* allocated space at eof */ bool conv; /* overwriting unwritten extents */ - bool stack_switch; - bool kswapd; /* allocation in kswapd context */ int flags; struct completion *done; struct work_struct work; @@ -66,8 +64,6 @@ struct xfs_bmalloca { int xfs_bmap_finish(struct xfs_trans **tp, struct xfs_bmap_free *flist, int *committed); int xfs_bmap_rtalloc(struct xfs_bmalloca *ap); -int xfs_bmapi_allocate(struct xfs_bmalloca *args); -int __xfs_bmapi_allocate(struct xfs_bmalloca *args); int xfs_bmap_eof(struct xfs_inode *ip, xfs_fileoff_t endoff, int whichfork, int *eof); int xfs_bmap_count_blocks(struct xfs_trans *tp, struct xfs_inode *ip, diff --git a/fs/xfs/xfs_btree.c b/fs/xfs/xfs_btree.c index bf810c6baf2..cf893bc1e37 100644 --- a/fs/xfs/xfs_btree.c +++ b/fs/xfs/xfs_btree.c @@ -33,6 +33,7 @@ #include "xfs_error.h" #include "xfs_trace.h" #include "xfs_cksum.h" +#include "xfs_alloc.h" /* * Cursor allocation zone. @@ -2323,7 +2324,7 @@ error1: * record (to be inserted into parent). */ STATIC int /* error */ -xfs_btree_split( +__xfs_btree_split( struct xfs_btree_cur *cur, int level, union xfs_btree_ptr *ptrp, @@ -2503,6 +2504,85 @@ error0: return error; } +struct xfs_btree_split_args { + struct xfs_btree_cur *cur; + int level; + union xfs_btree_ptr *ptrp; + union xfs_btree_key *key; + struct xfs_btree_cur **curp; + int *stat; /* success/failure */ + int result; + bool kswapd; /* allocation in kswapd context */ + struct completion *done; + struct work_struct work; +}; + +/* + * Stack switching interfaces for allocation + */ +static void +xfs_btree_split_worker( + struct work_struct *work) +{ + struct xfs_btree_split_args *args = container_of(work, + struct xfs_btree_split_args, work); + unsigned long pflags; + unsigned long new_pflags = PF_FSTRANS; + + /* + * we are in a transaction context here, but may also be doing work + * in kswapd context, and hence we may need to inherit that state + * temporarily to ensure that we don't block waiting for memory reclaim + * in any way. + */ + if (args->kswapd) + new_pflags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD; + + current_set_flags_nested(&pflags, new_pflags); + + args->result = __xfs_btree_split(args->cur, args->level, args->ptrp, + args->key, args->curp, args->stat); + complete(args->done); + + current_restore_flags_nested(&pflags, new_pflags); +} + +/* + * BMBT split requests often come in with little stack to work on. Push + * them off to a worker thread so there is lots of stack to use. For the other + * btree types, just call directly to avoid the context switch overhead here. + */ +STATIC int /* error */ +xfs_btree_split( + struct xfs_btree_cur *cur, + int level, + union xfs_btree_ptr *ptrp, + union xfs_btree_key *key, + struct xfs_btree_cur **curp, + int *stat) /* success/failure */ +{ + struct xfs_btree_split_args args; + DECLARE_COMPLETION_ONSTACK(done); + + if (cur->bc_btnum != XFS_BTNUM_BMAP) + return __xfs_btree_split(cur, level, ptrp, key, curp, stat); + + args.cur = cur; + args.level = level; + args.ptrp = ptrp; + args.key = key; + args.curp = curp; + args.stat = stat; + args.done = &done; + args.kswapd = current_is_kswapd(); + INIT_WORK_ONSTACK(&args.work, xfs_btree_split_worker); + queue_work(xfs_alloc_wq, &args.work); + wait_for_completion(&done); + destroy_work_on_stack(&args.work); + return args.result; +} + + /* * Copy the old inode root contents into a real block and make the * broot point to it. diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 6c5eb4c551e..6d3ec2b6ee2 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -749,8 +749,7 @@ xfs_iomap_write_allocate( * pointer that the caller gave to us. */ error = xfs_bmapi_write(tp, ip, map_start_fsb, - count_fsb, - XFS_BMAPI_STACK_SWITCH, + count_fsb, 0, &first_block, 1, imap, &nimaps, &free_list); if (error) diff --git a/fs/xfs/xfs_sb.c b/fs/xfs/xfs_sb.c index c3453b11f56..7703fa6770f 100644 --- a/fs/xfs/xfs_sb.c +++ b/fs/xfs/xfs_sb.c @@ -483,10 +483,16 @@ xfs_sb_quota_to_disk( } /* - * GQUOTINO and PQUOTINO cannot be used together in versions - * of superblock that do not have pquotino. from->sb_flags - * tells us which quota is active and should be copied to - * disk. + * GQUOTINO and PQUOTINO cannot be used together in versions of + * superblock that do not have pquotino. from->sb_flags tells us which + * quota is active and should be copied to disk. If neither are active, + * make sure we write NULLFSINO to the sb_gquotino field as a quota + * inode value of "0" is invalid when the XFS_SB_VERSION_QUOTA feature + * bit is set. + * + * Note that we don't need to handle the sb_uquotino or sb_pquotino here + * as they do not require any translation. Hence the main sb field loop + * will write them appropriately from the in-core superblock. */ if ((*fields & XFS_SB_GQUOTINO) && (from->sb_qflags & XFS_GQUOTA_ACCT)) @@ -494,6 +500,17 @@ xfs_sb_quota_to_disk( else if ((*fields & XFS_SB_PQUOTINO) && (from->sb_qflags & XFS_PQUOTA_ACCT)) to->sb_gquotino = cpu_to_be64(from->sb_pquotino); + else { + /* + * We can't rely on just the fields being logged to tell us + * that it is safe to write NULLFSINO - we should only do that + * if quotas are not actually enabled. Hence only write + * NULLFSINO if both in-core quota inodes are NULL. + */ + if (from->sb_gquotino == NULLFSINO && + from->sb_pquotino == NULLFSINO) + to->sb_gquotino = cpu_to_be64(NULLFSINO); + } *fields &= ~(XFS_SB_PQUOTINO | XFS_SB_GQUOTINO); } diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index ec4112d257b..8f8ae95c6e2 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -482,8 +482,8 @@ extern struct cpufreq_governor cpufreq_gov_conservative; *********************************************************************/ /* Special Values of .frequency field */ -#define CPUFREQ_ENTRY_INVALID ~0 -#define CPUFREQ_TABLE_END ~1 +#define CPUFREQ_ENTRY_INVALID ~0u +#define CPUFREQ_TABLE_END ~1u /* Special Values of .flags field */ #define CPUFREQ_BOOST_FREQ (1 << 0) diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 11692dea18a..42aa9b9ecd5 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -17,6 +17,7 @@ #include <linux/lockdep.h> #include <linux/atomic.h> #include <asm/processor.h> +#include <linux/osq_lock.h> /* * Simple, straightforward mutexes with strict semantics: @@ -46,7 +47,6 @@ * - detects multi-task circular deadlocks and prints out all affected * locks and tasks (and only those tasks) */ -struct optimistic_spin_queue; struct mutex { /* 1: unlocked, 0: locked, negative: locked, possible waiters */ atomic_t count; @@ -56,7 +56,7 @@ struct mutex { struct task_struct *owner; #endif #ifdef CONFIG_MUTEX_SPIN_ON_OWNER - struct optimistic_spin_queue *osq; /* Spinner MCS lock */ + struct optimistic_spin_queue osq; /* Spinner MCS lock */ #endif #ifdef CONFIG_DEBUG_MUTEXES const char *name; diff --git a/include/linux/osq_lock.h b/include/linux/osq_lock.h new file mode 100644 index 00000000000..90230d5811c --- /dev/null +++ b/include/linux/osq_lock.h @@ -0,0 +1,27 @@ +#ifndef __LINUX_OSQ_LOCK_H +#define __LINUX_OSQ_LOCK_H + +/* + * An MCS like lock especially tailored for optimistic spinning for sleeping + * lock implementations (mutex, rwsem, etc). + */ + +#define OSQ_UNLOCKED_VAL (0) + +struct optimistic_spin_queue { + /* + * Stores an encoded value of the CPU # of the tail node in the queue. + * If the queue is empty, then it's set to OSQ_UNLOCKED_VAL. + */ + atomic_t tail; +}; + +/* Init macro and function. */ +#define OSQ_LOCK_UNLOCKED { ATOMIC_INIT(OSQ_UNLOCKED_VAL) } + +static inline void osq_lock_init(struct optimistic_spin_queue *lock) +{ + atomic_set(&lock->tail, OSQ_UNLOCKED_VAL); +} + +#endif diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 5a75d19aa66..6a94cc8b1ca 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -44,7 +44,6 @@ #include <linux/debugobjects.h> #include <linux/bug.h> #include <linux/compiler.h> -#include <linux/percpu.h> #include <asm/barrier.h> extern int rcu_expedited; /* for sysctl */ @@ -300,41 +299,6 @@ bool __rcu_is_watching(void); #endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP) */ /* - * Hooks for cond_resched() and friends to avoid RCU CPU stall warnings. - */ - -#define RCU_COND_RESCHED_LIM 256 /* ms vs. 100s of ms. */ -DECLARE_PER_CPU(int, rcu_cond_resched_count); -void rcu_resched(void); - -/* - * Is it time to report RCU quiescent states? - * - * Note unsynchronized access to rcu_cond_resched_count. Yes, we might - * increment some random CPU's count, and possibly also load the result from - * yet another CPU's count. We might even clobber some other CPU's attempt - * to zero its counter. This is all OK because the goal is not precision, - * but rather reasonable amortization of rcu_note_context_switch() overhead - * and extremely high probability of avoiding RCU CPU stall warnings. - * Note that this function has to be preempted in just the wrong place, - * many thousands of times in a row, for anything bad to happen. - */ -static inline bool rcu_should_resched(void) -{ - return raw_cpu_inc_return(rcu_cond_resched_count) >= - RCU_COND_RESCHED_LIM; -} - -/* - * Report quiscent states to RCU if it is time to do so. - */ -static inline void rcu_cond_resched(void) -{ - if (unlikely(rcu_should_resched())) - rcu_resched(); -} - -/* * Infrastructure to implement the synchronize_() primitives in * TREE_RCU and rcu_barrier_() primitives in TINY_RCU. */ @@ -358,9 +322,19 @@ void wait_rcu_gp(call_rcu_func_t crf); * initialization. */ #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD +void init_rcu_head(struct rcu_head *head); +void destroy_rcu_head(struct rcu_head *head); void init_rcu_head_on_stack(struct rcu_head *head); void destroy_rcu_head_on_stack(struct rcu_head *head); #else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ +static inline void init_rcu_head(struct rcu_head *head) +{ +} + +static inline void destroy_rcu_head(struct rcu_head *head) +{ +} + static inline void init_rcu_head_on_stack(struct rcu_head *head) { } diff --git a/include/linux/rwsem-spinlock.h b/include/linux/rwsem-spinlock.h index d5b13bc07a0..561e8615528 100644 --- a/include/linux/rwsem-spinlock.h +++ b/include/linux/rwsem-spinlock.h @@ -15,13 +15,13 @@ #ifdef __KERNEL__ /* * the rw-semaphore definition - * - if activity is 0 then there are no active readers or writers - * - if activity is +ve then that is the number of active readers - * - if activity is -1 then there is one active writer + * - if count is 0 then there are no active readers or writers + * - if count is +ve then that is the number of active readers + * - if count is -1 then there is one active writer * - if wait_list is not empty, then there are processes waiting for the semaphore */ struct rw_semaphore { - __s32 activity; + __s32 count; raw_spinlock_t wait_lock; struct list_head wait_list; #ifdef CONFIG_DEBUG_LOCK_ALLOC diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index 8d79708146a..035d3c57fc8 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -13,10 +13,11 @@ #include <linux/kernel.h> #include <linux/list.h> #include <linux/spinlock.h> - #include <linux/atomic.h> +#ifdef CONFIG_RWSEM_SPIN_ON_OWNER +#include <linux/osq_lock.h> +#endif -struct optimistic_spin_queue; struct rw_semaphore; #ifdef CONFIG_RWSEM_GENERIC_SPINLOCK @@ -25,15 +26,15 @@ struct rw_semaphore; /* All arch specific implementations share the same struct */ struct rw_semaphore { long count; - raw_spinlock_t wait_lock; struct list_head wait_list; -#ifdef CONFIG_SMP + raw_spinlock_t wait_lock; +#ifdef CONFIG_RWSEM_SPIN_ON_OWNER + struct optimistic_spin_queue osq; /* spinner MCS lock */ /* * Write owner. Used as a speculative check to see * if the owner is running on the cpu. */ struct task_struct *owner; - struct optimistic_spin_queue *osq; /* spinner MCS lock */ #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; @@ -64,22 +65,19 @@ static inline int rwsem_is_locked(struct rw_semaphore *sem) # define __RWSEM_DEP_MAP_INIT(lockname) #endif -#if defined(CONFIG_SMP) && !defined(CONFIG_RWSEM_GENERIC_SPINLOCK) -#define __RWSEM_INITIALIZER(name) \ - { RWSEM_UNLOCKED_VALUE, \ - __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock), \ - LIST_HEAD_INIT((name).wait_list), \ - NULL, /* owner */ \ - NULL /* mcs lock */ \ - __RWSEM_DEP_MAP_INIT(name) } +#ifdef CONFIG_RWSEM_SPIN_ON_OWNER +#define __RWSEM_OPT_INIT(lockname) , .osq = OSQ_LOCK_UNLOCKED, .owner = NULL #else -#define __RWSEM_INITIALIZER(name) \ - { RWSEM_UNLOCKED_VALUE, \ - __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock), \ - LIST_HEAD_INIT((name).wait_list) \ - __RWSEM_DEP_MAP_INIT(name) } +#define __RWSEM_OPT_INIT(lockname) #endif +#define __RWSEM_INITIALIZER(name) \ + { .count = RWSEM_UNLOCKED_VALUE, \ + .wait_list = LIST_HEAD_INIT((name).wait_list), \ + .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock) \ + __RWSEM_OPT_INIT(name) \ + __RWSEM_DEP_MAP_INIT(name) } + #define DECLARE_RWSEM(name) \ struct rw_semaphore name = __RWSEM_INITIALIZER(name) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 713b0b88bd5..c4d86198d3d 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -6,6 +6,7 @@ #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/nf_tables.h> +#include <linux/u64_stats_sync.h> #include <net/netlink.h> #define NFT_JUMP_STACK_SIZE 16 @@ -528,8 +529,9 @@ enum nft_chain_type { }; struct nft_stats { - u64 bytes; - u64 pkts; + u64 bytes; + u64 pkts; + struct u64_stats_sync syncp; }; #define NFT_HOOK_OPS_MAX 2 diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h index 26a394cb91a..eee608b12cc 100644 --- a/include/net/netns/nftables.h +++ b/include/net/netns/nftables.h @@ -13,8 +13,8 @@ struct netns_nftables { struct nft_af_info *inet; struct nft_af_info *arp; struct nft_af_info *bridge; + unsigned int base_seq; u8 gencursor; - u8 genctr; }; #endif diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks index 35536d9c096..76768ee812b 100644 --- a/kernel/Kconfig.locks +++ b/kernel/Kconfig.locks @@ -220,9 +220,16 @@ config INLINE_WRITE_UNLOCK_IRQRESTORE endif +config ARCH_SUPPORTS_ATOMIC_RMW + bool + config MUTEX_SPIN_ON_OWNER def_bool y - depends on SMP && !DEBUG_MUTEXES + depends on SMP && !DEBUG_MUTEXES && ARCH_SUPPORTS_ATOMIC_RMW + +config RWSEM_SPIN_ON_OWNER + def_bool y + depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW config ARCH_USE_QUEUE_RWLOCK bool diff --git a/kernel/locking/mcs_spinlock.c b/kernel/locking/mcs_spinlock.c index 838dc9e0066..be9ee1559fc 100644 --- a/kernel/locking/mcs_spinlock.c +++ b/kernel/locking/mcs_spinlock.c @@ -14,21 +14,47 @@ * called from interrupt context and we have preemption disabled while * spinning. */ -static DEFINE_PER_CPU_SHARED_ALIGNED(struct optimistic_spin_queue, osq_node); +static DEFINE_PER_CPU_SHARED_ALIGNED(struct optimistic_spin_node, osq_node); + +/* + * We use the value 0 to represent "no CPU", thus the encoded value + * will be the CPU number incremented by 1. + */ +static inline int encode_cpu(int cpu_nr) +{ + return cpu_nr + 1; +} + +static inline struct optimistic_spin_node *decode_cpu(int encoded_cpu_val) +{ + int cpu_nr = encoded_cpu_val - 1; + + return per_cpu_ptr(&osq_node, cpu_nr); +} /* * Get a stable @node->next pointer, either for unlock() or unqueue() purposes. * Can return NULL in case we were the last queued and we updated @lock instead. */ -static inline struct optimistic_spin_queue * -osq_wait_next(struct optimistic_spin_queue **lock, - struct optimistic_spin_queue *node, - struct optimistic_spin_queue *prev) +static inline struct optimistic_spin_node * +osq_wait_next(struct optimistic_spin_queue *lock, + struct optimistic_spin_node *node, + struct optimistic_spin_node *prev) { - struct optimistic_spin_queue *next = NULL; + struct optimistic_spin_node *next = NULL; + int curr = encode_cpu(smp_processor_id()); + int old; + + /* + * If there is a prev node in queue, then the 'old' value will be + * the prev node's CPU #, else it's set to OSQ_UNLOCKED_VAL since if + * we're currently last in queue, then the queue will then become empty. + */ + old = prev ? prev->cpu : OSQ_UNLOCKED_VAL; for (;;) { - if (*lock == node && cmpxchg(lock, node, prev) == node) { + if (atomic_read(&lock->tail) == curr && + atomic_cmpxchg(&lock->tail, curr, old) == curr) { /* * We were the last queued, we moved @lock back. @prev * will now observe @lock and will complete its @@ -59,18 +85,23 @@ osq_wait_next(struct optimistic_spin_queue **lock, return next; } -bool osq_lock(struct optimistic_spin_queue **lock) +bool osq_lock(struct optimistic_spin_queue *lock) { - struct optimistic_spin_queue *node = this_cpu_ptr(&osq_node); - struct optimistic_spin_queue *prev, *next; + struct optimistic_spin_node *node = this_cpu_ptr(&osq_node); + struct optimistic_spin_node *prev, *next; + int curr = encode_cpu(smp_processor_id()); + int old; node->locked = 0; node->next = NULL; + node->cpu = curr; - node->prev = prev = xchg(lock, node); - if (likely(prev == NULL)) + old = atomic_xchg(&lock->tail, curr); + if (old == OSQ_UNLOCKED_VAL) return true; + prev = decode_cpu(old); + node->prev = prev; ACCESS_ONCE(prev->next) = node; /* @@ -149,20 +180,21 @@ unqueue: return false; } -void osq_unlock(struct optimistic_spin_queue **lock) +void osq_unlock(struct optimistic_spin_queue *lock) { - struct optimistic_spin_queue *node = this_cpu_ptr(&osq_node); - struct optimistic_spin_queue *next; + struct optimistic_spin_node *node, *next; + int curr = encode_cpu(smp_processor_id()); /* * Fast path for the uncontended case. */ - if (likely(cmpxchg(lock, node, NULL) == node)) + if (likely(atomic_cmpxchg(&lock->tail, curr, OSQ_UNLOCKED_VAL) == curr)) return; /* * Second most likely case. */ + node = this_cpu_ptr(&osq_node); next = xchg(&node->next, NULL); if (next) { ACCESS_ONCE(next->locked) = 1; diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h index a2dbac4aca6..74356dc0ce2 100644 --- a/kernel/locking/mcs_spinlock.h +++ b/kernel/locking/mcs_spinlock.h @@ -118,12 +118,13 @@ void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node) * mutex_lock()/rwsem_down_{read,write}() etc. */ -struct optimistic_spin_queue { - struct optimistic_spin_queue *next, *prev; +struct optimistic_spin_node { + struct optimistic_spin_node *next, *prev; int locked; /* 1 if lock acquired */ + int cpu; /* encoded CPU # value */ }; -extern bool osq_lock(struct optimistic_spin_queue **lock); -extern void osq_unlock(struct optimistic_spin_queue **lock); +extern bool osq_lock(struct optimistic_spin_queue *lock); +extern void osq_unlock(struct optimistic_spin_queue *lock); #endif /* __LINUX_MCS_SPINLOCK_H */ diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index bc73d33c676..acca2c1a3c5 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -60,7 +60,7 @@ __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key) INIT_LIST_HEAD(&lock->wait_list); mutex_clear_owner(lock); #ifdef CONFIG_MUTEX_SPIN_ON_OWNER - lock->osq = NULL; + osq_lock_init(&lock->osq); #endif debug_mutex_init(lock, name, key); diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c index 9be8a914497..2c93571162c 100644 --- a/kernel/locking/rwsem-spinlock.c +++ b/kernel/locking/rwsem-spinlock.c @@ -26,7 +26,7 @@ int rwsem_is_locked(struct rw_semaphore *sem) unsigned long flags; if (raw_spin_trylock_irqsave(&sem->wait_lock, flags)) { - ret = (sem->activity != 0); + ret = (sem->count != 0); raw_spin_unlock_irqrestore(&sem->wait_lock, flags); } return ret; @@ -46,7 +46,7 @@ void __init_rwsem(struct rw_semaphore *sem, const char *name, debug_check_no_locks_freed((void *)sem, sizeof(*sem)); lockdep_init_map(&sem->dep_map, name, key, 0); #endif - sem->activity = 0; + sem->count = 0; raw_spin_lock_init(&sem->wait_lock); INIT_LIST_HEAD(&sem->wait_list); } @@ -95,7 +95,7 @@ __rwsem_do_wake(struct rw_semaphore *sem, int wakewrite) waiter = list_entry(next, struct rwsem_waiter, list); } while (waiter->type != RWSEM_WAITING_FOR_WRITE); - sem->activity += woken; + sem->count += woken; out: return sem; @@ -126,9 +126,9 @@ void __sched __down_read(struct rw_semaphore *sem) raw_spin_lock_irqsave(&sem->wait_lock, flags); - if (sem->activity >= 0 && list_empty(&sem->wait_list)) { + if (sem->count >= 0 && list_empty(&sem->wait_list)) { /* granted */ - sem->activity++; + sem->count++; raw_spin_unlock_irqrestore(&sem->wait_lock, flags); goto out; } @@ -170,9 +170,9 @@ int __down_read_trylock(struct rw_semaphore *sem) raw_spin_lock_irqsave(&sem->wait_lock, flags); - if (sem->activity >= 0 && list_empty(&sem->wait_list)) { + if (sem->count >= 0 && list_empty(&sem->wait_list)) { /* granted */ - sem->activity++; + sem->count++; ret = 1; } @@ -206,7 +206,7 @@ void __sched __down_write_nested(struct rw_semaphore *sem, int subclass) * itself into sleep and waiting for system woke it or someone * else in the head of the wait list up. */ - if (sem->activity == 0) + if (sem->count == 0) break; set_task_state(tsk, TASK_UNINTERRUPTIBLE); raw_spin_unlock_irqrestore(&sem->wait_lock, flags); @@ -214,7 +214,7 @@ void __sched __down_write_nested(struct rw_semaphore *sem, int subclass) raw_spin_lock_irqsave(&sem->wait_lock, flags); } /* got the lock */ - sem->activity = -1; + sem->count = -1; list_del(&waiter.list); raw_spin_unlock_irqrestore(&sem->wait_lock, flags); @@ -235,9 +235,9 @@ int __down_write_trylock(struct rw_semaphore *sem) raw_spin_lock_irqsave(&sem->wait_lock, flags); - if (sem->activity == 0) { + if (sem->count == 0) { /* got the lock */ - sem->activity = -1; + sem->count = -1; ret = 1; } @@ -255,7 +255,7 @@ void __up_read(struct rw_semaphore *sem) raw_spin_lock_irqsave(&sem->wait_lock, flags); - if (--sem->activity == 0 && !list_empty(&sem->wait_list)) + if (--sem->count == 0 && !list_empty(&sem->wait_list)) sem = __rwsem_wake_one_writer(sem); raw_spin_unlock_irqrestore(&sem->wait_lock, flags); @@ -270,7 +270,7 @@ void __up_write(struct rw_semaphore *sem) raw_spin_lock_irqsave(&sem->wait_lock, flags); - sem->activity = 0; + sem->count = 0; if (!list_empty(&sem->wait_list)) sem = __rwsem_do_wake(sem, 1); @@ -287,7 +287,7 @@ void __downgrade_write(struct rw_semaphore *sem) raw_spin_lock_irqsave(&sem->wait_lock, flags); - sem->activity = 1; + sem->count = 1; if (!list_empty(&sem->wait_list)) sem = __rwsem_do_wake(sem, 0); diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index dacc32142fc..a2391ac135c 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -82,9 +82,9 @@ void __init_rwsem(struct rw_semaphore *sem, const char *name, sem->count = RWSEM_UNLOCKED_VALUE; raw_spin_lock_init(&sem->wait_lock); INIT_LIST_HEAD(&sem->wait_list); -#ifdef CONFIG_SMP +#ifdef CONFIG_RWSEM_SPIN_ON_OWNER sem->owner = NULL; - sem->osq = NULL; + osq_lock_init(&sem->osq); #endif } @@ -262,7 +262,7 @@ static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem) return false; } -#ifdef CONFIG_SMP +#ifdef CONFIG_RWSEM_SPIN_ON_OWNER /* * Try to acquire write lock before the writer has been put on wait queue. */ @@ -285,10 +285,10 @@ static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem) static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem) { struct task_struct *owner; - bool on_cpu = true; + bool on_cpu = false; if (need_resched()) - return 0; + return false; rcu_read_lock(); owner = ACCESS_ONCE(sem->owner); @@ -297,9 +297,9 @@ static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem) rcu_read_unlock(); /* - * If sem->owner is not set, the rwsem owner may have - * just acquired it and not set the owner yet or the rwsem - * has been released. + * If sem->owner is not set, yet we have just recently entered the + * slowpath, then there is a possibility reader(s) may have the lock. + * To be safe, avoid spinning in these situations. */ return on_cpu; } diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index 42f806de49d..e2d3bc7f03b 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -12,7 +12,7 @@ #include <linux/atomic.h> -#if defined(CONFIG_SMP) && defined(CONFIG_RWSEM_XCHGADD_ALGORITHM) +#ifdef CONFIG_RWSEM_SPIN_ON_OWNER static inline void rwsem_set_owner(struct rw_semaphore *sem) { sem->owner = current; diff --git a/kernel/power/process.c b/kernel/power/process.c index 0ca8d83e236..4ee194eb524 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -186,6 +186,7 @@ void thaw_processes(void) printk("Restarting tasks ... "); + __usermodehelper_set_disable_depth(UMH_FREEZING); thaw_workqueues(); read_lock(&tasklist_lock); diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 4dd8822f732..ed35a4790af 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -306,7 +306,7 @@ int suspend_devices_and_enter(suspend_state_t state) error = suspend_ops->begin(state); if (error) goto Close; - } else if (state == PM_SUSPEND_FREEZE && freeze_ops->begin) { + } else if (state == PM_SUSPEND_FREEZE && freeze_ops && freeze_ops->begin) { error = freeze_ops->begin(); if (error) goto Close; @@ -335,7 +335,7 @@ int suspend_devices_and_enter(suspend_state_t state) Close: if (need_suspend_ops(state) && suspend_ops->end) suspend_ops->end(); - else if (state == PM_SUSPEND_FREEZE && freeze_ops->end) + else if (state == PM_SUSPEND_FREEZE && freeze_ops && freeze_ops->end) freeze_ops->end(); return error; diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index f1ba77363fb..625d0b0cd75 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -206,6 +206,70 @@ void rcu_bh_qs(int cpu) rdp->passed_quiesce = 1; } +static DEFINE_PER_CPU(int, rcu_sched_qs_mask); + +static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = { + .dynticks_nesting = DYNTICK_TASK_EXIT_IDLE, + .dynticks = ATOMIC_INIT(1), +#ifdef CONFIG_NO_HZ_FULL_SYSIDLE + .dynticks_idle_nesting = DYNTICK_TASK_NEST_VALUE, + .dynticks_idle = ATOMIC_INIT(1), +#endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ +}; + +/* + * Let the RCU core know that this CPU has gone through the scheduler, + * which is a quiescent state. This is called when the need for a + * quiescent state is urgent, so we burn an atomic operation and full + * memory barriers to let the RCU core know about it, regardless of what + * this CPU might (or might not) do in the near future. + * + * We inform the RCU core by emulating a zero-duration dyntick-idle + * period, which we in turn do by incrementing the ->dynticks counter + * by two. + */ +static void rcu_momentary_dyntick_idle(void) +{ + unsigned long flags; + struct rcu_data *rdp; + struct rcu_dynticks *rdtp; + int resched_mask; + struct rcu_state *rsp; + + local_irq_save(flags); + + /* + * Yes, we can lose flag-setting operations. This is OK, because + * the flag will be set again after some delay. + */ + resched_mask = raw_cpu_read(rcu_sched_qs_mask); + raw_cpu_write(rcu_sched_qs_mask, 0); + + /* Find the flavor that needs a quiescent state. */ + for_each_rcu_flavor(rsp) { + rdp = raw_cpu_ptr(rsp->rda); + if (!(resched_mask & rsp->flavor_mask)) + continue; + smp_mb(); /* rcu_sched_qs_mask before cond_resched_completed. */ + if (ACCESS_ONCE(rdp->mynode->completed) != + ACCESS_ONCE(rdp->cond_resched_completed)) + continue; + + /* + * Pretend to be momentarily idle for the quiescent state. + * This allows the grace-period kthread to record the + * quiescent state, with no need for this CPU to do anything + * further. + */ + rdtp = this_cpu_ptr(&rcu_dynticks); + smp_mb__before_atomic(); /* Earlier stuff before QS. */ + atomic_add(2, &rdtp->dynticks); /* QS. */ + smp_mb__after_atomic(); /* Later stuff after QS. */ + break; + } + local_irq_restore(flags); +} + /* * Note a context switch. This is a quiescent state for RCU-sched, * and requires special handling for preemptible RCU. @@ -216,19 +280,12 @@ void rcu_note_context_switch(int cpu) trace_rcu_utilization(TPS("Start context switch")); rcu_sched_qs(cpu); rcu_preempt_note_context_switch(cpu); + if (unlikely(raw_cpu_read(rcu_sched_qs_mask))) + rcu_momentary_dyntick_idle(); trace_rcu_utilization(TPS("End context switch")); } EXPORT_SYMBOL_GPL(rcu_note_context_switch); -static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = { - .dynticks_nesting = DYNTICK_TASK_EXIT_IDLE, - .dynticks = ATOMIC_INIT(1), -#ifdef CONFIG_NO_HZ_FULL_SYSIDLE - .dynticks_idle_nesting = DYNTICK_TASK_NEST_VALUE, - .dynticks_idle = ATOMIC_INIT(1), -#endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ -}; - static long blimit = 10; /* Maximum callbacks per rcu_do_batch. */ static long qhimark = 10000; /* If this many pending, ignore blimit. */ static long qlowmark = 100; /* Once only this many pending, use blimit. */ @@ -243,6 +300,13 @@ static ulong jiffies_till_next_fqs = ULONG_MAX; module_param(jiffies_till_first_fqs, ulong, 0644); module_param(jiffies_till_next_fqs, ulong, 0644); +/* + * How long the grace period must be before we start recruiting + * quiescent-state help from rcu_note_context_switch(). + */ +static ulong jiffies_till_sched_qs = HZ / 20; +module_param(jiffies_till_sched_qs, ulong, 0644); + static bool rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp); static void force_qs_rnp(struct rcu_state *rsp, @@ -853,6 +917,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp, bool *isidle, unsigned long *maxj) { unsigned int curr; + int *rcrmp; unsigned int snap; curr = (unsigned int)atomic_add_return(0, &rdp->dynticks->dynticks); @@ -893,27 +958,43 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp, } /* - * There is a possibility that a CPU in adaptive-ticks state - * might run in the kernel with the scheduling-clock tick disabled - * for an extended time period. Invoke rcu_kick_nohz_cpu() to - * force the CPU to restart the scheduling-clock tick in this - * CPU is in this state. - */ - rcu_kick_nohz_cpu(rdp->cpu); - - /* - * Alternatively, the CPU might be running in the kernel - * for an extended period of time without a quiescent state. - * Attempt to force the CPU through the scheduler to gain the - * needed quiescent state, but only if the grace period has gone - * on for an uncommonly long time. If there are many stuck CPUs, - * we will beat on the first one until it gets unstuck, then move - * to the next. Only do this for the primary flavor of RCU. + * A CPU running for an extended time within the kernel can + * delay RCU grace periods. When the CPU is in NO_HZ_FULL mode, + * even context-switching back and forth between a pair of + * in-kernel CPU-bound tasks cannot advance grace periods. + * So if the grace period is old enough, make the CPU pay attention. + * Note that the unsynchronized assignments to the per-CPU + * rcu_sched_qs_mask variable are safe. Yes, setting of + * bits can be lost, but they will be set again on the next + * force-quiescent-state pass. So lost bit sets do not result + * in incorrect behavior, merely in a grace period lasting + * a few jiffies longer than it might otherwise. Because + * there are at most four threads involved, and because the + * updates are only once every few jiffies, the probability of + * lossage (and thus of slight grace-period extension) is + * quite low. + * + * Note that if the jiffies_till_sched_qs boot/sysfs parameter + * is set too high, we override with half of the RCU CPU stall + * warning delay. */ - if (rdp->rsp == rcu_state_p && + rcrmp = &per_cpu(rcu_sched_qs_mask, rdp->cpu); + if (ULONG_CMP_GE(jiffies, + rdp->rsp->gp_start + jiffies_till_sched_qs) || ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) { - rdp->rsp->jiffies_resched += 5; - resched_cpu(rdp->cpu); + if (!(ACCESS_ONCE(*rcrmp) & rdp->rsp->flavor_mask)) { + ACCESS_ONCE(rdp->cond_resched_completed) = + ACCESS_ONCE(rdp->mynode->completed); + smp_mb(); /* ->cond_resched_completed before *rcrmp. */ + ACCESS_ONCE(*rcrmp) = + ACCESS_ONCE(*rcrmp) + rdp->rsp->flavor_mask; + resched_cpu(rdp->cpu); /* Force CPU into scheduler. */ + rdp->rsp->jiffies_resched += 5; /* Enable beating. */ + } else if (ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) { + /* Time to beat on that CPU again! */ + resched_cpu(rdp->cpu); /* Force CPU into scheduler. */ + rdp->rsp->jiffies_resched += 5; /* Re-enable beating. */ + } } return 0; @@ -3491,6 +3572,7 @@ static void __init rcu_init_one(struct rcu_state *rsp, "rcu_node_fqs_1", "rcu_node_fqs_2", "rcu_node_fqs_3" }; /* Match MAX_RCU_LVLS */ + static u8 fl_mask = 0x1; int cpustride = 1; int i; int j; @@ -3509,6 +3591,8 @@ static void __init rcu_init_one(struct rcu_state *rsp, for (i = 1; i < rcu_num_lvls; i++) rsp->level[i] = rsp->level[i - 1] + rsp->levelcnt[i - 1]; rcu_init_levelspread(rsp); + rsp->flavor_mask = fl_mask; + fl_mask <<= 1; /* Initialize the elements themselves, starting from the leaves. */ diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index bf2c1e66969..0f69a79c5b7 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -307,6 +307,9 @@ struct rcu_data { /* 4) reasons this CPU needed to be kicked by force_quiescent_state */ unsigned long dynticks_fqs; /* Kicked due to dynticks idle. */ unsigned long offline_fqs; /* Kicked due to being offline. */ + unsigned long cond_resched_completed; + /* Grace period that needs help */ + /* from cond_resched(). */ /* 5) __rcu_pending() statistics. */ unsigned long n_rcu_pending; /* rcu_pending() calls since boot. */ @@ -392,6 +395,7 @@ struct rcu_state { struct rcu_node *level[RCU_NUM_LVLS]; /* Hierarchy levels. */ u32 levelcnt[MAX_RCU_LVLS + 1]; /* # nodes in each level. */ u8 levelspread[RCU_NUM_LVLS]; /* kids/node in each level. */ + u8 flavor_mask; /* bit in flavor mask. */ struct rcu_data __percpu *rda; /* pointer of percu rcu_data. */ void (*call)(struct rcu_head *head, /* call_rcu() flavor. */ void (*func)(struct rcu_head *head)); @@ -563,7 +567,7 @@ static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp); static void do_nocb_deferred_wakeup(struct rcu_data *rdp); static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp); static void rcu_spawn_nocb_kthreads(struct rcu_state *rsp); -static void rcu_kick_nohz_cpu(int cpu); +static void __maybe_unused rcu_kick_nohz_cpu(int cpu); static bool init_nocb_callback_list(struct rcu_data *rdp); static void rcu_sysidle_enter(struct rcu_dynticks *rdtp, int irq); static void rcu_sysidle_exit(struct rcu_dynticks *rdtp, int irq); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index cbc2c45265e..02ac0fb186b 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -2404,7 +2404,7 @@ static bool init_nocb_callback_list(struct rcu_data *rdp) * if an adaptive-ticks CPU is failing to respond to the current grace * period and has not be idle from an RCU perspective, kick it. */ -static void rcu_kick_nohz_cpu(int cpu) +static void __maybe_unused rcu_kick_nohz_cpu(int cpu) { #ifdef CONFIG_NO_HZ_FULL if (tick_nohz_full_cpu(cpu)) diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index a2aeb4df0f6..bc788357053 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -200,12 +200,12 @@ void wait_rcu_gp(call_rcu_func_t crf) EXPORT_SYMBOL_GPL(wait_rcu_gp); #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD -static inline void debug_init_rcu_head(struct rcu_head *head) +void init_rcu_head(struct rcu_head *head) { debug_object_init(head, &rcuhead_debug_descr); } -static inline void debug_rcu_head_free(struct rcu_head *head) +void destroy_rcu_head(struct rcu_head *head) { debug_object_free(head, &rcuhead_debug_descr); } @@ -350,21 +350,3 @@ static int __init check_cpu_stall_init(void) early_initcall(check_cpu_stall_init); #endif /* #ifdef CONFIG_RCU_STALL_COMMON */ - -/* - * Hooks for cond_resched() and friends to avoid RCU CPU stall warnings. - */ - -DEFINE_PER_CPU(int, rcu_cond_resched_count); - -/* - * Report a set of RCU quiescent states, for use by cond_resched() - * and friends. Out of line due to being called infrequently. - */ -void rcu_resched(void) -{ - preempt_disable(); - __this_cpu_write(rcu_cond_resched_count, 0); - rcu_note_context_switch(smp_processor_id()); - preempt_enable(); -} diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 3bdf01b494f..bc1638b3344 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4147,7 +4147,6 @@ static void __cond_resched(void) int __sched _cond_resched(void) { - rcu_cond_resched(); if (should_resched()) { __cond_resched(); return 1; @@ -4166,18 +4165,15 @@ EXPORT_SYMBOL(_cond_resched); */ int __cond_resched_lock(spinlock_t *lock) { - bool need_rcu_resched = rcu_should_resched(); int resched = should_resched(); int ret = 0; lockdep_assert_held(lock); - if (spin_needbreak(lock) || resched || need_rcu_resched) { + if (spin_needbreak(lock) || resched) { spin_unlock(lock); if (resched) __cond_resched(); - else if (unlikely(need_rcu_resched)) - rcu_resched(); else cpu_relax(); ret = 1; @@ -4191,7 +4187,6 @@ int __sched __cond_resched_softirq(void) { BUG_ON(!in_softirq()); - rcu_cond_resched(); /* BH disabled OK, just recording QSes. */ if (should_resched()) { local_bh_enable(); __cond_resched(); diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 695f9773bb6..627b3c34b82 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -608,7 +608,7 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) avg_atom = p->se.sum_exec_runtime; if (nr_switches) - do_div(avg_atom, nr_switches); + avg_atom = div64_ul(avg_atom, nr_switches); else avg_atom = -1LL; diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 88c9c65a430..fe75444ae7e 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -585,9 +585,14 @@ static int alarm_timer_set(struct k_itimer *timr, int flags, struct itimerspec *new_setting, struct itimerspec *old_setting) { + ktime_t exp; + if (!rtcdev) return -ENOTSUPP; + if (flags & ~TIMER_ABSTIME) + return -EINVAL; + if (old_setting) alarm_timer_get(timr, old_setting); @@ -597,8 +602,16 @@ static int alarm_timer_set(struct k_itimer *timr, int flags, /* start the timer */ timr->it.alarm.interval = timespec_to_ktime(new_setting->it_interval); - alarm_start(&timr->it.alarm.alarmtimer, - timespec_to_ktime(new_setting->it_value)); + exp = timespec_to_ktime(new_setting->it_value); + /* Convert (if necessary) to absolute time */ + if (flags != TIMER_ABSTIME) { + ktime_t now; + + now = alarm_bases[timr->it.alarm.alarmtimer.type].gettime(); + exp = ktime_add(now, exp); + } + + alarm_start(&timr->it.alarm.alarmtimer, exp); return 0; } @@ -730,6 +743,9 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags, if (!alarmtimer_get_rtcdev()) return -ENOTSUPP; + if (flags & ~TIMER_ABSTIME) + return -EINVAL; + if (!capable(CAP_WAKE_ALARM)) return -EPERM; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 5b372e3ed67..ac9d1dad630 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -265,12 +265,12 @@ static void update_ftrace_function(void) func = ftrace_ops_list_func; } + update_function_graph_func(); + /* If there's no change, then do nothing more here */ if (ftrace_trace_function == func) return; - update_function_graph_func(); - /* * If we are using the list function, it doesn't care * about the function_trace_ops. diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 7c56c3d0694..ff7027199a9 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -616,10 +616,6 @@ int ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu, struct ring_buffer_per_cpu *cpu_buffer; struct rb_irq_work *work; - if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) || - (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu))) - return POLLIN | POLLRDNORM; - if (cpu == RING_BUFFER_ALL_CPUS) work = &buffer->irq_work; else { diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index f243444a377..291397e6666 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -466,6 +466,12 @@ int __trace_puts(unsigned long ip, const char *str, int size) struct print_entry *entry; unsigned long irq_flags; int alloc; + int pc; + + if (!(trace_flags & TRACE_ITER_PRINTK)) + return 0; + + pc = preempt_count(); if (unlikely(tracing_selftest_running || tracing_disabled)) return 0; @@ -475,7 +481,7 @@ int __trace_puts(unsigned long ip, const char *str, int size) local_save_flags(irq_flags); buffer = global_trace.trace_buffer.buffer; event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc, - irq_flags, preempt_count()); + irq_flags, pc); if (!event) return 0; @@ -492,6 +498,7 @@ int __trace_puts(unsigned long ip, const char *str, int size) entry->buf[size] = '\0'; __buffer_unlock_commit(buffer, event); + ftrace_trace_stack(buffer, irq_flags, 4, pc); return size; } @@ -509,6 +516,12 @@ int __trace_bputs(unsigned long ip, const char *str) struct bputs_entry *entry; unsigned long irq_flags; int size = sizeof(struct bputs_entry); + int pc; + + if (!(trace_flags & TRACE_ITER_PRINTK)) + return 0; + + pc = preempt_count(); if (unlikely(tracing_selftest_running || tracing_disabled)) return 0; @@ -516,7 +529,7 @@ int __trace_bputs(unsigned long ip, const char *str) local_save_flags(irq_flags); buffer = global_trace.trace_buffer.buffer; event = trace_buffer_lock_reserve(buffer, TRACE_BPUTS, size, - irq_flags, preempt_count()); + irq_flags, pc); if (!event) return 0; @@ -525,6 +538,7 @@ int __trace_bputs(unsigned long ip, const char *str) entry->str = str; __buffer_unlock_commit(buffer, event); + ftrace_trace_stack(buffer, irq_flags, 4, pc); return 1; } @@ -809,7 +823,7 @@ static struct { { trace_clock_local, "local", 1 }, { trace_clock_global, "global", 1 }, { trace_clock_counter, "counter", 0 }, - { trace_clock_jiffies, "uptime", 1 }, + { trace_clock_jiffies, "uptime", 0 }, { trace_clock, "perf", 1 }, ARCH_TRACE_CLOCKS }; diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c index 26dc348332b..57b67b1f24d 100644 --- a/kernel/trace/trace_clock.c +++ b/kernel/trace/trace_clock.c @@ -59,13 +59,14 @@ u64 notrace trace_clock(void) /* * trace_jiffy_clock(): Simply use jiffies as a clock counter. + * Note that this use of jiffies_64 is not completely safe on + * 32-bit systems. But the window is tiny, and the effect if + * we are affected is that we will have an obviously bogus + * timestamp on a trace event - i.e. not life threatening. */ u64 notrace trace_clock_jiffies(void) { - u64 jiffy = jiffies - INITIAL_JIFFIES; - - /* Return nsecs */ - return (u64)jiffies_to_usecs(jiffy) * 1000ULL; + return jiffies_64_to_clock_t(jiffies_64 - INITIAL_JIFFIES); } /* diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index f99e0b3bca8..2de53628689 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -470,6 +470,7 @@ static void remove_event_file_dir(struct ftrace_event_file *file) list_del(&file->list); remove_subsystem(file->system); + free_event_filter(file->filter); kmem_cache_free(file_cachep, file); } diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 6f0d9ec3795..a957c814072 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -800,11 +800,6 @@ static int batadv_check_claim_group(struct batadv_priv *bat_priv, bla_dst = (struct batadv_bla_claim_dst *)hw_dst; bla_dst_own = &bat_priv->bla.claim_dest; - /* check if it is a claim packet in general */ - if (memcmp(bla_dst->magic, bla_dst_own->magic, - sizeof(bla_dst->magic)) != 0) - return 0; - /* if announcement packet, use the source, * otherwise assume it is in the hw_src */ @@ -866,12 +861,13 @@ static int batadv_bla_process_claim(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, struct sk_buff *skb) { - struct batadv_bla_claim_dst *bla_dst; + struct batadv_bla_claim_dst *bla_dst, *bla_dst_own; uint8_t *hw_src, *hw_dst; - struct vlan_ethhdr *vhdr; + struct vlan_hdr *vhdr, vhdr_buf; struct ethhdr *ethhdr; struct arphdr *arphdr; unsigned short vid; + int vlan_depth = 0; __be16 proto; int headlen; int ret; @@ -882,9 +878,24 @@ static int batadv_bla_process_claim(struct batadv_priv *bat_priv, proto = ethhdr->h_proto; headlen = ETH_HLEN; if (vid & BATADV_VLAN_HAS_TAG) { - vhdr = vlan_eth_hdr(skb); - proto = vhdr->h_vlan_encapsulated_proto; - headlen += VLAN_HLEN; + /* Traverse the VLAN/Ethertypes. + * + * At this point it is known that the first protocol is a VLAN + * header, so start checking at the encapsulated protocol. + * + * The depth of the VLAN headers is recorded to drop BLA claim + * frames encapsulated into multiple VLAN headers (QinQ). + */ + do { + vhdr = skb_header_pointer(skb, headlen, VLAN_HLEN, + &vhdr_buf); + if (!vhdr) + return 0; + + proto = vhdr->h_vlan_encapsulated_proto; + headlen += VLAN_HLEN; + vlan_depth++; + } while (proto == htons(ETH_P_8021Q)); } if (proto != htons(ETH_P_ARP)) @@ -914,6 +925,19 @@ static int batadv_bla_process_claim(struct batadv_priv *bat_priv, hw_src = (uint8_t *)arphdr + sizeof(struct arphdr); hw_dst = hw_src + ETH_ALEN + 4; bla_dst = (struct batadv_bla_claim_dst *)hw_dst; + bla_dst_own = &bat_priv->bla.claim_dest; + + /* check if it is a claim frame in general */ + if (memcmp(bla_dst->magic, bla_dst_own->magic, + sizeof(bla_dst->magic)) != 0) + return 0; + + /* check if there is a claim frame encapsulated deeper in (QinQ) and + * drop that, as this is not supported by BLA but should also not be + * sent via the mesh. + */ + if (vlan_depth > 1) + return 1; /* check if it is a claim frame. */ ret = batadv_check_claim_group(bat_priv, primary_if, hw_src, hw_dst, diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index d551e6302cf..e0a723991c5 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -448,10 +448,15 @@ out: * possibly free it * @softif_vlan: the vlan object to release */ -void batadv_softif_vlan_free_ref(struct batadv_softif_vlan *softif_vlan) +void batadv_softif_vlan_free_ref(struct batadv_softif_vlan *vlan) { - if (atomic_dec_and_test(&softif_vlan->refcount)) - kfree_rcu(softif_vlan, rcu); + if (atomic_dec_and_test(&vlan->refcount)) { + spin_lock_bh(&vlan->bat_priv->softif_vlan_list_lock); + hlist_del_rcu(&vlan->list); + spin_unlock_bh(&vlan->bat_priv->softif_vlan_list_lock); + + kfree_rcu(vlan, rcu); + } } /** @@ -505,6 +510,7 @@ int batadv_softif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid) if (!vlan) return -ENOMEM; + vlan->bat_priv = bat_priv; vlan->vid = vid; atomic_set(&vlan->refcount, 1); @@ -516,6 +522,10 @@ int batadv_softif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid) return err; } + spin_lock_bh(&bat_priv->softif_vlan_list_lock); + hlist_add_head_rcu(&vlan->list, &bat_priv->softif_vlan_list); + spin_unlock_bh(&bat_priv->softif_vlan_list_lock); + /* add a new TT local entry. This one will be marked with the NOPURGE * flag */ @@ -523,10 +533,6 @@ int batadv_softif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid) bat_priv->soft_iface->dev_addr, vid, BATADV_NULL_IFINDEX, BATADV_NO_MARK); - spin_lock_bh(&bat_priv->softif_vlan_list_lock); - hlist_add_head_rcu(&vlan->list, &bat_priv->softif_vlan_list); - spin_unlock_bh(&bat_priv->softif_vlan_list_lock); - return 0; } @@ -538,18 +544,13 @@ int batadv_softif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid) static void batadv_softif_destroy_vlan(struct batadv_priv *bat_priv, struct batadv_softif_vlan *vlan) { - spin_lock_bh(&bat_priv->softif_vlan_list_lock); - hlist_del_rcu(&vlan->list); - spin_unlock_bh(&bat_priv->softif_vlan_list_lock); - - batadv_sysfs_del_vlan(bat_priv, vlan); - /* explicitly remove the associated TT local entry because it is marked * with the NOPURGE flag */ batadv_tt_local_remove(bat_priv, bat_priv->soft_iface->dev_addr, vlan->vid, "vlan interface destroyed", false); + batadv_sysfs_del_vlan(bat_priv, vlan); batadv_softif_vlan_free_ref(vlan); } @@ -567,6 +568,8 @@ static int batadv_interface_add_vid(struct net_device *dev, __be16 proto, unsigned short vid) { struct batadv_priv *bat_priv = netdev_priv(dev); + struct batadv_softif_vlan *vlan; + int ret; /* only 802.1Q vlans are supported. * batman-adv does not know how to handle other types @@ -576,7 +579,36 @@ static int batadv_interface_add_vid(struct net_device *dev, __be16 proto, vid |= BATADV_VLAN_HAS_TAG; - return batadv_softif_create_vlan(bat_priv, vid); + /* if a new vlan is getting created and it already exists, it means that + * it was not deleted yet. batadv_softif_vlan_get() increases the + * refcount in order to revive the object. + * + * if it does not exist then create it. + */ + vlan = batadv_softif_vlan_get(bat_priv, vid); + if (!vlan) + return batadv_softif_create_vlan(bat_priv, vid); + + /* recreate the sysfs object if it was already destroyed (and it should + * be since we received a kill_vid() for this vlan + */ + if (!vlan->kobj) { + ret = batadv_sysfs_add_vlan(bat_priv->soft_iface, vlan); + if (ret) { + batadv_softif_vlan_free_ref(vlan); + return ret; + } + } + + /* add a new TT local entry. This one will be marked with the NOPURGE + * flag. This must be added again, even if the vlan object already + * exists, because the entry was deleted by kill_vid() + */ + batadv_tt_local_add(bat_priv->soft_iface, + bat_priv->soft_iface->dev_addr, vid, + BATADV_NULL_IFINDEX, BATADV_NO_MARK); + + return 0; } /** diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index d636bde72c9..5f59e7f899a 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -511,6 +511,7 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, struct batadv_priv *bat_priv = netdev_priv(soft_iface); struct batadv_tt_local_entry *tt_local; struct batadv_tt_global_entry *tt_global = NULL; + struct batadv_softif_vlan *vlan; struct net_device *in_dev = NULL; struct hlist_head *head; struct batadv_tt_orig_list_entry *orig_entry; @@ -572,6 +573,9 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, if (!tt_local) goto out; + /* increase the refcounter of the related vlan */ + vlan = batadv_softif_vlan_get(bat_priv, vid); + batadv_dbg(BATADV_DBG_TT, bat_priv, "Creating new local tt entry: %pM (vid: %d, ttvn: %d)\n", addr, BATADV_PRINT_VID(vid), @@ -604,6 +608,7 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, if (unlikely(hash_added != 0)) { /* remove the reference for the hash */ batadv_tt_local_entry_free_ref(tt_local); + batadv_softif_vlan_free_ref(vlan); goto out; } @@ -1009,6 +1014,7 @@ uint16_t batadv_tt_local_remove(struct batadv_priv *bat_priv, { struct batadv_tt_local_entry *tt_local_entry; uint16_t flags, curr_flags = BATADV_NO_FLAGS; + struct batadv_softif_vlan *vlan; tt_local_entry = batadv_tt_local_hash_find(bat_priv, addr, vid); if (!tt_local_entry) @@ -1039,6 +1045,11 @@ uint16_t batadv_tt_local_remove(struct batadv_priv *bat_priv, hlist_del_rcu(&tt_local_entry->common.hash_entry); batadv_tt_local_entry_free_ref(tt_local_entry); + /* decrease the reference held for this vlan */ + vlan = batadv_softif_vlan_get(bat_priv, vid); + batadv_softif_vlan_free_ref(vlan); + batadv_softif_vlan_free_ref(vlan); + out: if (tt_local_entry) batadv_tt_local_entry_free_ref(tt_local_entry); @@ -1111,6 +1122,7 @@ static void batadv_tt_local_table_free(struct batadv_priv *bat_priv) spinlock_t *list_lock; /* protects write access to the hash lists */ struct batadv_tt_common_entry *tt_common_entry; struct batadv_tt_local_entry *tt_local; + struct batadv_softif_vlan *vlan; struct hlist_node *node_tmp; struct hlist_head *head; uint32_t i; @@ -1131,6 +1143,13 @@ static void batadv_tt_local_table_free(struct batadv_priv *bat_priv) tt_local = container_of(tt_common_entry, struct batadv_tt_local_entry, common); + + /* decrease the reference held for this vlan */ + vlan = batadv_softif_vlan_get(bat_priv, + tt_common_entry->vid); + batadv_softif_vlan_free_ref(vlan); + batadv_softif_vlan_free_ref(vlan); + batadv_tt_local_entry_free_ref(tt_local); } spin_unlock_bh(list_lock); @@ -3139,6 +3158,7 @@ static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv) struct batadv_hashtable *hash = bat_priv->tt.local_hash; struct batadv_tt_common_entry *tt_common; struct batadv_tt_local_entry *tt_local; + struct batadv_softif_vlan *vlan; struct hlist_node *node_tmp; struct hlist_head *head; spinlock_t *list_lock; /* protects write access to the hash lists */ @@ -3167,6 +3187,12 @@ static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv) tt_local = container_of(tt_common, struct batadv_tt_local_entry, common); + + /* decrease the reference held for this vlan */ + vlan = batadv_softif_vlan_get(bat_priv, tt_common->vid); + batadv_softif_vlan_free_ref(vlan); + batadv_softif_vlan_free_ref(vlan); + batadv_tt_local_entry_free_ref(tt_local); } spin_unlock_bh(list_lock); diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 34891a56773..8854c05622a 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -687,6 +687,7 @@ struct batadv_priv_nc { /** * struct batadv_softif_vlan - per VLAN attributes set + * @bat_priv: pointer to the mesh object * @vid: VLAN identifier * @kobj: kobject for sysfs vlan subdirectory * @ap_isolation: AP isolation state @@ -696,6 +697,7 @@ struct batadv_priv_nc { * @rcu: struct used for freeing in a RCU-safe manner */ struct batadv_softif_vlan { + struct batadv_priv *bat_priv; unsigned short vid; struct kobject *kobj; atomic_t ap_isolation; /* boolean */ diff --git a/net/core/dev.c b/net/core/dev.c index e52a3788d18..e1b7cfaccd6 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4106,6 +4106,8 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) skb->vlan_tci = 0; skb->dev = napi->dev; skb->skb_iif = 0; + skb->encapsulation = 0; + skb_shinfo(skb)->gso_type = 0; skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); napi->skb = skb; diff --git a/net/dns_resolver/dns_query.c b/net/dns_resolver/dns_query.c index 9acec61f543..dd8696a3dbe 100644 --- a/net/dns_resolver/dns_query.c +++ b/net/dns_resolver/dns_query.c @@ -150,7 +150,7 @@ int dns_query(const char *type, const char *name, size_t namelen, goto put; memcpy(*_result, upayload->data, len); - *_result[len] = '\0'; + (*_result)[len] = '\0'; if (_expiry) *_expiry = rkey->expiry; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index d5e6836cf77..d156b3c5f36 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1429,6 +1429,9 @@ static int inet_gro_complete(struct sk_buff *skb, int nhoff) int proto = iph->protocol; int err = -ENOSYS; + if (skb->encapsulation) + skb_set_inner_network_header(skb, nhoff); + csum_replace2(&iph->check, iph->tot_len, newlen); iph->tot_len = newlen; diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index eb92deb1266..f0bdd47bbbc 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -263,6 +263,9 @@ static int gre_gro_complete(struct sk_buff *skb, int nhoff) int err = -ENOENT; __be16 type; + skb->encapsulation = 1; + skb_shinfo(skb)->gso_type = SKB_GSO_GRE; + type = greh->protocol; if (greh->flags & GRE_KEY) grehlen += GRE_HEADER_SECTION; diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index 5e7aecea05c..ad382499bac 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -288,6 +288,10 @@ int ip_options_compile(struct net *net, optptr++; continue; } + if (unlikely(l < 2)) { + pp_ptr = optptr; + goto error; + } optlen = optptr[1]; if (optlen < 2 || optlen > l) { pp_ptr = optptr; diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 4e86c59ec7f..55046ecd083 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -309,7 +309,7 @@ static int tcp4_gro_complete(struct sk_buff *skb, int thoff) th->check = ~tcp_v4_check(skb->len - thoff, iph->saddr, iph->daddr, 0); - skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; + skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4; return tcp_gro_complete(skb); } diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index 8517d3cd1ae..01b0ff9a0c2 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -73,7 +73,7 @@ static int tcp6_gro_complete(struct sk_buff *skb, int thoff) th->check = ~tcp_v6_check(skb->len - thoff, &iph->saddr, &iph->daddr, 0); - skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; + skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV6; return tcp_gro_complete(skb); } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index ab4566cfcbe..8746ff9a835 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -35,7 +35,7 @@ int nft_register_afinfo(struct net *net, struct nft_af_info *afi) { INIT_LIST_HEAD(&afi->tables); nfnl_lock(NFNL_SUBSYS_NFTABLES); - list_add_tail(&afi->list, &net->nft.af_info); + list_add_tail_rcu(&afi->list, &net->nft.af_info); nfnl_unlock(NFNL_SUBSYS_NFTABLES); return 0; } @@ -51,7 +51,7 @@ EXPORT_SYMBOL_GPL(nft_register_afinfo); void nft_unregister_afinfo(struct nft_af_info *afi) { nfnl_lock(NFNL_SUBSYS_NFTABLES); - list_del(&afi->list); + list_del_rcu(&afi->list); nfnl_unlock(NFNL_SUBSYS_NFTABLES); } EXPORT_SYMBOL_GPL(nft_unregister_afinfo); @@ -277,11 +277,14 @@ static int nf_tables_dump_tables(struct sk_buff *skb, struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; - list_for_each_entry(afi, &net->nft.af_info, list) { + rcu_read_lock(); + cb->seq = net->nft.base_seq; + + list_for_each_entry_rcu(afi, &net->nft.af_info, list) { if (family != NFPROTO_UNSPEC && family != afi->family) continue; - list_for_each_entry(table, &afi->tables, list) { + list_for_each_entry_rcu(table, &afi->tables, list) { if (idx < s_idx) goto cont; if (idx > s_idx) @@ -294,11 +297,14 @@ static int nf_tables_dump_tables(struct sk_buff *skb, NLM_F_MULTI, afi->family, table) < 0) goto done; + + nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: idx++; } } done: + rcu_read_unlock(); cb->args[0] = idx; return skb->len; } @@ -407,6 +413,9 @@ static int nf_tables_updtable(struct nft_ctx *ctx) if (flags & ~NFT_TABLE_F_DORMANT) return -EINVAL; + if (flags == ctx->table->flags) + return 0; + trans = nft_trans_alloc(ctx, NFT_MSG_NEWTABLE, sizeof(struct nft_trans_table)); if (trans == NULL) @@ -514,7 +523,7 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb, module_put(afi->owner); return err; } - list_add_tail(&table->list, &afi->tables); + list_add_tail_rcu(&table->list, &afi->tables); return 0; } @@ -546,7 +555,7 @@ static int nf_tables_deltable(struct sock *nlsk, struct sk_buff *skb, if (err < 0) return err; - list_del(&table->list); + list_del_rcu(&table->list); return 0; } @@ -635,13 +644,20 @@ static int nft_dump_stats(struct sk_buff *skb, struct nft_stats __percpu *stats) { struct nft_stats *cpu_stats, total; struct nlattr *nest; + unsigned int seq; + u64 pkts, bytes; int cpu; memset(&total, 0, sizeof(total)); for_each_possible_cpu(cpu) { cpu_stats = per_cpu_ptr(stats, cpu); - total.pkts += cpu_stats->pkts; - total.bytes += cpu_stats->bytes; + do { + seq = u64_stats_fetch_begin_irq(&cpu_stats->syncp); + pkts = cpu_stats->pkts; + bytes = cpu_stats->bytes; + } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, seq)); + total.pkts += pkts; + total.bytes += bytes; } nest = nla_nest_start(skb, NFTA_CHAIN_COUNTERS); if (nest == NULL) @@ -761,12 +777,15 @@ static int nf_tables_dump_chains(struct sk_buff *skb, struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; - list_for_each_entry(afi, &net->nft.af_info, list) { + rcu_read_lock(); + cb->seq = net->nft.base_seq; + + list_for_each_entry_rcu(afi, &net->nft.af_info, list) { if (family != NFPROTO_UNSPEC && family != afi->family) continue; - list_for_each_entry(table, &afi->tables, list) { - list_for_each_entry(chain, &table->chains, list) { + list_for_each_entry_rcu(table, &afi->tables, list) { + list_for_each_entry_rcu(chain, &table->chains, list) { if (idx < s_idx) goto cont; if (idx > s_idx) @@ -778,17 +797,19 @@ static int nf_tables_dump_chains(struct sk_buff *skb, NLM_F_MULTI, afi->family, table, chain) < 0) goto done; + + nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: idx++; } } } done: + rcu_read_unlock(); cb->args[0] = idx; return skb->len; } - static int nf_tables_getchain(struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) @@ -861,7 +882,7 @@ static struct nft_stats __percpu *nft_stats_alloc(const struct nlattr *attr) if (!tb[NFTA_COUNTER_BYTES] || !tb[NFTA_COUNTER_PACKETS]) return ERR_PTR(-EINVAL); - newstats = alloc_percpu(struct nft_stats); + newstats = netdev_alloc_pcpu_stats(struct nft_stats); if (newstats == NULL) return ERR_PTR(-ENOMEM); @@ -1077,7 +1098,7 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, } basechain->stats = stats; } else { - stats = alloc_percpu(struct nft_stats); + stats = netdev_alloc_pcpu_stats(struct nft_stats); if (IS_ERR(stats)) { module_put(type->owner); kfree(basechain); @@ -1130,7 +1151,7 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, goto err2; table->use++; - list_add_tail(&chain->list, &table->chains); + list_add_tail_rcu(&chain->list, &table->chains); return 0; err2: if (!(table->flags & NFT_TABLE_F_DORMANT) && @@ -1180,7 +1201,7 @@ static int nf_tables_delchain(struct sock *nlsk, struct sk_buff *skb, return err; table->use--; - list_del(&chain->list); + list_del_rcu(&chain->list); return 0; } @@ -1199,9 +1220,9 @@ int nft_register_expr(struct nft_expr_type *type) { nfnl_lock(NFNL_SUBSYS_NFTABLES); if (type->family == NFPROTO_UNSPEC) - list_add_tail(&type->list, &nf_tables_expressions); + list_add_tail_rcu(&type->list, &nf_tables_expressions); else - list_add(&type->list, &nf_tables_expressions); + list_add_rcu(&type->list, &nf_tables_expressions); nfnl_unlock(NFNL_SUBSYS_NFTABLES); return 0; } @@ -1216,7 +1237,7 @@ EXPORT_SYMBOL_GPL(nft_register_expr); void nft_unregister_expr(struct nft_expr_type *type) { nfnl_lock(NFNL_SUBSYS_NFTABLES); - list_del(&type->list); + list_del_rcu(&type->list); nfnl_unlock(NFNL_SUBSYS_NFTABLES); } EXPORT_SYMBOL_GPL(nft_unregister_expr); @@ -1549,16 +1570,17 @@ static int nf_tables_dump_rules(struct sk_buff *skb, unsigned int idx = 0, s_idx = cb->args[0]; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; - u8 genctr = ACCESS_ONCE(net->nft.genctr); - u8 gencursor = ACCESS_ONCE(net->nft.gencursor); - list_for_each_entry(afi, &net->nft.af_info, list) { + rcu_read_lock(); + cb->seq = net->nft.base_seq; + + list_for_each_entry_rcu(afi, &net->nft.af_info, list) { if (family != NFPROTO_UNSPEC && family != afi->family) continue; - list_for_each_entry(table, &afi->tables, list) { - list_for_each_entry(chain, &table->chains, list) { - list_for_each_entry(rule, &chain->rules, list) { + list_for_each_entry_rcu(table, &afi->tables, list) { + list_for_each_entry_rcu(chain, &table->chains, list) { + list_for_each_entry_rcu(rule, &chain->rules, list) { if (!nft_rule_is_active(net, rule)) goto cont; if (idx < s_idx) @@ -1572,6 +1594,8 @@ static int nf_tables_dump_rules(struct sk_buff *skb, NLM_F_MULTI | NLM_F_APPEND, afi->family, table, chain, rule) < 0) goto done; + + nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: idx++; } @@ -1579,9 +1603,7 @@ cont: } } done: - /* Invalidate this dump, a transition to the new generation happened */ - if (gencursor != net->nft.gencursor || genctr != net->nft.genctr) - return -EBUSY; + rcu_read_unlock(); cb->args[0] = idx; return skb->len; @@ -1932,7 +1954,7 @@ static LIST_HEAD(nf_tables_set_ops); int nft_register_set(struct nft_set_ops *ops) { nfnl_lock(NFNL_SUBSYS_NFTABLES); - list_add_tail(&ops->list, &nf_tables_set_ops); + list_add_tail_rcu(&ops->list, &nf_tables_set_ops); nfnl_unlock(NFNL_SUBSYS_NFTABLES); return 0; } @@ -1941,7 +1963,7 @@ EXPORT_SYMBOL_GPL(nft_register_set); void nft_unregister_set(struct nft_set_ops *ops) { nfnl_lock(NFNL_SUBSYS_NFTABLES); - list_del(&ops->list); + list_del_rcu(&ops->list); nfnl_unlock(NFNL_SUBSYS_NFTABLES); } EXPORT_SYMBOL_GPL(nft_unregister_set); @@ -2234,7 +2256,10 @@ static int nf_tables_dump_sets_table(struct nft_ctx *ctx, struct sk_buff *skb, if (cb->args[1]) return skb->len; - list_for_each_entry(set, &ctx->table->sets, list) { + rcu_read_lock(); + cb->seq = ctx->net->nft.base_seq; + + list_for_each_entry_rcu(set, &ctx->table->sets, list) { if (idx < s_idx) goto cont; if (nf_tables_fill_set(skb, ctx, set, NFT_MSG_NEWSET, @@ -2242,11 +2267,13 @@ static int nf_tables_dump_sets_table(struct nft_ctx *ctx, struct sk_buff *skb, cb->args[0] = idx; goto done; } + nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: idx++; } cb->args[1] = 1; done: + rcu_read_unlock(); return skb->len; } @@ -2260,7 +2287,10 @@ static int nf_tables_dump_sets_family(struct nft_ctx *ctx, struct sk_buff *skb, if (cb->args[1]) return skb->len; - list_for_each_entry(table, &ctx->afi->tables, list) { + rcu_read_lock(); + cb->seq = ctx->net->nft.base_seq; + + list_for_each_entry_rcu(table, &ctx->afi->tables, list) { if (cur_table) { if (cur_table != table) continue; @@ -2269,7 +2299,7 @@ static int nf_tables_dump_sets_family(struct nft_ctx *ctx, struct sk_buff *skb, } ctx->table = table; idx = 0; - list_for_each_entry(set, &ctx->table->sets, list) { + list_for_each_entry_rcu(set, &ctx->table->sets, list) { if (idx < s_idx) goto cont; if (nf_tables_fill_set(skb, ctx, set, NFT_MSG_NEWSET, @@ -2278,12 +2308,14 @@ static int nf_tables_dump_sets_family(struct nft_ctx *ctx, struct sk_buff *skb, cb->args[2] = (unsigned long) table; goto done; } + nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: idx++; } } cb->args[1] = 1; done: + rcu_read_unlock(); return skb->len; } @@ -2300,7 +2332,10 @@ static int nf_tables_dump_sets_all(struct nft_ctx *ctx, struct sk_buff *skb, if (cb->args[1]) return skb->len; - list_for_each_entry(afi, &net->nft.af_info, list) { + rcu_read_lock(); + cb->seq = net->nft.base_seq; + + list_for_each_entry_rcu(afi, &net->nft.af_info, list) { if (cur_family) { if (afi->family != cur_family) continue; @@ -2308,7 +2343,7 @@ static int nf_tables_dump_sets_all(struct nft_ctx *ctx, struct sk_buff *skb, cur_family = 0; } - list_for_each_entry(table, &afi->tables, list) { + list_for_each_entry_rcu(table, &afi->tables, list) { if (cur_table) { if (cur_table != table) continue; @@ -2319,7 +2354,7 @@ static int nf_tables_dump_sets_all(struct nft_ctx *ctx, struct sk_buff *skb, ctx->table = table; ctx->afi = afi; idx = 0; - list_for_each_entry(set, &ctx->table->sets, list) { + list_for_each_entry_rcu(set, &ctx->table->sets, list) { if (idx < s_idx) goto cont; if (nf_tables_fill_set(skb, ctx, set, @@ -2330,6 +2365,7 @@ static int nf_tables_dump_sets_all(struct nft_ctx *ctx, struct sk_buff *skb, cb->args[3] = afi->family; goto done; } + nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: idx++; } @@ -2339,6 +2375,7 @@ cont: } cb->args[1] = 1; done: + rcu_read_unlock(); return skb->len; } @@ -2597,7 +2634,7 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb, if (err < 0) goto err2; - list_add_tail(&set->list, &table->sets); + list_add_tail_rcu(&set->list, &table->sets); table->use++; return 0; @@ -2617,7 +2654,7 @@ static void nft_set_destroy(struct nft_set *set) static void nf_tables_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) { - list_del(&set->list); + list_del_rcu(&set->list); nf_tables_set_notify(ctx, set, NFT_MSG_DELSET, GFP_ATOMIC); nft_set_destroy(set); } @@ -2652,7 +2689,7 @@ static int nf_tables_delset(struct sock *nlsk, struct sk_buff *skb, if (err < 0) return err; - list_del(&set->list); + list_del_rcu(&set->list); ctx.table->use--; return 0; } @@ -2704,14 +2741,14 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, } bind: binding->chain = ctx->chain; - list_add_tail(&binding->list, &set->bindings); + list_add_tail_rcu(&binding->list, &set->bindings); return 0; } void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding) { - list_del(&binding->list); + list_del_rcu(&binding->list); if (list_empty(&set->bindings) && set->flags & NFT_SET_ANONYMOUS && !(set->flags & NFT_SET_INACTIVE)) @@ -3346,7 +3383,7 @@ static int nf_tables_commit(struct sk_buff *skb) struct nft_set *set; /* Bump generation counter, invalidate any dump in progress */ - net->nft.genctr++; + while (++net->nft.base_seq == 0); /* A new generation has just started */ net->nft.gencursor = gencursor_next(net); @@ -3491,12 +3528,12 @@ static int nf_tables_abort(struct sk_buff *skb) } nft_trans_destroy(trans); } else { - list_del(&trans->ctx.table->list); + list_del_rcu(&trans->ctx.table->list); } break; case NFT_MSG_DELTABLE: - list_add_tail(&trans->ctx.table->list, - &trans->ctx.afi->tables); + list_add_tail_rcu(&trans->ctx.table->list, + &trans->ctx.afi->tables); nft_trans_destroy(trans); break; case NFT_MSG_NEWCHAIN: @@ -3507,7 +3544,7 @@ static int nf_tables_abort(struct sk_buff *skb) nft_trans_destroy(trans); } else { trans->ctx.table->use--; - list_del(&trans->ctx.chain->list); + list_del_rcu(&trans->ctx.chain->list); if (!(trans->ctx.table->flags & NFT_TABLE_F_DORMANT) && trans->ctx.chain->flags & NFT_BASE_CHAIN) { nf_unregister_hooks(nft_base_chain(trans->ctx.chain)->ops, @@ -3517,8 +3554,8 @@ static int nf_tables_abort(struct sk_buff *skb) break; case NFT_MSG_DELCHAIN: trans->ctx.table->use++; - list_add_tail(&trans->ctx.chain->list, - &trans->ctx.table->chains); + list_add_tail_rcu(&trans->ctx.chain->list, + &trans->ctx.table->chains); nft_trans_destroy(trans); break; case NFT_MSG_NEWRULE: @@ -3532,12 +3569,12 @@ static int nf_tables_abort(struct sk_buff *skb) break; case NFT_MSG_NEWSET: trans->ctx.table->use--; - list_del(&nft_trans_set(trans)->list); + list_del_rcu(&nft_trans_set(trans)->list); break; case NFT_MSG_DELSET: trans->ctx.table->use++; - list_add_tail(&nft_trans_set(trans)->list, - &trans->ctx.table->sets); + list_add_tail_rcu(&nft_trans_set(trans)->list, + &trans->ctx.table->sets); nft_trans_destroy(trans); break; case NFT_MSG_NEWSETELEM: @@ -3951,6 +3988,7 @@ static int nf_tables_init_net(struct net *net) { INIT_LIST_HEAD(&net->nft.af_info); INIT_LIST_HEAD(&net->nft.commit_list); + net->nft.base_seq = 1; return 0; } diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 345acfb1720..3b90eb2b2c5 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -109,7 +109,7 @@ nft_do_chain(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops) struct nft_data data[NFT_REG_MAX + 1]; unsigned int stackptr = 0; struct nft_jumpstack jumpstack[NFT_JUMP_STACK_SIZE]; - struct nft_stats __percpu *stats; + struct nft_stats *stats; int rulenum; /* * Cache cursor to avoid problems in case that the cursor is updated @@ -205,9 +205,11 @@ next_rule: nft_trace_packet(pkt, basechain, -1, NFT_TRACE_POLICY); rcu_read_lock_bh(); - stats = rcu_dereference(nft_base_chain(basechain)->stats); - __this_cpu_inc(stats->pkts); - __this_cpu_add(stats->bytes, pkt->skb->len); + stats = this_cpu_ptr(rcu_dereference(nft_base_chain(basechain)->stats)); + u64_stats_update_begin(&stats->syncp); + stats->pkts++; + stats->bytes += pkt->skb->len; + u64_stats_update_end(&stats->syncp); rcu_read_unlock_bh(); return nft_base_chain(basechain)->policy; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index c39b583ace3..70c0be8d012 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -38,6 +38,7 @@ #include <linux/errno.h> #include <linux/rtnetlink.h> #include <linux/skbuff.h> +#include <linux/bitmap.h> #include <net/netlink.h> #include <net/act_api.h> #include <net/pkt_cls.h> @@ -460,17 +461,25 @@ static int u32_delete(struct tcf_proto *tp, unsigned long arg) return 0; } +#define NR_U32_NODE (1<<12) static u32 gen_new_kid(struct tc_u_hnode *ht, u32 handle) { struct tc_u_knode *n; - unsigned int i = 0x7FF; + unsigned long i; + unsigned long *bitmap = kzalloc(BITS_TO_LONGS(NR_U32_NODE) * sizeof(unsigned long), + GFP_KERNEL); + if (!bitmap) + return handle | 0xFFF; for (n = ht->ht[TC_U32_HASH(handle)]; n; n = n->next) - if (i < TC_U32_NODE(n->handle)) - i = TC_U32_NODE(n->handle); - i++; + set_bit(TC_U32_NODE(n->handle), bitmap); - return handle | (i > 0xFFF ? 0xFFF : i); + i = find_next_zero_bit(bitmap, NR_U32_NODE, 0x800); + if (i >= NR_U32_NODE) + i = find_next_zero_bit(bitmap, NR_U32_NODE, 1); + + kfree(bitmap); + return handle | (i >= NR_U32_NODE ? 0xFFF : i); } static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = { diff --git a/tools/lib/lockdep/include/liblockdep/mutex.h b/tools/lib/lockdep/include/liblockdep/mutex.h index c342f708714..ee53a42818c 100644 --- a/tools/lib/lockdep/include/liblockdep/mutex.h +++ b/tools/lib/lockdep/include/liblockdep/mutex.h @@ -35,7 +35,7 @@ static inline int __mutex_init(liblockdep_pthread_mutex_t *lock, static inline int liblockdep_pthread_mutex_lock(liblockdep_pthread_mutex_t *lock) { - lock_acquire(&lock->dep_map, 0, 0, 0, 2, NULL, (unsigned long)_RET_IP_); + lock_acquire(&lock->dep_map, 0, 0, 0, 1, NULL, (unsigned long)_RET_IP_); return pthread_mutex_lock(&lock->mutex); } @@ -47,7 +47,7 @@ static inline int liblockdep_pthread_mutex_unlock(liblockdep_pthread_mutex_t *lo static inline int liblockdep_pthread_mutex_trylock(liblockdep_pthread_mutex_t *lock) { - lock_acquire(&lock->dep_map, 0, 1, 0, 2, NULL, (unsigned long)_RET_IP_); + lock_acquire(&lock->dep_map, 0, 1, 0, 1, NULL, (unsigned long)_RET_IP_); return pthread_mutex_trylock(&lock->mutex) == 0 ? 1 : 0; } diff --git a/tools/lib/lockdep/include/liblockdep/rwlock.h b/tools/lib/lockdep/include/liblockdep/rwlock.h index a680ab8c2e3..4ec03f86155 100644 --- a/tools/lib/lockdep/include/liblockdep/rwlock.h +++ b/tools/lib/lockdep/include/liblockdep/rwlock.h @@ -36,7 +36,7 @@ static inline int __rwlock_init(liblockdep_pthread_rwlock_t *lock, static inline int liblockdep_pthread_rwlock_rdlock(liblockdep_pthread_rwlock_t *lock) { - lock_acquire(&lock->dep_map, 0, 0, 2, 2, NULL, (unsigned long)_RET_IP_); + lock_acquire(&lock->dep_map, 0, 0, 2, 1, NULL, (unsigned long)_RET_IP_); return pthread_rwlock_rdlock(&lock->rwlock); } @@ -49,19 +49,19 @@ static inline int liblockdep_pthread_rwlock_unlock(liblockdep_pthread_rwlock_t * static inline int liblockdep_pthread_rwlock_wrlock(liblockdep_pthread_rwlock_t *lock) { - lock_acquire(&lock->dep_map, 0, 0, 0, 2, NULL, (unsigned long)_RET_IP_); + lock_acquire(&lock->dep_map, 0, 0, 0, 1, NULL, (unsigned long)_RET_IP_); return pthread_rwlock_wrlock(&lock->rwlock); } static inline int liblockdep_pthread_rwlock_tryrdlock(liblockdep_pthread_rwlock_t *lock) { - lock_acquire(&lock->dep_map, 0, 1, 2, 2, NULL, (unsigned long)_RET_IP_); + lock_acquire(&lock->dep_map, 0, 1, 2, 1, NULL, (unsigned long)_RET_IP_); return pthread_rwlock_tryrdlock(&lock->rwlock) == 0 ? 1 : 0; } static inline int liblockdep_pthread_rwlock_trywlock(liblockdep_pthread_rwlock_t *lock) { - lock_acquire(&lock->dep_map, 0, 1, 0, 2, NULL, (unsigned long)_RET_IP_); + lock_acquire(&lock->dep_map, 0, 1, 0, 1, NULL, (unsigned long)_RET_IP_); return pthread_rwlock_trywlock(&lock->rwlock) == 0 ? 1 : 0; } diff --git a/tools/lib/lockdep/preload.c b/tools/lib/lockdep/preload.c index 23bd69cb5ad..6f803609e49 100644 --- a/tools/lib/lockdep/preload.c +++ b/tools/lib/lockdep/preload.c @@ -92,7 +92,7 @@ enum { none, prepare, done, } __init_state; static void init_preload(void); static void try_init_preload(void) { - if (!__init_state != done) + if (__init_state != done) init_preload(); } @@ -252,7 +252,7 @@ int pthread_mutex_lock(pthread_mutex_t *mutex) try_init_preload(); - lock_acquire(&__get_lock(mutex)->dep_map, 0, 0, 0, 2, NULL, + lock_acquire(&__get_lock(mutex)->dep_map, 0, 0, 0, 1, NULL, (unsigned long)_RET_IP_); /* * Here's the thing with pthread mutexes: unlike the kernel variant, @@ -281,7 +281,7 @@ int pthread_mutex_trylock(pthread_mutex_t *mutex) try_init_preload(); - lock_acquire(&__get_lock(mutex)->dep_map, 0, 1, 0, 2, NULL, (unsigned long)_RET_IP_); + lock_acquire(&__get_lock(mutex)->dep_map, 0, 1, 0, 1, NULL, (unsigned long)_RET_IP_); r = ll_pthread_mutex_trylock(mutex); if (r) lock_release(&__get_lock(mutex)->dep_map, 0, (unsigned long)_RET_IP_); @@ -303,7 +303,7 @@ int pthread_mutex_unlock(pthread_mutex_t *mutex) */ r = ll_pthread_mutex_unlock(mutex); if (r) - lock_acquire(&__get_lock(mutex)->dep_map, 0, 0, 0, 2, NULL, (unsigned long)_RET_IP_); + lock_acquire(&__get_lock(mutex)->dep_map, 0, 0, 0, 1, NULL, (unsigned long)_RET_IP_); return r; } @@ -352,7 +352,7 @@ int pthread_rwlock_rdlock(pthread_rwlock_t *rwlock) init_preload(); - lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 2, 2, NULL, (unsigned long)_RET_IP_); + lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 2, 1, NULL, (unsigned long)_RET_IP_); r = ll_pthread_rwlock_rdlock(rwlock); if (r) lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_); @@ -366,7 +366,7 @@ int pthread_rwlock_tryrdlock(pthread_rwlock_t *rwlock) init_preload(); - lock_acquire(&__get_lock(rwlock)->dep_map, 0, 1, 2, 2, NULL, (unsigned long)_RET_IP_); + lock_acquire(&__get_lock(rwlock)->dep_map, 0, 1, 2, 1, NULL, (unsigned long)_RET_IP_); r = ll_pthread_rwlock_tryrdlock(rwlock); if (r) lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_); @@ -380,7 +380,7 @@ int pthread_rwlock_trywrlock(pthread_rwlock_t *rwlock) init_preload(); - lock_acquire(&__get_lock(rwlock)->dep_map, 0, 1, 0, 2, NULL, (unsigned long)_RET_IP_); + lock_acquire(&__get_lock(rwlock)->dep_map, 0, 1, 0, 1, NULL, (unsigned long)_RET_IP_); r = ll_pthread_rwlock_trywrlock(rwlock); if (r) lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_); @@ -394,7 +394,7 @@ int pthread_rwlock_wrlock(pthread_rwlock_t *rwlock) init_preload(); - lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 0, 2, NULL, (unsigned long)_RET_IP_); + lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 0, 1, NULL, (unsigned long)_RET_IP_); r = ll_pthread_rwlock_wrlock(rwlock); if (r) lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_); @@ -411,7 +411,7 @@ int pthread_rwlock_unlock(pthread_rwlock_t *rwlock) lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_); r = ll_pthread_rwlock_unlock(rwlock); if (r) - lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 0, 2, NULL, (unsigned long)_RET_IP_); + lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 0, 1, NULL, (unsigned long)_RET_IP_); return r; } @@ -439,8 +439,6 @@ __attribute__((constructor)) static void init_preload(void) ll_pthread_rwlock_unlock = dlsym(RTLD_NEXT, "pthread_rwlock_unlock"); #endif - printf("%p\n", ll_pthread_mutex_trylock);fflush(stdout); - lockdep_init(); __init_state = done; |