diff options
157 files changed, 1929 insertions, 2051 deletions
@@ -17,6 +17,7 @@ Aleksey Gorelov <aleksey_gorelov@phoenix.com> Al Viro <viro@ftp.linux.org.uk> Al Viro <viro@zenIV.linux.org.uk> Andreas Herrmann <aherrman@de.ibm.com> +Andrey Ryabinin <ryabinin.a.a@gmail.com> <a.ryabinin@samsung.com> Andrew Morton <akpm@linux-foundation.org> Andrew Vasquez <andrew.vasquez@qlogic.com> Andy Adamson <andros@citi.umich.edu> diff --git a/Documentation/devicetree/bindings/arm/cpus.txt b/Documentation/devicetree/bindings/arm/cpus.txt index d6b794cef0b8..91e6e5c478d0 100644 --- a/Documentation/devicetree/bindings/arm/cpus.txt +++ b/Documentation/devicetree/bindings/arm/cpus.txt @@ -199,6 +199,7 @@ nodes to be present and contain the properties described below. "qcom,kpss-acc-v1" "qcom,kpss-acc-v2" "rockchip,rk3066-smp" + "ste,dbx500-smp" - cpu-release-addr Usage: required for systems that have an "enable-method" diff --git a/MAINTAINERS b/MAINTAINERS index a9ae6c105520..569568f6644f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3587,6 +3587,15 @@ S: Maintained F: drivers/gpu/drm/rockchip/ F: Documentation/devicetree/bindings/video/rockchip* +DRM DRIVERS FOR STI +M: Benjamin Gaignard <benjamin.gaignard@linaro.org> +M: Vincent Abriou <vincent.abriou@st.com> +L: dri-devel@lists.freedesktop.org +T: git http://git.linaro.org/people/benjamin.gaignard/kernel.git +S: Maintained +F: drivers/gpu/drm/sti +F: Documentation/devicetree/bindings/gpu/st,stih4xx.txt + DSBR100 USB FM RADIO DRIVER M: Alexey Klimov <klimov.linux@gmail.com> L: linux-media@vger.kernel.org @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 2 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = -rc7 NAME = Hurr durr I'ma sheep # *DOCUMENTATION* diff --git a/arch/Kconfig b/arch/Kconfig index 8a8ea7110de8..8f3638674e05 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -87,7 +87,6 @@ config KPROBES_ON_FTRACE config UPROBES def_bool n - select PERCPU_RWSEM help Uprobes is the user-space counterpart to kprobes: they enable instrumentation applications (such as 'perf probe') diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi index 4a0718ccf68e..1e29ccf77ea2 100644 --- a/arch/arm/boot/dts/dra7.dtsi +++ b/arch/arm/boot/dts/dra7.dtsi @@ -116,7 +116,7 @@ ranges = <0 0x2000 0x2000>; scm_conf: scm_conf@0 { - compatible = "syscon"; + compatible = "syscon", "simple-bus"; reg = <0x0 0x1400>; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/imx6qdl.dtsi b/arch/arm/boot/dts/imx6qdl.dtsi index e6d13592080d..b57033e8c633 100644 --- a/arch/arm/boot/dts/imx6qdl.dtsi +++ b/arch/arm/boot/dts/imx6qdl.dtsi @@ -181,10 +181,10 @@ interrupt-names = "msi"; #interrupt-cells = <1>; interrupt-map-mask = <0 0 0 0x7>; - interrupt-map = <0 0 0 1 &intc GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>, - <0 0 0 2 &intc GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>, - <0 0 0 3 &intc GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>, - <0 0 0 4 &intc GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>; + interrupt-map = <0 0 0 1 &gpc GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 2 &gpc GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 3 &gpc GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 4 &gpc GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX6QDL_CLK_PCIE_AXI>, <&clks IMX6QDL_CLK_LVDS1_GATE>, <&clks IMX6QDL_CLK_PCIE_REF_125M>; diff --git a/arch/arm/boot/dts/k2e.dtsi b/arch/arm/boot/dts/k2e.dtsi index 1b6494fbdb91..675fb8e492c6 100644 --- a/arch/arm/boot/dts/k2e.dtsi +++ b/arch/arm/boot/dts/k2e.dtsi @@ -131,10 +131,17 @@ <GIC_SPI 376 IRQ_TYPE_EDGE_RISING>; }; }; + + mdio: mdio@24200f00 { + compatible = "ti,keystone_mdio", "ti,davinci_mdio"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x24200f00 0x100>; + status = "disabled"; + clocks = <&clkcpgmac>; + clock-names = "fck"; + bus_freq = <2500000>; + }; /include/ "k2e-netcp.dtsi" }; }; - -&mdio { - reg = <0x24200f00 0x100>; -}; diff --git a/arch/arm/boot/dts/k2hk.dtsi b/arch/arm/boot/dts/k2hk.dtsi index ae6472407b22..d0810a5f2968 100644 --- a/arch/arm/boot/dts/k2hk.dtsi +++ b/arch/arm/boot/dts/k2hk.dtsi @@ -98,6 +98,17 @@ #gpio-cells = <2>; gpio,syscon-dev = <&devctrl 0x25c>; }; + + mdio: mdio@02090300 { + compatible = "ti,keystone_mdio", "ti,davinci_mdio"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x02090300 0x100>; + status = "disabled"; + clocks = <&clkcpgmac>; + clock-names = "fck"; + bus_freq = <2500000>; + }; /include/ "k2hk-netcp.dtsi" }; }; diff --git a/arch/arm/boot/dts/k2l.dtsi b/arch/arm/boot/dts/k2l.dtsi index 0e007483615e..49fd414f680c 100644 --- a/arch/arm/boot/dts/k2l.dtsi +++ b/arch/arm/boot/dts/k2l.dtsi @@ -29,7 +29,6 @@ }; soc { - /include/ "k2l-clocks.dtsi" uart2: serial@02348400 { @@ -79,6 +78,17 @@ #gpio-cells = <2>; gpio,syscon-dev = <&devctrl 0x24c>; }; + + mdio: mdio@26200f00 { + compatible = "ti,keystone_mdio", "ti,davinci_mdio"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x26200f00 0x100>; + status = "disabled"; + clocks = <&clkcpgmac>; + clock-names = "fck"; + bus_freq = <2500000>; + }; /include/ "k2l-netcp.dtsi" }; }; @@ -96,7 +106,3 @@ /* Pin muxed. Enabled and configured by Bootloader */ status = "disabled"; }; - -&mdio { - reg = <0x26200f00 0x100>; -}; diff --git a/arch/arm/boot/dts/keystone.dtsi b/arch/arm/boot/dts/keystone.dtsi index e7a6f6deabb6..72816d65f7ec 100644 --- a/arch/arm/boot/dts/keystone.dtsi +++ b/arch/arm/boot/dts/keystone.dtsi @@ -267,17 +267,6 @@ 1 0 0x21000A00 0x00000100>; }; - mdio: mdio@02090300 { - compatible = "ti,keystone_mdio", "ti,davinci_mdio"; - #address-cells = <1>; - #size-cells = <0>; - reg = <0x02090300 0x100>; - status = "disabled"; - clocks = <&clkpa>; - clock-names = "fck"; - bus_freq = <2500000>; - }; - kirq0: keystone_irq@26202a0 { compatible = "ti,keystone-irq"; interrupts = <GIC_SPI 4 IRQ_TYPE_EDGE_RISING>; diff --git a/arch/arm/boot/dts/omap2430.dtsi b/arch/arm/boot/dts/omap2430.dtsi index 11a7963be003..2390f387c271 100644 --- a/arch/arm/boot/dts/omap2430.dtsi +++ b/arch/arm/boot/dts/omap2430.dtsi @@ -51,7 +51,8 @@ }; scm_conf: scm_conf@270 { - compatible = "syscon"; + compatible = "syscon", + "simple-bus"; reg = <0x270 0x240>; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/omap4.dtsi b/arch/arm/boot/dts/omap4.dtsi index 7d31c6ff246f..abc4473e6f8a 100644 --- a/arch/arm/boot/dts/omap4.dtsi +++ b/arch/arm/boot/dts/omap4.dtsi @@ -191,7 +191,8 @@ }; omap4_padconf_global: omap4_padconf_global@5a0 { - compatible = "syscon"; + compatible = "syscon", + "simple-bus"; reg = <0x5a0 0x170>; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi index c8fd648a7108..b1a1263e6001 100644 --- a/arch/arm/boot/dts/omap5.dtsi +++ b/arch/arm/boot/dts/omap5.dtsi @@ -180,7 +180,8 @@ }; omap5_padconf_global: omap5_padconf_global@5a0 { - compatible = "syscon"; + compatible = "syscon", + "simple-bus"; reg = <0x5a0 0xec>; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/ste-dbx5x0.dtsi b/arch/arm/boot/dts/ste-dbx5x0.dtsi index a75f3289e653..b8f81fb418ce 100644 --- a/arch/arm/boot/dts/ste-dbx5x0.dtsi +++ b/arch/arm/boot/dts/ste-dbx5x0.dtsi @@ -15,6 +15,33 @@ #include "skeleton.dtsi" / { + cpus { + #address-cells = <1>; + #size-cells = <0>; + enable-method = "ste,dbx500-smp"; + + cpu-map { + cluster0 { + core0 { + cpu = <&CPU0>; + }; + core1 { + cpu = <&CPU1>; + }; + }; + }; + CPU0: cpu@300 { + device_type = "cpu"; + compatible = "arm,cortex-a9"; + reg = <0x300>; + }; + CPU1: cpu@301 { + device_type = "cpu"; + compatible = "arm,cortex-a9"; + reg = <0x301>; + }; + }; + soc { #address-cells = <1>; #size-cells = <1>; @@ -22,32 +49,6 @@ interrupt-parent = <&intc>; ranges; - cpus { - #address-cells = <1>; - #size-cells = <0>; - - cpu-map { - cluster0 { - core0 { - cpu = <&CPU0>; - }; - core1 { - cpu = <&CPU1>; - }; - }; - }; - CPU0: cpu@0 { - device_type = "cpu"; - compatible = "arm,cortex-a9"; - reg = <0>; - }; - CPU1: cpu@1 { - device_type = "cpu"; - compatible = "arm,cortex-a9"; - reg = <1>; - }; - }; - ptm@801ae000 { compatible = "arm,coresight-etm3x", "arm,primecell"; reg = <0x801ae000 0x1000>; diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index 92828a1dec80..b48dd4f37f80 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -61,6 +61,7 @@ work_pending: movlt scno, #(__NR_restart_syscall - __NR_SYSCALL_BASE) ldmia sp, {r0 - r6} @ have to reload r0 - r6 b local_restart @ ... and off we go +ENDPROC(ret_fast_syscall) /* * "slow" syscall return path. "why" tells us if this was a real syscall. diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index bd755d97e459..29e2991465cb 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -399,6 +399,9 @@ ENTRY(secondary_startup) sub lr, r4, r5 @ mmu has been enabled add r3, r7, lr ldrd r4, [r3, #0] @ get secondary_data.pgdir +ARM_BE8(eor r4, r4, r5) @ Swap r5 and r4 in BE: +ARM_BE8(eor r5, r4, r5) @ it can be done in 3 steps +ARM_BE8(eor r4, r4, r5) @ without using a temp reg. ldr r8, [r3, #8] @ get secondary_data.swapper_pg_dir badr lr, __enable_mmu @ return address mov r13, r12 @ __secondary_switched address diff --git a/arch/arm/kernel/vdso.c b/arch/arm/kernel/vdso.c index efe17dd9b921..54a5aeab988d 100644 --- a/arch/arm/kernel/vdso.c +++ b/arch/arm/kernel/vdso.c @@ -296,7 +296,6 @@ static bool tk_is_cntvct(const struct timekeeper *tk) */ void update_vsyscall(struct timekeeper *tk) { - struct timespec xtime_coarse; struct timespec64 *wtm = &tk->wall_to_monotonic; if (!cntvct_ok) { @@ -308,10 +307,10 @@ void update_vsyscall(struct timekeeper *tk) vdso_write_begin(vdso_data); - xtime_coarse = __current_kernel_time(); vdso_data->tk_is_cntvct = tk_is_cntvct(tk); - vdso_data->xtime_coarse_sec = xtime_coarse.tv_sec; - vdso_data->xtime_coarse_nsec = xtime_coarse.tv_nsec; + vdso_data->xtime_coarse_sec = tk->xtime_sec; + vdso_data->xtime_coarse_nsec = (u32)(tk->tkr_mono.xtime_nsec >> + tk->tkr_mono.shift); vdso_data->wtm_clock_sec = wtm->tv_sec; vdso_data->wtm_clock_nsec = wtm->tv_nsec; diff --git a/arch/arm/mach-exynos/pm_domains.c b/arch/arm/mach-exynos/pm_domains.c index 6001f1c9d136..4a87e86dec45 100644 --- a/arch/arm/mach-exynos/pm_domains.c +++ b/arch/arm/mach-exynos/pm_domains.c @@ -146,9 +146,8 @@ static __init int exynos4_pm_init_power_domain(void) pd->base = of_iomap(np, 0); if (!pd->base) { pr_warn("%s: failed to map memory\n", __func__); - kfree(pd->pd.name); + kfree_const(pd->pd.name); kfree(pd); - of_node_put(np); continue; } diff --git a/arch/arm/vdso/Makefile b/arch/arm/vdso/Makefile index 9d259d94e429..1160434eece0 100644 --- a/arch/arm/vdso/Makefile +++ b/arch/arm/vdso/Makefile @@ -14,7 +14,7 @@ VDSO_LDFLAGS += -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096 VDSO_LDFLAGS += -nostdlib -shared VDSO_LDFLAGS += $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) VDSO_LDFLAGS += $(call cc-ldoption, -Wl$(comma)--build-id) -VDSO_LDFLAGS += $(call cc-option, -fuse-ld=bfd) +VDSO_LDFLAGS += $(call cc-ldoption, -fuse-ld=bfd) obj-$(CONFIG_VDSO) += vdso.o extra-$(CONFIG_VDSO) += vdso.lds diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index ec37ab3f524f..97bc68f4c689 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -199,16 +199,15 @@ up_fail: */ void update_vsyscall(struct timekeeper *tk) { - struct timespec xtime_coarse; u32 use_syscall = strcmp(tk->tkr_mono.clock->name, "arch_sys_counter"); ++vdso_data->tb_seq_count; smp_wmb(); - xtime_coarse = __current_kernel_time(); vdso_data->use_syscall = use_syscall; - vdso_data->xtime_coarse_sec = xtime_coarse.tv_sec; - vdso_data->xtime_coarse_nsec = xtime_coarse.tv_nsec; + vdso_data->xtime_coarse_sec = tk->xtime_sec; + vdso_data->xtime_coarse_nsec = tk->tkr_mono.xtime_nsec >> + tk->tkr_mono.shift; vdso_data->wtm_clock_sec = tk->wall_to_monotonic.tv_sec; vdso_data->wtm_clock_nsec = tk->wall_to_monotonic.tv_nsec; diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S index ad4d44635c76..a6f6b762c47a 100644 --- a/arch/mips/kernel/scall64-64.S +++ b/arch/mips/kernel/scall64-64.S @@ -80,7 +80,7 @@ syscall_trace_entry: SAVE_STATIC move s0, t2 move a0, sp - daddiu a1, v0, __NR_64_Linux + move a1, v0 jal syscall_trace_enter bltz v0, 2f # seccomp failed? Skip syscall diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index 446cc654da56..4b2010654c46 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -72,7 +72,7 @@ n32_syscall_trace_entry: SAVE_STATIC move s0, t2 move a0, sp - daddiu a1, v0, __NR_N32_Linux + move a1, v0 jal syscall_trace_enter bltz v0, 2f # seccomp failed? Skip syscall diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 5a1844765a7a..a7e257d9cb90 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -140,6 +140,7 @@ sysexit_from_sys_call: */ andl $~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS) movl RIP(%rsp), %ecx /* User %eip */ + movq RAX(%rsp), %rax RESTORE_RSI_RDI xorl %edx, %edx /* Do not leak kernel information */ xorq %r8, %r8 @@ -219,7 +220,6 @@ sysexit_from_sys_call: 1: setbe %al /* 1 if error, 0 if not */ movzbl %al, %edi /* zero-extend that into %edi */ call __audit_syscall_exit - movq RAX(%rsp), %rax /* reload syscall return value */ movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %edi DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF @@ -368,6 +368,7 @@ sysretl_from_sys_call: RESTORE_RSI_RDI_RDX movl RIP(%rsp), %ecx movl EFLAGS(%rsp), %r11d + movq RAX(%rsp), %rax xorq %r10, %r10 xorq %r9, %r9 xorq %r8, %r8 diff --git a/arch/x86/include/asm/sigcontext.h b/arch/x86/include/asm/sigcontext.h index 6fe6b182c998..9dfce4e0417d 100644 --- a/arch/x86/include/asm/sigcontext.h +++ b/arch/x86/include/asm/sigcontext.h @@ -57,9 +57,9 @@ struct sigcontext { unsigned long ip; unsigned long flags; unsigned short cs; - unsigned short __pad2; /* Was called gs, but was always zero. */ - unsigned short __pad1; /* Was called fs, but was always zero. */ - unsigned short ss; + unsigned short gs; + unsigned short fs; + unsigned short __pad0; unsigned long err; unsigned long trapno; unsigned long oldmask; diff --git a/arch/x86/include/uapi/asm/sigcontext.h b/arch/x86/include/uapi/asm/sigcontext.h index 0e8a973de9ee..40836a9a7250 100644 --- a/arch/x86/include/uapi/asm/sigcontext.h +++ b/arch/x86/include/uapi/asm/sigcontext.h @@ -177,24 +177,9 @@ struct sigcontext { __u64 rip; __u64 eflags; /* RFLAGS */ __u16 cs; - - /* - * Prior to 2.5.64 ("[PATCH] x86-64 updates for 2.5.64-bk3"), - * Linux saved and restored fs and gs in these slots. This - * was counterproductive, as fsbase and gsbase were never - * saved, so arch_prctl was presumably unreliable. - * - * If these slots are ever needed for any other purpose, there - * is some risk that very old 64-bit binaries could get - * confused. I doubt that many such binaries still work, - * though, since the same patch in 2.5.64 also removed the - * 64-bit set_thread_area syscall, so it appears that there is - * no TLS API that works in both pre- and post-2.5.64 kernels. - */ - __u16 __pad2; /* Was gs. */ - __u16 __pad1; /* Was fs. */ - - __u16 ss; + __u16 gs; + __u16 fs; + __u16 __pad0; __u64 err; __u64 trapno; __u64 oldmask; diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index b9826a981fb2..6326ae24e4d5 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -2534,7 +2534,7 @@ static int intel_pmu_cpu_prepare(int cpu) if (x86_pmu.extra_regs || x86_pmu.lbr_sel_map) { cpuc->shared_regs = allocate_shared_regs(cpu); if (!cpuc->shared_regs) - return NOTIFY_BAD; + goto err; } if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) { @@ -2542,18 +2542,27 @@ static int intel_pmu_cpu_prepare(int cpu) cpuc->constraint_list = kzalloc(sz, GFP_KERNEL); if (!cpuc->constraint_list) - return NOTIFY_BAD; + goto err_shared_regs; cpuc->excl_cntrs = allocate_excl_cntrs(cpu); - if (!cpuc->excl_cntrs) { - kfree(cpuc->constraint_list); - kfree(cpuc->shared_regs); - return NOTIFY_BAD; - } + if (!cpuc->excl_cntrs) + goto err_constraint_list; + cpuc->excl_thread_id = 0; } return NOTIFY_OK; + +err_constraint_list: + kfree(cpuc->constraint_list); + cpuc->constraint_list = NULL; + +err_shared_regs: + kfree(cpuc->shared_regs); + cpuc->shared_regs = NULL; + +err: + return NOTIFY_BAD; } static void intel_pmu_cpu_starting(int cpu) diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c index 63eb68b73589..377e8f8ed391 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c +++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c @@ -1255,7 +1255,7 @@ static inline void cqm_pick_event_reader(int cpu) cpumask_set_cpu(cpu, &cqm_cpumask); } -static void intel_cqm_cpu_prepare(unsigned int cpu) +static void intel_cqm_cpu_starting(unsigned int cpu) { struct intel_pqr_state *state = &per_cpu(pqr_state, cpu); struct cpuinfo_x86 *c = &cpu_data(cpu); @@ -1296,13 +1296,11 @@ static int intel_cqm_cpu_notifier(struct notifier_block *nb, unsigned int cpu = (unsigned long)hcpu; switch (action & ~CPU_TASKS_FROZEN) { - case CPU_UP_PREPARE: - intel_cqm_cpu_prepare(cpu); - break; case CPU_DOWN_PREPARE: intel_cqm_cpu_exit(cpu); break; case CPU_STARTING: + intel_cqm_cpu_starting(cpu); cqm_pick_event_reader(cpu); break; } @@ -1373,7 +1371,7 @@ static int __init intel_cqm_init(void) goto out; for_each_online_cpu(i) { - intel_cqm_cpu_prepare(i); + intel_cqm_cpu_starting(i); cqm_pick_event_reader(i); } diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 206996c1669d..71820c42b6ce 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -93,8 +93,15 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc) COPY(r15); #endif /* CONFIG_X86_64 */ +#ifdef CONFIG_X86_32 COPY_SEG_CPL3(cs); COPY_SEG_CPL3(ss); +#else /* !CONFIG_X86_32 */ + /* Kernel saves and restores only the CS segment register on signals, + * which is the bare minimum needed to allow mixed 32/64-bit code. + * App's signal handler can save/restore other segments if needed. */ + COPY_SEG_CPL3(cs); +#endif /* CONFIG_X86_32 */ get_user_ex(tmpflags, &sc->flags); regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS); @@ -154,9 +161,8 @@ int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, #else /* !CONFIG_X86_32 */ put_user_ex(regs->flags, &sc->flags); put_user_ex(regs->cs, &sc->cs); - put_user_ex(0, &sc->__pad2); - put_user_ex(0, &sc->__pad1); - put_user_ex(regs->ss, &sc->ss); + put_user_ex(0, &sc->gs); + put_user_ex(0, &sc->fs); #endif /* CONFIG_X86_32 */ put_user_ex(fpstate, &sc->fpstate); @@ -451,19 +457,9 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, regs->sp = (unsigned long)frame; - /* - * Set up the CS and SS registers to run signal handlers in - * 64-bit mode, even if the handler happens to be interrupting - * 32-bit or 16-bit code. - * - * SS is subtle. In 64-bit mode, we don't need any particular - * SS descriptor, but we do need SS to be valid. It's possible - * that the old SS is entirely bogus -- this can happen if the - * signal we're trying to deliver is #GP or #SS caused by a bad - * SS value. - */ + /* Set up the CS register to run signal handlers in 64-bit mode, + even if the handler happens to be interrupting 32-bit code. */ regs->cs = __USER_CS; - regs->ss = __USER_DS; return 0; } diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index 6273324186ac..0ccb53a9fcd9 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -28,11 +28,11 @@ unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *re struct desc_struct *desc; unsigned long base; - seg &= ~7UL; + seg >>= 3; mutex_lock(&child->mm->context.lock); if (unlikely(!child->mm->context.ldt || - (seg >> 3) >= child->mm->context.ldt->size)) + seg >= child->mm->context.ldt->size)) addr = -1L; /* bogus selector, access would fault */ else { desc = &child->mm->context.ldt->entries[seg]; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 5ef2560075bf..8f0f6eca69da 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2105,7 +2105,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (guest_cpuid_has_tsc_adjust(vcpu)) { if (!msr_info->host_initiated) { s64 adj = data - vcpu->arch.ia32_tsc_adjust_msr; - kvm_x86_ops->adjust_tsc_offset(vcpu, adj, true); + adjust_tsc_offset_guest(vcpu, adj); } vcpu->arch.ia32_tsc_adjust_msr = data; } @@ -6327,6 +6327,7 @@ static void process_smi_save_state_64(struct kvm_vcpu *vcpu, char *buf) static void process_smi(struct kvm_vcpu *vcpu) { struct kvm_segment cs, ds; + struct desc_ptr dt; char buf[512]; u32 cr0; @@ -6359,6 +6360,10 @@ static void process_smi(struct kvm_vcpu *vcpu) kvm_x86_ops->set_cr4(vcpu, 0); + /* Undocumented: IDT limit is set to zero on entry to SMM. */ + dt.address = dt.size = 0; + kvm_x86_ops->set_idt(vcpu, &dt); + __kvm_set_dr(vcpu, 7, DR7_FIXED_1); cs.selector = (vcpu->arch.smbase >> 4) & 0xffff; diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c index f37e84ab49f3..3d8f2e421466 100644 --- a/arch/x86/math-emu/fpu_entry.c +++ b/arch/x86/math-emu/fpu_entry.c @@ -29,7 +29,6 @@ #include <asm/uaccess.h> #include <asm/traps.h> -#include <asm/desc.h> #include <asm/user.h> #include <asm/fpu/internal.h> @@ -181,7 +180,7 @@ void math_emulate(struct math_emu_info *info) math_abort(FPU_info, SIGILL); } - code_descriptor = LDT_DESCRIPTOR(FPU_CS); + code_descriptor = FPU_get_ldt_descriptor(FPU_CS); if (SEG_D_SIZE(code_descriptor)) { /* The above test may be wrong, the book is not clear */ /* Segmented 32 bit protected mode */ diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h index 9ccecb61a4fa..5e044d506b7a 100644 --- a/arch/x86/math-emu/fpu_system.h +++ b/arch/x86/math-emu/fpu_system.h @@ -16,9 +16,24 @@ #include <linux/kernel.h> #include <linux/mm.h> -/* s is always from a cpu register, and the cpu does bounds checking - * during register load --> no further bounds checks needed */ -#define LDT_DESCRIPTOR(s) (((struct desc_struct *)current->mm->context.ldt)[(s) >> 3]) +#include <asm/desc.h> +#include <asm/mmu_context.h> + +static inline struct desc_struct FPU_get_ldt_descriptor(unsigned seg) +{ + static struct desc_struct zero_desc; + struct desc_struct ret = zero_desc; + +#ifdef CONFIG_MODIFY_LDT_SYSCALL + seg >>= 3; + mutex_lock(¤t->mm->context.lock); + if (current->mm->context.ldt && seg < current->mm->context.ldt->size) + ret = current->mm->context.ldt->entries[seg]; + mutex_unlock(¤t->mm->context.lock); +#endif + return ret; +} + #define SEG_D_SIZE(x) ((x).b & (3 << 21)) #define SEG_G_BIT(x) ((x).b & (1 << 23)) #define SEG_GRANULARITY(x) (((x).b & (1 << 23)) ? 4096 : 1) diff --git a/arch/x86/math-emu/get_address.c b/arch/x86/math-emu/get_address.c index 6ef5e99380f9..8300db71c2a6 100644 --- a/arch/x86/math-emu/get_address.c +++ b/arch/x86/math-emu/get_address.c @@ -20,7 +20,6 @@ #include <linux/stddef.h> #include <asm/uaccess.h> -#include <asm/desc.h> #include "fpu_system.h" #include "exception.h" @@ -158,7 +157,7 @@ static long pm_address(u_char FPU_modrm, u_char segment, addr->selector = PM_REG_(segment); } - descriptor = LDT_DESCRIPTOR(PM_REG_(segment)); + descriptor = FPU_get_ldt_descriptor(addr->selector); base_address = SEG_BASE_ADDR(descriptor); address = base_address + offset; limit = base_address diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index 7322755f337a..4b6e29ac0968 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -13,13 +13,13 @@ CFLAGS_mmu.o := $(nostackp) obj-y := enlighten.o setup.o multicalls.o mmu.o irq.o \ time.o xen-asm.o xen-asm_$(BITS).o \ grant-table.o suspend.o platform-pci-unplug.o \ - p2m.o + p2m.o apic.o obj-$(CONFIG_EVENT_TRACING) += trace.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o obj-$(CONFIG_XEN_DEBUG_FS) += debugfs.o -obj-$(CONFIG_XEN_DOM0) += apic.o vga.o +obj-$(CONFIG_XEN_DOM0) += vga.o obj-$(CONFIG_SWIOTLB_XEN) += pci-swiotlb-xen.o obj-$(CONFIG_XEN_EFI) += efi.o diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index c20fe29e65f4..2292721b1d10 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -101,17 +101,15 @@ struct dom0_vga_console_info; #ifdef CONFIG_XEN_DOM0 void __init xen_init_vga(const struct dom0_vga_console_info *, size_t size); -void __init xen_init_apic(void); #else static inline void __init xen_init_vga(const struct dom0_vga_console_info *info, size_t size) { } -static inline void __init xen_init_apic(void) -{ -} #endif +void __init xen_init_apic(void); + #ifdef CONFIG_XEN_EFI extern void xen_efi_init(void); #else diff --git a/block/blk-settings.c b/block/blk-settings.c index 12600bfffca9..e0057d035200 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -241,8 +241,8 @@ EXPORT_SYMBOL(blk_queue_bounce_limit); * Description: * Enables a low level driver to set a hard upper limit, * max_hw_sectors, on the size of requests. max_hw_sectors is set by - * the device driver based upon the combined capabilities of I/O - * controller and storage device. + * the device driver based upon the capabilities of the I/O + * controller. * * max_sectors is a soft limit imposed by the block layer for * filesystem type requests. This value can be overridden on a diff --git a/drivers/base/regmap/regcache-rbtree.c b/drivers/base/regmap/regcache-rbtree.c index 81751a49d8bf..56486d92c4e7 100644 --- a/drivers/base/regmap/regcache-rbtree.c +++ b/drivers/base/regmap/regcache-rbtree.c @@ -296,11 +296,20 @@ static int regcache_rbtree_insert_to_block(struct regmap *map, if (!blk) return -ENOMEM; - present = krealloc(rbnode->cache_present, - BITS_TO_LONGS(blklen) * sizeof(*present), GFP_KERNEL); - if (!present) { - kfree(blk); - return -ENOMEM; + if (BITS_TO_LONGS(blklen) > BITS_TO_LONGS(rbnode->blklen)) { + present = krealloc(rbnode->cache_present, + BITS_TO_LONGS(blklen) * sizeof(*present), + GFP_KERNEL); + if (!present) { + kfree(blk); + return -ENOMEM; + } + + memset(present + BITS_TO_LONGS(rbnode->blklen), 0, + (BITS_TO_LONGS(blklen) - BITS_TO_LONGS(rbnode->blklen)) + * sizeof(*present)); + } else { + present = rbnode->cache_present; } /* insert the register value in the correct place in the rbnode block */ diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index ced96777b677..954c0029fb3b 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -369,8 +369,8 @@ static void purge_persistent_gnt(struct xen_blkif *blkif) return; } - if (work_pending(&blkif->persistent_purge_work)) { - pr_alert_ratelimited("Scheduled work from previous purge is still pending, cannot purge list\n"); + if (work_busy(&blkif->persistent_purge_work)) { + pr_alert_ratelimited("Scheduled work from previous purge is still busy, cannot purge list\n"); return; } diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 6d89ed35d80c..7a8a73f1fc04 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -179,6 +179,7 @@ static DEFINE_SPINLOCK(minor_lock); ((_segs + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME) static int blkfront_setup_indirect(struct blkfront_info *info); +static int blkfront_gather_backend_features(struct blkfront_info *info); static int get_id_from_freelist(struct blkfront_info *info) { @@ -1128,8 +1129,10 @@ static void blkif_completion(struct blk_shadow *s, struct blkfront_info *info, * Add the used indirect page back to the list of * available pages for indirect grefs. */ - indirect_page = pfn_to_page(s->indirect_grants[i]->pfn); - list_add(&indirect_page->lru, &info->indirect_pages); + if (!info->feature_persistent) { + indirect_page = pfn_to_page(s->indirect_grants[i]->pfn); + list_add(&indirect_page->lru, &info->indirect_pages); + } s->indirect_grants[i]->gref = GRANT_INVALID_REF; list_add_tail(&s->indirect_grants[i]->node, &info->grants); } @@ -1519,7 +1522,7 @@ static int blkif_recover(struct blkfront_info *info) info->shadow_free = info->ring.req_prod_pvt; info->shadow[BLK_RING_SIZE(info)-1].req.u.rw.id = 0x0fffffff; - rc = blkfront_setup_indirect(info); + rc = blkfront_gather_backend_features(info); if (rc) { kfree(copy); return rc; @@ -1720,20 +1723,13 @@ static void blkfront_setup_discard(struct blkfront_info *info) static int blkfront_setup_indirect(struct blkfront_info *info) { - unsigned int indirect_segments, segs; + unsigned int segs; int err, i; - err = xenbus_gather(XBT_NIL, info->xbdev->otherend, - "feature-max-indirect-segments", "%u", &indirect_segments, - NULL); - if (err) { - info->max_indirect_segments = 0; + if (info->max_indirect_segments == 0) segs = BLKIF_MAX_SEGMENTS_PER_REQUEST; - } else { - info->max_indirect_segments = min(indirect_segments, - xen_blkif_max_segments); + else segs = info->max_indirect_segments; - } err = fill_grant_buffer(info, (segs + INDIRECT_GREFS(segs)) * BLK_RING_SIZE(info)); if (err) @@ -1797,6 +1793,68 @@ out_of_memory: } /* + * Gather all backend feature-* + */ +static int blkfront_gather_backend_features(struct blkfront_info *info) +{ + int err; + int barrier, flush, discard, persistent; + unsigned int indirect_segments; + + info->feature_flush = 0; + + err = xenbus_gather(XBT_NIL, info->xbdev->otherend, + "feature-barrier", "%d", &barrier, + NULL); + + /* + * If there's no "feature-barrier" defined, then it means + * we're dealing with a very old backend which writes + * synchronously; nothing to do. + * + * If there are barriers, then we use flush. + */ + if (!err && barrier) + info->feature_flush = REQ_FLUSH | REQ_FUA; + /* + * And if there is "feature-flush-cache" use that above + * barriers. + */ + err = xenbus_gather(XBT_NIL, info->xbdev->otherend, + "feature-flush-cache", "%d", &flush, + NULL); + + if (!err && flush) + info->feature_flush = REQ_FLUSH; + + err = xenbus_gather(XBT_NIL, info->xbdev->otherend, + "feature-discard", "%d", &discard, + NULL); + + if (!err && discard) + blkfront_setup_discard(info); + + err = xenbus_gather(XBT_NIL, info->xbdev->otherend, + "feature-persistent", "%u", &persistent, + NULL); + if (err) + info->feature_persistent = 0; + else + info->feature_persistent = persistent; + + err = xenbus_gather(XBT_NIL, info->xbdev->otherend, + "feature-max-indirect-segments", "%u", &indirect_segments, + NULL); + if (err) + info->max_indirect_segments = 0; + else + info->max_indirect_segments = min(indirect_segments, + xen_blkif_max_segments); + + return blkfront_setup_indirect(info); +} + +/* * Invoked when the backend is finally 'ready' (and has told produced * the details about the physical device - #sectors, size, etc). */ @@ -1807,7 +1865,6 @@ static void blkfront_connect(struct blkfront_info *info) unsigned int physical_sector_size; unsigned int binfo; int err; - int barrier, flush, discard, persistent; switch (info->connected) { case BLKIF_STATE_CONNECTED: @@ -1864,48 +1921,7 @@ static void blkfront_connect(struct blkfront_info *info) if (err != 1) physical_sector_size = sector_size; - info->feature_flush = 0; - - err = xenbus_gather(XBT_NIL, info->xbdev->otherend, - "feature-barrier", "%d", &barrier, - NULL); - - /* - * If there's no "feature-barrier" defined, then it means - * we're dealing with a very old backend which writes - * synchronously; nothing to do. - * - * If there are barriers, then we use flush. - */ - if (!err && barrier) - info->feature_flush = REQ_FLUSH | REQ_FUA; - /* - * And if there is "feature-flush-cache" use that above - * barriers. - */ - err = xenbus_gather(XBT_NIL, info->xbdev->otherend, - "feature-flush-cache", "%d", &flush, - NULL); - - if (!err && flush) - info->feature_flush = REQ_FLUSH; - - err = xenbus_gather(XBT_NIL, info->xbdev->otherend, - "feature-discard", "%d", &discard, - NULL); - - if (!err && discard) - blkfront_setup_discard(info); - - err = xenbus_gather(XBT_NIL, info->xbdev->otherend, - "feature-persistent", "%u", &persistent, - NULL); - if (err) - info->feature_persistent = 0; - else - info->feature_persistent = persistent; - - err = blkfront_setup_indirect(info); + err = blkfront_gather_backend_features(info); if (err) { xenbus_dev_fatal(info->xbdev, err, "setup_indirect at %s", info->xbdev->otherend); diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index fb655e8d1e3b..763301c7828c 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -496,10 +496,9 @@ static void zram_meta_free(struct zram_meta *meta, u64 disksize) kfree(meta); } -static struct zram_meta *zram_meta_alloc(int device_id, u64 disksize) +static struct zram_meta *zram_meta_alloc(char *pool_name, u64 disksize) { size_t num_pages; - char pool_name[8]; struct zram_meta *meta = kmalloc(sizeof(*meta), GFP_KERNEL); if (!meta) @@ -512,7 +511,6 @@ static struct zram_meta *zram_meta_alloc(int device_id, u64 disksize) goto out_error; } - snprintf(pool_name, sizeof(pool_name), "zram%d", device_id); meta->mem_pool = zs_create_pool(pool_name, GFP_NOIO | __GFP_HIGHMEM); if (!meta->mem_pool) { pr_err("Error creating memory pool\n"); @@ -1031,7 +1029,7 @@ static ssize_t disksize_store(struct device *dev, return -EINVAL; disksize = PAGE_ALIGN(disksize); - meta = zram_meta_alloc(zram->disk->first_minor, disksize); + meta = zram_meta_alloc(zram->disk->disk_name, disksize); if (!meta) return -ENOMEM; diff --git a/drivers/clk/pxa/clk-pxa3xx.c b/drivers/clk/pxa/clk-pxa3xx.c index 4b93a1efb36d..ac03ba49e9d1 100644 --- a/drivers/clk/pxa/clk-pxa3xx.c +++ b/drivers/clk/pxa/clk-pxa3xx.c @@ -126,7 +126,7 @@ PARENTS(pxa3xx_ac97_bus) = { "ring_osc_60mhz", "ac97" }; PARENTS(pxa3xx_sbus) = { "ring_osc_60mhz", "system_bus" }; PARENTS(pxa3xx_smemcbus) = { "ring_osc_60mhz", "smemc" }; -#define CKEN_AB(bit) ((CKEN_ ## bit > 31) ? &CKENA : &CKENB) +#define CKEN_AB(bit) ((CKEN_ ## bit > 31) ? &CKENB : &CKENA) #define PXA3XX_CKEN(dev_id, con_id, parents, mult_lp, div_lp, mult_hp, \ div_hp, bit, is_lp, flags) \ PXA_CKEN(dev_id, con_id, bit, parents, mult_lp, div_lp, \ diff --git a/drivers/clocksource/sh_cmt.c b/drivers/clocksource/sh_cmt.c index b8ff3c64cc45..c96de14036a0 100644 --- a/drivers/clocksource/sh_cmt.c +++ b/drivers/clocksource/sh_cmt.c @@ -661,6 +661,9 @@ static void sh_cmt_clocksource_suspend(struct clocksource *cs) { struct sh_cmt_channel *ch = cs_to_sh_cmt(cs); + if (!ch->cs_enabled) + return; + sh_cmt_stop(ch, FLAG_CLOCKSOURCE); pm_genpd_syscore_poweroff(&ch->cmt->pdev->dev); } @@ -669,6 +672,9 @@ static void sh_cmt_clocksource_resume(struct clocksource *cs) { struct sh_cmt_channel *ch = cs_to_sh_cmt(cs); + if (!ch->cs_enabled) + return; + pm_genpd_syscore_poweron(&ch->cmt->pdev->dev); sh_cmt_start(ch, FLAG_CLOCKSOURCE); } diff --git a/drivers/edac/ppc4xx_edac.c b/drivers/edac/ppc4xx_edac.c index 3515b381c131..711d8ad74f11 100644 --- a/drivers/edac/ppc4xx_edac.c +++ b/drivers/edac/ppc4xx_edac.c @@ -920,7 +920,7 @@ static int ppc4xx_edac_init_csrows(struct mem_ctl_info *mci, u32 mcopt1) */ for (row = 0; row < mci->nr_csrows; row++) { - struct csrow_info *csi = &mci->csrows[row]; + struct csrow_info *csi = mci->csrows[row]; /* * Get the configuration settings for this diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index 2f7a5efa21c2..f5c22556ec2c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -374,7 +374,7 @@ static int amdgpu_uvd_cs_msg_decode(uint32_t *msg, unsigned buf_sizes[]) unsigned height_in_mb = ALIGN(height / 16, 2); unsigned fs_in_mb = width_in_mb * height_in_mb; - unsigned image_size, tmp, min_dpb_size, num_dpb_buffer; + unsigned image_size, tmp, min_dpb_size, num_dpb_buffer, min_ctx_size; image_size = width * height; image_size += image_size / 2; @@ -466,6 +466,8 @@ static int amdgpu_uvd_cs_msg_decode(uint32_t *msg, unsigned buf_sizes[]) num_dpb_buffer = (le32_to_cpu(msg[59]) & 0xff) + 2; min_dpb_size = image_size * num_dpb_buffer; + min_ctx_size = ((width + 255) / 16) * ((height + 255) / 16) + * 16 * num_dpb_buffer + 52 * 1024; break; default: @@ -486,6 +488,7 @@ static int amdgpu_uvd_cs_msg_decode(uint32_t *msg, unsigned buf_sizes[]) buf_sizes[0x1] = dpb_size; buf_sizes[0x2] = image_size; + buf_sizes[0x4] = min_ctx_size; return 0; } @@ -628,6 +631,13 @@ static int amdgpu_uvd_cs_pass2(struct amdgpu_uvd_cs_ctx *ctx) return -EINVAL; } + } else if (cmd == 0x206) { + if ((end - start) < ctx->buf_sizes[4]) { + DRM_ERROR("buffer (%d) to small (%d / %d)!\n", cmd, + (unsigned)(end - start), + ctx->buf_sizes[4]); + return -EINVAL; + } } else if ((cmd != 0x100) && (cmd != 0x204)) { DRM_ERROR("invalid UVD command %X!\n", cmd); return -EINVAL; @@ -755,9 +765,10 @@ int amdgpu_uvd_ring_parse_cs(struct amdgpu_cs_parser *parser, uint32_t ib_idx) struct amdgpu_uvd_cs_ctx ctx = {}; unsigned buf_sizes[] = { [0x00000000] = 2048, - [0x00000001] = 32 * 1024 * 1024, - [0x00000002] = 2048 * 1152 * 3, + [0x00000001] = 0xFFFFFFFF, + [0x00000002] = 0xFFFFFFFF, [0x00000003] = 2048, + [0x00000004] = 0xFFFFFFFF, }; struct amdgpu_ib *ib = &parser->ibs[ib_idx]; int r; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index f5a42ab1f65c..20e2cfd521d5 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -3135,7 +3135,7 @@ static int gfx_v8_0_cp_compute_resume(struct amdgpu_device *adev) WREG32(mmCP_MEC_DOORBELL_RANGE_LOWER, AMDGPU_DOORBELL_KIQ << 2); WREG32(mmCP_MEC_DOORBELL_RANGE_UPPER, - 0x7FFFF << 2); + AMDGPU_DOORBELL_MEC_RING7 << 2); } tmp = RREG32(mmCP_HQD_PQ_DOORBELL_CONTROL); tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_DOORBELL_CONTROL, diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c index 842d6b8dc3c4..2a652359af64 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c @@ -1745,7 +1745,6 @@ static int fimc_probe(struct platform_device *pdev) spin_lock_init(&ctx->lock); platform_set_drvdata(pdev, ctx); - pm_runtime_set_active(dev); pm_runtime_enable(dev); ret = exynos_drm_ippdrv_register(ippdrv); diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c index 8040ed2a831f..f1c6b76c127f 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c @@ -593,8 +593,7 @@ static int gsc_src_set_transf(struct device *dev, gsc_write(cfg, GSC_IN_CON); - ctx->rotation = cfg & - (GSC_IN_ROT_90 | GSC_IN_ROT_270) ? 1 : 0; + ctx->rotation = (cfg & GSC_IN_ROT_90) ? 1 : 0; *swap = ctx->rotation; return 0; @@ -857,8 +856,7 @@ static int gsc_dst_set_transf(struct device *dev, gsc_write(cfg, GSC_IN_CON); - ctx->rotation = cfg & - (GSC_IN_ROT_90 | GSC_IN_ROT_270) ? 1 : 0; + ctx->rotation = (cfg & GSC_IN_ROT_90) ? 1 : 0; *swap = ctx->rotation; return 0; diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c index 99e286489031..4a00990e4ae4 100644 --- a/drivers/gpu/drm/exynos/exynos_hdmi.c +++ b/drivers/gpu/drm/exynos/exynos_hdmi.c @@ -1064,6 +1064,7 @@ static int hdmi_get_modes(struct drm_connector *connector) { struct hdmi_context *hdata = ctx_from_connector(connector); struct edid *edid; + int ret; if (!hdata->ddc_adpt) return -ENODEV; @@ -1079,7 +1080,11 @@ static int hdmi_get_modes(struct drm_connector *connector) drm_mode_connector_update_edid_property(connector, edid); - return drm_add_edid_modes(connector, edid); + ret = drm_add_edid_modes(connector, edid); + + kfree(edid); + + return ret; } static int hdmi_find_phy_conf(struct hdmi_context *hdata, u32 pixel_clock) diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c index cae98db33062..4706b56902b4 100644 --- a/drivers/gpu/drm/exynos/exynos_mixer.c +++ b/drivers/gpu/drm/exynos/exynos_mixer.c @@ -718,6 +718,10 @@ static irqreturn_t mixer_irq_handler(int irq, void *arg) /* handling VSYNC */ if (val & MXR_INT_STATUS_VSYNC) { + /* vsync interrupt use different bit for read and clear */ + val |= MXR_INT_CLEAR_VSYNC; + val &= ~MXR_INT_STATUS_VSYNC; + /* interlace scan need to check shadow register */ if (ctx->interlace) { base = mixer_reg_read(res, MXR_GRAPHIC_BASE(0)); @@ -743,11 +747,6 @@ static irqreturn_t mixer_irq_handler(int irq, void *arg) out: /* clear interrupts */ - if (~val & MXR_INT_EN_VSYNC) { - /* vsync interrupt use different bit for read and clear */ - val &= ~MXR_INT_EN_VSYNC; - val |= MXR_INT_CLEAR_VSYNC; - } mixer_reg_write(res, MXR_INT_STATUS, val); spin_unlock(&res->reg_slock); @@ -907,8 +906,8 @@ static int mixer_enable_vblank(struct exynos_drm_crtc *crtc) } /* enable vsync interrupt */ - mixer_reg_writemask(res, MXR_INT_EN, MXR_INT_EN_VSYNC, - MXR_INT_EN_VSYNC); + mixer_reg_writemask(res, MXR_INT_STATUS, ~0, MXR_INT_CLEAR_VSYNC); + mixer_reg_writemask(res, MXR_INT_EN, ~0, MXR_INT_EN_VSYNC); return 0; } @@ -918,7 +917,13 @@ static void mixer_disable_vblank(struct exynos_drm_crtc *crtc) struct mixer_context *mixer_ctx = crtc->ctx; struct mixer_resources *res = &mixer_ctx->mixer_res; + if (!mixer_ctx->powered) { + mixer_ctx->int_en &= MXR_INT_EN_VSYNC; + return; + } + /* disable vsync interrupt */ + mixer_reg_writemask(res, MXR_INT_STATUS, ~0, MXR_INT_CLEAR_VSYNC); mixer_reg_writemask(res, MXR_INT_EN, 0, MXR_INT_EN_VSYNC); } @@ -1047,6 +1052,8 @@ static void mixer_enable(struct exynos_drm_crtc *crtc) mixer_reg_writemask(res, MXR_STATUS, ~0, MXR_STATUS_SOFT_RESET); + if (ctx->int_en & MXR_INT_EN_VSYNC) + mixer_reg_writemask(res, MXR_INT_STATUS, ~0, MXR_INT_CLEAR_VSYNC); mixer_reg_write(res, MXR_INT_EN, ctx->int_en); mixer_win_reset(ctx); } diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.c index 52c22b026005..e10f9644140f 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.c @@ -166,30 +166,14 @@ gk104_fifo_context_attach(struct nvkm_object *parent, } static int -gk104_fifo_chan_kick(struct gk104_fifo_chan *chan) -{ - struct nvkm_object *obj = (void *)chan; - struct gk104_fifo_priv *priv = (void *)obj->engine; - - nv_wr32(priv, 0x002634, chan->base.chid); - if (!nv_wait(priv, 0x002634, 0x100000, 0x000000)) { - nv_error(priv, "channel %d [%s] kick timeout\n", - chan->base.chid, nvkm_client_name(chan)); - return -EBUSY; - } - - return 0; -} - -static int gk104_fifo_context_detach(struct nvkm_object *parent, bool suspend, struct nvkm_object *object) { struct nvkm_bar *bar = nvkm_bar(parent); + struct gk104_fifo_priv *priv = (void *)parent->engine; struct gk104_fifo_base *base = (void *)parent->parent; struct gk104_fifo_chan *chan = (void *)parent; u32 addr; - int ret; switch (nv_engidx(object->engine)) { case NVDEV_ENGINE_SW : return 0; @@ -204,9 +188,13 @@ gk104_fifo_context_detach(struct nvkm_object *parent, bool suspend, return -EINVAL; } - ret = gk104_fifo_chan_kick(chan); - if (ret && suspend) - return ret; + nv_wr32(priv, 0x002634, chan->base.chid); + if (!nv_wait(priv, 0x002634, 0xffffffff, chan->base.chid)) { + nv_error(priv, "channel %d [%s] kick timeout\n", + chan->base.chid, nvkm_client_name(chan)); + if (suspend) + return -EBUSY; + } if (addr) { nv_wo32(base, addr + 0x00, 0x00000000); @@ -331,7 +319,6 @@ gk104_fifo_chan_fini(struct nvkm_object *object, bool suspend) gk104_fifo_runlist_update(priv, chan->engine); } - gk104_fifo_chan_kick(chan); nv_wr32(priv, 0x800000 + (chid * 8), 0x00000000); return nvkm_fifo_channel_fini(&chan->base, suspend); } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index 654c8daeb5ab..97ad3bcb99a7 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -2492,7 +2492,7 @@ int vmw_execbuf_process(struct drm_file *file_priv, ret = ttm_eu_reserve_buffers(&ticket, &sw_context->validate_nodes, true, NULL); if (unlikely(ret != 0)) - goto out_err; + goto out_err_nores; ret = vmw_validate_buffers(dev_priv, sw_context); if (unlikely(ret != 0)) @@ -2536,6 +2536,7 @@ int vmw_execbuf_process(struct drm_file *file_priv, vmw_resource_relocations_free(&sw_context->res_relocations); vmw_fifo_commit(dev_priv, command_size); + mutex_unlock(&dev_priv->binding_mutex); vmw_query_bo_switch_commit(dev_priv, sw_context); ret = vmw_execbuf_fence_commands(file_priv, dev_priv, @@ -2551,7 +2552,6 @@ int vmw_execbuf_process(struct drm_file *file_priv, DRM_ERROR("Fence submission error. Syncing.\n"); vmw_resource_list_unreserve(&sw_context->resource_list, false); - mutex_unlock(&dev_priv->binding_mutex); ttm_eu_fence_buffer_objects(&ticket, &sw_context->validate_nodes, (void *) fence); diff --git a/drivers/md/dm-cache-policy-mq.c b/drivers/md/dm-cache-policy-mq.c index 32814371b8d3..aa1b41ca40f7 100644 --- a/drivers/md/dm-cache-policy-mq.c +++ b/drivers/md/dm-cache-policy-mq.c @@ -1471,5 +1471,3 @@ module_exit(mq_exit); MODULE_AUTHOR("Joe Thornber <dm-devel@redhat.com>"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("mq cache policy"); - -MODULE_ALIAS("dm-cache-default"); diff --git a/drivers/md/dm-cache-policy-smq.c b/drivers/md/dm-cache-policy-smq.c index 48a4a826ae07..200366c62231 100644 --- a/drivers/md/dm-cache-policy-smq.c +++ b/drivers/md/dm-cache-policy-smq.c @@ -1789,3 +1789,5 @@ module_exit(smq_exit); MODULE_AUTHOR("Joe Thornber <dm-devel@redhat.com>"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("smq cache policy"); + +MODULE_ALIAS("dm-cache-default"); diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index 48dfe3c4d6aa..6ba47cfb1443 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -1293,8 +1293,8 @@ static int __release_metadata_snap(struct dm_pool_metadata *pmd) return r; disk_super = dm_block_data(copy); - dm_sm_dec_block(pmd->metadata_sm, le64_to_cpu(disk_super->data_mapping_root)); - dm_sm_dec_block(pmd->metadata_sm, le64_to_cpu(disk_super->device_details_root)); + dm_btree_del(&pmd->info, le64_to_cpu(disk_super->data_mapping_root)); + dm_btree_del(&pmd->details_info, le64_to_cpu(disk_super->device_details_root)); dm_sm_dec_block(pmd->metadata_sm, held_root); return dm_tm_unlock(pmd->tm, copy); diff --git a/drivers/md/persistent-data/dm-btree-internal.h b/drivers/md/persistent-data/dm-btree-internal.h index bf2b80d5c470..8731b6ea026b 100644 --- a/drivers/md/persistent-data/dm-btree-internal.h +++ b/drivers/md/persistent-data/dm-btree-internal.h @@ -138,4 +138,10 @@ int lower_bound(struct btree_node *n, uint64_t key); extern struct dm_block_validator btree_node_validator; +/* + * Value type for upper levels of multi-level btrees. + */ +extern void init_le64_type(struct dm_transaction_manager *tm, + struct dm_btree_value_type *vt); + #endif /* DM_BTREE_INTERNAL_H */ diff --git a/drivers/md/persistent-data/dm-btree-remove.c b/drivers/md/persistent-data/dm-btree-remove.c index 9ca9eccd512f..4222f774cf36 100644 --- a/drivers/md/persistent-data/dm-btree-remove.c +++ b/drivers/md/persistent-data/dm-btree-remove.c @@ -544,14 +544,6 @@ static int remove_raw(struct shadow_spine *s, struct dm_btree_info *info, return r; } -static struct dm_btree_value_type le64_type = { - .context = NULL, - .size = sizeof(__le64), - .inc = NULL, - .dec = NULL, - .equal = NULL -}; - int dm_btree_remove(struct dm_btree_info *info, dm_block_t root, uint64_t *keys, dm_block_t *new_root) { @@ -559,12 +551,14 @@ int dm_btree_remove(struct dm_btree_info *info, dm_block_t root, int index = 0, r = 0; struct shadow_spine spine; struct btree_node *n; + struct dm_btree_value_type le64_vt; + init_le64_type(info->tm, &le64_vt); init_shadow_spine(&spine, info); for (level = 0; level < info->levels; level++) { r = remove_raw(&spine, info, (level == last_level ? - &info->value_type : &le64_type), + &info->value_type : &le64_vt), root, keys[level], (unsigned *)&index); if (r < 0) break; @@ -654,11 +648,13 @@ static int remove_one(struct dm_btree_info *info, dm_block_t root, int index = 0, r = 0; struct shadow_spine spine; struct btree_node *n; + struct dm_btree_value_type le64_vt; uint64_t k; + init_le64_type(info->tm, &le64_vt); init_shadow_spine(&spine, info); for (level = 0; level < last_level; level++) { - r = remove_raw(&spine, info, &le64_type, + r = remove_raw(&spine, info, &le64_vt, root, keys[level], (unsigned *) &index); if (r < 0) goto out; diff --git a/drivers/md/persistent-data/dm-btree-spine.c b/drivers/md/persistent-data/dm-btree-spine.c index 1b5e13ec7f96..0dee514ba4c5 100644 --- a/drivers/md/persistent-data/dm-btree-spine.c +++ b/drivers/md/persistent-data/dm-btree-spine.c @@ -249,3 +249,40 @@ int shadow_root(struct shadow_spine *s) { return s->root; } + +static void le64_inc(void *context, const void *value_le) +{ + struct dm_transaction_manager *tm = context; + __le64 v_le; + + memcpy(&v_le, value_le, sizeof(v_le)); + dm_tm_inc(tm, le64_to_cpu(v_le)); +} + +static void le64_dec(void *context, const void *value_le) +{ + struct dm_transaction_manager *tm = context; + __le64 v_le; + + memcpy(&v_le, value_le, sizeof(v_le)); + dm_tm_dec(tm, le64_to_cpu(v_le)); +} + +static int le64_equal(void *context, const void *value1_le, const void *value2_le) +{ + __le64 v1_le, v2_le; + + memcpy(&v1_le, value1_le, sizeof(v1_le)); + memcpy(&v2_le, value2_le, sizeof(v2_le)); + return v1_le == v2_le; +} + +void init_le64_type(struct dm_transaction_manager *tm, + struct dm_btree_value_type *vt) +{ + vt->context = tm; + vt->size = sizeof(__le64); + vt->inc = le64_inc; + vt->dec = le64_dec; + vt->equal = le64_equal; +} diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c index fdd3793e22f9..c7726cebc495 100644 --- a/drivers/md/persistent-data/dm-btree.c +++ b/drivers/md/persistent-data/dm-btree.c @@ -667,12 +667,7 @@ static int insert(struct dm_btree_info *info, dm_block_t root, struct btree_node *n; struct dm_btree_value_type le64_type; - le64_type.context = NULL; - le64_type.size = sizeof(__le64); - le64_type.inc = NULL; - le64_type.dec = NULL; - le64_type.equal = NULL; - + init_le64_type(info->tm, &le64_type); init_shadow_spine(&spine, info); for (level = 0; level < (info->levels - 1); level++) { diff --git a/drivers/memory/omap-gpmc.c b/drivers/memory/omap-gpmc.c index 3a27a84ad3ec..9426276dbe14 100644 --- a/drivers/memory/omap-gpmc.c +++ b/drivers/memory/omap-gpmc.c @@ -2245,6 +2245,9 @@ void omap3_gpmc_save_context(void) { int i; + if (!gpmc_base) + return; + gpmc_context.sysconfig = gpmc_read_reg(GPMC_SYSCONFIG); gpmc_context.irqenable = gpmc_read_reg(GPMC_IRQENABLE); gpmc_context.timeout_ctrl = gpmc_read_reg(GPMC_TIMEOUT_CONTROL); @@ -2277,6 +2280,9 @@ void omap3_gpmc_restore_context(void) { int i; + if (!gpmc_base) + return; + gpmc_write_reg(GPMC_SYSCONFIG, gpmc_context.sysconfig); gpmc_write_reg(GPMC_IRQENABLE, gpmc_context.irqenable); gpmc_write_reg(GPMC_TIMEOUT_CONTROL, gpmc_context.timeout_ctrl); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index e1ccefce9a9d..a98dd4f1b0e3 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -786,6 +786,7 @@ static bool bond_should_notify_peers(struct bonding *bond) slave ? slave->dev->name : "NULL"); if (!slave || !bond->send_peer_notif || + !netif_carrier_ok(bond->dev) || test_bit(__LINK_STATE_LINKWATCH_PENDING, &slave->dev->state)) return false; diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c index 2d1ce3c5d0dd..753887d02b46 100644 --- a/drivers/net/ethernet/3com/3c59x.c +++ b/drivers/net/ethernet/3com/3c59x.c @@ -1763,16 +1763,9 @@ vortex_open(struct net_device *dev) vp->rx_ring[i].addr = cpu_to_le32(pci_map_single(VORTEX_PCI(vp), skb->data, PKT_BUF_SZ, PCI_DMA_FROMDEVICE)); } if (i != RX_RING_SIZE) { - int j; pr_emerg("%s: no memory for rx ring\n", dev->name); - for (j = 0; j < i; j++) { - if (vp->rx_skbuff[j]) { - dev_kfree_skb(vp->rx_skbuff[j]); - vp->rx_skbuff[j] = NULL; - } - } retval = -ENOMEM; - goto err_free_irq; + goto err_free_skb; } /* Wrap the ring. */ vp->rx_ring[i-1].next = cpu_to_le32(vp->rx_ring_dma); @@ -1782,7 +1775,13 @@ vortex_open(struct net_device *dev) if (!retval) goto out; -err_free_irq: +err_free_skb: + for (i = 0; i < RX_RING_SIZE; i++) { + if (vp->rx_skbuff[i]) { + dev_kfree_skb(vp->rx_skbuff[i]); + vp->rx_skbuff[i] = NULL; + } + } free_irq(dev->irq, dev); err: if (vortex_debug > 1) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index a90d7364334f..f7fbdc9d1325 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -262,9 +262,9 @@ static u16 bnx2x_free_tx_pkt(struct bnx2x *bp, struct bnx2x_fp_txdata *txdata, if (likely(skb)) { (*pkts_compl)++; (*bytes_compl) += skb->len; + dev_kfree_skb_any(skb); } - dev_kfree_skb_any(skb); tx_buf->first_bd = 0; tx_buf->skb = NULL; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index 76b9052a961c..5907c821d131 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -1718,6 +1718,22 @@ static int bnx2x_nvram_write(struct bnx2x *bp, u32 offset, u8 *data_buf, offset += sizeof(u32); data_buf += sizeof(u32); written_so_far += sizeof(u32); + + /* At end of each 4Kb page, release nvram lock to allow MFW + * chance to take it for its own use. + */ + if ((cmd_flags & MCPR_NVM_COMMAND_LAST) && + (written_so_far < buf_size)) { + DP(BNX2X_MSG_ETHTOOL | BNX2X_MSG_NVM, + "Releasing NVM lock after offset 0x%x\n", + (u32)(offset - sizeof(u32))); + bnx2x_release_nvram_lock(bp); + usleep_range(1000, 2000); + rc = bnx2x_acquire_nvram_lock(bp); + if (rc) + return rc; + } + cmd_flags = 0; } diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c index 0612b19f6313..506047c38607 100644 --- a/drivers/net/ethernet/brocade/bna/bnad.c +++ b/drivers/net/ethernet/brocade/bna/bnad.c @@ -676,6 +676,7 @@ bnad_cq_process(struct bnad *bnad, struct bna_ccb *ccb, int budget) if (!next_cmpl->valid) break; } + packets++; /* TODO: BNA_CQ_EF_LOCAL ? */ if (unlikely(flags & (BNA_CQ_EF_MAC_ERROR | @@ -692,7 +693,6 @@ bnad_cq_process(struct bnad *bnad, struct bna_ccb *ccb, int budget) else bnad_cq_setup_skb_frags(rcb, skb, sop_ci, nvecs, len); - packets++; rcb->rxq->rx_packets++; rcb->rxq->rx_bytes += totlen; ccb->bytes_per_intr += totlen; diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig index c4d6bbe9458d..02e23e6f1424 100644 --- a/drivers/net/ethernet/cavium/Kconfig +++ b/drivers/net/ethernet/cavium/Kconfig @@ -16,7 +16,6 @@ if NET_VENDOR_CAVIUM config THUNDER_NIC_PF tristate "Thunder Physical function driver" depends on 64BIT - default ARCH_THUNDER select THUNDER_NIC_BGX ---help--- This driver supports Thunder's NIC physical function. @@ -29,14 +28,12 @@ config THUNDER_NIC_PF config THUNDER_NIC_VF tristate "Thunder Virtual function driver" depends on 64BIT - default ARCH_THUNDER ---help--- This driver supports Thunder's NIC virtual function config THUNDER_NIC_BGX tristate "Thunder MAC interface driver (BGX)" depends on 64BIT - default ARCH_THUNDER ---help--- This driver supports programming and controlling of MAC interface from NIC physical function driver. diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c index a11485fbb33f..c3c7db41819d 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c @@ -2332,10 +2332,11 @@ int t4_setup_debugfs(struct adapter *adap) EXT_MEM1_SIZE_G(size)); } } else { - if (i & EXT_MEM_ENABLE_F) + if (i & EXT_MEM_ENABLE_F) { size = t4_read_reg(adap, MA_EXT_MEMORY_BAR_A); add_debugfs_mem(adap, "mc", MEM_MC, EXT_MEM_SIZE_G(size)); + } } de = debugfs_create_file_size("flash", S_IRUSR, adap->debugfs_root, adap, diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h index 2716e6f30d9a..00e3a6b6b822 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.h +++ b/drivers/net/ethernet/emulex/benet/be_cmds.h @@ -620,6 +620,11 @@ enum be_if_flags { BE_IF_FLAGS_VLAN_PROMISCUOUS |\ BE_IF_FLAGS_MCAST_PROMISCUOUS) +#define BE_IF_EN_FLAGS (BE_IF_FLAGS_BROADCAST | BE_IF_FLAGS_PASS_L3L4_ERRORS |\ + BE_IF_FLAGS_MULTICAST | BE_IF_FLAGS_UNTAGGED) + +#define BE_IF_ALL_FILT_FLAGS (BE_IF_EN_FLAGS | BE_IF_FLAGS_ALL_PROMISCUOUS) + /* An RX interface is an object with one or more MAC addresses and * filtering capabilities. */ struct be_cmd_req_if_create { diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 6f642426308c..c28e3bfdccd7 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -273,6 +273,10 @@ static int be_mac_addr_set(struct net_device *netdev, void *p) if (ether_addr_equal(addr->sa_data, netdev->dev_addr)) return 0; + /* if device is not running, copy MAC to netdev->dev_addr */ + if (!netif_running(netdev)) + goto done; + /* The PMAC_ADD cmd may fail if the VF doesn't have FILTMGMT * privilege or if PF did not provision the new MAC address. * On BE3, this cmd will always fail if the VF doesn't have the @@ -307,9 +311,9 @@ static int be_mac_addr_set(struct net_device *netdev, void *p) status = -EPERM; goto err; } - - memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len); - dev_info(dev, "MAC address changed to %pM\n", mac); +done: + ether_addr_copy(netdev->dev_addr, addr->sa_data); + dev_info(dev, "MAC address changed to %pM\n", addr->sa_data); return 0; err: dev_warn(dev, "MAC address change to %pM failed\n", addr->sa_data); @@ -2447,10 +2451,24 @@ static void be_eq_clean(struct be_eq_obj *eqo) be_eq_notify(eqo->adapter, eqo->q.id, false, true, num, 0); } -static void be_rx_cq_clean(struct be_rx_obj *rxo) +/* Free posted rx buffers that were not used */ +static void be_rxq_clean(struct be_rx_obj *rxo) { - struct be_rx_page_info *page_info; struct be_queue_info *rxq = &rxo->q; + struct be_rx_page_info *page_info; + + while (atomic_read(&rxq->used) > 0) { + page_info = get_rx_page_info(rxo); + put_page(page_info->page); + memset(page_info, 0, sizeof(*page_info)); + } + BUG_ON(atomic_read(&rxq->used)); + rxq->tail = 0; + rxq->head = 0; +} + +static void be_rx_cq_clean(struct be_rx_obj *rxo) +{ struct be_queue_info *rx_cq = &rxo->cq; struct be_rx_compl_info *rxcp; struct be_adapter *adapter = rxo->adapter; @@ -2487,16 +2505,6 @@ static void be_rx_cq_clean(struct be_rx_obj *rxo) /* After cleanup, leave the CQ in unarmed state */ be_cq_notify(adapter, rx_cq->id, false, 0); - - /* Then free posted rx buffers that were not used */ - while (atomic_read(&rxq->used) > 0) { - page_info = get_rx_page_info(rxo); - put_page(page_info->page); - memset(page_info, 0, sizeof(*page_info)); - } - BUG_ON(atomic_read(&rxq->used)); - rxq->tail = 0; - rxq->head = 0; } static void be_tx_compl_clean(struct be_adapter *adapter) @@ -2576,8 +2584,8 @@ static void be_evt_queues_destroy(struct be_adapter *adapter) be_cmd_q_destroy(adapter, &eqo->q, QTYPE_EQ); napi_hash_del(&eqo->napi); netif_napi_del(&eqo->napi); + free_cpumask_var(eqo->affinity_mask); } - free_cpumask_var(eqo->affinity_mask); be_queue_free(adapter, &eqo->q); } } @@ -2594,13 +2602,7 @@ static int be_evt_queues_create(struct be_adapter *adapter) for_all_evt_queues(adapter, eqo, i) { int numa_node = dev_to_node(&adapter->pdev->dev); - if (!zalloc_cpumask_var(&eqo->affinity_mask, GFP_KERNEL)) - return -ENOMEM; - cpumask_set_cpu(cpumask_local_spread(i, numa_node), - eqo->affinity_mask); - netif_napi_add(adapter->netdev, &eqo->napi, be_poll, - BE_NAPI_WEIGHT); - napi_hash_add(&eqo->napi); + aic = &adapter->aic_obj[i]; eqo->adapter = adapter; eqo->idx = i; @@ -2616,6 +2618,14 @@ static int be_evt_queues_create(struct be_adapter *adapter) rc = be_cmd_eq_create(adapter, eqo); if (rc) return rc; + + if (!zalloc_cpumask_var(&eqo->affinity_mask, GFP_KERNEL)) + return -ENOMEM; + cpumask_set_cpu(cpumask_local_spread(i, numa_node), + eqo->affinity_mask); + netif_napi_add(adapter->netdev, &eqo->napi, be_poll, + BE_NAPI_WEIGHT); + napi_hash_add(&eqo->napi); } return 0; } @@ -3354,13 +3364,54 @@ static void be_rx_qs_destroy(struct be_adapter *adapter) for_all_rx_queues(adapter, rxo, i) { q = &rxo->q; if (q->created) { + /* If RXQs are destroyed while in an "out of buffer" + * state, there is a possibility of an HW stall on + * Lancer. So, post 64 buffers to each queue to relieve + * the "out of buffer" condition. + * Make sure there's space in the RXQ before posting. + */ + if (lancer_chip(adapter)) { + be_rx_cq_clean(rxo); + if (atomic_read(&q->used) == 0) + be_post_rx_frags(rxo, GFP_KERNEL, + MAX_RX_POST); + } + be_cmd_rxq_destroy(adapter, q); be_rx_cq_clean(rxo); + be_rxq_clean(rxo); } be_queue_free(adapter, q); } } +static void be_disable_if_filters(struct be_adapter *adapter) +{ + be_cmd_pmac_del(adapter, adapter->if_handle, + adapter->pmac_id[0], 0); + + be_clear_uc_list(adapter); + + /* The IFACE flags are enabled in the open path and cleared + * in the close path. When a VF gets detached from the host and + * assigned to a VM the following happens: + * - VF's IFACE flags get cleared in the detach path + * - IFACE create is issued by the VF in the attach path + * Due to a bug in the BE3/Skyhawk-R FW + * (Lancer FW doesn't have the bug), the IFACE capability flags + * specified along with the IFACE create cmd issued by a VF are not + * honoured by FW. As a consequence, if a *new* driver + * (that enables/disables IFACE flags in open/close) + * is loaded in the host and an *old* driver is * used by a VM/VF, + * the IFACE gets created *without* the needed flags. + * To avoid this, disable RX-filter flags only for Lancer. + */ + if (lancer_chip(adapter)) { + be_cmd_rx_filter(adapter, BE_IF_ALL_FILT_FLAGS, OFF); + adapter->if_flags &= ~BE_IF_ALL_FILT_FLAGS; + } +} + static int be_close(struct net_device *netdev) { struct be_adapter *adapter = netdev_priv(netdev); @@ -3373,6 +3424,8 @@ static int be_close(struct net_device *netdev) if (!(adapter->flags & BE_FLAGS_SETUP_DONE)) return 0; + be_disable_if_filters(adapter); + be_roce_dev_close(adapter); if (adapter->flags & BE_FLAGS_NAPI_ENABLED) { @@ -3392,7 +3445,6 @@ static int be_close(struct net_device *netdev) be_tx_compl_clean(adapter); be_rx_qs_destroy(adapter); - be_clear_uc_list(adapter); for_all_evt_queues(adapter, eqo, i) { if (msix_enabled(adapter)) @@ -3477,6 +3529,31 @@ static int be_rx_qs_create(struct be_adapter *adapter) return 0; } +static int be_enable_if_filters(struct be_adapter *adapter) +{ + int status; + + status = be_cmd_rx_filter(adapter, BE_IF_EN_FLAGS, ON); + if (status) + return status; + + /* For BE3 VFs, the PF programs the initial MAC address */ + if (!(BEx_chip(adapter) && be_virtfn(adapter))) { + status = be_cmd_pmac_add(adapter, adapter->netdev->dev_addr, + adapter->if_handle, + &adapter->pmac_id[0], 0); + if (status) + return status; + } + + if (adapter->vlans_added) + be_vid_config(adapter); + + be_set_rx_mode(adapter->netdev); + + return 0; +} + static int be_open(struct net_device *netdev) { struct be_adapter *adapter = netdev_priv(netdev); @@ -3490,6 +3567,10 @@ static int be_open(struct net_device *netdev) if (status) goto err; + status = be_enable_if_filters(adapter); + if (status) + goto err; + status = be_irq_register(adapter); if (status) goto err; @@ -3686,16 +3767,6 @@ static void be_cancel_err_detection(struct be_adapter *adapter) } } -static void be_mac_clear(struct be_adapter *adapter) -{ - if (adapter->pmac_id) { - be_cmd_pmac_del(adapter, adapter->if_handle, - adapter->pmac_id[0], 0); - kfree(adapter->pmac_id); - adapter->pmac_id = NULL; - } -} - #ifdef CONFIG_BE2NET_VXLAN static void be_disable_vxlan_offloads(struct be_adapter *adapter) { @@ -3770,8 +3841,8 @@ static int be_clear(struct be_adapter *adapter) #ifdef CONFIG_BE2NET_VXLAN be_disable_vxlan_offloads(adapter); #endif - /* delete the primary mac along with the uc-mac list */ - be_mac_clear(adapter); + kfree(adapter->pmac_id); + adapter->pmac_id = NULL; be_cmd_if_destroy(adapter, adapter->if_handle, 0); @@ -3782,25 +3853,11 @@ static int be_clear(struct be_adapter *adapter) return 0; } -static int be_if_create(struct be_adapter *adapter, u32 *if_handle, - u32 cap_flags, u32 vf) -{ - u32 en_flags; - - en_flags = BE_IF_FLAGS_UNTAGGED | BE_IF_FLAGS_BROADCAST | - BE_IF_FLAGS_MULTICAST | BE_IF_FLAGS_PASS_L3L4_ERRORS | - BE_IF_FLAGS_RSS | BE_IF_FLAGS_DEFQ_RSS; - - en_flags &= cap_flags; - - return be_cmd_if_create(adapter, cap_flags, en_flags, if_handle, vf); -} - static int be_vfs_if_create(struct be_adapter *adapter) { struct be_resources res = {0}; + u32 cap_flags, en_flags, vf; struct be_vf_cfg *vf_cfg; - u32 cap_flags, vf; int status; /* If a FW profile exists, then cap_flags are updated */ @@ -3821,8 +3878,12 @@ static int be_vfs_if_create(struct be_adapter *adapter) } } - status = be_if_create(adapter, &vf_cfg->if_handle, - cap_flags, vf + 1); + en_flags = cap_flags & (BE_IF_FLAGS_UNTAGGED | + BE_IF_FLAGS_BROADCAST | + BE_IF_FLAGS_MULTICAST | + BE_IF_FLAGS_PASS_L3L4_ERRORS); + status = be_cmd_if_create(adapter, cap_flags, en_flags, + &vf_cfg->if_handle, vf + 1); if (status) return status; } @@ -4194,15 +4255,8 @@ static int be_mac_setup(struct be_adapter *adapter) memcpy(adapter->netdev->dev_addr, mac, ETH_ALEN); memcpy(adapter->netdev->perm_addr, mac, ETH_ALEN); - } else { - /* Maybe the HW was reset; dev_addr must be re-programmed */ - memcpy(mac, adapter->netdev->dev_addr, ETH_ALEN); } - /* For BE3-R VFs, the PF programs the initial MAC address */ - if (!(BEx_chip(adapter) && be_virtfn(adapter))) - be_cmd_pmac_add(adapter, mac, adapter->if_handle, - &adapter->pmac_id[0], 0); return 0; } @@ -4342,6 +4396,7 @@ static int be_func_init(struct be_adapter *adapter) static int be_setup(struct be_adapter *adapter) { struct device *dev = &adapter->pdev->dev; + u32 en_flags; int status; status = be_func_init(adapter); @@ -4364,8 +4419,11 @@ static int be_setup(struct be_adapter *adapter) if (status) goto err; - status = be_if_create(adapter, &adapter->if_handle, - be_if_cap_flags(adapter), 0); + /* will enable all the needed filter flags in be_open() */ + en_flags = BE_IF_FLAGS_RSS | BE_IF_FLAGS_DEFQ_RSS; + en_flags = en_flags & be_if_cap_flags(adapter); + status = be_cmd_if_create(adapter, be_if_cap_flags(adapter), en_flags, + &adapter->if_handle, 0); if (status) goto err; @@ -4391,11 +4449,6 @@ static int be_setup(struct be_adapter *adapter) dev_err(dev, "Please upgrade firmware to version >= 4.0\n"); } - if (adapter->vlans_added) - be_vid_config(adapter); - - be_set_rx_mode(adapter->netdev); - status = be_cmd_set_flow_control(adapter, adapter->tx_fc, adapter->rx_fc); if (status) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 32e3807c650e..271bb5862346 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3433,6 +3433,7 @@ fec_probe(struct platform_device *pdev) pm_runtime_set_autosuspend_delay(&pdev->dev, FEC_MDIO_PM_TIMEOUT); pm_runtime_use_autosuspend(&pdev->dev); + pm_runtime_get_noresume(&pdev->dev); pm_runtime_set_active(&pdev->dev); pm_runtime_enable(&pdev->dev); diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c index 56316db6c5a6..cf8e54652df9 100644 --- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c +++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c @@ -586,7 +586,8 @@ static int fs_enet_start_xmit(struct sk_buff *skb, struct net_device *dev) frag = skb_shinfo(skb)->frags; while (nr_frags) { CBDC_SC(bdp, - BD_ENET_TX_STATS | BD_ENET_TX_LAST | BD_ENET_TX_TC); + BD_ENET_TX_STATS | BD_ENET_TX_INTR | BD_ENET_TX_LAST | + BD_ENET_TX_TC); CBDS_SC(bdp, BD_ENET_TX_READY); if ((CBDR_SC(bdp) & BD_ENET_TX_WRAP) == 0) diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c index b34214e2df5f..016743e355de 100644 --- a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c +++ b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c @@ -110,7 +110,7 @@ static int do_pd_setup(struct fs_enet_private *fep) } #define FEC_NAPI_RX_EVENT_MSK (FEC_ENET_RXF | FEC_ENET_RXB) -#define FEC_NAPI_TX_EVENT_MSK (FEC_ENET_TXF | FEC_ENET_TXB) +#define FEC_NAPI_TX_EVENT_MSK (FEC_ENET_TXF) #define FEC_RX_EVENT (FEC_ENET_RXF) #define FEC_TX_EVENT (FEC_ENET_TXF) #define FEC_ERR_EVENT_MSK (FEC_ENET_HBERR | FEC_ENET_BABR | \ diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c index 3c0a8f825b63..5b90fcf96265 100644 --- a/drivers/net/ethernet/freescale/gianfar_ethtool.c +++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c @@ -900,27 +900,6 @@ static int gfar_check_filer_hardware(struct gfar_private *priv) return 0; } -static int gfar_comp_asc(const void *a, const void *b) -{ - return memcmp(a, b, 4); -} - -static int gfar_comp_desc(const void *a, const void *b) -{ - return -memcmp(a, b, 4); -} - -static void gfar_swap(void *a, void *b, int size) -{ - u32 *_a = a; - u32 *_b = b; - - swap(_a[0], _b[0]); - swap(_a[1], _b[1]); - swap(_a[2], _b[2]); - swap(_a[3], _b[3]); -} - /* Write a mask to filer cache */ static void gfar_set_mask(u32 mask, struct filer_table *tab) { @@ -1270,310 +1249,6 @@ static int gfar_convert_to_filer(struct ethtool_rx_flow_spec *rule, return 0; } -/* Copy size filer entries */ -static void gfar_copy_filer_entries(struct gfar_filer_entry dst[0], - struct gfar_filer_entry src[0], s32 size) -{ - while (size > 0) { - size--; - dst[size].ctrl = src[size].ctrl; - dst[size].prop = src[size].prop; - } -} - -/* Delete the contents of the filer-table between start and end - * and collapse them - */ -static int gfar_trim_filer_entries(u32 begin, u32 end, struct filer_table *tab) -{ - int length; - - if (end > MAX_FILER_CACHE_IDX || end < begin) - return -EINVAL; - - end++; - length = end - begin; - - /* Copy */ - while (end < tab->index) { - tab->fe[begin].ctrl = tab->fe[end].ctrl; - tab->fe[begin++].prop = tab->fe[end++].prop; - - } - /* Fill up with don't cares */ - while (begin < tab->index) { - tab->fe[begin].ctrl = 0x60; - tab->fe[begin].prop = 0xFFFFFFFF; - begin++; - } - - tab->index -= length; - return 0; -} - -/* Make space on the wanted location */ -static int gfar_expand_filer_entries(u32 begin, u32 length, - struct filer_table *tab) -{ - if (length == 0 || length + tab->index > MAX_FILER_CACHE_IDX || - begin > MAX_FILER_CACHE_IDX) - return -EINVAL; - - gfar_copy_filer_entries(&(tab->fe[begin + length]), &(tab->fe[begin]), - tab->index - length + 1); - - tab->index += length; - return 0; -} - -static int gfar_get_next_cluster_start(int start, struct filer_table *tab) -{ - for (; (start < tab->index) && (start < MAX_FILER_CACHE_IDX - 1); - start++) { - if ((tab->fe[start].ctrl & (RQFCR_AND | RQFCR_CLE)) == - (RQFCR_AND | RQFCR_CLE)) - return start; - } - return -1; -} - -static int gfar_get_next_cluster_end(int start, struct filer_table *tab) -{ - for (; (start < tab->index) && (start < MAX_FILER_CACHE_IDX - 1); - start++) { - if ((tab->fe[start].ctrl & (RQFCR_AND | RQFCR_CLE)) == - (RQFCR_CLE)) - return start; - } - return -1; -} - -/* Uses hardwares clustering option to reduce - * the number of filer table entries - */ -static void gfar_cluster_filer(struct filer_table *tab) -{ - s32 i = -1, j, iend, jend; - - while ((i = gfar_get_next_cluster_start(++i, tab)) != -1) { - j = i; - while ((j = gfar_get_next_cluster_start(++j, tab)) != -1) { - /* The cluster entries self and the previous one - * (a mask) must be identical! - */ - if (tab->fe[i].ctrl != tab->fe[j].ctrl) - break; - if (tab->fe[i].prop != tab->fe[j].prop) - break; - if (tab->fe[i - 1].ctrl != tab->fe[j - 1].ctrl) - break; - if (tab->fe[i - 1].prop != tab->fe[j - 1].prop) - break; - iend = gfar_get_next_cluster_end(i, tab); - jend = gfar_get_next_cluster_end(j, tab); - if (jend == -1 || iend == -1) - break; - - /* First we make some free space, where our cluster - * element should be. Then we copy it there and finally - * delete in from its old location. - */ - if (gfar_expand_filer_entries(iend, (jend - j), tab) == - -EINVAL) - break; - - gfar_copy_filer_entries(&(tab->fe[iend + 1]), - &(tab->fe[jend + 1]), jend - j); - - if (gfar_trim_filer_entries(jend - 1, - jend + (jend - j), - tab) == -EINVAL) - return; - - /* Mask out cluster bit */ - tab->fe[iend].ctrl &= ~(RQFCR_CLE); - } - } -} - -/* Swaps the masked bits of a1<>a2 and b1<>b2 */ -static void gfar_swap_bits(struct gfar_filer_entry *a1, - struct gfar_filer_entry *a2, - struct gfar_filer_entry *b1, - struct gfar_filer_entry *b2, u32 mask) -{ - u32 temp[4]; - temp[0] = a1->ctrl & mask; - temp[1] = a2->ctrl & mask; - temp[2] = b1->ctrl & mask; - temp[3] = b2->ctrl & mask; - - a1->ctrl &= ~mask; - a2->ctrl &= ~mask; - b1->ctrl &= ~mask; - b2->ctrl &= ~mask; - - a1->ctrl |= temp[1]; - a2->ctrl |= temp[0]; - b1->ctrl |= temp[3]; - b2->ctrl |= temp[2]; -} - -/* Generate a list consisting of masks values with their start and - * end of validity and block as indicator for parts belonging - * together (glued by ANDs) in mask_table - */ -static u32 gfar_generate_mask_table(struct gfar_mask_entry *mask_table, - struct filer_table *tab) -{ - u32 i, and_index = 0, block_index = 1; - - for (i = 0; i < tab->index; i++) { - - /* LSByte of control = 0 sets a mask */ - if (!(tab->fe[i].ctrl & 0xF)) { - mask_table[and_index].mask = tab->fe[i].prop; - mask_table[and_index].start = i; - mask_table[and_index].block = block_index; - if (and_index >= 1) - mask_table[and_index - 1].end = i - 1; - and_index++; - } - /* cluster starts and ends will be separated because they should - * hold their position - */ - if (tab->fe[i].ctrl & RQFCR_CLE) - block_index++; - /* A not set AND indicates the end of a depended block */ - if (!(tab->fe[i].ctrl & RQFCR_AND)) - block_index++; - } - - mask_table[and_index - 1].end = i - 1; - - return and_index; -} - -/* Sorts the entries of mask_table by the values of the masks. - * Important: The 0xFF80 flags of the first and last entry of a - * block must hold their position (which queue, CLusterEnable, ReJEct, - * AND) - */ -static void gfar_sort_mask_table(struct gfar_mask_entry *mask_table, - struct filer_table *temp_table, u32 and_index) -{ - /* Pointer to compare function (_asc or _desc) */ - int (*gfar_comp)(const void *, const void *); - - u32 i, size = 0, start = 0, prev = 1; - u32 old_first, old_last, new_first, new_last; - - gfar_comp = &gfar_comp_desc; - - for (i = 0; i < and_index; i++) { - if (prev != mask_table[i].block) { - old_first = mask_table[start].start + 1; - old_last = mask_table[i - 1].end; - sort(mask_table + start, size, - sizeof(struct gfar_mask_entry), - gfar_comp, &gfar_swap); - - /* Toggle order for every block. This makes the - * thing more efficient! - */ - if (gfar_comp == gfar_comp_desc) - gfar_comp = &gfar_comp_asc; - else - gfar_comp = &gfar_comp_desc; - - new_first = mask_table[start].start + 1; - new_last = mask_table[i - 1].end; - - gfar_swap_bits(&temp_table->fe[new_first], - &temp_table->fe[old_first], - &temp_table->fe[new_last], - &temp_table->fe[old_last], - RQFCR_QUEUE | RQFCR_CLE | - RQFCR_RJE | RQFCR_AND); - - start = i; - size = 0; - } - size++; - prev = mask_table[i].block; - } -} - -/* Reduces the number of masks needed in the filer table to save entries - * This is done by sorting the masks of a depended block. A depended block is - * identified by gluing ANDs or CLE. The sorting order toggles after every - * block. Of course entries in scope of a mask must change their location with - * it. - */ -static int gfar_optimize_filer_masks(struct filer_table *tab) -{ - struct filer_table *temp_table; - struct gfar_mask_entry *mask_table; - - u32 and_index = 0, previous_mask = 0, i = 0, j = 0, size = 0; - s32 ret = 0; - - /* We need a copy of the filer table because - * we want to change its order - */ - temp_table = kmemdup(tab, sizeof(*temp_table), GFP_KERNEL); - if (temp_table == NULL) - return -ENOMEM; - - mask_table = kcalloc(MAX_FILER_CACHE_IDX / 2 + 1, - sizeof(struct gfar_mask_entry), GFP_KERNEL); - - if (mask_table == NULL) { - ret = -ENOMEM; - goto end; - } - - and_index = gfar_generate_mask_table(mask_table, tab); - - gfar_sort_mask_table(mask_table, temp_table, and_index); - - /* Now we can copy the data from our duplicated filer table to - * the real one in the order the mask table says - */ - for (i = 0; i < and_index; i++) { - size = mask_table[i].end - mask_table[i].start + 1; - gfar_copy_filer_entries(&(tab->fe[j]), - &(temp_table->fe[mask_table[i].start]), size); - j += size; - } - - /* And finally we just have to check for duplicated masks and drop the - * second ones - */ - for (i = 0; i < tab->index && i < MAX_FILER_CACHE_IDX; i++) { - if (tab->fe[i].ctrl == 0x80) { - previous_mask = i++; - break; - } - } - for (; i < tab->index && i < MAX_FILER_CACHE_IDX; i++) { - if (tab->fe[i].ctrl == 0x80) { - if (tab->fe[i].prop == tab->fe[previous_mask].prop) { - /* Two identical ones found! - * So drop the second one! - */ - gfar_trim_filer_entries(i, i, tab); - } else - /* Not identical! */ - previous_mask = i; - } - } - - kfree(mask_table); -end: kfree(temp_table); - return ret; -} - /* Write the bit-pattern from software's buffer to hardware registers */ static int gfar_write_filer_table(struct gfar_private *priv, struct filer_table *tab) @@ -1583,11 +1258,10 @@ static int gfar_write_filer_table(struct gfar_private *priv, return -EBUSY; /* Fill regular entries */ - for (; i < MAX_FILER_IDX - 1 && (tab->fe[i].ctrl | tab->fe[i].prop); - i++) + for (; i < MAX_FILER_IDX && (tab->fe[i].ctrl | tab->fe[i].prop); i++) gfar_write_filer(priv, i, tab->fe[i].ctrl, tab->fe[i].prop); /* Fill the rest with fall-troughs */ - for (; i < MAX_FILER_IDX - 1; i++) + for (; i < MAX_FILER_IDX; i++) gfar_write_filer(priv, i, 0x60, 0xFFFFFFFF); /* Last entry must be default accept * because that's what people expect @@ -1621,7 +1295,6 @@ static int gfar_process_filer_changes(struct gfar_private *priv) { struct ethtool_flow_spec_container *j; struct filer_table *tab; - s32 i = 0; s32 ret = 0; /* So index is set to zero, too! */ @@ -1646,17 +1319,6 @@ static int gfar_process_filer_changes(struct gfar_private *priv) } } - i = tab->index; - - /* Optimizations to save entries */ - gfar_cluster_filer(tab); - gfar_optimize_filer_masks(tab); - - pr_debug("\tSummary:\n" - "\tData on hardware: %d\n" - "\tCompression rate: %d%%\n", - tab->index, 100 - (100 * tab->index) / i); - /* Write everything to hardware */ ret = gfar_write_filer_table(priv, tab); if (ret == -EBUSY) { @@ -1722,13 +1384,14 @@ static int gfar_add_cls(struct gfar_private *priv, } process: + priv->rx_list.count++; ret = gfar_process_filer_changes(priv); if (ret) goto clean_list; - priv->rx_list.count++; return ret; clean_list: + priv->rx_list.count--; list_del(&temp->list); clean_mem: kfree(temp); diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index 3e8b1bfb1f2e..d9884fd15b45 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -27,6 +27,8 @@ #include <linux/of_address.h> #include <linux/phy.h> #include <linux/clk.h> +#include <linux/hrtimer.h> +#include <linux/ktime.h> #include <uapi/linux/ppp_defs.h> #include <net/ip.h> #include <net/ipv6.h> @@ -299,6 +301,7 @@ /* Coalescing */ #define MVPP2_TXDONE_COAL_PKTS_THRESH 15 +#define MVPP2_TXDONE_HRTIMER_PERIOD_NS 1000000UL #define MVPP2_RX_COAL_PKTS 32 #define MVPP2_RX_COAL_USEC 100 @@ -660,6 +663,14 @@ struct mvpp2_pcpu_stats { u64 tx_bytes; }; +/* Per-CPU port control */ +struct mvpp2_port_pcpu { + struct hrtimer tx_done_timer; + bool timer_scheduled; + /* Tasklet for egress finalization */ + struct tasklet_struct tx_done_tasklet; +}; + struct mvpp2_port { u8 id; @@ -679,6 +690,9 @@ struct mvpp2_port { u32 pending_cause_rx; struct napi_struct napi; + /* Per-CPU port control */ + struct mvpp2_port_pcpu __percpu *pcpu; + /* Flags */ unsigned long flags; @@ -776,6 +790,9 @@ struct mvpp2_txq_pcpu { /* Array of transmitted skb */ struct sk_buff **tx_skb; + /* Array of transmitted buffers' physical addresses */ + dma_addr_t *tx_buffs; + /* Index of last TX DMA descriptor that was inserted */ int txq_put_index; @@ -913,8 +930,6 @@ struct mvpp2_bm_pool { /* Occupied buffers indicator */ atomic_t in_use; int in_use_thresh; - - spinlock_t lock; }; struct mvpp2_buff_hdr { @@ -963,9 +978,13 @@ static void mvpp2_txq_inc_get(struct mvpp2_txq_pcpu *txq_pcpu) } static void mvpp2_txq_inc_put(struct mvpp2_txq_pcpu *txq_pcpu, - struct sk_buff *skb) + struct sk_buff *skb, + struct mvpp2_tx_desc *tx_desc) { txq_pcpu->tx_skb[txq_pcpu->txq_put_index] = skb; + if (skb) + txq_pcpu->tx_buffs[txq_pcpu->txq_put_index] = + tx_desc->buf_phys_addr; txq_pcpu->txq_put_index++; if (txq_pcpu->txq_put_index == txq_pcpu->size) txq_pcpu->txq_put_index = 0; @@ -3376,7 +3395,6 @@ static int mvpp2_bm_pool_create(struct platform_device *pdev, bm_pool->pkt_size = 0; bm_pool->buf_num = 0; atomic_set(&bm_pool->in_use, 0); - spin_lock_init(&bm_pool->lock); return 0; } @@ -3647,7 +3665,6 @@ static struct mvpp2_bm_pool * mvpp2_bm_pool_use(struct mvpp2_port *port, int pool, enum mvpp2_bm_type type, int pkt_size) { - unsigned long flags = 0; struct mvpp2_bm_pool *new_pool = &port->priv->bm_pools[pool]; int num; @@ -3656,8 +3673,6 @@ mvpp2_bm_pool_use(struct mvpp2_port *port, int pool, enum mvpp2_bm_type type, return NULL; } - spin_lock_irqsave(&new_pool->lock, flags); - if (new_pool->type == MVPP2_BM_FREE) new_pool->type = type; @@ -3686,8 +3701,6 @@ mvpp2_bm_pool_use(struct mvpp2_port *port, int pool, enum mvpp2_bm_type type, if (num != pkts_num) { WARN(1, "pool %d: %d of %d allocated\n", new_pool->id, num, pkts_num); - /* We need to undo the bufs_add() allocations */ - spin_unlock_irqrestore(&new_pool->lock, flags); return NULL; } } @@ -3695,15 +3708,12 @@ mvpp2_bm_pool_use(struct mvpp2_port *port, int pool, enum mvpp2_bm_type type, mvpp2_bm_pool_bufsize_set(port->priv, new_pool, MVPP2_RX_BUF_SIZE(new_pool->pkt_size)); - spin_unlock_irqrestore(&new_pool->lock, flags); - return new_pool; } /* Initialize pools for swf */ static int mvpp2_swf_bm_pool_init(struct mvpp2_port *port) { - unsigned long flags = 0; int rxq; if (!port->pool_long) { @@ -3714,9 +3724,7 @@ static int mvpp2_swf_bm_pool_init(struct mvpp2_port *port) if (!port->pool_long) return -ENOMEM; - spin_lock_irqsave(&port->pool_long->lock, flags); port->pool_long->port_map |= (1 << port->id); - spin_unlock_irqrestore(&port->pool_long->lock, flags); for (rxq = 0; rxq < rxq_number; rxq++) mvpp2_rxq_long_pool_set(port, rxq, port->pool_long->id); @@ -3730,9 +3738,7 @@ static int mvpp2_swf_bm_pool_init(struct mvpp2_port *port) if (!port->pool_short) return -ENOMEM; - spin_lock_irqsave(&port->pool_short->lock, flags); port->pool_short->port_map |= (1 << port->id); - spin_unlock_irqrestore(&port->pool_short->lock, flags); for (rxq = 0; rxq < rxq_number; rxq++) mvpp2_rxq_short_pool_set(port, rxq, @@ -3806,7 +3812,6 @@ static void mvpp2_interrupts_unmask(void *arg) mvpp2_write(port->priv, MVPP2_ISR_RX_TX_MASK_REG(port->id), (MVPP2_CAUSE_MISC_SUM_MASK | - MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_MASK | MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK)); } @@ -4382,23 +4387,6 @@ static void mvpp2_rx_time_coal_set(struct mvpp2_port *port, rxq->time_coal = usec; } -/* Set threshold for TX_DONE pkts coalescing */ -static void mvpp2_tx_done_pkts_coal_set(void *arg) -{ - struct mvpp2_port *port = arg; - int queue; - u32 val; - - for (queue = 0; queue < txq_number; queue++) { - struct mvpp2_tx_queue *txq = port->txqs[queue]; - - val = (txq->done_pkts_coal << MVPP2_TRANSMITTED_THRESH_OFFSET) & - MVPP2_TRANSMITTED_THRESH_MASK; - mvpp2_write(port->priv, MVPP2_TXQ_NUM_REG, txq->id); - mvpp2_write(port->priv, MVPP2_TXQ_THRESH_REG, val); - } -} - /* Free Tx queue skbuffs */ static void mvpp2_txq_bufs_free(struct mvpp2_port *port, struct mvpp2_tx_queue *txq, @@ -4407,8 +4395,8 @@ static void mvpp2_txq_bufs_free(struct mvpp2_port *port, int i; for (i = 0; i < num; i++) { - struct mvpp2_tx_desc *tx_desc = txq->descs + - txq_pcpu->txq_get_index; + dma_addr_t buf_phys_addr = + txq_pcpu->tx_buffs[txq_pcpu->txq_get_index]; struct sk_buff *skb = txq_pcpu->tx_skb[txq_pcpu->txq_get_index]; mvpp2_txq_inc_get(txq_pcpu); @@ -4416,8 +4404,8 @@ static void mvpp2_txq_bufs_free(struct mvpp2_port *port, if (!skb) continue; - dma_unmap_single(port->dev->dev.parent, tx_desc->buf_phys_addr, - tx_desc->data_size, DMA_TO_DEVICE); + dma_unmap_single(port->dev->dev.parent, buf_phys_addr, + skb_headlen(skb), DMA_TO_DEVICE); dev_kfree_skb_any(skb); } } @@ -4433,7 +4421,7 @@ static inline struct mvpp2_rx_queue *mvpp2_get_rx_queue(struct mvpp2_port *port, static inline struct mvpp2_tx_queue *mvpp2_get_tx_queue(struct mvpp2_port *port, u32 cause) { - int queue = fls(cause >> 16) - 1; + int queue = fls(cause) - 1; return port->txqs[queue]; } @@ -4460,6 +4448,29 @@ static void mvpp2_txq_done(struct mvpp2_port *port, struct mvpp2_tx_queue *txq, netif_tx_wake_queue(nq); } +static unsigned int mvpp2_tx_done(struct mvpp2_port *port, u32 cause) +{ + struct mvpp2_tx_queue *txq; + struct mvpp2_txq_pcpu *txq_pcpu; + unsigned int tx_todo = 0; + + while (cause) { + txq = mvpp2_get_tx_queue(port, cause); + if (!txq) + break; + + txq_pcpu = this_cpu_ptr(txq->pcpu); + + if (txq_pcpu->count) { + mvpp2_txq_done(port, txq, txq_pcpu); + tx_todo += txq_pcpu->count; + } + + cause &= ~(1 << txq->log_id); + } + return tx_todo; +} + /* Rx/Tx queue initialization/cleanup methods */ /* Allocate and initialize descriptors for aggr TXQ */ @@ -4649,12 +4660,13 @@ static int mvpp2_txq_init(struct mvpp2_port *port, txq_pcpu->tx_skb = kmalloc(txq_pcpu->size * sizeof(*txq_pcpu->tx_skb), GFP_KERNEL); - if (!txq_pcpu->tx_skb) { - dma_free_coherent(port->dev->dev.parent, - txq->size * MVPP2_DESC_ALIGNED_SIZE, - txq->descs, txq->descs_phys); - return -ENOMEM; - } + if (!txq_pcpu->tx_skb) + goto error; + + txq_pcpu->tx_buffs = kmalloc(txq_pcpu->size * + sizeof(dma_addr_t), GFP_KERNEL); + if (!txq_pcpu->tx_buffs) + goto error; txq_pcpu->count = 0; txq_pcpu->reserved_num = 0; @@ -4663,6 +4675,19 @@ static int mvpp2_txq_init(struct mvpp2_port *port, } return 0; + +error: + for_each_present_cpu(cpu) { + txq_pcpu = per_cpu_ptr(txq->pcpu, cpu); + kfree(txq_pcpu->tx_skb); + kfree(txq_pcpu->tx_buffs); + } + + dma_free_coherent(port->dev->dev.parent, + txq->size * MVPP2_DESC_ALIGNED_SIZE, + txq->descs, txq->descs_phys); + + return -ENOMEM; } /* Free allocated TXQ resources */ @@ -4675,6 +4700,7 @@ static void mvpp2_txq_deinit(struct mvpp2_port *port, for_each_present_cpu(cpu) { txq_pcpu = per_cpu_ptr(txq->pcpu, cpu); kfree(txq_pcpu->tx_skb); + kfree(txq_pcpu->tx_buffs); } if (txq->descs) @@ -4805,7 +4831,6 @@ static int mvpp2_setup_txqs(struct mvpp2_port *port) goto err_cleanup; } - on_each_cpu(mvpp2_tx_done_pkts_coal_set, port, 1); on_each_cpu(mvpp2_txq_sent_counter_clear, port, 1); return 0; @@ -4887,6 +4912,49 @@ static void mvpp2_link_event(struct net_device *dev) } } +static void mvpp2_timer_set(struct mvpp2_port_pcpu *port_pcpu) +{ + ktime_t interval; + + if (!port_pcpu->timer_scheduled) { + port_pcpu->timer_scheduled = true; + interval = ktime_set(0, MVPP2_TXDONE_HRTIMER_PERIOD_NS); + hrtimer_start(&port_pcpu->tx_done_timer, interval, + HRTIMER_MODE_REL_PINNED); + } +} + +static void mvpp2_tx_proc_cb(unsigned long data) +{ + struct net_device *dev = (struct net_device *)data; + struct mvpp2_port *port = netdev_priv(dev); + struct mvpp2_port_pcpu *port_pcpu = this_cpu_ptr(port->pcpu); + unsigned int tx_todo, cause; + + if (!netif_running(dev)) + return; + port_pcpu->timer_scheduled = false; + + /* Process all the Tx queues */ + cause = (1 << txq_number) - 1; + tx_todo = mvpp2_tx_done(port, cause); + + /* Set the timer in case not all the packets were processed */ + if (tx_todo) + mvpp2_timer_set(port_pcpu); +} + +static enum hrtimer_restart mvpp2_hr_timer_cb(struct hrtimer *timer) +{ + struct mvpp2_port_pcpu *port_pcpu = container_of(timer, + struct mvpp2_port_pcpu, + tx_done_timer); + + tasklet_schedule(&port_pcpu->tx_done_tasklet); + + return HRTIMER_NORESTART; +} + /* Main RX/TX processing routines */ /* Display more error info */ @@ -5144,11 +5212,11 @@ static int mvpp2_tx_frag_process(struct mvpp2_port *port, struct sk_buff *skb, if (i == (skb_shinfo(skb)->nr_frags - 1)) { /* Last descriptor */ tx_desc->command = MVPP2_TXD_L_DESC; - mvpp2_txq_inc_put(txq_pcpu, skb); + mvpp2_txq_inc_put(txq_pcpu, skb, tx_desc); } else { /* Descriptor in the middle: Not First, Not Last */ tx_desc->command = 0; - mvpp2_txq_inc_put(txq_pcpu, NULL); + mvpp2_txq_inc_put(txq_pcpu, NULL, tx_desc); } } @@ -5214,12 +5282,12 @@ static int mvpp2_tx(struct sk_buff *skb, struct net_device *dev) /* First and Last descriptor */ tx_cmd |= MVPP2_TXD_F_DESC | MVPP2_TXD_L_DESC; tx_desc->command = tx_cmd; - mvpp2_txq_inc_put(txq_pcpu, skb); + mvpp2_txq_inc_put(txq_pcpu, skb, tx_desc); } else { /* First but not Last */ tx_cmd |= MVPP2_TXD_F_DESC | MVPP2_TXD_PADDING_DISABLE; tx_desc->command = tx_cmd; - mvpp2_txq_inc_put(txq_pcpu, NULL); + mvpp2_txq_inc_put(txq_pcpu, NULL, tx_desc); /* Continue with other skb fragments */ if (mvpp2_tx_frag_process(port, skb, aggr_txq, txq)) { @@ -5255,6 +5323,17 @@ out: dev_kfree_skb_any(skb); } + /* Finalize TX processing */ + if (txq_pcpu->count >= txq->done_pkts_coal) + mvpp2_txq_done(port, txq, txq_pcpu); + + /* Set the timer in case not all frags were processed */ + if (txq_pcpu->count <= frags && txq_pcpu->count > 0) { + struct mvpp2_port_pcpu *port_pcpu = this_cpu_ptr(port->pcpu); + + mvpp2_timer_set(port_pcpu); + } + return NETDEV_TX_OK; } @@ -5268,10 +5347,11 @@ static inline void mvpp2_cause_error(struct net_device *dev, int cause) netdev_err(dev, "tx fifo underrun error\n"); } -static void mvpp2_txq_done_percpu(void *arg) +static int mvpp2_poll(struct napi_struct *napi, int budget) { - struct mvpp2_port *port = arg; - u32 cause_rx_tx, cause_tx, cause_misc; + u32 cause_rx_tx, cause_rx, cause_misc; + int rx_done = 0; + struct mvpp2_port *port = netdev_priv(napi->dev); /* Rx/Tx cause register * @@ -5285,7 +5365,7 @@ static void mvpp2_txq_done_percpu(void *arg) */ cause_rx_tx = mvpp2_read(port->priv, MVPP2_ISR_RX_TX_CAUSE_REG(port->id)); - cause_tx = cause_rx_tx & MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_MASK; + cause_rx_tx &= ~MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_MASK; cause_misc = cause_rx_tx & MVPP2_CAUSE_MISC_SUM_MASK; if (cause_misc) { @@ -5297,26 +5377,6 @@ static void mvpp2_txq_done_percpu(void *arg) cause_rx_tx & ~MVPP2_CAUSE_MISC_SUM_MASK); } - /* Release TX descriptors */ - if (cause_tx) { - struct mvpp2_tx_queue *txq = mvpp2_get_tx_queue(port, cause_tx); - struct mvpp2_txq_pcpu *txq_pcpu = this_cpu_ptr(txq->pcpu); - - if (txq_pcpu->count) - mvpp2_txq_done(port, txq, txq_pcpu); - } -} - -static int mvpp2_poll(struct napi_struct *napi, int budget) -{ - u32 cause_rx_tx, cause_rx; - int rx_done = 0; - struct mvpp2_port *port = netdev_priv(napi->dev); - - on_each_cpu(mvpp2_txq_done_percpu, port, 1); - - cause_rx_tx = mvpp2_read(port->priv, - MVPP2_ISR_RX_TX_CAUSE_REG(port->id)); cause_rx = cause_rx_tx & MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK; /* Process RX packets */ @@ -5561,6 +5621,8 @@ err_cleanup_rxqs: static int mvpp2_stop(struct net_device *dev) { struct mvpp2_port *port = netdev_priv(dev); + struct mvpp2_port_pcpu *port_pcpu; + int cpu; mvpp2_stop_dev(port); mvpp2_phy_disconnect(port); @@ -5569,6 +5631,13 @@ static int mvpp2_stop(struct net_device *dev) on_each_cpu(mvpp2_interrupts_mask, port, 1); free_irq(port->irq, port); + for_each_present_cpu(cpu) { + port_pcpu = per_cpu_ptr(port->pcpu, cpu); + + hrtimer_cancel(&port_pcpu->tx_done_timer); + port_pcpu->timer_scheduled = false; + tasklet_kill(&port_pcpu->tx_done_tasklet); + } mvpp2_cleanup_rxqs(port); mvpp2_cleanup_txqs(port); @@ -5784,7 +5853,6 @@ static int mvpp2_ethtool_set_coalesce(struct net_device *dev, txq->done_pkts_coal = c->tx_max_coalesced_frames; } - on_each_cpu(mvpp2_tx_done_pkts_coal_set, port, 1); return 0; } @@ -6035,6 +6103,7 @@ static int mvpp2_port_probe(struct platform_device *pdev, { struct device_node *phy_node; struct mvpp2_port *port; + struct mvpp2_port_pcpu *port_pcpu; struct net_device *dev; struct resource *res; const char *dt_mac_addr; @@ -6044,7 +6113,7 @@ static int mvpp2_port_probe(struct platform_device *pdev, int features; int phy_mode; int priv_common_regs_num = 2; - int err, i; + int err, i, cpu; dev = alloc_etherdev_mqs(sizeof(struct mvpp2_port), txq_number, rxq_number); @@ -6135,6 +6204,24 @@ static int mvpp2_port_probe(struct platform_device *pdev, } mvpp2_port_power_up(port); + port->pcpu = alloc_percpu(struct mvpp2_port_pcpu); + if (!port->pcpu) { + err = -ENOMEM; + goto err_free_txq_pcpu; + } + + for_each_present_cpu(cpu) { + port_pcpu = per_cpu_ptr(port->pcpu, cpu); + + hrtimer_init(&port_pcpu->tx_done_timer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL_PINNED); + port_pcpu->tx_done_timer.function = mvpp2_hr_timer_cb; + port_pcpu->timer_scheduled = false; + + tasklet_init(&port_pcpu->tx_done_tasklet, mvpp2_tx_proc_cb, + (unsigned long)dev); + } + netif_napi_add(dev, &port->napi, mvpp2_poll, NAPI_POLL_WEIGHT); features = NETIF_F_SG | NETIF_F_IP_CSUM; dev->features = features | NETIF_F_RXCSUM; @@ -6144,7 +6231,7 @@ static int mvpp2_port_probe(struct platform_device *pdev, err = register_netdev(dev); if (err < 0) { dev_err(&pdev->dev, "failed to register netdev\n"); - goto err_free_txq_pcpu; + goto err_free_port_pcpu; } netdev_info(dev, "Using %s mac address %pM\n", mac_from, dev->dev_addr); @@ -6153,6 +6240,8 @@ static int mvpp2_port_probe(struct platform_device *pdev, priv->port_list[id] = port; return 0; +err_free_port_pcpu: + free_percpu(port->pcpu); err_free_txq_pcpu: for (i = 0; i < txq_number; i++) free_percpu(port->txqs[i]->pcpu); @@ -6171,6 +6260,7 @@ static void mvpp2_port_remove(struct mvpp2_port *port) int i; unregister_netdev(port->dev); + free_percpu(port->pcpu); free_percpu(port->stats); for (i = 0; i < txq_number; i++) free_percpu(port->txqs[i]->pcpu); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index afad529838de..06e3e1e54c35 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -391,6 +391,8 @@ static int handle_hca_cap(struct mlx5_core_dev *dev) /* disable cmdif checksum */ MLX5_SET(cmd_hca_cap, set_hca_cap, cmdif_checksum, 0); + MLX5_SET(cmd_hca_cap, set_hca_cap, log_uar_page_sz, PAGE_SHIFT - 12); + err = set_caps(dev, set_ctx, set_sz); query_ex: diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 3df51faf18ae..f790f61ea78a 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -4875,10 +4875,12 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_46: case RTL_GIGA_MAC_VER_47: case RTL_GIGA_MAC_VER_48: + RTL_W32(RxConfig, RX128_INT_EN | RX_DMA_BURST | RX_EARLY_OFF); + break; case RTL_GIGA_MAC_VER_49: case RTL_GIGA_MAC_VER_50: case RTL_GIGA_MAC_VER_51: - RTL_W32(RxConfig, RX128_INT_EN | RX_DMA_BURST | RX_EARLY_OFF); + RTL_W32(RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST | RX_EARLY_OFF); break; default: RTL_W32(RxConfig, RX128_INT_EN | RX_DMA_BURST); diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index 2d8578cade03..2e7f9a2834be 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -4821,6 +4821,7 @@ static void rocker_remove_ports(const struct rocker *rocker) rocker_port_ig_tbl(rocker_port, SWITCHDEV_TRANS_NONE, ROCKER_OP_FLAG_REMOVE); unregister_netdev(rocker_port->dev); + free_netdev(rocker_port->dev); } kfree(rocker->ports); } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c index 7e3129e7f143..f0e4bb4e3ec5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c @@ -42,7 +42,7 @@ #define NSS_COMMON_CLK_DIV_MASK 0x7f #define NSS_COMMON_CLK_SRC_CTRL 0x14 -#define NSS_COMMON_CLK_SRC_CTRL_OFFSET(x) (1 << x) +#define NSS_COMMON_CLK_SRC_CTRL_OFFSET(x) (x) /* Mode is coded on 1 bit but is different depending on the MAC ID: * MAC0: QSGMII=0 RGMII=1 * MAC1: QSGMII=0 SGMII=0 RGMII=1 @@ -291,7 +291,7 @@ static void *ipq806x_gmac_setup(struct platform_device *pdev) /* Configure the clock src according to the mode */ regmap_read(gmac->nss_common, NSS_COMMON_CLK_SRC_CTRL, &val); - val &= ~NSS_COMMON_CLK_SRC_CTRL_OFFSET(gmac->id); + val &= ~(1 << NSS_COMMON_CLK_SRC_CTRL_OFFSET(gmac->id)); switch (gmac->phy_mode) { case PHY_INTERFACE_MODE_RGMII: val |= NSS_COMMON_CLK_SRC_CTRL_RGMII(gmac->id) << diff --git a/drivers/net/ethernet/ti/netcp.h b/drivers/net/ethernet/ti/netcp.h index a8a730641bbb..bb1bb72121c0 100644 --- a/drivers/net/ethernet/ti/netcp.h +++ b/drivers/net/ethernet/ti/netcp.h @@ -85,7 +85,6 @@ struct netcp_intf { struct list_head rxhook_list_head; unsigned int rx_queue_id; void *rx_fdq[KNAV_DMA_FDQ_PER_CHAN]; - u32 rx_buffer_sizes[KNAV_DMA_FDQ_PER_CHAN]; struct napi_struct rx_napi; struct napi_struct tx_napi; diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index 9749dfd78c43..4755838c6137 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -34,6 +34,7 @@ #define NETCP_SOP_OFFSET (NET_IP_ALIGN + NET_SKB_PAD) #define NETCP_NAPI_WEIGHT 64 #define NETCP_TX_TIMEOUT (5 * HZ) +#define NETCP_PACKET_SIZE (ETH_FRAME_LEN + ETH_FCS_LEN) #define NETCP_MIN_PACKET_SIZE ETH_ZLEN #define NETCP_MAX_MCAST_ADDR 16 @@ -804,30 +805,28 @@ static void netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq) if (likely(fdq == 0)) { unsigned int primary_buf_len; /* Allocate a primary receive queue entry */ - buf_len = netcp->rx_buffer_sizes[0] + NETCP_SOP_OFFSET; + buf_len = NETCP_PACKET_SIZE + NETCP_SOP_OFFSET; primary_buf_len = SKB_DATA_ALIGN(buf_len) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - if (primary_buf_len <= PAGE_SIZE) { - bufptr = netdev_alloc_frag(primary_buf_len); - pad[1] = primary_buf_len; - } else { - bufptr = kmalloc(primary_buf_len, GFP_ATOMIC | - GFP_DMA32 | __GFP_COLD); - pad[1] = 0; - } + bufptr = netdev_alloc_frag(primary_buf_len); + pad[1] = primary_buf_len; if (unlikely(!bufptr)) { - dev_warn_ratelimited(netcp->ndev_dev, "Primary RX buffer alloc failed\n"); + dev_warn_ratelimited(netcp->ndev_dev, + "Primary RX buffer alloc failed\n"); goto fail; } dma = dma_map_single(netcp->dev, bufptr, buf_len, DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(netcp->dev, dma))) + goto fail; + pad[0] = (u32)bufptr; } else { /* Allocate a secondary receive queue entry */ - page = alloc_page(GFP_ATOMIC | GFP_DMA32 | __GFP_COLD); + page = alloc_page(GFP_ATOMIC | GFP_DMA | __GFP_COLD); if (unlikely(!page)) { dev_warn_ratelimited(netcp->ndev_dev, "Secondary page alloc failed\n"); goto fail; @@ -1010,7 +1009,7 @@ netcp_tx_map_skb(struct sk_buff *skb, struct netcp_intf *netcp) /* Map the linear buffer */ dma_addr = dma_map_single(dev, skb->data, pkt_len, DMA_TO_DEVICE); - if (unlikely(!dma_addr)) { + if (unlikely(dma_mapping_error(dev, dma_addr))) { dev_err(netcp->ndev_dev, "Failed to map skb buffer\n"); return NULL; } @@ -1546,8 +1545,8 @@ static int netcp_setup_navigator_resources(struct net_device *ndev) knav_queue_disable_notify(netcp->rx_queue); /* open Rx FDQs */ - for (i = 0; i < KNAV_DMA_FDQ_PER_CHAN && - netcp->rx_queue_depths[i] && netcp->rx_buffer_sizes[i]; ++i) { + for (i = 0; i < KNAV_DMA_FDQ_PER_CHAN && netcp->rx_queue_depths[i]; + ++i) { snprintf(name, sizeof(name), "rx-fdq-%s-%d", ndev->name, i); netcp->rx_fdq[i] = knav_queue_open(name, KNAV_QUEUE_GP, 0); if (IS_ERR_OR_NULL(netcp->rx_fdq[i])) { @@ -1941,14 +1940,6 @@ static int netcp_create_interface(struct netcp_device *netcp_device, netcp->rx_queue_depths[0] = 128; } - ret = of_property_read_u32_array(node_interface, "rx-buffer-size", - netcp->rx_buffer_sizes, - KNAV_DMA_FDQ_PER_CHAN); - if (ret) { - dev_err(dev, "missing \"rx-buffer-size\" parameter\n"); - netcp->rx_buffer_sizes[0] = 1536; - } - ret = of_property_read_u32_array(node_interface, "rx-pool", temp, 2); if (ret < 0) { dev_err(dev, "missing \"rx-pool\" parameter\n"); diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c index 2ffbf13471d0..216bfd350169 100644 --- a/drivers/net/hamradio/mkiss.c +++ b/drivers/net/hamradio/mkiss.c @@ -728,11 +728,12 @@ static int mkiss_open(struct tty_struct *tty) dev->type = ARPHRD_AX25; /* Perform the low-level AX25 initialization. */ - if ((err = ax_open(ax->dev))) { + err = ax_open(ax->dev); + if (err) goto out_free_netdev; - } - if (register_netdev(dev)) + err = register_netdev(dev); + if (err) goto out_free_buffers; /* after register_netdev() - because else printk smashes the kernel */ diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 7fbca37a1adf..237f8e5e493d 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1756,9 +1756,9 @@ static int virtnet_probe(struct virtio_device *vdev) /* Do we support "hardware" checksums? */ if (virtio_has_feature(vdev, VIRTIO_NET_F_CSUM)) { /* This opens up the world of extra features. */ - dev->hw_features |= NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST; + dev->hw_features |= NETIF_F_HW_CSUM | NETIF_F_SG; if (csum) - dev->features |= NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST; + dev->features |= NETIF_F_HW_CSUM | NETIF_F_SG; if (virtio_has_feature(vdev, VIRTIO_NET_F_GSO)) { dev->hw_features |= NETIF_F_TSO | NETIF_F_UFO diff --git a/drivers/net/wan/cosa.c b/drivers/net/wan/cosa.c index 7193b7304fdd..848ea6a399f2 100644 --- a/drivers/net/wan/cosa.c +++ b/drivers/net/wan/cosa.c @@ -589,7 +589,8 @@ static int cosa_probe(int base, int irq, int dma) chan->netdev->base_addr = chan->cosa->datareg; chan->netdev->irq = chan->cosa->irq; chan->netdev->dma = chan->cosa->dma; - if (register_hdlc_device(chan->netdev)) { + err = register_hdlc_device(chan->netdev); + if (err) { netdev_warn(chan->netdev, "register_hdlc_device() failed\n"); free_netdev(chan->netdev); diff --git a/drivers/net/wireless/b43/tables_nphy.c b/drivers/net/wireless/b43/tables_nphy.c index 25d1cbd34306..b2f0d245bcf3 100644 --- a/drivers/net/wireless/b43/tables_nphy.c +++ b/drivers/net/wireless/b43/tables_nphy.c @@ -3728,7 +3728,7 @@ const u32 *b43_nphy_get_tx_gain_table(struct b43_wldev *dev) switch (phy->rev) { case 6: case 5: - if (sprom->fem.ghz5.extpa_gain == 3) + if (sprom->fem.ghz2.extpa_gain == 3) return b43_ntab_tx_gain_epa_rev3_hi_pwr_2g; /* fall through */ case 4: diff --git a/drivers/net/wireless/iwlwifi/mvm/scan.c b/drivers/net/wireless/iwlwifi/mvm/scan.c index 5000bfcded61..5514ad6d4e54 100644 --- a/drivers/net/wireless/iwlwifi/mvm/scan.c +++ b/drivers/net/wireless/iwlwifi/mvm/scan.c @@ -1023,7 +1023,7 @@ static void iwl_mvm_scan_umac_dwell(struct iwl_mvm *mvm, cmd->scan_priority = iwl_mvm_scan_priority(mvm, IWL_SCAN_PRIORITY_EXT_6); - if (iwl_mvm_scan_total_iterations(params) == 0) + if (iwl_mvm_scan_total_iterations(params) == 1) cmd->ooc_priority = iwl_mvm_scan_priority(mvm, IWL_SCAN_PRIORITY_EXT_6); else diff --git a/drivers/net/wireless/iwlwifi/pcie/trans.c b/drivers/net/wireless/iwlwifi/pcie/trans.c index 6203c4ad9bba..9e144e71da0b 100644 --- a/drivers/net/wireless/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/iwlwifi/pcie/trans.c @@ -478,10 +478,16 @@ static void iwl_pcie_apm_stop(struct iwl_trans *trans, bool op_mode_leave) if (trans->cfg->device_family == IWL_DEVICE_FAMILY_7000) iwl_set_bits_prph(trans, APMG_PCIDEV_STT_REG, APMG_PCIDEV_STT_VAL_WAKE_ME); - else if (trans->cfg->device_family == IWL_DEVICE_FAMILY_8000) + else if (trans->cfg->device_family == IWL_DEVICE_FAMILY_8000) { + iwl_set_bit(trans, CSR_DBG_LINK_PWR_MGMT_REG, + CSR_RESET_LINK_PWR_MGMT_DISABLED); iwl_set_bit(trans, CSR_HW_IF_CONFIG_REG, CSR_HW_IF_CONFIG_REG_PREPARE | CSR_HW_IF_CONFIG_REG_ENABLE_PME); + mdelay(1); + iwl_clear_bit(trans, CSR_DBG_LINK_PWR_MGMT_REG, + CSR_RESET_LINK_PWR_MGMT_DISABLED); + } mdelay(5); } @@ -575,6 +581,10 @@ static int iwl_pcie_prepare_card_hw(struct iwl_trans *trans) if (ret >= 0) return 0; + iwl_set_bit(trans, CSR_DBG_LINK_PWR_MGMT_REG, + CSR_RESET_LINK_PWR_MGMT_DISABLED); + msleep(1); + for (iter = 0; iter < 10; iter++) { /* If HW is not ready, prepare the conditions to check again */ iwl_set_bit(trans, CSR_HW_IF_CONFIG_REG, @@ -582,8 +592,10 @@ static int iwl_pcie_prepare_card_hw(struct iwl_trans *trans) do { ret = iwl_pcie_set_hw_ready(trans); - if (ret >= 0) - return 0; + if (ret >= 0) { + ret = 0; + goto out; + } usleep_range(200, 1000); t += 200; @@ -593,6 +605,10 @@ static int iwl_pcie_prepare_card_hw(struct iwl_trans *trans) IWL_ERR(trans, "Couldn't prepare the card\n"); +out: + iwl_clear_bit(trans, CSR_DBG_LINK_PWR_MGMT_REG, + CSR_RESET_LINK_PWR_MGMT_DISABLED); + return ret; } diff --git a/drivers/net/wireless/iwlwifi/pcie/tx.c b/drivers/net/wireless/iwlwifi/pcie/tx.c index 2b86c2135de3..607acb53c847 100644 --- a/drivers/net/wireless/iwlwifi/pcie/tx.c +++ b/drivers/net/wireless/iwlwifi/pcie/tx.c @@ -1875,8 +1875,19 @@ int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb, /* start timer if queue currently empty */ if (q->read_ptr == q->write_ptr) { - if (txq->wd_timeout) - mod_timer(&txq->stuck_timer, jiffies + txq->wd_timeout); + if (txq->wd_timeout) { + /* + * If the TXQ is active, then set the timer, if not, + * set the timer in remainder so that the timer will + * be armed with the right value when the station will + * wake up. + */ + if (!txq->frozen) + mod_timer(&txq->stuck_timer, + jiffies + txq->wd_timeout); + else + txq->frozen_expiry_remainder = txq->wd_timeout; + } IWL_DEBUG_RPM(trans, "Q: %d first tx - take ref\n", q->id); iwl_trans_pcie_ref(trans); } diff --git a/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c b/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c index b6cc9ff47fc2..1c6788aecc62 100644 --- a/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c +++ b/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c @@ -172,6 +172,7 @@ static int rsi_load_ta_instructions(struct rsi_common *common) (struct rsi_91x_sdiodev *)adapter->rsi_dev; u32 len; u32 num_blocks; + const u8 *fw; const struct firmware *fw_entry = NULL; u32 block_size = dev->tx_blk_size; int status = 0; @@ -200,6 +201,10 @@ static int rsi_load_ta_instructions(struct rsi_common *common) return status; } + /* Copy firmware into DMA-accessible memory */ + fw = kmemdup(fw_entry->data, fw_entry->size, GFP_KERNEL); + if (!fw) + return -ENOMEM; len = fw_entry->size; if (len % 4) @@ -210,7 +215,8 @@ static int rsi_load_ta_instructions(struct rsi_common *common) rsi_dbg(INIT_ZONE, "%s: Instruction size:%d\n", __func__, len); rsi_dbg(INIT_ZONE, "%s: num blocks: %d\n", __func__, num_blocks); - status = rsi_copy_to_card(common, fw_entry->data, len, num_blocks); + status = rsi_copy_to_card(common, fw, len, num_blocks); + kfree(fw); release_firmware(fw_entry); return status; } diff --git a/drivers/net/wireless/rsi/rsi_91x_usb_ops.c b/drivers/net/wireless/rsi/rsi_91x_usb_ops.c index 1106ce76707e..30c2cf7fa93b 100644 --- a/drivers/net/wireless/rsi/rsi_91x_usb_ops.c +++ b/drivers/net/wireless/rsi/rsi_91x_usb_ops.c @@ -146,7 +146,10 @@ static int rsi_load_ta_instructions(struct rsi_common *common) return status; } + /* Copy firmware into DMA-accessible memory */ fw = kmemdup(fw_entry->data, fw_entry->size, GFP_KERNEL); + if (!fw) + return -ENOMEM; len = fw_entry->size; if (len % 4) @@ -158,6 +161,7 @@ static int rsi_load_ta_instructions(struct rsi_common *common) rsi_dbg(INIT_ZONE, "%s: num blocks: %d\n", __func__, num_blocks); status = rsi_copy_to_card(common, fw, len, num_blocks); + kfree(fw); release_firmware(fw_entry); return status; } diff --git a/drivers/net/wireless/rtlwifi/core.c b/drivers/net/wireless/rtlwifi/core.c index 3b3a88b53b11..585d0883c7e5 100644 --- a/drivers/net/wireless/rtlwifi/core.c +++ b/drivers/net/wireless/rtlwifi/core.c @@ -1015,9 +1015,12 @@ static void send_beacon_frame(struct ieee80211_hw *hw, { struct rtl_priv *rtlpriv = rtl_priv(hw); struct sk_buff *skb = ieee80211_beacon_get(hw, vif); + struct rtl_tcb_desc tcb_desc; - if (skb) - rtlpriv->intf_ops->adapter_tx(hw, NULL, skb, NULL); + if (skb) { + memset(&tcb_desc, 0, sizeof(struct rtl_tcb_desc)); + rtlpriv->intf_ops->adapter_tx(hw, NULL, skb, &tcb_desc); + } } static void rtl_op_bss_info_changed(struct ieee80211_hw *hw, diff --git a/drivers/net/wireless/rtlwifi/rtl8723be/sw.c b/drivers/net/wireless/rtlwifi/rtl8723be/sw.c index 1017f02d7bf7..7bf88d9dcdc3 100644 --- a/drivers/net/wireless/rtlwifi/rtl8723be/sw.c +++ b/drivers/net/wireless/rtlwifi/rtl8723be/sw.c @@ -385,6 +385,7 @@ module_param_named(debug, rtl8723be_mod_params.debug, int, 0444); module_param_named(ips, rtl8723be_mod_params.inactiveps, bool, 0444); module_param_named(swlps, rtl8723be_mod_params.swctrl_lps, bool, 0444); module_param_named(fwlps, rtl8723be_mod_params.fwctrl_lps, bool, 0444); +module_param_named(msi, rtl8723be_mod_params.msi_support, bool, 0444); module_param_named(disable_watchdog, rtl8723be_mod_params.disable_watchdog, bool, 0444); MODULE_PARM_DESC(swenc, "Set to 1 for software crypto (default 0)\n"); diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 1a83e190fc15..28577a31549d 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -61,6 +61,12 @@ void xenvif_skb_zerocopy_prepare(struct xenvif_queue *queue, void xenvif_skb_zerocopy_complete(struct xenvif_queue *queue) { atomic_dec(&queue->inflight_packets); + + /* Wake the dealloc thread _after_ decrementing inflight_packets so + * that if kthread_stop() has already been called, the dealloc thread + * does not wait forever with nothing to wake it. + */ + wake_up(&queue->dealloc_wq); } int xenvif_schedulable(struct xenvif *vif) diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 7d50711476fe..3f44b522b831 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -810,23 +810,17 @@ static inline struct sk_buff *xenvif_alloc_skb(unsigned int size) static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif_queue *queue, struct sk_buff *skb, struct xen_netif_tx_request *txp, - struct gnttab_map_grant_ref *gop) + struct gnttab_map_grant_ref *gop, + unsigned int frag_overflow, + struct sk_buff *nskb) { struct skb_shared_info *shinfo = skb_shinfo(skb); skb_frag_t *frags = shinfo->frags; u16 pending_idx = XENVIF_TX_CB(skb)->pending_idx; int start; pending_ring_idx_t index; - unsigned int nr_slots, frag_overflow = 0; + unsigned int nr_slots; - /* At this point shinfo->nr_frags is in fact the number of - * slots, which can be as large as XEN_NETBK_LEGACY_SLOTS_MAX. - */ - if (shinfo->nr_frags > MAX_SKB_FRAGS) { - frag_overflow = shinfo->nr_frags - MAX_SKB_FRAGS; - BUG_ON(frag_overflow > MAX_SKB_FRAGS); - shinfo->nr_frags = MAX_SKB_FRAGS; - } nr_slots = shinfo->nr_frags; /* Skip first skb fragment if it is on same page as header fragment. */ @@ -841,13 +835,6 @@ static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif_queue *que } if (frag_overflow) { - struct sk_buff *nskb = xenvif_alloc_skb(0); - if (unlikely(nskb == NULL)) { - if (net_ratelimit()) - netdev_err(queue->vif->dev, - "Can't allocate the frag_list skb.\n"); - return NULL; - } shinfo = skb_shinfo(nskb); frags = shinfo->frags; @@ -1175,9 +1162,10 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, unsigned *copy_ops, unsigned *map_ops) { - struct gnttab_map_grant_ref *gop = queue->tx_map_ops, *request_gop; - struct sk_buff *skb; + struct gnttab_map_grant_ref *gop = queue->tx_map_ops; + struct sk_buff *skb, *nskb; int ret; + unsigned int frag_overflow; while (skb_queue_len(&queue->tx_queue) < budget) { struct xen_netif_tx_request txreq; @@ -1265,6 +1253,29 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, break; } + skb_shinfo(skb)->nr_frags = ret; + if (data_len < txreq.size) + skb_shinfo(skb)->nr_frags++; + /* At this point shinfo->nr_frags is in fact the number of + * slots, which can be as large as XEN_NETBK_LEGACY_SLOTS_MAX. + */ + frag_overflow = 0; + nskb = NULL; + if (skb_shinfo(skb)->nr_frags > MAX_SKB_FRAGS) { + frag_overflow = skb_shinfo(skb)->nr_frags - MAX_SKB_FRAGS; + BUG_ON(frag_overflow > MAX_SKB_FRAGS); + skb_shinfo(skb)->nr_frags = MAX_SKB_FRAGS; + nskb = xenvif_alloc_skb(0); + if (unlikely(nskb == NULL)) { + kfree_skb(skb); + xenvif_tx_err(queue, &txreq, idx); + if (net_ratelimit()) + netdev_err(queue->vif->dev, + "Can't allocate the frag_list skb.\n"); + break; + } + } + if (extras[XEN_NETIF_EXTRA_TYPE_GSO - 1].type) { struct xen_netif_extra_info *gso; gso = &extras[XEN_NETIF_EXTRA_TYPE_GSO - 1]; @@ -1272,6 +1283,7 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, if (xenvif_set_skb_gso(queue->vif, skb, gso)) { /* Failure in xenvif_set_skb_gso is fatal. */ kfree_skb(skb); + kfree_skb(nskb); break; } } @@ -1294,9 +1306,7 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, (*copy_ops)++; - skb_shinfo(skb)->nr_frags = ret; if (data_len < txreq.size) { - skb_shinfo(skb)->nr_frags++; frag_set_pending_idx(&skb_shinfo(skb)->frags[0], pending_idx); xenvif_tx_create_map_op(queue, pending_idx, &txreq, gop); @@ -1310,13 +1320,8 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, queue->pending_cons++; - request_gop = xenvif_get_requests(queue, skb, txfrags, gop); - if (request_gop == NULL) { - kfree_skb(skb); - xenvif_tx_err(queue, &txreq, idx); - break; - } - gop = request_gop; + gop = xenvif_get_requests(queue, skb, txfrags, gop, + frag_overflow, nskb); __skb_queue_tail(&queue->tx_queue, skb); @@ -1536,7 +1541,6 @@ void xenvif_zerocopy_callback(struct ubuf_info *ubuf, bool zerocopy_success) smp_wmb(); queue->dealloc_prod++; } while (ubuf); - wake_up(&queue->dealloc_wq); spin_unlock_irqrestore(&queue->callback_lock, flags); if (likely(zerocopy_success)) diff --git a/drivers/scsi/libfc/fc_exch.c b/drivers/scsi/libfc/fc_exch.c index 1b3a09473452..30f9ef0c0d4f 100644 --- a/drivers/scsi/libfc/fc_exch.c +++ b/drivers/scsi/libfc/fc_exch.c @@ -733,8 +733,6 @@ static bool fc_invoke_resp(struct fc_exch *ep, struct fc_seq *sp, if (resp) { resp(sp, fp, arg); res = true; - } else if (!IS_ERR(fp)) { - fc_frame_free(fp); } spin_lock_bh(&ep->ex_lock); @@ -1596,7 +1594,8 @@ static void fc_exch_recv_seq_resp(struct fc_exch_mgr *mp, struct fc_frame *fp) * If new exch resp handler is valid then call that * first. */ - fc_invoke_resp(ep, sp, fp); + if (!fc_invoke_resp(ep, sp, fp)) + fc_frame_free(fp); fc_exch_release(ep); return; @@ -1695,7 +1694,8 @@ static void fc_exch_abts_resp(struct fc_exch *ep, struct fc_frame *fp) fc_exch_hold(ep); if (!rc) fc_exch_delete(ep); - fc_invoke_resp(ep, sp, fp); + if (!fc_invoke_resp(ep, sp, fp)) + fc_frame_free(fp); if (has_rec) fc_exch_timer_set(ep, ep->r_a_tov); fc_exch_release(ep); diff --git a/drivers/scsi/libfc/fc_fcp.c b/drivers/scsi/libfc/fc_fcp.c index c6795941b45d..2d5909c4685c 100644 --- a/drivers/scsi/libfc/fc_fcp.c +++ b/drivers/scsi/libfc/fc_fcp.c @@ -1039,11 +1039,26 @@ restart: fc_fcp_pkt_hold(fsp); spin_unlock_irqrestore(&si->scsi_queue_lock, flags); - if (!fc_fcp_lock_pkt(fsp)) { + spin_lock_bh(&fsp->scsi_pkt_lock); + if (!(fsp->state & FC_SRB_COMPL)) { + fsp->state |= FC_SRB_COMPL; + /* + * TODO: dropping scsi_pkt_lock and then reacquiring + * again around fc_fcp_cleanup_cmd() is required, + * since fc_fcp_cleanup_cmd() calls into + * fc_seq_set_resp() and that func preempts cpu using + * schedule. May be schedule and related code should be + * removed instead of unlocking here to avoid scheduling + * while atomic bug. + */ + spin_unlock_bh(&fsp->scsi_pkt_lock); + fc_fcp_cleanup_cmd(fsp, error); + + spin_lock_bh(&fsp->scsi_pkt_lock); fc_io_compl(fsp); - fc_fcp_unlock_pkt(fsp); } + spin_unlock_bh(&fsp->scsi_pkt_lock); fc_fcp_pkt_release(fsp); spin_lock_irqsave(&si->scsi_queue_lock, flags); diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index 8053f24f0349..98d9bb6ff725 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -2941,10 +2941,10 @@ void iscsi_conn_teardown(struct iscsi_cls_conn *cls_conn) { struct iscsi_conn *conn = cls_conn->dd_data; struct iscsi_session *session = conn->session; - unsigned long flags; del_timer_sync(&conn->transport_timer); + mutex_lock(&session->eh_mutex); spin_lock_bh(&session->frwd_lock); conn->c_stage = ISCSI_CONN_CLEANUP_WAIT; if (session->leadconn == conn) { @@ -2956,28 +2956,6 @@ void iscsi_conn_teardown(struct iscsi_cls_conn *cls_conn) } spin_unlock_bh(&session->frwd_lock); - /* - * Block until all in-progress commands for this connection - * time out or fail. - */ - for (;;) { - spin_lock_irqsave(session->host->host_lock, flags); - if (!atomic_read(&session->host->host_busy)) { /* OK for ERL == 0 */ - spin_unlock_irqrestore(session->host->host_lock, flags); - break; - } - spin_unlock_irqrestore(session->host->host_lock, flags); - msleep_interruptible(500); - iscsi_conn_printk(KERN_INFO, conn, "iscsi conn_destroy(): " - "host_busy %d host_failed %d\n", - atomic_read(&session->host->host_busy), - session->host->host_failed); - /* - * force eh_abort() to unblock - */ - wake_up(&conn->ehwait); - } - /* flush queued up work because we free the connection below */ iscsi_suspend_tx(conn); @@ -2994,6 +2972,7 @@ void iscsi_conn_teardown(struct iscsi_cls_conn *cls_conn) if (session->leadconn == conn) session->leadconn = NULL; spin_unlock_bh(&session->frwd_lock); + mutex_unlock(&session->eh_mutex); iscsi_destroy_conn(cls_conn); } diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 3b2fcb4fada0..a20da8c25b4f 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -2770,9 +2770,9 @@ static int sd_revalidate_disk(struct gendisk *disk) max_xfer = sdkp->max_xfer_blocks; max_xfer <<= ilog2(sdp->sector_size) - 9; - max_xfer = min_not_zero(queue_max_hw_sectors(sdkp->disk->queue), - max_xfer); - blk_queue_max_hw_sectors(sdkp->disk->queue, max_xfer); + sdkp->disk->queue->limits.max_sectors = + min_not_zero(queue_max_hw_sectors(sdkp->disk->queue), max_xfer); + set_capacity(disk, sdkp->capacity); sd_config_write_same(sdkp); kfree(buffer); diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 1495eccb1617..96093ae369a5 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -452,12 +452,10 @@ static void xen_free_irq(unsigned irq) irq_free_desc(irq); } -static void xen_evtchn_close(unsigned int port, unsigned int cpu) +static void xen_evtchn_close(unsigned int port) { struct evtchn_close close; - xen_evtchn_op_close(port, cpu); - close.port = port; if (HYPERVISOR_event_channel_op(EVTCHNOP_close, &close) != 0) BUG(); @@ -546,7 +544,7 @@ out: err: pr_err("irq%d: Failed to set port to irq mapping (%d)\n", irq, rc); - xen_evtchn_close(evtchn, NR_CPUS); + xen_evtchn_close(evtchn); return 0; } @@ -567,7 +565,7 @@ static void shutdown_pirq(struct irq_data *data) return; mask_evtchn(evtchn); - xen_evtchn_close(evtchn, cpu_from_evtchn(evtchn)); + xen_evtchn_close(evtchn); xen_irq_info_cleanup(info); } @@ -611,7 +609,7 @@ static void __unbind_from_irq(unsigned int irq) if (VALID_EVTCHN(evtchn)) { unsigned int cpu = cpu_from_irq(irq); - xen_evtchn_close(evtchn, cpu); + xen_evtchn_close(evtchn); switch (type_from_irq(irq)) { case IRQT_VIRQ: diff --git a/drivers/xen/events/events_fifo.c b/drivers/xen/events/events_fifo.c index 6df8aac966b9..ed673e1acd61 100644 --- a/drivers/xen/events/events_fifo.c +++ b/drivers/xen/events/events_fifo.c @@ -255,12 +255,6 @@ static void evtchn_fifo_unmask(unsigned port) } } -static bool evtchn_fifo_is_linked(unsigned port) -{ - event_word_t *word = event_word_from_port(port); - return sync_test_bit(EVTCHN_FIFO_BIT(LINKED, word), BM(word)); -} - static uint32_t clear_linked(volatile event_word_t *word) { event_word_t new, old, w; @@ -287,8 +281,7 @@ static void handle_irq_for_port(unsigned port) static void consume_one_event(unsigned cpu, struct evtchn_fifo_control_block *control_block, - unsigned priority, unsigned long *ready, - bool drop) + unsigned priority, unsigned long *ready) { struct evtchn_fifo_queue *q = &per_cpu(cpu_queue, cpu); uint32_t head; @@ -320,15 +313,13 @@ static void consume_one_event(unsigned cpu, if (head == 0) clear_bit(priority, ready); - if (evtchn_fifo_is_pending(port) && !evtchn_fifo_is_masked(port)) { - if (likely(!drop)) - handle_irq_for_port(port); - } + if (evtchn_fifo_is_pending(port) && !evtchn_fifo_is_masked(port)) + handle_irq_for_port(port); q->head[priority] = head; } -static void __evtchn_fifo_handle_events(unsigned cpu, bool drop) +static void evtchn_fifo_handle_events(unsigned cpu) { struct evtchn_fifo_control_block *control_block; unsigned long ready; @@ -340,16 +331,11 @@ static void __evtchn_fifo_handle_events(unsigned cpu, bool drop) while (ready) { q = find_first_bit(&ready, EVTCHN_FIFO_MAX_QUEUES); - consume_one_event(cpu, control_block, q, &ready, drop); + consume_one_event(cpu, control_block, q, &ready); ready |= xchg(&control_block->ready, 0); } } -static void evtchn_fifo_handle_events(unsigned cpu) -{ - __evtchn_fifo_handle_events(cpu, false); -} - static void evtchn_fifo_resume(void) { unsigned cpu; @@ -385,26 +371,6 @@ static void evtchn_fifo_resume(void) event_array_pages = 0; } -static void evtchn_fifo_close(unsigned port, unsigned int cpu) -{ - if (cpu == NR_CPUS) - return; - - get_online_cpus(); - if (cpu_online(cpu)) { - if (WARN_ON(irqs_disabled())) - goto out; - - while (evtchn_fifo_is_linked(port)) - cpu_relax(); - } else { - __evtchn_fifo_handle_events(cpu, true); - } - -out: - put_online_cpus(); -} - static const struct evtchn_ops evtchn_ops_fifo = { .max_channels = evtchn_fifo_max_channels, .nr_channels = evtchn_fifo_nr_channels, @@ -418,7 +384,6 @@ static const struct evtchn_ops evtchn_ops_fifo = { .unmask = evtchn_fifo_unmask, .handle_events = evtchn_fifo_handle_events, .resume = evtchn_fifo_resume, - .close = evtchn_fifo_close, }; static int evtchn_fifo_alloc_control_block(unsigned cpu) diff --git a/drivers/xen/events/events_internal.h b/drivers/xen/events/events_internal.h index d18e12315ec0..50c2050a1e32 100644 --- a/drivers/xen/events/events_internal.h +++ b/drivers/xen/events/events_internal.h @@ -68,7 +68,6 @@ struct evtchn_ops { bool (*test_and_set_mask)(unsigned port); void (*mask)(unsigned port); void (*unmask)(unsigned port); - void (*close)(unsigned port, unsigned cpu); void (*handle_events)(unsigned cpu); void (*resume)(void); @@ -146,12 +145,6 @@ static inline void xen_evtchn_resume(void) evtchn_ops->resume(); } -static inline void xen_evtchn_op_close(unsigned port, unsigned cpu) -{ - if (evtchn_ops->close) - return evtchn_ops->close(port, cpu); -} - void xen_evtchn_2l_init(void); int xen_evtchn_fifo_init(void); diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c index 9ad327238ba9..e30353575d5d 100644 --- a/drivers/xen/xenbus/xenbus_client.c +++ b/drivers/xen/xenbus/xenbus_client.c @@ -814,8 +814,10 @@ static int xenbus_unmap_ring_vfree_hvm(struct xenbus_device *dev, void *vaddr) rv = xenbus_unmap_ring(dev, node->handles, node->nr_handles, addrs); - if (!rv) + if (!rv) { vunmap(vaddr); + free_xenballooned_pages(node->nr_handles, node->hvm.pages); + } else WARN(1, "Leaking %p, size %u page(s)\n", vaddr, node->nr_handles); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index f5021fcb154e..a8ab8f5ef38e 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1638,9 +1638,7 @@ static void do_async_commit(struct work_struct *work) * Tell lockdep about it. */ if (ac->newtrans->type & __TRANS_FREEZABLE) - rwsem_acquire_read( - &ac->root->fs_info->sb->s_writers.lock_map[SB_FREEZE_FS-1], - 0, 1, _THIS_IP_); + __sb_writers_acquired(ac->root->fs_info->sb, SB_FREEZE_FS); current->journal_info = ac->newtrans; @@ -1679,9 +1677,7 @@ int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans, * async commit thread will be the one to unlock it. */ if (ac->newtrans->type & __TRANS_FREEZABLE) - rwsem_release( - &root->fs_info->sb->s_writers.lock_map[SB_FREEZE_FS-1], - 1, _THIS_IP_); + __sb_writers_release(root->fs_info->sb, SB_FREEZE_FS); schedule_work(&ac->work); diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 80cc1b35d460..ebb5e37455a0 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -2246,7 +2246,15 @@ static long fuse_dev_ioctl(struct file *file, unsigned int cmd, err = -EINVAL; if (old) { - struct fuse_dev *fud = fuse_get_dev(old); + struct fuse_dev *fud = NULL; + + /* + * Check against file->f_op because CUSE + * uses the same ioctl handler. + */ + if (old->f_op == file->f_op && + old->f_cred->user_ns == file->f_cred->user_ns) + fud = fuse_get_dev(old); if (fud) { mutex_lock(&fuse_mutex); diff --git a/fs/super.c b/fs/super.c index fd427ec0b372..954aeb80e202 100644 --- a/fs/super.c +++ b/fs/super.c @@ -135,6 +135,24 @@ static unsigned long super_cache_count(struct shrinker *shrink, return total_objects; } +static void destroy_super_work(struct work_struct *work) +{ + struct super_block *s = container_of(work, struct super_block, + destroy_work); + int i; + + for (i = 0; i < SB_FREEZE_LEVELS; i++) + percpu_free_rwsem(&s->s_writers.rw_sem[i]); + kfree(s); +} + +static void destroy_super_rcu(struct rcu_head *head) +{ + struct super_block *s = container_of(head, struct super_block, rcu); + INIT_WORK(&s->destroy_work, destroy_super_work); + schedule_work(&s->destroy_work); +} + /** * destroy_super - frees a superblock * @s: superblock to free @@ -143,16 +161,13 @@ static unsigned long super_cache_count(struct shrinker *shrink, */ static void destroy_super(struct super_block *s) { - int i; list_lru_destroy(&s->s_dentry_lru); list_lru_destroy(&s->s_inode_lru); - for (i = 0; i < SB_FREEZE_LEVELS; i++) - percpu_counter_destroy(&s->s_writers.counter[i]); security_sb_free(s); WARN_ON(!list_empty(&s->s_mounts)); kfree(s->s_subtype); kfree(s->s_options); - kfree_rcu(s, rcu); + call_rcu(&s->rcu, destroy_super_rcu); } /** @@ -178,13 +193,11 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags) goto fail; for (i = 0; i < SB_FREEZE_LEVELS; i++) { - if (percpu_counter_init(&s->s_writers.counter[i], 0, - GFP_KERNEL) < 0) + if (__percpu_init_rwsem(&s->s_writers.rw_sem[i], + sb_writers_name[i], + &type->s_writers_key[i])) goto fail; - lockdep_init_map(&s->s_writers.lock_map[i], sb_writers_name[i], - &type->s_writers_key[i], 0); } - init_waitqueue_head(&s->s_writers.wait); init_waitqueue_head(&s->s_writers.wait_unfrozen); s->s_bdi = &noop_backing_dev_info; s->s_flags = flags; @@ -1148,72 +1161,46 @@ out: */ void __sb_end_write(struct super_block *sb, int level) { - percpu_counter_dec(&sb->s_writers.counter[level-1]); - /* - * Make sure s_writers are updated before we wake up waiters in - * freeze_super(). - */ - smp_mb(); - if (waitqueue_active(&sb->s_writers.wait)) - wake_up(&sb->s_writers.wait); - rwsem_release(&sb->s_writers.lock_map[level-1], 1, _RET_IP_); + percpu_up_read(sb->s_writers.rw_sem + level-1); } EXPORT_SYMBOL(__sb_end_write); -#ifdef CONFIG_LOCKDEP -/* - * We want lockdep to tell us about possible deadlocks with freezing but - * it's it bit tricky to properly instrument it. Getting a freeze protection - * works as getting a read lock but there are subtle problems. XFS for example - * gets freeze protection on internal level twice in some cases, which is OK - * only because we already hold a freeze protection also on higher level. Due - * to these cases we have to tell lockdep we are doing trylock when we - * already hold a freeze protection for a higher freeze level. - */ -static void acquire_freeze_lock(struct super_block *sb, int level, bool trylock, - unsigned long ip) -{ - int i; - - if (!trylock) { - for (i = 0; i < level - 1; i++) - if (lock_is_held(&sb->s_writers.lock_map[i])) { - trylock = true; - break; - } - } - rwsem_acquire_read(&sb->s_writers.lock_map[level-1], 0, trylock, ip); -} -#endif - /* * This is an internal function, please use sb_start_{write,pagefault,intwrite} * instead. */ int __sb_start_write(struct super_block *sb, int level, bool wait) { -retry: - if (unlikely(sb->s_writers.frozen >= level)) { - if (!wait) - return 0; - wait_event(sb->s_writers.wait_unfrozen, - sb->s_writers.frozen < level); - } + bool force_trylock = false; + int ret = 1; #ifdef CONFIG_LOCKDEP - acquire_freeze_lock(sb, level, !wait, _RET_IP_); -#endif - percpu_counter_inc(&sb->s_writers.counter[level-1]); /* - * Make sure counter is updated before we check for frozen. - * freeze_super() first sets frozen and then checks the counter. + * We want lockdep to tell us about possible deadlocks with freezing + * but it's it bit tricky to properly instrument it. Getting a freeze + * protection works as getting a read lock but there are subtle + * problems. XFS for example gets freeze protection on internal level + * twice in some cases, which is OK only because we already hold a + * freeze protection also on higher level. Due to these cases we have + * to use wait == F (trylock mode) which must not fail. */ - smp_mb(); - if (unlikely(sb->s_writers.frozen >= level)) { - __sb_end_write(sb, level); - goto retry; + if (wait) { + int i; + + for (i = 0; i < level - 1; i++) + if (percpu_rwsem_is_held(sb->s_writers.rw_sem + i)) { + force_trylock = true; + break; + } } - return 1; +#endif + if (wait && !force_trylock) + percpu_down_read(sb->s_writers.rw_sem + level-1); + else + ret = percpu_down_read_trylock(sb->s_writers.rw_sem + level-1); + + WARN_ON(force_trylock & !ret); + return ret; } EXPORT_SYMBOL(__sb_start_write); @@ -1223,37 +1210,33 @@ EXPORT_SYMBOL(__sb_start_write); * @level: type of writers we wait for (normal vs page fault) * * This function waits until there are no writers of given type to given file - * system. Caller of this function should make sure there can be no new writers - * of type @level before calling this function. Otherwise this function can - * livelock. + * system. */ static void sb_wait_write(struct super_block *sb, int level) { - s64 writers; - + percpu_down_write(sb->s_writers.rw_sem + level-1); /* - * We just cycle-through lockdep here so that it does not complain - * about returning with lock to userspace + * We are going to return to userspace and forget about this lock, the + * ownership goes to the caller of thaw_super() which does unlock. + * + * FIXME: we should do this before return from freeze_super() after we + * called sync_filesystem(sb) and s_op->freeze_fs(sb), and thaw_super() + * should re-acquire these locks before s_op->unfreeze_fs(sb). However + * this leads to lockdep false-positives, so currently we do the early + * release right after acquire. */ - rwsem_acquire(&sb->s_writers.lock_map[level-1], 0, 0, _THIS_IP_); - rwsem_release(&sb->s_writers.lock_map[level-1], 1, _THIS_IP_); - - do { - DEFINE_WAIT(wait); + percpu_rwsem_release(sb->s_writers.rw_sem + level-1, 0, _THIS_IP_); +} - /* - * We use a barrier in prepare_to_wait() to separate setting - * of frozen and checking of the counter - */ - prepare_to_wait(&sb->s_writers.wait, &wait, - TASK_UNINTERRUPTIBLE); +static void sb_freeze_unlock(struct super_block *sb) +{ + int level; - writers = percpu_counter_sum(&sb->s_writers.counter[level-1]); - if (writers) - schedule(); + for (level = 0; level < SB_FREEZE_LEVELS; ++level) + percpu_rwsem_acquire(sb->s_writers.rw_sem + level, 0, _THIS_IP_); - finish_wait(&sb->s_writers.wait, &wait); - } while (writers); + for (level = SB_FREEZE_LEVELS - 1; level >= 0; level--) + percpu_up_write(sb->s_writers.rw_sem + level); } /** @@ -1312,20 +1295,14 @@ int freeze_super(struct super_block *sb) return 0; } - /* From now on, no new normal writers can start */ sb->s_writers.frozen = SB_FREEZE_WRITE; - smp_wmb(); - /* Release s_umount to preserve sb_start_write -> s_umount ordering */ up_write(&sb->s_umount); - sb_wait_write(sb, SB_FREEZE_WRITE); + down_write(&sb->s_umount); /* Now we go and block page faults... */ - down_write(&sb->s_umount); sb->s_writers.frozen = SB_FREEZE_PAGEFAULT; - smp_wmb(); - sb_wait_write(sb, SB_FREEZE_PAGEFAULT); /* All writers are done so after syncing there won't be dirty data */ @@ -1333,7 +1310,6 @@ int freeze_super(struct super_block *sb) /* Now wait for internal filesystem counter */ sb->s_writers.frozen = SB_FREEZE_FS; - smp_wmb(); sb_wait_write(sb, SB_FREEZE_FS); if (sb->s_op->freeze_fs) { @@ -1342,7 +1318,7 @@ int freeze_super(struct super_block *sb) printk(KERN_ERR "VFS:Filesystem freeze failed\n"); sb->s_writers.frozen = SB_UNFROZEN; - smp_wmb(); + sb_freeze_unlock(sb); wake_up(&sb->s_writers.wait_unfrozen); deactivate_locked_super(sb); return ret; @@ -1374,8 +1350,10 @@ int thaw_super(struct super_block *sb) return -EINVAL; } - if (sb->s_flags & MS_RDONLY) + if (sb->s_flags & MS_RDONLY) { + sb->s_writers.frozen = SB_UNFROZEN; goto out; + } if (sb->s_op->unfreeze_fs) { error = sb->s_op->unfreeze_fs(sb); @@ -1387,12 +1365,11 @@ int thaw_super(struct super_block *sb) } } -out: sb->s_writers.frozen = SB_UNFROZEN; - smp_wmb(); + sb_freeze_unlock(sb); +out: wake_up(&sb->s_writers.wait_unfrozen); deactivate_locked_super(sb); - return 0; } EXPORT_SYMBOL(thaw_super); diff --git a/fs/ufs/Makefile b/fs/ufs/Makefile index 4d0e02b022b3..392db25c0b56 100644 --- a/fs/ufs/Makefile +++ b/fs/ufs/Makefile @@ -5,5 +5,5 @@ obj-$(CONFIG_UFS_FS) += ufs.o ufs-objs := balloc.o cylinder.o dir.o file.o ialloc.o inode.o \ - namei.o super.o symlink.o truncate.o util.o + namei.o super.o symlink.o util.o ccflags-$(CONFIG_UFS_DEBUG) += -DDEBUG diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c index a7106eda5024..fb8b54eb77c5 100644 --- a/fs/ufs/balloc.c +++ b/fs/ufs/balloc.c @@ -417,7 +417,9 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment, if (oldcount == 0) { result = ufs_alloc_fragments (inode, cgno, goal, count, err); if (result) { + write_seqlock(&UFS_I(inode)->meta_lock); ufs_cpu_to_data_ptr(sb, p, result); + write_sequnlock(&UFS_I(inode)->meta_lock); *err = 0; UFS_I(inode)->i_lastfrag = max(UFS_I(inode)->i_lastfrag, fragment + count); @@ -473,7 +475,9 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment, ufs_change_blocknr(inode, fragment - oldcount, oldcount, uspi->s_sbbase + tmp, uspi->s_sbbase + result, locked_page); + write_seqlock(&UFS_I(inode)->meta_lock); ufs_cpu_to_data_ptr(sb, p, result); + write_sequnlock(&UFS_I(inode)->meta_lock); *err = 0; UFS_I(inode)->i_lastfrag = max(UFS_I(inode)->i_lastfrag, fragment + count); diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index f913a6924b23..a064cf44b143 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -41,9 +41,7 @@ #include "swab.h" #include "util.h" -static u64 ufs_frag_map(struct inode *inode, sector_t frag, bool needs_lock); - -static int ufs_block_to_path(struct inode *inode, sector_t i_block, sector_t offsets[4]) +static int ufs_block_to_path(struct inode *inode, sector_t i_block, unsigned offsets[4]) { struct ufs_sb_private_info *uspi = UFS_SB(inode->i_sb)->s_uspi; int ptrs = uspi->s_apb; @@ -75,227 +73,232 @@ static int ufs_block_to_path(struct inode *inode, sector_t i_block, sector_t off return n; } +typedef struct { + void *p; + union { + __fs32 key32; + __fs64 key64; + }; + struct buffer_head *bh; +} Indirect; + +static inline int grow_chain32(struct ufs_inode_info *ufsi, + struct buffer_head *bh, __fs32 *v, + Indirect *from, Indirect *to) +{ + Indirect *p; + unsigned seq; + to->bh = bh; + do { + seq = read_seqbegin(&ufsi->meta_lock); + to->key32 = *(__fs32 *)(to->p = v); + for (p = from; p <= to && p->key32 == *(__fs32 *)p->p; p++) + ; + } while (read_seqretry(&ufsi->meta_lock, seq)); + return (p > to); +} + +static inline int grow_chain64(struct ufs_inode_info *ufsi, + struct buffer_head *bh, __fs64 *v, + Indirect *from, Indirect *to) +{ + Indirect *p; + unsigned seq; + to->bh = bh; + do { + seq = read_seqbegin(&ufsi->meta_lock); + to->key64 = *(__fs64 *)(to->p = v); + for (p = from; p <= to && p->key64 == *(__fs64 *)p->p; p++) + ; + } while (read_seqretry(&ufsi->meta_lock, seq)); + return (p > to); +} + /* * Returns the location of the fragment from * the beginning of the filesystem. */ -static u64 ufs_frag_map(struct inode *inode, sector_t frag, bool needs_lock) +static u64 ufs_frag_map(struct inode *inode, unsigned offsets[4], int depth) { struct ufs_inode_info *ufsi = UFS_I(inode); struct super_block *sb = inode->i_sb; struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi; u64 mask = (u64) uspi->s_apbmask>>uspi->s_fpbshift; int shift = uspi->s_apbshift-uspi->s_fpbshift; - sector_t offsets[4], *p; - int depth = ufs_block_to_path(inode, frag >> uspi->s_fpbshift, offsets); - u64 ret = 0L; - __fs32 block; - __fs64 u2_block = 0L; + Indirect chain[4], *q = chain; + unsigned *p; unsigned flags = UFS_SB(sb)->s_flags; - u64 temp = 0L; + u64 res = 0; - UFSD(": frag = %llu depth = %d\n", (unsigned long long)frag, depth); UFSD(": uspi->s_fpbshift = %d ,uspi->s_apbmask = %x, mask=%llx\n", uspi->s_fpbshift, uspi->s_apbmask, (unsigned long long)mask); if (depth == 0) - return 0; + goto no_block; +again: p = offsets; - if (needs_lock) - lock_ufs(sb); if ((flags & UFS_TYPE_MASK) == UFS_TYPE_UFS2) goto ufs2; - block = ufsi->i_u1.i_data[*p++]; - if (!block) - goto out; + if (!grow_chain32(ufsi, NULL, &ufsi->i_u1.i_data[*p++], chain, q)) + goto changed; + if (!q->key32) + goto no_block; while (--depth) { + __fs32 *ptr; struct buffer_head *bh; - sector_t n = *p++; + unsigned n = *p++; - bh = sb_bread(sb, uspi->s_sbbase + fs32_to_cpu(sb, block)+(n>>shift)); + bh = sb_bread(sb, uspi->s_sbbase + + fs32_to_cpu(sb, q->key32) + (n>>shift)); if (!bh) - goto out; - block = ((__fs32 *) bh->b_data)[n & mask]; - brelse (bh); - if (!block) - goto out; - } - ret = (u64) (uspi->s_sbbase + fs32_to_cpu(sb, block) + (frag & uspi->s_fpbmask)); - goto out; -ufs2: - u2_block = ufsi->i_u1.u2_i_data[*p++]; - if (!u2_block) - goto out; + goto no_block; + ptr = (__fs32 *)bh->b_data + (n & mask); + if (!grow_chain32(ufsi, bh, ptr, chain, ++q)) + goto changed; + if (!q->key32) + goto no_block; + } + res = fs32_to_cpu(sb, q->key32); + goto found; +ufs2: + if (!grow_chain64(ufsi, NULL, &ufsi->i_u1.u2_i_data[*p++], chain, q)) + goto changed; + if (!q->key64) + goto no_block; while (--depth) { + __fs64 *ptr; struct buffer_head *bh; - sector_t n = *p++; - + unsigned n = *p++; - temp = (u64)(uspi->s_sbbase) + fs64_to_cpu(sb, u2_block); - bh = sb_bread(sb, temp +(u64) (n>>shift)); + bh = sb_bread(sb, uspi->s_sbbase + + fs64_to_cpu(sb, q->key64) + (n>>shift)); if (!bh) - goto out; - u2_block = ((__fs64 *)bh->b_data)[n & mask]; - brelse(bh); - if (!u2_block) - goto out; + goto no_block; + ptr = (__fs64 *)bh->b_data + (n & mask); + if (!grow_chain64(ufsi, bh, ptr, chain, ++q)) + goto changed; + if (!q->key64) + goto no_block; } - temp = (u64)uspi->s_sbbase + fs64_to_cpu(sb, u2_block); - ret = temp + (u64) (frag & uspi->s_fpbmask); + res = fs64_to_cpu(sb, q->key64); +found: + res += uspi->s_sbbase; +no_block: + while (q > chain) { + brelse(q->bh); + q--; + } + return res; -out: - if (needs_lock) - unlock_ufs(sb); - return ret; +changed: + while (q > chain) { + brelse(q->bh); + q--; + } + goto again; +} + +/* + * Unpacking tails: we have a file with partial final block and + * we had been asked to extend it. If the fragment being written + * is within the same block, we need to extend the tail just to cover + * that fragment. Otherwise the tail is extended to full block. + * + * Note that we might need to create a _new_ tail, but that will + * be handled elsewhere; this is strictly for resizing old + * ones. + */ +static bool +ufs_extend_tail(struct inode *inode, u64 writes_to, + int *err, struct page *locked_page) +{ + struct ufs_inode_info *ufsi = UFS_I(inode); + struct super_block *sb = inode->i_sb; + struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi; + unsigned lastfrag = ufsi->i_lastfrag; /* it's a short file, so unsigned is enough */ + unsigned block = ufs_fragstoblks(lastfrag); + unsigned new_size; + void *p; + u64 tmp; + + if (writes_to < (lastfrag | uspi->s_fpbmask)) + new_size = (writes_to & uspi->s_fpbmask) + 1; + else + new_size = uspi->s_fpb; + + p = ufs_get_direct_data_ptr(uspi, ufsi, block); + tmp = ufs_new_fragments(inode, p, lastfrag, ufs_data_ptr_to_cpu(sb, p), + new_size, err, locked_page); + return tmp != 0; } /** * ufs_inode_getfrag() - allocate new fragment(s) * @inode: pointer to inode - * @fragment: number of `fragment' which hold pointer - * to new allocated fragment(s) + * @index: number of block pointer within the inode's array. * @new_fragment: number of new allocated fragment(s) - * @required: how many fragment(s) we require * @err: we set it if something wrong - * @phys: pointer to where we save physical number of new allocated fragments, - * NULL if we allocate not data(indirect blocks for example). * @new: we set it if we allocate new block * @locked_page: for ufs_new_fragments() */ -static struct buffer_head * -ufs_inode_getfrag(struct inode *inode, u64 fragment, - sector_t new_fragment, unsigned int required, int *err, - long *phys, int *new, struct page *locked_page) +static u64 +ufs_inode_getfrag(struct inode *inode, unsigned index, + sector_t new_fragment, int *err, + int *new, struct page *locked_page) { struct ufs_inode_info *ufsi = UFS_I(inode); struct super_block *sb = inode->i_sb; struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi; - struct buffer_head * result; - unsigned blockoff, lastblockoff; - u64 tmp, goal, lastfrag, block, lastblock; - void *p, *p2; - - UFSD("ENTER, ino %lu, fragment %llu, new_fragment %llu, required %u, " - "metadata %d\n", inode->i_ino, (unsigned long long)fragment, - (unsigned long long)new_fragment, required, !phys); + u64 tmp, goal, lastfrag; + unsigned nfrags = uspi->s_fpb; + void *p; /* TODO : to be done for write support if ( (flags & UFS_TYPE_MASK) == UFS_TYPE_UFS2) goto ufs2; */ - block = ufs_fragstoblks (fragment); - blockoff = ufs_fragnum (fragment); - p = ufs_get_direct_data_ptr(uspi, ufsi, block); - - goal = 0; - -repeat: + p = ufs_get_direct_data_ptr(uspi, ufsi, index); tmp = ufs_data_ptr_to_cpu(sb, p); + if (tmp) + goto out; lastfrag = ufsi->i_lastfrag; - if (tmp && fragment < lastfrag) { - if (!phys) { - result = sb_getblk(sb, uspi->s_sbbase + tmp + blockoff); - if (tmp == ufs_data_ptr_to_cpu(sb, p)) { - UFSD("EXIT, result %llu\n", - (unsigned long long)tmp + blockoff); - return result; - } - brelse (result); - goto repeat; - } else { - *phys = uspi->s_sbbase + tmp + blockoff; - return NULL; - } - } - lastblock = ufs_fragstoblks (lastfrag); - lastblockoff = ufs_fragnum (lastfrag); - /* - * We will extend file into new block beyond last allocated block - */ - if (lastblock < block) { - /* - * We must reallocate last allocated block - */ - if (lastblockoff) { - p2 = ufs_get_direct_data_ptr(uspi, ufsi, lastblock); - tmp = ufs_new_fragments(inode, p2, lastfrag, - ufs_data_ptr_to_cpu(sb, p2), - uspi->s_fpb - lastblockoff, - err, locked_page); - if (!tmp) { - if (lastfrag != ufsi->i_lastfrag) - goto repeat; - else - return NULL; - } - lastfrag = ufsi->i_lastfrag; - - } - tmp = ufs_data_ptr_to_cpu(sb, - ufs_get_direct_data_ptr(uspi, ufsi, - lastblock)); - if (tmp) - goal = tmp + uspi->s_fpb; - tmp = ufs_new_fragments (inode, p, fragment - blockoff, - goal, required + blockoff, - err, - phys != NULL ? locked_page : NULL); - } else if (lastblock == block) { - /* - * We will extend last allocated block - */ - tmp = ufs_new_fragments(inode, p, fragment - - (blockoff - lastblockoff), - ufs_data_ptr_to_cpu(sb, p), - required + (blockoff - lastblockoff), - err, phys != NULL ? locked_page : NULL); - } else /* (lastblock > block) */ { - /* - * We will allocate new block before last allocated block - */ - if (block) { - tmp = ufs_data_ptr_to_cpu(sb, - ufs_get_direct_data_ptr(uspi, ufsi, block - 1)); - if (tmp) - goal = tmp + uspi->s_fpb; - } - tmp = ufs_new_fragments(inode, p, fragment - blockoff, - goal, uspi->s_fpb, err, - phys != NULL ? locked_page : NULL); + /* will that be a new tail? */ + if (new_fragment < UFS_NDIR_FRAGMENT && new_fragment >= lastfrag) + nfrags = (new_fragment & uspi->s_fpbmask) + 1; + + goal = 0; + if (index) { + goal = ufs_data_ptr_to_cpu(sb, + ufs_get_direct_data_ptr(uspi, ufsi, index - 1)); + if (goal) + goal += uspi->s_fpb; } + tmp = ufs_new_fragments(inode, p, ufs_blknum(new_fragment), + goal, uspi->s_fpb, err, locked_page); + if (!tmp) { - if ((!blockoff && ufs_data_ptr_to_cpu(sb, p)) || - (blockoff && lastfrag != ufsi->i_lastfrag)) - goto repeat; *err = -ENOSPC; - return NULL; + return 0; } - if (!phys) { - result = sb_getblk(sb, uspi->s_sbbase + tmp + blockoff); - } else { - *phys = uspi->s_sbbase + tmp + blockoff; - result = NULL; - *err = 0; + if (new) *new = 1; - } - inode->i_ctime = CURRENT_TIME_SEC; if (IS_SYNC(inode)) ufs_sync_inode (inode); mark_inode_dirty(inode); - UFSD("EXIT, result %llu\n", (unsigned long long)tmp + blockoff); - return result; +out: + return tmp + uspi->s_sbbase; /* This part : To be implemented .... Required only for writing, not required for READ-ONLY. @@ -316,95 +319,70 @@ repeat2: /** * ufs_inode_getblock() - allocate new block * @inode: pointer to inode - * @bh: pointer to block which hold "pointer" to new allocated block - * @fragment: number of `fragment' which hold pointer - * to new allocated block + * @ind_block: block number of the indirect block + * @index: number of pointer within the indirect block * @new_fragment: number of new allocated fragment * (block will hold this fragment and also uspi->s_fpb-1) * @err: see ufs_inode_getfrag() - * @phys: see ufs_inode_getfrag() * @new: see ufs_inode_getfrag() * @locked_page: see ufs_inode_getfrag() */ -static struct buffer_head * -ufs_inode_getblock(struct inode *inode, struct buffer_head *bh, - u64 fragment, sector_t new_fragment, int *err, - long *phys, int *new, struct page *locked_page) +static u64 +ufs_inode_getblock(struct inode *inode, u64 ind_block, + unsigned index, sector_t new_fragment, int *err, + int *new, struct page *locked_page) { struct super_block *sb = inode->i_sb; struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi; - struct buffer_head * result; - unsigned blockoff; - u64 tmp, goal, block; + int shift = uspi->s_apbshift - uspi->s_fpbshift; + u64 tmp = 0, goal; + struct buffer_head *bh; void *p; - block = ufs_fragstoblks (fragment); - blockoff = ufs_fragnum (fragment); - - UFSD("ENTER, ino %lu, fragment %llu, new_fragment %llu, metadata %d\n", - inode->i_ino, (unsigned long long)fragment, - (unsigned long long)new_fragment, !phys); + if (!ind_block) + return 0; - result = NULL; - if (!bh) - goto out; - if (!buffer_uptodate(bh)) { - ll_rw_block (READ, 1, &bh); - wait_on_buffer (bh); - if (!buffer_uptodate(bh)) - goto out; + bh = sb_bread(sb, ind_block + (index >> shift)); + if (unlikely(!bh)) { + *err = -EIO; + return 0; } + + index &= uspi->s_apbmask >> uspi->s_fpbshift; if (uspi->fs_magic == UFS2_MAGIC) - p = (__fs64 *)bh->b_data + block; + p = (__fs64 *)bh->b_data + index; else - p = (__fs32 *)bh->b_data + block; -repeat: + p = (__fs32 *)bh->b_data + index; + tmp = ufs_data_ptr_to_cpu(sb, p); - if (tmp) { - if (!phys) { - result = sb_getblk(sb, uspi->s_sbbase + tmp + blockoff); - if (tmp == ufs_data_ptr_to_cpu(sb, p)) - goto out; - brelse (result); - goto repeat; - } else { - *phys = uspi->s_sbbase + tmp + blockoff; - goto out; - } - } + if (tmp) + goto out; - if (block && (uspi->fs_magic == UFS2_MAGIC ? - (tmp = fs64_to_cpu(sb, ((__fs64 *)bh->b_data)[block-1])) : - (tmp = fs32_to_cpu(sb, ((__fs32 *)bh->b_data)[block-1])))) + if (index && (uspi->fs_magic == UFS2_MAGIC ? + (tmp = fs64_to_cpu(sb, ((__fs64 *)bh->b_data)[index-1])) : + (tmp = fs32_to_cpu(sb, ((__fs32 *)bh->b_data)[index-1])))) goal = tmp + uspi->s_fpb; else goal = bh->b_blocknr + uspi->s_fpb; tmp = ufs_new_fragments(inode, p, ufs_blknum(new_fragment), goal, uspi->s_fpb, err, locked_page); - if (!tmp) { - if (ufs_data_ptr_to_cpu(sb, p)) - goto repeat; + if (!tmp) goto out; - } - - if (!phys) { - result = sb_getblk(sb, uspi->s_sbbase + tmp + blockoff); - } else { - *phys = uspi->s_sbbase + tmp + blockoff; + if (new) *new = 1; - } mark_buffer_dirty(bh); if (IS_SYNC(inode)) sync_dirty_buffer(bh); inode->i_ctime = CURRENT_TIME_SEC; mark_inode_dirty(inode); - UFSD("result %llu\n", (unsigned long long)tmp + blockoff); out: brelse (bh); UFSD("EXIT\n"); - return result; + if (tmp) + tmp += uspi->s_sbbase; + return tmp; } /** @@ -412,103 +390,64 @@ out: * readpage, writepage and so on */ -int ufs_getfrag_block(struct inode *inode, sector_t fragment, struct buffer_head *bh_result, int create) +static int ufs_getfrag_block(struct inode *inode, sector_t fragment, struct buffer_head *bh_result, int create) { - struct super_block * sb = inode->i_sb; - struct ufs_sb_info * sbi = UFS_SB(sb); - struct ufs_sb_private_info * uspi = sbi->s_uspi; - struct buffer_head * bh; - int ret, err, new; - unsigned long ptr,phys; + struct super_block *sb = inode->i_sb; + struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi; + int err = 0, new = 0; + unsigned offsets[4]; + int depth = ufs_block_to_path(inode, fragment >> uspi->s_fpbshift, offsets); u64 phys64 = 0; - bool needs_lock = (sbi->mutex_owner != current); - + unsigned frag = fragment & uspi->s_fpbmask; + if (!create) { - phys64 = ufs_frag_map(inode, fragment, needs_lock); - UFSD("phys64 = %llu\n", (unsigned long long)phys64); - if (phys64) - map_bh(bh_result, sb, phys64); - return 0; + phys64 = ufs_frag_map(inode, offsets, depth); + goto out; } /* This code entered only while writing ....? */ - err = -EIO; - new = 0; - ret = 0; - bh = NULL; - - if (needs_lock) - lock_ufs(sb); + mutex_lock(&UFS_I(inode)->truncate_mutex); UFSD("ENTER, ino %lu, fragment %llu\n", inode->i_ino, (unsigned long long)fragment); - if (fragment > - ((UFS_NDADDR + uspi->s_apb + uspi->s_2apb + uspi->s_3apb) - << uspi->s_fpbshift)) - goto abort_too_big; - - err = 0; - ptr = fragment; - - /* - * ok, these macros clean the logic up a bit and make - * it much more readable: - */ -#define GET_INODE_DATABLOCK(x) \ - ufs_inode_getfrag(inode, x, fragment, 1, &err, &phys, &new,\ - bh_result->b_page) -#define GET_INODE_PTR(x) \ - ufs_inode_getfrag(inode, x, fragment, uspi->s_fpb, &err, NULL, NULL,\ - bh_result->b_page) -#define GET_INDIRECT_DATABLOCK(x) \ - ufs_inode_getblock(inode, bh, x, fragment, \ - &err, &phys, &new, bh_result->b_page) -#define GET_INDIRECT_PTR(x) \ - ufs_inode_getblock(inode, bh, x, fragment, \ - &err, NULL, NULL, NULL) - - if (ptr < UFS_NDIR_FRAGMENT) { - bh = GET_INODE_DATABLOCK(ptr); + if (unlikely(!depth)) { + ufs_warning(sb, "ufs_get_block", "block > big"); + err = -EIO; goto out; } - ptr -= UFS_NDIR_FRAGMENT; - if (ptr < (1 << (uspi->s_apbshift + uspi->s_fpbshift))) { - bh = GET_INODE_PTR(UFS_IND_FRAGMENT + (ptr >> uspi->s_apbshift)); - goto get_indirect; - } - ptr -= 1 << (uspi->s_apbshift + uspi->s_fpbshift); - if (ptr < (1 << (uspi->s_2apbshift + uspi->s_fpbshift))) { - bh = GET_INODE_PTR(UFS_DIND_FRAGMENT + (ptr >> uspi->s_2apbshift)); - goto get_double; - } - ptr -= 1 << (uspi->s_2apbshift + uspi->s_fpbshift); - bh = GET_INODE_PTR(UFS_TIND_FRAGMENT + (ptr >> uspi->s_3apbshift)); - bh = GET_INDIRECT_PTR((ptr >> uspi->s_2apbshift) & uspi->s_apbmask); -get_double: - bh = GET_INDIRECT_PTR((ptr >> uspi->s_apbshift) & uspi->s_apbmask); -get_indirect: - bh = GET_INDIRECT_DATABLOCK(ptr & uspi->s_apbmask); - -#undef GET_INODE_DATABLOCK -#undef GET_INODE_PTR -#undef GET_INDIRECT_DATABLOCK -#undef GET_INDIRECT_PTR -out: - if (err) - goto abort; - if (new) - set_buffer_new(bh_result); - map_bh(bh_result, sb, phys); -abort: - if (needs_lock) - unlock_ufs(sb); + if (UFS_I(inode)->i_lastfrag < UFS_NDIR_FRAGMENT) { + unsigned lastfrag = UFS_I(inode)->i_lastfrag; + unsigned tailfrags = lastfrag & uspi->s_fpbmask; + if (tailfrags && fragment >= lastfrag) { + if (!ufs_extend_tail(inode, fragment, + &err, bh_result->b_page)) + goto out; + } + } + if (depth == 1) { + phys64 = ufs_inode_getfrag(inode, offsets[0], fragment, + &err, &new, bh_result->b_page); + } else { + int i; + phys64 = ufs_inode_getfrag(inode, offsets[0], fragment, + &err, NULL, NULL); + for (i = 1; i < depth - 1; i++) + phys64 = ufs_inode_getblock(inode, phys64, offsets[i], + fragment, &err, NULL, NULL); + phys64 = ufs_inode_getblock(inode, phys64, offsets[depth - 1], + fragment, &err, &new, bh_result->b_page); + } +out: + if (phys64) { + phys64 += frag; + map_bh(bh_result, sb, phys64); + if (new) + set_buffer_new(bh_result); + } + mutex_unlock(&UFS_I(inode)->truncate_mutex); return err; - -abort_too_big: - ufs_warning(sb, "ufs_get_block", "block > big"); - goto abort; } static int ufs_writepage(struct page *page, struct writeback_control *wbc) @@ -526,12 +465,16 @@ int ufs_prepare_chunk(struct page *page, loff_t pos, unsigned len) return __block_write_begin(page, pos, len, ufs_getfrag_block); } +static void ufs_truncate_blocks(struct inode *); + static void ufs_write_failed(struct address_space *mapping, loff_t to) { struct inode *inode = mapping->host; - if (to > inode->i_size) + if (to > inode->i_size) { truncate_pagecache(inode, inode->i_size); + ufs_truncate_blocks(inode); + } } static int ufs_write_begin(struct file *file, struct address_space *mapping, @@ -548,6 +491,18 @@ static int ufs_write_begin(struct file *file, struct address_space *mapping, return ret; } +static int ufs_write_end(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata) +{ + int ret; + + ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata); + if (ret < len) + ufs_write_failed(mapping, pos + len); + return ret; +} + static sector_t ufs_bmap(struct address_space *mapping, sector_t block) { return generic_block_bmap(mapping,block,ufs_getfrag_block); @@ -557,7 +512,7 @@ const struct address_space_operations ufs_aops = { .readpage = ufs_readpage, .writepage = ufs_writepage, .write_begin = ufs_write_begin, - .write_end = generic_write_end, + .write_end = ufs_write_end, .bmap = ufs_bmap }; @@ -599,7 +554,7 @@ static int ufs1_read_inode(struct inode *inode, struct ufs_inode *ufs_inode) ufs_error (sb, "ufs_read_inode", "inode %lu has zero nlink\n", inode->i_ino); return -1; } - + /* * Linux now has 32-bit uid and gid, so we can support EFT. */ @@ -619,7 +574,7 @@ static int ufs1_read_inode(struct inode *inode, struct ufs_inode *ufs_inode) ufsi->i_shadow = fs32_to_cpu(sb, ufs_inode->ui_u3.ui_sun.ui_shadow); ufsi->i_oeftflag = fs32_to_cpu(sb, ufs_inode->ui_u3.ui_sun.ui_oeftflag); - + if (S_ISCHR(mode) || S_ISBLK(mode) || inode->i_blocks) { memcpy(ufsi->i_u1.i_data, &ufs_inode->ui_u2.ui_addr, sizeof(ufs_inode->ui_u2.ui_addr)); @@ -753,7 +708,7 @@ static void ufs1_update_inode(struct inode *inode, struct ufs_inode *ufs_inode) ufs_set_inode_uid(sb, ufs_inode, i_uid_read(inode)); ufs_set_inode_gid(sb, ufs_inode, i_gid_read(inode)); - + ufs_inode->ui_size = cpu_to_fs64(sb, inode->i_size); ufs_inode->ui_atime.tv_sec = cpu_to_fs32(sb, inode->i_atime.tv_sec); ufs_inode->ui_atime.tv_usec = 0; @@ -855,23 +810,19 @@ static int ufs_update_inode(struct inode * inode, int do_sync) ufs1_update_inode(inode, ufs_inode + ufs_inotofsbo(inode->i_ino)); } - + mark_buffer_dirty(bh); if (do_sync) sync_dirty_buffer(bh); brelse (bh); - + UFSD("EXIT\n"); return 0; } int ufs_write_inode(struct inode *inode, struct writeback_control *wbc) { - int ret; - lock_ufs(inode->i_sb); - ret = ufs_update_inode(inode, wbc->sync_mode == WB_SYNC_ALL); - unlock_ufs(inode->i_sb); - return ret; + return ufs_update_inode(inode, wbc->sync_mode == WB_SYNC_ALL); } int ufs_sync_inode (struct inode *inode) @@ -888,24 +839,389 @@ void ufs_evict_inode(struct inode * inode) truncate_inode_pages_final(&inode->i_data); if (want_delete) { - loff_t old_i_size; - /*UFS_I(inode)->i_dtime = CURRENT_TIME;*/ - lock_ufs(inode->i_sb); - mark_inode_dirty(inode); - ufs_update_inode(inode, IS_SYNC(inode)); - old_i_size = inode->i_size; inode->i_size = 0; - if (inode->i_blocks && ufs_truncate(inode, old_i_size)) - ufs_warning(inode->i_sb, __func__, "ufs_truncate failed\n"); - unlock_ufs(inode->i_sb); + if (inode->i_blocks) + ufs_truncate_blocks(inode); } invalidate_inode_buffers(inode); clear_inode(inode); - if (want_delete) { - lock_ufs(inode->i_sb); + if (want_delete) ufs_free_inode(inode); - unlock_ufs(inode->i_sb); +} + +struct to_free { + struct inode *inode; + u64 to; + unsigned count; +}; + +static inline void free_data(struct to_free *ctx, u64 from, unsigned count) +{ + if (ctx->count && ctx->to != from) { + ufs_free_blocks(ctx->inode, ctx->to - ctx->count, ctx->count); + ctx->count = 0; + } + ctx->count += count; + ctx->to = from + count; +} + +#define DIRECT_BLOCK ((inode->i_size + uspi->s_bsize - 1) >> uspi->s_bshift) +#define DIRECT_FRAGMENT ((inode->i_size + uspi->s_fsize - 1) >> uspi->s_fshift) + +static void ufs_trunc_direct(struct inode *inode) +{ + struct ufs_inode_info *ufsi = UFS_I(inode); + struct super_block * sb; + struct ufs_sb_private_info * uspi; + void *p; + u64 frag1, frag2, frag3, frag4, block1, block2; + struct to_free ctx = {.inode = inode}; + unsigned i, tmp; + + UFSD("ENTER: ino %lu\n", inode->i_ino); + + sb = inode->i_sb; + uspi = UFS_SB(sb)->s_uspi; + + frag1 = DIRECT_FRAGMENT; + frag4 = min_t(u64, UFS_NDIR_FRAGMENT, ufsi->i_lastfrag); + frag2 = ((frag1 & uspi->s_fpbmask) ? ((frag1 | uspi->s_fpbmask) + 1) : frag1); + frag3 = frag4 & ~uspi->s_fpbmask; + block1 = block2 = 0; + if (frag2 > frag3) { + frag2 = frag4; + frag3 = frag4 = 0; + } else if (frag2 < frag3) { + block1 = ufs_fragstoblks (frag2); + block2 = ufs_fragstoblks (frag3); + } + + UFSD("ino %lu, frag1 %llu, frag2 %llu, block1 %llu, block2 %llu," + " frag3 %llu, frag4 %llu\n", inode->i_ino, + (unsigned long long)frag1, (unsigned long long)frag2, + (unsigned long long)block1, (unsigned long long)block2, + (unsigned long long)frag3, (unsigned long long)frag4); + + if (frag1 >= frag2) + goto next1; + + /* + * Free first free fragments + */ + p = ufs_get_direct_data_ptr(uspi, ufsi, ufs_fragstoblks(frag1)); + tmp = ufs_data_ptr_to_cpu(sb, p); + if (!tmp ) + ufs_panic (sb, "ufs_trunc_direct", "internal error"); + frag2 -= frag1; + frag1 = ufs_fragnum (frag1); + + ufs_free_fragments(inode, tmp + frag1, frag2); + +next1: + /* + * Free whole blocks + */ + for (i = block1 ; i < block2; i++) { + p = ufs_get_direct_data_ptr(uspi, ufsi, i); + tmp = ufs_data_ptr_to_cpu(sb, p); + if (!tmp) + continue; + write_seqlock(&ufsi->meta_lock); + ufs_data_ptr_clear(uspi, p); + write_sequnlock(&ufsi->meta_lock); + + free_data(&ctx, tmp, uspi->s_fpb); + } + + free_data(&ctx, 0, 0); + + if (frag3 >= frag4) + goto next3; + + /* + * Free last free fragments + */ + p = ufs_get_direct_data_ptr(uspi, ufsi, ufs_fragstoblks(frag3)); + tmp = ufs_data_ptr_to_cpu(sb, p); + if (!tmp ) + ufs_panic(sb, "ufs_truncate_direct", "internal error"); + frag4 = ufs_fragnum (frag4); + write_seqlock(&ufsi->meta_lock); + ufs_data_ptr_clear(uspi, p); + write_sequnlock(&ufsi->meta_lock); + + ufs_free_fragments (inode, tmp, frag4); + next3: + + UFSD("EXIT: ino %lu\n", inode->i_ino); +} + +static void free_full_branch(struct inode *inode, u64 ind_block, int depth) +{ + struct super_block *sb = inode->i_sb; + struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi; + struct ufs_buffer_head *ubh = ubh_bread(sb, ind_block, uspi->s_bsize); + unsigned i; + + if (!ubh) + return; + + if (--depth) { + for (i = 0; i < uspi->s_apb; i++) { + void *p = ubh_get_data_ptr(uspi, ubh, i); + u64 block = ufs_data_ptr_to_cpu(sb, p); + if (block) + free_full_branch(inode, block, depth); + } + } else { + struct to_free ctx = {.inode = inode}; + + for (i = 0; i < uspi->s_apb; i++) { + void *p = ubh_get_data_ptr(uspi, ubh, i); + u64 block = ufs_data_ptr_to_cpu(sb, p); + if (block) + free_data(&ctx, block, uspi->s_fpb); + } + free_data(&ctx, 0, 0); + } + + ubh_bforget(ubh); + ufs_free_blocks(inode, ind_block, uspi->s_fpb); +} + +static void free_branch_tail(struct inode *inode, unsigned from, struct ufs_buffer_head *ubh, int depth) +{ + struct super_block *sb = inode->i_sb; + struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi; + unsigned i; + + if (--depth) { + for (i = from; i < uspi->s_apb ; i++) { + void *p = ubh_get_data_ptr(uspi, ubh, i); + u64 block = ufs_data_ptr_to_cpu(sb, p); + if (block) { + write_seqlock(&UFS_I(inode)->meta_lock); + ufs_data_ptr_clear(uspi, p); + write_sequnlock(&UFS_I(inode)->meta_lock); + ubh_mark_buffer_dirty(ubh); + free_full_branch(inode, block, depth); + } + } + } else { + struct to_free ctx = {.inode = inode}; + + for (i = from; i < uspi->s_apb; i++) { + void *p = ubh_get_data_ptr(uspi, ubh, i); + u64 block = ufs_data_ptr_to_cpu(sb, p); + if (block) { + write_seqlock(&UFS_I(inode)->meta_lock); + ufs_data_ptr_clear(uspi, p); + write_sequnlock(&UFS_I(inode)->meta_lock); + ubh_mark_buffer_dirty(ubh); + free_data(&ctx, block, uspi->s_fpb); + } + } + free_data(&ctx, 0, 0); + } + if (IS_SYNC(inode) && ubh_buffer_dirty(ubh)) + ubh_sync_block(ubh); + ubh_brelse(ubh); +} + +static int ufs_alloc_lastblock(struct inode *inode, loff_t size) +{ + int err = 0; + struct super_block *sb = inode->i_sb; + struct address_space *mapping = inode->i_mapping; + struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi; + unsigned i, end; + sector_t lastfrag; + struct page *lastpage; + struct buffer_head *bh; + u64 phys64; + + lastfrag = (size + uspi->s_fsize - 1) >> uspi->s_fshift; + + if (!lastfrag) + goto out; + + lastfrag--; + + lastpage = ufs_get_locked_page(mapping, lastfrag >> + (PAGE_CACHE_SHIFT - inode->i_blkbits)); + if (IS_ERR(lastpage)) { + err = -EIO; + goto out; + } + + end = lastfrag & ((1 << (PAGE_CACHE_SHIFT - inode->i_blkbits)) - 1); + bh = page_buffers(lastpage); + for (i = 0; i < end; ++i) + bh = bh->b_this_page; + + + err = ufs_getfrag_block(inode, lastfrag, bh, 1); + + if (unlikely(err)) + goto out_unlock; + + if (buffer_new(bh)) { + clear_buffer_new(bh); + unmap_underlying_metadata(bh->b_bdev, + bh->b_blocknr); + /* + * we do not zeroize fragment, because of + * if it maped to hole, it already contains zeroes + */ + set_buffer_uptodate(bh); + mark_buffer_dirty(bh); + set_page_dirty(lastpage); + } + + if (lastfrag >= UFS_IND_FRAGMENT) { + end = uspi->s_fpb - ufs_fragnum(lastfrag) - 1; + phys64 = bh->b_blocknr + 1; + for (i = 0; i < end; ++i) { + bh = sb_getblk(sb, i + phys64); + lock_buffer(bh); + memset(bh->b_data, 0, sb->s_blocksize); + set_buffer_uptodate(bh); + mark_buffer_dirty(bh); + unlock_buffer(bh); + sync_dirty_buffer(bh); + brelse(bh); + } + } +out_unlock: + ufs_put_locked_page(lastpage); +out: + return err; +} + +static void __ufs_truncate_blocks(struct inode *inode) +{ + struct ufs_inode_info *ufsi = UFS_I(inode); + struct super_block *sb = inode->i_sb; + struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi; + unsigned offsets[4]; + int depth = ufs_block_to_path(inode, DIRECT_BLOCK, offsets); + int depth2; + unsigned i; + struct ufs_buffer_head *ubh[3]; + void *p; + u64 block; + + if (!depth) + return; + + /* find the last non-zero in offsets[] */ + for (depth2 = depth - 1; depth2; depth2--) + if (offsets[depth2]) + break; + + mutex_lock(&ufsi->truncate_mutex); + if (depth == 1) { + ufs_trunc_direct(inode); + offsets[0] = UFS_IND_BLOCK; + } else { + /* get the blocks that should be partially emptied */ + p = ufs_get_direct_data_ptr(uspi, ufsi, offsets[0]); + for (i = 0; i < depth2; i++) { + offsets[i]++; /* next branch is fully freed */ + block = ufs_data_ptr_to_cpu(sb, p); + if (!block) + break; + ubh[i] = ubh_bread(sb, block, uspi->s_bsize); + if (!ubh[i]) { + write_seqlock(&ufsi->meta_lock); + ufs_data_ptr_clear(uspi, p); + write_sequnlock(&ufsi->meta_lock); + break; + } + p = ubh_get_data_ptr(uspi, ubh[i], offsets[i + 1]); + } + while (i--) + free_branch_tail(inode, offsets[i + 1], ubh[i], depth - i - 1); + } + for (i = offsets[0]; i <= UFS_TIND_BLOCK; i++) { + p = ufs_get_direct_data_ptr(uspi, ufsi, i); + block = ufs_data_ptr_to_cpu(sb, p); + if (block) { + write_seqlock(&ufsi->meta_lock); + ufs_data_ptr_clear(uspi, p); + write_sequnlock(&ufsi->meta_lock); + free_full_branch(inode, block, i - UFS_IND_BLOCK + 1); + } } + ufsi->i_lastfrag = DIRECT_FRAGMENT; + mark_inode_dirty(inode); + mutex_unlock(&ufsi->truncate_mutex); +} + +static int ufs_truncate(struct inode *inode, loff_t size) +{ + int err = 0; + + UFSD("ENTER: ino %lu, i_size: %llu, old_i_size: %llu\n", + inode->i_ino, (unsigned long long)size, + (unsigned long long)i_size_read(inode)); + + if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || + S_ISLNK(inode->i_mode))) + return -EINVAL; + if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) + return -EPERM; + + err = ufs_alloc_lastblock(inode, size); + + if (err) + goto out; + + block_truncate_page(inode->i_mapping, size, ufs_getfrag_block); + + truncate_setsize(inode, size); + + __ufs_truncate_blocks(inode); + inode->i_mtime = inode->i_ctime = CURRENT_TIME_SEC; + mark_inode_dirty(inode); +out: + UFSD("EXIT: err %d\n", err); + return err; +} + +void ufs_truncate_blocks(struct inode *inode) +{ + if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || + S_ISLNK(inode->i_mode))) + return; + if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) + return; + __ufs_truncate_blocks(inode); +} + +int ufs_setattr(struct dentry *dentry, struct iattr *attr) +{ + struct inode *inode = d_inode(dentry); + unsigned int ia_valid = attr->ia_valid; + int error; + + error = inode_change_ok(inode, attr); + if (error) + return error; + + if (ia_valid & ATTR_SIZE && attr->ia_size != inode->i_size) { + error = ufs_truncate(inode, attr->ia_size); + if (error) + return error; + } + + setattr_copy(inode, attr); + mark_inode_dirty(inode); + return 0; } + +const struct inode_operations ufs_file_inode_operations = { + .setattr = ufs_setattr, +}; diff --git a/fs/ufs/super.c b/fs/ufs/super.c index 250579a80d90..f6390eec02ca 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -94,22 +94,6 @@ #include "swab.h" #include "util.h" -void lock_ufs(struct super_block *sb) -{ - struct ufs_sb_info *sbi = UFS_SB(sb); - - mutex_lock(&sbi->mutex); - sbi->mutex_owner = current; -} - -void unlock_ufs(struct super_block *sb) -{ - struct ufs_sb_info *sbi = UFS_SB(sb); - - sbi->mutex_owner = NULL; - mutex_unlock(&sbi->mutex); -} - static struct inode *ufs_nfs_get_inode(struct super_block *sb, u64 ino, u32 generation) { struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi; @@ -694,7 +678,6 @@ static int ufs_sync_fs(struct super_block *sb, int wait) struct ufs_super_block_third * usb3; unsigned flags; - lock_ufs(sb); mutex_lock(&UFS_SB(sb)->s_lock); UFSD("ENTER\n"); @@ -714,7 +697,6 @@ static int ufs_sync_fs(struct super_block *sb, int wait) UFSD("EXIT\n"); mutex_unlock(&UFS_SB(sb)->s_lock); - unlock_ufs(sb); return 0; } @@ -758,7 +740,6 @@ static void ufs_put_super(struct super_block *sb) ubh_brelse_uspi (sbi->s_uspi); kfree (sbi->s_uspi); - mutex_destroy(&sbi->mutex); kfree (sbi); sb->s_fs_info = NULL; UFSD("EXIT\n"); @@ -801,7 +782,6 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent) UFSD("flag %u\n", (int)(sb->s_flags & MS_RDONLY)); - mutex_init(&sbi->mutex); mutex_init(&sbi->s_lock); spin_lock_init(&sbi->work_lock); INIT_DELAYED_WORK(&sbi->sync_work, delayed_sync_fs); @@ -1257,7 +1237,6 @@ magic_found: return 0; failed: - mutex_destroy(&sbi->mutex); if (ubh) ubh_brelse_uspi (uspi); kfree (uspi); @@ -1280,7 +1259,6 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) unsigned flags; sync_filesystem(sb); - lock_ufs(sb); mutex_lock(&UFS_SB(sb)->s_lock); uspi = UFS_SB(sb)->s_uspi; flags = UFS_SB(sb)->s_flags; @@ -1296,7 +1274,6 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) ufs_set_opt (new_mount_opt, ONERROR_LOCK); if (!ufs_parse_options (data, &new_mount_opt)) { mutex_unlock(&UFS_SB(sb)->s_lock); - unlock_ufs(sb); return -EINVAL; } if (!(new_mount_opt & UFS_MOUNT_UFSTYPE)) { @@ -1304,14 +1281,12 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) } else if ((new_mount_opt & UFS_MOUNT_UFSTYPE) != ufstype) { pr_err("ufstype can't be changed during remount\n"); mutex_unlock(&UFS_SB(sb)->s_lock); - unlock_ufs(sb); return -EINVAL; } if ((*mount_flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) { UFS_SB(sb)->s_mount_opt = new_mount_opt; mutex_unlock(&UFS_SB(sb)->s_lock); - unlock_ufs(sb); return 0; } @@ -1335,7 +1310,6 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) #ifndef CONFIG_UFS_FS_WRITE pr_err("ufs was compiled with read-only support, can't be mounted as read-write\n"); mutex_unlock(&UFS_SB(sb)->s_lock); - unlock_ufs(sb); return -EINVAL; #else if (ufstype != UFS_MOUNT_UFSTYPE_SUN && @@ -1345,13 +1319,11 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) ufstype != UFS_MOUNT_UFSTYPE_UFS2) { pr_err("this ufstype is read-only supported\n"); mutex_unlock(&UFS_SB(sb)->s_lock); - unlock_ufs(sb); return -EINVAL; } if (!ufs_read_cylinder_structures(sb)) { pr_err("failed during remounting\n"); mutex_unlock(&UFS_SB(sb)->s_lock); - unlock_ufs(sb); return -EPERM; } sb->s_flags &= ~MS_RDONLY; @@ -1359,7 +1331,6 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) } UFS_SB(sb)->s_mount_opt = new_mount_opt; mutex_unlock(&UFS_SB(sb)->s_lock); - unlock_ufs(sb); return 0; } @@ -1391,8 +1362,7 @@ static int ufs_statfs(struct dentry *dentry, struct kstatfs *buf) struct ufs_super_block_third *usb3; u64 id = huge_encode_dev(sb->s_bdev->bd_dev); - lock_ufs(sb); - + mutex_lock(&UFS_SB(sb)->s_lock); usb3 = ubh_get_usb_third(uspi); if ((flags & UFS_TYPE_MASK) == UFS_TYPE_UFS2) { @@ -1413,7 +1383,7 @@ static int ufs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_fsid.val[0] = (u32)id; buf->f_fsid.val[1] = (u32)(id >> 32); - unlock_ufs(sb); + mutex_unlock(&UFS_SB(sb)->s_lock); return 0; } @@ -1429,6 +1399,8 @@ static struct inode *ufs_alloc_inode(struct super_block *sb) return NULL; ei->vfs_inode.i_version = 1; + seqlock_init(&ei->meta_lock); + mutex_init(&ei->truncate_mutex); return &ei->vfs_inode; } diff --git a/fs/ufs/truncate.c b/fs/ufs/truncate.c deleted file mode 100644 index 21154704c168..000000000000 --- a/fs/ufs/truncate.c +++ /dev/null @@ -1,523 +0,0 @@ -/* - * linux/fs/ufs/truncate.c - * - * Copyright (C) 1998 - * Daniel Pirkl <daniel.pirkl@email.cz> - * Charles University, Faculty of Mathematics and Physics - * - * from - * - * linux/fs/ext2/truncate.c - * - * Copyright (C) 1992, 1993, 1994, 1995 - * Remy Card (card@masi.ibp.fr) - * Laboratoire MASI - Institut Blaise Pascal - * Universite Pierre et Marie Curie (Paris VI) - * - * from - * - * linux/fs/minix/truncate.c - * - * Copyright (C) 1991, 1992 Linus Torvalds - * - * Big-endian to little-endian byte-swapping/bitmaps by - * David S. Miller (davem@caip.rutgers.edu), 1995 - */ - -/* - * Real random numbers for secure rm added 94/02/18 - * Idea from Pierre del Perugia <delperug@gla.ecoledoc.ibp.fr> - */ - -/* - * Adoptation to use page cache and UFS2 write support by - * Evgeniy Dushistov <dushistov@mail.ru>, 2006-2007 - */ - -#include <linux/errno.h> -#include <linux/fs.h> -#include <linux/fcntl.h> -#include <linux/time.h> -#include <linux/stat.h> -#include <linux/string.h> -#include <linux/buffer_head.h> -#include <linux/blkdev.h> -#include <linux/sched.h> - -#include "ufs_fs.h" -#include "ufs.h" -#include "swab.h" -#include "util.h" - -/* - * Secure deletion currently doesn't work. It interacts very badly - * with buffers shared with memory mappings, and for that reason - * can't be done in the truncate() routines. It should instead be - * done separately in "release()" before calling the truncate routines - * that will release the actual file blocks. - * - * Linus - */ - -#define DIRECT_BLOCK ((inode->i_size + uspi->s_bsize - 1) >> uspi->s_bshift) -#define DIRECT_FRAGMENT ((inode->i_size + uspi->s_fsize - 1) >> uspi->s_fshift) - - -static int ufs_trunc_direct(struct inode *inode) -{ - struct ufs_inode_info *ufsi = UFS_I(inode); - struct super_block * sb; - struct ufs_sb_private_info * uspi; - void *p; - u64 frag1, frag2, frag3, frag4, block1, block2; - unsigned frag_to_free, free_count; - unsigned i, tmp; - int retry; - - UFSD("ENTER: ino %lu\n", inode->i_ino); - - sb = inode->i_sb; - uspi = UFS_SB(sb)->s_uspi; - - frag_to_free = 0; - free_count = 0; - retry = 0; - - frag1 = DIRECT_FRAGMENT; - frag4 = min_t(u64, UFS_NDIR_FRAGMENT, ufsi->i_lastfrag); - frag2 = ((frag1 & uspi->s_fpbmask) ? ((frag1 | uspi->s_fpbmask) + 1) : frag1); - frag3 = frag4 & ~uspi->s_fpbmask; - block1 = block2 = 0; - if (frag2 > frag3) { - frag2 = frag4; - frag3 = frag4 = 0; - } else if (frag2 < frag3) { - block1 = ufs_fragstoblks (frag2); - block2 = ufs_fragstoblks (frag3); - } - - UFSD("ino %lu, frag1 %llu, frag2 %llu, block1 %llu, block2 %llu," - " frag3 %llu, frag4 %llu\n", inode->i_ino, - (unsigned long long)frag1, (unsigned long long)frag2, - (unsigned long long)block1, (unsigned long long)block2, - (unsigned long long)frag3, (unsigned long long)frag4); - - if (frag1 >= frag2) - goto next1; - - /* - * Free first free fragments - */ - p = ufs_get_direct_data_ptr(uspi, ufsi, ufs_fragstoblks(frag1)); - tmp = ufs_data_ptr_to_cpu(sb, p); - if (!tmp ) - ufs_panic (sb, "ufs_trunc_direct", "internal error"); - frag2 -= frag1; - frag1 = ufs_fragnum (frag1); - - ufs_free_fragments(inode, tmp + frag1, frag2); - mark_inode_dirty(inode); - frag_to_free = tmp + frag1; - -next1: - /* - * Free whole blocks - */ - for (i = block1 ; i < block2; i++) { - p = ufs_get_direct_data_ptr(uspi, ufsi, i); - tmp = ufs_data_ptr_to_cpu(sb, p); - if (!tmp) - continue; - ufs_data_ptr_clear(uspi, p); - - if (free_count == 0) { - frag_to_free = tmp; - free_count = uspi->s_fpb; - } else if (free_count > 0 && frag_to_free == tmp - free_count) - free_count += uspi->s_fpb; - else { - ufs_free_blocks (inode, frag_to_free, free_count); - frag_to_free = tmp; - free_count = uspi->s_fpb; - } - mark_inode_dirty(inode); - } - - if (free_count > 0) - ufs_free_blocks (inode, frag_to_free, free_count); - - if (frag3 >= frag4) - goto next3; - - /* - * Free last free fragments - */ - p = ufs_get_direct_data_ptr(uspi, ufsi, ufs_fragstoblks(frag3)); - tmp = ufs_data_ptr_to_cpu(sb, p); - if (!tmp ) - ufs_panic(sb, "ufs_truncate_direct", "internal error"); - frag4 = ufs_fragnum (frag4); - ufs_data_ptr_clear(uspi, p); - - ufs_free_fragments (inode, tmp, frag4); - mark_inode_dirty(inode); - next3: - - UFSD("EXIT: ino %lu\n", inode->i_ino); - return retry; -} - - -static int ufs_trunc_indirect(struct inode *inode, u64 offset, void *p) -{ - struct super_block * sb; - struct ufs_sb_private_info * uspi; - struct ufs_buffer_head * ind_ubh; - void *ind; - u64 tmp, indirect_block, i, frag_to_free; - unsigned free_count; - int retry; - - UFSD("ENTER: ino %lu, offset %llu, p: %p\n", - inode->i_ino, (unsigned long long)offset, p); - - BUG_ON(!p); - - sb = inode->i_sb; - uspi = UFS_SB(sb)->s_uspi; - - frag_to_free = 0; - free_count = 0; - retry = 0; - - tmp = ufs_data_ptr_to_cpu(sb, p); - if (!tmp) - return 0; - ind_ubh = ubh_bread(sb, tmp, uspi->s_bsize); - if (tmp != ufs_data_ptr_to_cpu(sb, p)) { - ubh_brelse (ind_ubh); - return 1; - } - if (!ind_ubh) { - ufs_data_ptr_clear(uspi, p); - return 0; - } - - indirect_block = (DIRECT_BLOCK > offset) ? (DIRECT_BLOCK - offset) : 0; - for (i = indirect_block; i < uspi->s_apb; i++) { - ind = ubh_get_data_ptr(uspi, ind_ubh, i); - tmp = ufs_data_ptr_to_cpu(sb, ind); - if (!tmp) - continue; - - ufs_data_ptr_clear(uspi, ind); - ubh_mark_buffer_dirty(ind_ubh); - if (free_count == 0) { - frag_to_free = tmp; - free_count = uspi->s_fpb; - } else if (free_count > 0 && frag_to_free == tmp - free_count) - free_count += uspi->s_fpb; - else { - ufs_free_blocks (inode, frag_to_free, free_count); - frag_to_free = tmp; - free_count = uspi->s_fpb; - } - - mark_inode_dirty(inode); - } - - if (free_count > 0) { - ufs_free_blocks (inode, frag_to_free, free_count); - } - for (i = 0; i < uspi->s_apb; i++) - if (!ufs_is_data_ptr_zero(uspi, - ubh_get_data_ptr(uspi, ind_ubh, i))) - break; - if (i >= uspi->s_apb) { - tmp = ufs_data_ptr_to_cpu(sb, p); - ufs_data_ptr_clear(uspi, p); - - ufs_free_blocks (inode, tmp, uspi->s_fpb); - mark_inode_dirty(inode); - ubh_bforget(ind_ubh); - ind_ubh = NULL; - } - if (IS_SYNC(inode) && ind_ubh && ubh_buffer_dirty(ind_ubh)) - ubh_sync_block(ind_ubh); - ubh_brelse (ind_ubh); - - UFSD("EXIT: ino %lu\n", inode->i_ino); - - return retry; -} - -static int ufs_trunc_dindirect(struct inode *inode, u64 offset, void *p) -{ - struct super_block * sb; - struct ufs_sb_private_info * uspi; - struct ufs_buffer_head *dind_bh; - u64 i, tmp, dindirect_block; - void *dind; - int retry = 0; - - UFSD("ENTER: ino %lu\n", inode->i_ino); - - sb = inode->i_sb; - uspi = UFS_SB(sb)->s_uspi; - - dindirect_block = (DIRECT_BLOCK > offset) - ? ((DIRECT_BLOCK - offset) >> uspi->s_apbshift) : 0; - retry = 0; - - tmp = ufs_data_ptr_to_cpu(sb, p); - if (!tmp) - return 0; - dind_bh = ubh_bread(sb, tmp, uspi->s_bsize); - if (tmp != ufs_data_ptr_to_cpu(sb, p)) { - ubh_brelse (dind_bh); - return 1; - } - if (!dind_bh) { - ufs_data_ptr_clear(uspi, p); - return 0; - } - - for (i = dindirect_block ; i < uspi->s_apb ; i++) { - dind = ubh_get_data_ptr(uspi, dind_bh, i); - tmp = ufs_data_ptr_to_cpu(sb, dind); - if (!tmp) - continue; - retry |= ufs_trunc_indirect (inode, offset + (i << uspi->s_apbshift), dind); - ubh_mark_buffer_dirty(dind_bh); - } - - for (i = 0; i < uspi->s_apb; i++) - if (!ufs_is_data_ptr_zero(uspi, - ubh_get_data_ptr(uspi, dind_bh, i))) - break; - if (i >= uspi->s_apb) { - tmp = ufs_data_ptr_to_cpu(sb, p); - ufs_data_ptr_clear(uspi, p); - - ufs_free_blocks(inode, tmp, uspi->s_fpb); - mark_inode_dirty(inode); - ubh_bforget(dind_bh); - dind_bh = NULL; - } - if (IS_SYNC(inode) && dind_bh && ubh_buffer_dirty(dind_bh)) - ubh_sync_block(dind_bh); - ubh_brelse (dind_bh); - - UFSD("EXIT: ino %lu\n", inode->i_ino); - - return retry; -} - -static int ufs_trunc_tindirect(struct inode *inode) -{ - struct super_block *sb = inode->i_sb; - struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi; - struct ufs_inode_info *ufsi = UFS_I(inode); - struct ufs_buffer_head * tind_bh; - u64 tindirect_block, tmp, i; - void *tind, *p; - int retry; - - UFSD("ENTER: ino %lu\n", inode->i_ino); - - retry = 0; - - tindirect_block = (DIRECT_BLOCK > (UFS_NDADDR + uspi->s_apb + uspi->s_2apb)) - ? ((DIRECT_BLOCK - UFS_NDADDR - uspi->s_apb - uspi->s_2apb) >> uspi->s_2apbshift) : 0; - - p = ufs_get_direct_data_ptr(uspi, ufsi, UFS_TIND_BLOCK); - if (!(tmp = ufs_data_ptr_to_cpu(sb, p))) - return 0; - tind_bh = ubh_bread (sb, tmp, uspi->s_bsize); - if (tmp != ufs_data_ptr_to_cpu(sb, p)) { - ubh_brelse (tind_bh); - return 1; - } - if (!tind_bh) { - ufs_data_ptr_clear(uspi, p); - return 0; - } - - for (i = tindirect_block ; i < uspi->s_apb ; i++) { - tind = ubh_get_data_ptr(uspi, tind_bh, i); - retry |= ufs_trunc_dindirect(inode, UFS_NDADDR + - uspi->s_apb + ((i + 1) << uspi->s_2apbshift), tind); - ubh_mark_buffer_dirty(tind_bh); - } - for (i = 0; i < uspi->s_apb; i++) - if (!ufs_is_data_ptr_zero(uspi, - ubh_get_data_ptr(uspi, tind_bh, i))) - break; - if (i >= uspi->s_apb) { - tmp = ufs_data_ptr_to_cpu(sb, p); - ufs_data_ptr_clear(uspi, p); - - ufs_free_blocks(inode, tmp, uspi->s_fpb); - mark_inode_dirty(inode); - ubh_bforget(tind_bh); - tind_bh = NULL; - } - if (IS_SYNC(inode) && tind_bh && ubh_buffer_dirty(tind_bh)) - ubh_sync_block(tind_bh); - ubh_brelse (tind_bh); - - UFSD("EXIT: ino %lu\n", inode->i_ino); - return retry; -} - -static int ufs_alloc_lastblock(struct inode *inode) -{ - int err = 0; - struct super_block *sb = inode->i_sb; - struct address_space *mapping = inode->i_mapping; - struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi; - unsigned i, end; - sector_t lastfrag; - struct page *lastpage; - struct buffer_head *bh; - u64 phys64; - - lastfrag = (i_size_read(inode) + uspi->s_fsize - 1) >> uspi->s_fshift; - - if (!lastfrag) - goto out; - - lastfrag--; - - lastpage = ufs_get_locked_page(mapping, lastfrag >> - (PAGE_CACHE_SHIFT - inode->i_blkbits)); - if (IS_ERR(lastpage)) { - err = -EIO; - goto out; - } - - end = lastfrag & ((1 << (PAGE_CACHE_SHIFT - inode->i_blkbits)) - 1); - bh = page_buffers(lastpage); - for (i = 0; i < end; ++i) - bh = bh->b_this_page; - - - err = ufs_getfrag_block(inode, lastfrag, bh, 1); - - if (unlikely(err)) - goto out_unlock; - - if (buffer_new(bh)) { - clear_buffer_new(bh); - unmap_underlying_metadata(bh->b_bdev, - bh->b_blocknr); - /* - * we do not zeroize fragment, because of - * if it maped to hole, it already contains zeroes - */ - set_buffer_uptodate(bh); - mark_buffer_dirty(bh); - set_page_dirty(lastpage); - } - - if (lastfrag >= UFS_IND_FRAGMENT) { - end = uspi->s_fpb - ufs_fragnum(lastfrag) - 1; - phys64 = bh->b_blocknr + 1; - for (i = 0; i < end; ++i) { - bh = sb_getblk(sb, i + phys64); - lock_buffer(bh); - memset(bh->b_data, 0, sb->s_blocksize); - set_buffer_uptodate(bh); - mark_buffer_dirty(bh); - unlock_buffer(bh); - sync_dirty_buffer(bh); - brelse(bh); - } - } -out_unlock: - ufs_put_locked_page(lastpage); -out: - return err; -} - -int ufs_truncate(struct inode *inode, loff_t old_i_size) -{ - struct ufs_inode_info *ufsi = UFS_I(inode); - struct super_block *sb = inode->i_sb; - struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi; - int retry, err = 0; - - UFSD("ENTER: ino %lu, i_size: %llu, old_i_size: %llu\n", - inode->i_ino, (unsigned long long)i_size_read(inode), - (unsigned long long)old_i_size); - - if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || - S_ISLNK(inode->i_mode))) - return -EINVAL; - if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) - return -EPERM; - - err = ufs_alloc_lastblock(inode); - - if (err) { - i_size_write(inode, old_i_size); - goto out; - } - - block_truncate_page(inode->i_mapping, inode->i_size, ufs_getfrag_block); - - while (1) { - retry = ufs_trunc_direct(inode); - retry |= ufs_trunc_indirect(inode, UFS_IND_BLOCK, - ufs_get_direct_data_ptr(uspi, ufsi, - UFS_IND_BLOCK)); - retry |= ufs_trunc_dindirect(inode, UFS_IND_BLOCK + uspi->s_apb, - ufs_get_direct_data_ptr(uspi, ufsi, - UFS_DIND_BLOCK)); - retry |= ufs_trunc_tindirect (inode); - if (!retry) - break; - if (IS_SYNC(inode) && (inode->i_state & I_DIRTY)) - ufs_sync_inode (inode); - yield(); - } - - inode->i_mtime = inode->i_ctime = CURRENT_TIME_SEC; - ufsi->i_lastfrag = DIRECT_FRAGMENT; - mark_inode_dirty(inode); -out: - UFSD("EXIT: err %d\n", err); - return err; -} - -int ufs_setattr(struct dentry *dentry, struct iattr *attr) -{ - struct inode *inode = d_inode(dentry); - unsigned int ia_valid = attr->ia_valid; - int error; - - error = inode_change_ok(inode, attr); - if (error) - return error; - - if (ia_valid & ATTR_SIZE && attr->ia_size != inode->i_size) { - loff_t old_i_size = inode->i_size; - - /* XXX(truncate): truncate_setsize should be called last */ - truncate_setsize(inode, attr->ia_size); - - lock_ufs(inode->i_sb); - error = ufs_truncate(inode, old_i_size); - unlock_ufs(inode->i_sb); - if (error) - return error; - } - - setattr_copy(inode, attr); - mark_inode_dirty(inode); - return 0; -} - -const struct inode_operations ufs_file_inode_operations = { - .setattr = ufs_setattr, -}; diff --git a/fs/ufs/ufs.h b/fs/ufs/ufs.h index 2e31ea2e35a3..7da4aca868c0 100644 --- a/fs/ufs/ufs.h +++ b/fs/ufs/ufs.h @@ -24,8 +24,6 @@ struct ufs_sb_info { unsigned s_cgno[UFS_MAX_GROUP_LOADED]; unsigned short s_cg_loaded; unsigned s_mount_opt; - struct mutex mutex; - struct task_struct *mutex_owner; struct super_block *sb; int work_queued; /* non-zero if the delayed work is queued */ struct delayed_work sync_work; /* FS sync delayed work */ @@ -46,6 +44,8 @@ struct ufs_inode_info { __u32 i_oeftflag; __u16 i_osync; __u64 i_lastfrag; + seqlock_t meta_lock; + struct mutex truncate_mutex; __u32 i_dir_start_lookup; struct inode vfs_inode; }; @@ -122,7 +122,7 @@ extern struct inode *ufs_iget(struct super_block *, unsigned long); extern int ufs_write_inode (struct inode *, struct writeback_control *); extern int ufs_sync_inode (struct inode *); extern void ufs_evict_inode (struct inode *); -extern int ufs_getfrag_block (struct inode *inode, sector_t fragment, struct buffer_head *bh_result, int create); +extern int ufs_setattr(struct dentry *dentry, struct iattr *attr); /* namei.c */ extern const struct file_operations ufs_dir_operations; @@ -140,10 +140,6 @@ void ufs_mark_sb_dirty(struct super_block *sb); extern const struct inode_operations ufs_fast_symlink_inode_operations; extern const struct inode_operations ufs_symlink_inode_operations; -/* truncate.c */ -extern int ufs_truncate (struct inode *, loff_t); -extern int ufs_setattr(struct dentry *dentry, struct iattr *attr); - static inline struct ufs_sb_info *UFS_SB(struct super_block *sb) { return sb->s_fs_info; @@ -170,7 +166,4 @@ static inline u32 ufs_dtogd(struct ufs_sb_private_info * uspi, u64 b) return do_div(b, uspi->s_fpg); } -extern void lock_ufs(struct super_block *sb); -extern void unlock_ufs(struct super_block *sb); - #endif /* _UFS_UFS_H */ diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 3859f5e27a4d..9bbb3507376a 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -119,8 +119,7 @@ xfs_setfilesize_trans_alloc( * We may pass freeze protection with a transaction. So tell lockdep * we released it. */ - rwsem_release(&ioend->io_inode->i_sb->s_writers.lock_map[SB_FREEZE_FS-1], - 1, _THIS_IP_); + __sb_writers_release(ioend->io_inode->i_sb, SB_FREEZE_FS); /* * We hand off the transaction to the completion thread now, so * clear the flag here. @@ -171,8 +170,7 @@ xfs_setfilesize_ioend( * Similarly for freeze protection. */ current_set_flags_nested(&tp->t_pflags, PF_FSTRANS); - rwsem_acquire_read(&VFS_I(ip)->i_sb->s_writers.lock_map[SB_FREEZE_FS-1], - 0, 1, _THIS_IP_); + __sb_writers_acquired(VFS_I(ip)->i_sb, SB_FREEZE_FS); return xfs_setfilesize(ip, tp, ioend->io_offset, ioend->io_size); } diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h index 45c39a37f924..8bc073d297db 100644 --- a/include/drm/drm_pciids.h +++ b/include/drm/drm_pciids.h @@ -172,6 +172,7 @@ {0x1002, 0x6610, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6611, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6613, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6617, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6620, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6621, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6623, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ diff --git a/include/linux/fs.h b/include/linux/fs.h index 34cfa60db678..9b85aa5c7a70 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1,7 +1,6 @@ #ifndef _LINUX_FS_H #define _LINUX_FS_H - #include <linux/linkage.h> #include <linux/wait.h> #include <linux/kdev_t.h> @@ -30,6 +29,8 @@ #include <linux/lockdep.h> #include <linux/percpu-rwsem.h> #include <linux/blk_types.h> +#include <linux/workqueue.h> +#include <linux/percpu-rwsem.h> #include <asm/byteorder.h> #include <uapi/linux/fs.h> @@ -1274,16 +1275,9 @@ enum { #define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1) struct sb_writers { - /* Counters for counting writers at each level */ - struct percpu_counter counter[SB_FREEZE_LEVELS]; - wait_queue_head_t wait; /* queue for waiting for - writers / faults to finish */ - int frozen; /* Is sb frozen? */ - wait_queue_head_t wait_unfrozen; /* queue for waiting for - sb to be thawed */ -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map lock_map[SB_FREEZE_LEVELS]; -#endif + int frozen; /* Is sb frozen? */ + wait_queue_head_t wait_unfrozen; /* for get_super_thawed() */ + struct percpu_rw_semaphore rw_sem[SB_FREEZE_LEVELS]; }; struct super_block { @@ -1374,6 +1368,7 @@ struct super_block { struct list_lru s_dentry_lru ____cacheline_aligned_in_smp; struct list_lru s_inode_lru ____cacheline_aligned_in_smp; struct rcu_head rcu; + struct work_struct destroy_work; struct mutex s_sync_lock; /* sync serialisation lock */ @@ -1396,6 +1391,11 @@ extern struct timespec current_fs_time(struct super_block *sb); void __sb_end_write(struct super_block *sb, int level); int __sb_start_write(struct super_block *sb, int level, bool wait); +#define __sb_writers_acquired(sb, lev) \ + percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) +#define __sb_writers_release(sb, lev) \ + percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) + /** * sb_end_write - drop write access to a superblock * @sb: the super we wrote to diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h index 3e88c9a7d57f..834c4e52cb2d 100644 --- a/include/linux/percpu-rwsem.h +++ b/include/linux/percpu-rwsem.h @@ -16,6 +16,7 @@ struct percpu_rw_semaphore { }; extern void percpu_down_read(struct percpu_rw_semaphore *); +extern int percpu_down_read_trylock(struct percpu_rw_semaphore *); extern void percpu_up_read(struct percpu_rw_semaphore *); extern void percpu_down_write(struct percpu_rw_semaphore *); @@ -31,4 +32,23 @@ extern void percpu_free_rwsem(struct percpu_rw_semaphore *); __percpu_init_rwsem(brw, #brw, &rwsem_key); \ }) + +#define percpu_rwsem_is_held(sem) lockdep_is_held(&(sem)->rw_sem) + +static inline void percpu_rwsem_release(struct percpu_rw_semaphore *sem, + bool read, unsigned long ip) +{ + lock_release(&sem->rw_sem.dep_map, 1, ip); +#ifdef CONFIG_RWSEM_SPIN_ON_OWNER + if (!read) + sem->rw_sem.owner = NULL; +#endif +} + +static inline void percpu_rwsem_acquire(struct percpu_rw_semaphore *sem, + bool read, unsigned long ip) +{ + lock_acquire(&sem->rw_sem.dep_map, 0, 1, read, 1, NULL, ip); +} + #endif diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d6cdd6e87d53..22b6d9ca1654 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2884,11 +2884,11 @@ static inline bool skb_defer_rx_timestamp(struct sk_buff *skb) * * PHY drivers may accept clones of transmitted packets for * timestamping via their phy_driver.txtstamp method. These drivers - * must call this function to return the skb back to the stack, with - * or without a timestamp. + * must call this function to return the skb back to the stack with a + * timestamp. * * @skb: clone of the the original outgoing packet - * @hwtstamps: hardware time stamps, may be NULL if not available + * @hwtstamps: hardware time stamps * */ void skb_complete_tx_timestamp(struct sk_buff *skb, diff --git a/init/Kconfig b/init/Kconfig index af09b4fb43d2..288c0122c2a5 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -925,7 +925,6 @@ config NUMA_BALANCING_DEFAULT_ENABLED menuconfig CGROUPS bool "Control Group support" select KERNFS - select PERCPU_RWSEM help This option adds support for grouping sets of processes together, for use with process control subsystems such as Cpusets, CFS, memory diff --git a/ipc/sem.c b/ipc/sem.c index bc3d530cb23e..b471e5a3863d 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -253,6 +253,16 @@ static void sem_rcu_free(struct rcu_head *head) } /* + * spin_unlock_wait() and !spin_is_locked() are not memory barriers, they + * are only control barriers. + * The code must pair with spin_unlock(&sem->lock) or + * spin_unlock(&sem_perm.lock), thus just the control barrier is insufficient. + * + * smp_rmb() is sufficient, as writes cannot pass the control barrier. + */ +#define ipc_smp_acquire__after_spin_is_unlocked() smp_rmb() + +/* * Wait until all currently ongoing simple ops have completed. * Caller must own sem_perm.lock. * New simple ops cannot start, because simple ops first check @@ -275,6 +285,7 @@ static void sem_wait_array(struct sem_array *sma) sem = sma->sem_base + i; spin_unlock_wait(&sem->lock); } + ipc_smp_acquire__after_spin_is_unlocked(); } /* @@ -327,13 +338,12 @@ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops, /* Then check that the global lock is free */ if (!spin_is_locked(&sma->sem_perm.lock)) { /* - * The ipc object lock check must be visible on all - * cores before rechecking the complex count. Otherwise - * we can race with another thread that does: + * We need a memory barrier with acquire semantics, + * otherwise we can race with another thread that does: * complex_count++; * spin_unlock(sem_perm.lock); */ - smp_rmb(); + ipc_smp_acquire__after_spin_is_unlocked(); /* * Now repeat the test of complex_count: @@ -2074,17 +2084,28 @@ void exit_sem(struct task_struct *tsk) rcu_read_lock(); un = list_entry_rcu(ulp->list_proc.next, struct sem_undo, list_proc); - if (&un->list_proc == &ulp->list_proc) - semid = -1; - else - semid = un->semid; + if (&un->list_proc == &ulp->list_proc) { + /* + * We must wait for freeary() before freeing this ulp, + * in case we raced with last sem_undo. There is a small + * possibility where we exit while freeary() didn't + * finish unlocking sem_undo_list. + */ + spin_unlock_wait(&ulp->lock); + rcu_read_unlock(); + break; + } + spin_lock(&ulp->lock); + semid = un->semid; + spin_unlock(&ulp->lock); + /* exit_sem raced with IPC_RMID, nothing to do */ if (semid == -1) { rcu_read_unlock(); - break; + continue; } - sma = sem_obtain_object_check(tsk->nsproxy->ipc_ns, un->semid); + sma = sem_obtain_object_check(tsk->nsproxy->ipc_ns, semid); /* exit_sem raced with IPC_RMID, nothing to do */ if (IS_ERR(sma)) { rcu_read_unlock(); @@ -2112,9 +2133,11 @@ void exit_sem(struct task_struct *tsk) ipc_assert_locked_object(&sma->sem_perm); list_del(&un->list_id); - spin_lock(&ulp->lock); + /* we are the last process using this ulp, acquiring ulp->lock + * isn't required. Besides that, we are also protected against + * IPC_RMID as we hold sma->sem_perm lock now + */ list_del_rcu(&un->list_proc); - spin_unlock(&ulp->lock); /* perform adjustments registered in un */ for (i = 0; i < sma->sem_nsems; i++) { diff --git a/kernel/events/core.c b/kernel/events/core.c index d3dae3419b99..e6feb5114134 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1868,8 +1868,6 @@ event_sched_in(struct perf_event *event, perf_pmu_disable(event->pmu); - event->tstamp_running += tstamp - event->tstamp_stopped; - perf_set_shadow_time(event, ctx, tstamp); perf_log_itrace_start(event); @@ -1881,6 +1879,8 @@ event_sched_in(struct perf_event *event, goto out; } + event->tstamp_running += tstamp - event->tstamp_stopped; + if (!is_software_event(event)) cpuctx->active_oncpu++; if (!ctx->nr_active++) @@ -3958,28 +3958,21 @@ static void perf_event_for_each(struct perf_event *event, perf_event_for_each_child(sibling, func); } -static int perf_event_period(struct perf_event *event, u64 __user *arg) -{ - struct perf_event_context *ctx = event->ctx; - int ret = 0, active; +struct period_event { + struct perf_event *event; u64 value; +}; - if (!is_sampling_event(event)) - return -EINVAL; - - if (copy_from_user(&value, arg, sizeof(value))) - return -EFAULT; - - if (!value) - return -EINVAL; +static int __perf_event_period(void *info) +{ + struct period_event *pe = info; + struct perf_event *event = pe->event; + struct perf_event_context *ctx = event->ctx; + u64 value = pe->value; + bool active; - raw_spin_lock_irq(&ctx->lock); + raw_spin_lock(&ctx->lock); if (event->attr.freq) { - if (value > sysctl_perf_event_sample_rate) { - ret = -EINVAL; - goto unlock; - } - event->attr.sample_freq = value; } else { event->attr.sample_period = value; @@ -3998,11 +3991,53 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg) event->pmu->start(event, PERF_EF_RELOAD); perf_pmu_enable(ctx->pmu); } + raw_spin_unlock(&ctx->lock); -unlock: + return 0; +} + +static int perf_event_period(struct perf_event *event, u64 __user *arg) +{ + struct period_event pe = { .event = event, }; + struct perf_event_context *ctx = event->ctx; + struct task_struct *task; + u64 value; + + if (!is_sampling_event(event)) + return -EINVAL; + + if (copy_from_user(&value, arg, sizeof(value))) + return -EFAULT; + + if (!value) + return -EINVAL; + + if (event->attr.freq && value > sysctl_perf_event_sample_rate) + return -EINVAL; + + task = ctx->task; + pe.value = value; + + if (!task) { + cpu_function_call(event->cpu, __perf_event_period, &pe); + return 0; + } + +retry: + if (!task_function_call(task, __perf_event_period, &pe)) + return 0; + + raw_spin_lock_irq(&ctx->lock); + if (ctx->is_active) { + raw_spin_unlock_irq(&ctx->lock); + task = ctx->task; + goto retry; + } + + __perf_event_period(&pe); raw_spin_unlock_irq(&ctx->lock); - return ret; + return 0; } static const struct file_operations perf_fops; @@ -4740,12 +4775,20 @@ static const struct file_operations perf_fops = { * to user-space before waking everybody up. */ +static inline struct fasync_struct **perf_event_fasync(struct perf_event *event) +{ + /* only the parent has fasync state */ + if (event->parent) + event = event->parent; + return &event->fasync; +} + void perf_event_wakeup(struct perf_event *event) { ring_buffer_wakeup(event); if (event->pending_kill) { - kill_fasync(&event->fasync, SIGIO, event->pending_kill); + kill_fasync(perf_event_fasync(event), SIGIO, event->pending_kill); event->pending_kill = 0; } } @@ -6124,7 +6167,7 @@ static int __perf_event_overflow(struct perf_event *event, else perf_event_output(event, data, regs); - if (event->fasync && event->pending_kill) { + if (*perf_event_fasync(event) && event->pending_kill) { event->pending_wakeup = 1; irq_work_queue(&event->pending); } diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index b2be01b1aa9d..c8aa3f75bc4d 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -559,11 +559,13 @@ static void __rb_free_aux(struct ring_buffer *rb) rb->aux_priv = NULL; } - for (pg = 0; pg < rb->aux_nr_pages; pg++) - rb_free_aux_page(rb, pg); + if (rb->aux_nr_pages) { + for (pg = 0; pg < rb->aux_nr_pages; pg++) + rb_free_aux_page(rb, pg); - kfree(rb->aux_pages); - rb->aux_nr_pages = 0; + kfree(rb->aux_pages); + rb->aux_nr_pages = 0; + } } void rb_free_aux(struct ring_buffer *rb) diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile index 7dd5c9918e4c..4c6a97e1a849 100644 --- a/kernel/locking/Makefile +++ b/kernel/locking/Makefile @@ -1,5 +1,5 @@ -obj-y += mutex.o semaphore.o rwsem.o +obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_lockdep.o = $(CC_FLAGS_FTRACE) @@ -25,6 +25,5 @@ obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o -obj-$(CONFIG_PERCPU_RWSEM) += percpu-rwsem.o obj-$(CONFIG_QUEUED_RWLOCKS) += qrwlock.o obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c index 652a8ee8efe9..f32567254867 100644 --- a/kernel/locking/percpu-rwsem.c +++ b/kernel/locking/percpu-rwsem.c @@ -88,6 +88,19 @@ void percpu_down_read(struct percpu_rw_semaphore *brw) __up_read(&brw->rw_sem); } +int percpu_down_read_trylock(struct percpu_rw_semaphore *brw) +{ + if (unlikely(!update_fast_ctr(brw, +1))) { + if (!__down_read_trylock(&brw->rw_sem)) + return 0; + atomic_inc(&brw->slow_read_ctr); + __up_read(&brw->rw_sem); + } + + rwsem_acquire_read(&brw->rw_sem.dep_map, 0, 1, _RET_IP_); + return 1; +} + void percpu_up_read(struct percpu_rw_semaphore *brw) { rwsem_release(&brw->rw_sem.dep_map, 1, _RET_IP_); diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h index 04ab18151cc8..df19ae4debd0 100644 --- a/kernel/locking/qspinlock_paravirt.h +++ b/kernel/locking/qspinlock_paravirt.h @@ -4,6 +4,7 @@ #include <linux/hash.h> #include <linux/bootmem.h> +#include <linux/debug_locks.h> /* * Implement paravirt qspinlocks; the general idea is to halt the vcpus instead @@ -286,15 +287,23 @@ __visible void __pv_queued_spin_unlock(struct qspinlock *lock) { struct __qspinlock *l = (void *)lock; struct pv_node *node; + u8 lockval = cmpxchg(&l->locked, _Q_LOCKED_VAL, 0); /* * We must not unlock if SLOW, because in that case we must first * unhash. Otherwise it would be possible to have multiple @lock * entries, which would be BAD. */ - if (likely(cmpxchg(&l->locked, _Q_LOCKED_VAL, 0) == _Q_LOCKED_VAL)) + if (likely(lockval == _Q_LOCKED_VAL)) return; + if (unlikely(lockval != _Q_SLOW_VAL)) { + if (debug_locks_silent) + return; + WARN(1, "pvqspinlock: lock %p has corrupted value 0x%x!\n", lock, atomic_read(&lock->val)); + return; + } + /* * Since the above failed to release, this must be the SLOW path. * Therefore start by looking up the blocked node and unhashing it. diff --git a/lib/Kconfig b/lib/Kconfig index 3a2ef67db6c7..f6aa03dc1576 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -53,9 +53,6 @@ config GENERIC_IO config STMP_DEVICE bool -config PERCPU_RWSEM - bool - config ARCH_USE_CMPXCHG_LOCKREF bool @@ -16,7 +16,7 @@ struct cma { extern struct cma cma_areas[MAX_CMA_AREAS]; extern unsigned cma_area_count; -static unsigned long cma_bitmap_maxno(struct cma *cma) +static inline unsigned long cma_bitmap_maxno(struct cma *cma) { return cma->count >> cma->order_per_bit; } diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c index 6c513a63ea84..7b28e9cdf1c7 100644 --- a/mm/kasan/kasan.c +++ b/mm/kasan/kasan.c @@ -2,7 +2,7 @@ * This file contains shadow memory manipulation code. * * Copyright (c) 2014 Samsung Electronics Co., Ltd. - * Author: Andrey Ryabinin <a.ryabinin@samsung.com> + * Author: Andrey Ryabinin <ryabinin.a.a@gmail.com> * * Some of code borrowed from https://github.com/xairy/linux by * Andrey Konovalov <adech.fo@gmail.com> diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 680ceedf810a..e07c94fbd0ac 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -2,7 +2,7 @@ * This file contains error reporting code. * * Copyright (c) 2014 Samsung Electronics Co., Ltd. - * Author: Andrey Ryabinin <a.ryabinin@samsung.com> + * Author: Andrey Ryabinin <ryabinin.a.a@gmail.com> * * Some of code borrowed from https://github.com/xairy/linux by * Andrey Konovalov <adech.fo@gmail.com> diff --git a/mm/memory-failure.c b/mm/memory-failure.c index ea5a93659488..1f4446a90cef 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1146,8 +1146,11 @@ int memory_failure(unsigned long pfn, int trapno, int flags) } if (!PageHuge(p) && PageTransHuge(hpage)) { - if (unlikely(split_huge_page(hpage))) { - pr_err("MCE: %#lx: thp split failed\n", pfn); + if (!PageAnon(hpage) || unlikely(split_huge_page(hpage))) { + if (!PageAnon(hpage)) + pr_err("MCE: %#lx: non anonymous thp\n", pfn); + else + pr_err("MCE: %#lx: thp split failed\n", pfn); if (TestClearPageHWPoison(p)) atomic_long_sub(nr_pages, &num_poisoned_pages); put_page(p); @@ -1538,6 +1541,8 @@ static int get_any_page(struct page *page, unsigned long pfn, int flags) */ ret = __get_any_page(page, pfn, 0); if (!PageLRU(page)) { + /* Drop page reference which is from __get_any_page() */ + put_page(page); pr_info("soft_offline: %#lx: unknown non LRU page type %lx\n", pfn, page->flags); return -EIO; @@ -1567,13 +1572,12 @@ static int soft_offline_huge_page(struct page *page, int flags) unlock_page(hpage); ret = isolate_huge_page(hpage, &pagelist); - if (ret) { - /* - * get_any_page() and isolate_huge_page() takes a refcount each, - * so need to drop one here. - */ - put_page(hpage); - } else { + /* + * get_any_page() and isolate_huge_page() takes a refcount each, + * so need to drop one here. + */ + put_page(hpage); + if (!ret) { pr_info("soft offline: %#lx hugepage failed to isolate\n", pfn); return -EBUSY; } diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 003dbe4b060d..6da82bcb0a8b 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1277,6 +1277,7 @@ int __ref add_memory(int nid, u64 start, u64 size) /* create new memmap entry */ firmware_map_add_hotplug(start, start + size, "System RAM"); + memblock_add_node(start, size, nid); goto out; @@ -2013,6 +2014,8 @@ void __ref remove_memory(int nid, u64 start, u64 size) /* remove memmap entry */ firmware_map_remove(start, start + size, "System RAM"); + memblock_free(start, size); + memblock_remove(start, size); arch_remove_memory(start, size); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index beda41710802..df959b7d6085 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5060,6 +5060,10 @@ static unsigned long __meminit zone_spanned_pages_in_node(int nid, { unsigned long zone_start_pfn, zone_end_pfn; + /* When hotadd a new node, the node should be empty */ + if (!node_start_pfn && !node_end_pfn) + return 0; + /* Get the start and end of the zone */ zone_start_pfn = arch_zone_lowest_possible_pfn[zone_type]; zone_end_pfn = arch_zone_highest_possible_pfn[zone_type]; @@ -5123,6 +5127,10 @@ static unsigned long __meminit zone_absent_pages_in_node(int nid, unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type]; unsigned long zone_start_pfn, zone_end_pfn; + /* When hotadd a new node, the node should be empty */ + if (!node_start_pfn && !node_end_pfn) + return 0; + zone_start_pfn = clamp(node_start_pfn, zone_low, zone_high); zone_end_pfn = clamp(node_end_pfn, zone_low, zone_high); diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index fb54e6aed096..6d0b471eede8 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -1138,6 +1138,9 @@ void batadv_dat_snoop_outgoing_arp_reply(struct batadv_priv *bat_priv, * @bat_priv: the bat priv with all the soft interface information * @skb: packet to check * @hdr_size: size of the encapsulation header + * + * Returns true if the packet was snooped and consumed by DAT. False if the + * packet has to be delivered to the interface */ bool batadv_dat_snoop_incoming_arp_reply(struct batadv_priv *bat_priv, struct sk_buff *skb, int hdr_size) @@ -1145,7 +1148,7 @@ bool batadv_dat_snoop_incoming_arp_reply(struct batadv_priv *bat_priv, uint16_t type; __be32 ip_src, ip_dst; uint8_t *hw_src, *hw_dst; - bool ret = false; + bool dropped = false; unsigned short vid; if (!atomic_read(&bat_priv->distributed_arp_table)) @@ -1174,12 +1177,17 @@ bool batadv_dat_snoop_incoming_arp_reply(struct batadv_priv *bat_priv, /* if this REPLY is directed to a client of mine, let's deliver the * packet to the interface */ - ret = !batadv_is_my_client(bat_priv, hw_dst, vid); + dropped = !batadv_is_my_client(bat_priv, hw_dst, vid); + + /* if this REPLY is sent on behalf of a client of mine, let's drop the + * packet because the client will reply by itself + */ + dropped |= batadv_is_my_client(bat_priv, hw_src, vid); out: - if (ret) + if (dropped) kfree_skb(skb); - /* if ret == false -> packet has to be delivered to the interface */ - return ret; + /* if dropped == false -> deliver to the interface */ + return dropped; } /** diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index bb0158620628..cffa92dd9877 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -439,6 +439,8 @@ static void batadv_gw_node_add(struct batadv_priv *bat_priv, INIT_HLIST_NODE(&gw_node->list); gw_node->orig_node = orig_node; + gw_node->bandwidth_down = ntohl(gateway->bandwidth_down); + gw_node->bandwidth_up = ntohl(gateway->bandwidth_up); atomic_set(&gw_node->refcount, 1); spin_lock_bh(&bat_priv->gw.list_lock); diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index c002961da75d..a2fc843c2243 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -479,6 +479,9 @@ out: */ void batadv_softif_vlan_free_ref(struct batadv_softif_vlan *vlan) { + if (!vlan) + return; + if (atomic_dec_and_test(&vlan->refcount)) { spin_lock_bh(&vlan->bat_priv->softif_vlan_list_lock); hlist_del_rcu(&vlan->list); diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index b4824951010b..5e953297d3b2 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -594,6 +594,9 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, /* increase the refcounter of the related vlan */ vlan = batadv_softif_vlan_get(bat_priv, vid); + if (WARN(!vlan, "adding TT local entry %pM to non-existent VLAN %d", + addr, BATADV_PRINT_VID(vid))) + goto out; batadv_dbg(BATADV_DBG_TT, bat_priv, "Creating new local tt entry: %pM (vid: %d, ttvn: %d)\n", @@ -1034,6 +1037,7 @@ 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; + void *tt_entry_exists; tt_local_entry = batadv_tt_local_hash_find(bat_priv, addr, vid); if (!tt_local_entry) @@ -1061,11 +1065,22 @@ uint16_t batadv_tt_local_remove(struct batadv_priv *bat_priv, * immediately purge it */ batadv_tt_local_event(bat_priv, tt_local_entry, BATADV_TT_CLIENT_DEL); - hlist_del_rcu(&tt_local_entry->common.hash_entry); + + tt_entry_exists = batadv_hash_remove(bat_priv->tt.local_hash, + batadv_compare_tt, + batadv_choose_tt, + &tt_local_entry->common); + if (!tt_entry_exists) + goto out; + + /* extra call to free the local tt 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); + if (!vlan) + goto out; + batadv_softif_vlan_free_ref(vlan); batadv_softif_vlan_free_ref(vlan); @@ -1166,8 +1181,10 @@ static void batadv_tt_local_table_free(struct batadv_priv *bat_priv) /* 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); + if (vlan) { + batadv_softif_vlan_free_ref(vlan); + batadv_softif_vlan_free_ref(vlan); + } batadv_tt_local_entry_free_ref(tt_local); } @@ -3207,8 +3224,10 @@ static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv) /* 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); + if (vlan) { + batadv_softif_vlan_free_ref(vlan); + batadv_softif_vlan_free_ref(vlan); + } batadv_tt_local_entry_free_ref(tt_local); } diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 7998fb279165..92720f3fe573 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -7820,7 +7820,7 @@ void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent) /* Make sure we copy only the significant bytes based on the * encryption key size, and set the rest of the value to zeroes. */ - memcpy(ev.key.val, key->val, sizeof(key->enc_size)); + memcpy(ev.key.val, key->val, key->enc_size); memset(ev.key.val + key->enc_size, 0, sizeof(ev.key.val) - key->enc_size); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 3da5525eb8a2..4d74a0639c4c 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -112,6 +112,8 @@ static inline size_t br_port_info_size(void) + nla_total_size(1) /* IFLA_BRPORT_FAST_LEAVE */ + nla_total_size(1) /* IFLA_BRPORT_LEARNING */ + nla_total_size(1) /* IFLA_BRPORT_UNICAST_FLOOD */ + + nla_total_size(1) /* IFLA_BRPORT_PROXYARP */ + + nla_total_size(1) /* IFLA_BRPORT_PROXYARP_WIFI */ + 0; } @@ -506,6 +508,8 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_FAST_LEAVE]= { .type = NLA_U8 }, [IFLA_BRPORT_LEARNING] = { .type = NLA_U8 }, [IFLA_BRPORT_UNICAST_FLOOD] = { .type = NLA_U8 }, + [IFLA_BRPORT_PROXYARP] = { .type = NLA_U8 }, + [IFLA_BRPORT_PROXYARP_WIFI] = { .type = NLA_U8 }, }; /* Change the state of the port and notify spanning tree */ diff --git a/net/core/datagram.c b/net/core/datagram.c index 4967262b2707..617088aee21d 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -131,12 +131,12 @@ out_noerr: goto out; } -static int skb_set_peeked(struct sk_buff *skb) +static struct sk_buff *skb_set_peeked(struct sk_buff *skb) { struct sk_buff *nskb; if (skb->peeked) - return 0; + return skb; /* We have to unshare an skb before modifying it. */ if (!skb_shared(skb)) @@ -144,7 +144,7 @@ static int skb_set_peeked(struct sk_buff *skb) nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) - return -ENOMEM; + return ERR_PTR(-ENOMEM); skb->prev->next = nskb; skb->next->prev = nskb; @@ -157,7 +157,7 @@ static int skb_set_peeked(struct sk_buff *skb) done: skb->peeked = 1; - return 0; + return skb; } /** @@ -229,8 +229,9 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags, continue; } - error = skb_set_peeked(skb); - if (error) + skb = skb_set_peeked(skb); + error = PTR_ERR(skb); + if (IS_ERR(skb)) goto unlock_err; atomic_inc(&skb->users); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 1ebdf1c0d118..1cbd209192ea 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3514,8 +3514,6 @@ static int pktgen_thread_worker(void *arg) set_freezable(); - __set_current_state(TASK_RUNNING); - while (!kthread_should_stop()) { pkt_dev = next_to_run(t); @@ -3560,7 +3558,6 @@ static int pktgen_thread_worker(void *arg) try_to_freeze(); } - set_current_state(TASK_INTERRUPTIBLE); pr_debug("%s stopping all device\n", t->tsk->comm); pktgen_stop(t); diff --git a/net/core/request_sock.c b/net/core/request_sock.c index 87b22c0bc08c..b42f0e26f89e 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -103,10 +103,16 @@ void reqsk_queue_destroy(struct request_sock_queue *queue) spin_lock_bh(&queue->syn_wait_lock); while ((req = lopt->syn_table[i]) != NULL) { lopt->syn_table[i] = req->dl_next; + /* Because of following del_timer_sync(), + * we must release the spinlock here + * or risk a dead lock. + */ + spin_unlock_bh(&queue->syn_wait_lock); atomic_inc(&lopt->qlen_dec); - if (del_timer(&req->rsk_timer)) + if (del_timer_sync(&req->rsk_timer)) reqsk_put(req); reqsk_put(req); + spin_lock_bh(&queue->syn_wait_lock); } spin_unlock_bh(&queue->syn_wait_lock); } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 0917123790ea..35c47ddd04f0 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -756,7 +756,8 @@ static int dsa_slave_phy_connect(struct dsa_slave_priv *p, return -ENODEV; /* Use already configured phy mode */ - p->phy_interface = p->phy->interface; + if (p->phy_interface == PHY_INTERFACE_MODE_NA) + p->phy_interface = p->phy->interface; phy_connect_direct(slave_dev, p->phy, dsa_slave_adjust_link, p->phy_interface); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 60021d0d9326..05e3145f7dc3 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -593,7 +593,7 @@ static bool reqsk_queue_unlink(struct request_sock_queue *queue, } spin_unlock(&queue->syn_wait_lock); - if (del_timer(&req->rsk_timer)) + if (del_timer_sync(&req->rsk_timer)) reqsk_put(req); return found; } diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index fe8cc183411e..95ea633e8356 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -226,7 +226,8 @@ synproxy_send_client_ack(const struct synproxy_net *snet, synproxy_build_options(nth, opts); - synproxy_send_tcp(skb, nskb, NULL, 0, niph, nth, tcp_hdr_size); + synproxy_send_tcp(skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY, + niph, nth, tcp_hdr_size); } static bool diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index d7d4c2b79cf2..0ea2e1c5d395 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1348,7 +1348,7 @@ static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) req = inet_csk_search_req(sk, th->source, iph->saddr, iph->daddr); if (req) { nsk = tcp_check_req(sk, skb, req, false); - if (!nsk) + if (!nsk || nsk == sk) reqsk_put(req); return nsk; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 83aa604f9273..1b8c5ba7d5f7 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1995,12 +1995,19 @@ void udp_v4_early_demux(struct sk_buff *skb) skb->sk = sk; skb->destructor = sock_efree; - dst = sk->sk_rx_dst; + dst = READ_ONCE(sk->sk_rx_dst); if (dst) dst = dst_check(dst, 0); - if (dst) - skb_dst_set_noref(skb, dst); + if (dst) { + /* DST_NOCACHE can not be used without taking a reference */ + if (dst->flags & DST_NOCACHE) { + if (likely(atomic_inc_not_zero(&dst->__refcnt))) + skb_dst_set(skb, dst); + } else { + skb_dst_set_noref(skb, dst); + } + } } int udp_rcv(struct sk_buff *skb) diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c index 6edb7b106de7..ebbb754c2111 100644 --- a/net/ipv6/netfilter/ip6t_SYNPROXY.c +++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c @@ -37,12 +37,13 @@ synproxy_build_ip(struct sk_buff *skb, const struct in6_addr *saddr, } static void -synproxy_send_tcp(const struct sk_buff *skb, struct sk_buff *nskb, +synproxy_send_tcp(const struct synproxy_net *snet, + const struct sk_buff *skb, struct sk_buff *nskb, struct nf_conntrack *nfct, enum ip_conntrack_info ctinfo, struct ipv6hdr *niph, struct tcphdr *nth, unsigned int tcp_hdr_size) { - struct net *net = nf_ct_net((struct nf_conn *)nfct); + struct net *net = nf_ct_net(snet->tmpl); struct dst_entry *dst; struct flowi6 fl6; @@ -83,7 +84,8 @@ free_nskb: } static void -synproxy_send_client_synack(const struct sk_buff *skb, const struct tcphdr *th, +synproxy_send_client_synack(const struct synproxy_net *snet, + const struct sk_buff *skb, const struct tcphdr *th, const struct synproxy_options *opts) { struct sk_buff *nskb; @@ -119,7 +121,7 @@ synproxy_send_client_synack(const struct sk_buff *skb, const struct tcphdr *th, synproxy_build_options(nth, opts); - synproxy_send_tcp(skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY, + synproxy_send_tcp(snet, skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY, niph, nth, tcp_hdr_size); } @@ -163,7 +165,7 @@ synproxy_send_server_syn(const struct synproxy_net *snet, synproxy_build_options(nth, opts); - synproxy_send_tcp(skb, nskb, &snet->tmpl->ct_general, IP_CT_NEW, + synproxy_send_tcp(snet, skb, nskb, &snet->tmpl->ct_general, IP_CT_NEW, niph, nth, tcp_hdr_size); } @@ -203,7 +205,7 @@ synproxy_send_server_ack(const struct synproxy_net *snet, synproxy_build_options(nth, opts); - synproxy_send_tcp(skb, nskb, NULL, 0, niph, nth, tcp_hdr_size); + synproxy_send_tcp(snet, skb, nskb, NULL, 0, niph, nth, tcp_hdr_size); } static void @@ -241,7 +243,8 @@ synproxy_send_client_ack(const struct synproxy_net *snet, synproxy_build_options(nth, opts); - synproxy_send_tcp(skb, nskb, NULL, 0, niph, nth, tcp_hdr_size); + synproxy_send_tcp(snet, skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY, + niph, nth, tcp_hdr_size); } static bool @@ -301,7 +304,7 @@ synproxy_tg6(struct sk_buff *skb, const struct xt_action_param *par) XT_SYNPROXY_OPT_SACK_PERM | XT_SYNPROXY_OPT_ECN); - synproxy_send_client_synack(skb, th, &opts); + synproxy_send_client_synack(snet, skb, th, &opts); return NF_DROP; } else if (th->ack && !(th->fin || th->rst || th->syn)) { diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 6090969937f8..9de4d2bcd916 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1831,6 +1831,7 @@ int ip6_route_add(struct fib6_config *cfg) int gwa_type; gw_addr = &cfg->fc_gateway; + gwa_type = ipv6_addr_type(gw_addr); /* if gw_addr is local we will fail to detect this in case * address is still TENTATIVE (DAD in progress). rt6_lookup() @@ -1838,11 +1839,12 @@ int ip6_route_add(struct fib6_config *cfg) * prefix route was assigned to, which might be non-loopback. */ err = -EINVAL; - if (ipv6_chk_addr_and_flags(net, gw_addr, NULL, 0, 0)) + if (ipv6_chk_addr_and_flags(net, gw_addr, + gwa_type & IPV6_ADDR_LINKLOCAL ? + dev : NULL, 0, 0)) goto out; rt->rt6i_gateway = *gw_addr; - gwa_type = ipv6_addr_type(gw_addr); if (gwa_type != (IPV6_ADDR_LINKLOCAL|IPV6_ADDR_UNICAST)) { struct rt6_info *grt; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 6748c4277aff..7a6cea5e4274 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -943,7 +943,7 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk, struct sk_buff *skb) &ipv6_hdr(skb)->daddr, tcp_v6_iif(skb)); if (req) { nsk = tcp_check_req(sk, skb, req, false); - if (!nsk) + if (!nsk || nsk == sk) reqsk_put(req); return nsk; } diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 651039ad1681..3c20d02aee73 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -292,7 +292,7 @@ struct nf_conn *nf_ct_tmpl_alloc(struct net *net, u16 zone, gfp_t flags) { struct nf_conn *tmpl; - tmpl = kzalloc(sizeof(struct nf_conn), GFP_KERNEL); + tmpl = kzalloc(sizeof(*tmpl), flags); if (tmpl == NULL) return NULL; @@ -303,7 +303,7 @@ struct nf_conn *nf_ct_tmpl_alloc(struct net *net, u16 zone, gfp_t flags) if (zone) { struct nf_conntrack_zone *nf_ct_zone; - nf_ct_zone = nf_ct_ext_add(tmpl, NF_CT_EXT_ZONE, GFP_ATOMIC); + nf_ct_zone = nf_ct_ext_add(tmpl, NF_CT_EXT_ZONE, flags); if (!nf_ct_zone) goto out_free; nf_ct_zone->id = zone; @@ -1544,10 +1544,8 @@ void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls) sz = nr_slots * sizeof(struct hlist_nulls_head); hash = (void *)__get_free_pages(GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO, get_order(sz)); - if (!hash) { - printk(KERN_WARNING "nf_conntrack: falling back to vmalloc.\n"); + if (!hash) hash = vzalloc(sz); - } if (hash && nulls) for (i = 0; i < nr_slots; i++) diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index 71f1e9fdfa18..d7f168527903 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -353,10 +353,8 @@ static int __net_init synproxy_net_init(struct net *net) int err = -ENOMEM; ct = nf_ct_tmpl_alloc(net, 0, GFP_KERNEL); - if (IS_ERR(ct)) { - err = PTR_ERR(ct); + if (!ct) goto err1; - } if (!nfct_seqadj_ext_add(ct)) goto err2; diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index c6630030c912..43ddeee404e9 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -202,9 +202,10 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par, goto err1; ct = nf_ct_tmpl_alloc(par->net, info->zone, GFP_KERNEL); - ret = PTR_ERR(ct); - if (IS_ERR(ct)) + if (!ct) { + ret = -ENOMEM; goto err2; + } ret = 0; if ((info->ct_events || info->exp_events) && diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index d8e2e3918ce2..67d210477863 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1096,6 +1096,11 @@ static int netlink_insert(struct sock *sk, u32 portid) err = __netlink_insert(table, sk); if (err) { + /* In case the hashtable backend returns with -EBUSY + * from here, it must not escape to the caller. + */ + if (unlikely(err == -EBUSY)) + err = -EOVERFLOW; if (err == -EEXIST) err = -EADDRINUSE; nlk_sk(sk)->portid = 0; diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 8a8c0b8b4f63..ee34f474ad14 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -273,28 +273,36 @@ static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *flow_key, return 0; } -static void set_ip_addr(struct sk_buff *skb, struct iphdr *nh, - __be32 *addr, __be32 new_addr) +static void update_ip_l4_checksum(struct sk_buff *skb, struct iphdr *nh, + __be32 addr, __be32 new_addr) { int transport_len = skb->len - skb_transport_offset(skb); + if (nh->frag_off & htons(IP_OFFSET)) + return; + if (nh->protocol == IPPROTO_TCP) { if (likely(transport_len >= sizeof(struct tcphdr))) inet_proto_csum_replace4(&tcp_hdr(skb)->check, skb, - *addr, new_addr, 1); + addr, new_addr, 1); } else if (nh->protocol == IPPROTO_UDP) { if (likely(transport_len >= sizeof(struct udphdr))) { struct udphdr *uh = udp_hdr(skb); if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) { inet_proto_csum_replace4(&uh->check, skb, - *addr, new_addr, 1); + addr, new_addr, 1); if (!uh->check) uh->check = CSUM_MANGLED_0; } } } +} +static void set_ip_addr(struct sk_buff *skb, struct iphdr *nh, + __be32 *addr, __be32 new_addr) +{ + update_ip_l4_checksum(skb, nh, *addr, new_addr); csum_replace4(&nh->check, *addr, new_addr); skb_clear_hash(skb); *addr = new_addr; diff --git a/net/rds/info.c b/net/rds/info.c index 9a6b4f66187c..140a44a5f7b7 100644 --- a/net/rds/info.c +++ b/net/rds/info.c @@ -176,7 +176,7 @@ int rds_info_getsockopt(struct socket *sock, int optname, char __user *optval, /* check for all kinds of wrapping and the like */ start = (unsigned long)optval; - if (len < 0 || len + PAGE_SIZE - 1 < len || start + len < start) { + if (len < 0 || len > INT_MAX - PAGE_SIZE + 1 || start + len < start) { ret = -EINVAL; goto out; } diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index a42a3b257226..268545050ddb 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -98,6 +98,8 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, return ret; ret = ACT_P_CREATED; } else { + if (bind) + return 0; if (!ovr) { tcf_hash_release(a, bind); return -EEXIST; diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 21ca33c9f036..a9ba030435a2 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -288,10 +288,26 @@ begin: static void fq_codel_reset(struct Qdisc *sch) { - struct sk_buff *skb; + struct fq_codel_sched_data *q = qdisc_priv(sch); + int i; - while ((skb = fq_codel_dequeue(sch)) != NULL) - kfree_skb(skb); + INIT_LIST_HEAD(&q->new_flows); + INIT_LIST_HEAD(&q->old_flows); + for (i = 0; i < q->flows_cnt; i++) { + struct fq_codel_flow *flow = q->flows + i; + + while (flow->head) { + struct sk_buff *skb = dequeue_head(flow); + + qdisc_qstats_backlog_dec(sch, skb); + kfree_skb(skb); + } + + INIT_LIST_HEAD(&flow->flowchain); + codel_vars_init(&flow->cvars); + } + memset(q->backlogs, 0, q->flows_cnt * sizeof(u32)); + sch->q.qlen = 0; } static const struct nla_policy fq_codel_policy[TCA_FQ_CODEL_MAX + 1] = { diff --git a/scripts/kconfig/streamline_config.pl b/scripts/kconfig/streamline_config.pl index 9cb8522d8d22..f3d3fb42b873 100755 --- a/scripts/kconfig/streamline_config.pl +++ b/scripts/kconfig/streamline_config.pl @@ -137,7 +137,7 @@ my $ksource = ($ARGV[0] ? $ARGV[0] : '.'); my $kconfig = $ARGV[1]; my $lsmod_file = $ENV{'LSMOD'}; -my @makefiles = `find $ksource -name Makefile 2>/dev/null`; +my @makefiles = `find $ksource -name Makefile -or -name Kbuild 2>/dev/null`; chomp @makefiles; my %depends; diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index 094ddaee104c..d31fac19c30b 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -638,7 +638,7 @@ ifndef DESTDIR prefix ?= $(HOME) endif bindir_relative = bin -bindir = $(prefix)/$(bindir_relative) +bindir = $(abspath $(prefix)/$(bindir_relative)) mandir = share/man infodir = share/info perfexecdir = libexec/perf-core diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 53e8bb7bc852..2a5d8d7698ae 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -85,7 +85,7 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count, else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES)) update_stats(&runtime_cycles_stats[ctx][cpu], count[0]); else if (perf_stat_evsel__is(counter, CYCLES_IN_TX)) - update_stats(&runtime_transaction_stats[ctx][cpu], count[0]); + update_stats(&runtime_cycles_in_tx_stats[ctx][cpu], count[0]); else if (perf_stat_evsel__is(counter, TRANSACTION_START)) update_stats(&runtime_transaction_stats[ctx][cpu], count[0]); else if (perf_stat_evsel__is(counter, ELISION_START)) @@ -398,20 +398,18 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel, " # %5.2f%% aborted cycles ", 100.0 * ((total2-avg) / total)); } else if (perf_stat_evsel__is(evsel, TRANSACTION_START) && - avg > 0 && runtime_cycles_in_tx_stats[ctx][cpu].n != 0) { total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]); - if (total) + if (avg) ratio = total / avg; fprintf(out, " # %8.0f cycles / transaction ", ratio); } else if (perf_stat_evsel__is(evsel, ELISION_START) && - avg > 0 && runtime_cycles_in_tx_stats[ctx][cpu].n != 0) { total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]); - if (total) + if (avg) ratio = total / avg; fprintf(out, " # %8.0f cycles / elision ", ratio); |