diff options
Diffstat (limited to 'arch')
158 files changed, 2112 insertions, 1629 deletions
diff --git a/arch/arm/boot/dts/msm8660-surf.dts b/arch/arm/boot/dts/msm8660-surf.dts index 31f2157cd7d..67f8670c4d6 100644 --- a/arch/arm/boot/dts/msm8660-surf.dts +++ b/arch/arm/boot/dts/msm8660-surf.dts @@ -38,4 +38,10 @@ <0x19c00000 0x1000>; interrupts = <0 195 0x0>; }; + + qcom,ssbi@500000 { + compatible = "qcom,ssbi"; + reg = <0x500000 0x1000>; + qcom,controller-type = "pmic-arbiter"; + }; }; diff --git a/arch/arm/boot/dts/msm8960-cdp.dts b/arch/arm/boot/dts/msm8960-cdp.dts index 9e621b5ad3d..c9b09a813a4 100644 --- a/arch/arm/boot/dts/msm8960-cdp.dts +++ b/arch/arm/boot/dts/msm8960-cdp.dts @@ -38,4 +38,10 @@ <0x16400000 0x1000>; interrupts = <0 154 0x0>; }; + + qcom,ssbi@500000 { + compatible = "qcom,ssbi"; + reg = <0x500000 0x1000>; + qcom,controller-type = "pmic-arbiter"; + }; }; diff --git a/arch/arm/boot/dts/spear1310.dtsi b/arch/arm/boot/dts/spear1310.dtsi index 1513c1927cc..122ae94076c 100644 --- a/arch/arm/boot/dts/spear1310.dtsi +++ b/arch/arm/boot/dts/spear1310.dtsi @@ -89,7 +89,7 @@ pinmux: pinmux@e0700000 { compatible = "st,spear1310-pinmux"; reg = <0xe0700000 0x1000>; - #gpio-range-cells = <2>; + #gpio-range-cells = <3>; }; apb { @@ -212,7 +212,7 @@ interrupt-controller; gpio-controller; #gpio-cells = <2>; - gpio-ranges = <&pinmux 0 246>; + gpio-ranges = <&pinmux 0 0 246>; status = "disabled"; st-plgpio,ngpio = <246>; diff --git a/arch/arm/boot/dts/spear1340.dtsi b/arch/arm/boot/dts/spear1340.dtsi index 34da11aa679..c511c4772ef 100644 --- a/arch/arm/boot/dts/spear1340.dtsi +++ b/arch/arm/boot/dts/spear1340.dtsi @@ -63,7 +63,7 @@ pinmux: pinmux@e0700000 { compatible = "st,spear1340-pinmux"; reg = <0xe0700000 0x1000>; - #gpio-range-cells = <2>; + #gpio-range-cells = <3>; }; pwm: pwm@e0180000 { @@ -127,7 +127,7 @@ interrupt-controller; gpio-controller; #gpio-cells = <2>; - gpio-ranges = <&pinmux 0 252>; + gpio-ranges = <&pinmux 0 0 252>; status = "disabled"; st-plgpio,ngpio = <250>; diff --git a/arch/arm/boot/dts/spear310.dtsi b/arch/arm/boot/dts/spear310.dtsi index ab45b8c8198..95372080eea 100644 --- a/arch/arm/boot/dts/spear310.dtsi +++ b/arch/arm/boot/dts/spear310.dtsi @@ -25,7 +25,7 @@ pinmux: pinmux@b4000000 { compatible = "st,spear310-pinmux"; reg = <0xb4000000 0x1000>; - #gpio-range-cells = <2>; + #gpio-range-cells = <3>; }; fsmc: flash@44000000 { @@ -102,7 +102,7 @@ interrupt-controller; gpio-controller; #gpio-cells = <2>; - gpio-ranges = <&pinmux 0 102>; + gpio-ranges = <&pinmux 0 0 102>; status = "disabled"; st-plgpio,ngpio = <102>; diff --git a/arch/arm/boot/dts/spear320.dtsi b/arch/arm/boot/dts/spear320.dtsi index caa5520b1fd..ffea342aeec 100644 --- a/arch/arm/boot/dts/spear320.dtsi +++ b/arch/arm/boot/dts/spear320.dtsi @@ -24,7 +24,7 @@ pinmux: pinmux@b3000000 { compatible = "st,spear320-pinmux"; reg = <0xb3000000 0x1000>; - #gpio-range-cells = <2>; + #gpio-range-cells = <3>; }; clcd@90000000 { @@ -130,7 +130,7 @@ interrupt-controller; gpio-controller; #gpio-cells = <2>; - gpio-ranges = <&pinmux 0 102>; + gpio-ranges = <&pinmux 0 0 102>; status = "disabled"; st-plgpio,ngpio = <102>; diff --git a/arch/arm/boot/dts/vt8500-bv07.dts b/arch/arm/boot/dts/vt8500-bv07.dts index 567cf4e8ab8..877b33afa7e 100644 --- a/arch/arm/boot/dts/vt8500-bv07.dts +++ b/arch/arm/boot/dts/vt8500-bv07.dts @@ -11,26 +11,22 @@ / { model = "Benign BV07 Netbook"; +}; - /* - * Display node is based on Sascha Hauer's patch on dri-devel. - * Added a bpp property to calculate the size of the framebuffer - * until the binding is formalized. - */ - display: display@0 { - modes { - mode0: mode@0 { - hactive = <800>; - vactive = <480>; - hback-porch = <88>; - hfront-porch = <40>; - hsync-len = <0>; - vback-porch = <32>; - vfront-porch = <11>; - vsync-len = <1>; - clock = <0>; /* unused but required */ - bpp = <16>; /* non-standard but required */ - }; +&fb { + bits-per-pixel = <16>; + display-timings { + native-mode = <&timing0>; + timing0: 800x480 { + clock-frequency = <0>; /* unused but required */ + hactive = <800>; + vactive = <480>; + hfront-porch = <40>; + hback-porch = <88>; + hsync-len = <0>; + vback-porch = <32>; + vfront-porch = <11>; + vsync-len = <1>; }; }; }; diff --git a/arch/arm/boot/dts/vt8500.dtsi b/arch/arm/boot/dts/vt8500.dtsi index cf31ced4660..68c8dc64438 100644 --- a/arch/arm/boot/dts/vt8500.dtsi +++ b/arch/arm/boot/dts/vt8500.dtsi @@ -98,12 +98,10 @@ interrupts = <43>; }; - fb@d800e400 { + fb: fb@d8050800 { compatible = "via,vt8500-fb"; reg = <0xd800e400 0x400>; interrupts = <12>; - display = <&display>; - default-mode = <&mode0>; }; ge_rops@d8050400 { diff --git a/arch/arm/boot/dts/wm8505-ref.dts b/arch/arm/boot/dts/wm8505-ref.dts index fd4e248074c..edd2cec3d37 100644 --- a/arch/arm/boot/dts/wm8505-ref.dts +++ b/arch/arm/boot/dts/wm8505-ref.dts @@ -11,26 +11,22 @@ / { model = "Wondermedia WM8505 Netbook"; +}; - /* - * Display node is based on Sascha Hauer's patch on dri-devel. - * Added a bpp property to calculate the size of the framebuffer - * until the binding is formalized. - */ - display: display@0 { - modes { - mode0: mode@0 { - hactive = <800>; - vactive = <480>; - hback-porch = <88>; - hfront-porch = <40>; - hsync-len = <0>; - vback-porch = <32>; - vfront-porch = <11>; - vsync-len = <1>; - clock = <0>; /* unused but required */ - bpp = <32>; /* non-standard but required */ - }; +&fb { + bits-per-pixel = <32>; + display-timings { + native-mode = <&timing0>; + timing0: 800x480 { + clock-frequency = <0>; /* unused but required */ + hactive = <800>; + vactive = <480>; + hfront-porch = <40>; + hback-porch = <88>; + hsync-len = <0>; + vback-porch = <32>; + vfront-porch = <11>; + vsync-len = <1>; }; }; }; diff --git a/arch/arm/boot/dts/wm8505.dtsi b/arch/arm/boot/dts/wm8505.dtsi index e74a1c0fb9a..bcf668d31b2 100644 --- a/arch/arm/boot/dts/wm8505.dtsi +++ b/arch/arm/boot/dts/wm8505.dtsi @@ -128,11 +128,9 @@ interrupts = <0>; }; - fb@d8050800 { + fb: fb@d8050800 { compatible = "wm,wm8505-fb"; reg = <0xd8050800 0x200>; - display = <&display>; - default-mode = <&mode0>; }; ge_rops@d8050400 { diff --git a/arch/arm/boot/dts/wm8650-mid.dts b/arch/arm/boot/dts/wm8650-mid.dts index cefd938f842..61671a0d9ed 100644 --- a/arch/arm/boot/dts/wm8650-mid.dts +++ b/arch/arm/boot/dts/wm8650-mid.dts @@ -11,26 +11,24 @@ / { model = "Wondermedia WM8650-MID Tablet"; +}; + +&fb { + bits-per-pixel = <16>; - /* - * Display node is based on Sascha Hauer's patch on dri-devel. - * Added a bpp property to calculate the size of the framebuffer - * until the binding is formalized. - */ - display: display@0 { - modes { - mode0: mode@0 { - hactive = <800>; - vactive = <480>; - hback-porch = <88>; - hfront-porch = <40>; - hsync-len = <0>; - vback-porch = <32>; - vfront-porch = <11>; - vsync-len = <1>; - clock = <0>; /* unused but required */ - bpp = <16>; /* non-standard but required */ - }; + display-timings { + native-mode = <&timing0>; + timing0: 800x480 { + clock-frequency = <0>; /* unused but required */ + hactive = <800>; + vactive = <480>; + hfront-porch = <40>; + hback-porch = <88>; + hsync-len = <0>; + vback-porch = <32>; + vfront-porch = <11>; + vsync-len = <1>; }; }; }; + diff --git a/arch/arm/boot/dts/wm8650.dtsi b/arch/arm/boot/dts/wm8650.dtsi index db3c0a12e05..9313407bbc3 100644 --- a/arch/arm/boot/dts/wm8650.dtsi +++ b/arch/arm/boot/dts/wm8650.dtsi @@ -128,11 +128,9 @@ interrupts = <43>; }; - fb@d8050800 { + fb: fb@d8050800 { compatible = "wm,wm8505-fb"; reg = <0xd8050800 0x200>; - display = <&display>; - default-mode = <&mode0>; }; ge_rops@d8050400 { diff --git a/arch/arm/boot/dts/wm8850-w70v2.dts b/arch/arm/boot/dts/wm8850-w70v2.dts index fcc660c8954..32d22532cd6 100644 --- a/arch/arm/boot/dts/wm8850-w70v2.dts +++ b/arch/arm/boot/dts/wm8850-w70v2.dts @@ -15,28 +15,6 @@ / { model = "Wondermedia WM8850-W70v2 Tablet"; - /* - * Display node is based on Sascha Hauer's patch on dri-devel. - * Added a bpp property to calculate the size of the framebuffer - * until the binding is formalized. - */ - display: display@0 { - modes { - mode0: mode@0 { - hactive = <800>; - vactive = <480>; - hback-porch = <88>; - hfront-porch = <40>; - hsync-len = <0>; - vback-porch = <32>; - vfront-porch = <11>; - vsync-len = <1>; - clock = <0>; /* unused but required */ - bpp = <16>; /* non-standard but required */ - }; - }; - }; - backlight { compatible = "pwm-backlight"; pwms = <&pwm 0 50000 1>; /* duty inverted */ @@ -45,3 +23,21 @@ default-brightness-level = <5>; }; }; + +&fb { + bits-per-pixel = <16>; + display-timings { + native-mode = <&timing0>; + timing0: 800x480 { + clock-frequency = <0>; /* unused but required */ + hactive = <800>; + vactive = <480>; + hfront-porch = <40>; + hback-porch = <88>; + hsync-len = <0>; + vback-porch = <32>; + vfront-porch = <11>; + vsync-len = <1>; + }; + }; +}; diff --git a/arch/arm/boot/dts/wm8850.dtsi b/arch/arm/boot/dts/wm8850.dtsi index e8cbfdc87bb..7149cd13e3b 100644 --- a/arch/arm/boot/dts/wm8850.dtsi +++ b/arch/arm/boot/dts/wm8850.dtsi @@ -135,11 +135,9 @@ }; }; - fb@d8051700 { + fb: fb@d8051700 { compatible = "wm,wm8505-fb"; reg = <0xd8051700 0x200>; - display = <&display>; - default-mode = <&mode0>; }; ge_rops@d8050400 { diff --git a/arch/arm/include/asm/glue-cache.h b/arch/arm/include/asm/glue-cache.h index cca9f15704e..ea289e1435e 100644 --- a/arch/arm/include/asm/glue-cache.h +++ b/arch/arm/include/asm/glue-cache.h @@ -19,14 +19,6 @@ #undef _CACHE #undef MULTI_CACHE -#if defined(CONFIG_CPU_CACHE_V3) -# ifdef _CACHE -# define MULTI_CACHE 1 -# else -# define _CACHE v3 -# endif -#endif - #if defined(CONFIG_CPU_CACHE_V4) # ifdef _CACHE # define MULTI_CACHE 1 diff --git a/arch/arm/include/asm/hardware/iop3xx.h b/arch/arm/include/asm/hardware/iop3xx.h index 02fe2fbe247..ed94b1a366a 100644 --- a/arch/arm/include/asm/hardware/iop3xx.h +++ b/arch/arm/include/asm/hardware/iop3xx.h @@ -37,7 +37,7 @@ extern int iop3xx_get_init_atu(void); * IOP3XX processor registers */ #define IOP3XX_PERIPHERAL_PHYS_BASE 0xffffe000 -#define IOP3XX_PERIPHERAL_VIRT_BASE 0xfeffe000 +#define IOP3XX_PERIPHERAL_VIRT_BASE 0xfedfe000 #define IOP3XX_PERIPHERAL_SIZE 0x00002000 #define IOP3XX_PERIPHERAL_UPPER_PA (IOP3XX_PERIPHERAL_PHYS_BASE +\ IOP3XX_PERIPHERAL_SIZE - 1) diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index 6ef8afd1b64..86b8fe398b9 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -111,7 +111,7 @@ #define L_PTE_S2_MT_WRITETHROUGH (_AT(pteval_t, 0xa) << 2) /* MemAttr[3:0] */ #define L_PTE_S2_MT_WRITEBACK (_AT(pteval_t, 0xf) << 2) /* MemAttr[3:0] */ #define L_PTE_S2_RDONLY (_AT(pteval_t, 1) << 6) /* HAP[1] */ -#define L_PTE_S2_RDWR (_AT(pteval_t, 2) << 6) /* HAP[2:1] */ +#define L_PTE_S2_RDWR (_AT(pteval_t, 3) << 6) /* HAP[2:1] */ /* * Hyp-mode PL2 PTE definitions for LPAE. diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h index 9e9c041358c..ab865e65a84 100644 --- a/arch/arm/include/asm/tlbflush.h +++ b/arch/arm/include/asm/tlbflush.h @@ -14,7 +14,6 @@ #include <asm/glue.h> -#define TLB_V3_PAGE (1 << 0) #define TLB_V4_U_PAGE (1 << 1) #define TLB_V4_D_PAGE (1 << 2) #define TLB_V4_I_PAGE (1 << 3) @@ -22,7 +21,6 @@ #define TLB_V6_D_PAGE (1 << 5) #define TLB_V6_I_PAGE (1 << 6) -#define TLB_V3_FULL (1 << 8) #define TLB_V4_U_FULL (1 << 9) #define TLB_V4_D_FULL (1 << 10) #define TLB_V4_I_FULL (1 << 11) @@ -52,7 +50,6 @@ * ============= * * We have the following to choose from: - * v3 - ARMv3 * v4 - ARMv4 without write buffer * v4wb - ARMv4 with write buffer without I TLB flush entry instruction * v4wbi - ARMv4 with write buffer with I TLB flush entry instruction @@ -330,7 +327,6 @@ static inline void local_flush_tlb_all(void) if (tlb_flag(TLB_WB)) dsb(); - tlb_op(TLB_V3_FULL, "c6, c0, 0", zero); tlb_op(TLB_V4_U_FULL | TLB_V6_U_FULL, "c8, c7, 0", zero); tlb_op(TLB_V4_D_FULL | TLB_V6_D_FULL, "c8, c6, 0", zero); tlb_op(TLB_V4_I_FULL | TLB_V6_I_FULL, "c8, c5, 0", zero); @@ -351,9 +347,8 @@ static inline void local_flush_tlb_mm(struct mm_struct *mm) if (tlb_flag(TLB_WB)) dsb(); - if (possible_tlb_flags & (TLB_V3_FULL|TLB_V4_U_FULL|TLB_V4_D_FULL|TLB_V4_I_FULL)) { + if (possible_tlb_flags & (TLB_V4_U_FULL|TLB_V4_D_FULL|TLB_V4_I_FULL)) { if (cpumask_test_cpu(get_cpu(), mm_cpumask(mm))) { - tlb_op(TLB_V3_FULL, "c6, c0, 0", zero); tlb_op(TLB_V4_U_FULL, "c8, c7, 0", zero); tlb_op(TLB_V4_D_FULL, "c8, c6, 0", zero); tlb_op(TLB_V4_I_FULL, "c8, c5, 0", zero); @@ -385,9 +380,8 @@ local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) if (tlb_flag(TLB_WB)) dsb(); - if (possible_tlb_flags & (TLB_V3_PAGE|TLB_V4_U_PAGE|TLB_V4_D_PAGE|TLB_V4_I_PAGE|TLB_V4_I_FULL) && + if (possible_tlb_flags & (TLB_V4_U_PAGE|TLB_V4_D_PAGE|TLB_V4_I_PAGE|TLB_V4_I_FULL) && cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) { - tlb_op(TLB_V3_PAGE, "c6, c0, 0", uaddr); tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", uaddr); tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", uaddr); tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", uaddr); @@ -418,7 +412,6 @@ static inline void local_flush_tlb_kernel_page(unsigned long kaddr) if (tlb_flag(TLB_WB)) dsb(); - tlb_op(TLB_V3_PAGE, "c6, c0, 0", kaddr); tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", kaddr); tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", kaddr); tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", kaddr); diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index 5dc1aa6f0f7..1fd749ee4a1 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -1043,7 +1043,7 @@ static int dbg_cpu_pm_notify(struct notifier_block *self, unsigned long action, return NOTIFY_OK; } -static struct notifier_block __cpuinitdata dbg_cpu_pm_nb = { +static struct notifier_block dbg_cpu_pm_nb = { .notifier_call = dbg_cpu_pm_notify, }; diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index 146157dfe27..8c3094d0f7b 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -253,7 +253,10 @@ validate_event(struct pmu_hw_events *hw_events, struct arm_pmu *armpmu = to_arm_pmu(event->pmu); struct pmu *leader_pmu = event->group_leader->pmu; - if (event->pmu != leader_pmu || event->state <= PERF_EVENT_STATE_OFF) + if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF) + return 1; + + if (event->state == PERF_EVENT_STATE_OFF && !event->attr.enable_on_exec) return 1; return armpmu->get_event_idx(hw_events, event) >= 0; diff --git a/arch/arm/kernel/sched_clock.c b/arch/arm/kernel/sched_clock.c index bd6f56b9ec2..59d2adb764a 100644 --- a/arch/arm/kernel/sched_clock.c +++ b/arch/arm/kernel/sched_clock.c @@ -45,12 +45,12 @@ static u32 notrace jiffy_sched_clock_read(void) static u32 __read_mostly (*read_sched_clock)(void) = jiffy_sched_clock_read; -static inline u64 cyc_to_ns(u64 cyc, u32 mult, u32 shift) +static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift) { return (cyc * mult) >> shift; } -static unsigned long long cyc_to_sched_clock(u32 cyc, u32 mask) +static unsigned long long notrace cyc_to_sched_clock(u32 cyc, u32 mask) { u64 epoch_ns; u32 epoch_cyc; diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index d343a6c3a6d..234e339196c 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -56,7 +56,6 @@ #include <asm/virt.h> #include "atags.h" -#include "tcm.h" #if defined(CONFIG_FPE_NWFPE) || defined(CONFIG_FPE_FASTFPE) @@ -798,8 +797,6 @@ void __init setup_arch(char **cmdline_p) reserve_crashkernel(); - tcm_init(); - #ifdef CONFIG_MULTI_IRQ_HANDLER handle_arch_irq = mdesc->handle_irq; #endif diff --git a/arch/arm/kernel/tcm.c b/arch/arm/kernel/tcm.c index 30ae6bb4a31..f50f19e5c13 100644 --- a/arch/arm/kernel/tcm.c +++ b/arch/arm/kernel/tcm.c @@ -17,7 +17,6 @@ #include <asm/mach/map.h> #include <asm/memory.h> #include <asm/system_info.h> -#include "tcm.h" static struct gen_pool *tcm_pool; static bool dtcm_present; diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 5a936988eb2..c1fe498983a 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -201,6 +201,7 @@ int kvm_dev_ioctl_check_extension(long ext) break; case KVM_CAP_ARM_SET_DEVICE_ADDR: r = 1; + break; case KVM_CAP_NR_VCPUS: r = num_online_cpus(); break; diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c index 4ea9a982269..7bed7556077 100644 --- a/arch/arm/kvm/coproc.c +++ b/arch/arm/kvm/coproc.c @@ -79,11 +79,11 @@ static bool access_dcsw(struct kvm_vcpu *vcpu, u32 val; int cpu; - cpu = get_cpu(); - if (!p->is_write) return read_from_write_only(vcpu, p); + cpu = get_cpu(); + cpumask_setall(&vcpu->arch.require_dcache_flush); cpumask_clear_cpu(cpu, &vcpu->arch.require_dcache_flush); diff --git a/arch/arm/mach-highbank/hotplug.c b/arch/arm/mach-highbank/hotplug.c index f30c5284339..890cae23c12 100644 --- a/arch/arm/mach-highbank/hotplug.c +++ b/arch/arm/mach-highbank/hotplug.c @@ -28,13 +28,11 @@ extern void secondary_startup(void); */ void __ref highbank_cpu_die(unsigned int cpu) { - flush_cache_all(); - highbank_set_cpu_jump(cpu, phys_to_virt(0)); - highbank_set_core_pwr(); - cpu_do_idle(); + flush_cache_louis(); + highbank_set_core_pwr(); - /* We should never return from idle */ - panic("highbank: cpu %d unexpectedly exit from shutdown\n", cpu); + while (1) + cpu_do_idle(); } diff --git a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c index 9e0576569e0..eaba9dc91a0 100644 --- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c @@ -2714,16 +2714,22 @@ static struct omap_ocp2scp_dev ocp2scp_dev_attr[] = { { } }; -static struct omap_hwmod_opt_clk ocp2scp_usb_phy_opt_clks[] = { - { .role = "48mhz", .clk = "ocp2scp_usb_phy_phy_48m" }, -}; - /* ocp2scp_usb_phy */ static struct omap_hwmod omap44xx_ocp2scp_usb_phy_hwmod = { .name = "ocp2scp_usb_phy", .class = &omap44xx_ocp2scp_hwmod_class, .clkdm_name = "l3_init_clkdm", - .main_clk = "func_48m_fclk", + /* + * ocp2scp_usb_phy_phy_48m is provided by the OMAP4 PRCM IP + * block as an "optional clock," and normally should never be + * specified as the main_clk for an OMAP IP block. However it + * turns out that this clock is actually the main clock for + * the ocp2scp_usb_phy IP block: + * http://lists.infradead.org/pipermail/linux-arm-kernel/2012-September/119943.html + * So listing ocp2scp_usb_phy_phy_48m as a main_clk here seems + * to be the best workaround. + */ + .main_clk = "ocp2scp_usb_phy_phy_48m", .prcm = { .omap4 = { .clkctrl_offs = OMAP4_CM_L3INIT_USBPHYOCP2SCP_CLKCTRL_OFFSET, @@ -2732,8 +2738,6 @@ static struct omap_hwmod omap44xx_ocp2scp_usb_phy_hwmod = { }, }, .dev_attr = ocp2scp_dev_attr, - .opt_clks = ocp2scp_usb_phy_opt_clks, - .opt_clks_cnt = ARRAY_SIZE(ocp2scp_usb_phy_opt_clks), }; /* diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index 025d1732873..4045c4931a3 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -43,7 +43,7 @@ config CPU_ARM740T depends on !MMU select CPU_32v4T select CPU_ABRT_LV4T - select CPU_CACHE_V3 # although the core is v4t + select CPU_CACHE_V4 select CPU_CP15_MPU select CPU_PABRT_LEGACY help @@ -469,9 +469,6 @@ config CPU_PABRT_V7 bool # The cache model -config CPU_CACHE_V3 - bool - config CPU_CACHE_V4 bool diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile index 4e333fa2756..9e51be96f63 100644 --- a/arch/arm/mm/Makefile +++ b/arch/arm/mm/Makefile @@ -33,7 +33,6 @@ obj-$(CONFIG_CPU_PABRT_LEGACY) += pabort-legacy.o obj-$(CONFIG_CPU_PABRT_V6) += pabort-v6.o obj-$(CONFIG_CPU_PABRT_V7) += pabort-v7.o -obj-$(CONFIG_CPU_CACHE_V3) += cache-v3.o obj-$(CONFIG_CPU_CACHE_V4) += cache-v4.o obj-$(CONFIG_CPU_CACHE_V4WT) += cache-v4wt.o obj-$(CONFIG_CPU_CACHE_V4WB) += cache-v4wb.o diff --git a/arch/arm/mm/cache-feroceon-l2.c b/arch/arm/mm/cache-feroceon-l2.c index dd3d59122cc..48bc3c0a87c 100644 --- a/arch/arm/mm/cache-feroceon-l2.c +++ b/arch/arm/mm/cache-feroceon-l2.c @@ -343,6 +343,7 @@ void __init feroceon_l2_init(int __l2_wt_override) outer_cache.inv_range = feroceon_l2_inv_range; outer_cache.clean_range = feroceon_l2_clean_range; outer_cache.flush_range = feroceon_l2_flush_range; + outer_cache.inv_all = l2_inv_all; enable_l2(); diff --git a/arch/arm/mm/cache-v3.S b/arch/arm/mm/cache-v3.S deleted file mode 100644 index 8a3fadece8d..00000000000 --- a/arch/arm/mm/cache-v3.S +++ /dev/null @@ -1,137 +0,0 @@ -/* - * linux/arch/arm/mm/cache-v3.S - * - * Copyright (C) 1997-2002 Russell king - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#include <linux/linkage.h> -#include <linux/init.h> -#include <asm/page.h> -#include "proc-macros.S" - -/* - * flush_icache_all() - * - * Unconditionally clean and invalidate the entire icache. - */ -ENTRY(v3_flush_icache_all) - mov pc, lr -ENDPROC(v3_flush_icache_all) - -/* - * flush_user_cache_all() - * - * Invalidate all cache entries in a particular address - * space. - * - * - mm - mm_struct describing address space - */ -ENTRY(v3_flush_user_cache_all) - /* FALLTHROUGH */ -/* - * flush_kern_cache_all() - * - * Clean and invalidate the entire cache. - */ -ENTRY(v3_flush_kern_cache_all) - /* FALLTHROUGH */ - -/* - * flush_user_cache_range(start, end, flags) - * - * Invalidate a range of cache entries in the specified - * address space. - * - * - start - start address (may not be aligned) - * - end - end address (exclusive, may not be aligned) - * - flags - vma_area_struct flags describing address space - */ -ENTRY(v3_flush_user_cache_range) - mov ip, #0 - mcreq p15, 0, ip, c7, c0, 0 @ flush ID cache - mov pc, lr - -/* - * coherent_kern_range(start, end) - * - * Ensure coherency between the Icache and the Dcache in the - * region described by start. If you have non-snooping - * Harvard caches, you need to implement this function. - * - * - start - virtual start address - * - end - virtual end address - */ -ENTRY(v3_coherent_kern_range) - /* FALLTHROUGH */ - -/* - * coherent_user_range(start, end) - * - * Ensure coherency between the Icache and the Dcache in the - * region described by start. If you have non-snooping - * Harvard caches, you need to implement this function. - * - * - start - virtual start address - * - end - virtual end address - */ -ENTRY(v3_coherent_user_range) - mov r0, #0 - mov pc, lr - -/* - * flush_kern_dcache_area(void *page, size_t size) - * - * Ensure no D cache aliasing occurs, either with itself or - * the I cache - * - * - addr - kernel address - * - size - region size - */ -ENTRY(v3_flush_kern_dcache_area) - /* FALLTHROUGH */ - -/* - * dma_flush_range(start, end) - * - * Clean and invalidate the specified virtual address range. - * - * - start - virtual start address - * - end - virtual end address - */ -ENTRY(v3_dma_flush_range) - mov r0, #0 - mcr p15, 0, r0, c7, c0, 0 @ flush ID cache - mov pc, lr - -/* - * dma_unmap_area(start, size, dir) - * - start - kernel virtual start address - * - size - size of region - * - dir - DMA direction - */ -ENTRY(v3_dma_unmap_area) - teq r2, #DMA_TO_DEVICE - bne v3_dma_flush_range - /* FALLTHROUGH */ - -/* - * dma_map_area(start, size, dir) - * - start - kernel virtual start address - * - size - size of region - * - dir - DMA direction - */ -ENTRY(v3_dma_map_area) - mov pc, lr -ENDPROC(v3_dma_unmap_area) -ENDPROC(v3_dma_map_area) - - .globl v3_flush_kern_cache_louis - .equ v3_flush_kern_cache_louis, v3_flush_kern_cache_all - - __INITDATA - - @ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S) - define_cache_functions v3 diff --git a/arch/arm/mm/cache-v4.S b/arch/arm/mm/cache-v4.S index 43e5d77be67..a7ba68f59f0 100644 --- a/arch/arm/mm/cache-v4.S +++ b/arch/arm/mm/cache-v4.S @@ -58,7 +58,7 @@ ENTRY(v4_flush_kern_cache_all) ENTRY(v4_flush_user_cache_range) #ifdef CONFIG_CPU_CP15 mov ip, #0 - mcreq p15, 0, ip, c7, c7, 0 @ flush ID cache + mcr p15, 0, ip, c7, c7, 0 @ flush ID cache mov pc, lr #else /* FALLTHROUGH */ diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 78978945492..a84ff763ac3 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -34,6 +34,7 @@ #include <asm/mach/pci.h> #include "mm.h" +#include "tcm.h" /* * empty_zero_page is a special page that is used for @@ -1277,6 +1278,7 @@ void __init paging_init(struct machine_desc *mdesc) dma_contiguous_remap(); devicemaps_init(mdesc); kmap_init(); + tcm_init(); top_pmd = pmd_off_k(0xffff0000); diff --git a/arch/arm/mm/proc-arm740.S b/arch/arm/mm/proc-arm740.S index dc5de5d53f2..fde2d2a794c 100644 --- a/arch/arm/mm/proc-arm740.S +++ b/arch/arm/mm/proc-arm740.S @@ -77,24 +77,27 @@ __arm740_setup: mcr p15, 0, r0, c6, c0 @ set area 0, default ldr r0, =(CONFIG_DRAM_BASE & 0xFFFFF000) @ base[31:12] of RAM - ldr r1, =(CONFIG_DRAM_SIZE >> 12) @ size of RAM (must be >= 4KB) - mov r2, #10 @ 11 is the minimum (4KB) -1: add r2, r2, #1 @ area size *= 2 - mov r1, r1, lsr #1 + ldr r3, =(CONFIG_DRAM_SIZE >> 12) @ size of RAM (must be >= 4KB) + mov r4, #10 @ 11 is the minimum (4KB) +1: add r4, r4, #1 @ area size *= 2 + movs r3, r3, lsr #1 bne 1b @ count not zero r-shift - orr r0, r0, r2, lsl #1 @ the area register value + orr r0, r0, r4, lsl #1 @ the area register value orr r0, r0, #1 @ set enable bit mcr p15, 0, r0, c6, c1 @ set area 1, RAM ldr r0, =(CONFIG_FLASH_MEM_BASE & 0xFFFFF000) @ base[31:12] of FLASH - ldr r1, =(CONFIG_FLASH_SIZE >> 12) @ size of FLASH (must be >= 4KB) - mov r2, #10 @ 11 is the minimum (4KB) -1: add r2, r2, #1 @ area size *= 2 - mov r1, r1, lsr #1 + ldr r3, =(CONFIG_FLASH_SIZE >> 12) @ size of FLASH (must be >= 4KB) + cmp r3, #0 + moveq r0, #0 + beq 2f + mov r4, #10 @ 11 is the minimum (4KB) +1: add r4, r4, #1 @ area size *= 2 + movs r3, r3, lsr #1 bne 1b @ count not zero r-shift - orr r0, r0, r2, lsl #1 @ the area register value + orr r0, r0, r4, lsl #1 @ the area register value orr r0, r0, #1 @ set enable bit - mcr p15, 0, r0, c6, c2 @ set area 2, ROM/FLASH +2: mcr p15, 0, r0, c6, c2 @ set area 2, ROM/FLASH mov r0, #0x06 mcr p15, 0, r0, c2, c0 @ Region 1&2 cacheable @@ -137,13 +140,14 @@ __arm740_proc_info: .long 0x41807400 .long 0xfffffff0 .long 0 + .long 0 b __arm740_setup .long cpu_arch_name .long cpu_elf_name - .long HWCAP_SWP | HWCAP_HALF | HWCAP_26BIT + .long HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB | HWCAP_26BIT .long cpu_arm740_name .long arm740_processor_functions .long 0 .long 0 - .long v3_cache_fns @ cache model + .long v4_cache_fns @ cache model .size __arm740_proc_info, . - __arm740_proc_info diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S index 2c3b9421ab5..2556cf1c2da 100644 --- a/arch/arm/mm/proc-arm920.S +++ b/arch/arm/mm/proc-arm920.S @@ -387,7 +387,7 @@ ENTRY(cpu_arm920_set_pte_ext) /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */ .globl cpu_arm920_suspend_size .equ cpu_arm920_suspend_size, 4 * 3 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_arm920_do_suspend) stmfd sp!, {r4 - r6, lr} mrc p15, 0, r4, c13, c0, 0 @ PID diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S index f1803f7e297..344c8a548cc 100644 --- a/arch/arm/mm/proc-arm926.S +++ b/arch/arm/mm/proc-arm926.S @@ -402,7 +402,7 @@ ENTRY(cpu_arm926_set_pte_ext) /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */ .globl cpu_arm926_suspend_size .equ cpu_arm926_suspend_size, 4 * 3 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_arm926_do_suspend) stmfd sp!, {r4 - r6, lr} mrc p15, 0, r4, c13, c0, 0 @ PID diff --git a/arch/arm/mm/proc-mohawk.S b/arch/arm/mm/proc-mohawk.S index 82f9cdc751d..0b60dd3d742 100644 --- a/arch/arm/mm/proc-mohawk.S +++ b/arch/arm/mm/proc-mohawk.S @@ -350,7 +350,7 @@ ENTRY(cpu_mohawk_set_pte_ext) .globl cpu_mohawk_suspend_size .equ cpu_mohawk_suspend_size, 4 * 6 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_mohawk_do_suspend) stmfd sp!, {r4 - r9, lr} mrc p14, 0, r4, c6, c0, 0 @ clock configuration, for turbo mode diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S index 3aa0da11fd8..d92dfd08142 100644 --- a/arch/arm/mm/proc-sa1100.S +++ b/arch/arm/mm/proc-sa1100.S @@ -172,7 +172,7 @@ ENTRY(cpu_sa1100_set_pte_ext) .globl cpu_sa1100_suspend_size .equ cpu_sa1100_suspend_size, 4 * 3 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_sa1100_do_suspend) stmfd sp!, {r4 - r6, lr} mrc p15, 0, r4, c3, c0, 0 @ domain ID diff --git a/arch/arm/mm/proc-syms.c b/arch/arm/mm/proc-syms.c index 3e6210b4d6d..054b491ff76 100644 --- a/arch/arm/mm/proc-syms.c +++ b/arch/arm/mm/proc-syms.c @@ -17,7 +17,9 @@ #ifndef MULTI_CPU EXPORT_SYMBOL(cpu_dcache_clean_area); +#ifdef CONFIG_MMU EXPORT_SYMBOL(cpu_set_pte_ext); +#endif #else EXPORT_SYMBOL(processor); #endif diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S index bcaaa8de932..5c07ee4fe3e 100644 --- a/arch/arm/mm/proc-v6.S +++ b/arch/arm/mm/proc-v6.S @@ -138,7 +138,7 @@ ENTRY(cpu_v6_set_pte_ext) /* Suspend/resume support: taken from arch/arm/mach-s3c64xx/sleep.S */ .globl cpu_v6_suspend_size .equ cpu_v6_suspend_size, 4 * 6 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_v6_do_suspend) stmfd sp!, {r4 - r9, lr} mrc p15, 0, r4, c13, c0, 0 @ FCSE/PID diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S index eb93d6487f3..e8efd83b6f2 100644 --- a/arch/arm/mm/proc-xsc3.S +++ b/arch/arm/mm/proc-xsc3.S @@ -413,7 +413,7 @@ ENTRY(cpu_xsc3_set_pte_ext) .globl cpu_xsc3_suspend_size .equ cpu_xsc3_suspend_size, 4 * 6 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_xsc3_do_suspend) stmfd sp!, {r4 - r9, lr} mrc p14, 0, r4, c6, c0, 0 @ clock configuration, for turbo mode diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S index 25510361aa1..e766f889bfd 100644 --- a/arch/arm/mm/proc-xscale.S +++ b/arch/arm/mm/proc-xscale.S @@ -528,7 +528,7 @@ ENTRY(cpu_xscale_set_pte_ext) .globl cpu_xscale_suspend_size .equ cpu_xscale_suspend_size, 4 * 6 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_xscale_do_suspend) stmfd sp!, {r4 - r9, lr} mrc p14, 0, r4, c6, c0, 0 @ clock configuration, for turbo mode diff --git a/arch/arm/kernel/tcm.h b/arch/arm/mm/tcm.h index 8015ad434a4..8015ad434a4 100644 --- a/arch/arm/kernel/tcm.h +++ b/arch/arm/mm/tcm.h diff --git a/arch/arm/plat-samsung/include/plat/fb.h b/arch/arm/plat-samsung/include/plat/fb.h index b885322717a..9ae50727078 100644 --- a/arch/arm/plat-samsung/include/plat/fb.h +++ b/arch/arm/plat-samsung/include/plat/fb.h @@ -15,55 +15,7 @@ #ifndef __PLAT_S3C_FB_H #define __PLAT_S3C_FB_H __FILE__ -/* S3C_FB_MAX_WIN - * Set to the maximum number of windows that any of the supported hardware - * can use. Since the platform data uses this for an array size, having it - * set to the maximum of any version of the hardware can do is safe. - */ -#define S3C_FB_MAX_WIN (5) - -/** - * struct s3c_fb_pd_win - per window setup data - * @xres : The window X size. - * @yres : The window Y size. - * @virtual_x: The virtual X size. - * @virtual_y: The virtual Y size. - */ -struct s3c_fb_pd_win { - unsigned short default_bpp; - unsigned short max_bpp; - unsigned short xres; - unsigned short yres; - unsigned short virtual_x; - unsigned short virtual_y; -}; - -/** - * struct s3c_fb_platdata - S3C driver platform specific information - * @setup_gpio: Setup the external GPIO pins to the right state to transfer - * the data from the display system to the connected display - * device. - * @vidcon0: The base vidcon0 values to control the panel data format. - * @vidcon1: The base vidcon1 values to control the panel data output. - * @vtiming: Video timing when connected to a RGB type panel. - * @win: The setup data for each hardware window, or NULL for unused. - * @display_mode: The LCD output display mode. - * - * The platform data supplies the video driver with all the information - * it requires to work with the display(s) attached to the machine. It - * controls the initial mode, the number of display windows (0 is always - * the base framebuffer) that are initialised etc. - * - */ -struct s3c_fb_platdata { - void (*setup_gpio)(void); - - struct s3c_fb_pd_win *win[S3C_FB_MAX_WIN]; - struct fb_videomode *vtiming; - - u32 vidcon0; - u32 vidcon1; -}; +#include <linux/platform_data/video_s3c.h> /** * s3c_fb_set_platdata() - Setup the FB device with platform data. diff --git a/arch/avr32/include/asm/io.h b/arch/avr32/include/asm/io.h index cf60d0a9f17..fc6483f83cc 100644 --- a/arch/avr32/include/asm/io.h +++ b/arch/avr32/include/asm/io.h @@ -165,6 +165,10 @@ BUILDIO_IOPORT(l, u32) #define readw_be __raw_readw #define readl_be __raw_readl +#define writeb_relaxed writeb +#define writew_relaxed writew +#define writel_relaxed writel + #define writeb_be __raw_writeb #define writew_be __raw_writew #define writel_be __raw_writel diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 9a02f71c6b1..e7e55a00f94 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -187,7 +187,7 @@ config IA64_DIG config IA64_DIG_VTD bool "DIG+Intel+IOMMU" - select DMAR + select INTEL_IOMMU select PCI_MSI config IA64_HP_ZX1 diff --git a/arch/ia64/include/asm/futex.h b/arch/ia64/include/asm/futex.h index d2bf1fd5e44..76acbcd5c06 100644 --- a/arch/ia64/include/asm/futex.h +++ b/arch/ia64/include/asm/futex.h @@ -106,16 +106,15 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, return -EFAULT; { - register unsigned long r8 __asm ("r8"); + register unsigned long r8 __asm ("r8") = 0; unsigned long prev; __asm__ __volatile__( " mf;; \n" - " mov %0=r0 \n" " mov ar.ccv=%4;; \n" "[1:] cmpxchg4.acq %1=[%2],%3,ar.ccv \n" " .xdata4 \"__ex_table\", 1b-., 2f-. \n" "[2:]" - : "=r" (r8), "=r" (prev) + : "+r" (r8), "=&r" (prev) : "r" (uaddr), "r" (newval), "rO" ((long) (unsigned) oldval) : "memory"); diff --git a/arch/ia64/include/asm/mca.h b/arch/ia64/include/asm/mca.h index 43f96ab18fa..8c709616871 100644 --- a/arch/ia64/include/asm/mca.h +++ b/arch/ia64/include/asm/mca.h @@ -143,6 +143,7 @@ extern unsigned long __per_cpu_mca[NR_CPUS]; extern int cpe_vector; extern int ia64_cpe_irq; extern void ia64_mca_init(void); +extern void ia64_mca_irq_init(void); extern void ia64_mca_cpu_init(void *); extern void ia64_os_mca_dispatch(void); extern void ia64_os_mca_dispatch_end(void); diff --git a/arch/ia64/include/asm/numa.h b/arch/ia64/include/asm/numa.h index 2e27ef17565..2db0a6c6daa 100644 --- a/arch/ia64/include/asm/numa.h +++ b/arch/ia64/include/asm/numa.h @@ -67,14 +67,13 @@ extern int paddr_to_nid(unsigned long paddr); extern void map_cpu_to_node(int cpu, int nid); extern void unmap_cpu_from_node(int cpu, int nid); - +extern void numa_clear_node(int cpu); #else /* !CONFIG_NUMA */ #define map_cpu_to_node(cpu, nid) do{}while(0) #define unmap_cpu_from_node(cpu, nid) do{}while(0) - #define paddr_to_nid(addr) 0 - +#define numa_clear_node(cpu) do { } while (0) #endif /* CONFIG_NUMA */ #endif /* _ASM_IA64_NUMA_H */ diff --git a/arch/ia64/kernel/fsys.S b/arch/ia64/kernel/fsys.S index c4cd45d9774..abc6dee3799 100644 --- a/arch/ia64/kernel/fsys.S +++ b/arch/ia64/kernel/fsys.S @@ -90,53 +90,6 @@ ENTRY(fsys_getpid) FSYS_RETURN END(fsys_getpid) -ENTRY(fsys_getppid) - .prologue - .altrp b6 - .body - add r17=IA64_TASK_GROUP_LEADER_OFFSET,r16 - ;; - ld8 r17=[r17] // r17 = current->group_leader - add r9=TI_FLAGS+IA64_TASK_SIZE,r16 - ;; - - ld4 r9=[r9] - add r17=IA64_TASK_REAL_PARENT_OFFSET,r17 // r17 = ¤t->group_leader->real_parent - ;; - and r9=TIF_ALLWORK_MASK,r9 - -1: ld8 r18=[r17] // r18 = current->group_leader->real_parent - ;; - cmp.ne p8,p0=0,r9 - add r8=IA64_TASK_TGID_OFFSET,r18 // r8 = ¤t->group_leader->real_parent->tgid - ;; - - /* - * The .acq is needed to ensure that the read of tgid has returned its data before - * we re-check "real_parent". - */ - ld4.acq r8=[r8] // r8 = current->group_leader->real_parent->tgid -#ifdef CONFIG_SMP - /* - * Re-read current->group_leader->real_parent. - */ - ld8 r19=[r17] // r19 = current->group_leader->real_parent -(p8) br.spnt.many fsys_fallback_syscall - ;; - cmp.ne p6,p0=r18,r19 // did real_parent change? - mov r19=0 // i must not leak kernel bits... -(p6) br.cond.spnt.few 1b // yes -> redo the read of tgid and the check - ;; - mov r17=0 // i must not leak kernel bits... - mov r18=0 // i must not leak kernel bits... -#else - mov r17=0 // i must not leak kernel bits... - mov r18=0 // i must not leak kernel bits... - mov r19=0 // i must not leak kernel bits... -#endif - FSYS_RETURN -END(fsys_getppid) - ENTRY(fsys_set_tid_address) .prologue .altrp b6 @@ -614,7 +567,7 @@ paravirt_fsyscall_table: data8 0 // chown data8 0 // lseek // 1040 data8 fsys_getpid // getpid - data8 fsys_getppid // getppid + data8 0 // getppid data8 0 // mount data8 0 // umount data8 0 // setuid // 1045 diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c index ee33c3aaa2f..19f107be734 100644 --- a/arch/ia64/kernel/iosapic.c +++ b/arch/ia64/kernel/iosapic.c @@ -76,7 +76,7 @@ * PCI pin -> global system interrupt (GSI) -> IA-64 vector <-> IRQ * * Note: The term "IRQ" is loosely used everywhere in Linux kernel to - * describeinterrupts. Now we use "IRQ" only for Linux IRQ's. ISA IRQ + * describe interrupts. Now we use "IRQ" only for Linux IRQ's. ISA IRQ * (isa_irq) is the only exception in this source code. */ @@ -1010,6 +1010,26 @@ iosapic_check_gsi_range (unsigned int gsi_base, unsigned int ver) return 0; } +static int +iosapic_delete_rte(unsigned int irq, unsigned int gsi) +{ + struct iosapic_rte_info *rte, *temp; + + list_for_each_entry_safe(rte, temp, &iosapic_intr_info[irq].rtes, + rte_list) { + if (rte->iosapic->gsi_base + rte->rte_index == gsi) { + if (rte->refcnt) + return -EBUSY; + + list_del(&rte->rte_list); + kfree(rte); + return 0; + } + } + + return -EINVAL; +} + int iosapic_init(unsigned long phys_addr, unsigned int gsi_base) { int num_rte, err, index; @@ -1069,7 +1089,7 @@ int iosapic_init(unsigned long phys_addr, unsigned int gsi_base) int iosapic_remove(unsigned int gsi_base) { - int index, err = 0; + int i, irq, index, err = 0; unsigned long flags; spin_lock_irqsave(&iosapic_lock, flags); @@ -1087,6 +1107,16 @@ int iosapic_remove(unsigned int gsi_base) goto out; } + for (i = gsi_base; i < gsi_base + iosapic_lists[index].num_rte; i++) { + irq = __gsi_to_irq(i); + if (irq < 0) + continue; + + err = iosapic_delete_rte(irq, i); + if (err) + goto out; + } + iounmap(iosapic_lists[index].addr); iosapic_free(index); out: diff --git a/arch/ia64/kernel/irq.c b/arch/ia64/kernel/irq.c index ad69606613e..f2c41828113 100644 --- a/arch/ia64/kernel/irq.c +++ b/arch/ia64/kernel/irq.c @@ -23,6 +23,8 @@ #include <linux/interrupt.h> #include <linux/kernel_stat.h> +#include <asm/mca.h> + /* * 'what should we do if we get a hw irq event on an illegal vector'. * each architecture has to answer this themselves. @@ -83,6 +85,12 @@ bool is_affinity_mask_valid(const struct cpumask *cpumask) #endif /* CONFIG_SMP */ +int __init arch_early_irq_init(void) +{ + ia64_mca_irq_init(); + return 0; +} + #ifdef CONFIG_HOTPLUG_CPU unsigned int vectors_in_migration[NR_IRQS]; diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c index 65bf9cd3904..d7396dbb07b 100644 --- a/arch/ia64/kernel/mca.c +++ b/arch/ia64/kernel/mca.c @@ -2074,22 +2074,16 @@ ia64_mca_init(void) printk(KERN_INFO "MCA related initialization done\n"); } + /* - * ia64_mca_late_init - * - * Opportunity to setup things that require initialization later - * than ia64_mca_init. Setup a timer to poll for CPEs if the - * platform doesn't support an interrupt driven mechanism. - * - * Inputs : None - * Outputs : Status + * These pieces cannot be done in ia64_mca_init() because it is called before + * early_irq_init() which would wipe out our percpu irq registrations. But we + * cannot leave them until ia64_mca_late_init() because by then all the other + * processors have been brought online and have set their own CMC vectors to + * point at a non-existant action. Called from arch_early_irq_init(). */ -static int __init -ia64_mca_late_init(void) +void __init ia64_mca_irq_init(void) { - if (!mca_init) - return 0; - /* * Configure the CMCI/P vector and handler. Interrupts for CMC are * per-processor, so AP CMC interrupts are setup in smp_callin() (smpboot.c). @@ -2108,6 +2102,23 @@ ia64_mca_late_init(void) /* Setup the CPEI/P handler */ register_percpu_irq(IA64_CPEP_VECTOR, &mca_cpep_irqaction); #endif +} + +/* + * ia64_mca_late_init + * + * Opportunity to setup things that require initialization later + * than ia64_mca_init. Setup a timer to poll for CPEs if the + * platform doesn't support an interrupt driven mechanism. + * + * Inputs : None + * Outputs : Status + */ +static int __init +ia64_mca_late_init(void) +{ + if (!mca_init) + return 0; register_hotcpu_notifier(&mca_cpu_notifier); diff --git a/arch/ia64/kernel/mca_drv.c b/arch/ia64/kernel/mca_drv.c index 9392e021c93..94f8bf777af 100644 --- a/arch/ia64/kernel/mca_drv.c +++ b/arch/ia64/kernel/mca_drv.c @@ -349,7 +349,7 @@ init_record_index_pools(void) /* - 3 - */ slidx_pool.max_idx = (rec_max_size/sect_min_size) * 2 + 1; - slidx_pool.buffer = (slidx_list_t *) + slidx_pool.buffer = kmalloc(slidx_pool.max_idx * sizeof(slidx_list_t), GFP_KERNEL); return slidx_pool.buffer ? 0 : -ENOMEM; diff --git a/arch/ia64/kvm/vtlb.c b/arch/ia64/kvm/vtlb.c index 4332f7ee520..a7869f8f49a 100644 --- a/arch/ia64/kvm/vtlb.c +++ b/arch/ia64/kvm/vtlb.c @@ -256,7 +256,7 @@ u64 guest_vhpt_lookup(u64 iha, u64 *pte) "srlz.d;;" "ssm psr.i;;" "srlz.d;;" - : "=r"(ret) : "r"(iha), "r"(pte):"memory"); + : "=&r"(ret) : "r"(iha), "r"(pte) : "memory"); return ret; } diff --git a/arch/ia64/mm/ioremap.c b/arch/ia64/mm/ioremap.c index 3dccdd8eb27..43964cde621 100644 --- a/arch/ia64/mm/ioremap.c +++ b/arch/ia64/mm/ioremap.c @@ -16,7 +16,7 @@ #include <asm/meminit.h> static inline void __iomem * -__ioremap (unsigned long phys_addr) +__ioremap_uc(unsigned long phys_addr) { return (void __iomem *) (__IA64_UNCACHED_OFFSET | phys_addr); } @@ -24,7 +24,11 @@ __ioremap (unsigned long phys_addr) void __iomem * early_ioremap (unsigned long phys_addr, unsigned long size) { - return __ioremap(phys_addr); + u64 attr; + attr = kern_mem_attribute(phys_addr, size); + if (attr & EFI_MEMORY_WB) + return (void __iomem *) phys_to_virt(phys_addr); + return __ioremap_uc(phys_addr); } void __iomem * @@ -47,7 +51,7 @@ ioremap (unsigned long phys_addr, unsigned long size) if (attr & EFI_MEMORY_WB) return (void __iomem *) phys_to_virt(phys_addr); else if (attr & EFI_MEMORY_UC) - return __ioremap(phys_addr); + return __ioremap_uc(phys_addr); /* * Some chipsets don't support UC access to memory. If @@ -93,7 +97,7 @@ ioremap (unsigned long phys_addr, unsigned long size) return (void __iomem *) (offset + (char __iomem *)addr); } - return __ioremap(phys_addr); + return __ioremap_uc(phys_addr); } EXPORT_SYMBOL(ioremap); @@ -103,7 +107,7 @@ ioremap_nocache (unsigned long phys_addr, unsigned long size) if (kern_mem_attribute(phys_addr, size) & EFI_MEMORY_WB) return NULL; - return __ioremap(phys_addr); + return __ioremap_uc(phys_addr); } EXPORT_SYMBOL(ioremap_nocache); diff --git a/arch/ia64/mm/numa.c b/arch/ia64/mm/numa.c index 3efea7d0a35..def782e31aa 100644 --- a/arch/ia64/mm/numa.c +++ b/arch/ia64/mm/numa.c @@ -73,6 +73,11 @@ int __meminit __early_pfn_to_nid(unsigned long pfn) return -1; } +void __cpuinit numa_clear_node(int cpu) +{ + unmap_cpu_from_node(cpu, NUMA_NO_NODE); +} + #ifdef CONFIG_MEMORY_HOTPLUG /* * SRAT information is stored in node_memblk[], then we can use SRAT diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c index 60532ab2734..de1474ff0bc 100644 --- a/arch/ia64/pci/pci.c +++ b/arch/ia64/pci/pci.c @@ -15,6 +15,7 @@ #include <linux/types.h> #include <linux/kernel.h> #include <linux/pci.h> +#include <linux/pci-acpi.h> #include <linux/init.h> #include <linux/ioport.h> #include <linux/slab.h> @@ -458,6 +459,16 @@ void pcibios_fixup_bus(struct pci_bus *b) platform_pci_fixup_bus(b); } +void pcibios_add_bus(struct pci_bus *bus) +{ + acpi_pci_add_bus(bus); +} + +void pcibios_remove_bus(struct pci_bus *bus) +{ + acpi_pci_remove_bus(bus); +} + void pcibios_set_master (struct pci_dev *dev) { /* No special bus mastering setup handling */ diff --git a/arch/ia64/sn/kernel/tiocx.c b/arch/ia64/sn/kernel/tiocx.c index 14c1711238c..e35f6485c1f 100644 --- a/arch/ia64/sn/kernel/tiocx.c +++ b/arch/ia64/sn/kernel/tiocx.c @@ -490,11 +490,14 @@ static int __init tiocx_init(void) { cnodeid_t cnodeid; int found_tiocx_device = 0; + int err; if (!ia64_platform_is("sn2")) return 0; - bus_register(&tiocx_bus_type); + err = bus_register(&tiocx_bus_type); + if (err) + return err; for (cnodeid = 0; cnodeid < num_cnodes; cnodeid++) { nasid_t nasid; diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h index 99fc547af9d..eab99e536b5 100644 --- a/arch/mips/include/asm/page.h +++ b/arch/mips/include/asm/page.h @@ -31,7 +31,7 @@ #define PAGE_SHIFT 16 #endif #define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT) -#define PAGE_MASK (~(PAGE_SIZE - 1)) +#define PAGE_MASK (~((1 << PAGE_SHIFT) - 1)) #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT #define HPAGE_SHIFT (PAGE_SHIFT + PAGE_SHIFT - 3) diff --git a/arch/mips/pci/pci.c b/arch/mips/pci/pci.c index 0872f12f268..594e60d6a43 100644 --- a/arch/mips/pci/pci.c +++ b/arch/mips/pci/pci.c @@ -115,7 +115,6 @@ static void pcibios_scanbus(struct pci_controller *hose) pci_bus_assign_resources(bus); pci_enable_bridges(bus); } - bus->dev.of_node = hose->of_node; } } @@ -169,6 +168,13 @@ void pci_load_of_ranges(struct pci_controller *hose, struct device_node *node) } } } + +struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus) +{ + struct pci_controller *hose = bus->sysdata; + + return of_node_get(hose->of_node); +} #endif static DEFINE_MUTEX(pci_scan_mutex); diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile index 01d95e2f058..113e2820650 100644 --- a/arch/parisc/Makefile +++ b/arch/parisc/Makefile @@ -65,8 +65,10 @@ ifndef CONFIG_FUNCTION_TRACER endif # Use long jumps instead of long branches (needed if your linker fails to -# link a too big vmlinux executable) -cflags-$(CONFIG_MLONGCALLS) += -mlong-calls +# link a too big vmlinux executable). Not enabled for building modules. +ifdef CONFIG_MLONGCALLS +KBUILD_CFLAGS_KERNEL += -mlong-calls +endif # select which processor to optimise for cflags-$(CONFIG_PA7100) += -march=1.1 -mschedule=7100 diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h index 79f694f3ad9..f0e2784e7cc 100644 --- a/arch/parisc/include/asm/cacheflush.h +++ b/arch/parisc/include/asm/cacheflush.h @@ -140,7 +140,10 @@ static inline void *kmap(struct page *page) return page_address(page); } -#define kunmap(page) kunmap_parisc(page_address(page)) +static inline void kunmap(struct page *page) +{ + kunmap_parisc(page_address(page)); +} static inline void *kmap_atomic(struct page *page) { diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index 7df49fad29f..1e40d7f86be 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -16,6 +16,8 @@ #include <asm/processor.h> #include <asm/cache.h> +extern spinlock_t pa_dbit_lock; + /* * kern_addr_valid(ADDR) tests if ADDR is pointing to valid kernel * memory. For the return value to be meaningful, ADDR must be >= @@ -44,8 +46,11 @@ extern void purge_tlb_entries(struct mm_struct *, unsigned long); #define set_pte_at(mm, addr, ptep, pteval) \ do { \ + unsigned long flags; \ + spin_lock_irqsave(&pa_dbit_lock, flags); \ set_pte(ptep, pteval); \ purge_tlb_entries(mm, addr); \ + spin_unlock_irqrestore(&pa_dbit_lock, flags); \ } while (0) #endif /* !__ASSEMBLY__ */ @@ -435,48 +440,46 @@ extern void update_mmu_cache(struct vm_area_struct *, unsigned long, pte_t *); static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { -#ifdef CONFIG_SMP + pte_t pte; + unsigned long flags; + if (!pte_young(*ptep)) return 0; - return test_and_clear_bit(xlate_pabit(_PAGE_ACCESSED_BIT), &pte_val(*ptep)); -#else - pte_t pte = *ptep; - if (!pte_young(pte)) + + spin_lock_irqsave(&pa_dbit_lock, flags); + pte = *ptep; + if (!pte_young(pte)) { + spin_unlock_irqrestore(&pa_dbit_lock, flags); return 0; - set_pte_at(vma->vm_mm, addr, ptep, pte_mkold(pte)); + } + set_pte(ptep, pte_mkold(pte)); + purge_tlb_entries(vma->vm_mm, addr); + spin_unlock_irqrestore(&pa_dbit_lock, flags); return 1; -#endif } -extern spinlock_t pa_dbit_lock; - struct mm_struct; static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { pte_t old_pte; + unsigned long flags; - spin_lock(&pa_dbit_lock); + spin_lock_irqsave(&pa_dbit_lock, flags); old_pte = *ptep; pte_clear(mm,addr,ptep); - spin_unlock(&pa_dbit_lock); + purge_tlb_entries(mm, addr); + spin_unlock_irqrestore(&pa_dbit_lock, flags); return old_pte; } static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { -#ifdef CONFIG_SMP - unsigned long new, old; - - do { - old = pte_val(*ptep); - new = pte_val(pte_wrprotect(__pte (old))); - } while (cmpxchg((unsigned long *) ptep, old, new) != old); + unsigned long flags; + spin_lock_irqsave(&pa_dbit_lock, flags); + set_pte(ptep, pte_wrprotect(*ptep)); purge_tlb_entries(mm, addr); -#else - pte_t old_pte = *ptep; - set_pte_at(mm, addr, ptep, pte_wrprotect(old_pte)); -#endif + spin_unlock_irqrestore(&pa_dbit_lock, flags); } #define pte_same(A,B) (pte_val(A) == pte_val(B)) diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h index 4ba2c93770f..e0a82358517 100644 --- a/arch/parisc/include/asm/uaccess.h +++ b/arch/parisc/include/asm/uaccess.h @@ -181,30 +181,24 @@ struct exception_data { #if !defined(CONFIG_64BIT) #define __put_kernel_asm64(__val,ptr) do { \ - u64 __val64 = (u64)(__val); \ - u32 hi = (__val64) >> 32; \ - u32 lo = (__val64) & 0xffffffff; \ __asm__ __volatile__ ( \ "\n1:\tstw %2,0(%1)" \ - "\n2:\tstw %3,4(%1)\n\t" \ + "\n2:\tstw %R2,4(%1)\n\t" \ ASM_EXCEPTIONTABLE_ENTRY(1b,fixup_put_user_skip_2)\ ASM_EXCEPTIONTABLE_ENTRY(2b,fixup_put_user_skip_1)\ : "=r"(__pu_err) \ - : "r"(ptr), "r"(hi), "r"(lo), "0"(__pu_err) \ + : "r"(ptr), "r"(__val), "0"(__pu_err) \ : "r1"); \ } while (0) #define __put_user_asm64(__val,ptr) do { \ - u64 __val64 = (u64)(__val); \ - u32 hi = (__val64) >> 32; \ - u32 lo = (__val64) & 0xffffffff; \ __asm__ __volatile__ ( \ "\n1:\tstw %2,0(%%sr3,%1)" \ - "\n2:\tstw %3,4(%%sr3,%1)\n\t" \ + "\n2:\tstw %R2,4(%%sr3,%1)\n\t" \ ASM_EXCEPTIONTABLE_ENTRY(1b,fixup_put_user_skip_2)\ ASM_EXCEPTIONTABLE_ENTRY(2b,fixup_put_user_skip_1)\ : "=r"(__pu_err) \ - : "r"(ptr), "r"(hi), "r"(lo), "0"(__pu_err) \ + : "r"(ptr), "r"(__val), "0"(__pu_err) \ : "r1"); \ } while (0) diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index 4b12890642e..83ded26cad0 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -421,14 +421,11 @@ void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) /* Note: purge_tlb_entries can be called at startup with no context. */ - /* Disable preemption while we play with %sr1. */ - preempt_disable(); - mtsp(mm->context, 1); purge_tlb_start(flags); + mtsp(mm->context, 1); pdtlb(addr); pitlb(addr); purge_tlb_end(flags); - preempt_enable(); } EXPORT_SYMBOL(purge_tlb_entries); diff --git a/arch/parisc/kernel/parisc_ksyms.c b/arch/parisc/kernel/parisc_ksyms.c index 6795dc6c995..568b2c61ea0 100644 --- a/arch/parisc/kernel/parisc_ksyms.c +++ b/arch/parisc/kernel/parisc_ksyms.c @@ -120,11 +120,13 @@ extern void __ashrdi3(void); extern void __ashldi3(void); extern void __lshrdi3(void); extern void __muldi3(void); +extern void __ucmpdi2(void); EXPORT_SYMBOL(__ashrdi3); EXPORT_SYMBOL(__ashldi3); EXPORT_SYMBOL(__lshrdi3); EXPORT_SYMBOL(__muldi3); +EXPORT_SYMBOL(__ucmpdi2); asmlinkage void * __canonicalize_funcptr_for_compare(void *); EXPORT_SYMBOL(__canonicalize_funcptr_for_compare); diff --git a/arch/parisc/lib/Makefile b/arch/parisc/lib/Makefile index 5f2e6904d14..5651536ac73 100644 --- a/arch/parisc/lib/Makefile +++ b/arch/parisc/lib/Makefile @@ -2,6 +2,7 @@ # Makefile for parisc-specific library files # -lib-y := lusercopy.o bitops.o checksum.o io.o memset.o fixup.o memcpy.o +lib-y := lusercopy.o bitops.o checksum.o io.o memset.o fixup.o memcpy.o \ + ucmpdi2.o obj-y := iomap.o diff --git a/arch/parisc/lib/ucmpdi2.c b/arch/parisc/lib/ucmpdi2.c new file mode 100644 index 00000000000..149c016f32c --- /dev/null +++ b/arch/parisc/lib/ucmpdi2.c @@ -0,0 +1,25 @@ +#include <linux/module.h> + +union ull_union { + unsigned long long ull; + struct { + unsigned int high; + unsigned int low; + } ui; +}; + +int __ucmpdi2(unsigned long long a, unsigned long long b) +{ + union ull_union au = {.ull = a}; + union ull_union bu = {.ull = b}; + + if (au.ui.high < bu.ui.high) + return 0; + else if (au.ui.high > bu.ui.high) + return 2; + if (au.ui.low < bu.ui.low) + return 0; + else if (au.ui.low > bu.ui.low) + return 2; + return 1; +} diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 256c5bf0adb..04d69c4a5ac 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -304,7 +304,7 @@ syscall_exit_work: subi r12,r12,TI_FLAGS 4: /* Anything else left to do? */ - SET_DEFAULT_THREAD_PPR(r3, r9) /* Set thread.ppr = 3 */ + SET_DEFAULT_THREAD_PPR(r3, r10) /* Set thread.ppr = 3 */ andi. r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP) beq .ret_from_except_lite @@ -657,7 +657,7 @@ resume_kernel: /* Clear _TIF_EMULATE_STACK_STORE flag */ lis r11,_TIF_EMULATE_STACK_STORE@h addi r5,r9,TI_FLAGS - ldarx r4,0,r5 +0: ldarx r4,0,r5 andc r4,r4,r11 stdcx. r4,0,r5 bne- 0b diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 59dd545fdde..16e77a81ab4 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -555,10 +555,12 @@ static inline void tm_recheckpoint_new_task(struct task_struct *new) new->thread.regs->msr |= (MSR_FP | new->thread.fpexc_mode); } +#ifdef CONFIG_ALTIVEC if (msr & MSR_VEC) { do_load_up_transact_altivec(&new->thread); new->thread.regs->msr |= MSR_VEC; } +#endif /* We may as well turn on VSX too since all the state is restored now */ if (msr & MSR_VSX) new->thread.regs->msr |= MSR_VSX; diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 3acb28e245b..95068bf569a 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -866,10 +866,12 @@ static long restore_tm_user_regs(struct pt_regs *regs, do_load_up_transact_fpu(¤t->thread); regs->msr |= (MSR_FP | current->thread.fpexc_mode); } +#ifdef CONFIG_ALTIVEC if (msr & MSR_VEC) { do_load_up_transact_altivec(¤t->thread); regs->msr |= MSR_VEC; } +#endif return 0; } diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 995f8543cb5..c1794286098 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -522,10 +522,12 @@ static long restore_tm_sigcontexts(struct pt_regs *regs, do_load_up_transact_fpu(¤t->thread); regs->msr |= (MSR_FP | current->thread.fpexc_mode); } +#ifdef CONFIG_ALTIVEC if (msr & MSR_VEC) { do_load_up_transact_altivec(¤t->thread); regs->msr |= MSR_VEC; } +#endif return err; } diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index 84dbace657c..2da67e7a16d 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -309,6 +309,7 @@ _GLOBAL(tm_recheckpoint) or r5, r6, r5 /* Set MSR.FP+.VSX/.VEC */ mtmsr r5 +#ifdef CONFIG_ALTIVEC /* FP and VEC registers: These are recheckpointed from thread.fpr[] * and thread.vr[] respectively. The thread.transact_fpr[] version * is more modern, and will be loaded subsequently by any FPUnavailable @@ -323,6 +324,7 @@ _GLOBAL(tm_recheckpoint) REST_32VRS(0, r5, r3) /* r5 scratch, r3 THREAD ptr */ ld r5, THREAD_VRSAVE(r3) mtspr SPRN_VRSAVE, r5 +#endif dont_restore_vec: andi. r0, r4, MSR_FP diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h index 41cefd43655..33db48a8ce2 100644 --- a/arch/powerpc/kvm/e500.h +++ b/arch/powerpc/kvm/e500.h @@ -26,17 +26,20 @@ #define E500_PID_NUM 3 #define E500_TLB_NUM 2 -#define E500_TLB_VALID 1 -#define E500_TLB_BITMAP 2 +/* entry is mapped somewhere in host TLB */ +#define E500_TLB_VALID (1 << 0) +/* TLB1 entry is mapped by host TLB1, tracked by bitmaps */ +#define E500_TLB_BITMAP (1 << 1) +/* TLB1 entry is mapped by host TLB0 */ #define E500_TLB_TLB0 (1 << 2) struct tlbe_ref { - pfn_t pfn; - unsigned int flags; /* E500_TLB_* */ + pfn_t pfn; /* valid only for TLB0, except briefly */ + unsigned int flags; /* E500_TLB_* */ }; struct tlbe_priv { - struct tlbe_ref ref; /* TLB0 only -- TLB1 uses tlb_refs */ + struct tlbe_ref ref; }; #ifdef CONFIG_KVM_E500V2 @@ -63,17 +66,6 @@ struct kvmppc_vcpu_e500 { unsigned int gtlb_nv[E500_TLB_NUM]; - /* - * information associated with each host TLB entry -- - * TLB1 only for now. If/when guest TLB1 entries can be - * mapped with host TLB0, this will be used for that too. - * - * We don't want to use this for guest TLB0 because then we'd - * have the overhead of doing the translation again even if - * the entry is still in the guest TLB (e.g. we swapped out - * and back, and our host TLB entries got evicted). - */ - struct tlbe_ref *tlb_refs[E500_TLB_NUM]; unsigned int host_tlb1_nv; u32 svr; diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index a222edfb9a9..1c6a9d729df 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -193,8 +193,11 @@ void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel, struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[tlbsel][esel].ref; /* Don't bother with unmapped entries */ - if (!(ref->flags & E500_TLB_VALID)) - return; + if (!(ref->flags & E500_TLB_VALID)) { + WARN(ref->flags & (E500_TLB_BITMAP | E500_TLB_TLB0), + "%s: flags %x\n", __func__, ref->flags); + WARN_ON(tlbsel == 1 && vcpu_e500->g2h_tlb1_map[esel]); + } if (tlbsel == 1 && ref->flags & E500_TLB_BITMAP) { u64 tmp = vcpu_e500->g2h_tlb1_map[esel]; @@ -248,7 +251,7 @@ static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref, pfn_t pfn) { ref->pfn = pfn; - ref->flags = E500_TLB_VALID; + ref->flags |= E500_TLB_VALID; if (tlbe_is_writable(gtlbe)) kvm_set_pfn_dirty(pfn); @@ -257,6 +260,7 @@ static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref, static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref) { if (ref->flags & E500_TLB_VALID) { + /* FIXME: don't log bogus pfn for TLB1 */ trace_kvm_booke206_ref_release(ref->pfn, ref->flags); ref->flags = 0; } @@ -274,36 +278,23 @@ static void clear_tlb1_bitmap(struct kvmppc_vcpu_e500 *vcpu_e500) static void clear_tlb_privs(struct kvmppc_vcpu_e500 *vcpu_e500) { - int tlbsel = 0; - int i; - - for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) { - struct tlbe_ref *ref = - &vcpu_e500->gtlb_priv[tlbsel][i].ref; - kvmppc_e500_ref_release(ref); - } -} - -static void clear_tlb_refs(struct kvmppc_vcpu_e500 *vcpu_e500) -{ - int stlbsel = 1; + int tlbsel; int i; - kvmppc_e500_tlbil_all(vcpu_e500); - - for (i = 0; i < host_tlb_params[stlbsel].entries; i++) { - struct tlbe_ref *ref = - &vcpu_e500->tlb_refs[stlbsel][i]; - kvmppc_e500_ref_release(ref); + for (tlbsel = 0; tlbsel <= 1; tlbsel++) { + for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) { + struct tlbe_ref *ref = + &vcpu_e500->gtlb_priv[tlbsel][i].ref; + kvmppc_e500_ref_release(ref); + } } - - clear_tlb_privs(vcpu_e500); } void kvmppc_core_flush_tlb(struct kvm_vcpu *vcpu) { struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); - clear_tlb_refs(vcpu_e500); + kvmppc_e500_tlbil_all(vcpu_e500); + clear_tlb_privs(vcpu_e500); clear_tlb1_bitmap(vcpu_e500); } @@ -458,8 +449,6 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1); } - /* Drop old ref and setup new one. */ - kvmppc_e500_ref_release(ref); kvmppc_e500_ref_setup(ref, gtlbe, pfn); kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize, @@ -507,14 +496,15 @@ static int kvmppc_e500_tlb1_map_tlb1(struct kvmppc_vcpu_e500 *vcpu_e500, if (unlikely(vcpu_e500->host_tlb1_nv >= tlb1_max_shadow_size())) vcpu_e500->host_tlb1_nv = 0; - vcpu_e500->tlb_refs[1][sesel] = *ref; - vcpu_e500->g2h_tlb1_map[esel] |= (u64)1 << sesel; - vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_BITMAP; if (vcpu_e500->h2g_tlb1_rmap[sesel]) { - unsigned int idx = vcpu_e500->h2g_tlb1_rmap[sesel]; + unsigned int idx = vcpu_e500->h2g_tlb1_rmap[sesel] - 1; vcpu_e500->g2h_tlb1_map[idx] &= ~(1ULL << sesel); } - vcpu_e500->h2g_tlb1_rmap[sesel] = esel; + + vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_BITMAP; + vcpu_e500->g2h_tlb1_map[esel] |= (u64)1 << sesel; + vcpu_e500->h2g_tlb1_rmap[sesel] = esel + 1; + WARN_ON(!(ref->flags & E500_TLB_VALID)); return sesel; } @@ -526,13 +516,12 @@ static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500, u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe, struct kvm_book3e_206_tlb_entry *stlbe, int esel) { - struct tlbe_ref ref; + struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[1][esel].ref; int sesel; int r; - ref.flags = 0; r = kvmppc_e500_shadow_map(vcpu_e500, gvaddr, gfn, gtlbe, 1, stlbe, - &ref); + ref); if (r) return r; @@ -544,7 +533,7 @@ static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500, } /* Otherwise map into TLB1 */ - sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, &ref, esel); + sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, ref, esel); write_stlbe(vcpu_e500, gtlbe, stlbe, 1, sesel); return 0; @@ -565,7 +554,7 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr, case 0: priv = &vcpu_e500->gtlb_priv[tlbsel][esel]; - /* Triggers after clear_tlb_refs or on initial mapping */ + /* Triggers after clear_tlb_privs or on initial mapping */ if (!(priv->ref.flags & E500_TLB_VALID)) { kvmppc_e500_tlb0_map(vcpu_e500, esel, &stlbe); } else { @@ -665,35 +654,16 @@ int e500_mmu_host_init(struct kvmppc_vcpu_e500 *vcpu_e500) host_tlb_params[0].entries / host_tlb_params[0].ways; host_tlb_params[1].sets = 1; - vcpu_e500->tlb_refs[0] = - kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[0].entries, - GFP_KERNEL); - if (!vcpu_e500->tlb_refs[0]) - goto err; - - vcpu_e500->tlb_refs[1] = - kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[1].entries, - GFP_KERNEL); - if (!vcpu_e500->tlb_refs[1]) - goto err; - vcpu_e500->h2g_tlb1_rmap = kzalloc(sizeof(unsigned int) * host_tlb_params[1].entries, GFP_KERNEL); if (!vcpu_e500->h2g_tlb1_rmap) - goto err; + return -EINVAL; return 0; - -err: - kfree(vcpu_e500->tlb_refs[0]); - kfree(vcpu_e500->tlb_refs[1]); - return -EINVAL; } void e500_mmu_host_uninit(struct kvmppc_vcpu_e500 *vcpu_e500) { kfree(vcpu_e500->h2g_tlb1_rmap); - kfree(vcpu_e500->tlb_refs[0]); - kfree(vcpu_e500->tlb_refs[1]); } diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c index 1f89d26e65f..2f4baa074b2 100644 --- a/arch/powerpc/kvm/e500mc.c +++ b/arch/powerpc/kvm/e500mc.c @@ -108,6 +108,8 @@ void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr) { } +static DEFINE_PER_CPU(struct kvm_vcpu *, last_vcpu_on_cpu); + void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); @@ -136,8 +138,11 @@ void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) mtspr(SPRN_GDEAR, vcpu->arch.shared->dar); mtspr(SPRN_GESR, vcpu->arch.shared->esr); - if (vcpu->arch.oldpir != mfspr(SPRN_PIR)) + if (vcpu->arch.oldpir != mfspr(SPRN_PIR) || + __get_cpu_var(last_vcpu_on_cpu) != vcpu) { kvmppc_e500_tlbil_all(vcpu_e500); + __get_cpu_var(last_vcpu_on_cpu) = vcpu; + } kvmppc_load_guest_fp(vcpu); } diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index eb8fb629f00..bda6ba6f3cf 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -375,19 +375,6 @@ config PACK_STACK Say Y if you are unsure. -config SMALL_STACK - def_bool n - prompt "Use 8kb for kernel stack instead of 16kb" - depends on PACK_STACK && 64BIT && !LOCKDEP - help - If you say Y here and the compiler supports the -mkernel-backchain - option the kernel will use a smaller kernel stack size. The reduced - size is 8kb instead of 16kb. This allows to run more threads on a - system and reduces the pressure on the memory management for higher - order page allocations. - - Say N if you are unsure. - config CHECK_STACK def_bool y prompt "Detect kernel stack overflow" diff --git a/arch/s390/Makefile b/arch/s390/Makefile index 7e3ce78d429..a7d68a467ce 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -55,22 +55,12 @@ cflags-$(CONFIG_FRAME_POINTER) += -fno-optimize-sibling-calls ifeq ($(call cc-option-yn,-mkernel-backchain),y) cflags-$(CONFIG_PACK_STACK) += -mkernel-backchain -D__PACK_STACK aflags-$(CONFIG_PACK_STACK) += -D__PACK_STACK -cflags-$(CONFIG_SMALL_STACK) += -D__SMALL_STACK -aflags-$(CONFIG_SMALL_STACK) += -D__SMALL_STACK -ifdef CONFIG_SMALL_STACK -STACK_SIZE := $(shell echo $$(($(STACK_SIZE)/2)) ) -endif endif # new style option for packed stacks ifeq ($(call cc-option-yn,-mpacked-stack),y) cflags-$(CONFIG_PACK_STACK) += -mpacked-stack -D__PACK_STACK aflags-$(CONFIG_PACK_STACK) += -D__PACK_STACK -cflags-$(CONFIG_SMALL_STACK) += -D__SMALL_STACK -aflags-$(CONFIG_SMALL_STACK) += -D__SMALL_STACK -ifdef CONFIG_SMALL_STACK -STACK_SIZE := $(shell echo $$(($(STACK_SIZE)/2)) ) -endif endif ifeq ($(call cc-option-yn,-mstack-size=8192 -mstack-guard=128),y) diff --git a/arch/s390/hypfs/hypfs_dbfs.c b/arch/s390/hypfs/hypfs_dbfs.c index 9fd4a40c675..bb5dd496614 100644 --- a/arch/s390/hypfs/hypfs_dbfs.c +++ b/arch/s390/hypfs/hypfs_dbfs.c @@ -105,9 +105,7 @@ void hypfs_dbfs_remove_file(struct hypfs_dbfs_file *df) int hypfs_dbfs_init(void) { dbfs_dir = debugfs_create_dir("s390_hypfs", NULL); - if (IS_ERR(dbfs_dir)) - return PTR_ERR(dbfs_dir); - return 0; + return PTR_RET(dbfs_dir); } void hypfs_dbfs_exit(void) diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h index 15422933c60..4d8604e311f 100644 --- a/arch/s390/include/asm/bitops.h +++ b/arch/s390/include/asm/bitops.h @@ -61,8 +61,6 @@ extern const char _sb_findmap[]; #ifndef CONFIG_64BIT -#define __BITOPS_ALIGN 3 -#define __BITOPS_WORDSIZE 32 #define __BITOPS_OR "or" #define __BITOPS_AND "nr" #define __BITOPS_XOR "xr" @@ -81,8 +79,6 @@ extern const char _sb_findmap[]; #else /* CONFIG_64BIT */ -#define __BITOPS_ALIGN 7 -#define __BITOPS_WORDSIZE 64 #define __BITOPS_OR "ogr" #define __BITOPS_AND "ngr" #define __BITOPS_XOR "xgr" @@ -101,8 +97,7 @@ extern const char _sb_findmap[]; #endif /* CONFIG_64BIT */ -#define __BITOPS_WORDS(bits) (((bits)+__BITOPS_WORDSIZE-1)/__BITOPS_WORDSIZE) -#define __BITOPS_BARRIER() asm volatile("" : : : "memory") +#define __BITOPS_WORDS(bits) (((bits) + BITS_PER_LONG - 1) / BITS_PER_LONG) #ifdef CONFIG_SMP /* @@ -114,9 +109,9 @@ static inline void set_bit_cs(unsigned long nr, volatile unsigned long *ptr) addr = (unsigned long) ptr; /* calculate address for CS */ - addr += (nr ^ (nr & (__BITOPS_WORDSIZE - 1))) >> 3; + addr += (nr ^ (nr & (BITS_PER_LONG - 1))) >> 3; /* make OR mask */ - mask = 1UL << (nr & (__BITOPS_WORDSIZE - 1)); + mask = 1UL << (nr & (BITS_PER_LONG - 1)); /* Do the atomic update. */ __BITOPS_LOOP(old, new, addr, mask, __BITOPS_OR); } @@ -130,9 +125,9 @@ static inline void clear_bit_cs(unsigned long nr, volatile unsigned long *ptr) addr = (unsigned long) ptr; /* calculate address for CS */ - addr += (nr ^ (nr & (__BITOPS_WORDSIZE - 1))) >> 3; + addr += (nr ^ (nr & (BITS_PER_LONG - 1))) >> 3; /* make AND mask */ - mask = ~(1UL << (nr & (__BITOPS_WORDSIZE - 1))); + mask = ~(1UL << (nr & (BITS_PER_LONG - 1))); /* Do the atomic update. */ __BITOPS_LOOP(old, new, addr, mask, __BITOPS_AND); } @@ -146,9 +141,9 @@ static inline void change_bit_cs(unsigned long nr, volatile unsigned long *ptr) addr = (unsigned long) ptr; /* calculate address for CS */ - addr += (nr ^ (nr & (__BITOPS_WORDSIZE - 1))) >> 3; + addr += (nr ^ (nr & (BITS_PER_LONG - 1))) >> 3; /* make XOR mask */ - mask = 1UL << (nr & (__BITOPS_WORDSIZE - 1)); + mask = 1UL << (nr & (BITS_PER_LONG - 1)); /* Do the atomic update. */ __BITOPS_LOOP(old, new, addr, mask, __BITOPS_XOR); } @@ -163,12 +158,12 @@ test_and_set_bit_cs(unsigned long nr, volatile unsigned long *ptr) addr = (unsigned long) ptr; /* calculate address for CS */ - addr += (nr ^ (nr & (__BITOPS_WORDSIZE - 1))) >> 3; + addr += (nr ^ (nr & (BITS_PER_LONG - 1))) >> 3; /* make OR/test mask */ - mask = 1UL << (nr & (__BITOPS_WORDSIZE - 1)); + mask = 1UL << (nr & (BITS_PER_LONG - 1)); /* Do the atomic update. */ __BITOPS_LOOP(old, new, addr, mask, __BITOPS_OR); - __BITOPS_BARRIER(); + barrier(); return (old & mask) != 0; } @@ -182,12 +177,12 @@ test_and_clear_bit_cs(unsigned long nr, volatile unsigned long *ptr) addr = (unsigned long) ptr; /* calculate address for CS */ - addr += (nr ^ (nr & (__BITOPS_WORDSIZE - 1))) >> 3; + addr += (nr ^ (nr & (BITS_PER_LONG - 1))) >> 3; /* make AND/test mask */ - mask = ~(1UL << (nr & (__BITOPS_WORDSIZE - 1))); + mask = ~(1UL << (nr & (BITS_PER_LONG - 1))); /* Do the atomic update. */ __BITOPS_LOOP(old, new, addr, mask, __BITOPS_AND); - __BITOPS_BARRIER(); + barrier(); return (old ^ new) != 0; } @@ -201,12 +196,12 @@ test_and_change_bit_cs(unsigned long nr, volatile unsigned long *ptr) addr = (unsigned long) ptr; /* calculate address for CS */ - addr += (nr ^ (nr & (__BITOPS_WORDSIZE - 1))) >> 3; + addr += (nr ^ (nr & (BITS_PER_LONG - 1))) >> 3; /* make XOR/test mask */ - mask = 1UL << (nr & (__BITOPS_WORDSIZE - 1)); + mask = 1UL << (nr & (BITS_PER_LONG - 1)); /* Do the atomic update. */ __BITOPS_LOOP(old, new, addr, mask, __BITOPS_XOR); - __BITOPS_BARRIER(); + barrier(); return (old & mask) != 0; } #endif /* CONFIG_SMP */ @@ -218,7 +213,7 @@ static inline void __set_bit(unsigned long nr, volatile unsigned long *ptr) { unsigned long addr; - addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3); + addr = (unsigned long) ptr + ((nr ^ (BITS_PER_LONG - 8)) >> 3); asm volatile( " oc %O0(1,%R0),%1" : "=Q" (*(char *) addr) : "Q" (_oi_bitmap[nr & 7]) : "cc" ); @@ -229,7 +224,7 @@ __constant_set_bit(const unsigned long nr, volatile unsigned long *ptr) { unsigned long addr; - addr = ((unsigned long) ptr) + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3); + addr = ((unsigned long) ptr) + ((nr ^ (BITS_PER_LONG - 8)) >> 3); *(unsigned char *) addr |= 1 << (nr & 7); } @@ -246,7 +241,7 @@ __clear_bit(unsigned long nr, volatile unsigned long *ptr) { unsigned long addr; - addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3); + addr = (unsigned long) ptr + ((nr ^ (BITS_PER_LONG - 8)) >> 3); asm volatile( " nc %O0(1,%R0),%1" : "=Q" (*(char *) addr) : "Q" (_ni_bitmap[nr & 7]) : "cc" ); @@ -257,7 +252,7 @@ __constant_clear_bit(const unsigned long nr, volatile unsigned long *ptr) { unsigned long addr; - addr = ((unsigned long) ptr) + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3); + addr = ((unsigned long) ptr) + ((nr ^ (BITS_PER_LONG - 8)) >> 3); *(unsigned char *) addr &= ~(1 << (nr & 7)); } @@ -273,7 +268,7 @@ static inline void __change_bit(unsigned long nr, volatile unsigned long *ptr) { unsigned long addr; - addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3); + addr = (unsigned long) ptr + ((nr ^ (BITS_PER_LONG - 8)) >> 3); asm volatile( " xc %O0(1,%R0),%1" : "=Q" (*(char *) addr) : "Q" (_oi_bitmap[nr & 7]) : "cc" ); @@ -284,7 +279,7 @@ __constant_change_bit(const unsigned long nr, volatile unsigned long *ptr) { unsigned long addr; - addr = ((unsigned long) ptr) + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3); + addr = ((unsigned long) ptr) + ((nr ^ (BITS_PER_LONG - 8)) >> 3); *(unsigned char *) addr ^= 1 << (nr & 7); } @@ -302,7 +297,7 @@ test_and_set_bit_simple(unsigned long nr, volatile unsigned long *ptr) unsigned long addr; unsigned char ch; - addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3); + addr = (unsigned long) ptr + ((nr ^ (BITS_PER_LONG - 8)) >> 3); ch = *(unsigned char *) addr; asm volatile( " oc %O0(1,%R0),%1" @@ -321,7 +316,7 @@ test_and_clear_bit_simple(unsigned long nr, volatile unsigned long *ptr) unsigned long addr; unsigned char ch; - addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3); + addr = (unsigned long) ptr + ((nr ^ (BITS_PER_LONG - 8)) >> 3); ch = *(unsigned char *) addr; asm volatile( " nc %O0(1,%R0),%1" @@ -340,7 +335,7 @@ test_and_change_bit_simple(unsigned long nr, volatile unsigned long *ptr) unsigned long addr; unsigned char ch; - addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3); + addr = (unsigned long) ptr + ((nr ^ (BITS_PER_LONG - 8)) >> 3); ch = *(unsigned char *) addr; asm volatile( " xc %O0(1,%R0),%1" @@ -376,7 +371,7 @@ static inline int __test_bit(unsigned long nr, const volatile unsigned long *ptr unsigned long addr; unsigned char ch; - addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3); + addr = (unsigned long) ptr + ((nr ^ (BITS_PER_LONG - 8)) >> 3); ch = *(volatile unsigned char *) addr; return (ch >> (nr & 7)) & 1; } @@ -384,7 +379,7 @@ static inline int __test_bit(unsigned long nr, const volatile unsigned long *ptr static inline int __constant_test_bit(unsigned long nr, const volatile unsigned long *addr) { return (((volatile char *) addr) - [(nr^(__BITOPS_WORDSIZE-8))>>3] & (1<<(nr&7))) != 0; + [(nr^(BITS_PER_LONG-8))>>3] & (1<<(nr&7))) != 0; } #define test_bit(nr,addr) \ @@ -693,18 +688,18 @@ static inline int find_next_bit_left(const unsigned long *addr, if (offset >= size) return size; - bit = offset & (__BITOPS_WORDSIZE - 1); + bit = offset & (BITS_PER_LONG - 1); offset -= bit; size -= offset; - p = addr + offset / __BITOPS_WORDSIZE; + p = addr + offset / BITS_PER_LONG; if (bit) { set = __flo_word(0, *p & (~0UL << bit)); if (set >= size) return size + offset; - if (set < __BITOPS_WORDSIZE) + if (set < BITS_PER_LONG) return set + offset; - offset += __BITOPS_WORDSIZE; - size -= __BITOPS_WORDSIZE; + offset += BITS_PER_LONG; + size -= BITS_PER_LONG; p++; } return offset + find_first_bit_left(p, size); @@ -736,22 +731,22 @@ static inline int find_next_zero_bit (const unsigned long * addr, if (offset >= size) return size; - bit = offset & (__BITOPS_WORDSIZE - 1); + bit = offset & (BITS_PER_LONG - 1); offset -= bit; size -= offset; - p = addr + offset / __BITOPS_WORDSIZE; + p = addr + offset / BITS_PER_LONG; if (bit) { /* - * __ffz_word returns __BITOPS_WORDSIZE + * __ffz_word returns BITS_PER_LONG * if no zero bit is present in the word. */ set = __ffz_word(bit, *p >> bit); if (set >= size) return size + offset; - if (set < __BITOPS_WORDSIZE) + if (set < BITS_PER_LONG) return set + offset; - offset += __BITOPS_WORDSIZE; - size -= __BITOPS_WORDSIZE; + offset += BITS_PER_LONG; + size -= BITS_PER_LONG; p++; } return offset + find_first_zero_bit(p, size); @@ -773,22 +768,22 @@ static inline int find_next_bit (const unsigned long * addr, if (offset >= size) return size; - bit = offset & (__BITOPS_WORDSIZE - 1); + bit = offset & (BITS_PER_LONG - 1); offset -= bit; size -= offset; - p = addr + offset / __BITOPS_WORDSIZE; + p = addr + offset / BITS_PER_LONG; if (bit) { /* - * __ffs_word returns __BITOPS_WORDSIZE + * __ffs_word returns BITS_PER_LONG * if no one bit is present in the word. */ set = __ffs_word(0, *p & (~0UL << bit)); if (set >= size) return size + offset; - if (set < __BITOPS_WORDSIZE) + if (set < BITS_PER_LONG) return set + offset; - offset += __BITOPS_WORDSIZE; - size -= __BITOPS_WORDSIZE; + offset += BITS_PER_LONG; + size -= BITS_PER_LONG; p++; } return offset + find_first_bit(p, size); @@ -843,22 +838,22 @@ static inline int find_next_zero_bit_le(void *vaddr, unsigned long size, if (offset >= size) return size; - bit = offset & (__BITOPS_WORDSIZE - 1); + bit = offset & (BITS_PER_LONG - 1); offset -= bit; size -= offset; - p = addr + offset / __BITOPS_WORDSIZE; + p = addr + offset / BITS_PER_LONG; if (bit) { /* - * s390 version of ffz returns __BITOPS_WORDSIZE + * s390 version of ffz returns BITS_PER_LONG * if no zero bit is present in the word. */ set = __ffz_word(bit, __load_ulong_le(p, 0) >> bit); if (set >= size) return size + offset; - if (set < __BITOPS_WORDSIZE) + if (set < BITS_PER_LONG) return set + offset; - offset += __BITOPS_WORDSIZE; - size -= __BITOPS_WORDSIZE; + offset += BITS_PER_LONG; + size -= BITS_PER_LONG; p++; } return offset + find_first_zero_bit_le(p, size); @@ -885,22 +880,22 @@ static inline int find_next_bit_le(void *vaddr, unsigned long size, if (offset >= size) return size; - bit = offset & (__BITOPS_WORDSIZE - 1); + bit = offset & (BITS_PER_LONG - 1); offset -= bit; size -= offset; - p = addr + offset / __BITOPS_WORDSIZE; + p = addr + offset / BITS_PER_LONG; if (bit) { /* - * s390 version of ffz returns __BITOPS_WORDSIZE + * s390 version of ffz returns BITS_PER_LONG * if no zero bit is present in the word. */ set = __ffs_word(0, __load_ulong_le(p, 0) & (~0UL << bit)); if (set >= size) return size + offset; - if (set < __BITOPS_WORDSIZE) + if (set < BITS_PER_LONG) return set + offset; - offset += __BITOPS_WORDSIZE; - size -= __BITOPS_WORDSIZE; + offset += BITS_PER_LONG; + size -= BITS_PER_LONG; p++; } return offset + find_first_bit_le(p, size); diff --git a/arch/s390/include/asm/ccwdev.h b/arch/s390/include/asm/ccwdev.h index e6061617a50..f201af8be58 100644 --- a/arch/s390/include/asm/ccwdev.h +++ b/arch/s390/include/asm/ccwdev.h @@ -220,7 +220,8 @@ extern void ccw_device_get_id(struct ccw_device *, struct ccw_dev_id *); #define to_ccwdrv(n) container_of(n, struct ccw_driver, driver) extern struct ccw_device *ccw_device_probe_console(void); -extern int ccw_device_force_console(void); +extern void ccw_device_wait_idle(struct ccw_device *); +extern int ccw_device_force_console(struct ccw_device *); int ccw_device_siosl(struct ccw_device *); diff --git a/arch/s390/include/asm/cio.h b/arch/s390/include/asm/cio.h index ad2b924167d..ffb898961c8 100644 --- a/arch/s390/include/asm/cio.h +++ b/arch/s390/include/asm/cio.h @@ -296,8 +296,6 @@ static inline int ccw_dev_id_is_equal(struct ccw_dev_id *dev_id1, return 0; } -extern void wait_cons_dev(void); - extern void css_schedule_reprobe(void); extern void reipl_ccw_dev(struct ccw_dev_id *id); diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h index f8c6df6cd1f..c1e7c646727 100644 --- a/arch/s390/include/asm/compat.h +++ b/arch/s390/include/asm/compat.h @@ -70,6 +70,22 @@ typedef u32 compat_ulong_t; typedef u64 compat_u64; typedef u32 compat_uptr_t; +typedef struct { + u32 mask; + u32 addr; +} __aligned(8) psw_compat_t; + +typedef struct { + psw_compat_t psw; + u32 gprs[NUM_GPRS]; + u32 acrs[NUM_ACRS]; + u32 orig_gpr2; +} s390_compat_regs; + +typedef struct { + u32 gprs_high[NUM_GPRS]; +} s390_compat_regs_high; + struct compat_timespec { compat_time_t tv_sec; s32 tv_nsec; @@ -124,18 +140,33 @@ struct compat_flock64 { }; struct compat_statfs { - s32 f_type; - s32 f_bsize; - s32 f_blocks; - s32 f_bfree; - s32 f_bavail; - s32 f_files; - s32 f_ffree; + u32 f_type; + u32 f_bsize; + u32 f_blocks; + u32 f_bfree; + u32 f_bavail; + u32 f_files; + u32 f_ffree; + compat_fsid_t f_fsid; + u32 f_namelen; + u32 f_frsize; + u32 f_flags; + u32 f_spare[4]; +}; + +struct compat_statfs64 { + u32 f_type; + u32 f_bsize; + u64 f_blocks; + u64 f_bfree; + u64 f_bavail; + u64 f_files; + u64 f_ffree; compat_fsid_t f_fsid; - s32 f_namelen; - s32 f_frsize; - s32 f_flags; - s32 f_spare[5]; + u32 f_namelen; + u32 f_frsize; + u32 f_flags; + u32 f_spare[4]; }; #define COMPAT_RLIM_OLD_INFINITY 0x7fffffff @@ -248,8 +279,6 @@ static inline int is_compat_task(void) return is_32bit_task(); } -#endif - static inline void __user *arch_compat_alloc_user_space(long len) { unsigned long stack; @@ -260,6 +289,8 @@ static inline void __user *arch_compat_alloc_user_space(long len) return (void __user *) (stack - len); } +#endif + struct compat_ipc64_perm { compat_key_t key; __compat_uid32_t uid; diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h index 1bfdf24b85a..78f4f8711d5 100644 --- a/arch/s390/include/asm/elf.h +++ b/arch/s390/include/asm/elf.h @@ -119,6 +119,8 @@ */ #include <asm/ptrace.h> +#include <asm/compat.h> +#include <asm/syscall.h> #include <asm/user.h> typedef s390_fp_regs elf_fpregset_t; @@ -180,18 +182,31 @@ extern unsigned long elf_hwcap; extern char elf_platform[]; #define ELF_PLATFORM (elf_platform) -#ifdef CONFIG_64BIT +#ifndef CONFIG_COMPAT +#define SET_PERSONALITY(ex) \ +do { \ + set_personality(PER_LINUX | \ + (current->personality & (~PER_MASK))); \ + current_thread_info()->sys_call_table = \ + (unsigned long) &sys_call_table; \ +} while (0) +#else /* CONFIG_COMPAT */ #define SET_PERSONALITY(ex) \ do { \ if (personality(current->personality) != PER_LINUX32) \ set_personality(PER_LINUX | \ (current->personality & ~PER_MASK)); \ - if ((ex).e_ident[EI_CLASS] == ELFCLASS32) \ + if ((ex).e_ident[EI_CLASS] == ELFCLASS32) { \ set_thread_flag(TIF_31BIT); \ - else \ + current_thread_info()->sys_call_table = \ + (unsigned long) &sys_call_table_emu; \ + } else { \ clear_thread_flag(TIF_31BIT); \ + current_thread_info()->sys_call_table = \ + (unsigned long) &sys_call_table; \ + } \ } while (0) -#endif /* CONFIG_64BIT */ +#endif /* CONFIG_COMPAT */ #define STACK_RND_MASK 0x7ffUL diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h index 27cb32185ce..379d96e2105 100644 --- a/arch/s390/include/asm/io.h +++ b/arch/s390/include/asm/io.h @@ -50,10 +50,6 @@ void unxlate_dev_mem_ptr(unsigned long phys, void *addr); #define ioremap_nocache(addr, size) ioremap(addr, size) #define ioremap_wc ioremap_nocache -/* TODO: s390 cannot support io_remap_pfn_range... */ -#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) \ - remap_pfn_range(vma, vaddr, pfn, size, prot) - static inline void __iomem *ioremap(unsigned long offset, unsigned long size) { return (void __iomem *) offset; diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index 05333b7f046..6c1801235db 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -140,6 +140,7 @@ static inline bool zdev_enabled(struct zpci_dev *zdev) struct zpci_dev *zpci_alloc_device(void); int zpci_create_device(struct zpci_dev *); int zpci_enable_device(struct zpci_dev *); +int zpci_disable_device(struct zpci_dev *); void zpci_stop_device(struct zpci_dev *); void zpci_free_device(struct zpci_dev *); int zpci_scan_device(struct zpci_dev *); diff --git a/arch/s390/include/asm/pci_debug.h b/arch/s390/include/asm/pci_debug.h index 6bbec4265b6..1ca5d1047c7 100644 --- a/arch/s390/include/asm/pci_debug.h +++ b/arch/s390/include/asm/pci_debug.h @@ -7,14 +7,11 @@ extern debug_info_t *pci_debug_msg_id; extern debug_info_t *pci_debug_err_id; #ifdef CONFIG_PCI_DEBUG -#define zpci_dbg(fmt, args...) \ - do { \ - if (pci_debug_msg_id->level >= 2) \ - debug_sprintf_event(pci_debug_msg_id, 2, fmt , ## args);\ - } while (0) +#define zpci_dbg(imp, fmt, args...) \ + debug_sprintf_event(pci_debug_msg_id, imp, fmt, ##args) #else /* !CONFIG_PCI_DEBUG */ -#define zpci_dbg(fmt, args...) do { } while (0) +#define zpci_dbg(imp, fmt, args...) do { } while (0) #endif #define zpci_err(text...) \ diff --git a/arch/s390/include/asm/pci_insn.h b/arch/s390/include/asm/pci_insn.h index 1486a98d5da..e6a2bdd4d70 100644 --- a/arch/s390/include/asm/pci_insn.h +++ b/arch/s390/include/asm/pci_insn.h @@ -1,10 +1,6 @@ #ifndef _ASM_S390_PCI_INSN_H #define _ASM_S390_PCI_INSN_H -#include <linux/delay.h> - -#define ZPCI_INSN_BUSY_DELAY 1 /* 1 microsecond */ - /* Load/Store status codes */ #define ZPCI_PCI_ST_FUNC_NOT_ENABLED 4 #define ZPCI_PCI_ST_FUNC_IN_ERR 8 @@ -82,199 +78,12 @@ struct zpci_fib { u64 reserved7; } __packed; -/* Modify PCI Function Controls */ -static inline u8 __mpcifc(u64 req, struct zpci_fib *fib, u8 *status) -{ - u8 cc; - - asm volatile ( - " .insn rxy,0xe300000000d0,%[req],%[fib]\n" - " ipm %[cc]\n" - " srl %[cc],28\n" - : [cc] "=d" (cc), [req] "+d" (req), [fib] "+Q" (*fib) - : : "cc"); - *status = req >> 24 & 0xff; - return cc; -} - -static inline int mpcifc_instr(u64 req, struct zpci_fib *fib) -{ - u8 cc, status; - - do { - cc = __mpcifc(req, fib, &status); - if (cc == 2) - msleep(ZPCI_INSN_BUSY_DELAY); - } while (cc == 2); - - if (cc) - printk_once(KERN_ERR "%s: error cc: %d status: %d\n", - __func__, cc, status); - return (cc) ? -EIO : 0; -} - -/* Refresh PCI Translations */ -static inline u8 __rpcit(u64 fn, u64 addr, u64 range, u8 *status) -{ - register u64 __addr asm("2") = addr; - register u64 __range asm("3") = range; - u8 cc; - - asm volatile ( - " .insn rre,0xb9d30000,%[fn],%[addr]\n" - " ipm %[cc]\n" - " srl %[cc],28\n" - : [cc] "=d" (cc), [fn] "+d" (fn) - : [addr] "d" (__addr), "d" (__range) - : "cc"); - *status = fn >> 24 & 0xff; - return cc; -} - -static inline int rpcit_instr(u64 fn, u64 addr, u64 range) -{ - u8 cc, status; - - do { - cc = __rpcit(fn, addr, range, &status); - if (cc == 2) - udelay(ZPCI_INSN_BUSY_DELAY); - } while (cc == 2); - - if (cc) - printk_once(KERN_ERR "%s: error cc: %d status: %d dma_addr: %Lx size: %Lx\n", - __func__, cc, status, addr, range); - return (cc) ? -EIO : 0; -} - -/* Store PCI function controls */ -static inline u8 __stpcifc(u32 handle, u8 space, struct zpci_fib *fib, u8 *status) -{ - u64 fn = (u64) handle << 32 | space << 16; - u8 cc; - - asm volatile ( - " .insn rxy,0xe300000000d4,%[fn],%[fib]\n" - " ipm %[cc]\n" - " srl %[cc],28\n" - : [cc] "=d" (cc), [fn] "+d" (fn), [fib] "=m" (*fib) - : : "cc"); - *status = fn >> 24 & 0xff; - return cc; -} - -/* Set Interruption Controls */ -static inline void sic_instr(u16 ctl, char *unused, u8 isc) -{ - asm volatile ( - " .insn rsy,0xeb00000000d1,%[ctl],%[isc],%[u]\n" - : : [ctl] "d" (ctl), [isc] "d" (isc << 27), [u] "Q" (*unused)); -} - -/* PCI Load */ -static inline u8 __pcilg(u64 *data, u64 req, u64 offset, u8 *status) -{ - register u64 __req asm("2") = req; - register u64 __offset asm("3") = offset; - u64 __data; - u8 cc; - - asm volatile ( - " .insn rre,0xb9d20000,%[data],%[req]\n" - " ipm %[cc]\n" - " srl %[cc],28\n" - : [cc] "=d" (cc), [data] "=d" (__data), [req] "+d" (__req) - : "d" (__offset) - : "cc"); - *status = __req >> 24 & 0xff; - *data = __data; - return cc; -} - -static inline int pcilg_instr(u64 *data, u64 req, u64 offset) -{ - u8 cc, status; - - do { - cc = __pcilg(data, req, offset, &status); - if (cc == 2) - udelay(ZPCI_INSN_BUSY_DELAY); - } while (cc == 2); - - if (cc) { - printk_once(KERN_ERR "%s: error cc: %d status: %d req: %Lx offset: %Lx\n", - __func__, cc, status, req, offset); - /* TODO: on IO errors set data to 0xff... - * here or in users of pcilg (le conversion)? - */ - } - return (cc) ? -EIO : 0; -} - -/* PCI Store */ -static inline u8 __pcistg(u64 data, u64 req, u64 offset, u8 *status) -{ - register u64 __req asm("2") = req; - register u64 __offset asm("3") = offset; - u8 cc; - - asm volatile ( - " .insn rre,0xb9d00000,%[data],%[req]\n" - " ipm %[cc]\n" - " srl %[cc],28\n" - : [cc] "=d" (cc), [req] "+d" (__req) - : "d" (__offset), [data] "d" (data) - : "cc"); - *status = __req >> 24 & 0xff; - return cc; -} - -static inline int pcistg_instr(u64 data, u64 req, u64 offset) -{ - u8 cc, status; - - do { - cc = __pcistg(data, req, offset, &status); - if (cc == 2) - udelay(ZPCI_INSN_BUSY_DELAY); - } while (cc == 2); - - if (cc) - printk_once(KERN_ERR "%s: error cc: %d status: %d req: %Lx offset: %Lx\n", - __func__, cc, status, req, offset); - return (cc) ? -EIO : 0; -} - -/* PCI Store Block */ -static inline u8 __pcistb(const u64 *data, u64 req, u64 offset, u8 *status) -{ - u8 cc; - - asm volatile ( - " .insn rsy,0xeb00000000d0,%[req],%[offset],%[data]\n" - " ipm %[cc]\n" - " srl %[cc],28\n" - : [cc] "=d" (cc), [req] "+d" (req) - : [offset] "d" (offset), [data] "Q" (*data) - : "cc"); - *status = req >> 24 & 0xff; - return cc; -} - -static inline int pcistb_instr(const u64 *data, u64 req, u64 offset) -{ - u8 cc, status; - - do { - cc = __pcistb(data, req, offset, &status); - if (cc == 2) - udelay(ZPCI_INSN_BUSY_DELAY); - } while (cc == 2); - if (cc) - printk_once(KERN_ERR "%s: error cc: %d status: %d req: %Lx offset: %Lx\n", - __func__, cc, status, req, offset); - return (cc) ? -EIO : 0; -} +int s390pci_mod_fc(u64 req, struct zpci_fib *fib); +int s390pci_refresh_trans(u64 fn, u64 addr, u64 range); +int s390pci_load(u64 *data, u64 req, u64 offset); +int s390pci_store(u64 data, u64 req, u64 offset); +int s390pci_store_block(const u64 *data, u64 req, u64 offset); +void set_irq_ctrl(u16 ctl, char *unused, u8 isc); #endif diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h index 5fd81f31d6c..83a9caa6ae5 100644 --- a/arch/s390/include/asm/pci_io.h +++ b/arch/s390/include/asm/pci_io.h @@ -36,7 +36,7 @@ static inline RETTYPE zpci_read_##RETTYPE(const volatile void __iomem *addr) \ u64 data; \ int rc; \ \ - rc = pcilg_instr(&data, req, ZPCI_OFFSET(addr)); \ + rc = s390pci_load(&data, req, ZPCI_OFFSET(addr)); \ if (rc) \ data = -1ULL; \ return (RETTYPE) data; \ @@ -50,7 +50,7 @@ static inline void zpci_write_##VALTYPE(VALTYPE val, \ u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, LENGTH); \ u64 data = (VALTYPE) val; \ \ - pcistg_instr(data, req, ZPCI_OFFSET(addr)); \ + s390pci_store(data, req, ZPCI_OFFSET(addr)); \ } zpci_read(8, u64) @@ -83,15 +83,18 @@ static inline int zpci_write_single(u64 req, const u64 *data, u64 offset, u8 len val = 0; /* let FW report error */ break; } - return pcistg_instr(val, req, offset); + return s390pci_store(val, req, offset); } static inline int zpci_read_single(u64 req, u64 *dst, u64 offset, u8 len) { u64 data; - u8 cc; + int cc; + + cc = s390pci_load(&data, req, offset); + if (cc) + goto out; - cc = pcilg_instr(&data, req, offset); switch (len) { case 1: *((u8 *) dst) = (u8) data; @@ -106,12 +109,13 @@ static inline int zpci_read_single(u64 req, u64 *dst, u64 offset, u8 len) *((u64 *) dst) = (u64) data; break; } +out: return cc; } static inline int zpci_write_block(u64 req, const u64 *data, u64 offset) { - return pcistb_instr(data, req, offset); + return s390pci_store_block(data, req, offset); } static inline u8 zpci_get_max_write_size(u64 src, u64 dst, int len, int max) diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 4a5443118cf..4a64c0e5428 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -57,6 +57,10 @@ extern unsigned long zero_page_mask; (((unsigned long)(vaddr)) &zero_page_mask)))) #define __HAVE_COLOR_ZERO_PAGE +/* TODO: s390 cannot support io_remap_pfn_range... */ +#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) \ + remap_pfn_range(vma, vaddr, pfn, size, prot) + #endif /* !__ASSEMBLY__ */ /* @@ -760,6 +764,8 @@ void gmap_disable(struct gmap *gmap); int gmap_map_segment(struct gmap *gmap, unsigned long from, unsigned long to, unsigned long length); int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len); +unsigned long __gmap_translate(unsigned long address, struct gmap *); +unsigned long gmap_translate(unsigned long address, struct gmap *); unsigned long __gmap_fault(unsigned long address, struct gmap *); unsigned long gmap_fault(unsigned long address, struct gmap *); void gmap_discard(unsigned long from, unsigned long to, struct gmap *); diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 94e749c9023..6b499870662 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -161,7 +161,8 @@ extern unsigned long thread_saved_pc(struct task_struct *t); extern void show_code(struct pt_regs *regs); extern void print_fn_code(unsigned char *code, unsigned long len); -extern int insn_to_mnemonic(unsigned char *instruction, char buf[8]); +extern int insn_to_mnemonic(unsigned char *instruction, char *buf, + unsigned int len); unsigned long get_wchan(struct task_struct *p); #define task_pt_regs(tsk) ((struct pt_regs *) \ diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h index 3ee5da3bc10..559512a455d 100644 --- a/arch/s390/include/asm/ptrace.h +++ b/arch/s390/include/asm/ptrace.h @@ -9,9 +9,7 @@ #include <uapi/asm/ptrace.h> #ifndef __ASSEMBLY__ -#ifndef __s390x__ -#else /* __s390x__ */ -#endif /* __s390x__ */ + extern long psw_kernel_bits; extern long psw_user_bits; @@ -77,8 +75,6 @@ struct per_struct_kernel { #define PER_CONTROL_SUSPENSION 0x00400000UL #define PER_CONTROL_ALTERATION 0x00200000UL -#ifdef __s390x__ -#endif /* __s390x__ */ /* * These are defined as per linux/ptrace.h, which see. */ diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h index fe7b99759e1..cd29d2f4e4f 100644 --- a/arch/s390/include/asm/syscall.h +++ b/arch/s390/include/asm/syscall.h @@ -23,6 +23,7 @@ * type here is what we want [need] for both 32 bit and 64 bit systems. */ extern const unsigned int sys_call_table[]; +extern const unsigned int sys_call_table_emu[]; static inline long syscall_get_nr(struct task_struct *task, struct pt_regs *regs) diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h index 9e2cfe0349c..eb5f64d26d0 100644 --- a/arch/s390/include/asm/thread_info.h +++ b/arch/s390/include/asm/thread_info.h @@ -14,13 +14,8 @@ #define THREAD_ORDER 1 #define ASYNC_ORDER 1 #else /* CONFIG_64BIT */ -#ifndef __SMALL_STACK #define THREAD_ORDER 2 #define ASYNC_ORDER 2 -#else -#define THREAD_ORDER 1 -#define ASYNC_ORDER 1 -#endif #endif /* CONFIG_64BIT */ #define THREAD_SIZE (PAGE_SIZE << THREAD_ORDER) @@ -41,6 +36,7 @@ struct thread_info { struct task_struct *task; /* main task structure */ struct exec_domain *exec_domain; /* execution domain */ unsigned long flags; /* low level flags */ + unsigned long sys_call_table; /* System call table address */ unsigned int cpu; /* current CPU */ int preempt_count; /* 0 => preemptable, <0 => BUG */ struct restart_block restart_block; diff --git a/arch/s390/include/uapi/asm/ptrace.h b/arch/s390/include/uapi/asm/ptrace.h index a5ca214b34f..3aa9f1ec5b2 100644 --- a/arch/s390/include/uapi/asm/ptrace.h +++ b/arch/s390/include/uapi/asm/ptrace.h @@ -215,12 +215,6 @@ typedef struct unsigned long addr; } __attribute__ ((aligned(8))) psw_t; -typedef struct -{ - __u32 mask; - __u32 addr; -} __attribute__ ((aligned(8))) psw_compat_t; - #ifndef __s390x__ #define PSW_MASK_PER 0x40000000UL @@ -295,20 +289,6 @@ typedef struct unsigned long orig_gpr2; } s390_regs; -typedef struct -{ - psw_compat_t psw; - __u32 gprs[NUM_GPRS]; - __u32 acrs[NUM_ACRS]; - __u32 orig_gpr2; -} s390_compat_regs; - -typedef struct -{ - __u32 gprs_high[NUM_GPRS]; -} s390_compat_regs_high; - - /* * Now for the user space program event recording (trace) definitions. * The following structures are used only for the ptrace interface, don't diff --git a/arch/s390/include/uapi/asm/statfs.h b/arch/s390/include/uapi/asm/statfs.h index 5acca0a34c2..a61d538756f 100644 --- a/arch/s390/include/uapi/asm/statfs.h +++ b/arch/s390/include/uapi/asm/statfs.h @@ -7,9 +7,6 @@ #ifndef _S390_STATFS_H #define _S390_STATFS_H -#ifndef __s390x__ -#include <asm-generic/statfs.h> -#else /* * We can't use <asm-generic/statfs.h> because in 64-bit mode * we mix ints of different sizes in our struct statfs. @@ -21,49 +18,33 @@ typedef __kernel_fsid_t fsid_t; #endif struct statfs { - int f_type; - int f_bsize; - long f_blocks; - long f_bfree; - long f_bavail; - long f_files; - long f_ffree; + unsigned int f_type; + unsigned int f_bsize; + unsigned long f_blocks; + unsigned long f_bfree; + unsigned long f_bavail; + unsigned long f_files; + unsigned long f_ffree; __kernel_fsid_t f_fsid; - int f_namelen; - int f_frsize; - int f_flags; - int f_spare[4]; + unsigned int f_namelen; + unsigned int f_frsize; + unsigned int f_flags; + unsigned int f_spare[4]; }; struct statfs64 { - int f_type; - int f_bsize; - long f_blocks; - long f_bfree; - long f_bavail; - long f_files; - long f_ffree; + unsigned int f_type; + unsigned int f_bsize; + unsigned long f_blocks; + unsigned long f_bfree; + unsigned long f_bavail; + unsigned long f_files; + unsigned long f_ffree; __kernel_fsid_t f_fsid; - int f_namelen; - int f_frsize; - int f_flags; - int f_spare[4]; + unsigned int f_namelen; + unsigned int f_frsize; + unsigned int f_flags; + unsigned int f_spare[4]; }; -struct compat_statfs64 { - __u32 f_type; - __u32 f_bsize; - __u64 f_blocks; - __u64 f_bfree; - __u64 f_bavail; - __u64 f_files; - __u64 f_ffree; - __kernel_fsid_t f_fsid; - __u32 f_namelen; - __u32 f_frsize; - __u32 f_flags; - __u32 f_spare[4]; -}; - -#endif /* __s390x__ */ #endif diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index 2ac311ef5c9..1386fcaf4ef 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -14,16 +14,25 @@ endif CFLAGS_smp.o := -Wno-nonnull # +# Disable tailcall optimizations for stack / callchain walking functions +# since this might generate broken code when accessing register 15 and +# passing its content to other functions. +# +CFLAGS_stacktrace.o += -fno-optimize-sibling-calls +CFLAGS_dumpstack.o += -fno-optimize-sibling-calls + +# # Pass UTS_MACHINE for user_regset definition # CFLAGS_ptrace.o += -DUTS_MACHINE='"$(UTS_MACHINE)"' CFLAGS_sysinfo.o += -Iinclude/math-emu -Iarch/s390/math-emu -w -obj-y := bitmap.o traps.o time.o process.o base.o early.o setup.o vtime.o \ - processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o \ - debug.o irq.o ipl.o dis.o diag.o mem_detect.o sclp.o vdso.o \ - sysinfo.o jump_label.o lgr.o os_info.o machine_kexec.o pgm_check.o +obj-y := bitmap.o traps.o time.o process.o base.o early.o setup.o vtime.o +obj-y += processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o +obj-y += debug.o irq.o ipl.o dis.o diag.o mem_detect.o sclp.o vdso.o +obj-y += sysinfo.o jump_label.o lgr.o os_info.o machine_kexec.o pgm_check.o +obj-y += dumpstack.o obj-y += $(if $(CONFIG_64BIT),entry64.o,entry.o) obj-y += $(if $(CONFIG_64BIT),reipl64.o,reipl.o) diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index fface87056e..7a82f9f7010 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -35,6 +35,7 @@ int main(void) DEFINE(__TI_task, offsetof(struct thread_info, task)); DEFINE(__TI_domain, offsetof(struct thread_info, exec_domain)); DEFINE(__TI_flags, offsetof(struct thread_info, flags)); + DEFINE(__TI_sysc_table, offsetof(struct thread_info, sys_call_table)); DEFINE(__TI_cpu, offsetof(struct thread_info, cpu)); DEFINE(__TI_precount, offsetof(struct thread_info, preempt_count)); DEFINE(__TI_user_timer, offsetof(struct thread_info, user_timer)); diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c index 6de049fbe62..c439ac9ced0 100644 --- a/arch/s390/kernel/compat_signal.c +++ b/arch/s390/kernel/compat_signal.c @@ -362,6 +362,7 @@ static int setup_frame32(int sig, struct k_sigaction *ka, /* set extra registers only for synchronous signals */ regs->gprs[4] = regs->int_code & 127; regs->gprs[5] = regs->int_parm_long; + regs->gprs[6] = task_thread_info(current)->last_break; } /* Place signal number on stack to allow backtrace from handler. */ @@ -421,6 +422,7 @@ static int setup_rt_frame32(int sig, struct k_sigaction *ka, siginfo_t *info, regs->gprs[2] = map_signal(sig); regs->gprs[3] = (__force __u64) &frame->info; regs->gprs[4] = (__force __u64) &frame->uc; + regs->gprs[5] = task_thread_info(current)->last_break; return 0; give_sigsegv: diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c index 3ad5e954016..7f4a4a8c847 100644 --- a/arch/s390/kernel/dis.c +++ b/arch/s390/kernel/dis.c @@ -1696,14 +1696,15 @@ static struct insn *find_insn(unsigned char *code) * insn_to_mnemonic - decode an s390 instruction * @instruction: instruction to decode * @buf: buffer to fill with mnemonic + * @len: length of buffer * * Decode the instruction at @instruction and store the corresponding - * mnemonic into @buf. + * mnemonic into @buf of length @len. * @buf is left unchanged if the instruction could not be decoded. * Returns: * %0 on success, %-ENOENT if the instruction was not found. */ -int insn_to_mnemonic(unsigned char *instruction, char buf[8]) +int insn_to_mnemonic(unsigned char *instruction, char *buf, unsigned int len) { struct insn *insn; @@ -1711,10 +1712,10 @@ int insn_to_mnemonic(unsigned char *instruction, char buf[8]) if (!insn) return -ENOENT; if (insn->name[0] == '\0') - snprintf(buf, 8, "%s", + snprintf(buf, len, "%s", long_insn_name[(int) insn->name[1]]); else - snprintf(buf, 8, "%.5s", insn->name); + snprintf(buf, len, "%.5s", insn->name); return 0; } EXPORT_SYMBOL_GPL(insn_to_mnemonic); diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c new file mode 100644 index 00000000000..03dce39d01e --- /dev/null +++ b/arch/s390/kernel/dumpstack.c @@ -0,0 +1,236 @@ +/* + * Stack dumping functions + * + * Copyright IBM Corp. 1999, 2013 + */ + +#include <linux/kallsyms.h> +#include <linux/hardirq.h> +#include <linux/kprobes.h> +#include <linux/utsname.h> +#include <linux/export.h> +#include <linux/kdebug.h> +#include <linux/ptrace.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <asm/processor.h> +#include <asm/debug.h> +#include <asm/ipl.h> + +#ifndef CONFIG_64BIT +#define LONG "%08lx " +#define FOURLONG "%08lx %08lx %08lx %08lx\n" +static int kstack_depth_to_print = 12; +#else /* CONFIG_64BIT */ +#define LONG "%016lx " +#define FOURLONG "%016lx %016lx %016lx %016lx\n" +static int kstack_depth_to_print = 20; +#endif /* CONFIG_64BIT */ + +/* + * For show_trace we have tree different stack to consider: + * - the panic stack which is used if the kernel stack has overflown + * - the asynchronous interrupt stack (cpu related) + * - the synchronous kernel stack (process related) + * The stack trace can start at any of the three stack and can potentially + * touch all of them. The order is: panic stack, async stack, sync stack. + */ +static unsigned long +__show_trace(unsigned long sp, unsigned long low, unsigned long high) +{ + struct stack_frame *sf; + struct pt_regs *regs; + + while (1) { + sp = sp & PSW_ADDR_INSN; + if (sp < low || sp > high - sizeof(*sf)) + return sp; + sf = (struct stack_frame *) sp; + printk("([<%016lx>] ", sf->gprs[8] & PSW_ADDR_INSN); + print_symbol("%s)\n", sf->gprs[8] & PSW_ADDR_INSN); + /* Follow the backchain. */ + while (1) { + low = sp; + sp = sf->back_chain & PSW_ADDR_INSN; + if (!sp) + break; + if (sp <= low || sp > high - sizeof(*sf)) + return sp; + sf = (struct stack_frame *) sp; + printk(" [<%016lx>] ", sf->gprs[8] & PSW_ADDR_INSN); + print_symbol("%s\n", sf->gprs[8] & PSW_ADDR_INSN); + } + /* Zero backchain detected, check for interrupt frame. */ + sp = (unsigned long) (sf + 1); + if (sp <= low || sp > high - sizeof(*regs)) + return sp; + regs = (struct pt_regs *) sp; + printk(" [<%016lx>] ", regs->psw.addr & PSW_ADDR_INSN); + print_symbol("%s\n", regs->psw.addr & PSW_ADDR_INSN); + low = sp; + sp = regs->gprs[15]; + } +} + +static void show_trace(struct task_struct *task, unsigned long *stack) +{ + register unsigned long __r15 asm ("15"); + unsigned long sp; + + sp = (unsigned long) stack; + if (!sp) + sp = task ? task->thread.ksp : __r15; + printk("Call Trace:\n"); +#ifdef CONFIG_CHECK_STACK + sp = __show_trace(sp, S390_lowcore.panic_stack - 4096, + S390_lowcore.panic_stack); +#endif + sp = __show_trace(sp, S390_lowcore.async_stack - ASYNC_SIZE, + S390_lowcore.async_stack); + if (task) + __show_trace(sp, (unsigned long) task_stack_page(task), + (unsigned long) task_stack_page(task) + THREAD_SIZE); + else + __show_trace(sp, S390_lowcore.thread_info, + S390_lowcore.thread_info + THREAD_SIZE); + if (!task) + task = current; + debug_show_held_locks(task); +} + +void show_stack(struct task_struct *task, unsigned long *sp) +{ + register unsigned long *__r15 asm ("15"); + unsigned long *stack; + int i; + + if (!sp) + stack = task ? (unsigned long *) task->thread.ksp : __r15; + else + stack = sp; + + for (i = 0; i < kstack_depth_to_print; i++) { + if (((addr_t) stack & (THREAD_SIZE-1)) == 0) + break; + if ((i * sizeof(long) % 32) == 0) + printk("%s ", i == 0 ? "" : "\n"); + printk(LONG, *stack++); + } + printk("\n"); + show_trace(task, sp); +} + +static void show_last_breaking_event(struct pt_regs *regs) +{ +#ifdef CONFIG_64BIT + printk("Last Breaking-Event-Address:\n"); + printk(" [<%016lx>] ", regs->args[0] & PSW_ADDR_INSN); + print_symbol("%s\n", regs->args[0] & PSW_ADDR_INSN); +#endif +} + +/* + * The architecture-independent dump_stack generator + */ +void dump_stack(void) +{ + printk("CPU: %d %s %s %.*s\n", + task_thread_info(current)->cpu, print_tainted(), + init_utsname()->release, + (int)strcspn(init_utsname()->version, " "), + init_utsname()->version); + printk("Process %s (pid: %d, task: %p, ksp: %p)\n", + current->comm, current->pid, current, + (void *) current->thread.ksp); + show_stack(NULL, NULL); +} +EXPORT_SYMBOL(dump_stack); + +static inline int mask_bits(struct pt_regs *regs, unsigned long bits) +{ + return (regs->psw.mask & bits) / ((~bits + 1) & bits); +} + +void show_registers(struct pt_regs *regs) +{ + char *mode; + + mode = user_mode(regs) ? "User" : "Krnl"; + printk("%s PSW : %p %p", + mode, (void *) regs->psw.mask, + (void *) regs->psw.addr); + print_symbol(" (%s)\n", regs->psw.addr & PSW_ADDR_INSN); + printk(" R:%x T:%x IO:%x EX:%x Key:%x M:%x W:%x " + "P:%x AS:%x CC:%x PM:%x", mask_bits(regs, PSW_MASK_PER), + mask_bits(regs, PSW_MASK_DAT), mask_bits(regs, PSW_MASK_IO), + mask_bits(regs, PSW_MASK_EXT), mask_bits(regs, PSW_MASK_KEY), + mask_bits(regs, PSW_MASK_MCHECK), mask_bits(regs, PSW_MASK_WAIT), + mask_bits(regs, PSW_MASK_PSTATE), mask_bits(regs, PSW_MASK_ASC), + mask_bits(regs, PSW_MASK_CC), mask_bits(regs, PSW_MASK_PM)); +#ifdef CONFIG_64BIT + printk(" EA:%x", mask_bits(regs, PSW_MASK_EA | PSW_MASK_BA)); +#endif + printk("\n%s GPRS: " FOURLONG, mode, + regs->gprs[0], regs->gprs[1], regs->gprs[2], regs->gprs[3]); + printk(" " FOURLONG, + regs->gprs[4], regs->gprs[5], regs->gprs[6], regs->gprs[7]); + printk(" " FOURLONG, + regs->gprs[8], regs->gprs[9], regs->gprs[10], regs->gprs[11]); + printk(" " FOURLONG, + regs->gprs[12], regs->gprs[13], regs->gprs[14], regs->gprs[15]); + show_code(regs); +} + +void show_regs(struct pt_regs *regs) +{ + printk("CPU: %d %s %s %.*s\n", + task_thread_info(current)->cpu, print_tainted(), + init_utsname()->release, + (int)strcspn(init_utsname()->version, " "), + init_utsname()->version); + printk("Process %s (pid: %d, task: %p, ksp: %p)\n", + current->comm, current->pid, current, + (void *) current->thread.ksp); + show_registers(regs); + /* Show stack backtrace if pt_regs is from kernel mode */ + if (!user_mode(regs)) + show_trace(NULL, (unsigned long *) regs->gprs[15]); + show_last_breaking_event(regs); +} + +static DEFINE_SPINLOCK(die_lock); + +void die(struct pt_regs *regs, const char *str) +{ + static int die_counter; + + oops_enter(); + lgr_info_log(); + debug_stop_all(); + console_verbose(); + spin_lock_irq(&die_lock); + bust_spinlocks(1); + printk("%s: %04x [#%d] ", str, regs->int_code & 0xffff, ++die_counter); +#ifdef CONFIG_PREEMPT + printk("PREEMPT "); +#endif +#ifdef CONFIG_SMP + printk("SMP "); +#endif +#ifdef CONFIG_DEBUG_PAGEALLOC + printk("DEBUG_PAGEALLOC"); +#endif + printk("\n"); + notify_die(DIE_OOPS, str, regs, 0, regs->int_code & 0xffff, SIGSEGV); + print_modules(); + show_regs(regs); + bust_spinlocks(0); + add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE); + spin_unlock_irq(&die_lock); + if (in_interrupt()) + panic("Fatal exception in interrupt"); + if (panic_on_oops) + panic("Fatal exception: panic_on_oops"); + oops_exit(); + do_exit(SIGSEGV); +} diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 94feff7d613..4d5e6f8a797 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -45,6 +45,7 @@ _TIF_TRACE = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \ STACK_SHIFT = PAGE_SHIFT + THREAD_ORDER STACK_SIZE = 1 << STACK_SHIFT +STACK_INIT = STACK_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE #define BASED(name) name-system_call(%r13) @@ -97,10 +98,10 @@ STACK_SIZE = 1 << STACK_SHIFT sra %r14,\shift jnz 1f CHECK_STACK 1<<\shift,\savearea + ahi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) j 2f 1: l %r15,\stack # load target stack -2: ahi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) - la %r11,STACK_FRAME_OVERHEAD(%r15) +2: la %r11,STACK_FRAME_OVERHEAD(%r15) .endm .macro ADD64 high,low,timer @@ -150,7 +151,7 @@ ENTRY(__switch_to) l %r4,__THREAD_info(%r2) # get thread_info of prev l %r5,__THREAD_info(%r3) # get thread_info of next lr %r15,%r5 - ahi %r15,STACK_SIZE # end of kernel stack of next + ahi %r15,STACK_INIT # end of kernel stack of next st %r3,__LC_CURRENT # store task struct of next st %r5,__LC_THREAD_INFO # store thread info of next st %r15,__LC_KERNEL_STACK # store end of kernel stack @@ -178,7 +179,6 @@ sysc_stm: l %r13,__LC_SVC_NEW_PSW+4 sysc_per: l %r15,__LC_KERNEL_STACK - ahi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) la %r11,STACK_FRAME_OVERHEAD(%r15) # pointer to pt_regs sysc_vtime: UPDATE_VTIME %r8,%r9,__LC_SYNC_ENTER_TIMER @@ -188,6 +188,7 @@ sysc_vtime: mvc __PT_INT_CODE(4,%r11),__LC_SVC_ILC sysc_do_svc: oi __TI_flags+3(%r12),_TIF_SYSCALL + l %r10,__TI_sysc_table(%r12) # 31 bit system call table lh %r8,__PT_INT_CODE+2(%r11) sla %r8,2 # shift and test for svc0 jnz sysc_nr_ok @@ -198,7 +199,6 @@ sysc_do_svc: lr %r8,%r1 sla %r8,2 sysc_nr_ok: - l %r10,BASED(.Lsys_call_table) # 31 bit system call table xc __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) st %r2,__PT_ORIG_GPR2(%r11) st %r7,STACK_FRAME_OVERHEAD(%r15) @@ -359,11 +359,11 @@ ENTRY(pgm_check_handler) tm __LC_PGM_ILC+3,0x80 # check for per exception jnz pgm_svcper # -> single stepped svc 0: CHECK_STACK STACK_SIZE,__LC_SAVE_AREA_SYNC + ahi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) j 2f 1: UPDATE_VTIME %r14,%r15,__LC_SYNC_ENTER_TIMER l %r15,__LC_KERNEL_STACK -2: ahi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) - la %r11,STACK_FRAME_OVERHEAD(%r15) +2: la %r11,STACK_FRAME_OVERHEAD(%r15) stm %r0,%r7,__PT_R0(%r11) mvc __PT_R8(32,%r11),__LC_SAVE_AREA_SYNC stm %r8,%r9,__PT_PSW(%r11) @@ -485,7 +485,6 @@ io_work: # io_work_user: l %r1,__LC_KERNEL_STACK - ahi %r1,-(STACK_FRAME_OVERHEAD + __PT_SIZE) mvc STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11) xc __SF_BACKCHAIN(4,%r1),__SF_BACKCHAIN(%r1) la %r11,STACK_FRAME_OVERHEAD(%r1) @@ -646,7 +645,6 @@ mcck_skip: tm __PT_PSW+1(%r11),0x01 # returning to user ? jno mcck_return l %r1,__LC_KERNEL_STACK # switch to kernel stack - ahi %r1,-(STACK_FRAME_OVERHEAD + __PT_SIZE) mvc STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11) xc __SF_BACKCHAIN(4,%r1),__SF_BACKCHAIN(%r1) la %r11,STACK_FRAME_OVERHEAD(%r15) @@ -674,6 +672,7 @@ mcck_panic: sra %r14,PAGE_SHIFT jz 0f l %r15,__LC_PANIC_STACK + j mcck_skip 0: ahi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) j mcck_skip @@ -714,12 +713,10 @@ ENTRY(restart_int_handler) */ stack_overflow: l %r15,__LC_PANIC_STACK # change to panic stack - ahi %r15,-__PT_SIZE # create pt_regs - stm %r0,%r7,__PT_R0(%r15) - stm %r8,%r9,__PT_PSW(%r15) + la %r11,STACK_FRAME_OVERHEAD(%r15) + stm %r0,%r7,__PT_R0(%r11) + stm %r8,%r9,__PT_PSW(%r11) mvc __PT_R8(32,%r11),0(%r14) - lr %r15,%r11 - ahi %r15,-STACK_FRAME_OVERHEAD l %r1,BASED(1f) xc __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) lr %r2,%r11 # pass pointer to pt_regs @@ -799,15 +796,14 @@ cleanup_system_call: mvc __LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER # set up saved register 11 l %r15,__LC_KERNEL_STACK - ahi %r15,-__PT_SIZE - st %r15,12(%r11) # r11 pt_regs pointer + la %r9,STACK_FRAME_OVERHEAD(%r15) + st %r9,12(%r11) # r11 pt_regs pointer # fill pt_regs - mvc __PT_R8(32,%r15),__LC_SAVE_AREA_SYNC - stm %r0,%r7,__PT_R0(%r15) - mvc __PT_PSW(8,%r15),__LC_SVC_OLD_PSW - mvc __PT_INT_CODE(4,%r15),__LC_SVC_ILC + mvc __PT_R8(32,%r9),__LC_SAVE_AREA_SYNC + stm %r0,%r7,__PT_R0(%r9) + mvc __PT_PSW(8,%r9),__LC_SVC_OLD_PSW + mvc __PT_INT_CODE(4,%r9),__LC_SVC_ILC # setup saved register 15 - ahi %r15,-STACK_FRAME_OVERHEAD st %r15,28(%r11) # r15 stack pointer # set new psw address and exit l %r9,BASED(cleanup_table+4) # sysc_do_svc + 0x80000000 @@ -910,7 +906,6 @@ cleanup_idle_wait: .Ltrace_enter: .long do_syscall_trace_enter .Ltrace_exit: .long do_syscall_trace_exit .Lschedule_tail: .long schedule_tail -.Lsys_call_table: .long sys_call_table .Lsysc_per: .long sysc_per + 0x80000000 #ifdef CONFIG_TRACE_IRQFLAGS .Lhardirqs_on: .long trace_hardirqs_on_caller diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index c3a736a3ed4..aa0ab02e959 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -7,6 +7,7 @@ #include <asm/cputime.h> extern void *restart_stack; +extern unsigned long suspend_zero_pages; void system_call(void); void pgm_check_handler(void); diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S index 2e6d60c55f9..4c17eece707 100644 --- a/arch/s390/kernel/entry64.S +++ b/arch/s390/kernel/entry64.S @@ -39,6 +39,7 @@ __PT_R15 = __PT_GPRS + 120 STACK_SHIFT = PAGE_SHIFT + THREAD_ORDER STACK_SIZE = 1 << STACK_SHIFT +STACK_INIT = STACK_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE _TIF_WORK_SVC = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ _TIF_MCCK_PENDING | _TIF_PER_TRAP ) @@ -124,10 +125,10 @@ _TIF_EXIT_SIE = (_TIF_SIGPENDING | _TIF_NEED_RESCHED | _TIF_MCCK_PENDING) srag %r14,%r14,\shift jnz 1f CHECK_STACK 1<<\shift,\savearea + aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) j 2f 1: lg %r15,\stack # load target stack -2: aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) - la %r11,STACK_FRAME_OVERHEAD(%r15) +2: la %r11,STACK_FRAME_OVERHEAD(%r15) .endm .macro UPDATE_VTIME scratch,enter_timer @@ -177,7 +178,7 @@ ENTRY(__switch_to) lg %r4,__THREAD_info(%r2) # get thread_info of prev lg %r5,__THREAD_info(%r3) # get thread_info of next lgr %r15,%r5 - aghi %r15,STACK_SIZE # end of kernel stack of next + aghi %r15,STACK_INIT # end of kernel stack of next stg %r3,__LC_CURRENT # store task struct of next stg %r5,__LC_THREAD_INFO # store thread info of next stg %r15,__LC_KERNEL_STACK # store end of kernel stack @@ -203,10 +204,8 @@ sysc_stmg: stmg %r8,%r15,__LC_SAVE_AREA_SYNC lg %r10,__LC_LAST_BREAK lg %r12,__LC_THREAD_INFO - larl %r13,system_call sysc_per: lg %r15,__LC_KERNEL_STACK - aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) la %r11,STACK_FRAME_OVERHEAD(%r15) # pointer to pt_regs sysc_vtime: UPDATE_VTIME %r13,__LC_SYNC_ENTER_TIMER @@ -217,6 +216,7 @@ sysc_vtime: mvc __PT_INT_CODE(4,%r11),__LC_SVC_ILC sysc_do_svc: oi __TI_flags+7(%r12),_TIF_SYSCALL + lg %r10,__TI_sysc_table(%r12) # address of system call table llgh %r8,__PT_INT_CODE+2(%r11) slag %r8,%r8,2 # shift and test for svc 0 jnz sysc_nr_ok @@ -227,13 +227,6 @@ sysc_do_svc: sth %r1,__PT_INT_CODE+2(%r11) slag %r8,%r1,2 sysc_nr_ok: - larl %r10,sys_call_table # 64 bit system call table -#ifdef CONFIG_COMPAT - tm __TI_flags+5(%r12),(_TIF_31BIT>>16) - jno sysc_noemu - larl %r10,sys_call_table_emu # 31 bit system call table -sysc_noemu: -#endif xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) stg %r2,__PT_ORIG_GPR2(%r11) stg %r7,STACK_FRAME_OVERHEAD(%r15) @@ -389,6 +382,7 @@ ENTRY(pgm_check_handler) tm __LC_PGM_ILC+3,0x80 # check for per exception jnz pgm_svcper # -> single stepped svc 0: CHECK_STACK STACK_SIZE,__LC_SAVE_AREA_SYNC + aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) j 2f 1: UPDATE_VTIME %r14,__LC_SYNC_ENTER_TIMER LAST_BREAK %r14 @@ -398,8 +392,7 @@ ENTRY(pgm_check_handler) tm __LC_PGM_ILC+2,0x02 # check for transaction abort jz 2f mvc __THREAD_trap_tdb(256,%r14),0(%r13) -2: aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) - la %r11,STACK_FRAME_OVERHEAD(%r15) +2: la %r11,STACK_FRAME_OVERHEAD(%r15) stmg %r0,%r7,__PT_R0(%r11) mvc __PT_R8(64,%r11),__LC_SAVE_AREA_SYNC stmg %r8,%r9,__PT_PSW(%r11) @@ -526,7 +519,6 @@ io_work: # io_work_user: lg %r1,__LC_KERNEL_STACK - aghi %r1,-(STACK_FRAME_OVERHEAD + __PT_SIZE) mvc STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11) xc __SF_BACKCHAIN(8,%r1),__SF_BACKCHAIN(%r1) la %r11,STACK_FRAME_OVERHEAD(%r1) @@ -688,7 +680,6 @@ mcck_skip: tm __PT_PSW+1(%r11),0x01 # returning to user ? jno mcck_return lg %r1,__LC_KERNEL_STACK # switch to kernel stack - aghi %r1,-(STACK_FRAME_OVERHEAD + __PT_SIZE) mvc STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11) xc __SF_BACKCHAIN(8,%r1),__SF_BACKCHAIN(%r1) la %r11,STACK_FRAME_OVERHEAD(%r1) @@ -755,14 +746,12 @@ ENTRY(restart_int_handler) * Setup a pt_regs so that show_trace can provide a good call trace. */ stack_overflow: - lg %r11,__LC_PANIC_STACK # change to panic stack - aghi %r11,-__PT_SIZE # create pt_regs + lg %r15,__LC_PANIC_STACK # change to panic stack + la %r11,STACK_FRAME_OVERHEAD(%r15) stmg %r0,%r7,__PT_R0(%r11) stmg %r8,%r9,__PT_PSW(%r11) mvc __PT_R8(64,%r11),0(%r14) stg %r10,__PT_ORIG_GPR2(%r11) # store last break to orig_gpr2 - lgr %r15,%r11 - aghi %r15,-STACK_FRAME_OVERHEAD xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) lgr %r2,%r11 # pass pointer to pt_regs jg kernel_stack_overflow @@ -846,15 +835,14 @@ cleanup_system_call: mvc __TI_last_break(8,%r12),16(%r11) 0: # set up saved register r11 lg %r15,__LC_KERNEL_STACK - aghi %r15,-__PT_SIZE - stg %r15,24(%r11) # r11 pt_regs pointer + la %r9,STACK_FRAME_OVERHEAD(%r15) + stg %r9,24(%r11) # r11 pt_regs pointer # fill pt_regs - mvc __PT_R8(64,%r15),__LC_SAVE_AREA_SYNC - stmg %r0,%r7,__PT_R0(%r15) - mvc __PT_PSW(16,%r15),__LC_SVC_OLD_PSW - mvc __PT_INT_CODE(4,%r15),__LC_SVC_ILC + mvc __PT_R8(64,%r9),__LC_SAVE_AREA_SYNC + stmg %r0,%r7,__PT_R0(%r9) + mvc __PT_PSW(16,%r9),__LC_SVC_OLD_PSW + mvc __PT_INT_CODE(4,%r9),__LC_SVC_ILC # setup saved register r15 - aghi %r15,-STACK_FRAME_OVERHEAD stg %r15,56(%r11) # r15 stack pointer # set new psw address and exit larl %r9,sysc_do_svc @@ -1011,6 +999,7 @@ sys_call_table: #ifdef CONFIG_COMPAT #define SYSCALL(esa,esame,emu) .long emu + .globl sys_call_table_emu sys_call_table_emu: #include "syscalls.S" #undef SYSCALL diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index b3de2770001..ac2178161ec 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -13,6 +13,7 @@ #include <linux/reboot.h> #include <linux/ftrace.h> #include <linux/debug_locks.h> +#include <linux/suspend.h> #include <asm/cio.h> #include <asm/setup.h> #include <asm/pgtable.h> @@ -67,6 +68,35 @@ void setup_regs(void) memcpy((void *) SAVE_AREA_BASE, (void *) sa, sizeof(struct save_area)); } +/* + * PM notifier callback for kdump + */ +static int machine_kdump_pm_cb(struct notifier_block *nb, unsigned long action, + void *ptr) +{ + switch (action) { + case PM_SUSPEND_PREPARE: + case PM_HIBERNATION_PREPARE: + if (crashk_res.start) + crash_map_reserved_pages(); + break; + case PM_POST_SUSPEND: + case PM_POST_HIBERNATION: + if (crashk_res.start) + crash_unmap_reserved_pages(); + break; + default: + return NOTIFY_DONE; + } + return NOTIFY_OK; +} + +static int __init machine_kdump_pm_init(void) +{ + pm_notifier(machine_kdump_pm_cb, 0); + return 0; +} +arch_initcall(machine_kdump_pm_init); #endif /* diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 29268859d8e..0f419c5765c 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -377,11 +377,14 @@ static void __init setup_lowcore(void) PSW_MASK_DAT | PSW_MASK_MCHECK; lc->io_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) io_int_handler; lc->clock_comparator = -1ULL; - lc->kernel_stack = ((unsigned long) &init_thread_union) + THREAD_SIZE; + lc->kernel_stack = ((unsigned long) &init_thread_union) + + THREAD_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs); lc->async_stack = (unsigned long) - __alloc_bootmem(ASYNC_SIZE, ASYNC_SIZE, 0) + ASYNC_SIZE; + __alloc_bootmem(ASYNC_SIZE, ASYNC_SIZE, 0) + + ASYNC_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs); lc->panic_stack = (unsigned long) - __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, 0) + PAGE_SIZE; + __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, 0) + + PAGE_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs); lc->current_task = (unsigned long) init_thread_union.thread_info.task; lc->thread_info = (unsigned long) &init_thread_union; lc->machine_flags = S390_lowcore.machine_flags; diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 549c9d173c0..8bde89eafd8 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -181,8 +181,10 @@ static int __cpuinit pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu) lc = pcpu->lowcore; memcpy(lc, &S390_lowcore, 512); memset((char *) lc + 512, 0, sizeof(*lc) - 512); - lc->async_stack = pcpu->async_stack + ASYNC_SIZE; - lc->panic_stack = pcpu->panic_stack + PAGE_SIZE; + lc->async_stack = pcpu->async_stack + ASYNC_SIZE + - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs); + lc->panic_stack = pcpu->panic_stack + PAGE_SIZE + - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs); lc->cpu_nr = cpu; #ifndef CONFIG_64BIT if (MACHINE_HAS_IEEE) { @@ -253,7 +255,8 @@ static void pcpu_attach_task(struct pcpu *pcpu, struct task_struct *tsk) struct _lowcore *lc = pcpu->lowcore; struct thread_info *ti = task_thread_info(tsk); - lc->kernel_stack = (unsigned long) task_stack_page(tsk) + THREAD_SIZE; + lc->kernel_stack = (unsigned long) task_stack_page(tsk) + + THREAD_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs); lc->thread_info = (unsigned long) task_thread_info(tsk); lc->current_task = (unsigned long) tsk; lc->user_timer = ti->user_timer; @@ -810,8 +813,10 @@ void __init smp_prepare_boot_cpu(void) pcpu->state = CPU_STATE_CONFIGURED; pcpu->address = boot_cpu_address; pcpu->lowcore = (struct _lowcore *)(unsigned long) store_prefix(); - pcpu->async_stack = S390_lowcore.async_stack - ASYNC_SIZE; - pcpu->panic_stack = S390_lowcore.panic_stack - PAGE_SIZE; + pcpu->async_stack = S390_lowcore.async_stack - ASYNC_SIZE + + STACK_FRAME_OVERHEAD + sizeof(struct pt_regs); + pcpu->panic_stack = S390_lowcore.panic_stack - PAGE_SIZE + + STACK_FRAME_OVERHEAD + sizeof(struct pt_regs); S390_lowcore.percpu_offset = __per_cpu_offset[0]; smp_cpu_set_polarization(0, POLARIZATION_UNKNOWN); set_cpu_present(0, true); diff --git a/arch/s390/kernel/suspend.c b/arch/s390/kernel/suspend.c index aa1494d0e38..c479d2f9605 100644 --- a/arch/s390/kernel/suspend.c +++ b/arch/s390/kernel/suspend.c @@ -41,6 +41,7 @@ struct page_key_data { static struct page_key_data *page_key_data; static struct page_key_data *page_key_rp, *page_key_wp; static unsigned long page_key_rx, page_key_wx; +unsigned long suspend_zero_pages; /* * For each page in the hibernation image one additional byte is @@ -149,6 +150,36 @@ int pfn_is_nosave(unsigned long pfn) return 0; } +/* + * PM notifier callback for suspend + */ +static int suspend_pm_cb(struct notifier_block *nb, unsigned long action, + void *ptr) +{ + switch (action) { + case PM_SUSPEND_PREPARE: + case PM_HIBERNATION_PREPARE: + suspend_zero_pages = __get_free_pages(GFP_KERNEL, LC_ORDER); + if (!suspend_zero_pages) + return NOTIFY_BAD; + break; + case PM_POST_SUSPEND: + case PM_POST_HIBERNATION: + free_pages(suspend_zero_pages, LC_ORDER); + break; + default: + return NOTIFY_DONE; + } + return NOTIFY_OK; +} + +static int __init suspend_pm_init(void) +{ + pm_notifier(suspend_pm_cb, 0); + return 0; +} +arch_initcall(suspend_pm_init); + void save_processor_state(void) { /* swsusp_arch_suspend() actually saves all cpu register contents. diff --git a/arch/s390/kernel/swsusp_asm64.S b/arch/s390/kernel/swsusp_asm64.S index d4ca4e0617b..c487be4cfc8 100644 --- a/arch/s390/kernel/swsusp_asm64.S +++ b/arch/s390/kernel/swsusp_asm64.S @@ -36,8 +36,8 @@ ENTRY(swsusp_arch_suspend) /* Store prefix register on stack */ stpx __SF_EMPTY(%r15) - /* Save prefix register contents for lowcore */ - llgf %r4,__SF_EMPTY(%r15) + /* Save prefix register contents for lowcore copy */ + llgf %r10,__SF_EMPTY(%r15) /* Get pointer to save area */ lghi %r1,0x1000 @@ -91,7 +91,18 @@ ENTRY(swsusp_arch_suspend) xc __SF_EMPTY(4,%r15),__SF_EMPTY(%r15) spx __SF_EMPTY(%r15) + /* Save absolute zero pages */ + larl %r2,suspend_zero_pages + lg %r2,0(%r2) + lghi %r4,0 + lghi %r3,2*PAGE_SIZE + lghi %r5,2*PAGE_SIZE +1: mvcle %r2,%r4,0 + jo 1b + + /* Copy lowcore to absolute zero lowcore */ lghi %r2,0 + lgr %r4,%r10 lghi %r3,2*PAGE_SIZE lghi %r5,2*PAGE_SIZE 1: mvcle %r2,%r4,0 @@ -248,8 +259,20 @@ restore_registers: /* Load old stack */ lg %r15,0x2f8(%r13) + /* Save prefix register */ + mvc __SF_EMPTY(4,%r15),0x318(%r13) + + /* Restore absolute zero pages */ + lghi %r2,0 + larl %r4,suspend_zero_pages + lg %r4,0(%r4) + lghi %r3,2*PAGE_SIZE + lghi %r5,2*PAGE_SIZE +1: mvcle %r2,%r4,0 + jo 1b + /* Restore prefix register */ - spx 0x318(%r13) + spx __SF_EMPTY(%r15) /* Activate DAT */ stosm __SF_EMPTY(%r15),0x04 diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c index 13dd63fba36..c5762324d9e 100644 --- a/arch/s390/kernel/traps.c +++ b/arch/s390/kernel/traps.c @@ -12,49 +12,16 @@ * 'Traps.c' handles hardware traps and faults after we have saved some * state in 'asm.s'. */ -#include <linux/sched.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/errno.h> +#include <linux/kprobes.h> +#include <linux/kdebug.h> +#include <linux/module.h> #include <linux/ptrace.h> -#include <linux/timer.h> +#include <linux/sched.h> #include <linux/mm.h> -#include <linux/smp.h> -#include <linux/init.h> -#include <linux/interrupt.h> -#include <linux/seq_file.h> -#include <linux/delay.h> -#include <linux/module.h> -#include <linux/kdebug.h> -#include <linux/kallsyms.h> -#include <linux/reboot.h> -#include <linux/kprobes.h> -#include <linux/bug.h> -#include <linux/utsname.h> -#include <asm/uaccess.h> -#include <asm/io.h> -#include <linux/atomic.h> -#include <asm/mathemu.h> -#include <asm/cpcmd.h> -#include <asm/lowcore.h> -#include <asm/debug.h> -#include <asm/ipl.h> #include "entry.h" int show_unhandled_signals = 1; -#define stack_pointer ({ void **sp; asm("la %0,0(15)" : "=&d" (sp)); sp; }) - -#ifndef CONFIG_64BIT -#define LONG "%08lx " -#define FOURLONG "%08lx %08lx %08lx %08lx\n" -static int kstack_depth_to_print = 12; -#else /* CONFIG_64BIT */ -#define LONG "%016lx " -#define FOURLONG "%016lx %016lx %016lx %016lx\n" -static int kstack_depth_to_print = 20; -#endif /* CONFIG_64BIT */ - static inline void __user *get_trap_ip(struct pt_regs *regs) { #ifdef CONFIG_64BIT @@ -72,215 +39,6 @@ static inline void __user *get_trap_ip(struct pt_regs *regs) #endif } -/* - * For show_trace we have tree different stack to consider: - * - the panic stack which is used if the kernel stack has overflown - * - the asynchronous interrupt stack (cpu related) - * - the synchronous kernel stack (process related) - * The stack trace can start at any of the three stack and can potentially - * touch all of them. The order is: panic stack, async stack, sync stack. - */ -static unsigned long -__show_trace(unsigned long sp, unsigned long low, unsigned long high) -{ - struct stack_frame *sf; - struct pt_regs *regs; - - while (1) { - sp = sp & PSW_ADDR_INSN; - if (sp < low || sp > high - sizeof(*sf)) - return sp; - sf = (struct stack_frame *) sp; - printk("([<%016lx>] ", sf->gprs[8] & PSW_ADDR_INSN); - print_symbol("%s)\n", sf->gprs[8] & PSW_ADDR_INSN); - /* Follow the backchain. */ - while (1) { - low = sp; - sp = sf->back_chain & PSW_ADDR_INSN; - if (!sp) - break; - if (sp <= low || sp > high - sizeof(*sf)) - return sp; - sf = (struct stack_frame *) sp; - printk(" [<%016lx>] ", sf->gprs[8] & PSW_ADDR_INSN); - print_symbol("%s\n", sf->gprs[8] & PSW_ADDR_INSN); - } - /* Zero backchain detected, check for interrupt frame. */ - sp = (unsigned long) (sf + 1); - if (sp <= low || sp > high - sizeof(*regs)) - return sp; - regs = (struct pt_regs *) sp; - printk(" [<%016lx>] ", regs->psw.addr & PSW_ADDR_INSN); - print_symbol("%s\n", regs->psw.addr & PSW_ADDR_INSN); - low = sp; - sp = regs->gprs[15]; - } -} - -static void show_trace(struct task_struct *task, unsigned long *stack) -{ - register unsigned long __r15 asm ("15"); - unsigned long sp; - - sp = (unsigned long) stack; - if (!sp) - sp = task ? task->thread.ksp : __r15; - printk("Call Trace:\n"); -#ifdef CONFIG_CHECK_STACK - sp = __show_trace(sp, S390_lowcore.panic_stack - 4096, - S390_lowcore.panic_stack); -#endif - sp = __show_trace(sp, S390_lowcore.async_stack - ASYNC_SIZE, - S390_lowcore.async_stack); - if (task) - __show_trace(sp, (unsigned long) task_stack_page(task), - (unsigned long) task_stack_page(task) + THREAD_SIZE); - else - __show_trace(sp, S390_lowcore.thread_info, - S390_lowcore.thread_info + THREAD_SIZE); - if (!task) - task = current; - debug_show_held_locks(task); -} - -void show_stack(struct task_struct *task, unsigned long *sp) -{ - register unsigned long * __r15 asm ("15"); - unsigned long *stack; - int i; - - if (!sp) - stack = task ? (unsigned long *) task->thread.ksp : __r15; - else - stack = sp; - - for (i = 0; i < kstack_depth_to_print; i++) { - if (((addr_t) stack & (THREAD_SIZE-1)) == 0) - break; - if ((i * sizeof(long) % 32) == 0) - printk("%s ", i == 0 ? "" : "\n"); - printk(LONG, *stack++); - } - printk("\n"); - show_trace(task, sp); -} - -static void show_last_breaking_event(struct pt_regs *regs) -{ -#ifdef CONFIG_64BIT - printk("Last Breaking-Event-Address:\n"); - printk(" [<%016lx>] ", regs->args[0] & PSW_ADDR_INSN); - print_symbol("%s\n", regs->args[0] & PSW_ADDR_INSN); -#endif -} - -/* - * The architecture-independent dump_stack generator - */ -void dump_stack(void) -{ - printk("CPU: %d %s %s %.*s\n", - task_thread_info(current)->cpu, print_tainted(), - init_utsname()->release, - (int)strcspn(init_utsname()->version, " "), - init_utsname()->version); - printk("Process %s (pid: %d, task: %p, ksp: %p)\n", - current->comm, current->pid, current, - (void *) current->thread.ksp); - show_stack(NULL, NULL); -} -EXPORT_SYMBOL(dump_stack); - -static inline int mask_bits(struct pt_regs *regs, unsigned long bits) -{ - return (regs->psw.mask & bits) / ((~bits + 1) & bits); -} - -void show_registers(struct pt_regs *regs) -{ - char *mode; - - mode = user_mode(regs) ? "User" : "Krnl"; - printk("%s PSW : %p %p", - mode, (void *) regs->psw.mask, - (void *) regs->psw.addr); - print_symbol(" (%s)\n", regs->psw.addr & PSW_ADDR_INSN); - printk(" R:%x T:%x IO:%x EX:%x Key:%x M:%x W:%x " - "P:%x AS:%x CC:%x PM:%x", mask_bits(regs, PSW_MASK_PER), - mask_bits(regs, PSW_MASK_DAT), mask_bits(regs, PSW_MASK_IO), - mask_bits(regs, PSW_MASK_EXT), mask_bits(regs, PSW_MASK_KEY), - mask_bits(regs, PSW_MASK_MCHECK), mask_bits(regs, PSW_MASK_WAIT), - mask_bits(regs, PSW_MASK_PSTATE), mask_bits(regs, PSW_MASK_ASC), - mask_bits(regs, PSW_MASK_CC), mask_bits(regs, PSW_MASK_PM)); -#ifdef CONFIG_64BIT - printk(" EA:%x", mask_bits(regs, PSW_MASK_EA | PSW_MASK_BA)); -#endif - printk("\n%s GPRS: " FOURLONG, mode, - regs->gprs[0], regs->gprs[1], regs->gprs[2], regs->gprs[3]); - printk(" " FOURLONG, - regs->gprs[4], regs->gprs[5], regs->gprs[6], regs->gprs[7]); - printk(" " FOURLONG, - regs->gprs[8], regs->gprs[9], regs->gprs[10], regs->gprs[11]); - printk(" " FOURLONG, - regs->gprs[12], regs->gprs[13], regs->gprs[14], regs->gprs[15]); - - show_code(regs); -} - -void show_regs(struct pt_regs *regs) -{ - printk("CPU: %d %s %s %.*s\n", - task_thread_info(current)->cpu, print_tainted(), - init_utsname()->release, - (int)strcspn(init_utsname()->version, " "), - init_utsname()->version); - printk("Process %s (pid: %d, task: %p, ksp: %p)\n", - current->comm, current->pid, current, - (void *) current->thread.ksp); - show_registers(regs); - /* Show stack backtrace if pt_regs is from kernel mode */ - if (!user_mode(regs)) - show_trace(NULL, (unsigned long *) regs->gprs[15]); - show_last_breaking_event(regs); -} - -static DEFINE_SPINLOCK(die_lock); - -void die(struct pt_regs *regs, const char *str) -{ - static int die_counter; - - oops_enter(); - lgr_info_log(); - debug_stop_all(); - console_verbose(); - spin_lock_irq(&die_lock); - bust_spinlocks(1); - printk("%s: %04x [#%d] ", str, regs->int_code & 0xffff, ++die_counter); -#ifdef CONFIG_PREEMPT - printk("PREEMPT "); -#endif -#ifdef CONFIG_SMP - printk("SMP "); -#endif -#ifdef CONFIG_DEBUG_PAGEALLOC - printk("DEBUG_PAGEALLOC"); -#endif - printk("\n"); - notify_die(DIE_OOPS, str, regs, 0, regs->int_code & 0xffff, SIGSEGV); - print_modules(); - show_regs(regs); - bust_spinlocks(0); - add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE); - spin_unlock_irq(&die_lock); - if (in_interrupt()) - panic("Fatal exception in interrupt"); - if (panic_on_oops) - panic("Fatal exception: panic_on_oops"); - oops_exit(); - do_exit(SIGSEGV); -} - static inline void report_user_fault(struct pt_regs *regs, int signr) { if ((task_pid_nr(current) > 1) && !show_unhandled_signals) diff --git a/arch/s390/kvm/trace.h b/arch/s390/kvm/trace.h index 2b29e62351d..53252d2d472 100644 --- a/arch/s390/kvm/trace.h +++ b/arch/s390/kvm/trace.h @@ -117,7 +117,7 @@ TRACE_EVENT(kvm_s390_intercept_instruction, __entry->instruction, insn_to_mnemonic((unsigned char *) &__entry->instruction, - __entry->insn) ? + __entry->insn, sizeof(__entry->insn)) ? "unknown" : __entry->insn) ); diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c index 479e9428291..9d84a1feefe 100644 --- a/arch/s390/mm/cmm.c +++ b/arch/s390/mm/cmm.c @@ -458,12 +458,10 @@ static int __init cmm_init(void) if (rc) goto out_pm; cmm_thread_ptr = kthread_run(cmm_thread, NULL, "cmmthread"); - rc = IS_ERR(cmm_thread_ptr) ? PTR_ERR(cmm_thread_ptr) : 0; - if (rc) - goto out_kthread; - return 0; + if (!IS_ERR(cmm_thread_ptr)) + return 0; -out_kthread: + rc = PTR_ERR(cmm_thread_ptr); unregister_pm_notifier(&cmm_power_notifier); out_pm: unregister_oom_notifier(&cmm_oom_nb); diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 2fb9e63b8fc..047c3e4c59a 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -395,8 +395,13 @@ void __kprobes do_protection_exception(struct pt_regs *regs) int fault; trans_exc_code = regs->int_parm_long; - /* Protection exception is suppressing, decrement psw address. */ - regs->psw.addr = __rewind_psw(regs->psw, regs->int_code >> 16); + /* + * Protection exceptions are suppressing, decrement psw address. + * The exception to this rule are aborted transactions, for these + * the PSW already points to the correct location. + */ + if (!(regs->int_code & 0x200)) + regs->psw.addr = __rewind_psw(regs->psw, regs->int_code >> 16); /* * Check for low-address protection. This needs to be treated * as a special case because the translation exception code diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 49ce6bb2c64..9f9c315b4c0 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -63,10 +63,18 @@ static unsigned long __init setup_zero_pages(void) break; case 0x2097: /* z10 */ case 0x2098: /* z10 */ - default: + case 0x2817: /* z196 */ + case 0x2818: /* z196 */ order = 2; break; + case 0x2827: /* zEC12 */ + default: + order = 5; + break; } + /* Limit number of empty zero pages for small memory sizes */ + if (order > 2 && totalram_pages <= 16384) + order = 2; empty_zero_page = __get_free_pages(GFP_KERNEL | __GFP_ZERO, order); if (!empty_zero_page) diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c index d21040ed5e5..80adfbf7506 100644 --- a/arch/s390/mm/pageattr.c +++ b/arch/s390/mm/pageattr.c @@ -9,31 +9,25 @@ #include <asm/pgtable.h> #include <asm/page.h> +static inline unsigned long sske_frame(unsigned long addr, unsigned char skey) +{ + asm volatile(".insn rrf,0xb22b0000,%[skey],%[addr],9,0" + : [addr] "+a" (addr) : [skey] "d" (skey)); + return addr; +} + void storage_key_init_range(unsigned long start, unsigned long end) { - unsigned long boundary, function, size; + unsigned long boundary, size; while (start < end) { - if (MACHINE_HAS_EDAT2) { - /* set storage keys for a 2GB frame */ - function = 0x22000 | PAGE_DEFAULT_KEY; - size = 1UL << 31; - boundary = (start + size) & ~(size - 1); - if (boundary <= end) { - do { - start = pfmf(function, start); - } while (start < boundary); - continue; - } - } if (MACHINE_HAS_EDAT1) { /* set storage keys for a 1MB frame */ - function = 0x21000 | PAGE_DEFAULT_KEY; size = 1UL << 20; boundary = (start + size) & ~(size - 1); if (boundary <= end) { do { - start = pfmf(function, start); + start = sske_frame(start, PAGE_DEFAULT_KEY); } while (start < boundary); continue; } diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index ae44d2a3431..bd954e96f51 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -379,75 +379,183 @@ out_unmap: } EXPORT_SYMBOL_GPL(gmap_map_segment); -/* - * this function is assumed to be called with mmap_sem held - */ -unsigned long __gmap_fault(unsigned long address, struct gmap *gmap) +static unsigned long *gmap_table_walk(unsigned long address, struct gmap *gmap) { - unsigned long *table, vmaddr, segment; - struct mm_struct *mm; - struct gmap_pgtable *mp; - struct gmap_rmap *rmap; - struct vm_area_struct *vma; - struct page *page; - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; + unsigned long *table; - current->thread.gmap_addr = address; - mm = gmap->mm; - /* Walk the gmap address space page table */ table = gmap->table + ((address >> 53) & 0x7ff); if (unlikely(*table & _REGION_ENTRY_INV)) - return -EFAULT; + return ERR_PTR(-EFAULT); table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); table = table + ((address >> 42) & 0x7ff); if (unlikely(*table & _REGION_ENTRY_INV)) - return -EFAULT; + return ERR_PTR(-EFAULT); table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); table = table + ((address >> 31) & 0x7ff); if (unlikely(*table & _REGION_ENTRY_INV)) - return -EFAULT; + return ERR_PTR(-EFAULT); table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); table = table + ((address >> 20) & 0x7ff); + return table; +} + +/** + * __gmap_translate - translate a guest address to a user space address + * @address: guest address + * @gmap: pointer to guest mapping meta data structure + * + * Returns user space address which corresponds to the guest address or + * -EFAULT if no such mapping exists. + * This function does not establish potentially missing page table entries. + * The mmap_sem of the mm that belongs to the address space must be held + * when this function gets called. + */ +unsigned long __gmap_translate(unsigned long address, struct gmap *gmap) +{ + unsigned long *segment_ptr, vmaddr, segment; + struct gmap_pgtable *mp; + struct page *page; + current->thread.gmap_addr = address; + segment_ptr = gmap_table_walk(address, gmap); + if (IS_ERR(segment_ptr)) + return PTR_ERR(segment_ptr); /* Convert the gmap address to an mm address. */ - segment = *table; - if (likely(!(segment & _SEGMENT_ENTRY_INV))) { + segment = *segment_ptr; + if (!(segment & _SEGMENT_ENTRY_INV)) { page = pfn_to_page(segment >> PAGE_SHIFT); mp = (struct gmap_pgtable *) page->index; return mp->vmaddr | (address & ~PMD_MASK); } else if (segment & _SEGMENT_ENTRY_RO) { vmaddr = segment & _SEGMENT_ENTRY_ORIGIN; - vma = find_vma(mm, vmaddr); - if (!vma || vma->vm_start > vmaddr) - return -EFAULT; - - /* Walk the parent mm page table */ - pgd = pgd_offset(mm, vmaddr); - pud = pud_alloc(mm, pgd, vmaddr); - if (!pud) - return -ENOMEM; - pmd = pmd_alloc(mm, pud, vmaddr); - if (!pmd) - return -ENOMEM; - if (!pmd_present(*pmd) && - __pte_alloc(mm, vma, pmd, vmaddr)) - return -ENOMEM; - /* pmd now points to a valid segment table entry. */ - rmap = kmalloc(sizeof(*rmap), GFP_KERNEL|__GFP_REPEAT); - if (!rmap) - return -ENOMEM; - /* Link gmap segment table entry location to page table. */ - page = pmd_page(*pmd); - mp = (struct gmap_pgtable *) page->index; - rmap->entry = table; - spin_lock(&mm->page_table_lock); + return vmaddr | (address & ~PMD_MASK); + } + return -EFAULT; +} +EXPORT_SYMBOL_GPL(__gmap_translate); + +/** + * gmap_translate - translate a guest address to a user space address + * @address: guest address + * @gmap: pointer to guest mapping meta data structure + * + * Returns user space address which corresponds to the guest address or + * -EFAULT if no such mapping exists. + * This function does not establish potentially missing page table entries. + */ +unsigned long gmap_translate(unsigned long address, struct gmap *gmap) +{ + unsigned long rc; + + down_read(&gmap->mm->mmap_sem); + rc = __gmap_translate(address, gmap); + up_read(&gmap->mm->mmap_sem); + return rc; +} +EXPORT_SYMBOL_GPL(gmap_translate); + +static int gmap_connect_pgtable(unsigned long segment, + unsigned long *segment_ptr, + struct gmap *gmap) +{ + unsigned long vmaddr; + struct vm_area_struct *vma; + struct gmap_pgtable *mp; + struct gmap_rmap *rmap; + struct mm_struct *mm; + struct page *page; + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + + mm = gmap->mm; + vmaddr = segment & _SEGMENT_ENTRY_ORIGIN; + vma = find_vma(mm, vmaddr); + if (!vma || vma->vm_start > vmaddr) + return -EFAULT; + /* Walk the parent mm page table */ + pgd = pgd_offset(mm, vmaddr); + pud = pud_alloc(mm, pgd, vmaddr); + if (!pud) + return -ENOMEM; + pmd = pmd_alloc(mm, pud, vmaddr); + if (!pmd) + return -ENOMEM; + if (!pmd_present(*pmd) && + __pte_alloc(mm, vma, pmd, vmaddr)) + return -ENOMEM; + /* pmd now points to a valid segment table entry. */ + rmap = kmalloc(sizeof(*rmap), GFP_KERNEL|__GFP_REPEAT); + if (!rmap) + return -ENOMEM; + /* Link gmap segment table entry location to page table. */ + page = pmd_page(*pmd); + mp = (struct gmap_pgtable *) page->index; + rmap->entry = segment_ptr; + spin_lock(&mm->page_table_lock); + if (*segment_ptr == segment) { list_add(&rmap->list, &mp->mapper); - spin_unlock(&mm->page_table_lock); /* Set gmap segment table entry to page table. */ - *table = pmd_val(*pmd) & PAGE_MASK; - return vmaddr | (address & ~PMD_MASK); + *segment_ptr = pmd_val(*pmd) & PAGE_MASK; + rmap = NULL; + } + spin_unlock(&mm->page_table_lock); + kfree(rmap); + return 0; +} + +static void gmap_disconnect_pgtable(struct mm_struct *mm, unsigned long *table) +{ + struct gmap_rmap *rmap, *next; + struct gmap_pgtable *mp; + struct page *page; + int flush; + + flush = 0; + spin_lock(&mm->page_table_lock); + page = pfn_to_page(__pa(table) >> PAGE_SHIFT); + mp = (struct gmap_pgtable *) page->index; + list_for_each_entry_safe(rmap, next, &mp->mapper, list) { + *rmap->entry = + _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO | mp->vmaddr; + list_del(&rmap->list); + kfree(rmap); + flush = 1; + } + spin_unlock(&mm->page_table_lock); + if (flush) + __tlb_flush_global(); +} + +/* + * this function is assumed to be called with mmap_sem held + */ +unsigned long __gmap_fault(unsigned long address, struct gmap *gmap) +{ + unsigned long *segment_ptr, segment; + struct gmap_pgtable *mp; + struct page *page; + int rc; + + current->thread.gmap_addr = address; + segment_ptr = gmap_table_walk(address, gmap); + if (IS_ERR(segment_ptr)) + return -EFAULT; + /* Convert the gmap address to an mm address. */ + while (1) { + segment = *segment_ptr; + if (!(segment & _SEGMENT_ENTRY_INV)) { + /* Page table is present */ + page = pfn_to_page(segment >> PAGE_SHIFT); + mp = (struct gmap_pgtable *) page->index; + return mp->vmaddr | (address & ~PMD_MASK); + } + if (!(segment & _SEGMENT_ENTRY_RO)) + /* Nothing mapped in the gmap address space. */ + break; + rc = gmap_connect_pgtable(segment, segment_ptr, gmap); + if (rc) + return rc; } return -EFAULT; } @@ -511,29 +619,6 @@ void gmap_discard(unsigned long from, unsigned long to, struct gmap *gmap) } EXPORT_SYMBOL_GPL(gmap_discard); -void gmap_unmap_notifier(struct mm_struct *mm, unsigned long *table) -{ - struct gmap_rmap *rmap, *next; - struct gmap_pgtable *mp; - struct page *page; - int flush; - - flush = 0; - spin_lock(&mm->page_table_lock); - page = pfn_to_page(__pa(table) >> PAGE_SHIFT); - mp = (struct gmap_pgtable *) page->index; - list_for_each_entry_safe(rmap, next, &mp->mapper, list) { - *rmap->entry = - _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO | mp->vmaddr; - list_del(&rmap->list); - kfree(rmap); - flush = 1; - } - spin_unlock(&mm->page_table_lock); - if (flush) - __tlb_flush_global(); -} - static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm, unsigned long vmaddr) { @@ -586,8 +671,8 @@ static inline void page_table_free_pgste(unsigned long *table) { } -static inline void gmap_unmap_notifier(struct mm_struct *mm, - unsigned long *table) +static inline void gmap_disconnect_pgtable(struct mm_struct *mm, + unsigned long *table) { } @@ -653,7 +738,7 @@ void page_table_free(struct mm_struct *mm, unsigned long *table) unsigned int bit, mask; if (mm_has_pgste(mm)) { - gmap_unmap_notifier(mm, table); + gmap_disconnect_pgtable(mm, table); return page_table_free_pgste(table); } /* Free 1K/2K page table fragment of a 4K page */ @@ -696,7 +781,7 @@ void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table) mm = tlb->mm; if (mm_has_pgste(mm)) { - gmap_unmap_notifier(mm, table); + gmap_disconnect_pgtable(mm, table); table = (unsigned long *) (__pa(table) | FRAG_MASK); tlb_remove_table(tlb, table); return; diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 0972e91cced..82f165f8078 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -747,10 +747,9 @@ void bpf_jit_compile(struct sk_filter *fp) if (!bpf_jit_enable) return; - addrs = kmalloc(fp->len * sizeof(*addrs), GFP_KERNEL); + addrs = kcalloc(fp->len, sizeof(*addrs), GFP_KERNEL); if (addrs == NULL) return; - memset(addrs, 0, fp->len * sizeof(*addrs)); memset(&jit, 0, sizeof(cjit)); memset(&cjit, 0, sizeof(cjit)); diff --git a/arch/s390/pci/Makefile b/arch/s390/pci/Makefile index f0f426a113c..086a2e37935 100644 --- a/arch/s390/pci/Makefile +++ b/arch/s390/pci/Makefile @@ -2,5 +2,5 @@ # Makefile for the s390 PCI subsystem. # -obj-$(CONFIG_PCI) += pci.o pci_dma.o pci_clp.o pci_msi.o \ - pci_sysfs.o pci_event.o pci_debug.o +obj-$(CONFIG_PCI) += pci.o pci_dma.o pci_clp.o pci_msi.o pci_sysfs.o \ + pci_event.o pci_debug.o pci_insn.o diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 27b4c17855b..e6f15b5d8b7 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -99,9 +99,6 @@ static int __read_mostly aisb_max; static struct kmem_cache *zdev_irq_cache; static struct kmem_cache *zdev_fmb_cache; -debug_info_t *pci_debug_msg_id; -debug_info_t *pci_debug_err_id; - static inline int irq_to_msi_nr(unsigned int irq) { return irq & ZPCI_MSI_MASK; @@ -179,7 +176,7 @@ static int zpci_register_airq(struct zpci_dev *zdev, unsigned int aisb, fib->aisb = (u64) bucket->aisb + aisb / 8; fib->aisbo = aisb & ZPCI_MSI_MASK; - rc = mpcifc_instr(req, fib); + rc = s390pci_mod_fc(req, fib); pr_debug("%s mpcifc returned noi: %d\n", __func__, fib->noi); free_page((unsigned long) fib); @@ -209,7 +206,7 @@ static int mod_pci(struct zpci_dev *zdev, int fn, u8 dmaas, struct mod_pci_args fib->iota = args->iota; fib->fmb_addr = args->fmb_addr; - rc = mpcifc_instr(req, fib); + rc = s390pci_mod_fc(req, fib); free_page((unsigned long) fib); return rc; } @@ -249,10 +246,9 @@ int zpci_fmb_enable_device(struct zpci_dev *zdev) if (zdev->fmb) return -EINVAL; - zdev->fmb = kmem_cache_alloc(zdev_fmb_cache, GFP_KERNEL); + zdev->fmb = kmem_cache_zalloc(zdev_fmb_cache, GFP_KERNEL); if (!zdev->fmb) return -ENOMEM; - memset(zdev->fmb, 0, sizeof(*zdev->fmb)); WARN_ON((u64) zdev->fmb & 0xf); args.fmb_addr = virt_to_phys(zdev->fmb); @@ -284,12 +280,12 @@ static int zpci_cfg_load(struct zpci_dev *zdev, int offset, u32 *val, u8 len) u64 data; int rc; - rc = pcilg_instr(&data, req, offset); - data = data << ((8 - len) * 8); - data = le64_to_cpu(data); - if (!rc) + rc = s390pci_load(&data, req, offset); + if (!rc) { + data = data << ((8 - len) * 8); + data = le64_to_cpu(data); *val = (u32) data; - else + } else *val = 0xffffffff; return rc; } @@ -302,7 +298,7 @@ static int zpci_cfg_store(struct zpci_dev *zdev, int offset, u32 val, u8 len) data = cpu_to_le64(data); data = data >> ((8 - len) * 8); - rc = pcistg_instr(data, req, offset); + rc = s390pci_store(data, req, offset); return rc; } @@ -409,20 +405,28 @@ static int pci_read(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *val) { struct zpci_dev *zdev = get_zdev_by_bus(bus); + int ret; if (!zdev || devfn != ZPCI_DEVFN) - return 0; - return zpci_cfg_load(zdev, where, val, size); + ret = -ENODEV; + else + ret = zpci_cfg_load(zdev, where, val, size); + + return ret; } static int pci_write(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 val) { struct zpci_dev *zdev = get_zdev_by_bus(bus); + int ret; if (!zdev || devfn != ZPCI_DEVFN) - return 0; - return zpci_cfg_store(zdev, where, val, size); + ret = -ENODEV; + else + ret = zpci_cfg_store(zdev, where, val, size); + + return ret; } static struct pci_ops pci_root_ops = { @@ -474,7 +478,7 @@ scan: } /* enable interrupts again */ - sic_instr(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC); + set_irq_ctrl(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC); /* check again to not lose initiative */ rmb(); @@ -596,19 +600,6 @@ static void zpci_map_resources(struct zpci_dev *zdev) } }; -static void zpci_unmap_resources(struct pci_dev *pdev) -{ - resource_size_t len; - int i; - - for (i = 0; i < PCI_BAR_COUNT; i++) { - len = pci_resource_len(pdev, i); - if (!len) - continue; - pci_iounmap(pdev, (void *) pdev->resource[i].start); - } -}; - struct zpci_dev *zpci_alloc_device(void) { struct zpci_dev *zdev; @@ -636,32 +627,6 @@ void zpci_free_device(struct zpci_dev *zdev) kfree(zdev); } -/* Called on removal of pci_dev, leaves zpci and bus device */ -static void zpci_remove_device(struct pci_dev *pdev) -{ - struct zpci_dev *zdev = get_zdev(pdev); - - dev_info(&pdev->dev, "Removing device %u\n", zdev->domain); - zdev->state = ZPCI_FN_STATE_CONFIGURED; - zpci_dma_exit_device(zdev); - zpci_fmb_disable_device(zdev); - zpci_sysfs_remove_device(&pdev->dev); - zpci_unmap_resources(pdev); - list_del(&zdev->entry); /* can be called from init */ - zdev->pdev = NULL; -} - -static void zpci_scan_devices(void) -{ - struct zpci_dev *zdev; - - mutex_lock(&zpci_list_lock); - list_for_each_entry(zdev, &zpci_list, entry) - if (zdev->state == ZPCI_FN_STATE_CONFIGURED) - zpci_scan_device(zdev); - mutex_unlock(&zpci_list_lock); -} - /* * Too late for any s390 specific setup, since interrupts must be set up * already which requires DMA setup too and the pci scan will access the @@ -688,12 +653,6 @@ int pcibios_enable_device(struct pci_dev *pdev, int mask) return 0; } -void pcibios_disable_device(struct pci_dev *pdev) -{ - zpci_remove_device(pdev); - pdev->sysdata = NULL; -} - int pcibios_add_platform_entries(struct pci_dev *pdev) { return zpci_sysfs_add_device(&pdev->dev); @@ -789,7 +748,7 @@ static int __init zpci_irq_init(void) spin_lock_init(&bucket->lock); /* set summary to 1 to be called every time for the ISC */ *zpci_irq_si = 1; - sic_instr(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC); + set_irq_ctrl(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC); return 0; out_ai: @@ -872,7 +831,19 @@ static void zpci_free_iomap(struct zpci_dev *zdev, int entry) spin_unlock(&zpci_iomap_lock); } -static int zpci_create_device_bus(struct zpci_dev *zdev) +int pcibios_add_device(struct pci_dev *pdev) +{ + struct zpci_dev *zdev = get_zdev(pdev); + + zdev->pdev = pdev; + zpci_debug_init_device(zdev); + zpci_fmb_enable_device(zdev); + zpci_map_resources(zdev); + + return 0; +} + +static int zpci_scan_bus(struct zpci_dev *zdev) { struct resource *res; LIST_HEAD(resources); @@ -909,8 +880,8 @@ static int zpci_create_device_bus(struct zpci_dev *zdev) pci_add_resource(&resources, res); } - zdev->bus = pci_create_root_bus(NULL, ZPCI_BUS_NR, &pci_root_ops, - zdev, &resources); + zdev->bus = pci_scan_root_bus(NULL, ZPCI_BUS_NR, &pci_root_ops, + zdev, &resources); if (!zdev->bus) return -EIO; @@ -959,6 +930,13 @@ out: } EXPORT_SYMBOL_GPL(zpci_enable_device); +int zpci_disable_device(struct zpci_dev *zdev) +{ + zpci_dma_exit_device(zdev); + return clp_disable_fh(zdev); +} +EXPORT_SYMBOL_GPL(zpci_disable_device); + int zpci_create_device(struct zpci_dev *zdev) { int rc; @@ -967,9 +945,16 @@ int zpci_create_device(struct zpci_dev *zdev) if (rc) goto out; - rc = zpci_create_device_bus(zdev); + if (zdev->state == ZPCI_FN_STATE_CONFIGURED) { + rc = zpci_enable_device(zdev); + if (rc) + goto out_free; + + zdev->state = ZPCI_FN_STATE_ONLINE; + } + rc = zpci_scan_bus(zdev); if (rc) - goto out_bus; + goto out_disable; mutex_lock(&zpci_list_lock); list_add_tail(&zdev->entry, &zpci_list); @@ -977,21 +962,12 @@ int zpci_create_device(struct zpci_dev *zdev) hotplug_ops->create_slot(zdev); mutex_unlock(&zpci_list_lock); - if (zdev->state == ZPCI_FN_STATE_STANDBY) - return 0; - - rc = zpci_enable_device(zdev); - if (rc) - goto out_start; return 0; -out_start: - mutex_lock(&zpci_list_lock); - list_del(&zdev->entry); - if (hotplug_ops) - hotplug_ops->remove_slot(zdev); - mutex_unlock(&zpci_list_lock); -out_bus: +out_disable: + if (zdev->state == ZPCI_FN_STATE_ONLINE) + zpci_disable_device(zdev); +out_free: zpci_free_domain(zdev); out: return rc; @@ -1016,15 +992,9 @@ int zpci_scan_device(struct zpci_dev *zdev) goto out; } - zpci_debug_init_device(zdev); - zpci_fmb_enable_device(zdev); - zpci_map_resources(zdev); pci_bus_add_devices(zdev->bus); - /* now that pdev was added to the bus mark it as used */ - zdev->state = ZPCI_FN_STATE_ONLINE; return 0; - out: zpci_dma_exit_device(zdev); clp_disable_fh(zdev); @@ -1087,13 +1057,13 @@ void zpci_deregister_hp_ops(void) } EXPORT_SYMBOL_GPL(zpci_deregister_hp_ops); -unsigned int s390_pci_probe = 1; +unsigned int s390_pci_probe; EXPORT_SYMBOL_GPL(s390_pci_probe); char * __init pcibios_setup(char *str) { - if (!strcmp(str, "off")) { - s390_pci_probe = 0; + if (!strcmp(str, "on")) { + s390_pci_probe = 1; return NULL; } return str; @@ -1138,7 +1108,6 @@ static int __init pci_base_init(void) if (rc) goto out_find; - zpci_scan_devices(); return 0; out_find: diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c index f339fe2feb1..bd34359d154 100644 --- a/arch/s390/pci/pci_clp.c +++ b/arch/s390/pci/pci_clp.c @@ -13,6 +13,7 @@ #include <linux/err.h> #include <linux/delay.h> #include <linux/pci.h> +#include <asm/pci_debug.h> #include <asm/pci_clp.h> /* @@ -144,6 +145,7 @@ int clp_add_pci_device(u32 fid, u32 fh, int configured) struct zpci_dev *zdev; int rc; + zpci_dbg(3, "add fid:%x, fh:%x, c:%d\n", fid, fh, configured); zdev = zpci_alloc_device(); if (IS_ERR(zdev)) return PTR_ERR(zdev); @@ -204,8 +206,8 @@ static int clp_set_pci_fn(u32 *fh, u8 nr_dma_as, u8 command) if (!rc && rrb->response.hdr.rsp == CLP_RC_OK) *fh = rrb->response.fh; else { - pr_err("Set PCI FN failed with response: %x cc: %d\n", - rrb->response.hdr.rsp, rc); + zpci_dbg(0, "SPF fh:%x, cc:%d, resp:%x\n", *fh, rc, + rrb->response.hdr.rsp); rc = -EIO; } clp_free_block(rrb); @@ -221,6 +223,8 @@ int clp_enable_fh(struct zpci_dev *zdev, u8 nr_dma_as) if (!rc) /* Success -> store enabled handle in zdev */ zdev->fh = fh; + + zpci_dbg(3, "ena fid:%x, fh:%x, rc:%d\n", zdev->fid, zdev->fh, rc); return rc; } @@ -237,9 +241,8 @@ int clp_disable_fh(struct zpci_dev *zdev) if (!rc) /* Success -> store disabled handle in zdev */ zdev->fh = fh; - else - dev_err(&zdev->pdev->dev, - "Failed to disable fn handle: 0x%x\n", fh); + + zpci_dbg(3, "dis fid:%x, fh:%x, rc:%d\n", zdev->fid, zdev->fh, rc); return rc; } diff --git a/arch/s390/pci/pci_debug.c b/arch/s390/pci/pci_debug.c index a5d07bc2a54..771b82359af 100644 --- a/arch/s390/pci/pci_debug.c +++ b/arch/s390/pci/pci_debug.c @@ -11,12 +11,17 @@ #include <linux/kernel.h> #include <linux/seq_file.h> #include <linux/debugfs.h> +#include <linux/export.h> #include <linux/pci.h> #include <asm/debug.h> #include <asm/pci_dma.h> static struct dentry *debugfs_root; +debug_info_t *pci_debug_msg_id; +EXPORT_SYMBOL_GPL(pci_debug_msg_id); +debug_info_t *pci_debug_err_id; +EXPORT_SYMBOL_GPL(pci_debug_err_id); static char *pci_perf_names[] = { /* hardware counters */ @@ -168,7 +173,6 @@ int __init zpci_debug_init(void) return -EINVAL; debug_register_view(pci_debug_msg_id, &debug_sprintf_view); debug_set_level(pci_debug_msg_id, 3); - zpci_dbg("Debug view initialized\n"); /* error log */ pci_debug_err_id = debug_register("pci_error", 2, 1, 16); @@ -176,7 +180,6 @@ int __init zpci_debug_init(void) return -EINVAL; debug_register_view(pci_debug_err_id, &debug_hex_ascii_view); debug_set_level(pci_debug_err_id, 6); - zpci_err("Debug view initialized\n"); debugfs_root = debugfs_create_dir("pci", NULL); return 0; diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c index a547419907c..f8e69d5bc0a 100644 --- a/arch/s390/pci/pci_dma.c +++ b/arch/s390/pci/pci_dma.c @@ -169,8 +169,9 @@ static int dma_update_trans(struct zpci_dev *zdev, unsigned long pa, * needs to be redone! */ goto no_refresh; - rc = rpcit_instr((u64) zdev->fh << 32, start_dma_addr, - nr_pages * PAGE_SIZE); + + rc = s390pci_refresh_trans((u64) zdev->fh << 32, start_dma_addr, + nr_pages * PAGE_SIZE); no_refresh: spin_unlock_irqrestore(&zdev->dma_table_lock, irq_flags); @@ -268,8 +269,6 @@ static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page, int flags = ZPCI_PTE_VALID; dma_addr_t dma_addr; - WARN_ON_ONCE(offset > PAGE_SIZE); - /* This rounds up number of pages based on size and offset */ nr_pages = iommu_num_pages(pa, size, PAGE_SIZE); iommu_page_index = dma_alloc_iommu(zdev, nr_pages); @@ -291,7 +290,7 @@ static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page, if (!dma_update_trans(zdev, pa, dma_addr, size, flags)) { atomic64_add(nr_pages, (atomic64_t *) &zdev->fmb->mapped_pages); - return dma_addr + offset; + return dma_addr + (offset & ~PAGE_MASK); } out_free: diff --git a/arch/s390/pci/pci_insn.c b/arch/s390/pci/pci_insn.c new file mode 100644 index 00000000000..22eeb9d7ffe --- /dev/null +++ b/arch/s390/pci/pci_insn.c @@ -0,0 +1,202 @@ +/* + * s390 specific pci instructions + * + * Copyright IBM Corp. 2013 + */ + +#include <linux/export.h> +#include <linux/errno.h> +#include <linux/delay.h> +#include <asm/pci_insn.h> +#include <asm/processor.h> + +#define ZPCI_INSN_BUSY_DELAY 1 /* 1 microsecond */ + +/* Modify PCI Function Controls */ +static inline u8 __mpcifc(u64 req, struct zpci_fib *fib, u8 *status) +{ + u8 cc; + + asm volatile ( + " .insn rxy,0xe300000000d0,%[req],%[fib]\n" + " ipm %[cc]\n" + " srl %[cc],28\n" + : [cc] "=d" (cc), [req] "+d" (req), [fib] "+Q" (*fib) + : : "cc"); + *status = req >> 24 & 0xff; + return cc; +} + +int s390pci_mod_fc(u64 req, struct zpci_fib *fib) +{ + u8 cc, status; + + do { + cc = __mpcifc(req, fib, &status); + if (cc == 2) + msleep(ZPCI_INSN_BUSY_DELAY); + } while (cc == 2); + + if (cc) + printk_once(KERN_ERR "%s: error cc: %d status: %d\n", + __func__, cc, status); + return (cc) ? -EIO : 0; +} + +/* Refresh PCI Translations */ +static inline u8 __rpcit(u64 fn, u64 addr, u64 range, u8 *status) +{ + register u64 __addr asm("2") = addr; + register u64 __range asm("3") = range; + u8 cc; + + asm volatile ( + " .insn rre,0xb9d30000,%[fn],%[addr]\n" + " ipm %[cc]\n" + " srl %[cc],28\n" + : [cc] "=d" (cc), [fn] "+d" (fn) + : [addr] "d" (__addr), "d" (__range) + : "cc"); + *status = fn >> 24 & 0xff; + return cc; +} + +int s390pci_refresh_trans(u64 fn, u64 addr, u64 range) +{ + u8 cc, status; + + do { + cc = __rpcit(fn, addr, range, &status); + if (cc == 2) + udelay(ZPCI_INSN_BUSY_DELAY); + } while (cc == 2); + + if (cc) + printk_once(KERN_ERR "%s: error cc: %d status: %d dma_addr: %Lx size: %Lx\n", + __func__, cc, status, addr, range); + return (cc) ? -EIO : 0; +} + +/* Set Interruption Controls */ +void set_irq_ctrl(u16 ctl, char *unused, u8 isc) +{ + asm volatile ( + " .insn rsy,0xeb00000000d1,%[ctl],%[isc],%[u]\n" + : : [ctl] "d" (ctl), [isc] "d" (isc << 27), [u] "Q" (*unused)); +} + +/* PCI Load */ +static inline int __pcilg(u64 *data, u64 req, u64 offset, u8 *status) +{ + register u64 __req asm("2") = req; + register u64 __offset asm("3") = offset; + int cc = -ENXIO; + u64 __data; + + asm volatile ( + " .insn rre,0xb9d20000,%[data],%[req]\n" + "0: ipm %[cc]\n" + " srl %[cc],28\n" + "1:\n" + EX_TABLE(0b, 1b) + : [cc] "+d" (cc), [data] "=d" (__data), [req] "+d" (__req) + : "d" (__offset) + : "cc"); + *status = __req >> 24 & 0xff; + if (!cc) + *data = __data; + + return cc; +} + +int s390pci_load(u64 *data, u64 req, u64 offset) +{ + u8 status; + int cc; + + do { + cc = __pcilg(data, req, offset, &status); + if (cc == 2) + udelay(ZPCI_INSN_BUSY_DELAY); + } while (cc == 2); + + if (cc) + printk_once(KERN_ERR "%s: error cc: %d status: %d req: %Lx offset: %Lx\n", + __func__, cc, status, req, offset); + return (cc > 0) ? -EIO : cc; +} +EXPORT_SYMBOL_GPL(s390pci_load); + +/* PCI Store */ +static inline int __pcistg(u64 data, u64 req, u64 offset, u8 *status) +{ + register u64 __req asm("2") = req; + register u64 __offset asm("3") = offset; + int cc = -ENXIO; + + asm volatile ( + " .insn rre,0xb9d00000,%[data],%[req]\n" + "0: ipm %[cc]\n" + " srl %[cc],28\n" + "1:\n" + EX_TABLE(0b, 1b) + : [cc] "+d" (cc), [req] "+d" (__req) + : "d" (__offset), [data] "d" (data) + : "cc"); + *status = __req >> 24 & 0xff; + return cc; +} + +int s390pci_store(u64 data, u64 req, u64 offset) +{ + u8 status; + int cc; + + do { + cc = __pcistg(data, req, offset, &status); + if (cc == 2) + udelay(ZPCI_INSN_BUSY_DELAY); + } while (cc == 2); + + if (cc) + printk_once(KERN_ERR "%s: error cc: %d status: %d req: %Lx offset: %Lx\n", + __func__, cc, status, req, offset); + return (cc > 0) ? -EIO : cc; +} +EXPORT_SYMBOL_GPL(s390pci_store); + +/* PCI Store Block */ +static inline int __pcistb(const u64 *data, u64 req, u64 offset, u8 *status) +{ + int cc = -ENXIO; + + asm volatile ( + " .insn rsy,0xeb00000000d0,%[req],%[offset],%[data]\n" + "0: ipm %[cc]\n" + " srl %[cc],28\n" + "1:\n" + EX_TABLE(0b, 1b) + : [cc] "+d" (cc), [req] "+d" (req) + : [offset] "d" (offset), [data] "Q" (*data) + : "cc"); + *status = req >> 24 & 0xff; + return cc; +} + +int s390pci_store_block(const u64 *data, u64 req, u64 offset) +{ + u8 status; + int cc; + + do { + cc = __pcistb(data, req, offset, &status); + if (cc == 2) + udelay(ZPCI_INSN_BUSY_DELAY); + } while (cc == 2); + + if (cc) + printk_once(KERN_ERR "%s: error cc: %d status: %d req: %Lx offset: %Lx\n", + __func__, cc, status, req, offset); + return (cc > 0) ? -EIO : cc; +} +EXPORT_SYMBOL_GPL(s390pci_store_block); diff --git a/arch/s390/pci/pci_msi.c b/arch/s390/pci/pci_msi.c index 0297931335e..b097aed05a9 100644 --- a/arch/s390/pci/pci_msi.c +++ b/arch/s390/pci/pci_msi.c @@ -18,8 +18,9 @@ /* mapping of irq numbers to msi_desc */ static struct hlist_head *msi_hash; -static unsigned int msihash_shift = 6; -#define msi_hashfn(nr) hash_long(nr, msihash_shift) +static const unsigned int msi_hash_bits = 8; +#define MSI_HASH_BUCKETS (1U << msi_hash_bits) +#define msi_hashfn(nr) hash_long(nr, msi_hash_bits) static DEFINE_SPINLOCK(msi_map_lock); @@ -74,6 +75,7 @@ int zpci_setup_msi_irq(struct zpci_dev *zdev, struct msi_desc *msi, map->irq = nr; map->msi = msi; zdev->msi_map[nr & ZPCI_MSI_MASK] = map; + INIT_HLIST_NODE(&map->msi_chain); pr_debug("%s hashing irq: %u to bucket nr: %llu\n", __func__, nr, msi_hashfn(nr)); @@ -125,11 +127,11 @@ int __init zpci_msihash_init(void) { unsigned int i; - msi_hash = kmalloc(256 * sizeof(*msi_hash), GFP_KERNEL); + msi_hash = kmalloc(MSI_HASH_BUCKETS * sizeof(*msi_hash), GFP_KERNEL); if (!msi_hash) return -ENOMEM; - for (i = 0; i < (1U << msihash_shift); i++) + for (i = 0; i < MSI_HASH_BUCKETS; i++) INIT_HLIST_HEAD(&msi_hash[i]); return 0; } diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild index e26d430ce2f..ff18e3cfb6b 100644 --- a/arch/sparc/include/asm/Kbuild +++ b/arch/sparc/include/asm/Kbuild @@ -2,11 +2,16 @@ generic-y += clkdev.h +generic-y += cputime.h generic-y += div64.h +generic-y += emergency-restart.h generic-y += exec.h generic-y += local64.h +generic-y += mutex.h generic-y += irq_regs.h generic-y += local.h generic-y += module.h +generic-y += serial.h generic-y += trace_clock.h +generic-y += types.h generic-y += word-at-a-time.h diff --git a/arch/sparc/include/asm/cputime.h b/arch/sparc/include/asm/cputime.h deleted file mode 100644 index 1a642b81e01..00000000000 --- a/arch/sparc/include/asm/cputime.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __SPARC_CPUTIME_H -#define __SPARC_CPUTIME_H - -#include <asm-generic/cputime.h> - -#endif /* __SPARC_CPUTIME_H */ diff --git a/arch/sparc/include/asm/emergency-restart.h b/arch/sparc/include/asm/emergency-restart.h deleted file mode 100644 index 108d8c48e42..00000000000 --- a/arch/sparc/include/asm/emergency-restart.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _ASM_EMERGENCY_RESTART_H -#define _ASM_EMERGENCY_RESTART_H - -#include <asm-generic/emergency-restart.h> - -#endif /* _ASM_EMERGENCY_RESTART_H */ diff --git a/arch/sparc/include/asm/mutex.h b/arch/sparc/include/asm/mutex.h deleted file mode 100644 index 458c1f7fbc1..00000000000 --- a/arch/sparc/include/asm/mutex.h +++ /dev/null @@ -1,9 +0,0 @@ -/* - * Pull in the generic implementation for the mutex fastpath. - * - * TODO: implement optimized primitives instead, or leave the generic - * implementation in place, or pick the atomic_xchg() based generic - * implementation. (see asm-generic/mutex-xchg.h for details) - */ - -#include <asm-generic/mutex-dec.h> diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 08fcce90316..7619f2f792a 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -915,6 +915,7 @@ static inline int io_remap_pfn_range(struct vm_area_struct *vma, return remap_pfn_range(vma, from, phys_base >> PAGE_SHIFT, size, prot); } +#include <asm/tlbflush.h> #include <asm-generic/pgtable.h> /* We provide our own get_unmapped_area to cope with VA holes and diff --git a/arch/sparc/include/asm/serial.h b/arch/sparc/include/asm/serial.h deleted file mode 100644 index f90d61c2805..00000000000 --- a/arch/sparc/include/asm/serial.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __SPARC_SERIAL_H -#define __SPARC_SERIAL_H - -#define BASE_BAUD ( 1843200 / 16 ) - -#endif /* __SPARC_SERIAL_H */ diff --git a/arch/sparc/include/asm/smp_32.h b/arch/sparc/include/asm/smp_32.h index b73da3c5f10..3c8917f054d 100644 --- a/arch/sparc/include/asm/smp_32.h +++ b/arch/sparc/include/asm/smp_32.h @@ -36,7 +36,6 @@ typedef void (*smpfunc_t)(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); void cpu_panic(void); -extern void smp4m_irq_rotate(int cpu); /* * General functions that each host system must provide. @@ -46,7 +45,6 @@ void sun4m_init_smp(void); void sun4d_init_smp(void); void smp_callin(void); -void smp_boot_cpus(void); void smp_store_cpu_info(int); void smp_resched_interrupt(void); @@ -107,9 +105,6 @@ extern int hard_smp_processor_id(void); #define raw_smp_processor_id() (current_thread_info()->cpu) -#define prof_multiplier(__cpu) cpu_data(__cpu).multiplier -#define prof_counter(__cpu) cpu_data(__cpu).counter - void smp_setup_cpu_possible_map(void); #endif /* !(__ASSEMBLY__) */ diff --git a/arch/sparc/include/asm/switch_to_64.h b/arch/sparc/include/asm/switch_to_64.h index cad36f56fa0..c7de3323819 100644 --- a/arch/sparc/include/asm/switch_to_64.h +++ b/arch/sparc/include/asm/switch_to_64.h @@ -18,8 +18,7 @@ do { \ * and 2 stores in this critical code path. -DaveM */ #define switch_to(prev, next, last) \ -do { flush_tlb_pending(); \ - save_and_clear_fpu(); \ +do { save_and_clear_fpu(); \ /* If you are tempted to conditionalize the following */ \ /* so that ASI is only written if it changes, think again. */ \ __asm__ __volatile__("wr %%g0, %0, %%asi" \ diff --git a/arch/sparc/include/asm/tlbflush_64.h b/arch/sparc/include/asm/tlbflush_64.h index 2ef46349415..f0d6a9700f4 100644 --- a/arch/sparc/include/asm/tlbflush_64.h +++ b/arch/sparc/include/asm/tlbflush_64.h @@ -11,24 +11,40 @@ struct tlb_batch { struct mm_struct *mm; unsigned long tlb_nr; + unsigned long active; unsigned long vaddrs[TLB_BATCH_NR]; }; extern void flush_tsb_kernel_range(unsigned long start, unsigned long end); extern void flush_tsb_user(struct tlb_batch *tb); +extern void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr); /* TLB flush operations. */ -extern void flush_tlb_pending(void); +static inline void flush_tlb_mm(struct mm_struct *mm) +{ +} + +static inline void flush_tlb_page(struct vm_area_struct *vma, + unsigned long vmaddr) +{ +} + +static inline void flush_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ +} + +#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE -#define flush_tlb_range(vma,start,end) \ - do { (void)(start); flush_tlb_pending(); } while (0) -#define flush_tlb_page(vma,addr) flush_tlb_pending() -#define flush_tlb_mm(mm) flush_tlb_pending() +extern void flush_tlb_pending(void); +extern void arch_enter_lazy_mmu_mode(void); +extern void arch_leave_lazy_mmu_mode(void); +#define arch_flush_lazy_mmu_mode() do {} while (0) /* Local cpu only. */ extern void __flush_tlb_all(void); - +extern void __flush_tlb_page(unsigned long context, unsigned long vaddr); extern void __flush_tlb_kernel_range(unsigned long start, unsigned long end); #ifndef CONFIG_SMP @@ -38,15 +54,24 @@ do { flush_tsb_kernel_range(start,end); \ __flush_tlb_kernel_range(start,end); \ } while (0) +static inline void global_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr) +{ + __flush_tlb_page(CTX_HWBITS(mm->context), vaddr); +} + #else /* CONFIG_SMP */ extern void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end); +extern void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr); #define flush_tlb_kernel_range(start, end) \ do { flush_tsb_kernel_range(start,end); \ smp_flush_tlb_kernel_range(start, end); \ } while (0) +#define global_flush_tlb_page(mm, vaddr) \ + smp_flush_tlb_page(mm, vaddr) + #endif /* ! CONFIG_SMP */ #endif /* _SPARC64_TLBFLUSH_H */ diff --git a/arch/sparc/include/uapi/asm/Kbuild b/arch/sparc/include/uapi/asm/Kbuild index ce175aff71b..b5843ee09fb 100644 --- a/arch/sparc/include/uapi/asm/Kbuild +++ b/arch/sparc/include/uapi/asm/Kbuild @@ -44,7 +44,6 @@ header-y += swab.h header-y += termbits.h header-y += termios.h header-y += traps.h -header-y += types.h header-y += uctx.h header-y += unistd.h header-y += utrap.h diff --git a/arch/sparc/include/uapi/asm/types.h b/arch/sparc/include/uapi/asm/types.h deleted file mode 100644 index 383d156cde9..00000000000 --- a/arch/sparc/include/uapi/asm/types.h +++ /dev/null @@ -1,17 +0,0 @@ -#ifndef _SPARC_TYPES_H -#define _SPARC_TYPES_H -/* - * This file is never included by application software unless - * explicitly requested (e.g., via linux/types.h) in which case the - * application is Linux specific so (user-) name space pollution is - * not a major issue. However, for interoperability, libraries still - * need to be careful to avoid a name clashes. - */ - -#if defined(__sparc__) - -#include <asm-generic/int-ll64.h> - -#endif /* defined(__sparc__) */ - -#endif /* defined(_SPARC_TYPES_H) */ diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 537eb66abd0..ca64d2a86ec 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -849,7 +849,7 @@ void smp_tsb_sync(struct mm_struct *mm) } extern unsigned long xcall_flush_tlb_mm; -extern unsigned long xcall_flush_tlb_pending; +extern unsigned long xcall_flush_tlb_page; extern unsigned long xcall_flush_tlb_kernel_range; extern unsigned long xcall_fetch_glob_regs; extern unsigned long xcall_fetch_glob_pmu; @@ -1074,23 +1074,56 @@ local_flush_and_out: put_cpu(); } +struct tlb_pending_info { + unsigned long ctx; + unsigned long nr; + unsigned long *vaddrs; +}; + +static void tlb_pending_func(void *info) +{ + struct tlb_pending_info *t = info; + + __flush_tlb_pending(t->ctx, t->nr, t->vaddrs); +} + void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long *vaddrs) { u32 ctx = CTX_HWBITS(mm->context); + struct tlb_pending_info info; int cpu = get_cpu(); + info.ctx = ctx; + info.nr = nr; + info.vaddrs = vaddrs; + if (mm == current->mm && atomic_read(&mm->mm_users) == 1) cpumask_copy(mm_cpumask(mm), cpumask_of(cpu)); else - smp_cross_call_masked(&xcall_flush_tlb_pending, - ctx, nr, (unsigned long) vaddrs, - mm_cpumask(mm)); + smp_call_function_many(mm_cpumask(mm), tlb_pending_func, + &info, 1); __flush_tlb_pending(ctx, nr, vaddrs); put_cpu(); } +void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr) +{ + unsigned long context = CTX_HWBITS(mm->context); + int cpu = get_cpu(); + + if (mm == current->mm && atomic_read(&mm->mm_users) == 1) + cpumask_copy(mm_cpumask(mm), cpumask_of(cpu)); + else + smp_cross_call_masked(&xcall_flush_tlb_page, + context, vaddr, 0, + mm_cpumask(mm)); + __flush_tlb_page(context, vaddr); + + put_cpu(); +} + void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end) { start &= PAGE_MASK; diff --git a/arch/sparc/lib/bitext.c b/arch/sparc/lib/bitext.c index 48d00e72ce1..8ec4e9c0251 100644 --- a/arch/sparc/lib/bitext.c +++ b/arch/sparc/lib/bitext.c @@ -119,11 +119,7 @@ void bit_map_clear(struct bit_map *t, int offset, int len) void bit_map_init(struct bit_map *t, unsigned long *map, int size) { - - if ((size & 07) != 0) - BUG(); - memset(map, 0, size>>3); - + bitmap_zero(map, size); memset(t, 0, sizeof *t); spin_lock_init(&t->lock); t->map = map; diff --git a/arch/sparc/mm/iommu.c b/arch/sparc/mm/iommu.c index 0f4f7191fbb..28f96f27c76 100644 --- a/arch/sparc/mm/iommu.c +++ b/arch/sparc/mm/iommu.c @@ -34,7 +34,7 @@ #define IOMMU_RNGE IOMMU_RNGE_256MB #define IOMMU_START 0xF0000000 #define IOMMU_WINSIZE (256*1024*1024U) -#define IOMMU_NPTES (IOMMU_WINSIZE/PAGE_SIZE) /* 64K PTEs, 265KB */ +#define IOMMU_NPTES (IOMMU_WINSIZE/PAGE_SIZE) /* 64K PTEs, 256KB */ #define IOMMU_ORDER 6 /* 4096 * (1<<6) */ /* srmmu.c */ diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c index c38bb72e3e8..036c2797dec 100644 --- a/arch/sparc/mm/srmmu.c +++ b/arch/sparc/mm/srmmu.c @@ -280,7 +280,9 @@ static void __init srmmu_nocache_init(void) SRMMU_NOCACHE_ALIGN_MAX, 0UL); memset(srmmu_nocache_pool, 0, srmmu_nocache_size); - srmmu_nocache_bitmap = __alloc_bootmem(bitmap_bits >> 3, SMP_CACHE_BYTES, 0UL); + srmmu_nocache_bitmap = + __alloc_bootmem(BITS_TO_LONGS(bitmap_bits) * sizeof(long), + SMP_CACHE_BYTES, 0UL); bit_map_init(&srmmu_nocache_map, srmmu_nocache_bitmap, bitmap_bits); srmmu_swapper_pg_dir = __srmmu_get_nocache(SRMMU_PGD_TABLE_SIZE, SRMMU_PGD_TABLE_SIZE); diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c index ba6ae7ffdc2..83d89bcb44a 100644 --- a/arch/sparc/mm/tlb.c +++ b/arch/sparc/mm/tlb.c @@ -24,11 +24,17 @@ static DEFINE_PER_CPU(struct tlb_batch, tlb_batch); void flush_tlb_pending(void) { struct tlb_batch *tb = &get_cpu_var(tlb_batch); + struct mm_struct *mm = tb->mm; - if (tb->tlb_nr) { - flush_tsb_user(tb); + if (!tb->tlb_nr) + goto out; - if (CTX_VALID(tb->mm->context)) { + flush_tsb_user(tb); + + if (CTX_VALID(mm->context)) { + if (tb->tlb_nr == 1) { + global_flush_tlb_page(mm, tb->vaddrs[0]); + } else { #ifdef CONFIG_SMP smp_flush_tlb_pending(tb->mm, tb->tlb_nr, &tb->vaddrs[0]); @@ -37,12 +43,30 @@ void flush_tlb_pending(void) tb->tlb_nr, &tb->vaddrs[0]); #endif } - tb->tlb_nr = 0; } + tb->tlb_nr = 0; + +out: put_cpu_var(tlb_batch); } +void arch_enter_lazy_mmu_mode(void) +{ + struct tlb_batch *tb = &__get_cpu_var(tlb_batch); + + tb->active = 1; +} + +void arch_leave_lazy_mmu_mode(void) +{ + struct tlb_batch *tb = &__get_cpu_var(tlb_batch); + + if (tb->tlb_nr) + flush_tlb_pending(); + tb->active = 0; +} + static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr, bool exec) { @@ -60,6 +84,12 @@ static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr, nr = 0; } + if (!tb->active) { + global_flush_tlb_page(mm, vaddr); + flush_tsb_user_page(mm, vaddr); + goto out; + } + if (nr == 0) tb->mm = mm; @@ -68,6 +98,7 @@ static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr, if (nr >= TLB_BATCH_NR) flush_tlb_pending(); +out: put_cpu_var(tlb_batch); } diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c index 428982b9bec..2cc3bce5ee9 100644 --- a/arch/sparc/mm/tsb.c +++ b/arch/sparc/mm/tsb.c @@ -7,11 +7,10 @@ #include <linux/preempt.h> #include <linux/slab.h> #include <asm/page.h> -#include <asm/tlbflush.h> -#include <asm/tlb.h> -#include <asm/mmu_context.h> #include <asm/pgtable.h> +#include <asm/mmu_context.h> #include <asm/tsb.h> +#include <asm/tlb.h> #include <asm/oplib.h> extern struct tsb swapper_tsb[KERNEL_TSB_NENTRIES]; @@ -46,23 +45,27 @@ void flush_tsb_kernel_range(unsigned long start, unsigned long end) } } -static void __flush_tsb_one(struct tlb_batch *tb, unsigned long hash_shift, - unsigned long tsb, unsigned long nentries) +static void __flush_tsb_one_entry(unsigned long tsb, unsigned long v, + unsigned long hash_shift, + unsigned long nentries) { - unsigned long i; + unsigned long tag, ent, hash; - for (i = 0; i < tb->tlb_nr; i++) { - unsigned long v = tb->vaddrs[i]; - unsigned long tag, ent, hash; + v &= ~0x1UL; + hash = tsb_hash(v, hash_shift, nentries); + ent = tsb + (hash * sizeof(struct tsb)); + tag = (v >> 22UL); - v &= ~0x1UL; + tsb_flush(ent, tag); +} - hash = tsb_hash(v, hash_shift, nentries); - ent = tsb + (hash * sizeof(struct tsb)); - tag = (v >> 22UL); +static void __flush_tsb_one(struct tlb_batch *tb, unsigned long hash_shift, + unsigned long tsb, unsigned long nentries) +{ + unsigned long i; - tsb_flush(ent, tag); - } + for (i = 0; i < tb->tlb_nr; i++) + __flush_tsb_one_entry(tsb, tb->vaddrs[i], hash_shift, nentries); } void flush_tsb_user(struct tlb_batch *tb) @@ -90,6 +93,30 @@ void flush_tsb_user(struct tlb_batch *tb) spin_unlock_irqrestore(&mm->context.lock, flags); } +void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr) +{ + unsigned long nentries, base, flags; + + spin_lock_irqsave(&mm->context.lock, flags); + + base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb; + nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries; + if (tlb_type == cheetah_plus || tlb_type == hypervisor) + base = __pa(base); + __flush_tsb_one_entry(base, vaddr, PAGE_SHIFT, nentries); + +#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) + if (mm->context.tsb_block[MM_TSB_HUGE].tsb) { + base = (unsigned long) mm->context.tsb_block[MM_TSB_HUGE].tsb; + nentries = mm->context.tsb_block[MM_TSB_HUGE].tsb_nentries; + if (tlb_type == cheetah_plus || tlb_type == hypervisor) + base = __pa(base); + __flush_tsb_one_entry(base, vaddr, HPAGE_SHIFT, nentries); + } +#endif + spin_unlock_irqrestore(&mm->context.lock, flags); +} + #define HV_PGSZ_IDX_BASE HV_PGSZ_IDX_8K #define HV_PGSZ_MASK_BASE HV_PGSZ_MASK_8K diff --git a/arch/sparc/mm/ultra.S b/arch/sparc/mm/ultra.S index f8e13d421fc..432aa0cb1b3 100644 --- a/arch/sparc/mm/ultra.S +++ b/arch/sparc/mm/ultra.S @@ -53,6 +53,33 @@ __flush_tlb_mm: /* 18 insns */ nop .align 32 + .globl __flush_tlb_page +__flush_tlb_page: /* 22 insns */ + /* %o0 = context, %o1 = vaddr */ + rdpr %pstate, %g7 + andn %g7, PSTATE_IE, %g2 + wrpr %g2, %pstate + mov SECONDARY_CONTEXT, %o4 + ldxa [%o4] ASI_DMMU, %g2 + stxa %o0, [%o4] ASI_DMMU + andcc %o1, 1, %g0 + andn %o1, 1, %o3 + be,pn %icc, 1f + or %o3, 0x10, %o3 + stxa %g0, [%o3] ASI_IMMU_DEMAP +1: stxa %g0, [%o3] ASI_DMMU_DEMAP + membar #Sync + stxa %g2, [%o4] ASI_DMMU + sethi %hi(KERNBASE), %o4 + flush %o4 + retl + wrpr %g7, 0x0, %pstate + nop + nop + nop + nop + + .align 32 .globl __flush_tlb_pending __flush_tlb_pending: /* 26 insns */ /* %o0 = context, %o1 = nr, %o2 = vaddrs[] */ @@ -203,6 +230,31 @@ __cheetah_flush_tlb_mm: /* 19 insns */ retl wrpr %g7, 0x0, %pstate +__cheetah_flush_tlb_page: /* 22 insns */ + /* %o0 = context, %o1 = vaddr */ + rdpr %pstate, %g7 + andn %g7, PSTATE_IE, %g2 + wrpr %g2, 0x0, %pstate + wrpr %g0, 1, %tl + mov PRIMARY_CONTEXT, %o4 + ldxa [%o4] ASI_DMMU, %g2 + srlx %g2, CTX_PGSZ1_NUC_SHIFT, %o3 + sllx %o3, CTX_PGSZ1_NUC_SHIFT, %o3 + or %o0, %o3, %o0 /* Preserve nucleus page size fields */ + stxa %o0, [%o4] ASI_DMMU + andcc %o1, 1, %g0 + be,pn %icc, 1f + andn %o1, 1, %o3 + stxa %g0, [%o3] ASI_IMMU_DEMAP +1: stxa %g0, [%o3] ASI_DMMU_DEMAP + membar #Sync + stxa %g2, [%o4] ASI_DMMU + sethi %hi(KERNBASE), %o4 + flush %o4 + wrpr %g0, 0, %tl + retl + wrpr %g7, 0x0, %pstate + __cheetah_flush_tlb_pending: /* 27 insns */ /* %o0 = context, %o1 = nr, %o2 = vaddrs[] */ rdpr %pstate, %g7 @@ -269,6 +321,20 @@ __hypervisor_flush_tlb_mm: /* 10 insns */ retl nop +__hypervisor_flush_tlb_page: /* 11 insns */ + /* %o0 = context, %o1 = vaddr */ + mov %o0, %g2 + mov %o1, %o0 /* ARG0: vaddr + IMMU-bit */ + mov %g2, %o1 /* ARG1: mmu context */ + mov HV_MMU_ALL, %o2 /* ARG2: flags */ + srlx %o0, PAGE_SHIFT, %o0 + sllx %o0, PAGE_SHIFT, %o0 + ta HV_MMU_UNMAP_ADDR_TRAP + brnz,pn %o0, __hypervisor_tlb_tl0_error + mov HV_MMU_UNMAP_ADDR_TRAP, %o1 + retl + nop + __hypervisor_flush_tlb_pending: /* 16 insns */ /* %o0 = context, %o1 = nr, %o2 = vaddrs[] */ sllx %o1, 3, %g1 @@ -339,6 +405,13 @@ cheetah_patch_cachetlbops: call tlb_patch_one mov 19, %o2 + sethi %hi(__flush_tlb_page), %o0 + or %o0, %lo(__flush_tlb_page), %o0 + sethi %hi(__cheetah_flush_tlb_page), %o1 + or %o1, %lo(__cheetah_flush_tlb_page), %o1 + call tlb_patch_one + mov 22, %o2 + sethi %hi(__flush_tlb_pending), %o0 or %o0, %lo(__flush_tlb_pending), %o0 sethi %hi(__cheetah_flush_tlb_pending), %o1 @@ -397,10 +470,9 @@ xcall_flush_tlb_mm: /* 21 insns */ nop nop - .globl xcall_flush_tlb_pending -xcall_flush_tlb_pending: /* 21 insns */ - /* %g5=context, %g1=nr, %g7=vaddrs[] */ - sllx %g1, 3, %g1 + .globl xcall_flush_tlb_page +xcall_flush_tlb_page: /* 17 insns */ + /* %g5=context, %g1=vaddr */ mov PRIMARY_CONTEXT, %g4 ldxa [%g4] ASI_DMMU, %g2 srlx %g2, CTX_PGSZ1_NUC_SHIFT, %g4 @@ -408,20 +480,16 @@ xcall_flush_tlb_pending: /* 21 insns */ or %g5, %g4, %g5 mov PRIMARY_CONTEXT, %g4 stxa %g5, [%g4] ASI_DMMU -1: sub %g1, (1 << 3), %g1 - ldx [%g7 + %g1], %g5 - andcc %g5, 0x1, %g0 + andcc %g1, 0x1, %g0 be,pn %icc, 2f - - andn %g5, 0x1, %g5 + andn %g1, 0x1, %g5 stxa %g0, [%g5] ASI_IMMU_DEMAP 2: stxa %g0, [%g5] ASI_DMMU_DEMAP membar #Sync - brnz,pt %g1, 1b - nop stxa %g2, [%g4] ASI_DMMU retry nop + nop .globl xcall_flush_tlb_kernel_range xcall_flush_tlb_kernel_range: /* 25 insns */ @@ -656,15 +724,13 @@ __hypervisor_xcall_flush_tlb_mm: /* 21 insns */ membar #Sync retry - .globl __hypervisor_xcall_flush_tlb_pending -__hypervisor_xcall_flush_tlb_pending: /* 21 insns */ - /* %g5=ctx, %g1=nr, %g7=vaddrs[], %g2,%g3,%g4,g6=scratch */ - sllx %g1, 3, %g1 + .globl __hypervisor_xcall_flush_tlb_page +__hypervisor_xcall_flush_tlb_page: /* 17 insns */ + /* %g5=ctx, %g1=vaddr */ mov %o0, %g2 mov %o1, %g3 mov %o2, %g4 -1: sub %g1, (1 << 3), %g1 - ldx [%g7 + %g1], %o0 /* ARG0: virtual address */ + mov %g1, %o0 /* ARG0: virtual address */ mov %g5, %o1 /* ARG1: mmu context */ mov HV_MMU_ALL, %o2 /* ARG2: flags */ srlx %o0, PAGE_SHIFT, %o0 @@ -673,8 +739,6 @@ __hypervisor_xcall_flush_tlb_pending: /* 21 insns */ mov HV_MMU_UNMAP_ADDR_TRAP, %g6 brnz,a,pn %o0, __hypervisor_tlb_xcall_error mov %o0, %g5 - brnz,pt %g1, 1b - nop mov %g2, %o0 mov %g3, %o1 mov %g4, %o2 @@ -757,6 +821,13 @@ hypervisor_patch_cachetlbops: call tlb_patch_one mov 10, %o2 + sethi %hi(__flush_tlb_page), %o0 + or %o0, %lo(__flush_tlb_page), %o0 + sethi %hi(__hypervisor_flush_tlb_page), %o1 + or %o1, %lo(__hypervisor_flush_tlb_page), %o1 + call tlb_patch_one + mov 11, %o2 + sethi %hi(__flush_tlb_pending), %o0 or %o0, %lo(__flush_tlb_pending), %o0 sethi %hi(__hypervisor_flush_tlb_pending), %o1 @@ -788,12 +859,12 @@ hypervisor_patch_cachetlbops: call tlb_patch_one mov 21, %o2 - sethi %hi(xcall_flush_tlb_pending), %o0 - or %o0, %lo(xcall_flush_tlb_pending), %o0 - sethi %hi(__hypervisor_xcall_flush_tlb_pending), %o1 - or %o1, %lo(__hypervisor_xcall_flush_tlb_pending), %o1 + sethi %hi(xcall_flush_tlb_page), %o0 + or %o0, %lo(xcall_flush_tlb_page), %o0 + sethi %hi(__hypervisor_xcall_flush_tlb_page), %o1 + or %o1, %lo(__hypervisor_xcall_flush_tlb_page), %o1 call tlb_patch_one - mov 21, %o2 + mov 17, %o2 sethi %hi(xcall_flush_tlb_kernel_range), %o0 or %o0, %lo(xcall_flush_tlb_kernel_range), %o0 diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 70c0f3da047..15b5cef4aa3 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1549,6 +1549,7 @@ config X86_SMAP config EFI bool "EFI runtime service support" depends on ACPI + select UCS2_STRING ---help--- This enables the kernel to use EFI runtime services that are available (such as the EFI variable services). diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index c205035a6b9..35ee62fccf9 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -251,6 +251,51 @@ static void find_bits(unsigned long mask, u8 *pos, u8 *size) *size = len; } +static efi_status_t setup_efi_vars(struct boot_params *params) +{ + struct setup_data *data; + struct efi_var_bootdata *efidata; + u64 store_size, remaining_size, var_size; + efi_status_t status; + + if (sys_table->runtime->hdr.revision < EFI_2_00_SYSTEM_TABLE_REVISION) + return EFI_UNSUPPORTED; + + data = (struct setup_data *)(unsigned long)params->hdr.setup_data; + + while (data && data->next) + data = (struct setup_data *)(unsigned long)data->next; + + status = efi_call_phys4((void *)sys_table->runtime->query_variable_info, + EFI_VARIABLE_NON_VOLATILE | + EFI_VARIABLE_BOOTSERVICE_ACCESS | + EFI_VARIABLE_RUNTIME_ACCESS, &store_size, + &remaining_size, &var_size); + + if (status != EFI_SUCCESS) + return status; + + status = efi_call_phys3(sys_table->boottime->allocate_pool, + EFI_LOADER_DATA, sizeof(*efidata), &efidata); + + if (status != EFI_SUCCESS) + return status; + + efidata->data.type = SETUP_EFI_VARS; + efidata->data.len = sizeof(struct efi_var_bootdata) - + sizeof(struct setup_data); + efidata->data.next = 0; + efidata->store_size = store_size; + efidata->remaining_size = remaining_size; + efidata->max_var_size = var_size; + + if (data) + data->next = (unsigned long)efidata; + else + params->hdr.setup_data = (unsigned long)efidata; + +} + static efi_status_t setup_efi_pci(struct boot_params *params) { efi_pci_io_protocol *pci; @@ -1157,6 +1202,8 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table, setup_graphics(boot_params); + setup_efi_vars(boot_params); + setup_efi_pci(boot_params); status = efi_call_phys3(sys_table->boottime->allocate_pool, diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 60c89f30c72..2fb5d5884e2 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -102,6 +102,13 @@ extern void efi_call_phys_epilog(void); extern void efi_unmap_memmap(void); extern void efi_memory_uc(u64 addr, unsigned long size); +struct efi_var_bootdata { + struct setup_data data; + u64 store_size; + u64 remaining_size; + u64 max_var_size; +}; + #ifdef CONFIG_EFI static inline bool efi_is_native(void) diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index c15ddaf9071..08744242b8d 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -6,6 +6,7 @@ #define SETUP_E820_EXT 1 #define SETUP_DTB 2 #define SETUP_PCI 3 +#define SETUP_EFI_VARS 4 /* ram_size flags */ #define RAMDISK_IMAGE_START_MASK 0x07FF diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index a7d26d83fb7..8f4be53ea04 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -35,13 +35,6 @@ static bool __init ms_hyperv_platform(void) if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) return false; - /* - * Xen emulates Hyper-V to support enlightened Windows. - * Check to see first if we are on a Xen Hypervisor. - */ - if (xen_cpuid_base()) - return false; - cpuid(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS, &eax, &hyp_signature[0], &hyp_signature[1], &hyp_signature[2]); @@ -82,12 +75,6 @@ static void __init ms_hyperv_init_platform(void) if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE) clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100); -#if IS_ENABLED(CONFIG_HYPERV) - /* - * Setup the IDT for hypervisor callback. - */ - alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector); -#endif } const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = { @@ -103,6 +90,11 @@ static irq_handler_t vmbus_isr; void hv_register_vmbus_handler(int irq, irq_handler_t handler) { + /* + * Setup the IDT for hypervisor callback. + */ + alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector); + vmbus_irq = irq; vmbus_isr = handler; } diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index dab7580c47a..cc45deb791b 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -153,8 +153,14 @@ static struct event_constraint intel_gen_event_constraints[] __read_mostly = }; static struct extra_reg intel_snb_extra_regs[] __read_mostly = { - INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0), - INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1), + INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0), + INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3f807f8fffull, RSP_1), + EVENT_EXTRA_END +}; + +static struct extra_reg intel_snbep_extra_regs[] __read_mostly = { + INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0), + INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1), EVENT_EXTRA_END }; @@ -2097,7 +2103,10 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_snb_event_constraints; x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints; x86_pmu.pebs_aliases = intel_pebs_aliases_snb; - x86_pmu.extra_regs = intel_snb_extra_regs; + if (boot_cpu_data.x86_model == 45) + x86_pmu.extra_regs = intel_snbep_extra_regs; + else + x86_pmu.extra_regs = intel_snb_extra_regs; /* all extra regs are per-cpu when HT is on */ x86_pmu.er_flags |= ERF_HAS_RSP_1; x86_pmu.er_flags |= ERF_NO_HT_SHARING; @@ -2123,7 +2132,10 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_ivb_event_constraints; x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints; x86_pmu.pebs_aliases = intel_pebs_aliases_snb; - x86_pmu.extra_regs = intel_snb_extra_regs; + if (boot_cpu_data.x86_model == 62) + x86_pmu.extra_regs = intel_snbep_extra_regs; + else + x86_pmu.extra_regs = intel_snb_extra_regs; /* all extra regs are per-cpu when HT is on */ x86_pmu.er_flags |= ERF_HAS_RSP_1; x86_pmu.er_flags |= ERF_NO_HT_SHARING; diff --git a/arch/x86/kernel/microcode_core_early.c b/arch/x86/kernel/microcode_core_early.c index 577db8417d1..833d51d6ee0 100644 --- a/arch/x86/kernel/microcode_core_early.c +++ b/arch/x86/kernel/microcode_core_early.c @@ -45,9 +45,6 @@ static int __cpuinit x86_vendor(void) u32 eax = 0x00000000; u32 ebx, ecx = 0, edx; - if (!have_cpuid_p()) - return X86_VENDOR_UNKNOWN; - native_cpuid(&eax, &ebx, &ecx, &edx); if (CPUID_IS(CPUID_INTEL1, CPUID_INTEL2, CPUID_INTEL3, ebx, ecx, edx)) @@ -59,18 +56,45 @@ static int __cpuinit x86_vendor(void) return X86_VENDOR_UNKNOWN; } +static int __cpuinit x86_family(void) +{ + u32 eax = 0x00000001; + u32 ebx, ecx = 0, edx; + int x86; + + native_cpuid(&eax, &ebx, &ecx, &edx); + + x86 = (eax >> 8) & 0xf; + if (x86 == 15) + x86 += (eax >> 20) & 0xff; + + return x86; +} + void __init load_ucode_bsp(void) { - int vendor = x86_vendor(); + int vendor, x86; + + if (!have_cpuid_p()) + return; - if (vendor == X86_VENDOR_INTEL) + vendor = x86_vendor(); + x86 = x86_family(); + + if (vendor == X86_VENDOR_INTEL && x86 >= 6) load_ucode_intel_bsp(); } void __cpuinit load_ucode_ap(void) { - int vendor = x86_vendor(); + int vendor, x86; + + if (!have_cpuid_p()) + return; + + vendor = x86_vendor(); + x86 = x86_family(); - if (vendor == X86_VENDOR_INTEL) + if (vendor == X86_VENDOR_INTEL && x86 >= 6) load_ucode_intel_ap(); } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 90d8cc930f5..fae9134a2de 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -507,11 +507,14 @@ static void __init memblock_x86_reserve_range_setup_data(void) /* * Keep the crash kernel below this limit. On 32 bits earlier kernels * would limit the kernel to the low 512 MiB due to mapping restrictions. + * On 64bit, old kexec-tools need to under 896MiB. */ #ifdef CONFIG_X86_32 -# define CRASH_KERNEL_ADDR_MAX (512 << 20) +# define CRASH_KERNEL_ADDR_LOW_MAX (512 << 20) +# define CRASH_KERNEL_ADDR_HIGH_MAX (512 << 20) #else -# define CRASH_KERNEL_ADDR_MAX MAXMEM +# define CRASH_KERNEL_ADDR_LOW_MAX (896UL<<20) +# define CRASH_KERNEL_ADDR_HIGH_MAX MAXMEM #endif static void __init reserve_crashkernel_low(void) @@ -521,19 +524,35 @@ static void __init reserve_crashkernel_low(void) unsigned long long low_base = 0, low_size = 0; unsigned long total_low_mem; unsigned long long base; + bool auto_set = false; int ret; total_low_mem = memblock_mem_size(1UL<<(32-PAGE_SHIFT)); + /* crashkernel=Y,low */ ret = parse_crashkernel_low(boot_command_line, total_low_mem, &low_size, &base); - if (ret != 0 || low_size <= 0) - return; + if (ret != 0) { + /* + * two parts from lib/swiotlb.c: + * swiotlb size: user specified with swiotlb= or default. + * swiotlb overflow buffer: now is hardcoded to 32k. + * We round it to 8M for other buffers that + * may need to stay low too. + */ + low_size = swiotlb_size_or_default() + (8UL<<20); + auto_set = true; + } else { + /* passed with crashkernel=0,low ? */ + if (!low_size) + return; + } low_base = memblock_find_in_range(low_size, (1ULL<<32), low_size, alignment); if (!low_base) { - pr_info("crashkernel low reservation failed - No suitable area found.\n"); + if (!auto_set) + pr_info("crashkernel low reservation failed - No suitable area found.\n"); return; } @@ -554,14 +573,22 @@ static void __init reserve_crashkernel(void) const unsigned long long alignment = 16<<20; /* 16M */ unsigned long long total_mem; unsigned long long crash_size, crash_base; + bool high = false; int ret; total_mem = memblock_phys_mem_size(); + /* crashkernel=XM */ ret = parse_crashkernel(boot_command_line, total_mem, &crash_size, &crash_base); - if (ret != 0 || crash_size <= 0) - return; + if (ret != 0 || crash_size <= 0) { + /* crashkernel=X,high */ + ret = parse_crashkernel_high(boot_command_line, total_mem, + &crash_size, &crash_base); + if (ret != 0 || crash_size <= 0) + return; + high = true; + } /* 0 means: find the address automatically */ if (crash_base <= 0) { @@ -569,7 +596,9 @@ static void __init reserve_crashkernel(void) * kexec want bzImage is below CRASH_KERNEL_ADDR_MAX */ crash_base = memblock_find_in_range(alignment, - CRASH_KERNEL_ADDR_MAX, crash_size, alignment); + high ? CRASH_KERNEL_ADDR_HIGH_MAX : + CRASH_KERNEL_ADDR_LOW_MAX, + crash_size, alignment); if (!crash_base) { pr_info("crashkernel reservation failed - No suitable area found.\n"); diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 901177d75ff..305c68b8d53 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -6,6 +6,7 @@ #include <linux/sched.h> #include <linux/pci.h> +#include <linux/pci-acpi.h> #include <linux/ioport.h> #include <linux/init.h> #include <linux/dmi.h> @@ -170,6 +171,16 @@ void pcibios_fixup_bus(struct pci_bus *b) pcibios_fixup_device_resources(dev); } +void pcibios_add_bus(struct pci_bus *bus) +{ + acpi_pci_add_bus(bus); +} + +void pcibios_remove_bus(struct pci_bus *bus) +{ + acpi_pci_remove_bus(bus); +} + /* * Only use DMI information to set this if nothing was passed * on the kernel command line (which was parsed earlier). diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 94e76620460..4a9be6ddf05 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -177,7 +177,7 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) goto error; i = 0; list_for_each_entry(msidesc, &dev->msi_list, list) { - irq = xen_bind_pirq_msi_to_irq(dev, msidesc, v[i], 0, + irq = xen_bind_pirq_msi_to_irq(dev, msidesc, v[i], (type == PCI_CAP_ID_MSIX) ? "pcifront-msi-x" : "pcifront-msi", @@ -244,7 +244,7 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) dev_dbg(&dev->dev, "xen: msi already bound to pirq=%d\n", pirq); } - irq = xen_bind_pirq_msi_to_irq(dev, msidesc, pirq, 0, + irq = xen_bind_pirq_msi_to_irq(dev, msidesc, pirq, (type == PCI_CAP_ID_MSIX) ? "msi-x" : "msi", DOMID_SELF); @@ -326,7 +326,7 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) } ret = xen_bind_pirq_msi_to_irq(dev, msidesc, - map_irq.pirq, map_irq.index, + map_irq.pirq, (type == PCI_CAP_ID_MSIX) ? "msi-x" : "msi", domid); diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 5f2ecaf3f9d..e4a86a677ce 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -41,6 +41,7 @@ #include <linux/io.h> #include <linux/reboot.h> #include <linux/bcd.h> +#include <linux/ucs2_string.h> #include <asm/setup.h> #include <asm/efi.h> @@ -51,6 +52,13 @@ #define EFI_DEBUG 1 +/* + * There's some additional metadata associated with each + * variable. Intel's reference implementation is 60 bytes - bump that + * to account for potential alignment constraints + */ +#define VAR_METADATA_SIZE 64 + struct efi __read_mostly efi = { .mps = EFI_INVALID_TABLE_ADDR, .acpi = EFI_INVALID_TABLE_ADDR, @@ -69,6 +77,13 @@ struct efi_memory_map memmap; static struct efi efi_phys __initdata; static efi_system_table_t efi_systab __initdata; +static u64 efi_var_store_size; +static u64 efi_var_remaining_size; +static u64 efi_var_max_var_size; +static u64 boot_used_size; +static u64 boot_var_size; +static u64 active_size; + unsigned long x86_efi_facility; /* @@ -98,6 +113,15 @@ static int __init setup_add_efi_memmap(char *arg) } early_param("add_efi_memmap", setup_add_efi_memmap); +static bool efi_no_storage_paranoia; + +static int __init setup_storage_paranoia(char *arg) +{ + efi_no_storage_paranoia = true; + return 0; +} +early_param("efi_no_storage_paranoia", setup_storage_paranoia); + static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc) { @@ -162,8 +186,53 @@ static efi_status_t virt_efi_get_next_variable(unsigned long *name_size, efi_char16_t *name, efi_guid_t *vendor) { - return efi_call_virt3(get_next_variable, - name_size, name, vendor); + efi_status_t status; + static bool finished = false; + static u64 var_size; + + status = efi_call_virt3(get_next_variable, + name_size, name, vendor); + + if (status == EFI_NOT_FOUND) { + finished = true; + if (var_size < boot_used_size) { + boot_var_size = boot_used_size - var_size; + active_size += boot_var_size; + } else { + printk(KERN_WARNING FW_BUG "efi: Inconsistent initial sizes\n"); + } + } + + if (boot_used_size && !finished) { + unsigned long size; + u32 attr; + efi_status_t s; + void *tmp; + + s = virt_efi_get_variable(name, vendor, &attr, &size, NULL); + + if (s != EFI_BUFFER_TOO_SMALL || !size) + return status; + + tmp = kmalloc(size, GFP_ATOMIC); + + if (!tmp) + return status; + + s = virt_efi_get_variable(name, vendor, &attr, &size, tmp); + + if (s == EFI_SUCCESS && (attr & EFI_VARIABLE_NON_VOLATILE)) { + var_size += size; + var_size += ucs2_strsize(name, 1024); + active_size += size; + active_size += VAR_METADATA_SIZE; + active_size += ucs2_strsize(name, 1024); + } + + kfree(tmp); + } + + return status; } static efi_status_t virt_efi_set_variable(efi_char16_t *name, @@ -172,9 +241,34 @@ static efi_status_t virt_efi_set_variable(efi_char16_t *name, unsigned long data_size, void *data) { - return efi_call_virt5(set_variable, - name, vendor, attr, - data_size, data); + efi_status_t status; + u32 orig_attr = 0; + unsigned long orig_size = 0; + + status = virt_efi_get_variable(name, vendor, &orig_attr, &orig_size, + NULL); + + if (status != EFI_BUFFER_TOO_SMALL) + orig_size = 0; + + status = efi_call_virt5(set_variable, + name, vendor, attr, + data_size, data); + + if (status == EFI_SUCCESS) { + if (orig_size) { + active_size -= orig_size; + active_size -= ucs2_strsize(name, 1024); + active_size -= VAR_METADATA_SIZE; + } + if (data_size) { + active_size += data_size; + active_size += ucs2_strsize(name, 1024); + active_size += VAR_METADATA_SIZE; + } + } + + return status; } static efi_status_t virt_efi_query_variable_info(u32 attr, @@ -682,6 +776,9 @@ void __init efi_init(void) char vendor[100] = "unknown"; int i = 0; void *tmp; + struct setup_data *data; + struct efi_var_bootdata *efi_var_data; + u64 pa_data; #ifdef CONFIG_X86_32 if (boot_params.efi_info.efi_systab_hi || @@ -699,6 +796,22 @@ void __init efi_init(void) if (efi_systab_init(efi_phys.systab)) return; + pa_data = boot_params.hdr.setup_data; + while (pa_data) { + data = early_ioremap(pa_data, sizeof(*efi_var_data)); + if (data->type == SETUP_EFI_VARS) { + efi_var_data = (struct efi_var_bootdata *)data; + + efi_var_store_size = efi_var_data->store_size; + efi_var_remaining_size = efi_var_data->remaining_size; + efi_var_max_var_size = efi_var_data->max_var_size; + } + pa_data = data->next; + early_iounmap(data, sizeof(*efi_var_data)); + } + + boot_used_size = efi_var_store_size - efi_var_remaining_size; + set_bit(EFI_SYSTEM_TABLES, &x86_efi_facility); /* @@ -999,3 +1112,48 @@ u64 efi_mem_attributes(unsigned long phys_addr) } return 0; } + +/* + * Some firmware has serious problems when using more than 50% of the EFI + * variable store, i.e. it triggers bugs that can brick machines. Ensure that + * we never use more than this safe limit. + * + * Return EFI_SUCCESS if it is safe to write 'size' bytes to the variable + * store. + */ +efi_status_t efi_query_variable_store(u32 attributes, unsigned long size) +{ + efi_status_t status; + u64 storage_size, remaining_size, max_size; + + status = efi.query_variable_info(attributes, &storage_size, + &remaining_size, &max_size); + if (status != EFI_SUCCESS) + return status; + + if (!max_size && remaining_size > size) + printk_once(KERN_ERR FW_BUG "Broken EFI implementation" + " is returning MaxVariableSize=0\n"); + /* + * Some firmware implementations refuse to boot if there's insufficient + * space in the variable store. We account for that by refusing the + * write if permitting it would reduce the available space to under + * 50%. However, some firmware won't reclaim variable space until + * after the used (not merely the actively used) space drops below + * a threshold. We can approximate that case with the value calculated + * above. If both the firmware and our calculations indicate that the + * available space would drop below 50%, refuse the write. + */ + + if (!storage_size || size > remaining_size || + (max_size && size > max_size)) + return EFI_OUT_OF_RESOURCES; + + if (!efi_no_storage_paranoia && + ((active_size + size + VAR_METADATA_SIZE > storage_size / 2) && + (remaining_size - size < storage_size / 2))) + return EFI_OUT_OF_RESOURCES; + + return EFI_SUCCESS; +} +EXPORT_SYMBOL_GPL(efi_query_variable_store); diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index c8e1c7b95c3..ddbd54a9b84 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -31,6 +31,7 @@ #include <linux/pci.h> #include <linux/gfp.h> #include <linux/memblock.h> +#include <linux/edd.h> #include <xen/xen.h> #include <xen/events.h> @@ -1306,6 +1307,55 @@ static const struct machine_ops xen_machine_ops __initconst = { .emergency_restart = xen_emergency_restart, }; +static void __init xen_boot_params_init_edd(void) +{ +#if IS_ENABLED(CONFIG_EDD) + struct xen_platform_op op; + struct edd_info *edd_info; + u32 *mbr_signature; + unsigned nr; + int ret; + + edd_info = boot_params.eddbuf; + mbr_signature = boot_params.edd_mbr_sig_buffer; + + op.cmd = XENPF_firmware_info; + + op.u.firmware_info.type = XEN_FW_DISK_INFO; + for (nr = 0; nr < EDDMAXNR; nr++) { + struct edd_info *info = edd_info + nr; + + op.u.firmware_info.index = nr; + info->params.length = sizeof(info->params); + set_xen_guest_handle(op.u.firmware_info.u.disk_info.edd_params, + &info->params); + ret = HYPERVISOR_dom0_op(&op); + if (ret) + break; + +#define C(x) info->x = op.u.firmware_info.u.disk_info.x + C(device); + C(version); + C(interface_support); + C(legacy_max_cylinder); + C(legacy_max_head); + C(legacy_sectors_per_track); +#undef C + } + boot_params.eddbuf_entries = nr; + + op.u.firmware_info.type = XEN_FW_DISK_MBR_SIGNATURE; + for (nr = 0; nr < EDD_MBR_SIG_MAX; nr++) { + op.u.firmware_info.index = nr; + ret = HYPERVISOR_dom0_op(&op); + if (ret) + break; + mbr_signature[nr] = op.u.firmware_info.u.disk_mbr_signature.mbr_signature; + } + boot_params.edd_mbr_sig_buf_entries = nr; +#endif +} + /* * Set up the GDT and segment registers for -fstack-protector. Until * we do this, we have to be careful not to call any stack-protected @@ -1508,6 +1558,8 @@ asmlinkage void __init xen_start_kernel(void) /* Avoid searching for BIOS MP tables */ x86_init.mpparse.find_smp_config = x86_init_noop; x86_init.mpparse.get_smp_config = x86_init_uint_noop; + + xen_boot_params_init_edd(); } #ifdef CONFIG_PCI /* PCI BIOS service won't work from a PV guest. */ @@ -1589,8 +1641,11 @@ static int __cpuinit xen_hvm_cpu_notify(struct notifier_block *self, switch (action) { case CPU_UP_PREPARE: xen_vcpu_setup(cpu); - if (xen_have_vector_callback) + if (xen_have_vector_callback) { xen_init_lock_cpu(cpu); + if (xen_feature(XENFEAT_hvm_safe_pvclock)) + xen_setup_timer(cpu); + } break; default: break; diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 09ea61d2e02..0d466d7c717 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -144,6 +144,13 @@ static int xen_smp_intr_init(unsigned int cpu) goto fail; per_cpu(xen_callfuncsingle_irq, cpu) = rc; + /* + * The IRQ worker on PVHVM goes through the native path and uses the + * IPI mechanism. + */ + if (xen_hvm_domain()) + return 0; + callfunc_name = kasprintf(GFP_KERNEL, "irqwork%d", cpu); rc = bind_ipi_to_irqhandler(XEN_IRQ_WORK_VECTOR, cpu, @@ -167,6 +174,9 @@ static int xen_smp_intr_init(unsigned int cpu) if (per_cpu(xen_callfuncsingle_irq, cpu) >= 0) unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu), NULL); + if (xen_hvm_domain()) + return rc; + if (per_cpu(xen_irq_work, cpu) >= 0) unbind_from_irqhandler(per_cpu(xen_irq_work, cpu), NULL); @@ -418,7 +428,7 @@ static int xen_cpu_disable(void) static void xen_cpu_die(unsigned int cpu) { - while (HYPERVISOR_vcpu_op(VCPUOP_is_up, cpu, NULL)) { + while (xen_pv_domain() && HYPERVISOR_vcpu_op(VCPUOP_is_up, cpu, NULL)) { current->state = TASK_UNINTERRUPTIBLE; schedule_timeout(HZ/10); } @@ -426,7 +436,8 @@ static void xen_cpu_die(unsigned int cpu) unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu), NULL); unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu), NULL); unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu), NULL); - unbind_from_irqhandler(per_cpu(xen_irq_work, cpu), NULL); + if (!xen_hvm_domain()) + unbind_from_irqhandler(per_cpu(xen_irq_work, cpu), NULL); xen_uninit_lock_cpu(cpu); xen_teardown_timer(cpu); } @@ -657,11 +668,7 @@ static int __cpuinit xen_hvm_cpu_up(unsigned int cpu, struct task_struct *tidle) static void xen_hvm_cpu_die(unsigned int cpu) { - unbind_from_irqhandler(per_cpu(xen_resched_irq, cpu), NULL); - unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu), NULL); - unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu), NULL); - unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu), NULL); - unbind_from_irqhandler(per_cpu(xen_irq_work, cpu), NULL); + xen_cpu_die(cpu); native_cpu_die(cpu); } diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index f7a080ef035..8b54603ce81 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -364,6 +364,16 @@ void __cpuinit xen_init_lock_cpu(int cpu) int irq; const char *name; + WARN(per_cpu(lock_kicker_irq, cpu) > 0, "spinlock on CPU%d exists on IRQ%d!\n", + cpu, per_cpu(lock_kicker_irq, cpu)); + + /* + * See git commit f10cd522c5fbfec9ae3cc01967868c9c2401ed23 + * (xen: disable PV spinlocks on HVM) + */ + if (xen_hvm_domain()) + return; + name = kasprintf(GFP_KERNEL, "spinlock%d", cpu); irq = bind_ipi_to_irqhandler(XEN_SPIN_UNLOCK_VECTOR, cpu, @@ -382,11 +392,26 @@ void __cpuinit xen_init_lock_cpu(int cpu) void xen_uninit_lock_cpu(int cpu) { + /* + * See git commit f10cd522c5fbfec9ae3cc01967868c9c2401ed23 + * (xen: disable PV spinlocks on HVM) + */ + if (xen_hvm_domain()) + return; + unbind_from_irqhandler(per_cpu(lock_kicker_irq, cpu), NULL); + per_cpu(lock_kicker_irq, cpu) = -1; } void __init xen_init_spinlocks(void) { + /* + * See git commit f10cd522c5fbfec9ae3cc01967868c9c2401ed23 + * (xen: disable PV spinlocks on HVM) + */ + if (xen_hvm_domain()) + return; + BUILD_BUG_ON(sizeof(struct xen_spinlock) > sizeof(arch_spinlock_t)); pv_lock_ops.spin_is_locked = xen_spin_is_locked; diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index 0296a952250..3d88bfdf9e1 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -377,7 +377,7 @@ static const struct clock_event_device xen_vcpuop_clockevent = { static const struct clock_event_device *xen_clockevent = &xen_timerop_clockevent; -static DEFINE_PER_CPU(struct clock_event_device, xen_clock_events); +static DEFINE_PER_CPU(struct clock_event_device, xen_clock_events) = { .irq = -1 }; static irqreturn_t xen_timer_interrupt(int irq, void *dev_id) { @@ -401,6 +401,9 @@ void xen_setup_timer(int cpu) struct clock_event_device *evt; int irq; + evt = &per_cpu(xen_clock_events, cpu); + WARN(evt->irq >= 0, "IRQ%d for CPU%d is already allocated\n", evt->irq, cpu); + printk(KERN_INFO "installing Xen timer for CPU %d\n", cpu); name = kasprintf(GFP_KERNEL, "timer%d", cpu); @@ -413,7 +416,6 @@ void xen_setup_timer(int cpu) IRQF_FORCE_RESUME, name, NULL); - evt = &per_cpu(xen_clock_events, cpu); memcpy(evt, xen_clockevent, sizeof(*evt)); evt->cpumask = cpumask_of(cpu); @@ -426,6 +428,7 @@ void xen_teardown_timer(int cpu) BUG_ON(cpu == 0); evt = &per_cpu(xen_clock_events, cpu); unbind_from_irqhandler(evt->irq, NULL); + evt->irq = -1; } void xen_setup_cpu_clockevents(void) @@ -497,7 +500,11 @@ static void xen_hvm_setup_cpu_clockevents(void) { int cpu = smp_processor_id(); xen_setup_runstate_info(cpu); - xen_setup_timer(cpu); + /* + * xen_setup_timer(cpu) - snprintf is bad in atomic context. Hence + * doing it xen_hvm_cpu_notify (which gets called by smp_init during + * early bootup and also during CPU hotplug events). + */ xen_setup_cpu_clockevents(); } |