diff options
Diffstat (limited to 'arch')
104 files changed, 1489 insertions, 1697 deletions
diff --git a/arch/alpha/include/asm/futex.h b/arch/alpha/include/asm/futex.h index e8a761a..f939794 100644 --- a/arch/alpha/include/asm/futex.h +++ b/arch/alpha/include/asm/futex.h @@ -108,7 +108,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, " lda $31,3b-2b(%0)\n" " .previous\n" : "+r"(ret), "=&r"(prev), "=&r"(cmp) - : "r"(uaddr), "r"((long)oldval), "r"(newval) + : "r"(uaddr), "r"((long)(int)oldval), "r"(newval) : "memory"); *uval = prev; diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h index 29035e8..7bb8bf9 100644 --- a/arch/arm/include/asm/assembler.h +++ b/arch/arm/include/asm/assembler.h @@ -137,6 +137,11 @@ disable_irq .endm + .macro save_and_disable_irqs_notrace, oldcpsr + mrs \oldcpsr, cpsr + disable_irq_notrace + .endm + /* * Restore interrupt state previously stored in a register. We don't * guarantee that this will preserve the flags. diff --git a/arch/arm/include/asm/tls.h b/arch/arm/include/asm/tls.h index 60843eb..73409e6 100644 --- a/arch/arm/include/asm/tls.h +++ b/arch/arm/include/asm/tls.h @@ -7,6 +7,8 @@ .macro set_tls_v6k, tp, tmp1, tmp2 mcr p15, 0, \tp, c13, c0, 3 @ set TLS register + mov \tmp1, #0 + mcr p15, 0, \tmp1, c13, c0, 2 @ clear user r/w TLS register .endm .macro set_tls_v6, tp, tmp1, tmp2 @@ -15,6 +17,8 @@ mov \tmp2, #0xffff0fff tst \tmp1, #HWCAP_TLS @ hardware TLS available? mcrne p15, 0, \tp, c13, c0, 3 @ yes, set TLS register + movne \tmp1, #0 + mcrne p15, 0, \tmp1, c13, c0, 2 @ clear user r/w TLS register streq \tp, [\tmp2, #-15] @ set TLS value at 0xffff0ff0 .endm diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c index 9726006..172ae01 100644 --- a/arch/arm/kernel/ptrace.c +++ b/arch/arm/kernel/ptrace.c @@ -719,10 +719,13 @@ static int vfp_set(struct task_struct *target, { int ret; struct thread_info *thread = task_thread_info(target); - struct vfp_hard_struct new_vfp = thread->vfpstate.hard; + struct vfp_hard_struct new_vfp; const size_t user_fpregs_offset = offsetof(struct user_vfp, fpregs); const size_t user_fpscr_offset = offsetof(struct user_vfp, fpscr); + vfp_sync_hwstate(thread); + new_vfp = thread->vfpstate.hard; + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &new_vfp.fpregs, user_fpregs_offset, @@ -743,9 +746,8 @@ static int vfp_set(struct task_struct *target, if (ret) return ret; - vfp_sync_hwstate(thread); - thread->vfpstate.hard = new_vfp; vfp_flush_hwstate(thread); + thread->vfpstate.hard = new_vfp; return 0; } diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index 0340224..9e617bd 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -227,6 +227,8 @@ static int restore_vfp_context(struct vfp_sigframe __user *frame) if (magic != VFP_MAGIC || size != VFP_STORAGE_SIZE) return -EINVAL; + vfp_flush_hwstate(thread); + /* * Copy the floating point registers. There can be unused * registers see asm/hwcap.h for details. @@ -251,9 +253,6 @@ static int restore_vfp_context(struct vfp_sigframe __user *frame) __get_user_error(h->fpinst, &frame->ufp_exc.fpinst, err); __get_user_error(h->fpinst2, &frame->ufp_exc.fpinst2, err); - if (!err) - vfp_flush_hwstate(thread); - return err ? -EFAULT : 0; } diff --git a/arch/arm/mach-dove/common.c b/arch/arm/mach-dove/common.c index cf7e598..46c0449 100644 --- a/arch/arm/mach-dove/common.c +++ b/arch/arm/mach-dove/common.c @@ -31,6 +31,7 @@ #include <asm/mach/arch.h> #include <linux/irq.h> #include <plat/time.h> +#include <plat/ehci-orion.h> #include <plat/common.h> #include "common.h" @@ -74,7 +75,7 @@ void __init dove_map_io(void) void __init dove_ehci0_init(void) { orion_ehci_init(&dove_mbus_dram_info, - DOVE_USB0_PHYS_BASE, IRQ_DOVE_USB0); + DOVE_USB0_PHYS_BASE, IRQ_DOVE_USB0, EHCI_PHY_NA); } /***************************************************************************** diff --git a/arch/arm/mach-kirkwood/common.c b/arch/arm/mach-kirkwood/common.c index f3248cf..c5dbbb3 100644 --- a/arch/arm/mach-kirkwood/common.c +++ b/arch/arm/mach-kirkwood/common.c @@ -28,6 +28,7 @@ #include <plat/cache-feroceon-l2.h> #include <plat/mvsdio.h> #include <plat/orion_nand.h> +#include <plat/ehci-orion.h> #include <plat/common.h> #include <plat/time.h> #include "common.h" @@ -74,7 +75,7 @@ void __init kirkwood_ehci_init(void) { kirkwood_clk_ctrl |= CGC_USB0; orion_ehci_init(&kirkwood_mbus_dram_info, - USB_PHYS_BASE, IRQ_KIRKWOOD_USB); + USB_PHYS_BASE, IRQ_KIRKWOOD_USB, EHCI_PHY_NA); } diff --git a/arch/arm/mach-kirkwood/mpp.h b/arch/arm/mach-kirkwood/mpp.h index ac78795..7afccf4 100644 --- a/arch/arm/mach-kirkwood/mpp.h +++ b/arch/arm/mach-kirkwood/mpp.h @@ -31,313 +31,313 @@ #define MPP_F6282_MASK MPP( 0, 0x0, 0, 0, 0, 0, 0, 0, 1 ) #define MPP0_GPIO MPP( 0, 0x0, 1, 1, 1, 1, 1, 1, 1 ) -#define MPP0_NF_IO2 MPP( 0, 0x1, 1, 1, 1, 1, 1, 1, 1 ) -#define MPP0_SPI_SCn MPP( 0, 0x2, 0, 1, 1, 1, 1, 1, 1 ) +#define MPP0_NF_IO2 MPP( 0, 0x1, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP0_SPI_SCn MPP( 0, 0x2, 0, 0, 1, 1, 1, 1, 1 ) #define MPP1_GPO MPP( 1, 0x0, 0, 1, 1, 1, 1, 1, 1 ) -#define MPP1_NF_IO3 MPP( 1, 0x1, 1, 1, 1, 1, 1, 1, 1 ) -#define MPP1_SPI_MOSI MPP( 1, 0x2, 0, 1, 1, 1, 1, 1, 1 ) +#define MPP1_NF_IO3 MPP( 1, 0x1, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP1_SPI_MOSI MPP( 1, 0x2, 0, 0, 1, 1, 1, 1, 1 ) #define MPP2_GPO MPP( 2, 0x0, 0, 1, 1, 1, 1, 1, 1 ) -#define MPP2_NF_IO4 MPP( 2, 0x1, 1, 1, 1, 1, 1, 1, 1 ) -#define MPP2_SPI_SCK MPP( 2, 0x2, 0, 1, 1, 1, 1, 1, 1 ) +#define MPP2_NF_IO4 MPP( 2, 0x1, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP2_SPI_SCK MPP( 2, 0x2, 0, 0, 1, 1, 1, 1, 1 ) #define MPP3_GPO MPP( 3, 0x0, 0, 1, 1, 1, 1, 1, 1 ) -#define MPP3_NF_IO5 MPP( 3, 0x1, 1, 1, 1, 1, 1, 1, 1 ) -#define MPP3_SPI_MISO MPP( 3, 0x2, 1, 0, 1, 1, 1, 1, 1 ) +#define MPP3_NF_IO5 MPP( 3, 0x1, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP3_SPI_MISO MPP( 3, 0x2, 0, 0, 1, 1, 1, 1, 1 ) #define MPP4_GPIO MPP( 4, 0x0, 1, 1, 1, 1, 1, 1, 1 ) -#define MPP4_NF_IO6 MPP( 4, 0x1, 1, 1, 1, 1, 1, 1, 1 ) -#define MPP4_UART0_RXD MPP( 4, 0x2, 1, 0, 1, 1, 1, 1, 1 ) -#define MPP4_SATA1_ACTn MPP( 4, 0x5, 0, 1, 0, 0, 1, 1, 1 ) +#define MPP4_NF_IO6 MPP( 4, 0x1, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP4_UART0_RXD MPP( 4, 0x2, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP4_SATA1_ACTn MPP( 4, 0x5, 0, 0, 0, 0, 1, 1, 1 ) #define MPP4_LCD_VGA_HSYNC MPP( 4, 0xb, 0, 0, 0, 0, 0, 0, 1 ) -#define MPP4_PTP_CLK MPP( 4, 0xd, 1, 0, 1, 1, 1, 1, 0 ) +#define MPP4_PTP_CLK MPP( 4, 0xd, 0, 0, 1, 1, 1, 1, 0 ) #define MPP5_GPO MPP( 5, 0x0, 0, 1, 1, 1, 1, 1, 1 ) -#define MPP5_NF_IO7 MPP( 5, 0x1, 1, 1, 1, 1, 1, 1, 1 ) -#define MPP5_UART0_TXD MPP( 5, 0x2, 0, 1, 1, 1, 1, 1, 1 ) -#define MPP5_PTP_TRIG_GEN MPP( 5, 0x4, 0, 1, 1, 1, 1, 1, 0 ) -#define MPP5_SATA0_ACTn MPP( 5, 0x5, 0, 1, 0, 1, 1, 1, 1 ) +#define MPP5_NF_IO7 MPP( 5, 0x1, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP5_UART0_TXD MPP( 5, 0x2, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP5_PTP_TRIG_GEN MPP( 5, 0x4, 0, 0, 1, 1, 1, 1, 0 ) +#define MPP5_SATA0_ACTn MPP( 5, 0x5, 0, 0, 0, 1, 1, 1, 1 ) #define MPP5_LCD_VGA_VSYNC MPP( 5, 0xb, 0, 0, 0, 0, 0, 0, 1 ) -#define MPP6_SYSRST_OUTn MPP( 6, 0x1, 0, 1, 1, 1, 1, 1, 1 ) -#define MPP6_SPI_MOSI MPP( 6, 0x2, 0, 1, 1, 1, 1, 1, 1 ) -#define MPP6_PTP_TRIG_GEN MPP( 6, 0x3, 0, 1, 1, 1, 1, 1, 0 ) +#define MPP6_SYSRST_OUTn MPP( 6, 0x1, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP6_SPI_MOSI MPP( 6, 0x2, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP6_PTP_TRIG_GEN MPP( 6, 0x3, 0, 0, 1, 1, 1, 1, 0 ) #define MPP7_GPO MPP( 7, 0x0, 0, 1, 1, 1, 1, 1, 1 ) -#define MPP7_PEX_RST_OUTn MPP( 7, 0x1, 0, 1, 1, 1, 1, 1, 0 ) -#define MPP7_SPI_SCn MPP( 7, 0x2, 0, 1, 1, 1, 1, 1, 1 ) -#define MPP7_PTP_TRIG_GEN MPP( 7, 0x3, 0, 1, 1, 1, 1, 1, 0 ) -#define MPP7_LCD_PWM MPP( 7, 0xb, 0, 1, 0, 0, 0, 0, 1 ) +#define MPP7_PEX_RST_OUTn MPP( 7, 0x1, 0, 0, 1, 1, 1, 1, 0 ) +#define MPP7_SPI_SCn MPP( 7, 0x2, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP7_PTP_TRIG_GEN MPP( 7, 0x3, 0, 0, 1, 1, 1, 1, 0 ) +#define MPP7_LCD_PWM MPP( 7, 0xb, 0, 0, 0, 0, 0, 0, 1 ) #define MPP8_GPIO MPP( 8, 0x0, 1, 1, 1, 1, 1, 1, 1 ) -#define MPP8_TW0_SDA MPP( 8, 0x1, 1, 1, 1, 1, 1, 1, 1 ) -#define MPP8_UART0_RTS MPP( 8, 0x2, 0, 1, 1, 1, 1, 1, 1 ) -#define MPP8_UART1_RTS MPP( 8, 0x3, 0, 1, 1, 1, 1, 1, 1 ) -#define MPP8_MII0_RXERR MPP( 8, 0x4, 1, 0, 0, 1, 1, 1, 1 ) -#define MPP8_SATA1_PRESENTn MPP( 8, 0x5, 0, 1, 0, 0, 1, 1, 1 ) -#define MPP8_PTP_CLK MPP( 8, 0xc, 1, 0, 1, 1, 1, 1, 0 ) -#define MPP8_MII0_COL MPP( 8, 0xd, 1, 0, 1, 1, 1, 1, 1 ) +#define MPP8_TW0_SDA MPP( 8, 0x1, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP8_UART0_RTS MPP( 8, 0x2, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP8_UART1_RTS MPP( 8, 0x3, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP8_MII0_RXERR MPP( 8, 0x4, 0, 0, 0, 1, 1, 1, 1 ) +#define MPP8_SATA1_PRESENTn MPP( 8, 0x5, 0, 0, 0, 0, 1, 1, 1 ) +#define MPP8_PTP_CLK MPP( 8, 0xc, 0, 0, 1, 1, 1, 1, 0 ) +#define MPP8_MII0_COL MPP( 8, 0xd, 0, 0, 1, 1, 1, 1, 1 ) #define MPP9_GPIO MPP( 9, 0x0, 1, 1, 1, 1, 1, 1, 1 ) -#define MPP9_TW0_SCK MPP( 9, 0x1, 1, 1, 1, 1, 1, 1, 1 ) -#define MPP9_UART0_CTS MPP( 9, 0x2, 1, 0, 1, 1, 1, 1, 1 ) -#define MPP9_UART1_CTS MPP( 9, 0x3, 1, 0, 1, 1, 1, 1, 1 ) -#define MPP9_SATA0_PRESENTn MPP( 9, 0x5, 0, 1, 0, 1, 1, 1, 1 ) -#define MPP9_PTP_EVENT_REQ MPP( 9, 0xc, 1, 0, 1, 1, 1, 1, 0 ) -#define MPP9_MII0_CRS MPP( 9, 0xd, 1, 0, 1, 1, 1, 1, 1 ) +#define MPP9_TW0_SCK MPP( 9, 0x1, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP9_UART0_CTS MPP( 9, 0x2, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP9_UART1_CTS MPP( 9, 0x3, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP9_SATA0_PRESENTn MPP( 9, 0x5, 0, 0, 0, 1, 1, 1, 1 ) +#define MPP9_PTP_EVENT_REQ MPP( 9, 0xc, 0, 0, 1, 1, 1, 1, 0 ) +#define MPP9_MII0_CRS MPP( 9, 0xd, 0, 0, 1, 1, 1, 1, 1 ) #define MPP10_GPO MPP( 10, 0x0, 0, 1, 1, 1, 1, 1, 1 ) -#define MPP10_SPI_SCK MPP( 10, 0x2, 0, 1, 1, 1, 1, 1, 1 ) -#define MPP10_UART0_TXD MPP( 10, 0X3, 0, 1, 1, 1, 1, 1, 1 ) -#define MPP10_SATA1_ACTn MPP( 10, 0x5, 0, 1, 0, 0, 1, 1, 1 ) -#define MPP10_PTP_TRIG_GEN MPP( 10, 0xc, 0, 1, 1, 1, 1, 1, 0 ) +#define MPP10_SPI_SCK MPP( 10, 0x2, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP10_UART0_TXD MPP( 10, 0X3, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP10_SATA1_ACTn MPP( 10, 0x5, 0, 0, 0, 0, 1, 1, 1 ) +#define MPP10_PTP_TRIG_GEN MPP( 10, 0xc, 0, 0, 1, 1, 1, 1, 0 ) #define MPP11_GPIO MPP( 11, 0x0, 1, 1, 1, 1, 1, 1, 1 ) -#define MPP11_SPI_MISO MPP( 11, 0x2, 1, 0, 1, 1, 1, 1, 1 ) -#define MPP11_UART0_RXD MPP( 11, 0x3, 1, 0, 1, 1, 1, 1, 1 ) -#define MPP11_PTP_EVENT_REQ MPP( 11, 0x4, 1, 0, 1, 1, 1, 1, 0 ) -#define MPP11_PTP_TRIG_GEN MPP( 11, 0xc, 0, 1, 1, 1, 1, 1, 0 ) -#define MPP11_PTP_CLK MPP( 11, 0xd, 1, 0, 1, 1, 1, 1, 0 ) -#define MPP11_SATA0_ACTn MPP( 11, 0x5, 0, 1, 0, 1, 1, 1, 1 ) +#define MPP11_SPI_MISO MPP( 11, 0x2, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP11_UART0_RXD MPP( 11, 0x3, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP11_PTP_EVENT_REQ MPP( 11, 0x4, 0, 0, 1, 1, 1, 1, 0 ) +#define MPP11_PTP_TRIG_GEN MPP( 11, 0xc, 0, 0, 1, 1, 1, 1, 0 ) +#define MPP11_PTP_CLK MPP( 11, 0xd, 0, 0, 1, 1, 1, 1, 0 ) +#define MPP11_SATA0_ACTn MPP( 11, 0x5, 0, 0, 0, 1, 1, 1, 1 ) #define MPP12_GPO MPP( 12, 0x0, 0, 1, 1, 1, 1, 1, 1 ) -#define MPP12_SD_CLK MPP( 12, 0x1, 0, 1, 1, 1, 1, 1, 1 ) -#define MPP12_AU_SPDIF0 MPP( 12, 0xa, 0, 1, 0, 0, 0, 0, 1 ) -#define MPP12_SPI_MOSI MPP( 12, 0xb, 0, 1, 0, 0, 0, 0, 1 ) -#define MPP12_TW1_SDA MPP( 12, 0xd, 1, 0, 0, 0, 0, 0, 1 ) +#define MPP12_SD_CLK MPP( 12, 0x1, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP12_AU_SPDIF0 MPP( 12, 0xa, 0, 0, 0, 0, 0, 0, 1 ) +#define MPP12_SPI_MOSI MPP( 12, 0xb, 0, 0, 0, 0, 0, 0, 1 ) +#define MPP12_TW1_SDA MPP( 12, 0xd, 0, 0, 0, 0, 0, 0, 1 ) #define MPP13_GPIO MPP( 13, 0x0, 1, 1, 1, 1, 1, 1, 1 ) -#define MPP13_SD_CMD MPP( 13, 0x1, 1, 1, 1, 1, 1, 1, 1 ) -#define MPP13_UART1_TXD MPP( 13, 0x3, 0, 1, 1, 1, 1, 1, 1 ) -#define MPP13_AU_SPDIFRMCLK MPP( 13, 0xa, 0, 1, 0, 0, 0, 0, 1 ) -#define MPP13_LCDPWM MPP( 13, 0xb, 0, 1, 0, 0, 0, 0, 1 ) +#define MPP13_SD_CMD MPP( 13, 0x1, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP13_UART1_TXD MPP( 13, 0x3, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP13_AU_SPDIFRMCLK MPP( 13, 0xa, 0, 0, 0, 0, 0, 0, 1 ) +#define MPP13_LCDPWM MPP( 13, 0xb, 0, 0, 0, 0, 0, 0, 1 ) #define MPP14_GPIO MPP( 14, 0x0, 1, 1, 1, 1, 1, 1, 1 ) -#define MPP14_SD_D0 MPP( 14, 0x1, 1, 1, 1, 1, 1, 1, 1 ) -#define MPP14_UART1_RXD MPP( 14, 0x3, 1, 0, 1, 1, 1, 1, 1 ) -#define MPP14_SATA1_PRESENTn MPP( 14, 0x4, 0, 1, 0, 0, 1, 1, 1 ) -#define MPP14_AU_SPDIFI MPP( 14, 0xa, 1, 0, 0, 0, 0, 0, 1 ) -#define MPP14_AU_I2SDI MPP( 14, 0xb, 1, 0, 0, 0, 0, 0, 1 ) -#define MPP14_MII0_COL MPP( 14, 0xd, 1, 0, 1, 1, 1, 1, 1 ) +#define MPP14_SD_D0 MPP( 14, 0x1, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP14_UART1_RXD MPP( 14, 0x3, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP14_SATA1_PRESENTn MPP( 14, 0x4, 0, 0, 0, 0, 1, 1, 1 ) +#define MPP14_AU_SPDIFI MPP( 14, 0xa, 0, 0, 0, 0, 0, 0, 1 ) +#define MPP14_AU_I2SDI MPP( 14, 0xb, 0, 0, 0, 0, 0, 0, 1 ) +#define MPP14_MII0_COL MPP( 14, 0xd, 0, 0, 1, 1, 1, 1, 1 ) #define MPP15_GPIO MPP( 15, 0x0, 1, 1, 1, 1, 1, 1, 1 ) -#define MPP15_SD_D1 MPP( 15, 0x1, 1, 1, 1, 1, 1, 1, 1 ) -#define MPP15_UART0_RTS MPP( 15, 0x2, 0, 1, 1, 1, 1, 1, 1 ) -#define MPP15_UART1_TXD MPP( 15, 0x3, 0, 1, 1, 1, 1, 1, 1 ) -#define MPP15_SATA0_ACTn MPP( 15, 0x4, 0, 1, 0, 1, 1, 1, 1 ) -#define MPP15_SPI_CSn MPP( 15, 0xb, 0, 1, 0, 0, 0, 0, 1 ) +#define MPP15_SD_D1 MPP( 15, 0x1, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP15_UART0_RTS MPP( 15, 0x2, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP15_UART1_TXD MPP( 15, 0x3, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP15_SATA0_ACTn MPP( 15, 0x4, 0, 0, 0, 1, 1, 1, 1 ) +#define MPP15_SPI_CSn MPP( 15, 0xb, 0, 0, 0, 0, 0, 0, 1 ) #define MPP16_GPIO MPP( 16, 0x0, 1, 1, 1, 1, 1, 1, 1 ) -#define MPP16_SD_D2 MPP( 16, 0x1, 1, 1, 1, 1, 1, 1, 1 ) -#define MPP16_UART0_CTS MPP( 16, 0x2, 1, 0, 1, 1, 1, 1, 1 ) -#define MPP16_UART1_RXD MPP( 16, 0x3, 1, 0, 1, 1, 1, 1, 1 ) -#define MPP16_SATA1_ACTn MPP( 16, 0x4, 0, 1, 0, 0, 1, 1, 1 ) -#define MPP16_LCD_EXT_REF_CLK MPP( 16, 0xb, 1, 0, 0, 0, 0, 0, 1 ) -#define MPP16_MII0_CRS MPP( 16, 0xd, 1, 0, 1, 1, 1, 1, 1 ) +#define MPP16_SD_D2 MPP( 16, 0x1, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP16_UART0_CTS MPP( 16, 0x2, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP16_UART1_RXD MPP( 16, 0x3, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP16_SATA1_ACTn MPP( 16, 0x4, 0, 0, 0, 0, 1, 1, 1 ) +#define MPP16_LCD_EXT_REF_CLK MPP( 16, 0xb, 0, 0, 0, 0, 0, 0, 1 ) +#define MPP16_MII0_CRS MPP( 16, 0xd, 0, 0, 1, 1, 1, 1, 1 ) #define MPP17_GPIO MPP( 17, 0x0, 1, 1, 1, 1, 1, 1, 1 ) -#define MPP17_SD_D3 MPP( 17, 0x1, 1, 1, 1, 1, 1, 1, 1 ) -#define MPP17_SATA0_PRESENTn MPP( 17, 0x4, 0, 1, 0, 1, 1, 1, 1 ) -#define MPP17_SATA1_ACTn MPP( 17, 0xa, 0, 1, 0, 0, 0, 0, 1 ) -#define MPP17_TW1_SCK MPP( 17, 0xd, 1, 1, 0, 0, 0, 0, 1 ) +#define MPP17_SD_D3 MPP( 17, 0x1, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP17_SATA0_PRESENTn MPP( 17, 0x4, 0, 0, 0, 1, 1, 1, 1 ) +#define MPP17_SATA1_ACTn MPP( 17, 0xa, 0, 0, 0, 0, 0, 0, 1 ) +#define MPP17_TW1_SCK MPP( 17, 0xd, 0, 0, 0, 0, 0, 0, 1 ) #define MPP18_GPO MPP( 18, 0x0, 0, 1, 1, 1, 1, 1, 1 ) -#define MPP18_NF_IO0 MPP( 18, 0x1, 1, 1, 1, 1, 1, 1, 1 ) -#define MPP18_PEX0_CLKREQ MPP( 18, 0x2, 0, 1, 0, 0, 0, 0, 1 ) +#define MPP18_NF_IO0 MPP( 18, 0x1, 0, 0, 1, 1, 1, 1, 1 ) +#define MPP18_PEX0_CLKREQ MPP( 18, 0x2, 0, 0, 0, 0, 0, 0, 1 ) #define MPP19_GPO MPP( 19, 0x0, 0, 1, 1, 1, 1, 1, 1 ) -#define MPP19_NF_IO1 MPP( 19, 0x1, 1, 1, 1, 1, 1, 1, 1 ) +#define MPP19_NF_IO1 MPP( 19, 0x1, 0, 0, 1, 1, 1, 1, 1 ) #define MPP20_GPIO MPP( 20, 0x0, 1, 1, 0, 1, 1, 1, 1 ) -#define MPP20_TSMP0 MPP( 20, 0x1, 1, 1, 0, 0, 1, 1, 1 ) -#define MPP20_TDM_CH0_TX_QL MPP( 20, 0x2, 0, 1, 0, 0, 1, 1, 1 ) +#define MPP20_TSMP0 MPP( 20, 0x1, 0, 0, 0, 0, 1, 1, 1 ) +#define MPP20_TDM_CH0_TX_QL MPP( 20, 0x2, 0, 0, 0, 0, 1, 1, 1 ) #define MPP20_GE1_TXD0 MPP( 20, 0x3, 0, 0, 0, 1, 1, 1, 1 ) -#define MPP20_AU_SPDIFI MPP( 20, 0x4, 1, 0, 0, 0, 1, 1, 1 ) -#define MPP20_SATA1_ACTn MPP( 20, 0x5, 0, 1, 0, 0, 1, 1, 1 ) +#define MPP20_AU_SPDIFI MPP( 20, 0x4, 0, 0, 0, 0, 1, 1, 1 ) +#define MPP20_SATA1_ACTn MPP( 20, 0x5, 0, 0, 0, 0, 1, 1, 1 ) #define MPP20_LCD_D0 MPP( 20, 0xb, 0, 0, 0, 0, 0, 0, 1 ) #define MPP21_GPIO MPP( 21, 0x0, 1, 1, 0, 1, 1, 1, 1 ) -#define MPP21_TSMP1 MPP( 21, 0x1, 1, 1, 0, 0, 1, 1, 1 ) -#define MPP21_TDM_CH0_RX_QL MPP( 21, 0x2, 0, 1, 0, 0, 1, 1, 1 ) +#define MPP21_TSMP1 MPP( 21, 0x1, 0, 0, 0, 0, 1, 1, 1 ) +#define MPP21_TDM_CH0_RX_QL MPP( 21, 0x2, 0, 0, 0, 0, 1, 1, 1 ) #define MPP21_GE1_TXD1 MPP( 21, 0x3, 0, 0, 0, 1, 1, 1, 1 ) -#define MPP21_AU_SPDIFO MPP( 21, 0x4, 0, 1, 0, 0, 1, 1, 1 ) -#define MPP21_SATA0_ACTn MPP( 21, 0x5, 0, 1, 0, 1, 1, 1, 1 ) +#define MPP21_AU_SPDIFO MPP( 21, 0x4, 0, 0, 0, 0, 1, 1, 1 ) +#define MPP21_SATA0_ACTn MPP( 21, 0x5, 0, 0, 0, 1, 1, 1, 1 ) #define MPP21_LCD_D1 MPP( 21, 0xb, 0, 0, 0, 0, 0, 0, 1 ) #define MPP22_GPIO MPP( 22, 0x0, 1, 1, 0, 1, 1, 1, 1 ) -#define MPP22_TSMP2 MPP( 22, 0x1, 1, 1, 0, 0, 1, 1, 1 ) -#define MPP22_TDM_CH2_TX_QL MPP( 22, 0x2, 0, 1, 0, 0, 1, 1, 1 ) +#define MPP22_TSMP2 MPP( 22, 0x1, 0, 0, 0, 0, 1, 1, 1 ) +#define MPP22_TDM_CH2_TX_QL MPP( 22, 0x2, 0, 0, 0, 0, 1, 1, 1 ) #define MPP22_GE1_TXD2 MPP( 22, 0x3, 0, 0, 0, 1, 1, 1, 1 ) -#define MPP22_AU_SPDIFRMKCLK MPP( 22, 0x4, 0, 1, 0, 0, 1, 1, 1 ) -#define MPP22_SATA1_PRESENTn MPP( 22, 0x5, 0, 1, 0, 0, 1, 1, 1 ) +#define MPP22_AU_SPDIFRMKCLK MPP( 22, 0x4, 0, 0, 0, 0, 1, 1, 1 ) +#define MPP22_SATA1_PRESENTn MPP( 22, 0x5, 0, 0, 0, 0, 1, 1, 1 ) #define MPP22_LCD_D2 MPP( 22, 0xb, 0, 0, 0, 0, 0, 0, 1 ) #define MPP23_GPIO MPP( 23, 0x0, 1, 1, 0, 1, 1, 1, 1 ) -#define MPP23_TSMP3 MPP( 23, 0x1, 1, 1, 0, 0, 1, 1, 1 ) -#define MPP23_TDM_CH2_RX_QL MPP( 23, 0x2, 1, 0, 0, 0, 1, 1, 1 ) +#define MPP23_TSMP3 MPP( 23, 0x1, 0, 0, 0, 0, 1, 1, 1 ) +#define MPP23_TDM_CH2_RX_QL MPP( 23, 0x2, 0, 0, 0, 0, 1, 1, 1 ) #define MPP23_GE1_TXD3 MPP( 23, 0x3, 0, 0, 0, 1, 1, 1, 1 ) -#define MPP23_AU_I2SBCLK MPP( 23, 0x4, 0, 1, 0, 0, 1, 1, 1 ) -#define MPP23_SATA0_PRESENTn MPP( 23, 0x5, 0, 1, 0, 1, 1, 1, 1 ) +#define MPP23_AU_I2SBCLK MPP( 23, 0x4, 0, 0, 0, 0, 1, 1, 1 ) +#define MPP23_SATA0_PRESENTn MPP( 23, 0x5, 0, 0, 0, 1, 1, 1, 1 ) #define MPP23_LCD_D3 MPP( 23, 0xb, 0, 0, 0, 0, 0, 0, 1 ) #define MPP24_GPIO MPP( 24, 0x0, 1, 1, 0, 1, 1, 1, 1 ) -#define MPP24_TSMP4 MPP( 24, 0x1, 1, 1, 0, 0, 1, 1, 1 ) -#define MPP24_TDM_SPI_CS0 MPP( 24, 0x2, 0, 1, 0, 0, 1, 1, 1 ) +#define MPP24_TSMP4 MPP( 24, 0x1, 0, 0, 0, 0, 1, 1, 1 ) +#define MPP24_TDM_SPI_CS0 MPP( 24, 0x2, 0, 0, 0, 0, 1, 1, 1 ) #define MPP24_GE1_RXD0 MPP( 24, 0x3, 0, 0, 0, 1, 1, 1, 1 ) -#define MPP24_AU_I2SDO MPP( 24, 0x4, 0, 1, 0, 0, 1, 1, 1 ) +#define MPP24_AU_I2SDO MPP( 24, 0x4, 0, 0, 0, 0, 1, 1, 1 ) #define MPP24_LCD_D4 MPP( 24, 0xb, 0, 0, 0, 0, 0, 0, 1 ) #define MPP25_GPIO MPP( 25, 0x0, 1, 1, 0, 1, 1, 1, 1 ) -#define MPP25_TSMP5 MPP( 25, 0x1, 1, 1, 0, 0, 1, 1, 1 ) -#define MPP25_TDM_SPI_SCK MPP( 25, 0x2, 0, 1, 0, 0, 1, 1, 1 ) +#define MPP25_TSMP5 MPP( 25, 0x1, 0, 0, 0, 0, 1, 1, 1 ) +#define MPP25_TDM_SPI_SCK MPP( 25, 0x2, 0, 0, 0, 0, 1, 1, 1 ) #define MPP25_GE1_RXD1 MPP( 25, 0x3, 0, 0, 0, 1, 1, 1, 1 ) -#define MPP25_AU_I2SLRCLK MPP( 25, 0x4, 0, 1, 0, 0, 1, 1, 1 ) +#define MPP25_AU_I2SLRCLK MPP( 25, 0x4, 0, 0, 0, 0, 1, 1, 1 ) #define MPP25_LCD_D5 MPP( 25, 0xb, 0, 0, 0, 0, 0, 0, 1 ) #define MPP26_GPIO MPP( 26, 0x0, 1, 1, 0, 1, 1, 1, 1 ) -#define MPP26_TSMP6 MPP( 26, 0x1, 1, 1, 0, 0, 1, 1, 1 ) -#define MPP26_TDM_SPI_MISO MPP( 26, 0x2, 1, 0, 0, 0, 1, 1, 1 ) +#define MPP26_TSMP6 MPP( 26, 0x1, 0, 0, 0, 0, 1, 1, 1 ) +#define MPP26_TDM_SPI_MISO MPP( 26, 0x2, 0, 0, 0, 0, 1, 1, 1 ) #define MPP26_GE1_RXD2 MPP( 26, 0x3, 0, 0, 0, 1, 1, 1, 1 ) -#define MPP26_AU_I2SMCLK MPP( 26, 0x4, 0, 1, 0, 0, 1, 1, 1 ) +#define MPP26_AU_I2SMCLK MPP( 26, 0x4, 0, 0, 0, 0, 1, 1, 1 ) #define MPP26_LCD_D6 MPP( 26, 0xb, 0, 0, 0, 0, 0, 0, 1 ) #define MPP27_GPIO MPP( 27, 0x0, 1, 1, 0, 1, 1, 1, 1 ) -#define MPP27_TSMP7 MPP( 27, 0x1, 1, 1, 0, 0, 1, 1, 1 ) -#define MPP27_TDM_SPI_MOSI MPP( 27, 0x2, 0, 1, 0, 0, 1, 1, 1 ) +#define MPP27_TSMP7 MPP( 27, 0x1, 0, 0, 0, 0, 1, 1, 1 ) +#define MPP27_TDM_SPI_MOSI MPP( 27, 0x2, 0, 0, 0, 0, 1, 1, 1 ) #define MPP27_GE1_RXD3 MPP( 27, 0x3, 0, 0, 0, 1, 1, 1, 1 ) -#define MPP27_AU_I2SDI MPP( 27, 0x4, 1, 0, 0, 0, 1, 1, 1 ) +#define MPP27_AU_I2SDI MPP( 27, 0x4, 0, 0, 0, 0, 1, 1, 1 ) #define MPP27_LCD_D7 MPP( 27, 0xb, 0, 0, 0, 0, 0, 0, 1 ) #define MPP28_GPIO MPP( 28, 0x0, 1, 1, 0, 1, 1, 1, 1 ) -#define MPP28_TSMP8 MPP( 28, 0x1, 1, 1, 0, 0, 1, 1, 1 ) +#define MPP28_TSMP8 MPP( 28, 0x1, 0, 0, 0, 0, 1, 1, 1 ) #define MPP28_TDM_CODEC_INTn MPP( 28, 0x2, 0, 0, 0, 0, 1, 1, 1 ) #define MPP28_GE1_COL MPP( 28, 0x3, 0, 0, 0, 1, 1, 1, 1 ) -#define MPP28_AU_EXTCLK MPP( 28, 0x4, 1, 0, 0, 0, 1, 1, 1 ) +#define MPP28_AU_EXTCLK MPP( 28, 0x4, 0, 0, 0, 0, 1, 1, 1 ) #define MPP28_LCD_D8 MPP( 28, 0xb, 0, 0, 0, 0, 0, 0, 1 ) #define MPP29_GPIO MPP( 29, 0x0, 1, 1, 0, 1, 1, 1, 1 ) -#define MPP29_TSMP9 MPP( 29, 0x1, 1, 1, 0, 0, 1, 1, 1 ) +#define MPP29_TSMP9 MPP( 29, 0x1, 0, 0, 0, 0, 1, 1, 1 ) #define MPP29_TDM_CODEC_RSTn MPP( 29, 0x2, 0, 0, 0, 0, 1, 1, 1 ) #define MPP29_GE1_TCLK MPP( 29, 0x3, 0, 0, 0, 1, 1, 1, 1 ) #define MPP29_LCD_D9 MPP( 29, 0xb, 0, 0, 0, 0, 0, 0, 1 ) #define MPP30_GPIO MPP( 30, 0x0, 1, 1, 0, 1, 1, 1, 1 ) -#define MPP30_TSMP10 MPP( 30, 0x1, 1, 1, 0, 0, 1, 1, 1 ) -#define MPP30_TDM_PCLK MPP( 30, 0x2, 1, 1, 0, 0, 1, 1, 1 ) +#define MPP30_TSMP10 MPP( 30, 0x1, 0, 0, 0, 0, 1, 1, 1 ) +#define MPP30_TDM_PCLK MPP( 30, 0x2, 0, 0, 0, 0, 1, 1, 1 ) #define MPP30_GE1_RXCTL MPP( 30, 0x3, 0, 0, 0, 1, 1, 1, 1 ) #define MPP30_LCD_D10 MPP( 30, 0xb, 0, 0, 0, 0, 0, 0, 1 ) #define MPP31_GPIO MPP( 31, 0x0, 1, 1, 0, 1, 1, 1, 1 ) -#define MPP31_TSMP11 MPP( 31, 0x1, 1, 1, 0, 0, 1, 1, 1 ) -#define MPP31_TDM_FS MPP( 31, 0x2, 1, 1, 0, 0, 1, 1, 1 ) +#define MPP31_TSMP11 MPP( 31, 0x1, 0, 0, 0, 0, 1, 1, 1 ) +#define MPP31_TDM_FS MPP( 31, 0x2, 0, 0, 0, 0, 1, 1, 1 ) #define MPP31_GE1_RXCLK MPP( 31, 0x3, 0, 0, 0, 1, 1, 1, 1 ) #define MPP31_LCD_D11 MPP( 31, 0xb, 0, 0, 0, 0, 0, 0, 1 ) #define MPP32_GPIO MPP( 32, 0x0, 1, 1, 0, 1, 1, 1, 1 ) -#define MPP32_TSMP12 MPP( 32, 0x1, 1, 1, 0, 0, 1, 1, 1 ) -#define MPP32_TDM_DRX MPP( 32, 0x2, 1, 0, 0, 0, 1, 1, 1 ) +#define MPP32_TSMP12 MPP( 32, 0x1, 0, 0, 0, 0, 1, 1, 1 ) +#define MPP32_TDM_DRX MPP( 32, 0x2, 0, 0, 0, 0, 1, 1, 1 ) #define MPP32_GE1_TCLKOUT MPP( 32, 0x3, 0, 0, 0, 1, 1, 1, 1 ) #define MPP32_LCD_D12 MPP( 32, 0xb, 0, 0, 0, 0, 0, 0, 1 ) #define MPP33_GPO MPP( 33, 0x0, 0, 1, 0, 1, 1, 1, 1 ) -#define MPP33_TDM_DTX MPP( 33, 0x2, 0, 1, 0, 0, 1, 1, 1 ) +#define MPP33_TDM_DTX MPP( 33, 0x2, 0, 0, 0, 0, 1, 1, 1 ) #define MPP33_GE1_TXCTL MPP( 33, 0x3, 0, 0, 0, 1, 1, 1, 1 ) #define MPP33_LCD_D13 MPP( 33, 0xb, 0, 0, 0, 0, 0, 0, 1 ) #define MPP34_GPIO MPP( 34, 0x0, 1, 1, 0, 1, 1, 1, 1 ) -#define MPP34_TDM_SPI_CS1 MPP( 34, 0x2, 0, 1, 0, 0, 1, 1, 1 ) +#define MPP34_TDM_SPI_CS1 MPP( 34, 0x2, 0, 0, 0, 0, 1, 1, 1 ) #define MPP34_GE1_TXEN MPP( 34, 0x3, 0, 0, 0, 1, 1, 1, 1 ) -#define MPP34_SATA1_ACTn MPP( 34, 0x5, 0, 1, 0, 0, 0, 1, 1 ) +#define MPP34_SATA1_ACTn MPP( 34, 0x5, 0, 0, 0, 0, 0, 1, 1 ) #define MPP34_LCD_D14 MPP( 34, 0xb, 0, 0, 0, 0, 0, 0, 1 ) #define MPP35_GPIO MPP( 35, 0x0, 1, 1, 1, 1, 1, 1, 1 ) -#define MPP35_TDM_CH0_TX_QL MPP( 35, 0x2, 0, 1, 0, 0, 1, 1, 1 ) +#define MPP35_TDM_CH0_TX_QL MPP( 35, 0x2, 0, 0, 0, 0, 1, 1, 1 ) #define MPP35_GE1_RXERR MPP( 35, 0x3, 0, 0, 0, 1, 1, 1, 1 ) -#define MPP35_SATA0_ACTn MPP( 35, 0x5, 0, 1, 0, 1, 1, 1, 1 ) +#define MPP35_SATA0_ACTn MPP( 35, 0x5, 0, 0, 0, 1, 1, 1, 1 ) #define MPP35_LCD_D15 MPP( 22, 0xb, 0, 0, 0, 0, 0, 0, 1 ) -#define MPP35_MII0_RXERR MPP( 35, 0xc, 1, 0, 1, 1, 1, 1, 1 ) +#define MPP35_MII0_RXERR MPP( 35, 0xc, 0, 0, 1, 1, 1, 1, 1 ) #define MPP36_GPIO MPP( 36, 0x0, 1, 1, 1, 0, 0, 1, 1 ) -#define MPP36_TSMP0 MPP( 36, 0x1, 1, 1, 0, 0, 0, 1, 1 ) -#define MPP36_TDM_SPI_CS1 MPP( 36, 0x2, 0, 1, 0, 0, 0, 1, 1 ) -#define MPP36_AU_SPDIFI MPP( 36, 0x4, 1, 0, 1, 0, 0, 1, 1 ) -#define MPP36_TW1_SDA MPP( 36, 0xb, 1, 1, 0, 0, 0, 0, 1 ) +#define MPP36_TSMP0 MPP( 36, 0x1, 0, 0, 0, 0, 0, 1, 1 ) +#define MPP36_TDM_SPI_CS1 MPP( 36, 0x2, 0, 0, 0, 0, 0, 1, 1 ) +#define MPP36_AU_SPDIFI MPP( 36, 0x4, 0, 0, 1, 0, 0, 1, 1 ) +#define MPP36_TW1_SDA MPP( 36, 0xb, 0, 0, 0, 0, 0, 0, 1 ) #define MPP37_GPIO MPP( 37, 0x0, 1, 1, 1, 0, 0, 1, 1 ) -#define MPP37_TSMP1 MPP( 37, 0x1, 1, 1, 0, 0, 0, 1, 1 ) -#define MPP37_TDM_CH2_TX_QL MPP( 37, 0x2, 0, 1, 0, 0, 0, 1, 1 ) -#define MPP37_AU_SPDIFO MPP( 37, 0x4, 0, 1, 1, 0, 0, 1, 1 ) -#define MPP37_TW1_SCK MPP( 37, 0xb, 1, 1, 0, 0, 0, 0, 1 ) +#define MPP37_TSMP1 MPP( 37, 0x1, 0, 0, 0, 0, 0, 1, 1 ) +#define MPP37_TDM_CH2_TX_QL MPP( 37, 0x2, 0, 0, 0, 0, 0, 1, 1 ) +#define MPP37_AU_SPDIFO MPP( 37, 0x4, 0, 0, 1, 0, 0, 1, 1 ) +#define MPP37_TW1_SCK MPP( 37, 0xb, 0, 0, 0, 0, 0, 0, 1 ) #define MPP38_GPIO MPP( 38, 0x0, 1, 1, 1, 0, 0, 1, 1 ) -#define MPP38_TSMP2 MPP( 38, 0x1, 1, 1, 0, 0, 0, 1, 1 ) -#define MPP38_TDM_CH2_RX_QL MPP( 38, 0x2, 0, 1, 0, 0, 0, 1, 1 ) -#define MPP38_AU_SPDIFRMLCLK MPP( 38, 0x4, 0, 1, 1, 0, 0, 1, 1 ) +#define MPP38_TSMP2 MPP( 38, 0x1, 0, 0, 0, 0, 0, 1, 1 ) +#define MPP38_TDM_CH2_RX_QL MPP( 38, 0x2, 0, 0, 0, 0, 0, 1, 1 ) +#define MPP38_AU_SPDIFRMLCLK MPP( 38, 0x4, 0, 0, 1, 0, 0, 1, 1 ) #define MPP38_LCD_D18 MPP( 38, 0xb, 0, 0, 0, 0, 0, 0, 1 ) #define MPP39_GPIO MPP( 39, 0x0, 1, 1, 1, 0, 0, 1, 1 ) -#define MPP39_TSMP3 MPP( 39, 0x1, 1, 1, 0, 0, 0, 1, 1 ) -#define MPP39_TDM_SPI_CS0 MPP( 39, 0x2, 0, 1, 0, 0, 0, 1, 1 ) -#define MPP39_AU_I2SBCLK MPP( 39, 0x4, 0, 1, 1, 0, 0, 1, 1 ) +#define MPP39_TSMP3 MPP( 39, 0x1, 0, 0, 0, 0, 0, 1, 1 ) +#define MPP39_TDM_SPI_CS0 MPP( 39, 0x2, 0, 0, 0, 0, 0, 1, 1 ) +#define MPP39_AU_I2SBCLK MPP( 39, 0x4, 0, 0, 1, 0, 0, 1, 1 ) #define MPP39_LCD_D19 MPP( 39, 0xb, 0, 0, 0, 0, 0, 0, 1 ) #define MPP40_GPIO MPP( 40, 0x0, 1, 1, 1, 0, 0, 1, 1 ) -#define MPP40_TSMP4 MPP( 40, 0x1, 1, 1, 0, 0, 0, 1, 1 ) -#define MPP40_TDM_SPI_SCK MPP( 40, 0x2, 0, 1, 0, 0, 0, 1, 1 ) -#define MPP40_AU_I2SDO MPP( 40, 0x4, 0, 1, 1, 0, 0, 1, 1 ) +#define MPP40_TSMP4 MPP( 40, 0x1, 0, 0, 0, 0, 0, 1, 1 ) +#define MPP40_TDM_SPI_SCK MPP( 40, 0x2, 0, 0, 0, 0, 0, 1, 1 ) +#define MPP40_AU_I2SDO MPP( 40, 0x4, 0, 0, 1, 0, 0, 1, 1 ) #define MPP40_LCD_D20 MPP( 40, 0xb, 0, 0, 0, 0, 0, 0, 1 ) #define MPP41_GPIO MPP( 41, 0x0, 1, 1, 1, 0, 0, 1, 1 ) -#define MPP41_TSMP5 MPP( 41, 0x1, 1, 1, 0, 0, 0, 1, 1 ) -#define MPP41_TDM_SPI_MISO MPP( 41, 0x2, 1, 0, 0, 0, 0, 1, 1 ) -#define MPP41_AU_I2SLRCLK MPP( 41, 0x4, 0, 1, 1, 0, 0, 1, 1 ) +#define MPP41_TSMP5 MPP( 41, 0x1, 0, 0, 0, 0, 0, 1, 1 ) +#define MPP41_TDM_SPI_MISO MPP( 41, 0x2, 0, 0, 0, 0, 0, 1, 1 ) +#define MPP41_AU_I2SLRCLK MPP( 41, 0x4, 0, 0, 1, 0, 0, 1, 1 ) #define MPP41_LCD_D21 MPP( 41, 0xb, 0, 0, 0, 0, 0, 0, 1 ) #define MPP42_GPIO MPP( 42, 0x0, 1, 1, 1, 0, 0, 1, 1 ) -#define MPP42_TSMP6 MPP( 42, 0x1, 1, 1, 0, 0, 0, 1, 1 ) -#define MPP42_TDM_SPI_MOSI MPP( 42, 0x2, 0, 1, 0, 0, 0, 1, 1 ) -#define MPP42_AU_I2SMCLK MPP( 42, 0x4, 0, 1, 1, 0, 0, 1, 1 ) +#define MPP42_TSMP6 MPP( 42, 0x1, 0, 0, 0, 0, 0, 1, 1 ) +#define MPP42_TDM_SPI_MOSI MPP( 42, 0x2, 0, 0, 0, 0, 0, 1, 1 ) +#define MPP42_AU_I2SMCLK MPP( 42, 0x4, 0, 0, 1, 0, 0, 1, 1 ) #define MPP42_LCD_D22 MPP( 42, 0xb, 0, 0, 0, 0, 0, 0, 1 ) #define MPP43_GPIO MPP( 43, 0x0, 1, 1, 1, 0, 0, 1, 1 ) -#define MPP43_TSMP7 MPP( 43, 0x1, 1, 1, 0, 0, 0, 1, 1 ) +#define MPP43_TSMP7 MPP( 43, 0x1, 0, 0, 0, 0, 0, 1, 1 ) #define MPP43_TDM_CODEC_INTn MPP( 43, 0x2, 0, 0, 0, 0, 0, 1, 1 ) -#define MPP43_AU_I2SDI MPP( 43, 0x4, 1, 0, 1, 0, 0, 1, 1 ) +#define MPP43_AU_I2SDI MPP( 43, 0x4, 0, 0, 1, 0, 0, 1, 1 ) #define MPP43_LCD_D23 MPP( 22, 0xb, 0, 0, 0, 0, 0, 0, 1 ) #define MPP44_GPIO MPP( 44, 0x0, 1, 1, 1, 0, 0, 1, 1 ) -#define MPP44_TSMP8 MPP( 44, 0x1, 1, 1, 0, 0, 0, 1, 1 ) +#define MPP44_TSMP8 MPP( 44, 0x1, 0, 0, 0, 0, 0, 1, 1 ) #define MPP44_TDM_CODEC_RSTn MPP( 44, 0x2, 0, 0, 0, 0, 0, 1, 1 ) -#define MPP44_AU_EXTCLK MPP( 44, 0x4, 1, 0, 1, 0, 0, 1, 1 ) +#define MPP44_AU_EXTCLK MPP( 44, 0x4, 0, 0, 1, 0, 0, 1, 1 ) #define MPP44_LCD_CLK MPP( 44, 0xb, 0, 0, 0, 0, 0, 0, 1 ) #define MPP45_GPIO MPP( 45, 0x0, 1, 1, 0, 0, 0, 1, 1 ) -#define MPP45_TSMP9 MPP( 45, 0x1, 1, 1, 0, 0, 0, 1, 1 ) -#define MPP45_TDM_PCLK MPP( 45, 0x2, 1, 1, 0, 0, 0, 1, 1 ) +#define MPP45_TSMP9 MPP( 45, 0x1, 0, 0, 0, 0, 0, 1, 1 ) +#define MPP45_TDM_PCLK MPP( 45, 0x2, 0, 0, 0, 0, 0, 1, 1 ) #define MPP245_LCD_E MPP( 45, 0xb, 0, 0, 0, 0, 0, 0, 1 ) #define MPP46_GPIO MPP( 46, 0x0, 1, 1, 0, 0, 0, 1, 1 ) -#define MPP46_TSMP10 MPP( 46, 0x1, 1, 1, 0, 0, 0, 1, 1 ) -#define MPP46_TDM_FS MPP( 46, 0x2, 1, 1, 0, 0, 0, 1, 1 ) +#define MPP46_TSMP10 MPP( 46, 0x1, 0, 0, 0, 0, 0, 1, 1 ) +#define MPP46_TDM_FS MPP( 46, 0x2, 0, 0, 0, 0, 0, 1, 1 ) #define MPP46_LCD_HSYNC MPP( 46, 0xb, 0, 0, 0, 0, 0, 0, 1 ) #define MPP47_GPIO MPP( 47, 0x0, 1, 1, 0, 0, 0, 1, 1 ) -#define MPP47_TSMP11 MPP( 47, 0x1, 1, 1, 0, 0, 0, 1, 1 ) -#define MPP47_TDM_DRX MPP( 47, 0x2, 1, 0, 0, 0, 0, 1, 1 ) +#define MPP47_TSMP11 MPP( 47, 0x1, 0, 0, 0, 0, 0, 1, 1 ) +#define MPP47_TDM_DRX MPP( 47, 0x2, 0, 0, 0, 0, 0, 1, 1 ) #define MPP47_LCD_VSYNC MPP( 47, 0xb, 0, 0, 0, 0, 0, 0, 1 ) #define MPP48_GPIO MPP( 48, 0x0, 1, 1, 0, 0, 0, 1, 1 ) -#define MPP48_TSMP12 MPP( 48, 0x1, 1, 1, 0, 0, 0, 1, 1 ) -#define MPP48_TDM_DTX MPP( 48, 0x2, 0, 1, 0, 0, 0, 1, 1 ) +#define MPP48_TSMP12 MPP( 48, 0x1, 0, 0, 0, 0, 0, 1, 1 ) +#define MPP48_TDM_DTX MPP( 48, 0x2, 0, 0, 0, 0, 0, 1, 1 ) #define MPP48_LCD_D16 MPP( 22, 0xb, 0, 0, 0, 0, 0, 0, 1 ) #define MPP49_GPIO MPP( 49, 0x0, 1, 1, 0, 0, 0, 1, 0 ) #define MPP49_GPO MPP( 49, 0x0, 0, 1, 0, 0, 0, 0, 1 ) -#define MPP49_TSMP9 MPP( 49, 0x1, 1, 1, 0, 0, 0, 1, 0 ) -#define MPP49_TDM_CH0_RX_QL MPP( 49, 0x2, 0, 1, 0, 0, 0, 1, 1 ) -#define MPP49_PTP_CLK MPP( 49, 0x5, 1, 0, 0, 0, 0, 1, 0 ) -#define MPP49_PEX0_CLKREQ MPP( 49, 0xa, 0, 1, 0, 0, 0, 0, 1 ) +#define MPP49_TSMP9 MPP( 49, 0x1, 0, 0, 0, 0, 0, 1, 0 ) +#define MPP49_TDM_CH0_RX_QL MPP( 49, 0x2, 0, 0, 0, 0, 0, 1, 1 ) +#define MPP49_PTP_CLK MPP( 49, 0x5, 0, 0, 0, 0, 0, 1, 0 ) +#define MPP49_PEX0_CLKREQ MPP( 49, 0xa, 0, 0, 0, 0, 0, 0, 1 ) #define MPP49_LCD_D17 MPP( 49, 0xb, 0, 0, 0, 0, 0, 0, 1 ) #define MPP_MAX 49 diff --git a/arch/arm/mach-lpc32xx/include/mach/irqs.h b/arch/arm/mach-lpc32xx/include/mach/irqs.h index 2667f52..9e3b90d 100644 --- a/arch/arm/mach-lpc32xx/include/mach/irqs.h +++ b/arch/arm/mach-lpc32xx/include/mach/irqs.h @@ -61,7 +61,7 @@ */ #define IRQ_LPC32XX_JTAG_COMM_TX LPC32XX_SIC1_IRQ(1) #define IRQ_LPC32XX_JTAG_COMM_RX LPC32XX_SIC1_IRQ(2) -#define IRQ_LPC32XX_GPI_11 LPC32XX_SIC1_IRQ(4) +#define IRQ_LPC32XX_GPI_28 LPC32XX_SIC1_IRQ(4) #define IRQ_LPC32XX_TS_P LPC32XX_SIC1_IRQ(6) #define IRQ_LPC32XX_TS_IRQ LPC32XX_SIC1_IRQ(7) #define IRQ_LPC32XX_TS_AUX LPC32XX_SIC1_IRQ(8) diff --git a/arch/arm/mach-lpc32xx/irq.c b/arch/arm/mach-lpc32xx/irq.c index 4eae566..c74de01 100644 --- a/arch/arm/mach-lpc32xx/irq.c +++ b/arch/arm/mach-lpc32xx/irq.c @@ -118,6 +118,10 @@ static const struct lpc32xx_event_info lpc32xx_events[NR_IRQS] = { .event_group = &lpc32xx_event_pin_regs, .mask = LPC32XX_CLKPWR_EXTSRC_GPI_06_BIT, }, + [IRQ_LPC32XX_GPI_28] = { + .event_group = &lpc32xx_event_pin_regs, + .mask = LPC32XX_CLKPWR_EXTSRC_GPI_28_BIT, + }, [IRQ_LPC32XX_GPIO_00] = { .event_group = &lpc32xx_event_int_regs, .mask = LPC32XX_CLKPWR_INTSRC_GPIO_00_BIT, @@ -305,9 +309,18 @@ static int lpc32xx_irq_wake(struct irq_data *d, unsigned int state) if (state) eventreg |= lpc32xx_events[d->irq].mask; - else + else { eventreg &= ~lpc32xx_events[d->irq].mask; + /* + * When disabling the wakeup, clear the latched + * event + */ + __raw_writel(lpc32xx_events[d->irq].mask, + lpc32xx_events[d->irq]. + event_group->rawstat_reg); + } + __raw_writel(eventreg, lpc32xx_events[d->irq].event_group->enab_reg); @@ -380,13 +393,15 @@ void __init lpc32xx_init_irq(void) /* Setup SIC1 */ __raw_writel(0, LPC32XX_INTC_MASK(LPC32XX_SIC1_BASE)); - __raw_writel(MIC_APR_DEFAULT, LPC32XX_INTC_POLAR(LPC32XX_SIC1_BASE)); - __raw_writel(MIC_ATR_DEFAULT, LPC32XX_INTC_ACT_TYPE(LPC32XX_SIC1_BASE)); + __raw_writel(SIC1_APR_DEFAULT, LPC32XX_INTC_POLAR(LPC32XX_SIC1_BASE)); + __raw_writel(SIC1_ATR_DEFAULT, + LPC32XX_INTC_ACT_TYPE(LPC32XX_SIC1_BASE)); /* Setup SIC2 */ __raw_writel(0, LPC32XX_INTC_MASK(LPC32XX_SIC2_BASE)); - __raw_writel(MIC_APR_DEFAULT, LPC32XX_INTC_POLAR(LPC32XX_SIC2_BASE)); - __raw_writel(MIC_ATR_DEFAULT, LPC32XX_INTC_ACT_TYPE(LPC32XX_SIC2_BASE)); + __raw_writel(SIC2_APR_DEFAULT, LPC32XX_INTC_POLAR(LPC32XX_SIC2_BASE)); + __raw_writel(SIC2_ATR_DEFAULT, + LPC32XX_INTC_ACT_TYPE(LPC32XX_SIC2_BASE)); /* Configure supported IRQ's */ for (i = 0; i < NR_IRQS; i++) { diff --git a/arch/arm/mach-lpc32xx/serial.c b/arch/arm/mach-lpc32xx/serial.c index 429cfdb..f273528 100644 --- a/arch/arm/mach-lpc32xx/serial.c +++ b/arch/arm/mach-lpc32xx/serial.c @@ -88,6 +88,7 @@ struct uartinit { char *uart_ck_name; u32 ck_mode_mask; void __iomem *pdiv_clk_reg; + resource_size_t mapbase; }; static struct uartinit uartinit_data[] __initdata = { @@ -97,6 +98,7 @@ static struct uartinit uartinit_data[] __initdata = { .ck_mode_mask = LPC32XX_UART_CLKMODE_LOAD(LPC32XX_UART_CLKMODE_ON, 5), .pdiv_clk_reg = LPC32XX_CLKPWR_UART5_CLK_CTRL, + .mapbase = LPC32XX_UART5_BASE, }, #endif #ifdef CONFIG_ARCH_LPC32XX_UART3_SELECT @@ -105,6 +107,7 @@ static struct uartinit uartinit_data[] __initdata = { .ck_mode_mask = LPC32XX_UART_CLKMODE_LOAD(LPC32XX_UART_CLKMODE_ON, 3), .pdiv_clk_reg = LPC32XX_CLKPWR_UART3_CLK_CTRL, + .mapbase = LPC32XX_UART3_BASE, }, #endif #ifdef CONFIG_ARCH_LPC32XX_UART4_SELECT @@ -113,6 +116,7 @@ static struct uartinit uartinit_data[] __initdata = { .ck_mode_mask = LPC32XX_UART_CLKMODE_LOAD(LPC32XX_UART_CLKMODE_ON, 4), .pdiv_clk_reg = LPC32XX_CLKPWR_UART4_CLK_CTRL, + .mapbase = LPC32XX_UART4_BASE, }, #endif #ifdef CONFIG_ARCH_LPC32XX_UART6_SELECT @@ -121,6 +125,7 @@ static struct uartinit uartinit_data[] __initdata = { .ck_mode_mask = LPC32XX_UART_CLKMODE_LOAD(LPC32XX_UART_CLKMODE_ON, 6), .pdiv_clk_reg = LPC32XX_CLKPWR_UART6_CLK_CTRL, + .mapbase = LPC32XX_UART6_BASE, }, #endif }; @@ -165,11 +170,24 @@ void __init lpc32xx_serial_init(void) /* pre-UART clock divider set to 1 */ __raw_writel(0x0101, uartinit_data[i].pdiv_clk_reg); + + /* + * Force a flush of the RX FIFOs to work around a + * HW bug + */ + puart = uartinit_data[i].mapbase; + __raw_writel(0xC1, LPC32XX_UART_IIR_FCR(puart)); + __raw_writel(0x00, LPC32XX_UART_DLL_FIFO(puart)); + j = LPC32XX_SUART_FIFO_SIZE; + while (j--) + tmp = __raw_readl( + LPC32XX_UART_DLL_FIFO(puart)); + __raw_writel(0, LPC32XX_UART_IIR_FCR(puart)); } /* This needs to be done after all UART clocks are setup */ __raw_writel(clkmodes, LPC32XX_UARTCTL_CLKMODE); - for (i = 0; i < ARRAY_SIZE(uartinit_data) - 1; i++) { + for (i = 0; i < ARRAY_SIZE(uartinit_data); i++) { /* Force a flush of the RX FIFOs to work around a HW bug */ puart = serial_std_platform_data[i].mapbase; __raw_writel(0xC1, LPC32XX_UART_IIR_FCR(puart)); diff --git a/arch/arm/mach-mv78xx0/common.c b/arch/arm/mach-mv78xx0/common.c index 23d3980..d90e244 100644 --- a/arch/arm/mach-mv78xx0/common.c +++ b/arch/arm/mach-mv78xx0/common.c @@ -20,6 +20,7 @@ #include <mach/mv78xx0.h> #include <mach/bridge-regs.h> #include <plat/cache-feroceon-l2.h> +#include <plat/ehci-orion.h> #include <plat/orion_nand.h> #include <plat/time.h> #include <plat/common.h> @@ -170,7 +171,7 @@ void __init mv78xx0_map_io(void) void __init mv78xx0_ehci0_init(void) { orion_ehci_init(&mv78xx0_mbus_dram_info, - USB0_PHYS_BASE, IRQ_MV78XX0_USB_0); + USB0_PHYS_BASE, IRQ_MV78XX0_USB_0, EHCI_PHY_NA); } diff --git a/arch/arm/mach-mv78xx0/mpp.h b/arch/arm/mach-mv78xx0/mpp.h index b61b509..3752302 100644 --- a/arch/arm/mach-mv78xx0/mpp.h +++ b/arch/arm/mach-mv78xx0/mpp.h @@ -24,296 +24,296 @@ #define MPP_78100_A0_MASK MPP(0, 0x0, 0, 0, 1) #define MPP0_GPIO MPP(0, 0x0, 1, 1, 1) -#define MPP0_GE0_COL MPP(0, 0x1, 1, 0, 1) -#define MPP0_GE1_TXCLK MPP(0, 0x2, 0, 1, 1) +#define MPP0_GE0_COL MPP(0, 0x1, 0, 0, 1) +#define MPP0_GE1_TXCLK MPP(0, 0x2, 0, 0, 1) #define MPP0_UNUSED MPP(0, 0x3, 0, 0, 1) #define MPP1_GPIO MPP(1, 0x0, 1, 1, 1) -#define MPP1_GE0_RXERR MPP(1, 0x1, 1, 0, 1) -#define MPP1_GE1_TXCTL MPP(1, 0x2, 0, 1, 1) +#define MPP1_GE0_RXERR MPP(1, 0x1, 0, 0, 1) +#define MPP1_GE1_TXCTL MPP(1, 0x2, 0, 0, 1) #define MPP1_UNUSED MPP(1, 0x3, 0, 0, 1) #define MPP2_GPIO MPP(2, 0x0, 1, 1, 1) -#define MPP2_GE0_CRS MPP(2, 0x1, 1, 0, 1) -#define MPP2_GE1_RXCTL MPP(2, 0x2, 1, 0, 1) +#define MPP2_GE0_CRS MPP(2, 0x1, 0, 0, 1) +#define MPP2_GE1_RXCTL MPP(2, 0x2, 0, 0, 1) #define MPP2_UNUSED MPP(2, 0x3, 0, 0, 1) #define MPP3_GPIO MPP(3, 0x0, 1, 1, 1) -#define MPP3_GE0_TXERR MPP(3, 0x1, 0, 1, 1) -#define MPP3_GE1_RXCLK MPP(3, 0x2, 1, 0, 1) +#define MPP3_GE0_TXERR MPP(3, 0x1, 0, 0, 1) +#define MPP3_GE1_RXCLK MPP(3, 0x2, 0, 0, 1) #define MPP3_UNUSED MPP(3, 0x3, 0, 0, 1) #define MPP4_GPIO MPP(4, 0x0, 1, 1, 1) -#define MPP4_GE0_TXD4 MPP(4, 0x1, 0, 1, 1) -#define MPP4_GE1_TXD0 MPP(4, 0x2, 0, 1, 1) +#define MPP4_GE0_TXD4 MPP(4, 0x1, 0, 0, 1) +#define MPP4_GE1_TXD0 MPP(4, 0x2, 0, 0, 1) #define MPP4_UNUSED MPP(4, 0x3, 0, 0, 1) #define MPP5_GPIO MPP(5, 0x0, 1, 1, 1) -#define MPP5_GE0_TXD5 MPP(5, 0x1, 0, 1, 1) -#define MPP5_GE1_TXD1 MPP(5, 0x2, 0, 1, 1) +#define MPP5_GE0_TXD5 MPP(5, 0x1, 0, 0, 1) +#define MPP5_GE1_TXD1 MPP(5, 0x2, 0, 0, 1) #define MPP5_UNUSED MPP(5, 0x3, 0, 0, 1) #define MPP6_GPIO MPP(6, 0x0, 1, 1, 1) -#define MPP6_GE0_TXD6 MPP(6, 0x1, 0, 1, 1) -#define MPP6_GE1_TXD2 MPP(6, 0x2, 0, 1, 1) +#define MPP6_GE0_TXD6 MPP(6, 0x1, 0, 0, 1) +#define MPP6_GE1_TXD2 MPP(6, 0x2, 0, 0, 1) #define MPP6_UNUSED MPP(6, 0x3, 0, 0, 1) #define MPP7_GPIO MPP(7, 0x0, 1, 1, 1) -#define MPP7_GE0_TXD7 MPP(7, 0x1, 0, 1, 1) -#define MPP7_GE1_TXD3 MPP(7, 0x2, 0, 1, 1) +#define MPP7_GE0_TXD7 MPP(7, 0x1, 0, 0, 1) +#define MPP7_GE1_TXD3 MPP(7, 0x2, 0, 0, 1) #define MPP7_UNUSED MPP(7, 0x3, 0, 0, 1) #define MPP8_GPIO MPP(8, 0x0, 1, 1, 1) -#define MPP8_GE0_RXD4 MPP(8, 0x1, 1, 0, 1) -#define MPP8_GE1_RXD0 MPP(8, 0x2, 1, 0, 1) +#define MPP8_GE0_RXD4 MPP(8, 0x1, 0, 0, 1) +#define MPP8_GE1_RXD0 MPP(8, 0x2, 0, 0, 1) #define MPP8_UNUSED MPP(8, 0x3, 0, 0, 1) #define MPP9_GPIO MPP(9, 0x0, 1, 1, 1) -#define MPP9_GE0_RXD5 MPP(9, 0x1, 1, 0, 1) -#define MPP9_GE1_RXD1 MPP(9, 0x2, 1, 0, 1) +#define MPP9_GE0_RXD5 MPP(9, 0x1, 0, 0, 1) +#define MPP9_GE1_RXD1 MPP(9, 0x2, 0, 0, 1) #define MPP9_UNUSED MPP(9, 0x3, 0, 0, 1) #define MPP10_GPIO MPP(10, 0x0, 1, 1, 1) -#define MPP10_GE0_RXD6 MPP(10, 0x1, 1, 0, 1) -#define MPP10_GE1_RXD2 MPP(10, 0x2, 1, 0, 1) +#define MPP10_GE0_RXD6 MPP(10, 0x1, 0, 0, 1) +#define MPP10_GE1_RXD2 MPP(10, 0x2, 0, 0, 1) #define MPP10_UNUSED MPP(10, 0x3, 0, 0, 1) #define MPP11_GPIO MPP(11, 0x0, 1, 1, 1) -#define MPP11_GE0_RXD7 MPP(11, 0x1, 1, 0, 1) -#define MPP11_GE1_RXD3 MPP(11, 0x2, 1, 0, 1) +#define MPP11_GE0_RXD7 MPP(11, 0x1, 0, 0, 1) +#define MPP11_GE1_RXD3 MPP(11, 0x2, 0, 0, 1) #define MPP11_UNUSED MPP(11, 0x3, 0, 0, 1) #define MPP12_GPIO MPP(12, 0x0, 1, 1, 1) -#define MPP12_M_BB MPP(12, 0x3, 1, 0, 1) -#define MPP12_UA0_CTSn MPP(12, 0x4, 1, 0, 1) -#define MPP12_NAND_FLASH_REn0 MPP(12, 0x5, 0, 1, 1) -#define MPP12_TDM0_SCSn MPP(12, 0X6, 0, 1, 1) +#define MPP12_M_BB MPP(12, 0x3, 0, 0, 1) +#define MPP12_UA0_CTSn MPP(12, 0x4, 0, 0, 1) +#define MPP12_NAND_FLASH_REn0 MPP(12, 0x5, 0, 0, 1) +#define MPP12_TDM0_SCSn MPP(12, 0X6, 0, 0, 1) #define MPP12_UNUSED MPP(12, 0x1, 0, 0, 1) #define MPP13_GPIO MPP(13, 0x0, 1, 1, 1) -#define MPP13_SYSRST_OUTn MPP(13, 0x3, 0, 1, 1) -#define MPP13_UA0_RTSn MPP(13, 0x4, 0, 1, 1) -#define MPP13_NAN_FLASH_WEn0 MPP(13, 0x5, 0, 1, 1) -#define MPP13_TDM_SCLK MPP(13, 0x6, 0, 1, 1) +#define MPP13_SYSRST_OUTn MPP(13, 0x3, 0, 0, 1) +#define MPP13_UA0_RTSn MPP(13, 0x4, 0, 0, 1) +#define MPP13_NAN_FLASH_WEn0 MPP(13, 0x5, 0, 0, 1) +#define MPP13_TDM_SCLK MPP(13, 0x6, 0, 0, 1) #define MPP13_UNUSED MPP(13, 0x1, 0, 0, 1) #define MPP14_GPIO MPP(14, 0x0, 1, 1, 1) -#define MPP14_SATA1_ACTn MPP(14, 0x3, 0, 1, 1) -#define MPP14_UA1_CTSn MPP(14, 0x4, 1, 0, 1) -#define MPP14_NAND_FLASH_REn1 MPP(14, 0x5, 0, 1, 1) -#define MPP14_TDM_SMOSI MPP(14, 0x6, 0, 1, 1) +#define MPP14_SATA1_ACTn MPP(14, 0x3, 0, 0, 1) +#define MPP14_UA1_CTSn MPP(14, 0x4, 0, 0, 1) +#define MPP14_NAND_FLASH_REn1 MPP(14, 0x5, 0, 0, 1) +#define MPP14_TDM_SMOSI MPP(14, 0x6, 0, 0, 1) #define MPP14_UNUSED MPP(14, 0x1, 0, 0, 1) #define MPP15_GPIO MPP(15, 0x0, 1, 1, 1) -#define MPP15_SATA0_ACTn MPP(15, 0x3, 0, 1, 1) -#define MPP15_UA1_RTSn MPP(15, 0x4, 0, 1, 1) -#define MPP15_NAND_FLASH_WEn1 MPP(15, 0x5, 0, 1, 1) -#define MPP15_TDM_SMISO MPP(15, 0x6, 1, 0, 1) +#define MPP15_SATA0_ACTn MPP(15, 0x3, 0, 0, 1) +#define MPP15_UA1_RTSn MPP(15, 0x4, 0, 0, 1) +#define MPP15_NAND_FLASH_WEn1 MPP(15, 0x5, 0, 0, 1) +#define MPP15_TDM_SMISO MPP(15, 0x6, 0, 0, 1) #define MPP15_UNUSED MPP(15, 0x1, 0, 0, 1) #define MPP16_GPIO MPP(16, 0x0, 1, 1, 1) -#define MPP16_SATA1_PRESENTn MPP(16, 0x3, 0, 1, 1) -#define MPP16_UA2_TXD MPP(16, 0x4, 0, 1, 1) -#define MPP16_NAND_FLASH_REn3 MPP(16, 0x5, 0, 1, 1) -#define MPP16_TDM_INTn MPP(16, 0x6, 1, 0, 1) +#define MPP16_SATA1_PRESENTn MPP(16, 0x3, 0, 0, 1) +#define MPP16_UA2_TXD MPP(16, 0x4, 0, 0, 1) +#define MPP16_NAND_FLASH_REn3 MPP(16, 0x5, 0, 0, 1) +#define MPP16_TDM_INTn MPP(16, 0x6, 0, 0, 1) #define MPP16_UNUSED MPP(16, 0x1, 0, 0, 1) #define MPP17_GPIO MPP(17, 0x0, 1, 1, 1) -#define MPP17_SATA0_PRESENTn MPP(17, 0x3, 0, 1, 1) -#define MPP17_UA2_RXD MPP(17, 0x4, 1, 0, 1) -#define MPP17_NAND_FLASH_WEn3 MPP(17, 0x5, 0, 1, 1) -#define MPP17_TDM_RSTn MPP(17, 0x6, 0, 1, 1) +#define MPP17_SATA0_PRESENTn MPP(17, 0x3, 0, 0, 1) +#define MPP17_UA2_RXD MPP(17, 0x4, 0, 0, 1) +#define MPP17_NAND_FLASH_WEn3 MPP(17, 0x5, 0, 0, 1) +#define MPP17_TDM_RSTn MPP(17, 0x6, 0, 0, 1) #define MPP17_UNUSED MPP(17, 0x1, 0, 0, 1) #define MPP18_GPIO MPP(18, 0x0, 1, 1, 1) -#define MPP18_UA0_CTSn MPP(18, 0x4, 1, 0, 1) -#define MPP18_BOOT_FLASH_REn MPP(18, 0x5, 0, 1, 1) +#define MPP18_UA0_CTSn MPP(18, 0x4, 0, 0, 1) +#define MPP18_BOOT_FLASH_REn MPP(18, 0x5, 0, 0, 1) #define MPP18_UNUSED MPP(18, 0x1, 0, 0, 1) #define MPP19_GPIO MPP(19, 0x0, 1, 1, 1) -#define MPP19_UA0_CTSn MPP(19, 0x4, 0, 1, 1) -#define MPP19_BOOT_FLASH_WEn MPP(19, 0x5, 0, 1, 1) +#define MPP19_UA0_CTSn MPP(19, 0x4, 0, 0, 1) +#define MPP19_BOOT_FLASH_WEn MPP(19, 0x5, 0, 0, 1) #define MPP19_UNUSED MPP(19, 0x1, 0, 0, 1) #define MPP20_GPIO MPP(20, 0x0, 1, 1, 1) -#define MPP20_UA1_CTSs MPP(20, 0x4, 1, 0, 1) -#define MPP20_TDM_PCLK MPP(20, 0x6, 1, 1, 0) +#define MPP20_UA1_CTSs MPP(20, 0x4, 0, 0, 1) +#define MPP20_TDM_PCLK MPP(20, 0x6, 0, 0, 0) #define MPP20_UNUSED MPP(20, 0x1, 0, 0, 1) #define MPP21_GPIO MPP(21, 0x0, 1, 1, 1) -#define MPP21_UA1_CTSs MPP(21, 0x4, 0, 1, 1) -#define MPP21_TDM_FSYNC MPP(21, 0x6, 1, 1, 0) +#define MPP21_UA1_CTSs MPP(21, 0x4, 0, 0, 1) +#define MPP21_TDM_FSYNC MPP(21, 0x6, 0, 0, 0) #define MPP21_UNUSED MPP(21, 0x1, 0, 0, 1) #define MPP22_GPIO MPP(22, 0x0, 1, 1, 1) -#define MPP22_UA3_TDX MPP(22, 0x4, 0, 1, 1) -#define MPP22_NAND_FLASH_REn2 MPP(22, 0x5, 0, 1, 1) -#define MPP22_TDM_DRX MPP(22, 0x6, 1, 0, 1) +#define MPP22_UA3_TDX MPP(22, 0x4, 0, 0, 1) +#define MPP22_NAND_FLASH_REn2 MPP(22, 0x5, 0, 0, 1) +#define MPP22_TDM_DRX MPP(22, 0x6, 0, 0, 1) #define MPP22_UNUSED MPP(22, 0x1, 0, 0, 1) #define MPP23_GPIO MPP(23, 0x0, 1, 1, 1) -#define MPP23_UA3_RDX MPP(23, 0x4, 1, 0, 1) -#define MPP23_NAND_FLASH_WEn2 MPP(23, 0x5, 0, 1, 1) -#define MPP23_TDM_DTX MPP(23, 0x6, 0, 1, 1) +#define MPP23_UA3_RDX MPP(23, 0x4, 0, 0, 1) +#define MPP23_NAND_FLASH_WEn2 MPP(23, 0x5, 0, 0, 1) +#define MPP23_TDM_DTX MPP(23, 0x6, 0, 0, 1) #define MPP23_UNUSED MPP(23, 0x1, 0, 0, 1) #define MPP24_GPIO MPP(24, 0x0, 1, 1, 1) -#define MPP24_UA2_TXD MPP(24, 0x4, 0, 1, 1) -#define MPP24_TDM_INTn MPP(24, 0x6, 1, 0, 1) +#define MPP24_UA2_TXD MPP(24, 0x4, 0, 0, 1) +#define MPP24_TDM_INTn MPP(24, 0x6, 0, 0, 1) #define MPP24_UNUSED MPP(24, 0x1, 0, 0, 1) #define MPP25_GPIO MPP(25, 0x0, 1, 1, 1) -#define MPP25_UA2_RXD MPP(25, 0x4, 1, 0, 1) -#define MPP25_TDM_RSTn MPP(25, 0x6, 0, 1, 1) +#define MPP25_UA2_RXD MPP(25, 0x4, 0, 0, 1) +#define MPP25_TDM_RSTn MPP(25, 0x6, 0, 0, 1) #define MPP25_UNUSED MPP(25, 0x1, 0, 0, 1) #define MPP26_GPIO MPP(26, 0x0, 1, 1, 1) -#define MPP26_UA2_CTSn MPP(26, 0x4, 1, 0, 1) -#define MPP26_TDM_PCLK MPP(26, 0x6, 1, 1, 1) +#define MPP26_UA2_CTSn MPP(26, 0x4, 0, 0, 1) +#define MPP26_TDM_PCLK MPP(26, 0x6, 0, 0, 1) #define MPP26_UNUSED MPP(26, 0x1, 0, 0, 1) #define MPP27_GPIO MPP(27, 0x0, 1, 1, 1) -#define MPP27_UA2_RTSn MPP(27, 0x4, 0, 1, 1) -#define MPP27_TDM_FSYNC MPP(27, 0x6, 1, 1, 1) +#define MPP27_UA2_RTSn MPP(27, 0x4, 0, 0, 1) +#define MPP27_TDM_FSYNC MPP(27, 0x6, 0, 0, 1) #define MPP27_UNUSED MPP(27, 0x1, 0, 0, 1) #define MPP28_GPIO MPP(28, 0x0, 1, 1, 1) -#define MPP28_UA3_TXD MPP(28, 0x4, 0, 1, 1) -#define MPP28_TDM_DRX MPP(28, 0x6, 1, 0, 1) +#define MPP28_UA3_TXD MPP(28, 0x4, 0, 0, 1) +#define MPP28_TDM_DRX MPP(28, 0x6, 0, 0, 1) #define MPP28_UNUSED MPP(28, 0x1, 0, 0, 1) #define MPP29_GPIO MPP(29, 0x0, 1, 1, 1) -#define MPP29_UA3_RXD MPP(29, 0x4, 1, 0, 1) -#define MPP29_SYSRST_OUTn MPP(29, 0x5, 0, 1, 1) -#define MPP29_TDM_DTX MPP(29, 0x6, 0, 1, 1) +#define MPP29_UA3_RXD MPP(29, 0x4, 0, 0, 1) +#define MPP29_SYSRST_OUTn MPP(29, 0x5, 0, 0, 1) +#define MPP29_TDM_DTX MPP(29, 0x6, 0, 0, 1) #define MPP29_UNUSED MPP(29, 0x1, 0, 0, 1) #define MPP30_GPIO MPP(30, 0x0, 1, 1, 1) -#define MPP30_UA3_CTSn MPP(30, 0x4, 1, 0, 1) +#define MPP30_UA3_CTSn MPP(30, 0x4, 0, 0, 1) #define MPP30_UNUSED MPP(30, 0x1, 0, 0, 1) #define MPP31_GPIO MPP(31, 0x0, 1, 1, 1) -#define MPP31_UA3_RTSn MPP(31, 0x4, 0, 1, 1) -#define MPP31_TDM1_SCSn MPP(31, 0x6, 0, 1, 1) +#define MPP31_UA3_RTSn MPP(31, 0x4, 0, 0, 1) +#define MPP31_TDM1_SCSn MPP(31, 0x6, 0, 0, 1) #define MPP31_UNUSED MPP(31, 0x1, 0, 0, 1) #define MPP32_GPIO MPP(32, 0x1, 1, 1, 1) -#define MPP32_UA3_TDX MPP(32, 0x4, 0, 1, 1) -#define MPP32_SYSRST_OUTn MPP(32, 0x5, 0, 1, 1) -#define MPP32_TDM0_RXQ MPP(32, 0x6, 0, 1, 1) +#define MPP32_UA3_TDX MPP(32, 0x4, 0, 0, 1) +#define MPP32_SYSRST_OUTn MPP(32, 0x5, 0, 0, 1) +#define MPP32_TDM0_RXQ MPP(32, 0x6, 0, 0, 1) #define MPP32_UNUSED MPP(32, 0x3, 0, 0, 1) #define MPP33_GPIO MPP(33, 0x1, 1, 1, 1) -#define MPP33_UA3_RDX MPP(33, 0x4, 1, 0, 1) -#define MPP33_TDM0_TXQ MPP(33, 0x6, 0, 1, 1) +#define MPP33_UA3_RDX MPP(33, 0x4, 0, 0, 1) +#define MPP33_TDM0_TXQ MPP(33, 0x6, 0, 0, 1) #define MPP33_UNUSED MPP(33, 0x3, 0, 0, 1) #define MPP34_GPIO MPP(34, 0x1, 1, 1, 1) -#define MPP34_UA2_TDX MPP(34, 0x4, 0, 1, 1) -#define MPP34_TDM1_RXQ MPP(34, 0x6, 0, 1, 1) +#define MPP34_UA2_TDX MPP(34, 0x4, 0, 0, 1) +#define MPP34_TDM1_RXQ MPP(34, 0x6, 0, 0, 1) #define MPP34_UNUSED MPP(34, 0x3, 0, 0, 1) #define MPP35_GPIO MPP(35, 0x1, 1, 1, 1) -#define MPP35_UA2_RDX MPP(35, 0x4, 1, 0, 1) -#define MPP35_TDM1_TXQ MPP(35, 0x6, 0, 1, 1) +#define MPP35_UA2_RDX MPP(35, 0x4, 0, 0, 1) +#define MPP35_TDM1_TXQ MPP(35, 0x6, 0, 0, 1) #define MPP35_UNUSED MPP(35, 0x3, 0, 0, 1) #define MPP36_GPIO MPP(36, 0x1, 1, 1, 1) -#define MPP36_UA0_CTSn MPP(36, 0x2, 1, 0, 1) -#define MPP36_UA2_TDX MPP(36, 0x4, 0, 1, 1) -#define MPP36_TDM0_SCSn MPP(36, 0x6, 0, 1, 1) +#define MPP36_UA0_CTSn MPP(36, 0x2, 0, 0, 1) +#define MPP36_UA2_TDX MPP(36, 0x4, 0, 0, 1) +#define MPP36_TDM0_SCSn MPP(36, 0x6, 0, 0, 1) #define MPP36_UNUSED MPP(36, 0x3, 0, 0, 1) #define MPP37_GPIO MPP(37, 0x1, 1, 1, 1) -#define MPP37_UA0_RTSn MPP(37, 0x2, 0, 1, 1) -#define MPP37_UA2_RXD MPP(37, 0x4, 1, 0, 1) -#define MPP37_SYSRST_OUTn MPP(37, 0x5, 0, 1, 1) -#define MPP37_TDM_SCLK MPP(37, 0x6, 0, 1, 1) +#define MPP37_UA0_RTSn MPP(37, 0x2, 0, 0, 1) +#define MPP37_UA2_RXD MPP(37, 0x4, 0, 0, 1) +#define MPP37_SYSRST_OUTn MPP(37, 0x5, 0, 0, 1) +#define MPP37_TDM_SCLK MPP(37, 0x6, 0, 0, 1) #define MPP37_UNUSED MPP(37, 0x3, 0, 0, 1) #define MPP38_GPIO MPP(38, 0x1, 1, 1, 1) -#define MPP38_UA1_CTSn MPP(38, 0x2, 1, 0, 1) -#define MPP38_UA3_TXD MPP(38, 0x4, 0, 1, 1) -#define MPP38_SYSRST_OUTn MPP(38, 0x5, 0, 1, 1) -#define MPP38_TDM_SMOSI MPP(38, 0x6, 0, 1, 1) +#define MPP38_UA1_CTSn MPP(38, 0x2, 0, 0, 1) +#define MPP38_UA3_TXD MPP(38, 0x4, 0, 0, 1) +#define MPP38_SYSRST_OUTn MPP(38, 0x5, 0, 0, 1) +#define MPP38_TDM_SMOSI MPP(38, 0x6, 0, 0, 1) #define MPP38_UNUSED MPP(38, 0x3, 0, 0, 1) #define MPP39_GPIO MPP(39, 0x1, 1, 1, 1) -#define MPP39_UA1_RTSn MPP(39, 0x2, 0, 1, 1) -#define MPP39_UA3_RXD MPP(39, 0x4, 1, 0, 1) -#define MPP39_SYSRST_OUTn MPP(39, 0x5, 0, 1, 1) -#define MPP39_TDM_SMISO MPP(39, 0x6, 1, 0, 1) +#define MPP39_UA1_RTSn MPP(39, 0x2, 0, 0, 1) +#define MPP39_UA3_RXD MPP(39, 0x4, 0, 0, 1) +#define MPP39_SYSRST_OUTn MPP(39, 0x5, 0, 0, 1) +#define MPP39_TDM_SMISO MPP(39, 0x6, 0, 0, 1) #define MPP39_UNUSED MPP(39, 0x3, 0, 0, 1) #define MPP40_GPIO MPP(40, 0x1, 1, 1, 1) -#define MPP40_TDM_INTn MPP(40, 0x6, 1, 0, 1) +#define MPP40_TDM_INTn MPP(40, 0x6, 0, 0, 1) #define MPP40_UNUSED MPP(40, 0x0, 0, 0, 1) #define MPP41_GPIO MPP(41, 0x1, 1, 1, 1) -#define MPP41_TDM_RSTn MPP(41, 0x6, 0, 1, 1) +#define MPP41_TDM_RSTn MPP(41, 0x6, 0, 0, 1) #define MPP41_UNUSED MPP(41, 0x0, 0, 0, 1) #define MPP42_GPIO MPP(42, 0x1, 1, 1, 1) -#define MPP42_TDM_PCLK MPP(42, 0x6, 1, 1, 1) +#define MPP42_TDM_PCLK MPP(42, 0x6, 0, 0, 1) #define MPP42_UNUSED MPP(42, 0x0, 0, 0, 1) #define MPP43_GPIO MPP(43, 0x1, 1, 1, 1) -#define MPP43_TDM_FSYNC MPP(43, 0x6, 1, 1, 1) +#define MPP43_TDM_FSYNC MPP(43, 0x6, 0, 0, 1) #define MPP43_UNUSED MPP(43, 0x0, 0, 0, 1) #define MPP44_GPIO MPP(44, 0x1, 1, 1, 1) -#define MPP44_TDM_DRX MPP(44, 0x6, 1, 0, 1) +#define MPP44_TDM_DRX MPP(44, 0x6, 0, 0, 1) #define MPP44_UNUSED MPP(44, 0x0, 0, 0, 1) #define MPP45_GPIO MPP(45, 0x1, 1, 1, 1) -#define MPP45_SATA0_ACTn MPP(45, 0x3, 0, 1, 1) -#define MPP45_TDM_DRX MPP(45, 0x6, 0, 1, 1) +#define MPP45_SATA0_ACTn MPP(45, 0x3, 0, 0, 1) +#define MPP45_TDM_DRX MPP(45, 0x6, 0, 0, 1) #define MPP45_UNUSED MPP(45, 0x0, 0, 0, 1) #define MPP46_GPIO MPP(46, 0x1, 1, 1, 1) -#define MPP46_TDM_SCSn MPP(46, 0x6, 0, 1, 1) +#define MPP46_TDM_SCSn MPP(46, 0x6, 0, 0, 1) #define MPP46_UNUSED MPP(46, 0x0, 0, 0, 1) @@ -323,14 +323,14 @@ #define MPP48_GPIO MPP(48, 0x1, 1, 1, 1) -#define MPP48_SATA1_ACTn MPP(48, 0x3, 0, 1, 1) +#define MPP48_SATA1_ACTn MPP(48, 0x3, 0, 0, 1) #define MPP48_UNUSED MPP(48, 0x2, 0, 0, 1) #define MPP49_GPIO MPP(49, 0x1, 1, 1, 1) -#define MPP49_SATA0_ACTn MPP(49, 0x3, 0, 1, 1) -#define MPP49_M_BB MPP(49, 0x4, 1, 0, 1) +#define MPP49_SATA0_ACTn MPP(49, 0x3, 0, 0, 1) +#define MPP49_M_BB MPP(49, 0x4, 0, 0, 1) #define MPP49_UNUSED MPP(49, 0x2, 0, 0, 1) diff --git a/arch/arm/mach-omap2/board-4430sdp.c b/arch/arm/mach-omap2/board-4430sdp.c index 63de2d3..14a5971 100644 --- a/arch/arm/mach-omap2/board-4430sdp.c +++ b/arch/arm/mach-omap2/board-4430sdp.c @@ -49,8 +49,9 @@ #define ETH_KS8851_QUART 138 #define OMAP4_SFH7741_SENSOR_OUTPUT_GPIO 184 #define OMAP4_SFH7741_ENABLE_GPIO 188 -#define HDMI_GPIO_HPD 60 /* Hot plug pin for HDMI */ +#define HDMI_GPIO_CT_CP_HPD 60 /* HPD mode enable/disable */ #define HDMI_GPIO_LS_OE 41 /* Level shifter for HDMI */ +#define HDMI_GPIO_HPD 63 /* Hotplug detect */ static const int sdp4430_keymap[] = { KEY(0, 0, KEY_E), @@ -578,12 +579,8 @@ static void __init omap_sfh7741prox_init(void) static void sdp4430_hdmi_mux_init(void) { - /* PAD0_HDMI_HPD_PAD1_HDMI_CEC */ - omap_mux_init_signal("hdmi_hpd", - OMAP_PIN_INPUT_PULLUP); omap_mux_init_signal("hdmi_cec", OMAP_PIN_INPUT_PULLUP); - /* PAD0_HDMI_DDC_SCL_PAD1_HDMI_DDC_SDA */ omap_mux_init_signal("hdmi_ddc_scl", OMAP_PIN_INPUT_PULLUP); omap_mux_init_signal("hdmi_ddc_sda", @@ -591,8 +588,9 @@ static void sdp4430_hdmi_mux_init(void) } static struct gpio sdp4430_hdmi_gpios[] = { - { HDMI_GPIO_HPD, GPIOF_OUT_INIT_HIGH, "hdmi_gpio_hpd" }, + { HDMI_GPIO_CT_CP_HPD, GPIOF_OUT_INIT_HIGH, "hdmi_gpio_ct_cp_hpd" }, { HDMI_GPIO_LS_OE, GPIOF_OUT_INIT_HIGH, "hdmi_gpio_ls_oe" }, + { HDMI_GPIO_HPD, GPIOF_DIR_IN, "hdmi_gpio_hpd" }, }; static int sdp4430_panel_enable_hdmi(struct omap_dss_device *dssdev) @@ -609,26 +607,21 @@ static int sdp4430_panel_enable_hdmi(struct omap_dss_device *dssdev) static void sdp4430_panel_disable_hdmi(struct omap_dss_device *dssdev) { - gpio_free(HDMI_GPIO_LS_OE); - gpio_free(HDMI_GPIO_HPD); + gpio_free_array(sdp4430_hdmi_gpios, ARRAY_SIZE(sdp4430_hdmi_gpios)); } +static struct omap_dss_hdmi_data sdp4430_hdmi_data = { + .hpd_gpio = HDMI_GPIO_HPD, +}; + static struct omap_dss_device sdp4430_hdmi_device = { .name = "hdmi", .driver_name = "hdmi_panel", .type = OMAP_DISPLAY_TYPE_HDMI, - .clocks = { - .dispc = { - .dispc_fclk_src = OMAP_DSS_CLK_SRC_FCK, - }, - .hdmi = { - .regn = 15, - .regm2 = 1, - }, - }, .platform_enable = sdp4430_panel_enable_hdmi, .platform_disable = sdp4430_panel_disable_hdmi, .channel = OMAP_DSS_CHANNEL_DIGIT, + .data = &sdp4430_hdmi_data, }; static struct omap_dss_device *sdp4430_dss_devices[] = { @@ -645,6 +638,10 @@ void omap_4430sdp_display_init(void) { sdp4430_hdmi_mux_init(); omap_display_init(&sdp4430_dss_data); + + omap_mux_init_gpio(HDMI_GPIO_LS_OE, OMAP_PIN_OUTPUT); + omap_mux_init_gpio(HDMI_GPIO_CT_CP_HPD, OMAP_PIN_OUTPUT); + omap_mux_init_gpio(HDMI_GPIO_HPD, OMAP_PIN_INPUT_PULLDOWN); } #ifdef CONFIG_OMAP_MUX diff --git a/arch/arm/mach-omap2/board-omap4panda.c b/arch/arm/mach-omap2/board-omap4panda.c index 0cfe200..107dfc3 100644 --- a/arch/arm/mach-omap2/board-omap4panda.c +++ b/arch/arm/mach-omap2/board-omap4panda.c @@ -52,8 +52,9 @@ #define GPIO_HUB_NRESET 62 #define GPIO_WIFI_PMENA 43 #define GPIO_WIFI_IRQ 53 -#define HDMI_GPIO_HPD 60 /* Hot plug pin for HDMI */ +#define HDMI_GPIO_CT_CP_HPD 60 /* HPD mode enable/disable */ #define HDMI_GPIO_LS_OE 41 /* Level shifter for HDMI */ +#define HDMI_GPIO_HPD 63 /* Hotplug detect */ /* wl127x BT, FM, GPS connectivity chip */ static int wl1271_gpios[] = {46, -1, -1}; @@ -614,12 +615,8 @@ int __init omap4_panda_dvi_init(void) static void omap4_panda_hdmi_mux_init(void) { - /* PAD0_HDMI_HPD_PAD1_HDMI_CEC */ - omap_mux_init_signal("hdmi_hpd", - OMAP_PIN_INPUT_PULLUP); omap_mux_init_signal("hdmi_cec", OMAP_PIN_INPUT_PULLUP); - /* PAD0_HDMI_DDC_SCL_PAD1_HDMI_DDC_SDA */ omap_mux_init_signal("hdmi_ddc_scl", OMAP_PIN_INPUT_PULLUP); omap_mux_init_signal("hdmi_ddc_sda", @@ -627,8 +624,9 @@ static void omap4_panda_hdmi_mux_init(void) } static struct gpio panda_hdmi_gpios[] = { - { HDMI_GPIO_HPD, GPIOF_OUT_INIT_HIGH, "hdmi_gpio_hpd" }, + { HDMI_GPIO_CT_CP_HPD, GPIOF_OUT_INIT_HIGH, "hdmi_gpio_ct_cp_hpd" }, { HDMI_GPIO_LS_OE, GPIOF_OUT_INIT_HIGH, "hdmi_gpio_ls_oe" }, + { HDMI_GPIO_HPD, GPIOF_DIR_IN, "hdmi_gpio_hpd" }, }; static int omap4_panda_panel_enable_hdmi(struct omap_dss_device *dssdev) @@ -645,10 +643,13 @@ static int omap4_panda_panel_enable_hdmi(struct omap_dss_device *dssdev) static void omap4_panda_panel_disable_hdmi(struct omap_dss_device *dssdev) { - gpio_free(HDMI_GPIO_LS_OE); - gpio_free(HDMI_GPIO_HPD); + gpio_free_array(panda_hdmi_gpios, ARRAY_SIZE(panda_hdmi_gpios)); } +static struct omap_dss_hdmi_data omap4_panda_hdmi_data = { + .hpd_gpio = HDMI_GPIO_HPD, +}; + static struct omap_dss_device omap4_panda_hdmi_device = { .name = "hdmi", .driver_name = "hdmi_panel", @@ -656,6 +657,7 @@ static struct omap_dss_device omap4_panda_hdmi_device = { .platform_enable = omap4_panda_panel_enable_hdmi, .platform_disable = omap4_panda_panel_disable_hdmi, .channel = OMAP_DSS_CHANNEL_DIGIT, + .data = &omap4_panda_hdmi_data, }; static struct omap_dss_device *omap4_panda_dss_devices[] = { @@ -679,6 +681,10 @@ void omap4_panda_display_init(void) omap4_panda_hdmi_mux_init(); omap_display_init(&omap4_panda_dss_data); + + omap_mux_init_gpio(HDMI_GPIO_LS_OE, OMAP_PIN_OUTPUT); + omap_mux_init_gpio(HDMI_GPIO_CT_CP_HPD, OMAP_PIN_OUTPUT); + omap_mux_init_gpio(HDMI_GPIO_HPD, OMAP_PIN_INPUT_PULLDOWN); } static void __init omap4_panda_init(void) diff --git a/arch/arm/mach-omap2/board-rx51-peripherals.c b/arch/arm/mach-omap2/board-rx51-peripherals.c index 88bd6f7..c565971 100644 --- a/arch/arm/mach-omap2/board-rx51-peripherals.c +++ b/arch/arm/mach-omap2/board-rx51-peripherals.c @@ -133,7 +133,7 @@ static struct platform_device rx51_charger_device = { static void __init rx51_charger_init(void) { WARN_ON(gpio_request_one(RX51_USB_TRANSCEIVER_RST_GPIO, - GPIOF_OUT_INIT_LOW, "isp1704_reset")); + GPIOF_OUT_INIT_HIGH, "isp1704_reset")); platform_device_register(&rx51_charger_device); } diff --git a/arch/arm/mach-omap2/gpmc.c b/arch/arm/mach-omap2/gpmc.c index 130034b..dfffbbf 100644 --- a/arch/arm/mach-omap2/gpmc.c +++ b/arch/arm/mach-omap2/gpmc.c @@ -528,7 +528,13 @@ int gpmc_cs_configure(int cs, int cmd, int wval) case GPMC_CONFIG_DEV_SIZE: regval = gpmc_cs_read_reg(cs, GPMC_CS_CONFIG1); + + /* clear 2 target bits */ + regval &= ~GPMC_CONFIG1_DEVICESIZE(3); + + /* set the proper value */ regval |= GPMC_CONFIG1_DEVICESIZE(wval); + gpmc_cs_write_reg(cs, GPMC_CS_CONFIG1, regval); break; diff --git a/arch/arm/mach-orion5x/common.c b/arch/arm/mach-orion5x/common.c index 0ab531d..8a98da0 100644 --- a/arch/arm/mach-orion5x/common.c +++ b/arch/arm/mach-orion5x/common.c @@ -29,6 +29,7 @@ #include <mach/hardware.h> #include <mach/orion5x.h> #include <plat/orion_nand.h> +#include <plat/ehci-orion.h> #include <plat/time.h> #include <plat/common.h> #include "common.h" @@ -72,7 +73,8 @@ void __init orion5x_map_io(void) void __init orion5x_ehci0_init(void) { orion_ehci_init(&orion5x_mbus_dram_info, - ORION5X_USB0_PHYS_BASE, IRQ_ORION5X_USB0_CTRL); + ORION5X_USB0_PHYS_BASE, IRQ_ORION5X_USB0_CTRL, + EHCI_PHY_ORION); } diff --git a/arch/arm/mach-ux500/Kconfig b/arch/arm/mach-ux500/Kconfig index 9a9706c..6ebdb0d 100644 --- a/arch/arm/mach-ux500/Kconfig +++ b/arch/arm/mach-ux500/Kconfig @@ -7,6 +7,7 @@ config UX500_SOC_COMMON select HAS_MTU select ARM_ERRATA_753970 select ARM_ERRATA_754322 + select ARM_ERRATA_764369 menu "Ux500 SoC" diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S index 07c4bc8..a655d3d 100644 --- a/arch/arm/mm/cache-v7.S +++ b/arch/arm/mm/cache-v7.S @@ -54,9 +54,15 @@ loop1: and r1, r1, #7 @ mask of the bits for current cache only cmp r1, #2 @ see what cache we have at this level blt skip @ skip if no cache, or just i-cache +#ifdef CONFIG_PREEMPT + save_and_disable_irqs_notrace r9 @ make cssr&csidr read atomic +#endif mcr p15, 2, r10, c0, c0, 0 @ select current cache level in cssr isb @ isb to sych the new cssr&csidr mrc p15, 1, r1, c0, c0, 0 @ read the new csidr +#ifdef CONFIG_PREEMPT + restore_irqs_notrace r9 +#endif and r2, r1, #7 @ extract the length of the cache lines add r2, r2, #4 @ add 4 (line length offset) ldr r4, =0x3ff diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 0a309aa..e168799 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -278,10 +278,6 @@ cpu_resume_l1_flags: * Initialise TLB, Caches, and MMU state ready to switch the MMU * on. Return in r0 the new CP15 C1 control register setting. * - * We automatically detect if we have a Harvard cache, and use the - * Harvard cache control instructions insead of the unified cache - * control instructions. - * * This should be able to cover all ARMv7 cores. * * It is assumed that: @@ -379,7 +375,7 @@ __v7_setup: mcr p15, 0, r10, c15, c0, 1 @ write diagnostic register #endif #ifdef CONFIG_ARM_ERRATA_743622 - teq r5, #0x00200000 @ present in r2p* + teq r5, #0x00200000 @ only present in r2p* mrceq p15, 0, r10, c15, c0, 1 @ read diagnostic register orreq r10, r10, #1 << 6 @ set bit #6 mcreq p15, 0, r10, c15, c0, 1 @ write diagnostic register @@ -452,9 +448,7 @@ __v7_setup: #endif 4: mov r10, #0 -#ifdef HARVARD_CACHE mcr p15, 0, r10, c7, c5, 0 @ I+BTB cache invalidate -#endif dsb #ifdef CONFIG_MMU mcr p15, 0, r10, c8, c7, 0 @ invalidate I + D TLBs @@ -469,6 +463,18 @@ __v7_setup: mcr p15, 0, r5, c10, c2, 0 @ write PRRR mcr p15, 0, r6, c10, c2, 1 @ write NMRR #endif +#ifndef CONFIG_ARM_THUMBEE + mrc p15, 0, r0, c0, c1, 0 @ read ID_PFR0 for ThumbEE + and r0, r0, #(0xf << 12) @ ThumbEE enabled field + teq r0, #(1 << 12) @ check if ThumbEE is present + bne 1f + mov r5, #0 + mcr p14, 6, r5, c1, c0, 0 @ Initialize TEEHBR to 0 + mrc p14, 6, r0, c0, c0, 0 @ load TEECR + orr r0, r0, #1 @ set the 1st bit in order to + mcr p14, 6, r0, c0, c0, 0 @ stop userspace TEEHBR access +1: +#endif adr r5, v7_crval ldmia r5, {r5, r6} #ifdef CONFIG_CPU_ENDIAN_BE8 diff --git a/arch/arm/plat-mxc/pwm.c b/arch/arm/plat-mxc/pwm.c index 7a61ef8..f4b68be 100644 --- a/arch/arm/plat-mxc/pwm.c +++ b/arch/arm/plat-mxc/pwm.c @@ -32,6 +32,9 @@ #define MX3_PWMSAR 0x0C /* PWM Sample Register */ #define MX3_PWMPR 0x10 /* PWM Period Register */ #define MX3_PWMCR_PRESCALER(x) (((x - 1) & 0xFFF) << 4) +#define MX3_PWMCR_DOZEEN (1 << 24) +#define MX3_PWMCR_WAITEN (1 << 23) +#define MX3_PWMCR_DBGEN (1 << 22) #define MX3_PWMCR_CLKSRC_IPG_HIGH (2 << 16) #define MX3_PWMCR_CLKSRC_IPG (1 << 16) #define MX3_PWMCR_EN (1 << 0) @@ -74,10 +77,21 @@ int pwm_config(struct pwm_device *pwm, int duty_ns, int period_ns) do_div(c, period_ns); duty_cycles = c; + /* + * according to imx pwm RM, the real period value should be + * PERIOD value in PWMPR plus 2. + */ + if (period_cycles > 2) + period_cycles -= 2; + else + period_cycles = 0; + writel(duty_cycles, pwm->mmio_base + MX3_PWMSAR); writel(period_cycles, pwm->mmio_base + MX3_PWMPR); - cr = MX3_PWMCR_PRESCALER(prescale) | MX3_PWMCR_EN; + cr = MX3_PWMCR_PRESCALER(prescale) | + MX3_PWMCR_DOZEEN | MX3_PWMCR_WAITEN | + MX3_PWMCR_DBGEN | MX3_PWMCR_EN; if (cpu_is_mx25()) cr |= MX3_PWMCR_CLKSRC_IPG; diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c index 9e5451b..11dce87 100644 --- a/arch/arm/plat-orion/common.c +++ b/arch/arm/plat-orion/common.c @@ -806,10 +806,7 @@ void __init orion_xor1_init(unsigned long mapbase_low, /***************************************************************************** * EHCI ****************************************************************************/ -static struct orion_ehci_data orion_ehci_data = { - .phy_version = EHCI_PHY_NA, -}; - +static struct orion_ehci_data orion_ehci_data; static u64 ehci_dmamask = DMA_BIT_MASK(32); @@ -830,9 +827,11 @@ static struct platform_device orion_ehci = { void __init orion_ehci_init(struct mbus_dram_target_info *mbus_dram_info, unsigned long mapbase, - unsigned long irq) + unsigned long irq, + enum orion_ehci_phy_ver phy_version) { orion_ehci_data.dram = mbus_dram_info; + orion_ehci_data.phy_version = phy_version; fill_resources(&orion_ehci, orion_ehci_resources, mapbase, SZ_4K - 1, irq); diff --git a/arch/arm/plat-orion/include/plat/common.h b/arch/arm/plat-orion/include/plat/common.h index a63c357..a2c0e31 100644 --- a/arch/arm/plat-orion/include/plat/common.h +++ b/arch/arm/plat-orion/include/plat/common.h @@ -95,7 +95,8 @@ void __init orion_xor1_init(unsigned long mapbase_low, void __init orion_ehci_init(struct mbus_dram_target_info *mbus_dram_info, unsigned long mapbase, - unsigned long irq); + unsigned long irq, + enum orion_ehci_phy_ver phy_version); void __init orion_ehci_1_init(struct mbus_dram_target_info *mbus_dram_info, unsigned long mapbase, diff --git a/arch/arm/plat-orion/mpp.c b/arch/arm/plat-orion/mpp.c index 9155343..3b1e17b 100644 --- a/arch/arm/plat-orion/mpp.c +++ b/arch/arm/plat-orion/mpp.c @@ -64,8 +64,7 @@ void __init orion_mpp_conf(unsigned int *mpp_list, unsigned int variant_mask, gpio_mode |= GPIO_INPUT_OK; if (*mpp_list & MPP_OUTPUT_MASK) gpio_mode |= GPIO_OUTPUT_OK; - if (sel != 0) - gpio_mode = 0; + orion_gpio_set_valid(num, gpio_mode); } diff --git a/arch/arm/plat-s3c24xx/dma.c b/arch/arm/plat-s3c24xx/dma.c index 539bd0e..0719f49 100644 --- a/arch/arm/plat-s3c24xx/dma.c +++ b/arch/arm/plat-s3c24xx/dma.c @@ -1249,7 +1249,7 @@ static void s3c2410_dma_resume(void) struct s3c2410_dma_chan *cp = s3c2410_chans + dma_channels - 1; int channel; - for (channel = dma_channels - 1; channel >= 0; cp++, channel--) + for (channel = dma_channels - 1; channel >= 0; cp--, channel--) s3c2410_dma_resume_chan(cp); } diff --git a/arch/avr32/Kconfig b/arch/avr32/Kconfig index e9d689b..c614484 100644 --- a/arch/avr32/Kconfig +++ b/arch/avr32/Kconfig @@ -8,6 +8,7 @@ config AVR32 select HAVE_KPROBES select HAVE_GENERIC_HARDIRQS select GENERIC_IRQ_PROBE + select GENERIC_ATOMIC64 select HARDIRQS_SW_RESEND select GENERIC_IRQ_SHOW help diff --git a/arch/ia64/include/asm/futex.h b/arch/ia64/include/asm/futex.h index 8428525..21ab376 100644 --- a/arch/ia64/include/asm/futex.h +++ b/arch/ia64/include/asm/futex.h @@ -107,15 +107,16 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, return -EFAULT; { - register unsigned long r8 __asm ("r8") = 0; + register unsigned long r8 __asm ("r8"); unsigned long prev; __asm__ __volatile__( " mf;; \n" - " mov ar.ccv=%3;; \n" - "[1:] cmpxchg4.acq %0=[%1],%2,ar.ccv \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" (prev) + : "=r" (r8), "=r" (prev) : "r" (uaddr), "r" (newval), "rO" ((long) (unsigned) oldval) : "memory"); diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c index 3be485a..f19de9f 100644 --- a/arch/ia64/kernel/acpi.c +++ b/arch/ia64/kernel/acpi.c @@ -429,22 +429,24 @@ static u32 __devinitdata pxm_flag[PXM_FLAG_LEN]; static struct acpi_table_slit __initdata *slit_table; cpumask_t early_cpu_possible_map = CPU_MASK_NONE; -static int get_processor_proximity_domain(struct acpi_srat_cpu_affinity *pa) +static int __init +get_processor_proximity_domain(struct acpi_srat_cpu_affinity *pa) { int pxm; pxm = pa->proximity_domain_lo; - if (ia64_platform_is("sn2")) + if (ia64_platform_is("sn2") || acpi_srat_revision >= 2) pxm += pa->proximity_domain_hi[0] << 8; return pxm; } -static int get_memory_proximity_domain(struct acpi_srat_mem_affinity *ma) +static int __init +get_memory_proximity_domain(struct acpi_srat_mem_affinity *ma) { int pxm; pxm = ma->proximity_domain; - if (!ia64_platform_is("sn2")) + if (!ia64_platform_is("sn2") && acpi_srat_revision <= 1) pxm &= 0xff; return pxm; diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c index c247de0..1918d76 100644 --- a/arch/m68k/mac/config.c +++ b/arch/m68k/mac/config.c @@ -950,6 +950,9 @@ int __init mac_platform_init(void) { u8 *swim_base; + if (!MACH_IS_MAC) + return -ENODEV; + /* * Serial devices */ diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h index fe6f7c2..bc3c745 100644 --- a/arch/powerpc/include/asm/time.h +++ b/arch/powerpc/include/asm/time.h @@ -219,5 +219,7 @@ DECLARE_PER_CPU(struct cpu_usage, cpu_usage_array); extern void secondary_cpu_time_init(void); extern void iSeries_time_init_early(void); +extern void decrementer_check_overflow(void); + #endif /* __KERNEL__ */ #endif /* __POWERPC_TIME_H */ diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 5b428e3..ca2987d 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -170,16 +170,13 @@ notrace void arch_local_irq_restore(unsigned long en) */ local_paca->hard_enabled = en; -#ifndef CONFIG_BOOKE - /* On server, re-trigger the decrementer if it went negative since - * some processors only trigger on edge transitions of the sign bit. - * - * BookE has a level sensitive decrementer (latches in TSR) so we - * don't need that + /* + * Trigger the decrementer if we have a pending event. Some processors + * only trigger on edge transitions of the sign bit. We might also + * have disabled interrupts long enough that the decrementer wrapped + * to positive. */ - if ((int)mfspr(SPRN_DEC) < 0) - mtspr(SPRN_DEC, 1); -#endif /* CONFIG_BOOKE */ + decrementer_check_overflow(); /* * Force the delivery of pending soft-disabled interrupts on PS3. diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c index 822f630..5793c4b 100644 --- a/arch/powerpc/kernel/perf_event.c +++ b/arch/powerpc/kernel/perf_event.c @@ -865,6 +865,7 @@ static void power_pmu_start(struct perf_event *event, int ef_flags) { unsigned long flags; s64 left; + unsigned long val; if (!event->hw.idx || !event->hw.sample_period) return; @@ -880,7 +881,12 @@ static void power_pmu_start(struct perf_event *event, int ef_flags) event->hw.state = 0; left = local64_read(&event->hw.period_left); - write_pmc(event->hw.idx, left); + + val = 0; + if (left < 0x80000000L) + val = 0x80000000L - left; + + write_pmc(event->hw.idx, val); perf_event_update_userpage(event); perf_pmu_enable(event->pmu); diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 03b29a6..2de304a 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -889,6 +889,15 @@ static void __init clocksource_init(void) clock->name, clock->mult, clock->shift); } +void decrementer_check_overflow(void) +{ + u64 now = get_tb_or_rtc(); + struct decrementer_clock *decrementer = &__get_cpu_var(decrementers); + + if (now >= decrementer->next_tb) + set_dec(1); +} + static int decrementer_set_next_event(unsigned long evt, struct clock_event_device *dev) { diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c index db092d7..53a6be7 100644 --- a/arch/powerpc/platforms/powermac/smp.c +++ b/arch/powerpc/platforms/powermac/smp.c @@ -414,7 +414,7 @@ static struct irqaction psurge_irqaction = { static void __init smp_psurge_setup_cpu(int cpu_nr) { - if (cpu_nr != 0) + if (cpu_nr != 0 || !psurge_start) return; /* reset the entry point so if we get another intr we won't diff --git a/arch/powerpc/platforms/pseries/hvCall_inst.c b/arch/powerpc/platforms/pseries/hvCall_inst.c index f106662..c9311cf 100644 --- a/arch/powerpc/platforms/pseries/hvCall_inst.c +++ b/arch/powerpc/platforms/pseries/hvCall_inst.c @@ -109,7 +109,7 @@ static void probe_hcall_entry(void *ignored, unsigned long opcode, unsigned long if (opcode > MAX_HCALL_OPCODE) return; - h = &get_cpu_var(hcall_stats)[opcode / 4]; + h = &__get_cpu_var(hcall_stats)[opcode / 4]; h->tb_start = mftb(); h->purr_start = mfspr(SPRN_PURR); } @@ -126,8 +126,6 @@ static void probe_hcall_exit(void *ignored, unsigned long opcode, unsigned long h->num_calls++; h->tb_total += mftb() - h->tb_start; h->purr_total += mfspr(SPRN_PURR) - h->purr_start; - - put_cpu_var(hcall_stats); } static int __init hcall_inst_init(void) diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index ed96b37..81e30d9 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -745,6 +745,7 @@ void __trace_hcall_entry(unsigned long opcode, unsigned long *args) goto out; (*depth)++; + preempt_disable(); trace_hcall_entry(opcode, args); (*depth)--; @@ -767,6 +768,7 @@ void __trace_hcall_exit(long opcode, unsigned long retval, (*depth)++; trace_hcall_exit(opcode, retval, retbuf); + preempt_enable(); (*depth)--; out: diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index c03fef7..c395f71 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -89,7 +89,6 @@ config S390 select HAVE_GET_USER_PAGES_FAST select HAVE_ARCH_MUTEX_CPU_RELAX select HAVE_ARCH_JUMP_LABEL if !MARCH_G5 - select HAVE_RCU_TABLE_FREE if SMP select ARCH_INLINE_SPIN_TRYLOCK select ARCH_INLINE_SPIN_TRYLOCK_BH select ARCH_INLINE_SPIN_LOCK @@ -228,6 +227,9 @@ config COMPAT config SYSVIPC_COMPAT def_bool y if COMPAT && SYSVIPC +config KEYS_COMPAT + def_bool y if COMPAT && KEYS + config AUDIT_ARCH def_bool y diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h index da359ca..f7b74bc 100644 --- a/arch/s390/include/asm/compat.h +++ b/arch/s390/include/asm/compat.h @@ -172,13 +172,6 @@ static inline int is_compat_task(void) return is_32bit_task(); } -#else - -static inline int is_compat_task(void) -{ - return 0; -} - #endif static inline void __user *arch_compat_alloc_user_space(long len) diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index 38e71eb..e4b6609 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -22,10 +22,7 @@ void crst_table_free(struct mm_struct *, unsigned long *); unsigned long *page_table_alloc(struct mm_struct *); void page_table_free(struct mm_struct *, unsigned long *); -#ifdef CONFIG_HAVE_RCU_TABLE_FREE void page_table_free_rcu(struct mmu_gather *, unsigned long *); -void __tlb_remove_table(void *_table); -#endif static inline void clear_table(unsigned long *s, unsigned long val, size_t n) { diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h index c687a2c..775a5ee 100644 --- a/arch/s390/include/asm/tlb.h +++ b/arch/s390/include/asm/tlb.h @@ -30,14 +30,10 @@ struct mmu_gather { struct mm_struct *mm; -#ifdef CONFIG_HAVE_RCU_TABLE_FREE struct mmu_table_batch *batch; -#endif unsigned int fullmm; - unsigned int need_flush; }; -#ifdef CONFIG_HAVE_RCU_TABLE_FREE struct mmu_table_batch { struct rcu_head rcu; unsigned int nr; @@ -49,7 +45,6 @@ struct mmu_table_batch { extern void tlb_table_flush(struct mmu_gather *tlb); extern void tlb_remove_table(struct mmu_gather *tlb, void *table); -#endif static inline void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, @@ -57,29 +52,20 @@ static inline void tlb_gather_mmu(struct mmu_gather *tlb, { tlb->mm = mm; tlb->fullmm = full_mm_flush; - tlb->need_flush = 0; -#ifdef CONFIG_HAVE_RCU_TABLE_FREE tlb->batch = NULL; -#endif if (tlb->fullmm) __tlb_flush_mm(mm); } static inline void tlb_flush_mmu(struct mmu_gather *tlb) { - if (!tlb->need_flush) - return; - tlb->need_flush = 0; - __tlb_flush_mm(tlb->mm); -#ifdef CONFIG_HAVE_RCU_TABLE_FREE tlb_table_flush(tlb); -#endif } static inline void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end) { - tlb_flush_mmu(tlb); + tlb_table_flush(tlb); } /* @@ -105,10 +91,8 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, unsigned long address) { -#ifdef CONFIG_HAVE_RCU_TABLE_FREE if (!tlb->fullmm) return page_table_free_rcu(tlb, (unsigned long *) pte); -#endif page_table_free(tlb->mm, (unsigned long *) pte); } @@ -125,10 +109,8 @@ static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, #ifdef __s390x__ if (tlb->mm->context.asce_limit <= (1UL << 31)) return; -#ifdef CONFIG_HAVE_RCU_TABLE_FREE if (!tlb->fullmm) return tlb_remove_table(tlb, pmd); -#endif crst_table_free(tlb->mm, (unsigned long *) pmd); #endif } @@ -146,10 +128,8 @@ static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, #ifdef __s390x__ if (tlb->mm->context.asce_limit <= (1UL << 42)) return; -#ifdef CONFIG_HAVE_RCU_TABLE_FREE if (!tlb->fullmm) return tlb_remove_table(tlb, pud); -#endif crst_table_free(tlb->mm, (unsigned long *) pud); #endif } diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 541a750..abdc2b1 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -28,7 +28,6 @@ #include <asm/irq.h> #include <asm/timer.h> #include <asm/nmi.h> -#include <asm/compat.h> #include <asm/smp.h> #include "entry.h" diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index 5804cfa..5c55466 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -20,8 +20,8 @@ #include <linux/regset.h> #include <linux/tracehook.h> #include <linux/seccomp.h> +#include <linux/compat.h> #include <trace/syscall.h> -#include <asm/compat.h> #include <asm/segment.h> #include <asm/page.h> #include <asm/pgtable.h> diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 0c35dee..0260051 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -42,6 +42,7 @@ #include <linux/reboot.h> #include <linux/topology.h> #include <linux/ftrace.h> +#include <linux/compat.h> #include <asm/ipl.h> #include <asm/uaccess.h> diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index fe103e8..d814f79 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -36,7 +36,6 @@ #include <asm/pgtable.h> #include <asm/irq.h> #include <asm/mmu_context.h> -#include <asm/compat.h> #include "../kernel/entry.h" #ifndef CONFIG_64BIT diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index c9a9f7f..c0cf9ce 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -28,8 +28,8 @@ #include <linux/mm.h> #include <linux/module.h> #include <linux/random.h> +#include <linux/compat.h> #include <asm/pgalloc.h> -#include <asm/compat.h> static unsigned long stack_maxrandom_size(void) { diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 458893f..51b80b9 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -243,8 +243,6 @@ void page_table_free(struct mm_struct *mm, unsigned long *table) } } -#ifdef CONFIG_HAVE_RCU_TABLE_FREE - static void __page_table_free_rcu(void *table, unsigned bit) { struct page *page; @@ -301,7 +299,66 @@ void __tlb_remove_table(void *_table) free_pages((unsigned long) table, ALLOC_ORDER); } -#endif +static void tlb_remove_table_smp_sync(void *arg) +{ + /* Simply deliver the interrupt */ +} + +static void tlb_remove_table_one(void *table) +{ + /* + * This isn't an RCU grace period and hence the page-tables cannot be + * assumed to be actually RCU-freed. + * + * It is however sufficient for software page-table walkers that rely + * on IRQ disabling. See the comment near struct mmu_table_batch. + */ + smp_call_function(tlb_remove_table_smp_sync, NULL, 1); + __tlb_remove_table(table); +} + +static void tlb_remove_table_rcu(struct rcu_head *head) +{ + struct mmu_table_batch *batch; + int i; + + batch = container_of(head, struct mmu_table_batch, rcu); + + for (i = 0; i < batch->nr; i++) + __tlb_remove_table(batch->tables[i]); + + free_page((unsigned long)batch); +} + +void tlb_table_flush(struct mmu_gather *tlb) +{ + struct mmu_table_batch **batch = &tlb->batch; + + if (*batch) { + __tlb_flush_mm(tlb->mm); + call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu); + *batch = NULL; + } +} + +void tlb_remove_table(struct mmu_gather *tlb, void *table) +{ + struct mmu_table_batch **batch = &tlb->batch; + + if (*batch == NULL) { + *batch = (struct mmu_table_batch *) + __get_free_page(GFP_NOWAIT | __GFP_NOWARN); + if (*batch == NULL) { + __tlb_flush_mm(tlb->mm); + tlb_remove_table_one(table); + return; + } + (*batch)->nr = 0; + } + (*batch)->tables[(*batch)->nr++] = table; + if ((*batch)->nr == MAX_TABLE_BATCH) + tlb_table_flush(tlb); +} /* * switch on pgstes for its userspace process (for kvm) diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c index 0e358c2..422110a 100644 --- a/arch/s390/oprofile/init.c +++ b/arch/s390/oprofile/init.c @@ -90,7 +90,7 @@ static ssize_t hwsampler_write(struct file *file, char const __user *buf, return -EINVAL; retval = oprofilefs_ulong_from_user(&val, buf, count); - if (retval) + if (retval <= 0) return retval; if (oprofile_started) diff --git a/arch/score/kernel/entry.S b/arch/score/kernel/entry.S index 577abba..83bb960 100644 --- a/arch/score/kernel/entry.S +++ b/arch/score/kernel/entry.S @@ -408,7 +408,7 @@ ENTRY(handle_sys) sw r9, [r0, PT_EPC] cmpi.c r27, __NR_syscalls # check syscall number - bgtu illegal_syscall + bgeu illegal_syscall slli r8, r27, 2 # get syscall routine la r11, sys_call_table diff --git a/arch/sh/oprofile/common.c b/arch/sh/oprofile/common.c index b4c2d2b..e4dd5d5 100644 --- a/arch/sh/oprofile/common.c +++ b/arch/sh/oprofile/common.c @@ -49,7 +49,7 @@ int __init oprofile_arch_init(struct oprofile_operations *ops) return oprofile_perf_init(ops); } -void __exit oprofile_arch_exit(void) +void oprofile_arch_exit(void) { oprofile_perf_exit(); kfree(sh_pmu_op_name); @@ -60,5 +60,5 @@ int __init oprofile_arch_init(struct oprofile_operations *ops) ops->backtrace = sh_backtrace; return -ENODEV; } -void __exit oprofile_arch_exit(void) {} +void oprofile_arch_exit(void) {} #endif /* CONFIG_HW_PERF_EVENTS */ diff --git a/arch/sparc/Makefile b/arch/sparc/Makefile index ad1fb5d..eddcfb3 100644 --- a/arch/sparc/Makefile +++ b/arch/sparc/Makefile @@ -31,7 +31,7 @@ UTS_MACHINE := sparc #KBUILD_CFLAGS += -g -pipe -fcall-used-g5 -fcall-used-g7 KBUILD_CFLAGS += -m32 -pipe -mno-fpu -fcall-used-g5 -fcall-used-g7 -KBUILD_AFLAGS += -m32 +KBUILD_AFLAGS += -m32 -Wa,-Av8 #LDFLAGS_vmlinux = -N -Ttext 0xf0004000 # Since 2.5.40, the first stage is left not btfix-ed. diff --git a/arch/sparc/include/asm/pgtable_32.h b/arch/sparc/include/asm/pgtable_32.h index 5b31a8e..a790cc6 100644 --- a/arch/sparc/include/asm/pgtable_32.h +++ b/arch/sparc/include/asm/pgtable_32.h @@ -431,10 +431,6 @@ extern unsigned long *sparc_valid_addr_bitmap; #define kern_addr_valid(addr) \ (test_bit(__pa((unsigned long)(addr))>>20, sparc_valid_addr_bitmap)) -extern int io_remap_pfn_range(struct vm_area_struct *vma, - unsigned long from, unsigned long pfn, - unsigned long size, pgprot_t prot); - /* * For sparc32&64, the pfn in io_remap_pfn_range() carries <iospace> in * its high 4 bits. These macros/functions put it there or get it from there. @@ -443,6 +439,22 @@ extern int io_remap_pfn_range(struct vm_area_struct *vma, #define GET_IOSPACE(pfn) (pfn >> (BITS_PER_LONG - 4)) #define GET_PFN(pfn) (pfn & 0x0fffffffUL) +extern int remap_pfn_range(struct vm_area_struct *, unsigned long, unsigned long, + unsigned long, pgprot_t); + +static inline int io_remap_pfn_range(struct vm_area_struct *vma, + unsigned long from, unsigned long pfn, + unsigned long size, pgprot_t prot) +{ + unsigned long long offset, space, phys_base; + + offset = ((unsigned long long) GET_PFN(pfn)) << PAGE_SHIFT; + space = GET_IOSPACE(pfn); + phys_base = offset | (space << 32ULL); + + return remap_pfn_range(vma, from, phys_base >> PAGE_SHIFT, size, prot); +} + #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS #define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \ ({ \ diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 1e03c5a..9822628 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -750,10 +750,6 @@ static inline bool kern_addr_valid(unsigned long addr) extern int page_in_phys_avail(unsigned long paddr); -extern int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from, - unsigned long pfn, - unsigned long size, pgprot_t prot); - /* * For sparc32&64, the pfn in io_remap_pfn_range() carries <iospace> in * its high 4 bits. These macros/functions put it there or get it from there. @@ -762,6 +758,22 @@ extern int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from, #define GET_IOSPACE(pfn) (pfn >> (BITS_PER_LONG - 4)) #define GET_PFN(pfn) (pfn & 0x0fffffffffffffffUL) +extern int remap_pfn_range(struct vm_area_struct *, unsigned long, unsigned long, + unsigned long, pgprot_t); + +static inline int io_remap_pfn_range(struct vm_area_struct *vma, + unsigned long from, unsigned long pfn, + unsigned long size, pgprot_t prot) +{ + unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT; + int space = GET_IOSPACE(pfn); + unsigned long phys_base; + + phys_base = offset | (((unsigned long) space) << 32UL); + + return remap_pfn_range(vma, from, phys_base >> PAGE_SHIFT, size, prot); +} + #include <asm-generic/pgtable.h> /* We provide our own get_unmapped_area to cope with VA holes and diff --git a/arch/sparc/kernel/ds.c b/arch/sparc/kernel/ds.c index 7429b47..dcae702 100644 --- a/arch/sparc/kernel/ds.c +++ b/arch/sparc/kernel/ds.c @@ -1269,4 +1269,4 @@ static int __init ds_init(void) return vio_register_driver(&ds_driver); } -subsys_initcall(ds_init); +fs_initcall(ds_init); diff --git a/arch/sparc/kernel/entry.h b/arch/sparc/kernel/entry.h index e27f8ea..0c218e4 100644 --- a/arch/sparc/kernel/entry.h +++ b/arch/sparc/kernel/entry.h @@ -42,6 +42,9 @@ extern void fpsave(unsigned long *fpregs, unsigned long *fsr, extern void fpload(unsigned long *fpregs, unsigned long *fsr); #else /* CONFIG_SPARC32 */ + +#include <asm/trap_block.h> + struct popc_3insn_patch_entry { unsigned int addr; unsigned int insns[3]; @@ -57,6 +60,10 @@ extern struct popc_6insn_patch_entry __popc_6insn_patch, __popc_6insn_patch_end; extern void __init per_cpu_patch(void); +extern void sun4v_patch_1insn_range(struct sun4v_1insn_patch_entry *, + struct sun4v_1insn_patch_entry *); +extern void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *, + struct sun4v_2insn_patch_entry *); extern void __init sun4v_patch(void); extern void __init boot_cpu_id_too_large(int cpu); extern unsigned int dcache_parity_tl1_occurred; diff --git a/arch/sparc/kernel/module.c b/arch/sparc/kernel/module.c index 99ba5ba..8172c18 100644 --- a/arch/sparc/kernel/module.c +++ b/arch/sparc/kernel/module.c @@ -17,6 +17,8 @@ #include <asm/processor.h> #include <asm/spitfire.h> +#include "entry.h" + #ifdef CONFIG_SPARC64 #include <linux/jump_label.h> @@ -220,6 +222,29 @@ int apply_relocate_add(Elf_Shdr *sechdrs, } #ifdef CONFIG_SPARC64 +static void do_patch_sections(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs) +{ + const Elf_Shdr *s, *sun4v_1insn = NULL, *sun4v_2insn = NULL; + char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; + + for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) { + if (!strcmp(".sun4v_1insn_patch", secstrings + s->sh_name)) + sun4v_1insn = s; + if (!strcmp(".sun4v_2insn_patch", secstrings + s->sh_name)) + sun4v_2insn = s; + } + + if (sun4v_1insn && tlb_type == hypervisor) { + void *p = (void *) sun4v_1insn->sh_addr; + sun4v_patch_1insn_range(p, p + sun4v_1insn->sh_size); + } + if (sun4v_2insn && tlb_type == hypervisor) { + void *p = (void *) sun4v_2insn->sh_addr; + sun4v_patch_2insn_range(p, p + sun4v_2insn->sh_size); + } +} + int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *me) @@ -227,6 +252,8 @@ int module_finalize(const Elf_Ehdr *hdr, /* make jump label nops */ jump_label_apply_nops(me); + do_patch_sections(hdr, sechdrs); + /* Cheetah's I-cache is fully coherent. */ if (tlb_type == spitfire) { unsigned long va; diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c index b01a06e..9e73c4a 100644 --- a/arch/sparc/kernel/pci_sun4v.c +++ b/arch/sparc/kernel/pci_sun4v.c @@ -848,10 +848,10 @@ static int pci_sun4v_msiq_build_irq(struct pci_pbm_info *pbm, if (!irq) return -ENOMEM; - if (pci_sun4v_msiq_setstate(pbm->devhandle, msiqid, HV_MSIQSTATE_IDLE)) - return -EINVAL; if (pci_sun4v_msiq_setvalid(pbm->devhandle, msiqid, HV_MSIQ_VALID)) return -EINVAL; + if (pci_sun4v_msiq_setstate(pbm->devhandle, msiqid, HV_MSIQSTATE_IDLE)) + return -EINVAL; return irq; } diff --git a/arch/sparc/kernel/rtrap_64.S b/arch/sparc/kernel/rtrap_64.S index 77f1b95..9171fc2 100644 --- a/arch/sparc/kernel/rtrap_64.S +++ b/arch/sparc/kernel/rtrap_64.S @@ -20,11 +20,6 @@ .text .align 32 -__handle_softirq: - call do_softirq - nop - ba,a,pt %xcc, __handle_softirq_continue - nop __handle_preemption: call schedule wrpr %g0, RTRAP_PSTATE, %pstate @@ -89,9 +84,7 @@ rtrap: cmp %l1, 0 /* mm/ultra.S:xcall_report_regs KNOWS about this load. */ - bne,pn %icc, __handle_softirq ldx [%sp + PTREGS_OFF + PT_V9_TSTATE], %l1 -__handle_softirq_continue: rtrap_xcall: sethi %hi(0xf << 20), %l4 and %l1, %l4, %l4 diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c index 3c5bb78..4e7d3ff 100644 --- a/arch/sparc/kernel/setup_64.c +++ b/arch/sparc/kernel/setup_64.c @@ -234,40 +234,50 @@ void __init per_cpu_patch(void) } } -void __init sun4v_patch(void) +void sun4v_patch_1insn_range(struct sun4v_1insn_patch_entry *start, + struct sun4v_1insn_patch_entry *end) { - extern void sun4v_hvapi_init(void); - struct sun4v_1insn_patch_entry *p1; - struct sun4v_2insn_patch_entry *p2; - - if (tlb_type != hypervisor) - return; + while (start < end) { + unsigned long addr = start->addr; - p1 = &__sun4v_1insn_patch; - while (p1 < &__sun4v_1insn_patch_end) { - unsigned long addr = p1->addr; - - *(unsigned int *) (addr + 0) = p1->insn; + *(unsigned int *) (addr + 0) = start->insn; wmb(); __asm__ __volatile__("flush %0" : : "r" (addr + 0)); - p1++; + start++; } +} - p2 = &__sun4v_2insn_patch; - while (p2 < &__sun4v_2insn_patch_end) { - unsigned long addr = p2->addr; +void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *start, + struct sun4v_2insn_patch_entry *end) +{ + while (start < end) { + unsigned long addr = start->addr; - *(unsigned int *) (addr + 0) = p2->insns[0]; + *(unsigned int *) (addr + 0) = start->insns[0]; wmb(); __asm__ __volatile__("flush %0" : : "r" (addr + 0)); - *(unsigned int *) (addr + 4) = p2->insns[1]; + *(unsigned int *) (addr + 4) = start->insns[1]; wmb(); __asm__ __volatile__("flush %0" : : "r" (addr + 4)); - p2++; + start++; } +} + +void __init sun4v_patch(void) +{ + extern void sun4v_hvapi_init(void); + + if (tlb_type != hypervisor) + return; + + sun4v_patch_1insn_range(&__sun4v_1insn_patch, + &__sun4v_1insn_patch_end); + + sun4v_patch_2insn_range(&__sun4v_2insn_patch, + &__sun4v_2insn_patch_end); sun4v_hvapi_init(); } diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c index 5d92488..2e58328 100644 --- a/arch/sparc/kernel/signal32.c +++ b/arch/sparc/kernel/signal32.c @@ -829,21 +829,23 @@ static inline void syscall_restart32(unsigned long orig_i0, struct pt_regs *regs * want to handle. Thus you cannot kill init even with a SIGKILL even by * mistake. */ -void do_signal32(sigset_t *oldset, struct pt_regs * regs, - int restart_syscall, unsigned long orig_i0) +void do_signal32(sigset_t *oldset, struct pt_regs * regs) { struct k_sigaction ka; + unsigned long orig_i0; + int restart_syscall; siginfo_t info; int signr; signr = get_signal_to_deliver(&info, &ka, regs, NULL); - /* If the debugger messes with the program counter, it clears - * the "in syscall" bit, directing us to not perform a syscall - * restart. - */ - if (restart_syscall && !pt_regs_is_syscall(regs)) - restart_syscall = 0; + restart_syscall = 0; + orig_i0 = 0; + if (pt_regs_is_syscall(regs) && + (regs->tstate & (TSTATE_XCARRY | TSTATE_ICARRY))) { + restart_syscall = 1; + orig_i0 = regs->u_regs[UREG_G6]; + } if (signr > 0) { if (restart_syscall) diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c index 04ede8f..2302567 100644 --- a/arch/sparc/kernel/signal_32.c +++ b/arch/sparc/kernel/signal_32.c @@ -525,10 +525,26 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0) siginfo_t info; int signr; + /* It's a lot of work and synchronization to add a new ptrace + * register for GDB to save and restore in order to get + * orig_i0 correct for syscall restarts when debugging. + * + * Although it should be the case that most of the global + * registers are volatile across a system call, glibc already + * depends upon that fact that we preserve them. So we can't + * just use any global register to save away the orig_i0 value. + * + * In particular %g2, %g3, %g4, and %g5 are all assumed to be + * preserved across a system call trap by various pieces of + * code in glibc. + * + * %g7 is used as the "thread register". %g6 is not used in + * any fixed manner. %g6 is used as a scratch register and + * a compiler temporary, but it's value is never used across + * a system call. Therefore %g6 is usable for orig_i0 storage. + */ if (pt_regs_is_syscall(regs) && (regs->psr & PSR_C)) - restart_syscall = 1; - else - restart_syscall = 0; + regs->u_regs[UREG_G6] = orig_i0; if (test_thread_flag(TIF_RESTORE_SIGMASK)) oldset = ¤t->saved_sigmask; @@ -541,8 +557,12 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0) * the software "in syscall" bit, directing us to not perform * a syscall restart. */ - if (restart_syscall && !pt_regs_is_syscall(regs)) - restart_syscall = 0; + restart_syscall = 0; + if (pt_regs_is_syscall(regs) && (regs->psr & PSR_C)) { + restart_syscall = 1; + orig_i0 = regs->u_regs[UREG_G6]; + } + if (signr > 0) { if (restart_syscall) diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c index 47509df..d58260b 100644 --- a/arch/sparc/kernel/signal_64.c +++ b/arch/sparc/kernel/signal_64.c @@ -535,11 +535,27 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0) siginfo_t info; int signr; + /* It's a lot of work and synchronization to add a new ptrace + * register for GDB to save and restore in order to get + * orig_i0 correct for syscall restarts when debugging. + * + * Although it should be the case that most of the global + * registers are volatile across a system call, glibc already + * depends upon that fact that we preserve them. So we can't + * just use any global register to save away the orig_i0 value. + * + * In particular %g2, %g3, %g4, and %g5 are all assumed to be + * preserved across a system call trap by various pieces of + * code in glibc. + * + * %g7 is used as the "thread register". %g6 is not used in + * any fixed manner. %g6 is used as a scratch register and + * a compiler temporary, but it's value is never used across + * a system call. Therefore %g6 is usable for orig_i0 storage. + */ if (pt_regs_is_syscall(regs) && - (regs->tstate & (TSTATE_XCARRY | TSTATE_ICARRY))) { - restart_syscall = 1; - } else - restart_syscall = 0; + (regs->tstate & (TSTATE_XCARRY | TSTATE_ICARRY))) + regs->u_regs[UREG_G6] = orig_i0; if (current_thread_info()->status & TS_RESTORE_SIGMASK) oldset = ¤t->saved_sigmask; @@ -548,22 +564,20 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0) #ifdef CONFIG_COMPAT if (test_thread_flag(TIF_32BIT)) { - extern void do_signal32(sigset_t *, struct pt_regs *, - int restart_syscall, - unsigned long orig_i0); - do_signal32(oldset, regs, restart_syscall, orig_i0); + extern void do_signal32(sigset_t *, struct pt_regs *); + do_signal32(oldset, regs); return; } #endif signr = get_signal_to_deliver(&info, &ka, regs, NULL); - /* If the debugger messes with the program counter, it clears - * the software "in syscall" bit, directing us to not perform - * a syscall restart. - */ - if (restart_syscall && !pt_regs_is_syscall(regs)) - restart_syscall = 0; + restart_syscall = 0; + if (pt_regs_is_syscall(regs) && + (regs->tstate & (TSTATE_XCARRY | TSTATE_ICARRY))) { + restart_syscall = 1; + orig_i0 = regs->u_regs[UREG_G6]; + } if (signr > 0) { if (restart_syscall) diff --git a/arch/sparc/kernel/visemul.c b/arch/sparc/kernel/visemul.c index 3635771..9384a0c 100644 --- a/arch/sparc/kernel/visemul.c +++ b/arch/sparc/kernel/visemul.c @@ -713,17 +713,17 @@ static void pcmp(struct pt_regs *regs, unsigned int insn, unsigned int opf) s16 b = (rs2 >> (i * 16)) & 0xffff; if (a > b) - rd_val |= 1 << i; + rd_val |= 8 >> i; } break; case FCMPGT32_OPF: for (i = 0; i < 2; i++) { - s32 a = (rs1 >> (i * 32)) & 0xffff; - s32 b = (rs2 >> (i * 32)) & 0xffff; + s32 a = (rs1 >> (i * 32)) & 0xffffffff; + s32 b = (rs2 >> (i * 32)) & 0xffffffff; if (a > b) - rd_val |= 1 << i; + rd_val |= 2 >> i; } break; @@ -733,17 +733,17 @@ static void pcmp(struct pt_regs *regs, unsigned int insn, unsigned int opf) s16 b = (rs2 >> (i * 16)) & 0xffff; if (a <= b) - rd_val |= 1 << i; + rd_val |= 8 >> i; } break; case FCMPLE32_OPF: for (i = 0; i < 2; i++) { - s32 a = (rs1 >> (i * 32)) & 0xffff; - s32 b = (rs2 >> (i * 32)) & 0xffff; + s32 a = (rs1 >> (i * 32)) & 0xffffffff; + s32 b = (rs2 >> (i * 32)) & 0xffffffff; if (a <= b) - rd_val |= 1 << i; + rd_val |= 2 >> i; } break; @@ -753,17 +753,17 @@ static void pcmp(struct pt_regs *regs, unsigned int insn, unsigned int opf) s16 b = (rs2 >> (i * 16)) & 0xffff; if (a != b) - rd_val |= 1 << i; + rd_val |= 8 >> i; } break; case FCMPNE32_OPF: for (i = 0; i < 2; i++) { - s32 a = (rs1 >> (i * 32)) & 0xffff; - s32 b = (rs2 >> (i * 32)) & 0xffff; + s32 a = (rs1 >> (i * 32)) & 0xffffffff; + s32 b = (rs2 >> (i * 32)) & 0xffffffff; if (a != b) - rd_val |= 1 << i; + rd_val |= 2 >> i; } break; @@ -773,17 +773,17 @@ static void pcmp(struct pt_regs *regs, unsigned int insn, unsigned int opf) s16 b = (rs2 >> (i * 16)) & 0xffff; if (a == b) - rd_val |= 1 << i; + rd_val |= 8 >> i; } break; case FCMPEQ32_OPF: for (i = 0; i < 2; i++) { - s32 a = (rs1 >> (i * 32)) & 0xffff; - s32 b = (rs2 >> (i * 32)) & 0xffff; + s32 a = (rs1 >> (i * 32)) & 0xffffffff; + s32 b = (rs2 >> (i * 32)) & 0xffffffff; if (a == b) - rd_val |= 1 << i; + rd_val |= 2 >> i; } break; } diff --git a/arch/sparc/lib/memcpy.S b/arch/sparc/lib/memcpy.S index 34fe657..4d8c497 100644 --- a/arch/sparc/lib/memcpy.S +++ b/arch/sparc/lib/memcpy.S @@ -7,40 +7,12 @@ * Copyright (C) 1996 Jakub Jelinek (jj@sunsite.mff.cuni.cz) */ -#ifdef __KERNEL__ - -#define FUNC(x) \ +#define FUNC(x) \ .globl x; \ .type x,@function; \ - .align 4; \ + .align 4; \ x: -#undef FASTER_REVERSE -#undef FASTER_NONALIGNED -#define FASTER_ALIGNED - -/* In kernel these functions don't return a value. - * One should use macros in asm/string.h for that purpose. - * We return 0, so that bugs are more apparent. - */ -#define SETUP_RETL -#define RETL_INSN clr %o0 - -#else - -/* libc */ - -#include "DEFS.h" - -#define FASTER_REVERSE -#define FASTER_NONALIGNED -#define FASTER_ALIGNED - -#define SETUP_RETL mov %o0, %g6 -#define RETL_INSN mov %g6, %o0 - -#endif - /* Both these macros have to start with exactly the same insn */ #define MOVE_BIGCHUNK(src, dst, offset, t0, t1, t2, t3, t4, t5, t6, t7) \ ldd [%src + (offset) + 0x00], %t0; \ @@ -164,30 +136,6 @@ x: .text .align 4 -#ifdef FASTER_REVERSE - -70: /* rdword_align */ - - andcc %o1, 1, %g0 - be 4f - andcc %o1, 2, %g0 - - ldub [%o1 - 1], %g2 - sub %o1, 1, %o1 - stb %g2, [%o0 - 1] - sub %o2, 1, %o2 - be 3f - sub %o0, 1, %o0 -4: - lduh [%o1 - 2], %g2 - sub %o1, 2, %o1 - sth %g2, [%o0 - 2] - sub %o2, 2, %o2 - b 3f - sub %o0, 2, %o0 - -#endif /* FASTER_REVERSE */ - 0: retl nop ! Only bcopy returns here and it retuns void... @@ -198,7 +146,7 @@ FUNC(__memmove) #endif FUNC(memmove) cmp %o0, %o1 - SETUP_RETL + mov %o0, %g7 bleu 9f sub %o0, %o1, %o4 @@ -207,8 +155,6 @@ FUNC(memmove) bleu 0f andcc %o4, 3, %o5 -#ifndef FASTER_REVERSE - add %o1, %o2, %o1 add %o0, %o2, %o0 sub %o1, 1, %o1 @@ -224,295 +170,7 @@ FUNC(memmove) sub %o0, 1, %o0 retl - RETL_INSN - -#else /* FASTER_REVERSE */ - - add %o1, %o2, %o1 - add %o0, %o2, %o0 - bne 77f - cmp %o2, 15 - bleu 91f - andcc %o1, 3, %g0 - bne 70b -3: - andcc %o1, 4, %g0 - - be 2f - mov %o2, %g1 - - ld [%o1 - 4], %o4 - sub %g1, 4, %g1 - st %o4, [%o0 - 4] - sub %o1, 4, %o1 - sub %o0, 4, %o0 -2: - andcc %g1, 0xffffff80, %g7 - be 3f - andcc %o0, 4, %g0 - - be 74f + 4 -5: - RMOVE_BIGCHUNK(o1, o0, 0x00, o2, o3, o4, o5, g2, g3, g4, g5) - RMOVE_BIGCHUNK(o1, o0, 0x20, o2, o3, o4, o5, g2, g3, g4, g5) - RMOVE_BIGCHUNK(o1, o0, 0x40, o2, o3, o4, o5, g2, g3, g4, g5) - RMOVE_BIGCHUNK(o1, o0, 0x60, o2, o3, o4, o5, g2, g3, g4, g5) - subcc %g7, 128, %g7 - sub %o1, 128, %o1 - bne 5b - sub %o0, 128, %o0 -3: - andcc %g1, 0x70, %g7 - be 72f - andcc %g1, 8, %g0 - - sethi %hi(72f), %o5 - srl %g7, 1, %o4 - add %g7, %o4, %o4 - sub %o1, %g7, %o1 - sub %o5, %o4, %o5 - jmpl %o5 + %lo(72f), %g0 - sub %o0, %g7, %o0 - -71: /* rmemcpy_table */ - RMOVE_LASTCHUNK(o1, o0, 0x60, g2, g3, g4, g5) - RMOVE_LASTCHUNK(o1, o0, 0x50, g2, g3, g4, g5) - RMOVE_LASTCHUNK(o1, o0, 0x40, g2, g3, g4, g5) - RMOVE_LASTCHUNK(o1, o0, 0x30, g2, g3, g4, g5) - RMOVE_LASTCHUNK(o1, o0, 0x20, g2, g3, g4, g5) - RMOVE_LASTCHUNK(o1, o0, 0x10, g2, g3, g4, g5) - RMOVE_LASTCHUNK(o1, o0, 0x00, g2, g3, g4, g5) - -72: /* rmemcpy_table_end */ - - be 73f - andcc %g1, 4, %g0 - - ldd [%o1 - 0x08], %g2 - sub %o0, 8, %o0 - sub %o1, 8, %o1 - st %g2, [%o0] - st %g3, [%o0 + 0x04] - -73: /* rmemcpy_last7 */ - - be 1f - andcc %g1, 2, %g0 - - ld [%o1 - 4], %g2 - sub %o1, 4, %o1 - st %g2, [%o0 - 4] - sub %o0, 4, %o0 -1: - be 1f - andcc %g1, 1, %g0 - - lduh [%o1 - 2], %g2 - sub %o1, 2, %o1 - sth %g2, [%o0 - 2] - sub %o0, 2, %o0 -1: - be 1f - nop - - ldub [%o1 - 1], %g2 - stb %g2, [%o0 - 1] -1: - retl - RETL_INSN - -74: /* rldd_std */ - RMOVE_BIGALIGNCHUNK(o1, o0, 0x00, o2, o3, o4, o5, g2, g3, g4, g5) - RMOVE_BIGALIGNCHUNK(o1, o0, 0x20, o2, o3, o4, o5, g2, g3, g4, g5) - RMOVE_BIGALIGNCHUNK(o1, o0, 0x40, o2, o3, o4, o5, g2, g3, g4, g5) - RMOVE_BIGALIGNCHUNK(o1, o0, 0x60, o2, o3, o4, o5, g2, g3, g4, g5) - subcc %g7, 128, %g7 - sub %o1, 128, %o1 - bne 74b - sub %o0, 128, %o0 - - andcc %g1, 0x70, %g7 - be 72b - andcc %g1, 8, %g0 - - sethi %hi(72b), %o5 - srl %g7, 1, %o4 - add %g7, %o4, %o4 - sub %o1, %g7, %o1 - sub %o5, %o4, %o5 - jmpl %o5 + %lo(72b), %g0 - sub %o0, %g7, %o0 - -75: /* rshort_end */ - - and %o2, 0xe, %o3 -2: - sethi %hi(76f), %o5 - sll %o3, 3, %o4 - sub %o0, %o3, %o0 - sub %o5, %o4, %o5 - sub %o1, %o3, %o1 - jmpl %o5 + %lo(76f), %g0 - andcc %o2, 1, %g0 - - RMOVE_SHORTCHUNK(o1, o0, 0x0c, g2, g3) - RMOVE_SHORTCHUNK(o1, o0, 0x0a, g2, g3) - RMOVE_SHORTCHUNK(o1, o0, 0x08, g2, g3) - RMOVE_SHORTCHUNK(o1, o0, 0x06, g2, g3) - RMOVE_SHORTCHUNK(o1, o0, 0x04, g2, g3) - RMOVE_SHORTCHUNK(o1, o0, 0x02, g2, g3) - RMOVE_SHORTCHUNK(o1, o0, 0x00, g2, g3) - -76: /* rshort_table_end */ - - be 1f - nop - ldub [%o1 - 1], %g2 - stb %g2, [%o0 - 1] -1: - retl - RETL_INSN - -91: /* rshort_aligned_end */ - - bne 75b - andcc %o2, 8, %g0 - - be 1f - andcc %o2, 4, %g0 - - ld [%o1 - 0x08], %g2 - ld [%o1 - 0x04], %g3 - sub %o1, 8, %o1 - st %g2, [%o0 - 0x08] - st %g3, [%o0 - 0x04] - sub %o0, 8, %o0 -1: - b 73b - mov %o2, %g1 - -77: /* rnon_aligned */ - cmp %o2, 15 - bleu 75b - andcc %o0, 3, %g0 - be 64f - andcc %o0, 1, %g0 - be 63f - andcc %o0, 2, %g0 - ldub [%o1 - 1], %g5 - sub %o1, 1, %o1 - stb %g5, [%o0 - 1] - sub %o0, 1, %o0 - be 64f - sub %o2, 1, %o2 -63: - ldub [%o1 - 1], %g5 - sub %o1, 2, %o1 - stb %g5, [%o0 - 1] - sub %o0, 2, %o0 - ldub [%o1], %g5 - sub %o2, 2, %o2 - stb %g5, [%o0] -64: - and %o1, 3, %g2 - and %o1, -4, %o1 - and %o2, 0xc, %g3 - add %o1, 4, %o1 - cmp %g3, 4 - sll %g2, 3, %g4 - mov 32, %g2 - be 4f - sub %g2, %g4, %g7 - - blu 3f - cmp %g3, 8 - - be 2f - srl %o2, 2, %g3 - - ld [%o1 - 4], %o3 - add %o0, -8, %o0 - ld [%o1 - 8], %o4 - add %o1, -16, %o1 - b 7f - add %g3, 1, %g3 -2: - ld [%o1 - 4], %o4 - add %o0, -4, %o0 - ld [%o1 - 8], %g1 - add %o1, -12, %o1 - b 8f - add %g3, 2, %g3 -3: - ld [%o1 - 4], %o5 - add %o0, -12, %o0 - ld [%o1 - 8], %o3 - add %o1, -20, %o1 - b 6f - srl %o2, 2, %g3 -4: - ld [%o1 - 4], %g1 - srl %o2, 2, %g3 - ld [%o1 - 8], %o5 - add %o1, -24, %o1 - add %o0, -16, %o0 - add %g3, -1, %g3 - - ld [%o1 + 12], %o3 -5: - sll %o5, %g4, %g2 - srl %g1, %g7, %g5 - or %g2, %g5, %g2 - st %g2, [%o0 + 12] -6: - ld [%o1 + 8], %o4 - sll %o3, %g4, %g2 - srl %o5, %g7, %g5 - or %g2, %g5, %g2 - st %g2, [%o0 + 8] -7: - ld [%o1 + 4], %g1 - sll %o4, %g4, %g2 - srl %o3, %g7, %g5 - or %g2, %g5, %g2 - st %g2, [%o0 + 4] -8: - ld [%o1], %o5 - sll %g1, %g4, %g2 - srl %o4, %g7, %g5 - addcc %g3, -4, %g3 - or %g2, %g5, %g2 - add %o1, -16, %o1 - st %g2, [%o0] - add %o0, -16, %o0 - bne,a 5b - ld [%o1 + 12], %o3 - sll %o5, %g4, %g2 - srl %g1, %g7, %g5 - srl %g4, 3, %g3 - or %g2, %g5, %g2 - add %o1, %g3, %o1 - andcc %o2, 2, %g0 - st %g2, [%o0 + 12] - be 1f - andcc %o2, 1, %g0 - - ldub [%o1 + 15], %g5 - add %o1, -2, %o1 - stb %g5, [%o0 + 11] - add %o0, -2, %o0 - ldub [%o1 + 16], %g5 - stb %g5, [%o0 + 12] -1: - be 1f - nop - ldub [%o1 + 15], %g5 - stb %g5, [%o0 + 11] -1: - retl - RETL_INSN - -#endif /* FASTER_REVERSE */ + mov %g7, %o0 /* NOTE: This code is executed just for the cases, where %src (=%o1) & 3 is != 0. @@ -546,7 +204,7 @@ FUNC(memmove) FUNC(memcpy) /* %o0=dst %o1=src %o2=len */ sub %o0, %o1, %o4 - SETUP_RETL + mov %o0, %g7 9: andcc %o4, 3, %o5 0: @@ -569,7 +227,7 @@ FUNC(memcpy) /* %o0=dst %o1=src %o2=len */ add %o1, 4, %o1 add %o0, 4, %o0 2: - andcc %g1, 0xffffff80, %g7 + andcc %g1, 0xffffff80, %g0 be 3f andcc %o0, 4, %g0 @@ -579,22 +237,23 @@ FUNC(memcpy) /* %o0=dst %o1=src %o2=len */ MOVE_BIGCHUNK(o1, o0, 0x20, o2, o3, o4, o5, g2, g3, g4, g5) MOVE_BIGCHUNK(o1, o0, 0x40, o2, o3, o4, o5, g2, g3, g4, g5) MOVE_BIGCHUNK(o1, o0, 0x60, o2, o3, o4, o5, g2, g3, g4, g5) - subcc %g7, 128, %g7 + sub %g1, 128, %g1 add %o1, 128, %o1 - bne 5b + cmp %g1, 128 + bge 5b add %o0, 128, %o0 3: - andcc %g1, 0x70, %g7 + andcc %g1, 0x70, %g4 be 80f andcc %g1, 8, %g0 sethi %hi(80f), %o5 - srl %g7, 1, %o4 - add %g7, %o4, %o4 - add %o1, %g7, %o1 + srl %g4, 1, %o4 + add %g4, %o4, %o4 + add %o1, %g4, %o1 sub %o5, %o4, %o5 jmpl %o5 + %lo(80f), %g0 - add %o0, %g7, %o0 + add %o0, %g4, %o0 79: /* memcpy_table */ @@ -641,43 +300,28 @@ FUNC(memcpy) /* %o0=dst %o1=src %o2=len */ stb %g2, [%o0] 1: retl - RETL_INSN + mov %g7, %o0 82: /* ldd_std */ MOVE_BIGALIGNCHUNK(o1, o0, 0x00, o2, o3, o4, o5, g2, g3, g4, g5) MOVE_BIGALIGNCHUNK(o1, o0, 0x20, o2, o3, o4, o5, g2, g3, g4, g5) MOVE_BIGALIGNCHUNK(o1, o0, 0x40, o2, o3, o4, o5, g2, g3, g4, g5) MOVE_BIGALIGNCHUNK(o1, o0, 0x60, o2, o3, o4, o5, g2, g3, g4, g5) - subcc %g7, 128, %g7 + subcc %g1, 128, %g1 add %o1, 128, %o1 - bne 82b + cmp %g1, 128 + bge 82b add %o0, 128, %o0 -#ifndef FASTER_ALIGNED - - andcc %g1, 0x70, %g7 - be 80b - andcc %g1, 8, %g0 - - sethi %hi(80b), %o5 - srl %g7, 1, %o4 - add %g7, %o4, %o4 - add %o1, %g7, %o1 - sub %o5, %o4, %o5 - jmpl %o5 + %lo(80b), %g0 - add %o0, %g7, %o0 - -#else /* FASTER_ALIGNED */ - - andcc %g1, 0x70, %g7 + andcc %g1, 0x70, %g4 be 84f andcc %g1, 8, %g0 sethi %hi(84f), %o5 - add %o1, %g7, %o1 - sub %o5, %g7, %o5 + add %o1, %g4, %o1 + sub %o5, %g4, %o5 jmpl %o5 + %lo(84f), %g0 - add %o0, %g7, %o0 + add %o0, %g4, %o0 83: /* amemcpy_table */ @@ -721,382 +365,132 @@ FUNC(memcpy) /* %o0=dst %o1=src %o2=len */ stb %g2, [%o0] 1: retl - RETL_INSN - -#endif /* FASTER_ALIGNED */ + mov %g7, %o0 86: /* non_aligned */ cmp %o2, 6 bleu 88f + nop -#ifdef FASTER_NONALIGNED - - cmp %o2, 256 - bcc 87f - -#endif /* FASTER_NONALIGNED */ - - andcc %o0, 3, %g0 + save %sp, -96, %sp + andcc %i0, 3, %g0 be 61f - andcc %o0, 1, %g0 + andcc %i0, 1, %g0 be 60f - andcc %o0, 2, %g0 + andcc %i0, 2, %g0 - ldub [%o1], %g5 - add %o1, 1, %o1 - stb %g5, [%o0] - sub %o2, 1, %o2 + ldub [%i1], %g5 + add %i1, 1, %i1 + stb %g5, [%i0] + sub %i2, 1, %i2 bne 61f - add %o0, 1, %o0 + add %i0, 1, %i0 60: - ldub [%o1], %g3 - add %o1, 2, %o1 - stb %g3, [%o0] - sub %o2, 2, %o2 - ldub [%o1 - 1], %g3 - add %o0, 2, %o0 - stb %g3, [%o0 - 1] + ldub [%i1], %g3 + add %i1, 2, %i1 + stb %g3, [%i0] + sub %i2, 2, %i2 + ldub [%i1 - 1], %g3 + add %i0, 2, %i0 + stb %g3, [%i0 - 1] 61: - and %o1, 3, %g2 - and %o2, 0xc, %g3 - and %o1, -4, %o1 + and %i1, 3, %g2 + and %i2, 0xc, %g3 + and %i1, -4, %i1 cmp %g3, 4 sll %g2, 3, %g4 mov 32, %g2 be 4f - sub %g2, %g4, %g7 + sub %g2, %g4, %l0 blu 3f cmp %g3, 0x8 be 2f - srl %o2, 2, %g3 + srl %i2, 2, %g3 - ld [%o1], %o3 - add %o0, -8, %o0 - ld [%o1 + 4], %o4 + ld [%i1], %i3 + add %i0, -8, %i0 + ld [%i1 + 4], %i4 b 8f add %g3, 1, %g3 2: - ld [%o1], %o4 - add %o0, -12, %o0 - ld [%o1 + 4], %o5 + ld [%i1], %i4 + add %i0, -12, %i0 + ld [%i1 + 4], %i5 add %g3, 2, %g3 b 9f - add %o1, -4, %o1 + add %i1, -4, %i1 3: - ld [%o1], %g1 - add %o0, -4, %o0 - ld [%o1 + 4], %o3 - srl %o2, 2, %g3 + ld [%i1], %g1 + add %i0, -4, %i0 + ld [%i1 + 4], %i3 + srl %i2, 2, %g3 b 7f - add %o1, 4, %o1 + add %i1, 4, %i1 4: - ld [%o1], %o5 - cmp %o2, 7 - ld [%o1 + 4], %g1 - srl %o2, 2, %g3 + ld [%i1], %i5 + cmp %i2, 7 + ld [%i1 + 4], %g1 + srl %i2, 2, %g3 bleu 10f - add %o1, 8, %o1 + add %i1, 8, %i1 - ld [%o1], %o3 + ld [%i1], %i3 add %g3, -1, %g3 5: - sll %o5, %g4, %g2 - srl %g1, %g7, %g5 + sll %i5, %g4, %g2 + srl %g1, %l0, %g5 or %g2, %g5, %g2 - st %g2, [%o0] + st %g2, [%i0] 7: - ld [%o1 + 4], %o4 + ld [%i1 + 4], %i4 sll %g1, %g4, %g2 - srl %o3, %g7, %g5 + srl %i3, %l0, %g5 or %g2, %g5, %g2 - st %g2, [%o0 + 4] + st %g2, [%i0 + 4] 8: - ld [%o1 + 8], %o5 - sll %o3, %g4, %g2 - srl %o4, %g7, %g5 + ld [%i1 + 8], %i5 + sll %i3, %g4, %g2 + srl %i4, %l0, %g5 or %g2, %g5, %g2 - st %g2, [%o0 + 8] + st %g2, [%i0 + 8] 9: - ld [%o1 + 12], %g1 - sll %o4, %g4, %g2 - srl %o5, %g7, %g5 + ld [%i1 + 12], %g1 + sll %i4, %g4, %g2 + srl %i5, %l0, %g5 addcc %g3, -4, %g3 or %g2, %g5, %g2 - add %o1, 16, %o1 - st %g2, [%o0 + 12] - add %o0, 16, %o0 + add %i1, 16, %i1 + st %g2, [%i0 + 12] + add %i0, 16, %i0 bne,a 5b - ld [%o1], %o3 + ld [%i1], %i3 10: - sll %o5, %g4, %g2 - srl %g1, %g7, %g5 - srl %g7, 3, %g3 + sll %i5, %g4, %g2 + srl %g1, %l0, %g5 + srl %l0, 3, %g3 or %g2, %g5, %g2 - sub %o1, %g3, %o1 - andcc %o2, 2, %g0 - st %g2, [%o0] + sub %i1, %g3, %i1 + andcc %i2, 2, %g0 + st %g2, [%i0] be 1f - andcc %o2, 1, %g0 - - ldub [%o1], %g2 - add %o1, 2, %o1 - stb %g2, [%o0 + 4] - add %o0, 2, %o0 - ldub [%o1 - 1], %g2 - stb %g2, [%o0 + 3] + andcc %i2, 1, %g0 + + ldub [%i1], %g2 + add %i1, 2, %i1 + stb %g2, [%i0 + 4] + add %i0, 2, %i0 + ldub [%i1 - 1], %g2 + stb %g2, [%i0 + 3] 1: be 1f nop - ldub [%o1], %g2 - stb %g2, [%o0 + 4] -1: - retl - RETL_INSN - -#ifdef FASTER_NONALIGNED - -87: /* faster_nonaligned */ - - andcc %o1, 3, %g0 - be 3f - andcc %o1, 1, %g0 - - be 4f - andcc %o1, 2, %g0 - - ldub [%o1], %g2 - add %o1, 1, %o1 - stb %g2, [%o0] - sub %o2, 1, %o2 - bne 3f - add %o0, 1, %o0 -4: - lduh [%o1], %g2 - add %o1, 2, %o1 - srl %g2, 8, %g3 - sub %o2, 2, %o2 - stb %g3, [%o0] - add %o0, 2, %o0 - stb %g2, [%o0 - 1] -3: - andcc %o1, 4, %g0 - - bne 2f - cmp %o5, 1 - - ld [%o1], %o4 - srl %o4, 24, %g2 - stb %g2, [%o0] - srl %o4, 16, %g3 - stb %g3, [%o0 + 1] - srl %o4, 8, %g2 - stb %g2, [%o0 + 2] - sub %o2, 4, %o2 - stb %o4, [%o0 + 3] - add %o1, 4, %o1 - add %o0, 4, %o0 -2: - be 33f - cmp %o5, 2 - be 32f - sub %o2, 4, %o2 -31: - ld [%o1], %g2 - add %o1, 4, %o1 - srl %g2, 24, %g3 - and %o0, 7, %g5 - stb %g3, [%o0] - cmp %g5, 7 - sll %g2, 8, %g1 - add %o0, 4, %o0 - be 41f - and %o2, 0xffffffc0, %o3 - ld [%o0 - 7], %o4 -4: - SMOVE_CHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3) - SMOVE_CHUNK(o1, o0, 0x10, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3) - SMOVE_CHUNK(o1, o0, 0x20, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3) - SMOVE_CHUNK(o1, o0, 0x30, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3) - subcc %o3, 64, %o3 - add %o1, 64, %o1 - bne 4b - add %o0, 64, %o0 - - andcc %o2, 0x30, %o3 - be,a 1f - srl %g1, 16, %g2 -4: - SMOVE_CHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3) - subcc %o3, 16, %o3 - add %o1, 16, %o1 - bne 4b - add %o0, 16, %o0 - - srl %g1, 16, %g2 -1: - st %o4, [%o0 - 7] - sth %g2, [%o0 - 3] - srl %g1, 8, %g4 - b 88f - stb %g4, [%o0 - 1] -32: - ld [%o1], %g2 - add %o1, 4, %o1 - srl %g2, 16, %g3 - and %o0, 7, %g5 - sth %g3, [%o0] - cmp %g5, 6 - sll %g2, 16, %g1 - add %o0, 4, %o0 - be 42f - and %o2, 0xffffffc0, %o3 - ld [%o0 - 6], %o4 -4: - SMOVE_CHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2) - SMOVE_CHUNK(o1, o0, 0x10, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2) - SMOVE_CHUNK(o1, o0, 0x20, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2) - SMOVE_CHUNK(o1, o0, 0x30, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2) - subcc %o3, 64, %o3 - add %o1, 64, %o1 - bne 4b - add %o0, 64, %o0 - - andcc %o2, 0x30, %o3 - be,a 1f - srl %g1, 16, %g2 -4: - SMOVE_CHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2) - subcc %o3, 16, %o3 - add %o1, 16, %o1 - bne 4b - add %o0, 16, %o0 - - srl %g1, 16, %g2 -1: - st %o4, [%o0 - 6] - b 88f - sth %g2, [%o0 - 2] -33: - ld [%o1], %g2 - sub %o2, 4, %o2 - srl %g2, 24, %g3 - and %o0, 7, %g5 - stb %g3, [%o0] - cmp %g5, 5 - srl %g2, 8, %g4 - sll %g2, 24, %g1 - sth %g4, [%o0 + 1] - add %o1, 4, %o1 - be 43f - and %o2, 0xffffffc0, %o3 - - ld [%o0 - 1], %o4 - add %o0, 4, %o0 -4: - SMOVE_CHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, -1) - SMOVE_CHUNK(o1, o0, 0x10, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, -1) - SMOVE_CHUNK(o1, o0, 0x20, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, -1) - SMOVE_CHUNK(o1, o0, 0x30, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, -1) - subcc %o3, 64, %o3 - add %o1, 64, %o1 - bne 4b - add %o0, 64, %o0 - - andcc %o2, 0x30, %o3 - be,a 1f - srl %g1, 24, %g2 -4: - SMOVE_CHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, -1) - subcc %o3, 16, %o3 - add %o1, 16, %o1 - bne 4b - add %o0, 16, %o0 - - srl %g1, 24, %g2 -1: - st %o4, [%o0 - 5] - b 88f - stb %g2, [%o0 - 1] -41: - SMOVE_ALIGNCHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3) - SMOVE_ALIGNCHUNK(o1, o0, 0x10, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3) - SMOVE_ALIGNCHUNK(o1, o0, 0x20, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3) - SMOVE_ALIGNCHUNK(o1, o0, 0x30, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3) - subcc %o3, 64, %o3 - add %o1, 64, %o1 - bne 41b - add %o0, 64, %o0 - - andcc %o2, 0x30, %o3 - be,a 1f - srl %g1, 16, %g2 -4: - SMOVE_ALIGNCHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3) - subcc %o3, 16, %o3 - add %o1, 16, %o1 - bne 4b - add %o0, 16, %o0 - - srl %g1, 16, %g2 + ldub [%i1], %g2 + stb %g2, [%i0 + 4] 1: - sth %g2, [%o0 - 3] - srl %g1, 8, %g4 - b 88f - stb %g4, [%o0 - 1] -43: - SMOVE_ALIGNCHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, 3) - SMOVE_ALIGNCHUNK(o1, o0, 0x10, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, 3) - SMOVE_ALIGNCHUNK(o1, o0, 0x20, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, 3) - SMOVE_ALIGNCHUNK(o1, o0, 0x30, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, 3) - subcc %o3, 64, %o3 - add %o1, 64, %o1 - bne 43b - add %o0, 64, %o0 - - andcc %o2, 0x30, %o3 - be,a 1f - srl %g1, 24, %g2 -4: - SMOVE_ALIGNCHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, 3) - subcc %o3, 16, %o3 - add %o1, 16, %o1 - bne 4b - add %o0, 16, %o0 - - srl %g1, 24, %g2 -1: - stb %g2, [%o0 + 3] - b 88f - add %o0, 4, %o0 -42: - SMOVE_ALIGNCHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2) - SMOVE_ALIGNCHUNK(o1, o0, 0x10, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2) - SMOVE_ALIGNCHUNK(o1, o0, 0x20, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2) - SMOVE_ALIGNCHUNK(o1, o0, 0x30, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2) - subcc %o3, 64, %o3 - add %o1, 64, %o1 - bne 42b - add %o0, 64, %o0 - - andcc %o2, 0x30, %o3 - be,a 1f - srl %g1, 16, %g2 -4: - SMOVE_ALIGNCHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2) - subcc %o3, 16, %o3 - add %o1, 16, %o1 - bne 4b - add %o0, 16, %o0 - - srl %g1, 16, %g2 -1: - sth %g2, [%o0 - 2] - - /* Fall through */ - -#endif /* FASTER_NONALIGNED */ + ret + restore %g7, %g0, %o0 88: /* short_end */ @@ -1127,7 +521,7 @@ FUNC(memcpy) /* %o0=dst %o1=src %o2=len */ stb %g2, [%o0] 1: retl - RETL_INSN + mov %g7, %o0 90: /* short_aligned_end */ bne 88b diff --git a/arch/sparc/mm/Makefile b/arch/sparc/mm/Makefile index 79836a7..3b6e248 100644 --- a/arch/sparc/mm/Makefile +++ b/arch/sparc/mm/Makefile @@ -8,7 +8,6 @@ obj-$(CONFIG_SPARC64) += ultra.o tlb.o tsb.o obj-y += fault_$(BITS).o obj-y += init_$(BITS).o obj-$(CONFIG_SPARC32) += loadmmu.o -obj-y += generic_$(BITS).o obj-$(CONFIG_SPARC32) += extable.o btfixup.o srmmu.o iommu.o io-unit.o obj-$(CONFIG_SPARC32) += hypersparc.o viking.o tsunami.o swift.o obj-$(CONFIG_SPARC_LEON)+= leon_mm.o diff --git a/arch/sparc/mm/btfixup.c b/arch/sparc/mm/btfixup.c index 5175ac2..8a7f817 100644 --- a/arch/sparc/mm/btfixup.c +++ b/arch/sparc/mm/btfixup.c @@ -302,8 +302,7 @@ void __init btfixup(void) case 'i': /* INT */ if ((insn & 0xc1c00000) == 0x01000000) /* %HI */ set_addr(addr, q[1], fmangled, (insn & 0xffc00000) | (p[1] >> 10)); - else if ((insn & 0x80002000) == 0x80002000 && - (insn & 0x01800000) != 0x01800000) /* %LO */ + else if ((insn & 0x80002000) == 0x80002000) /* %LO */ set_addr(addr, q[1], fmangled, (insn & 0xffffe000) | (p[1] & 0x3ff)); else { prom_printf(insn_i, p, addr, insn); diff --git a/arch/sparc/mm/generic_32.c b/arch/sparc/mm/generic_32.c deleted file mode 100644 index e6067b7..0000000 --- a/arch/sparc/mm/generic_32.c +++ /dev/null @@ -1,98 +0,0 @@ -/* - * generic.c: Generic Sparc mm routines that are not dependent upon - * MMU type but are Sparc specific. - * - * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu) - */ - -#include <linux/kernel.h> -#include <linux/mm.h> -#include <linux/swap.h> -#include <linux/pagemap.h> - -#include <asm/pgalloc.h> -#include <asm/pgtable.h> -#include <asm/page.h> -#include <asm/cacheflush.h> -#include <asm/tlbflush.h> - -/* Remap IO memory, the same way as remap_pfn_range(), but use - * the obio memory space. - * - * They use a pgprot that sets PAGE_IO and does not check the - * mem_map table as this is independent of normal memory. - */ -static inline void io_remap_pte_range(struct mm_struct *mm, pte_t * pte, unsigned long address, unsigned long size, - unsigned long offset, pgprot_t prot, int space) -{ - unsigned long end; - - address &= ~PMD_MASK; - end = address + size; - if (end > PMD_SIZE) - end = PMD_SIZE; - do { - set_pte_at(mm, address, pte, mk_pte_io(offset, prot, space)); - address += PAGE_SIZE; - offset += PAGE_SIZE; - pte++; - } while (address < end); -} - -static inline int io_remap_pmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned long address, unsigned long size, - unsigned long offset, pgprot_t prot, int space) -{ - unsigned long end; - - address &= ~PGDIR_MASK; - end = address + size; - if (end > PGDIR_SIZE) - end = PGDIR_SIZE; - offset -= address; - do { - pte_t *pte = pte_alloc_map(mm, NULL, pmd, address); - if (!pte) - return -ENOMEM; - io_remap_pte_range(mm, pte, address, end - address, address + offset, prot, space); - address = (address + PMD_SIZE) & PMD_MASK; - pmd++; - } while (address < end); - return 0; -} - -int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from, - unsigned long pfn, unsigned long size, pgprot_t prot) -{ - int error = 0; - pgd_t * dir; - unsigned long beg = from; - unsigned long end = from + size; - struct mm_struct *mm = vma->vm_mm; - int space = GET_IOSPACE(pfn); - unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT; - - /* See comment in mm/memory.c remap_pfn_range */ - vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP; - vma->vm_pgoff = (offset >> PAGE_SHIFT) | - ((unsigned long)space << 28UL); - - offset -= from; - dir = pgd_offset(mm, from); - flush_cache_range(vma, beg, end); - - while (from < end) { - pmd_t *pmd = pmd_alloc(mm, dir, from); - error = -ENOMEM; - if (!pmd) - break; - error = io_remap_pmd_range(mm, pmd, from, end - from, offset + from, prot, space); - if (error) - break; - from = (from + PGDIR_SIZE) & PGDIR_MASK; - dir++; - } - - flush_tlb_range(vma, beg, end); - return error; -} -EXPORT_SYMBOL(io_remap_pfn_range); diff --git a/arch/sparc/mm/generic_64.c b/arch/sparc/mm/generic_64.c deleted file mode 100644 index 3cb00df..0000000 --- a/arch/sparc/mm/generic_64.c +++ /dev/null @@ -1,164 +0,0 @@ -/* - * generic.c: Generic Sparc mm routines that are not dependent upon - * MMU type but are Sparc specific. - * - * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu) - */ - -#include <linux/kernel.h> -#include <linux/mm.h> -#include <linux/swap.h> -#include <linux/pagemap.h> - -#include <asm/pgalloc.h> -#include <asm/pgtable.h> -#include <asm/page.h> -#include <asm/tlbflush.h> - -/* Remap IO memory, the same way as remap_pfn_range(), but use - * the obio memory space. - * - * They use a pgprot that sets PAGE_IO and does not check the - * mem_map table as this is independent of normal memory. - */ -static inline void io_remap_pte_range(struct mm_struct *mm, pte_t * pte, - unsigned long address, - unsigned long size, - unsigned long offset, pgprot_t prot, - int space) -{ - unsigned long end; - - /* clear hack bit that was used as a write_combine side-effect flag */ - offset &= ~0x1UL; - address &= ~PMD_MASK; - end = address + size; - if (end > PMD_SIZE) - end = PMD_SIZE; - do { - pte_t entry; - unsigned long curend = address + PAGE_SIZE; - - entry = mk_pte_io(offset, prot, space, PAGE_SIZE); - if (!(address & 0xffff)) { - if (PAGE_SIZE < (4 * 1024 * 1024) && - !(address & 0x3fffff) && - !(offset & 0x3ffffe) && - end >= address + 0x400000) { - entry = mk_pte_io(offset, prot, space, - 4 * 1024 * 1024); - curend = address + 0x400000; - offset += 0x400000; - } else if (PAGE_SIZE < (512 * 1024) && - !(address & 0x7ffff) && - !(offset & 0x7fffe) && - end >= address + 0x80000) { - entry = mk_pte_io(offset, prot, space, - 512 * 1024 * 1024); - curend = address + 0x80000; - offset += 0x80000; - } else if (PAGE_SIZE < (64 * 1024) && - !(offset & 0xfffe) && - end >= address + 0x10000) { - entry = mk_pte_io(offset, prot, space, - 64 * 1024); - curend = address + 0x10000; - offset += 0x10000; - } else - offset += PAGE_SIZE; - } else - offset += PAGE_SIZE; - - if (pte_write(entry)) - entry = pte_mkdirty(entry); - do { - BUG_ON(!pte_none(*pte)); - set_pte_at(mm, address, pte, entry); - address += PAGE_SIZE; - pte_val(entry) += PAGE_SIZE; - pte++; - } while (address < curend); - } while (address < end); -} - -static inline int io_remap_pmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned long address, unsigned long size, - unsigned long offset, pgprot_t prot, int space) -{ - unsigned long end; - - address &= ~PGDIR_MASK; - end = address + size; - if (end > PGDIR_SIZE) - end = PGDIR_SIZE; - offset -= address; - do { - pte_t *pte = pte_alloc_map(mm, NULL, pmd, address); - if (!pte) - return -ENOMEM; - io_remap_pte_range(mm, pte, address, end - address, address + offset, prot, space); - pte_unmap(pte); - address = (address + PMD_SIZE) & PMD_MASK; - pmd++; - } while (address < end); - return 0; -} - -static inline int io_remap_pud_range(struct mm_struct *mm, pud_t * pud, unsigned long address, unsigned long size, - unsigned long offset, pgprot_t prot, int space) -{ - unsigned long end; - - address &= ~PUD_MASK; - end = address + size; - if (end > PUD_SIZE) - end = PUD_SIZE; - offset -= address; - do { - pmd_t *pmd = pmd_alloc(mm, pud, address); - if (!pud) - return -ENOMEM; - io_remap_pmd_range(mm, pmd, address, end - address, address + offset, prot, space); - address = (address + PUD_SIZE) & PUD_MASK; - pud++; - } while (address < end); - return 0; -} - -int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from, - unsigned long pfn, unsigned long size, pgprot_t prot) -{ - int error = 0; - pgd_t * dir; - unsigned long beg = from; - unsigned long end = from + size; - struct mm_struct *mm = vma->vm_mm; - int space = GET_IOSPACE(pfn); - unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT; - unsigned long phys_base; - - phys_base = offset | (((unsigned long) space) << 32UL); - - /* See comment in mm/memory.c remap_pfn_range */ - vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP; - vma->vm_pgoff = phys_base >> PAGE_SHIFT; - - offset -= from; - dir = pgd_offset(mm, from); - flush_cache_range(vma, beg, end); - - while (from < end) { - pud_t *pud = pud_alloc(mm, dir, from); - error = -ENOMEM; - if (!pud) - break; - error = io_remap_pud_range(mm, pud, from, end - from, offset + from, prot, space); - if (error) - break; - from = (from + PGDIR_SIZE) & PGDIR_MASK; - dir++; - } - - flush_tlb_range(vma, beg, end); - return error; -} -EXPORT_SYMBOL(io_remap_pfn_range); diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h index 67f87f2..78a1eff 100644 --- a/arch/x86/include/asm/amd_nb.h +++ b/arch/x86/include/asm/amd_nb.h @@ -1,6 +1,7 @@ #ifndef _ASM_X86_AMD_NB_H #define _ASM_X86_AMD_NB_H +#include <linux/ioport.h> #include <linux/pci.h> struct amd_nb_bus_dev_range { @@ -13,6 +14,7 @@ extern const struct pci_device_id amd_nb_misc_ids[]; extern const struct amd_nb_bus_dev_range amd_nb_bus_dev_ranges[]; extern bool early_is_amd_nb(u32 value); +extern struct resource *amd_get_mmconfig_range(struct resource *res); extern int amd_cache_northbridges(void); extern void amd_flush_garts(void); extern int amd_numa_init(void); diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h index c9e09ea..a850b4d 100644 --- a/arch/x86/include/asm/i387.h +++ b/arch/x86/include/asm/i387.h @@ -29,8 +29,8 @@ extern unsigned int sig_xstate_size; extern void fpu_init(void); extern void mxcsr_feature_mask_init(void); extern int init_fpu(struct task_struct *child); -extern asmlinkage void math_state_restore(void); -extern void __math_state_restore(void); +extern void __math_state_restore(struct task_struct *); +extern void math_state_restore(void); extern int dump_fpu(struct pt_regs *, struct user_i387_struct *); extern user_regset_active_fn fpregs_active, xfpregs_active; @@ -212,19 +212,11 @@ static inline void fpu_fxsave(struct fpu *fpu) #endif /* CONFIG_X86_64 */ -/* We need a safe address that is cheap to find and that is already - in L1 during context switch. The best choices are unfortunately - different for UP and SMP */ -#ifdef CONFIG_SMP -#define safe_address (__per_cpu_offset[0]) -#else -#define safe_address (kstat_cpu(0).cpustat.user) -#endif - /* - * These must be called with preempt disabled + * These must be called with preempt disabled. Returns + * 'true' if the FPU state is still intact. */ -static inline void fpu_save_init(struct fpu *fpu) +static inline int fpu_save_init(struct fpu *fpu) { if (use_xsave()) { fpu_xsave(fpu); @@ -233,33 +225,33 @@ static inline void fpu_save_init(struct fpu *fpu) * xsave header may indicate the init state of the FP. */ if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP)) - return; + return 1; } else if (use_fxsr()) { fpu_fxsave(fpu); } else { asm volatile("fnsave %[fx]; fwait" : [fx] "=m" (fpu->state->fsave)); - return; + return 0; } - if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES)) + /* + * If exceptions are pending, we need to clear them so + * that we don't randomly get exceptions later. + * + * FIXME! Is this perhaps only true for the old-style + * irq13 case? Maybe we could leave the x87 state + * intact otherwise? + */ + if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES)) { asm volatile("fnclex"); - - /* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception - is pending. Clear the x87 state here by setting it to fixed - values. safe_address is a random variable that should be in L1 */ - alternative_input( - ASM_NOP8 ASM_NOP2, - "emms\n\t" /* clear stack tags */ - "fildl %P[addr]", /* set F?P to defined value */ - X86_FEATURE_FXSAVE_LEAK, - [addr] "m" (safe_address)); + return 0; + } + return 1; } -static inline void __save_init_fpu(struct task_struct *tsk) +static inline int __save_init_fpu(struct task_struct *tsk) { - fpu_save_init(&tsk->thread.fpu); - task_thread_info(tsk)->status &= ~TS_USEDFPU; + return fpu_save_init(&tsk->thread.fpu); } static inline int fpu_fxrstor_checking(struct fpu *fpu) @@ -281,39 +273,185 @@ static inline int restore_fpu_checking(struct task_struct *tsk) } /* - * Signal frame handlers... + * Software FPU state helpers. Careful: these need to + * be preemption protection *and* they need to be + * properly paired with the CR0.TS changes! */ -extern int save_i387_xstate(void __user *buf); -extern int restore_i387_xstate(void __user *buf); +static inline int __thread_has_fpu(struct task_struct *tsk) +{ + return tsk->thread.has_fpu; +} -static inline void __unlazy_fpu(struct task_struct *tsk) +/* Must be paired with an 'stts' after! */ +static inline void __thread_clear_has_fpu(struct task_struct *tsk) { - if (task_thread_info(tsk)->status & TS_USEDFPU) { - __save_init_fpu(tsk); - stts(); - } else - tsk->fpu_counter = 0; + tsk->thread.has_fpu = 0; +} + +/* Must be paired with a 'clts' before! */ +static inline void __thread_set_has_fpu(struct task_struct *tsk) +{ + tsk->thread.has_fpu = 1; } +/* + * Encapsulate the CR0.TS handling together with the + * software flag. + * + * These generally need preemption protection to work, + * do try to avoid using these on their own. + */ +static inline void __thread_fpu_end(struct task_struct *tsk) +{ + __thread_clear_has_fpu(tsk); + stts(); +} + +static inline void __thread_fpu_begin(struct task_struct *tsk) +{ + clts(); + __thread_set_has_fpu(tsk); +} + +/* + * FPU state switching for scheduling. + * + * This is a two-stage process: + * + * - switch_fpu_prepare() saves the old state and + * sets the new state of the CR0.TS bit. This is + * done within the context of the old process. + * + * - switch_fpu_finish() restores the new state as + * necessary. + */ +typedef struct { int preload; } fpu_switch_t; + +/* + * FIXME! We could do a totally lazy restore, but we need to + * add a per-cpu "this was the task that last touched the FPU + * on this CPU" variable, and the task needs to have a "I last + * touched the FPU on this CPU" and check them. + * + * We don't do that yet, so "fpu_lazy_restore()" always returns + * false, but some day.. + */ +#define fpu_lazy_restore(tsk) (0) +#define fpu_lazy_state_intact(tsk) do { } while (0) + +static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new) +{ + fpu_switch_t fpu; + + fpu.preload = tsk_used_math(new) && new->fpu_counter > 5; + if (__thread_has_fpu(old)) { + if (__save_init_fpu(old)) + fpu_lazy_state_intact(old); + __thread_clear_has_fpu(old); + old->fpu_counter++; + + /* Don't change CR0.TS if we just switch! */ + if (fpu.preload) { + __thread_set_has_fpu(new); + prefetch(new->thread.fpu.state); + } else + stts(); + } else { + old->fpu_counter = 0; + if (fpu.preload) { + if (fpu_lazy_restore(new)) + fpu.preload = 0; + else + prefetch(new->thread.fpu.state); + __thread_fpu_begin(new); + } + } + return fpu; +} + +/* + * By the time this gets called, we've already cleared CR0.TS and + * given the process the FPU if we are going to preload the FPU + * state - all we need to do is to conditionally restore the register + * state itself. + */ +static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu) +{ + if (fpu.preload) + __math_state_restore(new); +} + +/* + * Signal frame handlers... + */ +extern int save_i387_xstate(void __user *buf); +extern int restore_i387_xstate(void __user *buf); + static inline void __clear_fpu(struct task_struct *tsk) { - if (task_thread_info(tsk)->status & TS_USEDFPU) { + if (__thread_has_fpu(tsk)) { /* Ignore delayed exceptions from user space */ asm volatile("1: fwait\n" "2:\n" _ASM_EXTABLE(1b, 2b)); - task_thread_info(tsk)->status &= ~TS_USEDFPU; - stts(); + __thread_fpu_end(tsk); } } +/* + * Were we in an interrupt that interrupted kernel mode? + * + * We can do a kernel_fpu_begin/end() pair *ONLY* if that + * pair does nothing at all: the thread must not have fpu (so + * that we don't try to save the FPU state), and TS must + * be set (so that the clts/stts pair does nothing that is + * visible in the interrupted kernel thread). + */ +static inline bool interrupted_kernel_fpu_idle(void) +{ + return !__thread_has_fpu(current) && + (read_cr0() & X86_CR0_TS); +} + +/* + * Were we in user mode (or vm86 mode) when we were + * interrupted? + * + * Doing kernel_fpu_begin/end() is ok if we are running + * in an interrupt context from user mode - we'll just + * save the FPU state as required. + */ +static inline bool interrupted_user_mode(void) +{ + struct pt_regs *regs = get_irq_regs(); + return regs && user_mode_vm(regs); +} + +/* + * Can we use the FPU in kernel mode with the + * whole "kernel_fpu_begin/end()" sequence? + * + * It's always ok in process context (ie "not interrupt") + * but it is sometimes ok even from an irq. + */ +static inline bool irq_fpu_usable(void) +{ + return !in_interrupt() || + interrupted_user_mode() || + interrupted_kernel_fpu_idle(); +} + static inline void kernel_fpu_begin(void) { - struct thread_info *me = current_thread_info(); + struct task_struct *me = current; + + WARN_ON_ONCE(!irq_fpu_usable()); preempt_disable(); - if (me->status & TS_USEDFPU) - __save_init_fpu(me->task); - else + if (__thread_has_fpu(me)) { + __save_init_fpu(me); + __thread_clear_has_fpu(me); + /* We do 'stts()' in kernel_fpu_end() */ + } else clts(); } @@ -323,14 +461,6 @@ static inline void kernel_fpu_end(void) preempt_enable(); } -static inline bool irq_fpu_usable(void) -{ - struct pt_regs *regs; - - return !in_interrupt() || !(regs = get_irq_regs()) || \ - user_mode(regs) || (read_cr0() & X86_CR0_TS); -} - /* * Some instructions like VIA's padlock instructions generate a spurious * DNA fault but don't modify SSE registers. And these instructions @@ -363,20 +493,64 @@ static inline void irq_ts_restore(int TS_state) } /* + * The question "does this thread have fpu access?" + * is slightly racy, since preemption could come in + * and revoke it immediately after the test. + * + * However, even in that very unlikely scenario, + * we can just assume we have FPU access - typically + * to save the FP state - we'll just take a #NM + * fault and get the FPU access back. + * + * The actual user_fpu_begin/end() functions + * need to be preemption-safe, though. + * + * NOTE! user_fpu_end() must be used only after you + * have saved the FP state, and user_fpu_begin() must + * be used only immediately before restoring it. + * These functions do not do any save/restore on + * their own. + */ +static inline int user_has_fpu(void) +{ + return __thread_has_fpu(current); +} + +static inline void user_fpu_end(void) +{ + preempt_disable(); + __thread_fpu_end(current); + preempt_enable(); +} + +static inline void user_fpu_begin(void) +{ + preempt_disable(); + if (!user_has_fpu()) + __thread_fpu_begin(current); + preempt_enable(); +} + +/* * These disable preemption on their own and are safe */ static inline void save_init_fpu(struct task_struct *tsk) { + WARN_ON_ONCE(!__thread_has_fpu(tsk)); preempt_disable(); __save_init_fpu(tsk); - stts(); + __thread_fpu_end(tsk); preempt_enable(); } static inline void unlazy_fpu(struct task_struct *tsk) { preempt_disable(); - __unlazy_fpu(tsk); + if (__thread_has_fpu(tsk)) { + __save_init_fpu(tsk); + __thread_fpu_end(tsk); + } else + tsk->fpu_counter = 0; preempt_enable(); } diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 0049211..0ab6a4d 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -189,6 +189,9 @@ struct x86_emulate_ops { int (*intercept)(struct x86_emulate_ctxt *ctxt, struct x86_instruction_info *info, enum x86_intercept_stage stage); + + bool (*get_cpuid)(struct x86_emulate_ctxt *ctxt, + u32 *eax, u32 *ebx, u32 *ecx, u32 *edx); }; typedef u32 __attribute__((vector_size(16))) sse128_t; @@ -298,6 +301,19 @@ struct x86_emulate_ctxt { #define X86EMUL_MODE_PROT (X86EMUL_MODE_PROT16|X86EMUL_MODE_PROT32| \ X86EMUL_MODE_PROT64) +/* CPUID vendors */ +#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx 0x68747541 +#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx 0x444d4163 +#define X86EMUL_CPUID_VENDOR_AuthenticAMD_edx 0x69746e65 + +#define X86EMUL_CPUID_VENDOR_AMDisbetterI_ebx 0x69444d41 +#define X86EMUL_CPUID_VENDOR_AMDisbetterI_ecx 0x21726574 +#define X86EMUL_CPUID_VENDOR_AMDisbetterI_edx 0x74656273 + +#define X86EMUL_CPUID_VENDOR_GenuineIntel_ebx 0x756e6547 +#define X86EMUL_CPUID_VENDOR_GenuineIntel_ecx 0x6c65746e +#define X86EMUL_CPUID_VENDOR_GenuineIntel_edx 0x49656e69 + enum x86_intercept_stage { X86_ICTP_NONE = 0, /* Allow zero-init to not match anything */ X86_ICPT_PRE_EXCEPT, diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 2193715..5d9c61d 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -454,6 +454,7 @@ struct thread_struct { unsigned long trap_no; unsigned long error_code; /* floating point and extended processor state */ + unsigned long has_fpu; struct fpu fpu; #ifdef CONFIG_X86_32 /* Virtual 86 mode info */ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 1f2e61e..278d3d5 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -242,8 +242,6 @@ static inline struct thread_info *current_thread_info(void) * ever touches our thread-synchronous status, so we don't * have to worry about atomic accesses. */ -#define TS_USEDFPU 0x0001 /* FPU was used by this task - this quantum (SMP) */ #define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/ #define TS_POLLING 0x0004 /* idle task polling need_resched, skip sending interrupt */ diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h index 431793e..34baa0e 100644 --- a/arch/x86/include/asm/timer.h +++ b/arch/x86/include/asm/timer.h @@ -57,14 +57,10 @@ DECLARE_PER_CPU(unsigned long long, cyc2ns_offset); static inline unsigned long long __cycles_2_ns(unsigned long long cyc) { - unsigned long long quot; - unsigned long long rem; int cpu = smp_processor_id(); unsigned long long ns = per_cpu(cyc2ns_offset, cpu); - quot = (cyc >> CYC2NS_SCALE_FACTOR); - rem = cyc & ((1ULL << CYC2NS_SCALE_FACTOR) - 1); - ns += quot * per_cpu(cyc2ns, cpu) + - ((rem * per_cpu(cyc2ns, cpu)) >> CYC2NS_SCALE_FACTOR); + ns += mult_frac(cyc, per_cpu(cyc2ns, cpu), + (1UL << CYC2NS_SCALE_FACTOR)); return ns; } diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h index 54a13aa..21f7385 100644 --- a/arch/x86/include/asm/uv/uv_hub.h +++ b/arch/x86/include/asm/uv/uv_hub.h @@ -318,13 +318,13 @@ uv_gpa_in_mmr_space(unsigned long gpa) /* UV global physical address --> socket phys RAM */ static inline unsigned long uv_gpa_to_soc_phys_ram(unsigned long gpa) { - unsigned long paddr = gpa & uv_hub_info->gpa_mask; + unsigned long paddr; unsigned long remap_base = uv_hub_info->lowmem_remap_base; unsigned long remap_top = uv_hub_info->lowmem_remap_top; gpa = ((gpa << uv_hub_info->m_shift) >> uv_hub_info->m_shift) | ((gpa >> uv_hub_info->n_lshift) << uv_hub_info->m_val); - gpa = gpa & uv_hub_info->gpa_mask; + paddr = gpa & uv_hub_info->gpa_mask; if (paddr >= remap_base && paddr < remap_base + remap_top) paddr -= remap_base; return paddr; diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c index bfc8453..33df6e8 100644 --- a/arch/x86/kernel/amd_iommu_init.c +++ b/arch/x86/kernel/amd_iommu_init.c @@ -1031,8 +1031,9 @@ static int iommu_setup_msi(struct amd_iommu *iommu) { int r; - if (pci_enable_msi(iommu->dev)) - return 1; + r = pci_enable_msi(iommu->dev); + if (r) + return r; r = request_threaded_irq(iommu->dev->irq, amd_iommu_int_handler, @@ -1042,24 +1043,33 @@ static int iommu_setup_msi(struct amd_iommu *iommu) if (r) { pci_disable_msi(iommu->dev); - return 1; + return r; } iommu->int_enabled = true; - iommu_feature_enable(iommu, CONTROL_EVT_INT_EN); return 0; } static int iommu_init_msi(struct amd_iommu *iommu) { + int ret; + if (iommu->int_enabled) - return 0; + goto enable_faults; if (pci_find_capability(iommu->dev, PCI_CAP_ID_MSI)) - return iommu_setup_msi(iommu); + ret = iommu_setup_msi(iommu); + else + ret = -ENODEV; - return 1; + if (ret) + return ret; + +enable_faults: + iommu_feature_enable(iommu, CONTROL_EVT_INT_EN); + + return 0; } /**************************************************************************** diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 4c39baa..bae1efe 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -119,6 +119,37 @@ bool __init early_is_amd_nb(u32 device) return false; } +struct resource *amd_get_mmconfig_range(struct resource *res) +{ + u32 address; + u64 base, msr; + unsigned segn_busn_bits; + + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) + return NULL; + + /* assume all cpus from fam10h have mmconfig */ + if (boot_cpu_data.x86 < 0x10) + return NULL; + + address = MSR_FAM10H_MMIO_CONF_BASE; + rdmsrl(address, msr); + + /* mmconfig is not enabled */ + if (!(msr & FAM10H_MMIO_CONF_ENABLE)) + return NULL; + + base = msr & (FAM10H_MMIO_CONF_BASE_MASK<<FAM10H_MMIO_CONF_BASE_SHIFT); + + segn_busn_bits = (msr >> FAM10H_MMIO_CONF_BUSRANGE_SHIFT) & + FAM10H_MMIO_CONF_BUSRANGE_MASK; + + res->flags = IORESOURCE_MEM; + res->start = base; + res->end = base + (1ULL<<(segn_busn_bits + 20)) - 1; + return res; +} + int amd_get_subcaches(int cpu) { struct pci_dev *link = node_to_amd_nb(amd_get_nb_id(cpu))->link; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index b9338b8..1471695 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1558,9 +1558,11 @@ static int __init apic_verify(void) mp_lapic_addr = APIC_DEFAULT_PHYS_BASE; /* The BIOS may have set up the APIC at some other address */ - rdmsr(MSR_IA32_APICBASE, l, h); - if (l & MSR_IA32_APICBASE_ENABLE) - mp_lapic_addr = l & MSR_IA32_APICBASE_BASE; + if (boot_cpu_data.x86 >= 6) { + rdmsr(MSR_IA32_APICBASE, l, h); + if (l & MSR_IA32_APICBASE_ENABLE) + mp_lapic_addr = l & MSR_IA32_APICBASE_BASE; + } pr_info("Found and enabled local APIC!\n"); return 0; @@ -1578,13 +1580,15 @@ int __init apic_force_enable(unsigned long addr) * MSR. This can only be done in software for Intel P6 or later * and AMD K7 (Model > 1) or later. */ - rdmsr(MSR_IA32_APICBASE, l, h); - if (!(l & MSR_IA32_APICBASE_ENABLE)) { - pr_info("Local APIC disabled by BIOS -- reenabling.\n"); - l &= ~MSR_IA32_APICBASE_BASE; - l |= MSR_IA32_APICBASE_ENABLE | addr; - wrmsr(MSR_IA32_APICBASE, l, h); - enabled_via_apicbase = 1; + if (boot_cpu_data.x86 >= 6) { + rdmsr(MSR_IA32_APICBASE, l, h); + if (!(l & MSR_IA32_APICBASE_ENABLE)) { + pr_info("Local APIC disabled by BIOS -- reenabling.\n"); + l &= ~MSR_IA32_APICBASE_BASE; + l |= MSR_IA32_APICBASE_ENABLE | addr; + wrmsr(MSR_IA32_APICBASE, l, h); + enabled_via_apicbase = 1; + } } return apic_verify(); } @@ -2112,10 +2116,12 @@ static void lapic_resume(void) * FIXME! This will be wrong if we ever support suspend on * SMP! We'll need to do this as part of the CPU restore! */ - rdmsr(MSR_IA32_APICBASE, l, h); - l &= ~MSR_IA32_APICBASE_BASE; - l |= MSR_IA32_APICBASE_ENABLE | mp_lapic_addr; - wrmsr(MSR_IA32_APICBASE, l, h); + if (boot_cpu_data.x86 >= 6) { + rdmsr(MSR_IA32_APICBASE, l, h); + l &= ~MSR_IA32_APICBASE_BASE; + l |= MSR_IA32_APICBASE_ENABLE | mp_lapic_addr; + wrmsr(MSR_IA32_APICBASE, l, h); + } } maxlvt = lapic_get_maxlvt(); diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index cfeb978..874c208 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -779,7 +779,12 @@ void __init uv_system_init(void) for(i = 0; i < UVH_NODE_PRESENT_TABLE_DEPTH; i++) uv_possible_blades += hweight64(uv_read_local_mmr( UVH_NODE_PRESENT_TABLE + i * 8)); - printk(KERN_DEBUG "UV: Found %d blades\n", uv_num_possible_blades()); + + /* uv_num_possible_blades() is really the hub count */ + printk(KERN_INFO "UV: Found %d blades, %d hubs\n", + is_uv1_hub() ? uv_num_possible_blades() : + (uv_num_possible_blades() + 1) / 2, + uv_num_possible_blades()); bytes = sizeof(struct uv_blade_info) * uv_num_possible_blades(); uv_blade_info = kzalloc(bytes, GFP_KERNEL); diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index c105c53..fde4428 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -330,8 +330,7 @@ static void __cpuinit amd_calc_l3_indices(struct amd_l3_cache *l3) l3->indices = (max(max3(sc0, sc1, sc2), sc3) << 10) - 1; } -static void __cpuinit amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf, - int index) +static void __cpuinit amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf, int index) { static struct amd_l3_cache *__cpuinitdata l3_caches; int node; @@ -748,14 +747,16 @@ static DEFINE_PER_CPU(struct _cpuid4_info *, ici_cpuid4_info); #define CPUID4_INFO_IDX(x, y) (&((per_cpu(ici_cpuid4_info, x))[y])) #ifdef CONFIG_SMP -static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index) + +static int __cpuinit cache_shared_amd_cpu_map_setup(unsigned int cpu, int index) { - struct _cpuid4_info *this_leaf, *sibling_leaf; - unsigned long num_threads_sharing; - int index_msb, i, sibling; + struct _cpuid4_info *this_leaf; + int ret, i, sibling; struct cpuinfo_x86 *c = &cpu_data(cpu); - if ((index == 3) && (c->x86_vendor == X86_VENDOR_AMD)) { + ret = 0; + if (index == 3) { + ret = 1; for_each_cpu(i, cpu_llc_shared_mask(cpu)) { if (!per_cpu(ici_cpuid4_info, i)) continue; @@ -766,8 +767,35 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index) set_bit(sibling, this_leaf->shared_cpu_map); } } - return; + } else if ((c->x86 == 0x15) && ((index == 1) || (index == 2))) { + ret = 1; + for_each_cpu(i, cpu_sibling_mask(cpu)) { + if (!per_cpu(ici_cpuid4_info, i)) + continue; + this_leaf = CPUID4_INFO_IDX(i, index); + for_each_cpu(sibling, cpu_sibling_mask(cpu)) { + if (!cpu_online(sibling)) + continue; + set_bit(sibling, this_leaf->shared_cpu_map); + } + } } + + return ret; +} + +static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index) +{ + struct _cpuid4_info *this_leaf, *sibling_leaf; + unsigned long num_threads_sharing; + int index_msb, i; + struct cpuinfo_x86 *c = &cpu_data(cpu); + + if (c->x86_vendor == X86_VENDOR_AMD) { + if (cache_shared_amd_cpu_map_setup(cpu, index)) + return; + } + this_leaf = CPUID4_INFO_IDX(cpu, index); num_threads_sharing = 1 + this_leaf->eax.split.num_threads_sharing; diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 5c1a9197..edb3d46 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -98,12 +98,6 @@ #endif .endm -#ifdef CONFIG_VM86 -#define resume_userspace_sig check_userspace -#else -#define resume_userspace_sig resume_userspace -#endif - /* * User gs save/restore * @@ -327,10 +321,19 @@ ret_from_exception: preempt_stop(CLBR_ANY) ret_from_intr: GET_THREAD_INFO(%ebp) -check_userspace: +resume_userspace_sig: +#ifdef CONFIG_VM86 movl PT_EFLAGS(%esp), %eax # mix EFLAGS and CS movb PT_CS(%esp), %al andl $(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %eax +#else + /* + * We can be coming here from a syscall done in the kernel space, + * e.g. a failed kernel_execve(). + */ + movl PT_CS(%esp), %eax + andl $SEGMENT_RPL_MASK, %eax +#endif cmpl $USER_RPL, %eax jb resume_kernel # not returning to v8086 or userspace diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 5f9ecff..fc1f48d 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -43,6 +43,8 @@ #include <linux/smp.h> #include <linux/nmi.h> #include <linux/hw_breakpoint.h> +#include <linux/uaccess.h> +#include <linux/memory.h> #include <asm/debugreg.h> #include <asm/apicdef.h> @@ -710,6 +712,64 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long ip) regs->ip = ip; } +int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt) +{ + int err; + char opc[BREAK_INSTR_SIZE]; + + bpt->type = BP_BREAKPOINT; + err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr, + BREAK_INSTR_SIZE); + if (err) + return err; + err = probe_kernel_write((char *)bpt->bpt_addr, + arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE); +#ifdef CONFIG_DEBUG_RODATA + if (!err) + return err; + /* + * It is safe to call text_poke() because normal kernel execution + * is stopped on all cores, so long as the text_mutex is not locked. + */ + if (mutex_is_locked(&text_mutex)) + return -EBUSY; + text_poke((void *)bpt->bpt_addr, arch_kgdb_ops.gdb_bpt_instr, + BREAK_INSTR_SIZE); + err = probe_kernel_read(opc, (char *)bpt->bpt_addr, BREAK_INSTR_SIZE); + if (err) + return err; + if (memcmp(opc, arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE)) + return -EINVAL; + bpt->type = BP_POKE_BREAKPOINT; +#endif /* CONFIG_DEBUG_RODATA */ + return err; +} + +int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt) +{ +#ifdef CONFIG_DEBUG_RODATA + int err; + char opc[BREAK_INSTR_SIZE]; + + if (bpt->type != BP_POKE_BREAKPOINT) + goto knl_write; + /* + * It is safe to call text_poke() because normal kernel execution + * is stopped on all cores, so long as the text_mutex is not locked. + */ + if (mutex_is_locked(&text_mutex)) + goto knl_write; + text_poke((void *)bpt->bpt_addr, bpt->saved_instr, BREAK_INSTR_SIZE); + err = probe_kernel_read(opc, (char *)bpt->bpt_addr, BREAK_INSTR_SIZE); + if (err || memcmp(opc, bpt->saved_instr, BREAK_INSTR_SIZE)) + goto knl_write; + return err; +knl_write: +#endif /* CONFIG_DEBUG_RODATA */ + return probe_kernel_write((char *)bpt->bpt_addr, + (char *)bpt->saved_instr, BREAK_INSTR_SIZE); +} + struct kgdb_arch arch_kgdb_ops = { /* Breakpoint instruction: */ .gdb_bpt_instr = { 0xcc }, diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index c561038..b727450 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -298,13 +298,33 @@ free_table: return state; } +/* + * AMD microcode firmware naming convention, up to family 15h they are in + * the legacy file: + * + * amd-ucode/microcode_amd.bin + * + * This legacy file is always smaller than 2K in size. + * + * Starting at family 15h they are in family specific firmware files: + * + * amd-ucode/microcode_amd_fam15h.bin + * amd-ucode/microcode_amd_fam16h.bin + * ... + * + * These might be larger than 2K. + */ static enum ucode_state request_microcode_amd(int cpu, struct device *device) { - const char *fw_name = "amd-ucode/microcode_amd.bin"; + char fw_name[36] = "amd-ucode/microcode_amd.bin"; const struct firmware *fw; enum ucode_state ret = UCODE_NFOUND; + struct cpuinfo_x86 *c = &cpu_data(cpu); + + if (c->x86 >= 0x15) + snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", c->x86); - if (request_firmware(&fw, fw_name, device)) { + if (request_firmware(&fw, (const char *)fw_name, device)) { pr_err("failed to load file %s\n", fw_name); goto out; } diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index a3d0dc5..fcdb1b3 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -293,22 +293,11 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) *next = &next_p->thread; int cpu = smp_processor_id(); struct tss_struct *tss = &per_cpu(init_tss, cpu); - bool preload_fpu; + fpu_switch_t fpu; /* never put a printk in __switch_to... printk() calls wake_up*() indirectly */ - /* - * If the task has used fpu the last 5 timeslices, just do a full - * restore of the math state immediately to avoid the trap; the - * chances of needing FPU soon are obviously high now - */ - preload_fpu = tsk_used_math(next_p) && next_p->fpu_counter > 5; - - __unlazy_fpu(prev_p); - - /* we're going to use this soon, after a few expensive things */ - if (preload_fpu) - prefetch(next->fpu.state); + fpu = switch_fpu_prepare(prev_p, next_p); /* * Reload esp0. @@ -348,11 +337,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT)) __switch_to_xtra(prev_p, next_p, tss); - /* If we're going to preload the fpu context, make sure clts - is run while we're batching the cpu state updates. */ - if (preload_fpu) - clts(); - /* * Leave lazy mode, flushing any hypercalls made here. * This must be done before restoring TLS segments so @@ -362,15 +346,14 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) */ arch_end_context_switch(next_p); - if (preload_fpu) - __math_state_restore(); - /* * Restore %gs if needed (which is common) */ if (prev->gs | next->gs) lazy_load_gs(next->gs); + switch_fpu_finish(next_p, fpu); + percpu_write(current_task, next_p); return prev_p; diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 63c8aed..eeb5004 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -363,18 +363,9 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) int cpu = smp_processor_id(); struct tss_struct *tss = &per_cpu(init_tss, cpu); unsigned fsindex, gsindex; - bool preload_fpu; + fpu_switch_t fpu; - /* - * If the task has used fpu the last 5 timeslices, just do a full - * restore of the math state immediately to avoid the trap; the - * chances of needing FPU soon are obviously high now - */ - preload_fpu = tsk_used_math(next_p) && next_p->fpu_counter > 5; - - /* we're going to use this soon, after a few expensive things */ - if (preload_fpu) - prefetch(next->fpu.state); + fpu = switch_fpu_prepare(prev_p, next_p); /* * Reload esp0, LDT and the page table pointer: @@ -404,13 +395,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) load_TLS(next, cpu); - /* Must be after DS reload */ - __unlazy_fpu(prev_p); - - /* Make sure cpu is ready for new context */ - if (preload_fpu) - clts(); - /* * Leave lazy mode, flushing any hypercalls made here. * This must be done before restoring TLS segments so @@ -451,6 +435,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) wrmsrl(MSR_KERNEL_GS_BASE, next->gs); prev->gsindex = gsindex; + switch_fpu_finish(next_p, fpu); + /* * Switch the PDA and FPU contexts. */ @@ -469,13 +455,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV)) __switch_to_xtra(prev_p, next_p, tss); - /* - * Preload the FPU context, now that we've determined that the - * task is likely to be using it. - */ - if (preload_fpu) - __math_state_restore(); - return prev_p; } diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c index 6bb7b85..bcfec2d 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -163,7 +163,7 @@ int regset_tls_get(struct task_struct *target, const struct user_regset *regset, { const struct desc_struct *tls; - if (pos > GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) || + if (pos >= GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) || (pos % sizeof(struct user_desc)) != 0 || (count % sizeof(struct user_desc)) != 0) return -EINVAL; @@ -198,7 +198,7 @@ int regset_tls_set(struct task_struct *target, const struct user_regset *regset, struct user_desc infobuf[GDT_ENTRY_TLS_ENTRIES]; const struct user_desc *info; - if (pos > GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) || + if (pos >= GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) || (pos % sizeof(struct user_desc)) != 0 || (count % sizeof(struct user_desc)) != 0) return -EINVAL; diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index b9b6716..1b26e01 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -717,25 +717,34 @@ asmlinkage void __attribute__((weak)) smp_threshold_interrupt(void) } /* - * __math_state_restore assumes that cr0.TS is already clear and the - * fpu state is all ready for use. Used during context switch. + * This gets called with the process already owning the + * FPU state, and with CR0.TS cleared. It just needs to + * restore the FPU register state. */ -void __math_state_restore(void) +void __math_state_restore(struct task_struct *tsk) { - struct thread_info *thread = current_thread_info(); - struct task_struct *tsk = thread->task; + /* We need a safe address that is cheap to find and that is already + in L1. We've just brought in "tsk->thread.has_fpu", so use that */ +#define safe_address (tsk->thread.has_fpu) + + /* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception + is pending. Clear the x87 state here by setting it to fixed + values. safe_address is a random variable that should be in L1 */ + alternative_input( + ASM_NOP8 ASM_NOP2, + "emms\n\t" /* clear stack tags */ + "fildl %P[addr]", /* set F?P to defined value */ + X86_FEATURE_FXSAVE_LEAK, + [addr] "m" (safe_address)); /* * Paranoid restore. send a SIGSEGV if we fail to restore the state. */ if (unlikely(restore_fpu_checking(tsk))) { - stts(); + __thread_fpu_end(tsk); force_sig(SIGSEGV, tsk); return; } - - thread->status |= TS_USEDFPU; /* So we fnsave on switch_to() */ - tsk->fpu_counter++; } /* @@ -745,13 +754,12 @@ void __math_state_restore(void) * Careful.. There are problems with IBM-designed IRQ13 behaviour. * Don't touch unless you *really* know how it works. * - * Must be called with kernel preemption disabled (in this case, - * local interrupts are disabled at the call-site in entry.S). + * Must be called with kernel preemption disabled (eg with local + * local interrupts as in the case of do_device_not_available). */ -asmlinkage void math_state_restore(void) +void math_state_restore(void) { - struct thread_info *thread = current_thread_info(); - struct task_struct *tsk = thread->task; + struct task_struct *tsk = current; if (!tsk_used_math(tsk)) { local_irq_enable(); @@ -768,9 +776,10 @@ asmlinkage void math_state_restore(void) local_irq_disable(); } - clts(); /* Allow maths ops (or we recurse) */ + __thread_fpu_begin(tsk); + __math_state_restore(tsk); - __math_state_restore(); + tsk->fpu_counter++; } EXPORT_SYMBOL_GPL(math_state_restore); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 6cc6922..4406c03 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -623,7 +623,8 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) if (cpu_khz) { *scale = (NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR)/cpu_khz; - *offset = ns_now - (tsc_now * *scale >> CYC2NS_SCALE_FACTOR); + *offset = ns_now - mult_frac(tsc_now, *scale, + (1UL << CYC2NS_SCALE_FACTOR)); } sched_clock_idle_wakeup_event(0); @@ -956,6 +957,16 @@ static int __init init_tsc_clocksource(void) clocksource_tsc.rating = 0; clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS; } + + /* + * Trust the results of the earlier calibration on systems + * exporting a reliable TSC. + */ + if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) { + clocksource_register_khz(&clocksource_tsc, tsc_khz); + return 0; + } + schedule_delayed_work(&tsc_irqwork, 0); return 0; } diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 863f875..04b8726 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -172,6 +172,7 @@ static void mark_screen_rdonly(struct mm_struct *mm) spinlock_t *ptl; int i; + down_write(&mm->mmap_sem); pgd = pgd_offset(mm, 0xA0000); if (pgd_none_or_clear_bad(pgd)) goto out; @@ -190,6 +191,7 @@ static void mark_screen_rdonly(struct mm_struct *mm) } pte_unmap_unlock(pte, ptl); out: + up_write(&mm->mmap_sem); flush_tlb(); } diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index a391134..7110911 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -47,7 +47,7 @@ void __sanitize_i387_state(struct task_struct *tsk) if (!fx) return; - BUG_ON(task_thread_info(tsk)->status & TS_USEDFPU); + BUG_ON(__thread_has_fpu(tsk)); xstate_bv = tsk->thread.fpu.state->xsave.xsave_hdr.xstate_bv; @@ -168,7 +168,7 @@ int save_i387_xstate(void __user *buf) if (!used_math()) return 0; - if (task_thread_info(tsk)->status & TS_USEDFPU) { + if (user_has_fpu()) { if (use_xsave()) err = xsave_user(buf); else @@ -176,8 +176,7 @@ int save_i387_xstate(void __user *buf) if (err) return err; - task_thread_info(tsk)->status &= ~TS_USEDFPU; - stts(); + user_fpu_end(); } else { sanitize_i387_state(tsk); if (__copy_to_user(buf, &tsk->thread.fpu.state->fxsave, @@ -292,10 +291,7 @@ int restore_i387_xstate(void __user *buf) return err; } - if (!(task_thread_info(current)->status & TS_USEDFPU)) { - clts(); - task_thread_info(current)->status |= TS_USEDFPU; - } + user_fpu_begin(); if (use_xsave()) err = restore_user_xstate(buf); else diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index adc9867..3e7d913 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -1901,6 +1901,51 @@ setup_syscalls_segments(struct x86_emulate_ctxt *ctxt, ss->p = 1; } +static bool em_syscall_is_enabled(struct x86_emulate_ctxt *ctxt) +{ + struct x86_emulate_ops *ops = ctxt->ops; + u32 eax, ebx, ecx, edx; + + /* + * syscall should always be enabled in longmode - so only become + * vendor specific (cpuid) if other modes are active... + */ + if (ctxt->mode == X86EMUL_MODE_PROT64) + return true; + + eax = 0x00000000; + ecx = 0x00000000; + if (ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx)) { + /* + * Intel ("GenuineIntel") + * remark: Intel CPUs only support "syscall" in 64bit + * longmode. Also an 64bit guest with a + * 32bit compat-app running will #UD !! While this + * behaviour can be fixed (by emulating) into AMD + * response - CPUs of AMD can't behave like Intel. + */ + if (ebx == X86EMUL_CPUID_VENDOR_GenuineIntel_ebx && + ecx == X86EMUL_CPUID_VENDOR_GenuineIntel_ecx && + edx == X86EMUL_CPUID_VENDOR_GenuineIntel_edx) + return false; + + /* AMD ("AuthenticAMD") */ + if (ebx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx && + ecx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx && + edx == X86EMUL_CPUID_VENDOR_AuthenticAMD_edx) + return true; + + /* AMD ("AMDisbetter!") */ + if (ebx == X86EMUL_CPUID_VENDOR_AMDisbetterI_ebx && + ecx == X86EMUL_CPUID_VENDOR_AMDisbetterI_ecx && + edx == X86EMUL_CPUID_VENDOR_AMDisbetterI_edx) + return true; + } + + /* default: (not Intel, not AMD), apply Intel's stricter rules... */ + return false; +} + static int emulate_syscall(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) { @@ -1915,9 +1960,15 @@ emulate_syscall(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) ctxt->mode == X86EMUL_MODE_VM86) return emulate_ud(ctxt); + if (!(em_syscall_is_enabled(ctxt))) + return emulate_ud(ctxt); + ops->get_msr(ctxt, MSR_EFER, &efer); setup_syscalls_segments(ctxt, ops, &cs, &ss); + if (!(efer & EFER_SCE)) + return emulate_ud(ctxt); + ops->get_msr(ctxt, MSR_STAR, &msr_data); msr_data >>= 32; cs_sel = (u16)(msr_data & 0xfffc); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index d48ec60..2ad060a 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -948,7 +948,7 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx) #ifdef CONFIG_X86_64 wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base); #endif - if (current_thread_info()->status & TS_USEDFPU) + if (__thread_has_fpu(current)) clts(); load_gdt(&__get_cpu_var(host_gdt)); } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 77c9d86..fbb0936 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4407,6 +4407,28 @@ static int emulator_intercept(struct x86_emulate_ctxt *ctxt, return kvm_x86_ops->check_intercept(emul_to_vcpu(ctxt), info, stage); } +static bool emulator_get_cpuid(struct x86_emulate_ctxt *ctxt, + u32 *eax, u32 *ebx, u32 *ecx, u32 *edx) +{ + struct kvm_cpuid_entry2 *cpuid = NULL; + + if (eax && ecx) + cpuid = kvm_find_cpuid_entry(emul_to_vcpu(ctxt), + *eax, *ecx); + + if (cpuid) { + *eax = cpuid->eax; + *ecx = cpuid->ecx; + if (ebx) + *ebx = cpuid->ebx; + if (edx) + *edx = cpuid->edx; + return true; + } + + return false; +} + static struct x86_emulate_ops emulate_ops = { .read_std = kvm_read_guest_virt_system, .write_std = kvm_write_guest_virt_system, @@ -4437,6 +4459,7 @@ static struct x86_emulate_ops emulate_ops = { .get_fpu = emulator_get_fpu, .put_fpu = emulator_put_fpu, .intercept = emulator_intercept, + .get_cpuid = emulator_get_cpuid, }; static void cache_all_regs(struct kvm_vcpu *vcpu) diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c index fc45ba8..e395693 100644 --- a/arch/x86/lib/delay.c +++ b/arch/x86/lib/delay.c @@ -48,9 +48,9 @@ static void delay_loop(unsigned long loops) } /* TSC based delay: */ -static void delay_tsc(unsigned long loops) +static void delay_tsc(unsigned long __loops) { - unsigned long bclock, now; + u32 bclock, now, loops = __loops; int cpu; preempt_disable(); diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 1dab519..f927429 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -87,9 +87,9 @@ static unsigned long mmap_rnd(void) */ if (current->flags & PF_RANDOMIZE) { if (mmap_is_ia32()) - rnd = (long)get_random_int() % (1<<8); + rnd = get_random_int() % (1<<8); else - rnd = (long)(get_random_int() % (1<<28)); + rnd = get_random_int() % (1<<28); } return rnd << PAGE_SHIFT; } diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c index 81dbfde..7efd0c6 100644 --- a/arch/x86/mm/srat.c +++ b/arch/x86/mm/srat.c @@ -104,6 +104,8 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) if ((pa->flags & ACPI_SRAT_CPU_ENABLED) == 0) return; pxm = pa->proximity_domain_lo; + if (acpi_srat_revision >= 2) + pxm |= *((unsigned int*)pa->proximity_domain_hi) << 8; node = setup_node(pxm); if (node < 0) { printk(KERN_ERR "SRAT: Too many proximity domains %x\n", pxm); @@ -155,6 +157,8 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) start = ma->base_address; end = start + ma->length; pxm = ma->proximity_domain; + if (acpi_srat_revision <= 1) + pxm &= 0xff; node = setup_node(pxm); if (node < 0) { printk(KERN_ERR "SRAT: Too many proximity domains.\n"); diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index bfab3fa..5a5b6e4 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -151,17 +151,18 @@ void bpf_jit_compile(struct sk_filter *fp) cleanup_addr = proglen; /* epilogue address */ for (pass = 0; pass < 10; pass++) { + u8 seen_or_pass0 = (pass == 0) ? (SEEN_XREG | SEEN_DATAREF | SEEN_MEM) : seen; /* no prologue/epilogue for trivial filters (RET something) */ proglen = 0; prog = temp; - if (seen) { + if (seen_or_pass0) { EMIT4(0x55, 0x48, 0x89, 0xe5); /* push %rbp; mov %rsp,%rbp */ EMIT4(0x48, 0x83, 0xec, 96); /* subq $96,%rsp */ /* note : must save %rbx in case bpf_error is hit */ - if (seen & (SEEN_XREG | SEEN_DATAREF)) + if (seen_or_pass0 & (SEEN_XREG | SEEN_DATAREF)) EMIT4(0x48, 0x89, 0x5d, 0xf8); /* mov %rbx, -8(%rbp) */ - if (seen & SEEN_XREG) + if (seen_or_pass0 & SEEN_XREG) CLEAR_X(); /* make sure we dont leek kernel memory */ /* @@ -170,7 +171,7 @@ void bpf_jit_compile(struct sk_filter *fp) * r9 = skb->len - skb->data_len * r8 = skb->data */ - if (seen & SEEN_DATAREF) { + if (seen_or_pass0 & SEEN_DATAREF) { if (offsetof(struct sk_buff, len) <= 127) /* mov off8(%rdi),%r9d */ EMIT4(0x44, 0x8b, 0x4f, offsetof(struct sk_buff, len)); @@ -260,9 +261,14 @@ void bpf_jit_compile(struct sk_filter *fp) case BPF_S_ALU_DIV_X: /* A /= X; */ seen |= SEEN_XREG; EMIT2(0x85, 0xdb); /* test %ebx,%ebx */ - if (pc_ret0 != -1) - EMIT_COND_JMP(X86_JE, addrs[pc_ret0] - (addrs[i] - 4)); - else { + if (pc_ret0 > 0) { + /* addrs[pc_ret0 - 1] is start address of target + * (addrs[i] - 4) is the address following this jmp + * ("xor %edx,%edx; div %ebx" being 4 bytes long) + */ + EMIT_COND_JMP(X86_JE, addrs[pc_ret0 - 1] - + (addrs[i] - 4)); + } else { EMIT_COND_JMP(X86_JNE, 2 + 5); CLEAR_A(); EMIT1_off32(0xe9, cleanup_addr - (addrs[i] - 4)); /* jmp .+off32 */ @@ -283,7 +289,7 @@ void bpf_jit_compile(struct sk_filter *fp) EMIT2(0x24, K & 0xFF); /* and imm8,%al */ } else if (K >= 0xFFFF0000) { EMIT2(0x66, 0x25); /* and imm16,%ax */ - EMIT2(K, 2); + EMIT(K, 2); } else { EMIT1_off32(0x25, K); /* and imm32,%eax */ } @@ -335,12 +341,12 @@ void bpf_jit_compile(struct sk_filter *fp) } /* fallinto */ case BPF_S_RET_A: - if (seen) { + if (seen_or_pass0) { if (i != flen - 1) { EMIT_JMP(cleanup_addr - addrs[i]); break; } - if (seen & SEEN_XREG) + if (seen_or_pass0 & SEEN_XREG) EMIT4(0x48, 0x8b, 0x5d, 0xf8); /* mov -8(%rbp),%rbx */ EMIT1(0xc9); /* leaveq */ } @@ -469,8 +475,10 @@ void bpf_jit_compile(struct sk_filter *fp) case BPF_S_LD_W_ABS: func = sk_load_word; common_load: seen |= SEEN_DATAREF; - if ((int)K < 0) + if ((int)K < 0) { + /* Abort the JIT because __load_pointer() is needed. */ goto out; + } t_offset = func - (image + addrs[i]); EMIT1_off32(0xbe, K); /* mov imm32,%esi */ EMIT1_off32(0xe8, t_offset); /* call */ @@ -483,13 +491,8 @@ common_load: seen |= SEEN_DATAREF; goto common_load; case BPF_S_LDX_B_MSH: if ((int)K < 0) { - if (pc_ret0 != -1) { - EMIT_JMP(addrs[pc_ret0] - addrs[i]); - break; - } - CLEAR_A(); - EMIT_JMP(cleanup_addr - addrs[i]); - break; + /* Abort the JIT because __load_pointer() is needed. */ + goto out; } seen |= SEEN_DATAREF | SEEN_XREG; t_offset = sk_load_byte_msh - (image + addrs[i]); @@ -568,8 +571,8 @@ cond_branch: f_offset = addrs[i + filter[i].jf] - addrs[i]; break; } if (filter[i].jt != 0) { - if (filter[i].jf) - t_offset += is_near(f_offset) ? 2 : 6; + if (filter[i].jf && f_offset) + t_offset += is_near(f_offset) ? 2 : 5; EMIT_COND_JMP(t_op, t_offset); if (filter[i].jf) EMIT_JMP(f_offset); @@ -599,13 +602,14 @@ cond_branch: f_offset = addrs[i + filter[i].jf] - addrs[i]; * use it to give the cleanup instruction(s) addr */ cleanup_addr = proglen - 1; /* ret */ - if (seen) + if (seen_or_pass0) cleanup_addr -= 1; /* leaveq */ - if (seen & SEEN_XREG) + if (seen_or_pass0 & SEEN_XREG) cleanup_addr -= 4; /* mov -8(%rbp),%rbx */ if (image) { - WARN_ON(proglen != oldproglen); + if (proglen != oldproglen) + pr_err("bpb_jit_compile proglen=%u != oldproglen=%u\n", proglen, oldproglen); break; } if (proglen == oldproglen) { diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile index 6b8759f..d24d3da 100644 --- a/arch/x86/pci/Makefile +++ b/arch/x86/pci/Makefile @@ -18,8 +18,9 @@ obj-$(CONFIG_X86_NUMAQ) += numaq_32.o obj-$(CONFIG_X86_MRST) += mrst.o obj-y += common.o early.o -obj-y += amd_bus.o bus_numa.o +obj-y += bus_numa.o +obj-$(CONFIG_AMD_NB) += amd_bus.o obj-$(CONFIG_PCI_CNB20LE_QUIRK) += broadcom_bus.o ifeq ($(CONFIG_PCI_DEBUG),y) diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index 50b3f14..0473a8f 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -54,6 +54,16 @@ static const struct dmi_system_id pci_use_crs_table[] __initconst = { DMI_MATCH(DMI_BIOS_VENDOR, "American Megatrends Inc."), }, }, + /* https://bugzilla.kernel.org/show_bug.cgi?id=42619 */ + { + .callback = set_use_crs, + .ident = "MSI MS-7253", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "MICRO-STAR INTERNATIONAL CO., LTD"), + DMI_MATCH(DMI_BOARD_NAME, "MS-7253"), + DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies, LTD"), + }, + }, {} }; @@ -149,7 +159,7 @@ setup_resource(struct acpi_resource *acpi_res, void *data) struct acpi_resource_address64 addr; acpi_status status; unsigned long flags; - u64 start, end; + u64 start, orig_end, end; status = resource_to_addr(acpi_res, &addr); if (!ACPI_SUCCESS(status)) @@ -165,7 +175,21 @@ setup_resource(struct acpi_resource *acpi_res, void *data) return AE_OK; start = addr.minimum + addr.translation_offset; - end = addr.maximum + addr.translation_offset; + orig_end = end = addr.maximum + addr.translation_offset; + + /* Exclude non-addressable range or non-addressable portion of range */ + end = min(end, (u64)iomem_resource.end); + if (end <= start) { + dev_info(&info->bridge->dev, + "host bridge window [%#llx-%#llx] " + "(ignored, not CPU addressable)\n", start, orig_end); + return AE_OK; + } else if (orig_end != end) { + dev_info(&info->bridge->dev, + "host bridge window [%#llx-%#llx] " + "([%#llx-%#llx] ignored, not CPU addressable)\n", + start, orig_end, end + 1, orig_end); + } res = &info->res[info->res_num]; res->name = info->name; diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c index 026e493..385a940 100644 --- a/arch/x86/pci/amd_bus.c +++ b/arch/x86/pci/amd_bus.c @@ -30,34 +30,6 @@ static struct pci_hostbridge_probe pci_probes[] __initdata = { { 0, 0x18, PCI_VENDOR_ID_AMD, 0x1300 }, }; -static u64 __initdata fam10h_mmconf_start; -static u64 __initdata fam10h_mmconf_end; -static void __init get_pci_mmcfg_amd_fam10h_range(void) -{ - u32 address; - u64 base, msr; - unsigned segn_busn_bits; - - /* assume all cpus from fam10h have mmconf */ - if (boot_cpu_data.x86 < 0x10) - return; - - address = MSR_FAM10H_MMIO_CONF_BASE; - rdmsrl(address, msr); - - /* mmconfig is not enable */ - if (!(msr & FAM10H_MMIO_CONF_ENABLE)) - return; - - base = msr & (FAM10H_MMIO_CONF_BASE_MASK<<FAM10H_MMIO_CONF_BASE_SHIFT); - - segn_busn_bits = (msr >> FAM10H_MMIO_CONF_BUSRANGE_SHIFT) & - FAM10H_MMIO_CONF_BUSRANGE_MASK; - - fam10h_mmconf_start = base; - fam10h_mmconf_end = base + (1ULL<<(segn_busn_bits + 20)) - 1; -} - #define RANGE_NUM 16 /** @@ -85,6 +57,9 @@ static int __init early_fill_mp_bus_info(void) u64 val; u32 address; bool found; + struct resource fam10h_mmconf_res, *fam10h_mmconf; + u64 fam10h_mmconf_start; + u64 fam10h_mmconf_end; if (!early_pci_allowed()) return -1; @@ -211,12 +186,17 @@ static int __init early_fill_mp_bus_info(void) subtract_range(range, RANGE_NUM, 0, end); /* get mmconfig */ - get_pci_mmcfg_amd_fam10h_range(); + fam10h_mmconf = amd_get_mmconfig_range(&fam10h_mmconf_res); /* need to take out mmconf range */ - if (fam10h_mmconf_end) { - printk(KERN_DEBUG "Fam 10h mmconf [%llx, %llx]\n", fam10h_mmconf_start, fam10h_mmconf_end); + if (fam10h_mmconf) { + printk(KERN_DEBUG "Fam 10h mmconf %pR\n", fam10h_mmconf); + fam10h_mmconf_start = fam10h_mmconf->start; + fam10h_mmconf_end = fam10h_mmconf->end; subtract_range(range, RANGE_NUM, fam10h_mmconf_start, fam10h_mmconf_end + 1); + } else { + fam10h_mmconf_start = 0; + fam10h_mmconf_end = 0; } /* mmio resource */ diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index f567965..6e96e65 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -308,7 +308,7 @@ int __init pci_xen_init(void) int __init pci_xen_hvm_init(void) { - if (!xen_feature(XENFEAT_hvm_pirqs)) + if (!xen_have_vector_callback || !xen_feature(XENFEAT_hvm_pirqs)) return 0; #ifdef CONFIG_ACPI diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index 82cff4a..edf435b 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -1575,14 +1575,14 @@ static int calculate_destination_timeout(void) ts_ns = base * mult1 * mult2; ret = ts_ns / 1000; } else { - /* 4 bits 0/1 for 10/80us, 3 bits of multiplier */ - mmr_image = uv_read_local_mmr(UVH_AGING_PRESCALE_SEL); + /* 4 bits 0/1 for 10/80us base, 3 bits of multiplier */ + mmr_image = uv_read_local_mmr(UVH_LB_BAU_MISC_CONTROL); mmr_image = (mmr_image & UV_SA_MASK) >> UV_SA_SHFT; if (mmr_image & (1L << UV2_ACK_UNITS_SHFT)) - mult1 = 80; + base = 80; else - mult1 = 10; - base = mmr_image & UV2_ACK_MASK; + base = 10; + mult1 = mmr_image & UV2_ACK_MASK; ret = mult1 * base; } return ret; @@ -1820,6 +1820,8 @@ static int __init uv_bau_init(void) uv_base_pnode = uv_blade_to_pnode(uvhub); } + enable_timeouts(); + if (init_per_cpu(nuvhubs, uv_base_pnode)) { nobau = 1; return 0; @@ -1830,7 +1832,6 @@ static int __init uv_bau_init(void) if (uv_blade_nr_possible_cpus(uvhub)) init_uvhub(uvhub, vector, uv_base_pnode); - enable_timeouts(); alloc_intr_gate(vector, uv_bau_message_intr1); for_each_possible_blade(uvhub) { diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index d4fc6d4..2843b5e 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -172,6 +172,7 @@ static void __init xen_fill_possible_map(void) static void __init xen_filter_cpu_maps(void) { int i, rc; + unsigned int subtract = 0; if (!xen_initial_domain()) return; @@ -186,8 +187,22 @@ static void __init xen_filter_cpu_maps(void) } else { set_cpu_possible(i, false); set_cpu_present(i, false); + subtract++; } } +#ifdef CONFIG_HOTPLUG_CPU + /* This is akin to using 'nr_cpus' on the Linux command line. + * Which is OK as when we use 'dom0_max_vcpus=X' we can only + * have up to X, while nr_cpu_ids is greater than X. This + * normally is not a problem, except when CPU hotplugging + * is involved and then there might be more than X CPUs + * in the guest - which will not work as there is no + * hypercall to expand the max number of VCPUs an already + * running guest has. So cap it up to X. */ + if (subtract) + nr_cpu_ids = nr_cpu_ids - subtract; +#endif + } static void __init xen_smp_prepare_boot_cpu(void) diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 79d7362..3e45aa0 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -96,7 +96,7 @@ ENTRY(xen_restore_fl_direct) /* check for unmasked and pending */ cmpw $0x0001, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_pending - jz 1f + jnz 1f 2: call check_events 1: ENDPATCH(xen_restore_fl_direct) |