diff options
Diffstat (limited to 'arch')
119 files changed, 798 insertions, 447 deletions
diff --git a/arch/alpha/kernel/sys_alcor.c b/arch/alpha/kernel/sys_alcor.c index 118dc6af1805..7ad074fd5ab5 100644 --- a/arch/alpha/kernel/sys_alcor.c +++ b/arch/alpha/kernel/sys_alcor.c @@ -181,10 +181,10 @@ alcor_init_irq(void) * comes in on. This makes interrupt processing much easier. */ -static int __init +static int alcor_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[7][5] __initdata = { + static char irq_tab[7][5] = { /*INT INTA INTB INTC INTD */ /* note: IDSEL 17 is XLT only */ {16+13, 16+13, 16+13, 16+13, 16+13}, /* IdSel 17, TULIP */ diff --git a/arch/alpha/kernel/sys_cabriolet.c b/arch/alpha/kernel/sys_cabriolet.c index 4c50f8f40cbb..c0fa1fe5ce77 100644 --- a/arch/alpha/kernel/sys_cabriolet.c +++ b/arch/alpha/kernel/sys_cabriolet.c @@ -173,10 +173,10 @@ pc164_init_irq(void) * because it is the Saturn IO (SIO) PCI/ISA Bridge Chip. */ -static inline int __init +static inline int eb66p_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[5][5] __initdata = { + static char irq_tab[5][5] = { /*INT INTA INTB INTC INTD */ {16+0, 16+0, 16+5, 16+9, 16+13}, /* IdSel 6, slot 0, J25 */ {16+1, 16+1, 16+6, 16+10, 16+14}, /* IdSel 7, slot 1, J26 */ @@ -203,10 +203,10 @@ eb66p_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) * because it is the Saturn IO (SIO) PCI/ISA Bridge Chip. */ -static inline int __init +static inline int cabriolet_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[5][5] __initdata = { + static char irq_tab[5][5] = { /*INT INTA INTB INTC INTD */ { 16+2, 16+2, 16+7, 16+11, 16+15}, /* IdSel 5, slot 2, J21 */ { 16+0, 16+0, 16+5, 16+9, 16+13}, /* IdSel 6, slot 0, J19 */ @@ -287,10 +287,10 @@ cia_cab_init_pci(void) * */ -static inline int __init +static inline int alphapc164_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[7][5] __initdata = { + static char irq_tab[7][5] = { /*INT INTA INTB INTC INTD */ { 16+2, 16+2, 16+9, 16+13, 16+17}, /* IdSel 5, slot 2, J20 */ { 16+0, 16+0, 16+7, 16+11, 16+15}, /* IdSel 6, slot 0, J29 */ diff --git a/arch/alpha/kernel/sys_dp264.c b/arch/alpha/kernel/sys_dp264.c index 6c35159bc00e..9e1e40ea1d14 100644 --- a/arch/alpha/kernel/sys_dp264.c +++ b/arch/alpha/kernel/sys_dp264.c @@ -356,7 +356,7 @@ clipper_init_irq(void) * 10 64 bit PCI option slot 3 (not bus 0) */ -static int __init +static int isa_irq_fixup(const struct pci_dev *dev, int irq) { u8 irq8; @@ -372,10 +372,10 @@ isa_irq_fixup(const struct pci_dev *dev, int irq) return irq8 & 0xf; } -static int __init +static int dp264_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[6][5] __initdata = { + static char irq_tab[6][5] = { /*INT INTA INTB INTC INTD */ { -1, -1, -1, -1, -1}, /* IdSel 5 ISA Bridge */ { 16+ 3, 16+ 3, 16+ 2, 16+ 2, 16+ 2}, /* IdSel 6 SCSI builtin*/ @@ -394,10 +394,10 @@ dp264_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) return isa_irq_fixup(dev, irq); } -static int __init +static int monet_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[13][5] __initdata = { + static char irq_tab[13][5] = { /*INT INTA INTB INTC INTD */ { 45, 45, 45, 45, 45}, /* IdSel 3 21143 PCI1 */ { -1, -1, -1, -1, -1}, /* IdSel 4 unused */ @@ -423,7 +423,7 @@ monet_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) return isa_irq_fixup(dev, COMMON_TABLE_LOOKUP); } -static u8 __init +static u8 monet_swizzle(struct pci_dev *dev, u8 *pinp) { struct pci_controller *hose = dev->sysdata; @@ -456,10 +456,10 @@ monet_swizzle(struct pci_dev *dev, u8 *pinp) return slot; } -static int __init +static int webbrick_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[13][5] __initdata = { + static char irq_tab[13][5] = { /*INT INTA INTB INTC INTD */ { -1, -1, -1, -1, -1}, /* IdSel 7 ISA Bridge */ { -1, -1, -1, -1, -1}, /* IdSel 8 unused */ @@ -478,10 +478,10 @@ webbrick_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) return isa_irq_fixup(dev, COMMON_TABLE_LOOKUP); } -static int __init +static int clipper_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[7][5] __initdata = { + static char irq_tab[7][5] = { /*INT INTA INTB INTC INTD */ { 16+ 8, 16+ 8, 16+ 9, 16+10, 16+11}, /* IdSel 1 slot 1 */ { 16+12, 16+12, 16+13, 16+14, 16+15}, /* IdSel 2 slot 2 */ diff --git a/arch/alpha/kernel/sys_eb64p.c b/arch/alpha/kernel/sys_eb64p.c index ad40a425e841..372661c56537 100644 --- a/arch/alpha/kernel/sys_eb64p.c +++ b/arch/alpha/kernel/sys_eb64p.c @@ -167,10 +167,10 @@ eb64p_init_irq(void) * comes in on. This makes interrupt processing much easier. */ -static int __init +static int eb64p_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[5][5] __initdata = { + static char irq_tab[5][5] = { /*INT INTA INTB INTC INTD */ {16+7, 16+7, 16+7, 16+7, 16+7}, /* IdSel 5, slot ?, ?? */ {16+0, 16+0, 16+2, 16+4, 16+9}, /* IdSel 6, slot ?, ?? */ diff --git a/arch/alpha/kernel/sys_eiger.c b/arch/alpha/kernel/sys_eiger.c index 15f42083bdb3..2731738b5872 100644 --- a/arch/alpha/kernel/sys_eiger.c +++ b/arch/alpha/kernel/sys_eiger.c @@ -141,7 +141,7 @@ eiger_init_irq(void) } } -static int __init +static int eiger_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { u8 irq_orig; @@ -158,7 +158,7 @@ eiger_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) return irq_orig - 0x80; } -static u8 __init +static u8 eiger_swizzle(struct pci_dev *dev, u8 *pinp) { struct pci_controller *hose = dev->sysdata; diff --git a/arch/alpha/kernel/sys_miata.c b/arch/alpha/kernel/sys_miata.c index d5b9776a608d..731d693fa1f9 100644 --- a/arch/alpha/kernel/sys_miata.c +++ b/arch/alpha/kernel/sys_miata.c @@ -149,10 +149,10 @@ miata_init_irq(void) * comes in on. This makes interrupt processing much easier. */ -static int __init +static int miata_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[18][5] __initdata = { + static char irq_tab[18][5] = { /*INT INTA INTB INTC INTD */ {16+ 8, 16+ 8, 16+ 8, 16+ 8, 16+ 8}, /* IdSel 14, DC21142 */ { -1, -1, -1, -1, -1}, /* IdSel 15, EIDE */ @@ -196,7 +196,7 @@ miata_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) return COMMON_TABLE_LOOKUP; } -static u8 __init +static u8 miata_swizzle(struct pci_dev *dev, u8 *pinp) { int slot, pin = *pinp; diff --git a/arch/alpha/kernel/sys_mikasa.c b/arch/alpha/kernel/sys_mikasa.c index 5e82dc1ad6f2..350ec9c8335b 100644 --- a/arch/alpha/kernel/sys_mikasa.c +++ b/arch/alpha/kernel/sys_mikasa.c @@ -145,10 +145,10 @@ mikasa_init_irq(void) * comes in on. This makes interrupt processing much easier. */ -static int __init +static int mikasa_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[8][5] __initdata = { + static char irq_tab[8][5] = { /*INT INTA INTB INTC INTD */ {16+12, 16+12, 16+12, 16+12, 16+12}, /* IdSel 17, SCSI */ { -1, -1, -1, -1, -1}, /* IdSel 18, PCEB */ diff --git a/arch/alpha/kernel/sys_nautilus.c b/arch/alpha/kernel/sys_nautilus.c index 8ae04a121186..d019e4ce07bd 100644 --- a/arch/alpha/kernel/sys_nautilus.c +++ b/arch/alpha/kernel/sys_nautilus.c @@ -62,7 +62,7 @@ nautilus_init_irq(void) common_init_isa_dma(); } -static int __init +static int nautilus_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { /* Preserve the IRQ set up by the console. */ diff --git a/arch/alpha/kernel/sys_noritake.c b/arch/alpha/kernel/sys_noritake.c index 063e594fd969..2301678d9f9d 100644 --- a/arch/alpha/kernel/sys_noritake.c +++ b/arch/alpha/kernel/sys_noritake.c @@ -193,10 +193,10 @@ noritake_init_irq(void) * comes in on. This makes interrupt processing much easier. */ -static int __init +static int noritake_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[15][5] __initdata = { + static char irq_tab[15][5] = { /*INT INTA INTB INTC INTD */ /* note: IDSELs 16, 17, and 25 are CORELLE only */ { 16+1, 16+1, 16+1, 16+1, 16+1}, /* IdSel 16, QLOGIC */ @@ -221,7 +221,7 @@ noritake_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) return COMMON_TABLE_LOOKUP; } -static u8 __init +static u8 noritake_swizzle(struct pci_dev *dev, u8 *pinp) { int slot, pin = *pinp; diff --git a/arch/alpha/kernel/sys_rawhide.c b/arch/alpha/kernel/sys_rawhide.c index dfd510ae5d8c..546822d07dc7 100644 --- a/arch/alpha/kernel/sys_rawhide.c +++ b/arch/alpha/kernel/sys_rawhide.c @@ -221,10 +221,10 @@ rawhide_init_irq(void) * */ -static int __init +static int rawhide_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[5][5] __initdata = { + static char irq_tab[5][5] = { /*INT INTA INTB INTC INTD */ { 16+16, 16+16, 16+16, 16+16, 16+16}, /* IdSel 1 SCSI PCI 1 */ { 16+ 0, 16+ 0, 16+ 1, 16+ 2, 16+ 3}, /* IdSel 2 slot 2 */ diff --git a/arch/alpha/kernel/sys_ruffian.c b/arch/alpha/kernel/sys_ruffian.c index a3f485257170..3b35e1913492 100644 --- a/arch/alpha/kernel/sys_ruffian.c +++ b/arch/alpha/kernel/sys_ruffian.c @@ -117,10 +117,10 @@ ruffian_kill_arch (int mode) * */ -static int __init +static int ruffian_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[11][5] __initdata = { + static char irq_tab[11][5] = { /*INT INTA INTB INTC INTD */ {-1, -1, -1, -1, -1}, /* IdSel 13, 21052 */ {-1, -1, -1, -1, -1}, /* IdSel 14, SIO */ @@ -139,7 +139,7 @@ ruffian_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) return COMMON_TABLE_LOOKUP; } -static u8 __init +static u8 ruffian_swizzle(struct pci_dev *dev, u8 *pinp) { int slot, pin = *pinp; diff --git a/arch/alpha/kernel/sys_rx164.c b/arch/alpha/kernel/sys_rx164.c index 08ee737d4fba..e178007107ef 100644 --- a/arch/alpha/kernel/sys_rx164.c +++ b/arch/alpha/kernel/sys_rx164.c @@ -142,7 +142,7 @@ rx164_init_irq(void) * */ -static int __init +static int rx164_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { #if 0 @@ -156,7 +156,7 @@ rx164_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { 16+1, 16+1, 16+6, 16+11, 16+16}, /* IdSel 10, slot 4 */ }; #else - static char irq_tab[6][5] __initdata = { + static char irq_tab[6][5] = { /*INT INTA INTB INTC INTD */ { 16+0, 16+0, 16+6, 16+11, 16+16}, /* IdSel 5, slot 0 */ { 16+1, 16+1, 16+7, 16+12, 16+17}, /* IdSel 6, slot 1 */ diff --git a/arch/alpha/kernel/sys_sable.c b/arch/alpha/kernel/sys_sable.c index 8a0aa6d67b53..86d259c2612d 100644 --- a/arch/alpha/kernel/sys_sable.c +++ b/arch/alpha/kernel/sys_sable.c @@ -192,10 +192,10 @@ sable_init_irq(void) * with the values in the irq swizzling tables above. */ -static int __init +static int sable_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[9][5] __initdata = { + static char irq_tab[9][5] = { /*INT INTA INTB INTC INTD */ { 32+0, 32+0, 32+0, 32+0, 32+0}, /* IdSel 0, TULIP */ { 32+1, 32+1, 32+1, 32+1, 32+1}, /* IdSel 1, SCSI */ @@ -374,10 +374,10 @@ lynx_init_irq(void) * with the values in the irq swizzling tables above. */ -static int __init +static int lynx_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[19][5] __initdata = { + static char irq_tab[19][5] = { /*INT INTA INTB INTC INTD */ { -1, -1, -1, -1, -1}, /* IdSel 13, PCEB */ { -1, -1, -1, -1, -1}, /* IdSel 14, PPB */ @@ -404,7 +404,7 @@ lynx_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) return COMMON_TABLE_LOOKUP; } -static u8 __init +static u8 lynx_swizzle(struct pci_dev *dev, u8 *pinp) { int slot, pin = *pinp; diff --git a/arch/alpha/kernel/sys_sio.c b/arch/alpha/kernel/sys_sio.c index febd24eba7a6..9fd2895639d5 100644 --- a/arch/alpha/kernel/sys_sio.c +++ b/arch/alpha/kernel/sys_sio.c @@ -144,7 +144,7 @@ sio_fixup_irq_levels(unsigned int level_bits) outb((level_bits >> 8) & 0xff, 0x4d1); } -static inline int __init +static inline int noname_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { /* @@ -165,7 +165,7 @@ noname_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) * that they use the default INTA line, if they are interrupt * driven at all). */ - static char irq_tab[][5] __initdata = { + static char irq_tab[][5] = { /*INT A B C D */ { 3, 3, 3, 3, 3}, /* idsel 6 (53c810) */ {-1, -1, -1, -1, -1}, /* idsel 7 (SIO: PCI/ISA bridge) */ @@ -183,10 +183,10 @@ noname_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) return irq >= 0 ? tmp : -1; } -static inline int __init +static inline int p2k_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[][5] __initdata = { + static char irq_tab[][5] = { /*INT A B C D */ { 0, 0, -1, -1, -1}, /* idsel 6 (53c810) */ {-1, -1, -1, -1, -1}, /* idsel 7 (SIO: PCI/ISA bridge) */ diff --git a/arch/alpha/kernel/sys_sx164.c b/arch/alpha/kernel/sys_sx164.c index d063b360efed..23eee54d714a 100644 --- a/arch/alpha/kernel/sys_sx164.c +++ b/arch/alpha/kernel/sys_sx164.c @@ -94,10 +94,10 @@ sx164_init_irq(void) * 9 32 bit PCI option slot 3 */ -static int __init +static int sx164_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[5][5] __initdata = { + static char irq_tab[5][5] = { /*INT INTA INTB INTC INTD */ { 16+ 9, 16+ 9, 16+13, 16+17, 16+21}, /* IdSel 5 slot 2 J17 */ { 16+11, 16+11, 16+15, 16+19, 16+23}, /* IdSel 6 slot 0 J19 */ diff --git a/arch/alpha/kernel/sys_takara.c b/arch/alpha/kernel/sys_takara.c index dd0f1eae3c68..9101f2bb6176 100644 --- a/arch/alpha/kernel/sys_takara.c +++ b/arch/alpha/kernel/sys_takara.c @@ -155,10 +155,10 @@ takara_init_irq(void) * assign it whatever the hell IRQ we like and it doesn't matter. */ -static int __init +static int takara_map_irq_srm(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[15][5] __initdata = { + static char irq_tab[15][5] = { { 16+3, 16+3, 16+3, 16+3, 16+3}, /* slot 6 == device 3 */ { 16+2, 16+2, 16+2, 16+2, 16+2}, /* slot 7 == device 2 */ { 16+1, 16+1, 16+1, 16+1, 16+1}, /* slot 8 == device 1 */ @@ -210,7 +210,7 @@ takara_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) return COMMON_TABLE_LOOKUP; } -static u8 __init +static u8 takara_swizzle(struct pci_dev *dev, u8 *pinp) { int slot = PCI_SLOT(dev->devfn); diff --git a/arch/alpha/kernel/sys_wildfire.c b/arch/alpha/kernel/sys_wildfire.c index ee1874887776..c3f8b79fe214 100644 --- a/arch/alpha/kernel/sys_wildfire.c +++ b/arch/alpha/kernel/sys_wildfire.c @@ -288,10 +288,10 @@ wildfire_device_interrupt(unsigned long vector) * 7 64 bit PCI 1 option slot 7 */ -static int __init +static int wildfire_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[8][5] __initdata = { + static char irq_tab[8][5] = { /*INT INTA INTB INTC INTD */ { -1, -1, -1, -1, -1}, /* IdSel 0 ISA Bridge */ { 36, 36, 36+1, 36+2, 36+3}, /* IdSel 1 SCSI builtin */ diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts index 8adde1b492f1..8f627c200d60 100644 --- a/arch/arc/boot/dts/hsdk.dts +++ b/arch/arc/boot/dts/hsdk.dts @@ -137,14 +137,15 @@ /* * DW sdio controller has external ciu clock divider * controlled via register in SDIO IP. Due to its - * unexpected default value (it should devide by 1 - * but it devides by 8) SDIO IP uses wrong clock and + * unexpected default value (it should divide by 1 + * but it divides by 8) SDIO IP uses wrong clock and * works unstable (see STAR 9001204800) + * We switched to the minimum possible value of the + * divisor (div-by-2) in HSDK platform code. * So add temporary fix and change clock frequency - * from 100000000 to 12500000 Hz until we fix dw sdio - * driver itself. + * to 50000000 Hz until we fix dw sdio driver itself. */ - clock-frequency = <12500000>; + clock-frequency = <50000000>; #clock-cells = <0>; }; diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig index 15f0f6b5fec1..7b8f8faf8a24 100644 --- a/arch/arc/configs/hsdk_defconfig +++ b/arch/arc/configs/hsdk_defconfig @@ -63,7 +63,6 @@ CONFIG_MMC_SDHCI=y CONFIG_MMC_SDHCI_PLTFM=y CONFIG_MMC_DW=y # CONFIG_IOMMU_SUPPORT is not set -CONFIG_RESET_HSDK=y CONFIG_EXT3_FS=y CONFIG_VFAT_FS=y CONFIG_TMPFS=y diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c index f46267153ec2..6df9d94a9537 100644 --- a/arch/arc/kernel/smp.c +++ b/arch/arc/kernel/smp.c @@ -23,6 +23,8 @@ #include <linux/cpumask.h> #include <linux/reboot.h> #include <linux/irqdomain.h> +#include <linux/export.h> + #include <asm/processor.h> #include <asm/setup.h> #include <asm/mach_desc.h> @@ -30,6 +32,9 @@ #ifndef CONFIG_ARC_HAS_LLSC arch_spinlock_t smp_atomic_ops_lock = __ARCH_SPIN_LOCK_UNLOCKED; arch_spinlock_t smp_bitops_lock = __ARCH_SPIN_LOCK_UNLOCKED; + +EXPORT_SYMBOL_GPL(smp_atomic_ops_lock); +EXPORT_SYMBOL_GPL(smp_bitops_lock); #endif struct plat_smp_ops __weak plat_smp_ops; diff --git a/arch/arc/plat-hsdk/Kconfig b/arch/arc/plat-hsdk/Kconfig index bd08de4be75e..19ab3cf98f0f 100644 --- a/arch/arc/plat-hsdk/Kconfig +++ b/arch/arc/plat-hsdk/Kconfig @@ -8,3 +8,4 @@ menuconfig ARC_SOC_HSDK bool "ARC HS Development Kit SOC" select CLK_HSDK + select RESET_HSDK diff --git a/arch/arc/plat-hsdk/platform.c b/arch/arc/plat-hsdk/platform.c index 744e62e58788..fd0ae5e38639 100644 --- a/arch/arc/plat-hsdk/platform.c +++ b/arch/arc/plat-hsdk/platform.c @@ -74,6 +74,10 @@ static void __init hsdk_set_cpu_freq_1ghz(void) pr_err("Failed to setup CPU frequency to 1GHz!"); } +#define SDIO_BASE (ARC_PERIPHERAL_BASE + 0xA000) +#define SDIO_UHS_REG_EXT (SDIO_BASE + 0x108) +#define SDIO_UHS_REG_EXT_DIV_2 (2 << 30) + static void __init hsdk_init_early(void) { /* @@ -90,6 +94,12 @@ static void __init hsdk_init_early(void) writel(1, (void __iomem *) CREG_PAE_UPDATE); /* + * Switch SDIO external ciu clock divider from default div-by-8 to + * minimum possible div-by-2. + */ + iowrite32(SDIO_UHS_REG_EXT_DIV_2, (void __iomem *) SDIO_UHS_REG_EXT); + + /* * Setup CPU frequency to 1GHz. * TODO: remove it after smart hsdk pll driver will be introduced. */ diff --git a/arch/arm/Makefile b/arch/arm/Makefile index 47d3a1ab08d2..817e5cfef83a 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -131,7 +131,7 @@ endif KBUILD_CFLAGS +=$(CFLAGS_ABI) $(CFLAGS_ISA) $(arch-y) $(tune-y) $(call cc-option,-mshort-load-bytes,$(call cc-option,-malignment-traps,)) -msoft-float -Uarm KBUILD_AFLAGS +=$(CFLAGS_ABI) $(AFLAGS_ISA) $(arch-y) $(tune-y) -include asm/unified.h -msoft-float -CHECKFLAGS += -D__arm__ +CHECKFLAGS += -D__arm__ -m32 #Default value head-y := arch/arm/kernel/head$(MMUEXT).o diff --git a/arch/arm/boot/compressed/debug.S b/arch/arm/boot/compressed/debug.S index 5392ee63338f..8f6e37177de1 100644 --- a/arch/arm/boot/compressed/debug.S +++ b/arch/arm/boot/compressed/debug.S @@ -23,7 +23,11 @@ ENTRY(putc) strb r0, [r1] mov r0, #0x03 @ SYS_WRITEC ARM( svc #0x123456 ) +#ifdef CONFIG_CPU_V7M + THUMB( bkpt #0xab ) +#else THUMB( svc #0xab ) +#endif mov pc, lr .align 2 1: .word _GLOBAL_OFFSET_TABLE_ - . diff --git a/arch/arm/boot/dts/armada-38x.dtsi b/arch/arm/boot/dts/armada-38x.dtsi index 7ff0811e61db..4960722aab32 100644 --- a/arch/arm/boot/dts/armada-38x.dtsi +++ b/arch/arm/boot/dts/armada-38x.dtsi @@ -178,7 +178,7 @@ }; i2c0: i2c@11000 { - compatible = "marvell,mv64xxx-i2c"; + compatible = "marvell,mv78230-a0-i2c", "marvell,mv64xxx-i2c"; reg = <0x11000 0x20>; #address-cells = <1>; #size-cells = <0>; @@ -189,7 +189,7 @@ }; i2c1: i2c@11100 { - compatible = "marvell,mv64xxx-i2c"; + compatible = "marvell,mv78230-a0-i2c", "marvell,mv64xxx-i2c"; reg = <0x11100 0x20>; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/at91-sama5d27_som1.dtsi b/arch/arm/boot/dts/at91-sama5d27_som1.dtsi index 63a5af898165..cf0087b4c9e1 100644 --- a/arch/arm/boot/dts/at91-sama5d27_som1.dtsi +++ b/arch/arm/boot/dts/at91-sama5d27_som1.dtsi @@ -67,8 +67,8 @@ pinctrl-0 = <&pinctrl_macb0_default>; phy-mode = "rmii"; - ethernet-phy@1 { - reg = <0x1>; + ethernet-phy@0 { + reg = <0x0>; interrupt-parent = <&pioA>; interrupts = <PIN_PD31 IRQ_TYPE_LEVEL_LOW>; pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/at91-sama5d2_xplained.dts b/arch/arm/boot/dts/at91-sama5d2_xplained.dts index c7e9ccf2bc87..cbc26001247b 100644 --- a/arch/arm/boot/dts/at91-sama5d2_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d2_xplained.dts @@ -309,7 +309,7 @@ vddana-supply = <&vdd_3v3_lp_reg>; vref-supply = <&vdd_3v3_lp_reg>; pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_adc_default>; + pinctrl-0 = <&pinctrl_adc_default &pinctrl_adtrg_default>; status = "okay"; }; @@ -340,6 +340,20 @@ bias-disable; }; + /* + * The ADTRG pin can work on any edge type. + * In here it's being pulled up, so need to + * connect it to ground to get an edge e.g. + * Trigger can be configured on falling, rise + * or any edge, and the pull-up can be changed + * to pull-down or left floating according to + * needs. + */ + pinctrl_adtrg_default: adtrg_default { + pinmux = <PIN_PD31__ADTRG>; + bias-pull-up; + }; + pinctrl_charger_chglev: charger_chglev { pinmux = <PIN_PA12__GPIO>; bias-disable; diff --git a/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts b/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts index 82651c3eb682..b8565fc33eea 100644 --- a/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts +++ b/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts @@ -18,12 +18,9 @@ compatible = "raspberrypi,model-zero-w", "brcm,bcm2835"; model = "Raspberry Pi Zero W"; - /* Needed by firmware to properly init UARTs */ - aliases { - uart0 = "/soc/serial@7e201000"; - uart1 = "/soc/serial@7e215040"; - serial0 = "/soc/serial@7e201000"; - serial1 = "/soc/serial@7e215040"; + chosen { + /* 8250 auxiliary UART instead of pl011 */ + stdout-path = "serial1:115200n8"; }; leds { diff --git a/arch/arm/boot/dts/bcm2837-rpi-3-b.dts b/arch/arm/boot/dts/bcm2837-rpi-3-b.dts index 20725ca487f3..c71a0d73d2a2 100644 --- a/arch/arm/boot/dts/bcm2837-rpi-3-b.dts +++ b/arch/arm/boot/dts/bcm2837-rpi-3-b.dts @@ -8,6 +8,11 @@ compatible = "raspberrypi,3-model-b", "brcm,bcm2837"; model = "Raspberry Pi 3 Model B"; + chosen { + /* 8250 auxiliary UART instead of pl011 */ + stdout-path = "serial1:115200n8"; + }; + memory { reg = <0 0x40000000>; }; diff --git a/arch/arm/boot/dts/bcm283x.dtsi b/arch/arm/boot/dts/bcm283x.dtsi index 431dcfc900c0..013431e3d7c3 100644 --- a/arch/arm/boot/dts/bcm283x.dtsi +++ b/arch/arm/boot/dts/bcm283x.dtsi @@ -20,8 +20,13 @@ #address-cells = <1>; #size-cells = <1>; + aliases { + serial0 = &uart0; + serial1 = &uart1; + }; + chosen { - bootargs = "earlyprintk console=ttyAMA0"; + stdout-path = "serial0:115200n8"; }; thermal-zones { diff --git a/arch/arm/boot/dts/gemini.dtsi b/arch/arm/boot/dts/gemini.dtsi index c68e8d430234..f0d178c77153 100644 --- a/arch/arm/boot/dts/gemini.dtsi +++ b/arch/arm/boot/dts/gemini.dtsi @@ -145,11 +145,12 @@ }; watchdog@41000000 { - compatible = "cortina,gemini-watchdog"; + compatible = "cortina,gemini-watchdog", "faraday,ftwdt010"; reg = <0x41000000 0x1000>; interrupts = <3 IRQ_TYPE_LEVEL_HIGH>; resets = <&syscon GEMINI_RESET_WDOG>; clocks = <&syscon GEMINI_CLK_APB>; + clock-names = "PCLK"; }; uart0: serial@42000000 { diff --git a/arch/arm/boot/dts/imx7d.dtsi b/arch/arm/boot/dts/imx7d.dtsi index f46814a7ea44..4d308d17f040 100644 --- a/arch/arm/boot/dts/imx7d.dtsi +++ b/arch/arm/boot/dts/imx7d.dtsi @@ -144,10 +144,10 @@ interrupt-names = "msi"; #interrupt-cells = <1>; interrupt-map-mask = <0 0 0 0x7>; - interrupt-map = <0 0 0 1 &intc GIC_SPI 125 IRQ_TYPE_LEVEL_HIGH>, - <0 0 0 2 &intc GIC_SPI 124 IRQ_TYPE_LEVEL_HIGH>, - <0 0 0 3 &intc GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>, - <0 0 0 4 &intc GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>; + interrupt-map = <0 0 0 1 &intc GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 2 &intc GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 3 &intc GIC_SPI 124 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 4 &intc GIC_SPI 125 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX7D_PCIE_CTRL_ROOT_CLK>, <&clks IMX7D_PLL_ENET_MAIN_100M_CLK>, <&clks IMX7D_PCIE_PHY_ROOT_CLK>; diff --git a/arch/arm/boot/dts/moxart.dtsi b/arch/arm/boot/dts/moxart.dtsi index 1f4c795d3f72..da7b3237bfe9 100644 --- a/arch/arm/boot/dts/moxart.dtsi +++ b/arch/arm/boot/dts/moxart.dtsi @@ -87,9 +87,10 @@ }; watchdog: watchdog@98500000 { - compatible = "moxa,moxart-watchdog"; + compatible = "moxa,moxart-watchdog", "faraday,ftwdt010"; reg = <0x98500000 0x10>; clocks = <&clk_apb>; + clock-names = "PCLK"; }; sdhci: sdhci@98e00000 { diff --git a/arch/arm/boot/dts/sama5d2.dtsi b/arch/arm/boot/dts/sama5d2.dtsi index 38d2216c7ead..b1a26b42d190 100644 --- a/arch/arm/boot/dts/sama5d2.dtsi +++ b/arch/arm/boot/dts/sama5d2.dtsi @@ -1430,6 +1430,7 @@ atmel,min-sample-rate-hz = <200000>; atmel,max-sample-rate-hz = <20000000>; atmel,startup-time-ms = <4>; + atmel,trigger-edge-type = <IRQ_TYPE_EDGE_RISING>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/sun6i-a31.dtsi b/arch/arm/boot/dts/sun6i-a31.dtsi index b147cb0dc14b..eef072a21acc 100644 --- a/arch/arm/boot/dts/sun6i-a31.dtsi +++ b/arch/arm/boot/dts/sun6i-a31.dtsi @@ -311,8 +311,8 @@ #size-cells = <0>; reg = <0>; - tcon1_in_drc1: endpoint@0 { - reg = <0>; + tcon1_in_drc1: endpoint@1 { + reg = <1>; remote-endpoint = <&drc1_out_tcon1>; }; }; @@ -1012,8 +1012,8 @@ #size-cells = <0>; reg = <1>; - be1_out_drc1: endpoint@0 { - reg = <0>; + be1_out_drc1: endpoint@1 { + reg = <1>; remote-endpoint = <&drc1_in_be1>; }; }; @@ -1042,8 +1042,8 @@ #size-cells = <0>; reg = <0>; - drc1_in_be1: endpoint@0 { - reg = <0>; + drc1_in_be1: endpoint@1 { + reg = <1>; remote-endpoint = <&be1_out_drc1>; }; }; @@ -1053,8 +1053,8 @@ #size-cells = <0>; reg = <1>; - drc1_out_tcon1: endpoint@0 { - reg = <0>; + drc1_out_tcon1: endpoint@1 { + reg = <1>; remote-endpoint = <&tcon1_in_drc1>; }; }; diff --git a/arch/arm/kernel/debug.S b/arch/arm/kernel/debug.S index ea9646cc2a0e..0a498cb3fad8 100644 --- a/arch/arm/kernel/debug.S +++ b/arch/arm/kernel/debug.S @@ -115,7 +115,11 @@ ENTRY(printascii) mov r1, r0 mov r0, #0x04 @ SYS_WRITE0 ARM( svc #0x123456 ) +#ifdef CONFIG_CPU_V7M + THUMB( bkpt #0xab ) +#else THUMB( svc #0xab ) +#endif ret lr ENDPROC(printascii) @@ -124,7 +128,11 @@ ENTRY(printch) strb r0, [r1] mov r0, #0x03 @ SYS_WRITEC ARM( svc #0x123456 ) +#ifdef CONFIG_CPU_V7M + THUMB( bkpt #0xab ) +#else THUMB( svc #0xab ) +#endif ret lr ENDPROC(printch) diff --git a/arch/arm/mach-ux500/cpu-db8500.c b/arch/arm/mach-ux500/cpu-db8500.c index 71a34e8c345a..57058ac46f49 100644 --- a/arch/arm/mach-ux500/cpu-db8500.c +++ b/arch/arm/mach-ux500/cpu-db8500.c @@ -32,6 +32,7 @@ #include <asm/mach/arch.h> #include "db8500-regs.h" +#include "pm_domains.h" static int __init ux500_l2x0_unlock(void) { @@ -157,6 +158,9 @@ static const struct of_device_id u8500_local_bus_nodes[] = { static void __init u8500_init_machine(void) { + /* Initialize ux500 power domains */ + ux500_pm_domains_init(); + /* automatically probe child nodes of dbx5x0 devices */ if (of_machine_is_compatible("st-ericsson,u8540")) of_platform_populate(NULL, u8500_local_bus_nodes, diff --git a/arch/arm/mach-ux500/pm.c b/arch/arm/mach-ux500/pm.c index a970e7fcba9e..f6c33a0c1c61 100644 --- a/arch/arm/mach-ux500/pm.c +++ b/arch/arm/mach-ux500/pm.c @@ -19,7 +19,6 @@ #include <linux/of_address.h> #include "db8500-regs.h" -#include "pm_domains.h" /* ARM WFI Standby signal register */ #define PRCM_ARM_WFI_STANDBY (prcmu_base + 0x130) @@ -203,7 +202,4 @@ void __init ux500_pm_init(u32 phy_base, u32 size) /* Set up ux500 suspend callbacks. */ suspend_set_ops(UX500_SUSPEND_OPS); - - /* Initialize ux500 power domains */ - ux500_pm_domains_init(); } diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c index 3b8e728cc944..91537d90f5f5 100644 --- a/arch/arm/mm/nommu.c +++ b/arch/arm/mm/nommu.c @@ -344,6 +344,11 @@ void __init arm_mm_memblock_reserve(void) * reserved here. */ #endif + /* + * In any case, always ensure address 0 is never used as many things + * get very confused if 0 is returned as a legitimate address. + */ + memblock_reserve(0, 1); } void __init adjust_lowmem_bounds(void) diff --git a/arch/arm/xen/p2m.c b/arch/arm/xen/p2m.c index e71eefa2e427..0641ba54ab62 100644 --- a/arch/arm/xen/p2m.c +++ b/arch/arm/xen/p2m.c @@ -1,7 +1,7 @@ #include <linux/bootmem.h> #include <linux/gfp.h> #include <linux/export.h> -#include <linux/rwlock.h> +#include <linux/spinlock.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/dma-mapping.h> diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts index caf8b6fbe5e3..d06e34b5d192 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts @@ -61,13 +61,6 @@ chosen { stdout-path = "serial0:115200n8"; }; - - reg_vcc3v3: vcc3v3 { - compatible = "regulator-fixed"; - regulator-name = "vcc3v3"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - }; }; &ehci0 { @@ -91,7 +84,7 @@ &mmc0 { pinctrl-names = "default"; pinctrl-0 = <&mmc0_pins>; - vmmc-supply = <®_vcc3v3>; + vmmc-supply = <®_dcdc1>; cd-gpios = <&pio 5 6 GPIO_ACTIVE_HIGH>; cd-inverted; disable-wp; diff --git a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi index 8263a8a504a8..f2aa2a81de4d 100644 --- a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi @@ -336,7 +336,7 @@ /* non-prefetchable memory */ 0x82000000 0 0xf6000000 0 0xf6000000 0 0xf00000>; interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &cpm_icu 0 ICU_GRP_NSR 22 IRQ_TYPE_LEVEL_HIGH>; + interrupt-map = <0 0 0 0 &cpm_icu ICU_GRP_NSR 22 IRQ_TYPE_LEVEL_HIGH>; interrupts = <ICU_GRP_NSR 22 IRQ_TYPE_LEVEL_HIGH>; num-lanes = <1>; clocks = <&cpm_clk 1 13>; @@ -362,7 +362,7 @@ /* non-prefetchable memory */ 0x82000000 0 0xf7000000 0 0xf7000000 0 0xf00000>; interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &cpm_icu 0 ICU_GRP_NSR 24 IRQ_TYPE_LEVEL_HIGH>; + interrupt-map = <0 0 0 0 &cpm_icu ICU_GRP_NSR 24 IRQ_TYPE_LEVEL_HIGH>; interrupts = <ICU_GRP_NSR 24 IRQ_TYPE_LEVEL_HIGH>; num-lanes = <1>; @@ -389,7 +389,7 @@ /* non-prefetchable memory */ 0x82000000 0 0xf8000000 0 0xf8000000 0 0xf00000>; interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &cpm_icu 0 ICU_GRP_NSR 23 IRQ_TYPE_LEVEL_HIGH>; + interrupt-map = <0 0 0 0 &cpm_icu ICU_GRP_NSR 23 IRQ_TYPE_LEVEL_HIGH>; interrupts = <ICU_GRP_NSR 23 IRQ_TYPE_LEVEL_HIGH>; num-lanes = <1>; diff --git a/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi index b71ee6c83668..4fe70323abb3 100644 --- a/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi @@ -335,7 +335,7 @@ /* non-prefetchable memory */ 0x82000000 0 0xfa000000 0 0xfa000000 0 0xf00000>; interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &cps_icu 0 ICU_GRP_NSR 22 IRQ_TYPE_LEVEL_HIGH>; + interrupt-map = <0 0 0 0 &cps_icu ICU_GRP_NSR 22 IRQ_TYPE_LEVEL_HIGH>; interrupts = <ICU_GRP_NSR 22 IRQ_TYPE_LEVEL_HIGH>; num-lanes = <1>; clocks = <&cps_clk 1 13>; @@ -361,7 +361,7 @@ /* non-prefetchable memory */ 0x82000000 0 0xfb000000 0 0xfb000000 0 0xf00000>; interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &cps_icu 0 ICU_GRP_NSR 24 IRQ_TYPE_LEVEL_HIGH>; + interrupt-map = <0 0 0 0 &cps_icu ICU_GRP_NSR 24 IRQ_TYPE_LEVEL_HIGH>; interrupts = <ICU_GRP_NSR 24 IRQ_TYPE_LEVEL_HIGH>; num-lanes = <1>; @@ -388,7 +388,7 @@ /* non-prefetchable memory */ 0x82000000 0 0xfc000000 0 0xfc000000 0 0xf00000>; interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &cps_icu 0 ICU_GRP_NSR 23 IRQ_TYPE_LEVEL_HIGH>; + interrupt-map = <0 0 0 0 &cps_icu ICU_GRP_NSR 23 IRQ_TYPE_LEVEL_HIGH>; interrupts = <ICU_GRP_NSR 23 IRQ_TYPE_LEVEL_HIGH>; num-lanes = <1>; diff --git a/arch/arm64/boot/dts/renesas/salvator-common.dtsi b/arch/arm64/boot/dts/renesas/salvator-common.dtsi index 4786c67b5e65..d9d885006a8e 100644 --- a/arch/arm64/boot/dts/renesas/salvator-common.dtsi +++ b/arch/arm64/boot/dts/renesas/salvator-common.dtsi @@ -62,6 +62,7 @@ brightness-levels = <256 128 64 16 8 4 0>; default-brightness-level = <6>; + power-supply = <®_12v>; enable-gpios = <&gpio6 7 GPIO_ACTIVE_HIGH>; }; @@ -83,6 +84,15 @@ regulator-always-on; }; + reg_12v: regulator2 { + compatible = "regulator-fixed"; + regulator-name = "fixed-12V"; + regulator-min-microvolt = <12000000>; + regulator-max-microvolt = <12000000>; + regulator-boot-on; + regulator-always-on; + }; + rsnd_ak4613: sound { compatible = "simple-audio-card"; diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi index 6d615cb6e64d..41d61840fb99 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -582,7 +582,7 @@ vop_mmu: iommu@ff373f00 { compatible = "rockchip,iommu"; reg = <0x0 0xff373f00 0x0 0x100>; - interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH 0>; + interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "vop_mmu"; #iommu-cells = <0>; status = "disabled"; diff --git a/arch/arm64/boot/dts/rockchip/rk3368.dtsi b/arch/arm64/boot/dts/rockchip/rk3368.dtsi index 19fbaa5e7bdd..1070c8264c13 100644 --- a/arch/arm64/boot/dts/rockchip/rk3368.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3368.dtsi @@ -740,7 +740,7 @@ iep_mmu: iommu@ff900800 { compatible = "rockchip,iommu"; reg = <0x0 0xff900800 0x0 0x100>; - interrupts = <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH 0>; + interrupts = <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "iep_mmu"; #iommu-cells = <0>; status = "disabled"; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-firefly.dts b/arch/arm64/boot/dts/rockchip/rk3399-firefly.dts index 7fd4bfcaa38e..fef82274a39d 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-firefly.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-firefly.dts @@ -371,10 +371,10 @@ regulator-always-on; regulator-boot-on; regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <3300000>; + regulator-max-microvolt = <3000000>; regulator-state-mem { regulator-on-in-suspend; - regulator-suspend-microvolt = <3300000>; + regulator-suspend-microvolt = <3000000>; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi index 53ff3d191a1d..910628d18add 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi @@ -325,12 +325,12 @@ vcc_sd: LDO_REG4 { regulator-name = "vcc_sd"; regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <3300000>; + regulator-max-microvolt = <3000000>; regulator-always-on; regulator-boot-on; regulator-state-mem { regulator-on-in-suspend; - regulator-suspend-microvolt = <3300000>; + regulator-suspend-microvolt = <3000000>; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi index 6c30bb02210d..0f873c897d0d 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi @@ -315,10 +315,10 @@ regulator-always-on; regulator-boot-on; regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <3300000>; + regulator-max-microvolt = <3000000>; regulator-state-mem { regulator-on-in-suspend; - regulator-suspend-microvolt = <3300000>; + regulator-suspend-microvolt = <3000000>; }; }; diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h index 903f3bf48419..7e25c5cc353a 100644 --- a/arch/mips/include/asm/cmpxchg.h +++ b/arch/mips/include/asm/cmpxchg.h @@ -155,14 +155,16 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, return __cmpxchg_small(ptr, old, new, size); case 4: - return __cmpxchg_asm("ll", "sc", (volatile u32 *)ptr, old, new); + return __cmpxchg_asm("ll", "sc", (volatile u32 *)ptr, + (u32)old, new); case 8: /* lld/scd are only available for MIPS64 */ if (!IS_ENABLED(CONFIG_64BIT)) return __cmpxchg_called_with_bad_pointer(); - return __cmpxchg_asm("lld", "scd", (volatile u64 *)ptr, old, new); + return __cmpxchg_asm("lld", "scd", (volatile u64 *)ptr, + (u64)old, new); default: return __cmpxchg_called_with_bad_pointer(); diff --git a/arch/mips/loongson32/common/platform.c b/arch/mips/loongson32/common/platform.c index 100f23dfa438..ac584c5823d0 100644 --- a/arch/mips/loongson32/common/platform.c +++ b/arch/mips/loongson32/common/platform.c @@ -183,18 +183,20 @@ int ls1x_eth_mux_init(struct platform_device *pdev, void *priv) } static struct plat_stmmacenet_data ls1x_eth0_pdata = { - .bus_id = 0, - .phy_addr = -1, + .bus_id = 0, + .phy_addr = -1, #if defined(CONFIG_LOONGSON1_LS1B) - .interface = PHY_INTERFACE_MODE_MII, + .interface = PHY_INTERFACE_MODE_MII, #elif defined(CONFIG_LOONGSON1_LS1C) - .interface = PHY_INTERFACE_MODE_RMII, + .interface = PHY_INTERFACE_MODE_RMII, #endif - .mdio_bus_data = &ls1x_mdio_bus_data, - .dma_cfg = &ls1x_eth_dma_cfg, - .has_gmac = 1, - .tx_coe = 1, - .init = ls1x_eth_mux_init, + .mdio_bus_data = &ls1x_mdio_bus_data, + .dma_cfg = &ls1x_eth_dma_cfg, + .has_gmac = 1, + .tx_coe = 1, + .rx_queues_to_use = 1, + .tx_queues_to_use = 1, + .init = ls1x_eth_mux_init, }; static struct resource ls1x_eth0_resources[] = { @@ -222,14 +224,16 @@ struct platform_device ls1x_eth0_pdev = { #ifdef CONFIG_LOONGSON1_LS1B static struct plat_stmmacenet_data ls1x_eth1_pdata = { - .bus_id = 1, - .phy_addr = -1, - .interface = PHY_INTERFACE_MODE_MII, - .mdio_bus_data = &ls1x_mdio_bus_data, - .dma_cfg = &ls1x_eth_dma_cfg, - .has_gmac = 1, - .tx_coe = 1, - .init = ls1x_eth_mux_init, + .bus_id = 1, + .phy_addr = -1, + .interface = PHY_INTERFACE_MODE_MII, + .mdio_bus_data = &ls1x_mdio_bus_data, + .dma_cfg = &ls1x_eth_dma_cfg, + .has_gmac = 1, + .tx_coe = 1, + .rx_queues_to_use = 1, + .tx_queues_to_use = 1, + .init = ls1x_eth_mux_init, }; static struct resource ls1x_eth1_resources[] = { diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c index 192542dbd972..16d9ef5a78c5 100644 --- a/arch/mips/math-emu/cp1emu.c +++ b/arch/mips/math-emu/cp1emu.c @@ -2558,7 +2558,6 @@ dcopuop: break; default: /* Reserved R6 ops */ - pr_err("Reserved MIPS R6 CMP.condn.S operation\n"); return SIGILL; } } @@ -2719,7 +2718,6 @@ dcopuop: break; default: /* Reserved R6 ops */ - pr_err("Reserved MIPS R6 CMP.condn.D operation\n"); return SIGILL; } } diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c index 7646891c4e9b..01b7a87ea678 100644 --- a/arch/mips/net/ebpf_jit.c +++ b/arch/mips/net/ebpf_jit.c @@ -667,7 +667,7 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, { int src, dst, r, td, ts, mem_off, b_off; bool need_swap, did_move, cmp_eq; - unsigned int target; + unsigned int target = 0; u64 t64; s64 t64s; int bpf_op = BPF_OP(insn->code); diff --git a/arch/mips/tools/generic-board-config.sh b/arch/mips/tools/generic-board-config.sh index 5c4f93687039..654d652d7fa1 100755 --- a/arch/mips/tools/generic-board-config.sh +++ b/arch/mips/tools/generic-board-config.sh @@ -30,8 +30,6 @@ cfg="$4" boards_origin="$5" shift 5 -cd "${srctree}" - # Only print Skipping... lines if the user explicitly specified BOARDS=. In the # general case it only serves to obscure the useful output about what actually # was included. @@ -48,7 +46,7 @@ environment*) esac for board in $@; do - board_cfg="arch/mips/configs/generic/board-${board}.config" + board_cfg="${srctree}/arch/mips/configs/generic/board-${board}.config" if [ ! -f "${board_cfg}" ]; then echo "WARNING: Board config '${board_cfg}' not found" continue @@ -84,7 +82,7 @@ for board in $@; do done || continue # Merge this board config fragment into our final config file - ./scripts/kconfig/merge_config.sh \ + ${srctree}/scripts/kconfig/merge_config.sh \ -m -O ${objtree} ${cfg} ${board_cfg} \ | grep -Ev '^(#|Using)' done diff --git a/arch/parisc/kernel/parisc_ksyms.c b/arch/parisc/kernel/parisc_ksyms.c index c6d6272a934f..7baa2265d439 100644 --- a/arch/parisc/kernel/parisc_ksyms.c +++ b/arch/parisc/kernel/parisc_ksyms.c @@ -35,12 +35,12 @@ EXPORT_SYMBOL(memset); EXPORT_SYMBOL(__xchg8); EXPORT_SYMBOL(__xchg32); EXPORT_SYMBOL(__cmpxchg_u32); +EXPORT_SYMBOL(__cmpxchg_u64); #ifdef CONFIG_SMP EXPORT_SYMBOL(__atomic_hash); #endif #ifdef CONFIG_64BIT EXPORT_SYMBOL(__xchg64); -EXPORT_SYMBOL(__cmpxchg_u64); #endif #include <linux/uaccess.h> diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index 23de307c3052..41e60a9c7db2 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -742,7 +742,7 @@ lws_compare_and_swap_2: 10: ldd 0(%r25), %r25 11: ldd 0(%r24), %r24 #else - /* Load new value into r22/r23 - high/low */ + /* Load old value into r22/r23 - high/low */ 10: ldw 0(%r25), %r22 11: ldw 4(%r25), %r23 /* Load new value into fr4 for atomic store later */ @@ -834,11 +834,11 @@ cas2_action: copy %r0, %r28 #else /* Compare first word */ -19: ldw,ma 0(%r26), %r29 +19: ldw 0(%r26), %r29 sub,= %r29, %r22, %r0 b,n cas2_end /* Compare second word */ -20: ldw,ma 4(%r26), %r29 +20: ldw 4(%r26), %r29 sub,= %r29, %r23, %r0 b,n cas2_end /* Perform the store */ diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c index 2d956aa0a38a..8c0105a49839 100644 --- a/arch/parisc/kernel/time.c +++ b/arch/parisc/kernel/time.c @@ -253,7 +253,10 @@ static int __init init_cr16_clocksource(void) cpu0_loc = per_cpu(cpu_data, 0).cpu_loc; for_each_online_cpu(cpu) { - if (cpu0_loc == per_cpu(cpu_data, cpu).cpu_loc) + if (cpu == 0) + continue; + if ((cpu0_loc != 0) && + (cpu0_loc == per_cpu(cpu_data, cpu).cpu_loc)) continue; clocksource_cr16.name = "cr16_unstable"; diff --git a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S index c98e90b4ea7b..b4e2b7165f79 100644 --- a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S +++ b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S @@ -181,34 +181,25 @@ _GLOBAL(ftrace_stub) * - we have no stack frame and can not allocate one * - LR points back to the original caller (in A) * - CTR holds the new NIP in C - * - r0 & r12 are free - * - * r0 can't be used as the base register for a DS-form load or store, so - * we temporarily shuffle r1 (stack pointer) into r0 and then put it back. + * - r0, r11 & r12 are free */ livepatch_handler: CURRENT_THREAD_INFO(r12, r1) - /* Save stack pointer into r0 */ - mr r0, r1 - /* Allocate 3 x 8 bytes */ - ld r1, TI_livepatch_sp(r12) - addi r1, r1, 24 - std r1, TI_livepatch_sp(r12) + ld r11, TI_livepatch_sp(r12) + addi r11, r11, 24 + std r11, TI_livepatch_sp(r12) /* Save toc & real LR on livepatch stack */ - std r2, -24(r1) + std r2, -24(r11) mflr r12 - std r12, -16(r1) + std r12, -16(r11) /* Store stack end marker */ lis r12, STACK_END_MAGIC@h ori r12, r12, STACK_END_MAGIC@l - std r12, -8(r1) - - /* Restore real stack pointer */ - mr r1, r0 + std r12, -8(r11) /* Put ctr in r12 for global entry and branch there */ mfctr r12 @@ -216,36 +207,30 @@ livepatch_handler: /* * Now we are returning from the patched function to the original - * caller A. We are free to use r0 and r12, and we can use r2 until we + * caller A. We are free to use r11, r12 and we can use r2 until we * restore it. */ CURRENT_THREAD_INFO(r12, r1) - /* Save stack pointer into r0 */ - mr r0, r1 - - ld r1, TI_livepatch_sp(r12) + ld r11, TI_livepatch_sp(r12) /* Check stack marker hasn't been trashed */ lis r2, STACK_END_MAGIC@h ori r2, r2, STACK_END_MAGIC@l - ld r12, -8(r1) + ld r12, -8(r11) 1: tdne r12, r2 EMIT_BUG_ENTRY 1b, __FILE__, __LINE__ - 1, 0 /* Restore LR & toc from livepatch stack */ - ld r12, -16(r1) + ld r12, -16(r11) mtlr r12 - ld r2, -24(r1) + ld r2, -24(r11) /* Pop livepatch stack frame */ - CURRENT_THREAD_INFO(r12, r0) - subi r1, r1, 24 - std r1, TI_livepatch_sp(r12) - - /* Restore real stack pointer */ - mr r1, r0 + CURRENT_THREAD_INFO(r12, r1) + subi r11, r11, 24 + std r11, TI_livepatch_sp(r12) /* Return to original caller of live patched function */ blr diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index 8f2da8bba737..4dffa611376d 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -478,28 +478,30 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, return ret; dir = iommu_tce_direction(tce); + + idx = srcu_read_lock(&vcpu->kvm->srcu); + if ((dir != DMA_NONE) && kvmppc_gpa_to_ua(vcpu->kvm, - tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), &ua, NULL)) - return H_PARAMETER; + tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), &ua, NULL)) { + ret = H_PARAMETER; + goto unlock_exit; + } entry = ioba >> stt->page_shift; list_for_each_entry_lockless(stit, &stt->iommu_tables, next) { - if (dir == DMA_NONE) { + if (dir == DMA_NONE) ret = kvmppc_tce_iommu_unmap(vcpu->kvm, stit->tbl, entry); - } else { - idx = srcu_read_lock(&vcpu->kvm->srcu); + else ret = kvmppc_tce_iommu_map(vcpu->kvm, stit->tbl, entry, ua, dir); - srcu_read_unlock(&vcpu->kvm->srcu, idx); - } if (ret == H_SUCCESS) continue; if (ret == H_TOO_HARD) - return ret; + goto unlock_exit; WARN_ON_ONCE(1); kvmppc_clear_tce(stit->tbl, entry); @@ -507,7 +509,10 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, kvmppc_tce_put(stt, entry, tce); - return H_SUCCESS; +unlock_exit: + srcu_read_unlock(&vcpu->kvm->srcu, idx); + + return ret; } EXPORT_SYMBOL_GPL(kvmppc_h_put_tce); diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index ec69fa45d5a2..42639fba89e8 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -989,13 +989,14 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300) beq no_xive ld r11, VCPU_XIVE_SAVED_STATE(r4) li r9, TM_QW1_OS - stdcix r11,r9,r10 eieio + stdcix r11,r9,r10 lwz r11, VCPU_XIVE_CAM_WORD(r4) li r9, TM_QW1_OS + TM_WORD2 stwcix r11,r9,r10 li r9, 1 stw r9, VCPU_XIVE_PUSHED(r4) + eieio no_xive: #endif /* CONFIG_KVM_XICS */ @@ -1310,6 +1311,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) bne 3f BEGIN_FTR_SECTION PPC_MSGSYNC + lwsync END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) lbz r0, HSTATE_HOST_IPI(r13) cmpwi r0, 0 @@ -1400,8 +1402,8 @@ guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */ cmpldi cr0, r10, 0 beq 1f /* First load to pull the context, we ignore the value */ - lwzx r11, r7, r10 eieio + lwzx r11, r7, r10 /* Second load to recover the context state (Words 0 and 1) */ ldx r11, r6, r10 b 3f @@ -1409,8 +1411,8 @@ guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */ cmpldi cr0, r10, 0 beq 1f /* First load to pull the context, we ignore the value */ - lwzcix r11, r7, r10 eieio + lwzcix r11, r7, r10 /* Second load to recover the context state (Words 0 and 1) */ ldcix r11, r6, r10 3: std r11, VCPU_XIVE_SAVED_STATE(r9) @@ -1420,6 +1422,7 @@ guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */ stw r10, VCPU_XIVE_PUSHED(r9) stb r10, (VCPU_XIVE_SAVED_STATE+3)(r9) stb r0, (VCPU_XIVE_SAVED_STATE+4)(r9) + eieio 1: #endif /* CONFIG_KVM_XICS */ /* Save more register state */ @@ -2788,6 +2791,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) PPC_MSGCLR(6) /* see if it's a host IPI */ li r3, 1 +BEGIN_FTR_SECTION + PPC_MSGSYNC + lwsync +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) lbz r0, HSTATE_HOST_IPI(r13) cmpwi r0, 0 bnelr diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 3480faaf1ef8..ee279c7f4802 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -644,8 +644,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) break; #endif case KVM_CAP_PPC_HTM: - r = cpu_has_feature(CPU_FTR_TM_COMP) && - is_kvmppc_hv_enabled(kvm); + r = cpu_has_feature(CPU_FTR_TM_COMP) && hv_enabled; break; default: r = 0; diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c index 5e8418c28bd8..f208f560aecd 100644 --- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -1684,11 +1684,13 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, * Logical instructions */ case 26: /* cntlzw */ - op->val = __builtin_clz((unsigned int) regs->gpr[rd]); + val = (unsigned int) regs->gpr[rd]; + op->val = ( val ? __builtin_clz(val) : 32 ); goto logical_done; #ifdef __powerpc64__ case 58: /* cntlzd */ - op->val = __builtin_clzl(regs->gpr[rd]); + val = regs->gpr[rd]; + op->val = ( val ? __builtin_clzl(val) : 64 ); goto logical_done; #endif case 28: /* and */ diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index b95c584ce19d..a51df9ef529d 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1438,7 +1438,6 @@ out: int arch_update_cpu_topology(void) { - lockdep_assert_cpus_held(); return numa_update_cpu_topology(true); } diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index 9ccac86f3463..88126245881b 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -399,6 +399,20 @@ static void nest_imc_counters_release(struct perf_event *event) /* Take the mutex lock for this node and then decrement the reference count */ mutex_lock(&ref->lock); + if (ref->refc == 0) { + /* + * The scenario where this is true is, when perf session is + * started, followed by offlining of all cpus in a given node. + * + * In the cpuhotplug offline path, ppc_nest_imc_cpu_offline() + * function set the ref->count to zero, if the cpu which is + * about to offline is the last cpu in a given node and make + * an OPAL call to disable the engine in that node. + * + */ + mutex_unlock(&ref->lock); + return; + } ref->refc--; if (ref->refc == 0) { rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_NEST, @@ -523,8 +537,8 @@ static int core_imc_mem_init(int cpu, int size) /* We need only vbase for core counters */ mem_info->vbase = page_address(alloc_pages_node(phys_id, - GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE, - get_order(size))); + GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE | + __GFP_NOWARN, get_order(size))); if (!mem_info->vbase) return -ENOMEM; @@ -646,6 +660,20 @@ static void core_imc_counters_release(struct perf_event *event) return; mutex_lock(&ref->lock); + if (ref->refc == 0) { + /* + * The scenario where this is true is, when perf session is + * started, followed by offlining of all cpus in a given core. + * + * In the cpuhotplug offline path, ppc_core_imc_cpu_offline() + * function set the ref->count to zero, if the cpu which is + * about to offline is the last cpu in a given core and make + * an OPAL call to disable the engine in that core. + * + */ + mutex_unlock(&ref->lock); + return; + } ref->refc--; if (ref->refc == 0) { rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE, @@ -763,8 +791,8 @@ static int thread_imc_mem_alloc(int cpu_id, int size) * free the memory in cpu offline path. */ local_mem = page_address(alloc_pages_node(phys_id, - GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE, - get_order(size))); + GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE | + __GFP_NOWARN, get_order(size))); if (!local_mem) return -ENOMEM; @@ -1148,7 +1176,8 @@ static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr) } /* Only free the attr_groups which are dynamically allocated */ - kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]->attrs); + if (pmu_ptr->attr_groups[IMC_EVENT_ATTR]) + kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]->attrs); kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]); kfree(pmu_ptr); return; diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index afa46a7406ea..04e042edbab7 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -27,6 +27,7 @@ CONFIG_NET=y CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y # CONFIG_FIRMWARE_IN_KERNEL is not set +CONFIG_BLK_DEV_RAM=y # CONFIG_BLK_DEV_XPRAM is not set # CONFIG_DCSSBLK is not set # CONFIG_DASD is not set @@ -59,6 +60,7 @@ CONFIG_CONFIGFS_FS=y # CONFIG_NETWORK_FILESYSTEMS is not set CONFIG_PRINTK_TIME=y CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_FS=y CONFIG_DEBUG_KERNEL=y CONFIG_PANIC_ON_OOPS=y # CONFIG_SCHED_DEBUG is not set diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 21900e1cee9c..d185aa3965bf 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -521,12 +521,15 @@ ENTRY(pgm_check_handler) tmhh %r8,0x0001 # test problem state bit jnz 2f # -> fault in user space #if IS_ENABLED(CONFIG_KVM) - # cleanup critical section for sie64a + # cleanup critical section for program checks in sie64a lgr %r14,%r9 slg %r14,BASED(.Lsie_critical_start) clg %r14,BASED(.Lsie_critical_length) jhe 0f - brasl %r14,.Lcleanup_sie + lg %r14,__SF_EMPTY(%r15) # get control block pointer + ni __SIE_PROG0C+3(%r14),0xfe # no longer in SIE + lctlg %c1,%c1,__LC_USER_ASCE # load primary asce + larl %r9,sie_exit # skip forward to sie_exit #endif 0: tmhh %r8,0x4000 # PER bit set in old PSW ? jnz 1f # -> enabled, can't be a double fault diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 1cee6753d47a..495ff6959dec 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -293,7 +293,10 @@ static void pcpu_attach_task(struct pcpu *pcpu, struct task_struct *tsk) lc->lpp = LPP_MAGIC; lc->current_pid = tsk->pid; lc->user_timer = tsk->thread.user_timer; + lc->guest_timer = tsk->thread.guest_timer; lc->system_timer = tsk->thread.system_timer; + lc->hardirq_timer = tsk->thread.hardirq_timer; + lc->softirq_timer = tsk->thread.softirq_timer; lc->steal_timer = 0; } diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 971feac13506..6b94ca0aa585 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -170,7 +170,7 @@ config X86 select HAVE_PERF_USER_STACK_DUMP select HAVE_RCU_TABLE_FREE select HAVE_REGS_AND_STACK_ACCESS_API - select HAVE_RELIABLE_STACKTRACE if X86_64 && FRAME_POINTER_UNWINDER && STACK_VALIDATION + select HAVE_RELIABLE_STACKTRACE if X86_64 && UNWINDER_FRAME_POINTER && STACK_VALIDATION select HAVE_STACK_VALIDATION if X86_64 select HAVE_SYSCALL_TRACEPOINTS select HAVE_UNSTABLE_SCHED_CLOCK diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 71a48a30fc84..a4ff214fb760 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -358,28 +358,14 @@ config PUNIT_ATOM_DEBUG choice prompt "Choose kernel unwinder" - default FRAME_POINTER_UNWINDER + default UNWINDER_ORC if X86_64 + default UNWINDER_FRAME_POINTER if X86_32 ---help--- This determines which method will be used for unwinding kernel stack traces for panics, oopses, bugs, warnings, perf, /proc/<pid>/stack, livepatch, lockdep, and more. -config FRAME_POINTER_UNWINDER - bool "Frame pointer unwinder" - select FRAME_POINTER - ---help--- - This option enables the frame pointer unwinder for unwinding kernel - stack traces. - - The unwinder itself is fast and it uses less RAM than the ORC - unwinder, but the kernel text size will grow by ~3% and the kernel's - overall performance will degrade by roughly 5-10%. - - This option is recommended if you want to use the livepatch - consistency model, as this is currently the only way to get a - reliable stack trace (CONFIG_HAVE_RELIABLE_STACKTRACE). - -config ORC_UNWINDER +config UNWINDER_ORC bool "ORC unwinder" depends on X86_64 select STACK_VALIDATION @@ -395,7 +381,22 @@ config ORC_UNWINDER Enabling this option will increase the kernel's runtime memory usage by roughly 2-4MB, depending on your kernel config. -config GUESS_UNWINDER +config UNWINDER_FRAME_POINTER + bool "Frame pointer unwinder" + select FRAME_POINTER + ---help--- + This option enables the frame pointer unwinder for unwinding kernel + stack traces. + + The unwinder itself is fast and it uses less RAM than the ORC + unwinder, but the kernel text size will grow by ~3% and the kernel's + overall performance will degrade by roughly 5-10%. + + This option is recommended if you want to use the livepatch + consistency model, as this is currently the only way to get a + reliable stack trace (CONFIG_HAVE_RELIABLE_STACKTRACE). + +config UNWINDER_GUESS bool "Guess unwinder" depends on EXPERT ---help--- @@ -410,7 +411,7 @@ config GUESS_UNWINDER endchoice config FRAME_POINTER - depends on !ORC_UNWINDER && !GUESS_UNWINDER + depends on !UNWINDER_ORC && !UNWINDER_GUESS bool endmenu diff --git a/arch/x86/configs/tiny.config b/arch/x86/configs/tiny.config index 550cd5012b73..66c9e2aab16c 100644 --- a/arch/x86/configs/tiny.config +++ b/arch/x86/configs/tiny.config @@ -1,5 +1,5 @@ CONFIG_NOHIGHMEM=y # CONFIG_HIGHMEM4G is not set # CONFIG_HIGHMEM64G is not set -CONFIG_GUESS_UNWINDER=y -# CONFIG_FRAME_POINTER_UNWINDER is not set +CONFIG_UNWINDER_GUESS=y +# CONFIG_UNWINDER_FRAME_POINTER is not set diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index 4a4b16e56d35..e32fc1f274d8 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -299,6 +299,7 @@ CONFIG_DEBUG_STACKOVERFLOW=y # CONFIG_DEBUG_RODATA_TEST is not set CONFIG_DEBUG_BOOT_PARAMS=y CONFIG_OPTIMIZE_INLINING=y +CONFIG_UNWINDER_ORC=y CONFIG_SECURITY=y CONFIG_SECURITY_NETWORK=y CONFIG_SECURITY_SELINUX=y diff --git a/arch/x86/crypto/chacha20-avx2-x86_64.S b/arch/x86/crypto/chacha20-avx2-x86_64.S index 3a2dc3dc6cac..f3cd26f48332 100644 --- a/arch/x86/crypto/chacha20-avx2-x86_64.S +++ b/arch/x86/crypto/chacha20-avx2-x86_64.S @@ -45,7 +45,7 @@ ENTRY(chacha20_8block_xor_avx2) vzeroupper # 4 * 32 byte stack, 32-byte aligned - mov %rsp, %r8 + lea 8(%rsp),%r10 and $~31, %rsp sub $0x80, %rsp @@ -443,6 +443,6 @@ ENTRY(chacha20_8block_xor_avx2) vmovdqu %ymm15,0x01e0(%rsi) vzeroupper - mov %r8,%rsp + lea -8(%r10),%rsp ret ENDPROC(chacha20_8block_xor_avx2) diff --git a/arch/x86/crypto/chacha20-ssse3-x86_64.S b/arch/x86/crypto/chacha20-ssse3-x86_64.S index 3f511a7d73b8..512a2b500fd1 100644 --- a/arch/x86/crypto/chacha20-ssse3-x86_64.S +++ b/arch/x86/crypto/chacha20-ssse3-x86_64.S @@ -160,7 +160,7 @@ ENTRY(chacha20_4block_xor_ssse3) # done with the slightly better performing SSSE3 byte shuffling, # 7/12-bit word rotation uses traditional shift+OR. - mov %rsp,%r11 + lea 8(%rsp),%r10 sub $0x80,%rsp and $~63,%rsp @@ -625,6 +625,6 @@ ENTRY(chacha20_4block_xor_ssse3) pxor %xmm1,%xmm15 movdqu %xmm15,0xf0(%rsi) - mov %r11,%rsp + lea -8(%r10),%rsp ret ENDPROC(chacha20_4block_xor_ssse3) diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 8a13d468635a..50e0d2bc4528 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -176,7 +176,7 @@ /* * This is a sneaky trick to help the unwinder find pt_regs on the stack. The * frame pointer is replaced with an encoded pointer to pt_regs. The encoding - * is just setting the LSB, which makes it an invalid stack address and is also + * is just clearing the MSB, which makes it an invalid stack address and is also * a signal to the unwinder that it's a pt_regs pointer in disguise. * * NOTE: This macro must be used *after* SAVE_ALL because it corrupts the @@ -185,7 +185,7 @@ .macro ENCODE_FRAME_POINTER #ifdef CONFIG_FRAME_POINTER mov %esp, %ebp - orl $0x1, %ebp + andl $0x7fffffff, %ebp #endif .endm diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 49167258d587..846e84a1d1f7 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -808,7 +808,7 @@ apicinterrupt IRQ_WORK_VECTOR irq_work_interrupt smp_irq_work_interrupt .macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ENTRY(\sym) - UNWIND_HINT_IRET_REGS offset=8 + UNWIND_HINT_IRET_REGS offset=\has_error_code*8 /* Sanity check */ .if \shift_ist != -1 && \paranoid == 0 @@ -817,7 +817,7 @@ ENTRY(\sym) ASM_CLAC - .ifeq \has_error_code + .if \has_error_code == 0 pushq $-1 /* ORIG_RAX: no syscall to restart */ .endif diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c index 16076eb34699..141e07b06216 100644 --- a/arch/x86/events/intel/bts.c +++ b/arch/x86/events/intel/bts.c @@ -546,9 +546,6 @@ static int bts_event_init(struct perf_event *event) if (event->attr.type != bts_pmu.type) return -ENOENT; - if (x86_add_exclusive(x86_lbr_exclusive_bts)) - return -EBUSY; - /* * BTS leaks kernel addresses even when CPL0 tracing is * disabled, so disallow intel_bts driver for unprivileged @@ -562,6 +559,9 @@ static int bts_event_init(struct perf_event *event) !capable(CAP_SYS_ADMIN)) return -EACCES; + if (x86_add_exclusive(x86_lbr_exclusive_bts)) + return -EBUSY; + ret = x86_reserve_hardware(); if (ret) { x86_del_exclusive(x86_lbr_exclusive_bts); diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 1c5390f1cf09..d45e06346f14 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -822,7 +822,7 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid) pmus[i].type = type; pmus[i].boxes = kzalloc(size, GFP_KERNEL); if (!pmus[i].boxes) - return -ENOMEM; + goto err; } type->pmus = pmus; @@ -836,7 +836,7 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid) attr_group = kzalloc(sizeof(struct attribute *) * (i + 1) + sizeof(*attr_group), GFP_KERNEL); if (!attr_group) - return -ENOMEM; + goto err; attrs = (struct attribute **)(attr_group + 1); attr_group->name = "events"; @@ -849,7 +849,15 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid) } type->pmu_group = &uncore_pmu_attr_group; + return 0; + +err: + for (i = 0; i < type->num_boxes; i++) + kfree(pmus[i].boxes); + kfree(pmus); + + return -ENOMEM; } static int __init diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 1a8eb550c40f..a5db63f728a2 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -85,6 +85,8 @@ EXPORT_SYMBOL_GPL(hyperv_cs); u32 *hv_vp_index; EXPORT_SYMBOL_GPL(hv_vp_index); +u32 hv_max_vp_index; + static int hv_cpu_init(unsigned int cpu) { u64 msr_vp_index; @@ -93,6 +95,9 @@ static int hv_cpu_init(unsigned int cpu) hv_vp_index[smp_processor_id()] = msr_vp_index; + if (msr_vp_index > hv_max_vp_index) + hv_max_vp_index = msr_vp_index; + return 0; } diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c index 39e7f6e50919..9cc9e1c1e2db 100644 --- a/arch/x86/hyperv/mmu.c +++ b/arch/x86/hyperv/mmu.c @@ -36,9 +36,9 @@ struct hv_flush_pcpu_ex { /* Each gva in gva_list encodes up to 4096 pages to flush */ #define HV_TLB_FLUSH_UNIT (4096 * PAGE_SIZE) -static struct hv_flush_pcpu __percpu *pcpu_flush; +static struct hv_flush_pcpu __percpu **pcpu_flush; -static struct hv_flush_pcpu_ex __percpu *pcpu_flush_ex; +static struct hv_flush_pcpu_ex __percpu **pcpu_flush_ex; /* * Fills in gva_list starting from offset. Returns the number of items added. @@ -76,6 +76,18 @@ static inline int cpumask_to_vp_set(struct hv_flush_pcpu_ex *flush, { int cpu, vcpu, vcpu_bank, vcpu_offset, nr_bank = 1; + /* valid_bank_mask can represent up to 64 banks */ + if (hv_max_vp_index / 64 >= 64) + return 0; + + /* + * Clear all banks up to the maximum possible bank as hv_flush_pcpu_ex + * structs are not cleared between calls, we risk flushing unneeded + * vCPUs otherwise. + */ + for (vcpu_bank = 0; vcpu_bank <= hv_max_vp_index / 64; vcpu_bank++) + flush->hv_vp_set.bank_contents[vcpu_bank] = 0; + /* * Some banks may end up being empty but this is acceptable. */ @@ -83,11 +95,6 @@ static inline int cpumask_to_vp_set(struct hv_flush_pcpu_ex *flush, vcpu = hv_cpu_number_to_vp_number(cpu); vcpu_bank = vcpu / 64; vcpu_offset = vcpu % 64; - - /* valid_bank_mask can represent up to 64 banks */ - if (vcpu_bank >= 64) - return 0; - __set_bit(vcpu_offset, (unsigned long *) &flush->hv_vp_set.bank_contents[vcpu_bank]); if (vcpu_bank >= nr_bank) @@ -102,6 +109,7 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus, const struct flush_tlb_info *info) { int cpu, vcpu, gva_n, max_gvas; + struct hv_flush_pcpu **flush_pcpu; struct hv_flush_pcpu *flush; u64 status = U64_MAX; unsigned long flags; @@ -116,7 +124,17 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus, local_irq_save(flags); - flush = this_cpu_ptr(pcpu_flush); + flush_pcpu = this_cpu_ptr(pcpu_flush); + + if (unlikely(!*flush_pcpu)) + *flush_pcpu = page_address(alloc_page(GFP_ATOMIC)); + + flush = *flush_pcpu; + + if (unlikely(!flush)) { + local_irq_restore(flags); + goto do_native; + } if (info->mm) { flush->address_space = virt_to_phys(info->mm->pgd); @@ -173,6 +191,7 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus, const struct flush_tlb_info *info) { int nr_bank = 0, max_gvas, gva_n; + struct hv_flush_pcpu_ex **flush_pcpu; struct hv_flush_pcpu_ex *flush; u64 status = U64_MAX; unsigned long flags; @@ -187,7 +206,17 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus, local_irq_save(flags); - flush = this_cpu_ptr(pcpu_flush_ex); + flush_pcpu = this_cpu_ptr(pcpu_flush_ex); + + if (unlikely(!*flush_pcpu)) + *flush_pcpu = page_address(alloc_page(GFP_ATOMIC)); + + flush = *flush_pcpu; + + if (unlikely(!flush)) { + local_irq_restore(flags); + goto do_native; + } if (info->mm) { flush->address_space = virt_to_phys(info->mm->pgd); @@ -222,18 +251,18 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus, flush->flags |= HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY; status = hv_do_rep_hypercall( HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX, - 0, nr_bank + 2, flush, NULL); + 0, nr_bank, flush, NULL); } else if (info->end && ((info->end - info->start)/HV_TLB_FLUSH_UNIT) > max_gvas) { status = hv_do_rep_hypercall( HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX, - 0, nr_bank + 2, flush, NULL); + 0, nr_bank, flush, NULL); } else { gva_n = fill_gva_list(flush->gva_list, nr_bank, info->start, info->end); status = hv_do_rep_hypercall( HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX, - gva_n, nr_bank + 2, flush, NULL); + gva_n, nr_bank, flush, NULL); } local_irq_restore(flags); @@ -266,7 +295,7 @@ void hyper_alloc_mmu(void) return; if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) - pcpu_flush = __alloc_percpu(PAGE_SIZE, PAGE_SIZE); + pcpu_flush = alloc_percpu(struct hv_flush_pcpu *); else - pcpu_flush_ex = __alloc_percpu(PAGE_SIZE, PAGE_SIZE); + pcpu_flush_ex = alloc_percpu(struct hv_flush_pcpu_ex *); } diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h index e7636bac7372..6c98821fef5e 100644 --- a/arch/x86/include/asm/alternative-asm.h +++ b/arch/x86/include/asm/alternative-asm.h @@ -62,8 +62,10 @@ #define new_len2 145f-144f /* - * max without conditionals. Idea adapted from: + * gas compatible max based on the idea from: * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax + * + * The additional "-" is needed because gas uses a "true" value of -1. */ #define alt_max_short(a, b) ((a) ^ (((a) ^ (b)) & -(-((a) < (b))))) diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index c096624137ae..ccbe24e697c4 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -103,12 +103,12 @@ static inline int alternatives_text_reserved(void *start, void *end) alt_end_marker ":\n" /* - * max without conditionals. Idea adapted from: + * gas compatible max based on the idea from: * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax * - * The additional "-" is needed because gas works with s32s. + * The additional "-" is needed because gas uses a "true" value of -1. */ -#define alt_max_short(a, b) "((" a ") ^ (((" a ") ^ (" b ")) & -(-((" a ") - (" b ")))))" +#define alt_max_short(a, b) "((" a ") ^ (((" a ") ^ (" b ")) & -(-((" a ") < (" b ")))))" /* * Pad the second replacement alternative with additional NOPs if it is diff --git a/arch/x86/include/asm/archrandom.h b/arch/x86/include/asm/archrandom.h index 5b0579abb398..3ac991d81e74 100644 --- a/arch/x86/include/asm/archrandom.h +++ b/arch/x86/include/asm/archrandom.h @@ -45,7 +45,7 @@ static inline bool rdrand_long(unsigned long *v) bool ok; unsigned int retry = RDRAND_RETRY_LOOPS; do { - asm volatile(RDRAND_LONG "\n\t" + asm volatile(RDRAND_LONG CC_SET(c) : CC_OUT(c) (ok), "=a" (*v)); if (ok) @@ -59,7 +59,7 @@ static inline bool rdrand_int(unsigned int *v) bool ok; unsigned int retry = RDRAND_RETRY_LOOPS; do { - asm volatile(RDRAND_INT "\n\t" + asm volatile(RDRAND_INT CC_SET(c) : CC_OUT(c) (ok), "=a" (*v)); if (ok) @@ -71,7 +71,7 @@ static inline bool rdrand_int(unsigned int *v) static inline bool rdseed_long(unsigned long *v) { bool ok; - asm volatile(RDSEED_LONG "\n\t" + asm volatile(RDSEED_LONG CC_SET(c) : CC_OUT(c) (ok), "=a" (*v)); return ok; @@ -80,7 +80,7 @@ static inline bool rdseed_long(unsigned long *v) static inline bool rdseed_int(unsigned int *v) { bool ok; - asm volatile(RDSEED_INT "\n\t" + asm volatile(RDSEED_INT CC_SET(c) : CC_OUT(c) (ok), "=a" (*v)); return ok; diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 854022772c5b..8cee8db6dffb 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -142,7 +142,7 @@ static __always_inline void __clear_bit(long nr, volatile unsigned long *addr) static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr) { bool negative; - asm volatile(LOCK_PREFIX "andb %2,%1\n\t" + asm volatile(LOCK_PREFIX "andb %2,%1" CC_SET(s) : CC_OUT(s) (negative), ADDR : "ir" ((char) ~(1 << nr)) : "memory"); @@ -245,7 +245,7 @@ static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long * { bool oldbit; - asm("bts %2,%1\n\t" + asm("bts %2,%1" CC_SET(c) : CC_OUT(c) (oldbit), ADDR : "Ir" (nr)); @@ -285,7 +285,7 @@ static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long { bool oldbit; - asm volatile("btr %2,%1\n\t" + asm volatile("btr %2,%1" CC_SET(c) : CC_OUT(c) (oldbit), ADDR : "Ir" (nr)); @@ -297,7 +297,7 @@ static __always_inline bool __test_and_change_bit(long nr, volatile unsigned lon { bool oldbit; - asm volatile("btc %2,%1\n\t" + asm volatile("btc %2,%1" CC_SET(c) : CC_OUT(c) (oldbit), ADDR : "Ir" (nr) : "memory"); @@ -328,7 +328,7 @@ static __always_inline bool variable_test_bit(long nr, volatile const unsigned l { bool oldbit; - asm volatile("bt %2,%1\n\t" + asm volatile("bt %2,%1" CC_SET(c) : CC_OUT(c) (oldbit) : "m" (*(unsigned long *)addr), "Ir" (nr)); diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 181264989db5..8edac1de2e35 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -187,7 +187,6 @@ struct mca_msr_regs { extern struct mce_vendor_flags mce_flags; -extern struct mca_config mca_cfg; extern struct mca_msr_regs msr_ops; enum mce_notifier_prios { diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index c120b5db178a..3c856a15b98e 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -126,13 +126,7 @@ static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next) DEBUG_LOCKS_WARN_ON(preemptible()); } -static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) -{ - int cpu = smp_processor_id(); - - if (cpumask_test_cpu(cpu, mm_cpumask(mm))) - cpumask_clear_cpu(cpu, mm_cpumask(mm)); -} +void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk); static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h index 9eb7c718aaf8..9f05a1002aa9 100644 --- a/arch/x86/include/asm/module.h +++ b/arch/x86/include/asm/module.h @@ -5,7 +5,7 @@ #include <asm/orc_types.h> struct mod_arch_specific { -#ifdef CONFIG_ORC_UNWINDER +#ifdef CONFIG_UNWINDER_ORC unsigned int num_orcs; int *orc_unwind_ip; struct orc_entry *orc_unwind; diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 738503e1f80c..530f448fddaf 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -289,6 +289,7 @@ static inline u64 hv_do_rep_hypercall(u16 code, u16 rep_count, u16 varhead_size, * to this information. */ extern u32 *hv_vp_index; +extern u32 hv_max_vp_index; /** * hv_cpu_number_to_vp_number() - Map CPU to VP. diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index 9fa03604b2b3..b21a475fd7ed 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -525,7 +525,7 @@ static inline bool x86_this_cpu_variable_test_bit(int nr, { bool oldbit; - asm volatile("bt "__percpu_arg(2)",%1\n\t" + asm volatile("bt "__percpu_arg(2)",%1" CC_SET(c) : CC_OUT(c) (oldbit) : "m" (*(unsigned long __percpu *)addr), "Ir" (nr)); diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 91c04c8e67fa..e2afbf689309 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -135,9 +135,9 @@ static inline int v8086_mode(struct pt_regs *regs) #endif } -#ifdef CONFIG_X86_64 static inline bool user_64bit_mode(struct pt_regs *regs) { +#ifdef CONFIG_X86_64 #ifndef CONFIG_PARAVIRT /* * On non-paravirt systems, this is the only long mode CPL 3 @@ -148,8 +148,12 @@ static inline bool user_64bit_mode(struct pt_regs *regs) /* Headers are too twisted for this to go in paravirt.h. */ return regs->cs == __USER_CS || regs->cs == pv_info.extra_user_64bit_cs; #endif +#else /* !CONFIG_X86_64 */ + return false; +#endif } +#ifdef CONFIG_X86_64 #define current_user_stack_pointer() current_pt_regs()->sp #define compat_user_stack_pointer() current_pt_regs()->sp #endif diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h index 045f99211a99..0c411c8bbdbd 100644 --- a/arch/x86/include/asm/rmwcc.h +++ b/arch/x86/include/asm/rmwcc.h @@ -28,7 +28,7 @@ cc_label: \ #define __GEN_RMWcc(fullop, var, cc, clobbers, ...) \ do { \ bool c; \ - asm volatile (fullop ";" CC_SET(cc) \ + asm volatile (fullop CC_SET(cc) \ : [counter] "+m" (var), CC_OUT(cc) (c) \ : __VA_ARGS__ : clobbers); \ return c; \ diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h index 91dfcafe27a6..bad25bb80679 100644 --- a/arch/x86/include/asm/syscalls.h +++ b/arch/x86/include/asm/syscalls.h @@ -21,7 +21,7 @@ asmlinkage long sys_ioperm(unsigned long, unsigned long, int); asmlinkage long sys_iopl(unsigned int); /* kernel/ldt.c */ -asmlinkage int sys_modify_ldt(int, void __user *, unsigned long); +asmlinkage long sys_modify_ldt(int, void __user *, unsigned long); /* kernel/signal.c */ asmlinkage long sys_rt_sigreturn(void); diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 4893abf7f74f..c4aed0de565e 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -82,6 +82,22 @@ static inline u64 inc_mm_tlb_gen(struct mm_struct *mm) #define __flush_tlb_single(addr) __native_flush_tlb_single(addr) #endif +static inline bool tlb_defer_switch_to_init_mm(void) +{ + /* + * If we have PCID, then switching to init_mm is reasonably + * fast. If we don't have PCID, then switching to init_mm is + * quite slow, so we try to defer it in the hopes that we can + * avoid it entirely. The latter approach runs the risk of + * receiving otherwise unnecessary IPIs. + * + * This choice is just a heuristic. The tlb code can handle this + * function returning true or false regardless of whether we have + * PCID. + */ + return !static_cpu_has(X86_FEATURE_PCID); +} + /* * 6 because 6 should be plenty and struct tlb_state will fit in * two cache lines. @@ -105,6 +121,23 @@ struct tlb_state { u16 next_asid; /* + * We can be in one of several states: + * + * - Actively using an mm. Our CPU's bit will be set in + * mm_cpumask(loaded_mm) and is_lazy == false; + * + * - Not using a real mm. loaded_mm == &init_mm. Our CPU's bit + * will not be set in mm_cpumask(&init_mm) and is_lazy == false. + * + * - Lazily using a real mm. loaded_mm != &init_mm, our bit + * is set in mm_cpumask(loaded_mm), but is_lazy == true. + * We're heuristically guessing that the CR3 load we + * skipped more than makes up for the overhead added by + * lazy mode. + */ + bool is_lazy; + + /* * Access to this CR4 shadow and to H/W CR4 is protected by * disabling interrupts when modifying either one. */ diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 5545f6459bf5..da3c3a3674a5 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -144,4 +144,22 @@ enum { X86_TRAP_IRET = 32, /* 32, IRET Exception */ }; +/* + * Page fault error code bits: + * + * bit 0 == 0: no page found 1: protection fault + * bit 1 == 0: read access 1: write access + * bit 2 == 0: kernel-mode access 1: user-mode access + * bit 3 == 1: use of reserved bit detected + * bit 4 == 1: fault was an instruction fetch + * bit 5 == 1: protection keys block access + */ +enum x86_pf_error_code { + X86_PF_PROT = 1 << 0, + X86_PF_WRITE = 1 << 1, + X86_PF_USER = 1 << 2, + X86_PF_RSVD = 1 << 3, + X86_PF_INSTR = 1 << 4, + X86_PF_PK = 1 << 5, +}; #endif /* _ASM_X86_TRAPS_H */ diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h index e9f793e2df7a..35d67dc7b69f 100644 --- a/arch/x86/include/asm/unwind.h +++ b/arch/x86/include/asm/unwind.h @@ -12,11 +12,11 @@ struct unwind_state { struct task_struct *task; int graph_idx; bool error; -#if defined(CONFIG_ORC_UNWINDER) +#if defined(CONFIG_UNWINDER_ORC) bool signal, full_regs; unsigned long sp, bp, ip; struct pt_regs *regs; -#elif defined(CONFIG_FRAME_POINTER_UNWINDER) +#elif defined(CONFIG_UNWINDER_FRAME_POINTER) bool got_irq; unsigned long *bp, *orig_sp, ip; struct pt_regs *regs; @@ -50,7 +50,7 @@ void unwind_start(struct unwind_state *state, struct task_struct *task, __unwind_start(state, task, regs, first_frame); } -#if defined(CONFIG_ORC_UNWINDER) || defined(CONFIG_FRAME_POINTER_UNWINDER) +#if defined(CONFIG_UNWINDER_ORC) || defined(CONFIG_UNWINDER_FRAME_POINTER) static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state) { if (unwind_done(state)) @@ -65,7 +65,7 @@ static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state) } #endif -#ifdef CONFIG_ORC_UNWINDER +#ifdef CONFIG_UNWINDER_ORC void unwind_init(void); void unwind_module_init(struct module *mod, void *orc_ip, size_t orc_ip_size, void *orc, size_t orc_size); diff --git a/arch/x86/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h index 185f3d10c194..39946d0a1d41 100644 --- a/arch/x86/include/uapi/asm/processor-flags.h +++ b/arch/x86/include/uapi/asm/processor-flags.h @@ -151,5 +151,8 @@ #define CX86_ARR_BASE 0xc4 #define CX86_RCR_BASE 0xdc +#define CR0_STATE (X86_CR0_PE | X86_CR0_MP | X86_CR0_ET | \ + X86_CR0_NE | X86_CR0_WP | X86_CR0_AM | \ + X86_CR0_PG) #endif /* _UAPI_ASM_X86_PROCESSOR_FLAGS_H */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index fd0a7895b63f..5335d05b695e 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -26,7 +26,6 @@ KASAN_SANITIZE_dumpstack.o := n KASAN_SANITIZE_dumpstack_$(BITS).o := n KASAN_SANITIZE_stacktrace.o := n -OBJECT_FILES_NON_STANDARD_head_$(BITS).o := y OBJECT_FILES_NON_STANDARD_relocate_kernel_$(BITS).o := y OBJECT_FILES_NON_STANDARD_ftrace_$(BITS).o := y OBJECT_FILES_NON_STANDARD_test_nx.o := y @@ -127,9 +126,9 @@ obj-$(CONFIG_PERF_EVENTS) += perf_regs.o obj-$(CONFIG_TRACING) += tracepoint.o obj-$(CONFIG_SCHED_MC_PRIO) += itmt.o -obj-$(CONFIG_ORC_UNWINDER) += unwind_orc.o -obj-$(CONFIG_FRAME_POINTER_UNWINDER) += unwind_frame.o -obj-$(CONFIG_GUESS_UNWINDER) += unwind_guess.o +obj-$(CONFIG_UNWINDER_ORC) += unwind_orc.o +obj-$(CONFIG_UNWINDER_FRAME_POINTER) += unwind_frame.o +obj-$(CONFIG_UNWINDER_GUESS) += unwind_guess.o ### # 64 bit specific files diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 458da8509b75..6db28f17ff28 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -27,6 +27,8 @@ static const struct pci_device_id amd_root_ids[] = { {} }; +#define PCI_DEVICE_ID_AMD_CNB17H_F4 0x1704 + const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) }, @@ -37,6 +39,7 @@ const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) }, {} }; EXPORT_SYMBOL_GPL(amd_nb_misc_ids); @@ -48,6 +51,7 @@ static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) }, {} }; @@ -402,11 +406,48 @@ void amd_flush_garts(void) } EXPORT_SYMBOL_GPL(amd_flush_garts); +static void __fix_erratum_688(void *info) +{ +#define MSR_AMD64_IC_CFG 0xC0011021 + + msr_set_bit(MSR_AMD64_IC_CFG, 3); + msr_set_bit(MSR_AMD64_IC_CFG, 14); +} + +/* Apply erratum 688 fix so machines without a BIOS fix work. */ +static __init void fix_erratum_688(void) +{ + struct pci_dev *F4; + u32 val; + + if (boot_cpu_data.x86 != 0x14) + return; + + if (!amd_northbridges.num) + return; + + F4 = node_to_amd_nb(0)->link; + if (!F4) + return; + + if (pci_read_config_dword(F4, 0x164, &val)) + return; + + if (val & BIT(2)) + return; + + on_each_cpu(__fix_erratum_688, NULL, 0); + + pr_info("x86/cpu/AMD: CPU erratum 688 worked around\n"); +} + static __init int init_amd_nbs(void) { amd_cache_northbridges(); amd_cache_gart(); + fix_erratum_688(); + return 0; } diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index d705c769f77d..ff891772c9f8 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -573,11 +573,21 @@ static u32 bdx_deadline_rev(void) return ~0U; } +static u32 skx_deadline_rev(void) +{ + switch (boot_cpu_data.x86_mask) { + case 0x03: return 0x01000136; + case 0x04: return 0x02000014; + } + + return ~0U; +} + static const struct x86_cpu_id deadline_match[] = { DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_HASWELL_X, hsx_deadline_rev), DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_X, 0x0b000020), DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_BROADWELL_XEON_D, bdx_deadline_rev), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_SKYLAKE_X, 0x02000014), + DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_SKYLAKE_X, skx_deadline_rev), DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_CORE, 0x22), DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_ULT, 0x20), @@ -600,7 +610,8 @@ static void apic_check_deadline_errata(void) const struct x86_cpu_id *m; u32 rev; - if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) + if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER) || + boot_cpu_has(X86_FEATURE_HYPERVISOR)) return; m = x86_match_cpu(deadline_match); diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 24f749324c0f..9990a71e311f 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -831,7 +831,6 @@ static int __cache_amd_cpumap_setup(unsigned int cpu, int index, } else if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { unsigned int apicid, nshared, first, last; - this_leaf = this_cpu_ci->info_list + index; nshared = base->eax.split.num_threads_sharing + 1; apicid = cpu_data(cpu).apicid; first = apicid - (apicid % nshared); diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index 098530a93bb7..debb974fd17d 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -1,3 +1,6 @@ +#ifndef __X86_MCE_INTERNAL_H__ +#define __X86_MCE_INTERNAL_H__ + #include <linux/device.h> #include <asm/mce.h> @@ -108,3 +111,7 @@ static inline void mce_work_trigger(void) { } static inline void mce_register_injector_chain(struct notifier_block *nb) { } static inline void mce_unregister_injector_chain(struct notifier_block *nb) { } #endif + +extern struct mca_config mca_cfg; + +#endif /* __X86_MCE_INTERNAL_H__ */ diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 40e28ed77fbf..486f640b02ef 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -28,6 +28,8 @@ #include <asm/msr.h> #include <asm/trace/irq_vectors.h> +#include "mce-internal.h" + #define NR_BLOCKS 5 #define THRESHOLD_MAX 0xFFF #define INT_TYPE_APIC 0x00020000 diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 86e8f0b2537b..c4fa4a85d4cb 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -122,9 +122,6 @@ static bool __init check_loader_disabled_bsp(void) bool *res = &dis_ucode_ldr; #endif - if (!have_cpuid_p()) - return *res; - /* * CPUID(1).ECX[31]: reserved for hypervisor use. This is still not * completely accurate as xen pv guests don't see that CPUID bit set but @@ -166,24 +163,36 @@ bool get_builtin_firmware(struct cpio_data *cd, const char *name) void __init load_ucode_bsp(void) { unsigned int cpuid_1_eax; + bool intel = true; - if (check_loader_disabled_bsp()) + if (!have_cpuid_p()) return; cpuid_1_eax = native_cpuid_eax(1); switch (x86_cpuid_vendor()) { case X86_VENDOR_INTEL: - if (x86_family(cpuid_1_eax) >= 6) - load_ucode_intel_bsp(); + if (x86_family(cpuid_1_eax) < 6) + return; break; + case X86_VENDOR_AMD: - if (x86_family(cpuid_1_eax) >= 0x10) - load_ucode_amd_bsp(cpuid_1_eax); + if (x86_family(cpuid_1_eax) < 0x10) + return; + intel = false; break; + default: - break; + return; } + + if (check_loader_disabled_bsp()) + return; + + if (intel) + load_ucode_intel_bsp(); + else + load_ucode_amd_bsp(cpuid_1_eax); } static bool check_loader_disabled_ap(void) diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 8f7a9bbad514..7dbcb7adf797 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -34,6 +34,7 @@ #include <linux/mm.h> #include <asm/microcode_intel.h> +#include <asm/intel-family.h> #include <asm/processor.h> #include <asm/tlbflush.h> #include <asm/setup.h> @@ -918,6 +919,18 @@ static int get_ucode_fw(void *to, const void *from, size_t n) return 0; } +static bool is_blacklisted(unsigned int cpu) +{ + struct cpuinfo_x86 *c = &cpu_data(cpu); + + if (c->x86 == 6 && c->x86_model == INTEL_FAM6_BROADWELL_X) { + pr_err_once("late loading on model 79 is disabled.\n"); + return true; + } + + return false; +} + static enum ucode_state request_microcode_fw(int cpu, struct device *device, bool refresh_fw) { @@ -926,6 +939,9 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device, const struct firmware *firmware; enum ucode_state ret; + if (is_blacklisted(cpu)) + return UCODE_NFOUND; + sprintf(name, "intel-ucode/%02x-%02x-%02x", c->x86, c->x86_model, c->x86_mask); @@ -950,6 +966,9 @@ static int get_ucode_user(void *to, const void *from, size_t n) static enum ucode_state request_microcode_user(int cpu, const void __user *buf, size_t size) { + if (is_blacklisted(cpu)) + return UCODE_NFOUND; + return generic_load_microcode(cpu, (void *)buf, size, &get_ucode_user); } diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index cf2ce063f65a..2902ca4d5993 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -30,10 +30,11 @@ static void __init i386_default_early_setup(void) asmlinkage __visible void __init i386_start_kernel(void) { - cr4_init_shadow(); - + /* Make sure IDT is set up before any exception happens */ idt_setup_early_handler(); + cr4_init_shadow(); + sanitize_boot_params(&boot_params); x86_early_init_platform_quirks(); diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 9ed3074d0d27..62474df4e3e7 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -211,9 +211,6 @@ ENTRY(startup_32_smp) #endif .Ldefault_entry: -#define CR0_STATE (X86_CR0_PE | X86_CR0_MP | X86_CR0_ET | \ - X86_CR0_NE | X86_CR0_WP | X86_CR0_AM | \ - X86_CR0_PG) movl $(CR0_STATE & ~X86_CR0_PG),%eax movl %eax,%cr0 @@ -401,7 +398,7 @@ ENTRY(early_idt_handler_array) # 24(%rsp) error code i = 0 .rept NUM_EXCEPTION_VECTORS - .ifeq (EXCEPTION_ERRCODE_MASK >> i) & 1 + .if ((EXCEPTION_ERRCODE_MASK >> i) & 1) == 0 pushl $0 # Dummy error code, to make stack frame uniform .endif pushl $i # 20(%esp) Vector number diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 513cbb012ecc..189bf42dfa2b 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -49,6 +49,7 @@ L3_START_KERNEL = pud_index(__START_KERNEL_map) .code64 .globl startup_64 startup_64: + UNWIND_HINT_EMPTY /* * At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 0, * and someone has loaded an identity mapped page table @@ -88,6 +89,7 @@ startup_64: addq $(early_top_pgt - __START_KERNEL_map), %rax jmp 1f ENTRY(secondary_startup_64) + UNWIND_HINT_EMPTY /* * At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 0, * and someone has loaded a mapped page table. @@ -132,6 +134,7 @@ ENTRY(secondary_startup_64) movq $1f, %rax jmp *%rax 1: + UNWIND_HINT_EMPTY /* Check if nx is implemented */ movl $0x80000001, %eax @@ -149,9 +152,6 @@ ENTRY(secondary_startup_64) 1: wrmsr /* Make changes effective */ /* Setup cr0 */ -#define CR0_STATE (X86_CR0_PE | X86_CR0_MP | X86_CR0_ET | \ - X86_CR0_NE | X86_CR0_WP | X86_CR0_AM | \ - X86_CR0_PG) movl $CR0_STATE, %eax /* Make changes effective */ movq %rax, %cr0 @@ -234,7 +234,7 @@ ENTRY(secondary_startup_64) pushq %rax # target address in negative space lretq .Lafter_lret: -ENDPROC(secondary_startup_64) +END(secondary_startup_64) #include "verify_cpu.S" @@ -246,6 +246,7 @@ ENDPROC(secondary_startup_64) */ ENTRY(start_cpu0) movq initial_stack(%rip), %rsp + UNWIND_HINT_EMPTY jmp .Ljump_to_C_code ENDPROC(start_cpu0) #endif @@ -265,26 +266,24 @@ ENDPROC(start_cpu0) .quad init_thread_union + THREAD_SIZE - SIZEOF_PTREGS __FINITDATA -bad_address: - jmp bad_address - __INIT ENTRY(early_idt_handler_array) - # 104(%rsp) %rflags - # 96(%rsp) %cs - # 88(%rsp) %rip - # 80(%rsp) error code i = 0 .rept NUM_EXCEPTION_VECTORS - .ifeq (EXCEPTION_ERRCODE_MASK >> i) & 1 - pushq $0 # Dummy error code, to make stack frame uniform + .if ((EXCEPTION_ERRCODE_MASK >> i) & 1) == 0 + UNWIND_HINT_IRET_REGS + pushq $0 # Dummy error code, to make stack frame uniform + .else + UNWIND_HINT_IRET_REGS offset=8 .endif pushq $i # 72(%rsp) Vector number jmp early_idt_handler_common + UNWIND_HINT_IRET_REGS i = i + 1 .fill early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc .endr -ENDPROC(early_idt_handler_array) + UNWIND_HINT_IRET_REGS offset=16 +END(early_idt_handler_array) early_idt_handler_common: /* @@ -312,6 +311,7 @@ early_idt_handler_common: pushq %r13 /* pt_regs->r13 */ pushq %r14 /* pt_regs->r14 */ pushq %r15 /* pt_regs->r15 */ + UNWIND_HINT_REGS cmpq $14,%rsi /* Page fault? */ jnz 10f @@ -327,7 +327,7 @@ early_idt_handler_common: 20: decl early_recursion_flag(%rip) jmp restore_regs_and_iret -ENDPROC(early_idt_handler_common) +END(early_idt_handler_common) __INITDATA @@ -434,7 +434,7 @@ ENTRY(phys_base) EXPORT_SYMBOL(phys_base) #include "../../x86/xen/xen-head.S" - + __PAGE_ALIGNED_BSS NEXT_PAGE(empty_zero_page) .skip PAGE_SIZE diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h index db2182d63ed0..3fc0f9a794cb 100644 --- a/arch/x86/kernel/kprobes/common.h +++ b/arch/x86/kernel/kprobes/common.h @@ -3,6 +3,15 @@ /* Kprobes and Optprobes common header */ +#include <asm/asm.h> + +#ifdef CONFIG_FRAME_POINTER +# define SAVE_RBP_STRING " push %" _ASM_BP "\n" \ + " mov %" _ASM_SP ", %" _ASM_BP "\n" +#else +# define SAVE_RBP_STRING " push %" _ASM_BP "\n" +#endif + #ifdef CONFIG_X86_64 #define SAVE_REGS_STRING \ /* Skip cs, ip, orig_ax. */ \ @@ -17,7 +26,7 @@ " pushq %r10\n" \ " pushq %r11\n" \ " pushq %rbx\n" \ - " pushq %rbp\n" \ + SAVE_RBP_STRING \ " pushq %r12\n" \ " pushq %r13\n" \ " pushq %r14\n" \ @@ -48,7 +57,7 @@ " pushl %es\n" \ " pushl %ds\n" \ " pushl %eax\n" \ - " pushl %ebp\n" \ + SAVE_RBP_STRING \ " pushl %edi\n" \ " pushl %esi\n" \ " pushl %edx\n" \ diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index f0153714ddac..0742491cbb73 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -1080,8 +1080,6 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) * raw stack chunk with redzones: */ __memcpy(kcb->jprobes_stack, (kprobe_opcode_t *)addr, MIN_STACK_SIZE(addr)); - regs->flags &= ~X86_EFLAGS_IF; - trace_hardirqs_off(); regs->ip = (unsigned long)(jp->entry); /* diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index f0e64db18ac8..0402d44deb4d 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -12,6 +12,7 @@ #include <linux/string.h> #include <linux/mm.h> #include <linux/smp.h> +#include <linux/syscalls.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/uaccess.h> @@ -294,8 +295,8 @@ out: return error; } -asmlinkage int sys_modify_ldt(int func, void __user *ptr, - unsigned long bytecount) +SYSCALL_DEFINE3(modify_ldt, int , func , void __user * , ptr , + unsigned long , bytecount) { int ret = -ENOSYS; @@ -313,5 +314,14 @@ asmlinkage int sys_modify_ldt(int func, void __user *ptr, ret = write_ldt(ptr, bytecount, 0); break; } - return ret; + /* + * The SYSCALL_DEFINE() macros give us an 'unsigned long' + * return type, but tht ABI for sys_modify_ldt() expects + * 'int'. This cast gives us an int-sized value in %rax + * for the return code. The 'unsigned' is necessary so + * the compiler does not try to sign-extend the negative + * return codes into the high half of the register when + * taking the value from int->long. + */ + return (unsigned int)ret; } diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 54180fa6f66f..add33f600531 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -105,6 +105,10 @@ void __noreturn machine_real_restart(unsigned int type) load_cr3(initial_page_table); #else write_cr3(real_mode_header->trampoline_pgd); + + /* Exiting long mode will fail if CR4.PCIDE is set. */ + if (static_cpu_has(X86_FEATURE_PCID)) + cr4_clear_bits(X86_CR4_PCIDE); #endif /* Jump to the identity-mapped low memory code */ diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c index d145a0b1f529..3dc26f95d46e 100644 --- a/arch/x86/kernel/unwind_frame.c +++ b/arch/x86/kernel/unwind_frame.c @@ -44,7 +44,8 @@ static void unwind_dump(struct unwind_state *state) state->stack_info.type, state->stack_info.next_sp, state->stack_mask, state->graph_idx); - for (sp = state->orig_sp; sp; sp = PTR_ALIGN(stack_info.next_sp, sizeof(long))) { + for (sp = PTR_ALIGN(state->orig_sp, sizeof(long)); sp; + sp = PTR_ALIGN(stack_info.next_sp, sizeof(long))) { if (get_stack_info(sp, state->task, &stack_info, &visit_mask)) break; @@ -174,6 +175,7 @@ static bool is_last_task_frame(struct unwind_state *state) * This determines if the frame pointer actually contains an encoded pointer to * pt_regs on the stack. See ENCODE_FRAME_POINTER. */ +#ifdef CONFIG_X86_64 static struct pt_regs *decode_frame_pointer(unsigned long *bp) { unsigned long regs = (unsigned long)bp; @@ -183,6 +185,23 @@ static struct pt_regs *decode_frame_pointer(unsigned long *bp) return (struct pt_regs *)(regs & ~0x1); } +#else +static struct pt_regs *decode_frame_pointer(unsigned long *bp) +{ + unsigned long regs = (unsigned long)bp; + + if (regs & 0x80000000) + return NULL; + + return (struct pt_regs *)(regs | 0x80000000); +} +#endif + +#ifdef CONFIG_X86_32 +#define KERNEL_REGS_SIZE (sizeof(struct pt_regs) - 2*sizeof(long)) +#else +#define KERNEL_REGS_SIZE (sizeof(struct pt_regs)) +#endif static bool update_stack_state(struct unwind_state *state, unsigned long *next_bp) @@ -202,7 +221,7 @@ static bool update_stack_state(struct unwind_state *state, regs = decode_frame_pointer(next_bp); if (regs) { frame = (unsigned long *)regs; - len = regs_size(regs); + len = KERNEL_REGS_SIZE; state->got_irq = true; } else { frame = next_bp; @@ -226,6 +245,14 @@ static bool update_stack_state(struct unwind_state *state, frame < prev_frame_end) return false; + /* + * On 32-bit with user mode regs, make sure the last two regs are safe + * to access: + */ + if (IS_ENABLED(CONFIG_X86_32) && regs && user_mode(regs) && + !on_stack(info, frame, len + 2*sizeof(long))) + return false; + /* Move state to the next frame: */ if (regs) { state->regs = regs; @@ -328,6 +355,13 @@ bad_address: state->regs->sp < (unsigned long)task_pt_regs(state->task)) goto the_end; + /* + * There are some known frame pointer issues on 32-bit. Disable + * unwinder warnings on 32-bit until it gets objtool support. + */ + if (IS_ENABLED(CONFIG_X86_32)) + goto the_end; + if (state->regs) { printk_deferred_once(KERN_WARNING "WARNING: kernel stack regs at %p in %s:%d has bad 'bp' value %p\n", diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 570b70d3f604..b95007e7c1b3 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -86,8 +86,8 @@ static struct orc_entry *orc_find(unsigned long ip) idx = (ip - LOOKUP_START_IP) / LOOKUP_BLOCK_SIZE; if (unlikely((idx >= lookup_num_blocks-1))) { - orc_warn("WARNING: bad lookup idx: idx=%u num=%u ip=%lx\n", - idx, lookup_num_blocks, ip); + orc_warn("WARNING: bad lookup idx: idx=%u num=%u ip=%pB\n", + idx, lookup_num_blocks, (void *)ip); return NULL; } @@ -96,8 +96,8 @@ static struct orc_entry *orc_find(unsigned long ip) if (unlikely((__start_orc_unwind + start >= __stop_orc_unwind) || (__start_orc_unwind + stop > __stop_orc_unwind))) { - orc_warn("WARNING: bad lookup value: idx=%u num=%u start=%u stop=%u ip=%lx\n", - idx, lookup_num_blocks, start, stop, ip); + orc_warn("WARNING: bad lookup value: idx=%u num=%u start=%u stop=%u ip=%pB\n", + idx, lookup_num_blocks, start, stop, (void *)ip); return NULL; } @@ -373,7 +373,7 @@ bool unwind_next_frame(struct unwind_state *state) case ORC_REG_R10: if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg R10 at ip %p\n", + orc_warn("missing regs for base reg R10 at ip %pB\n", (void *)state->ip); goto done; } @@ -382,7 +382,7 @@ bool unwind_next_frame(struct unwind_state *state) case ORC_REG_R13: if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg R13 at ip %p\n", + orc_warn("missing regs for base reg R13 at ip %pB\n", (void *)state->ip); goto done; } @@ -391,7 +391,7 @@ bool unwind_next_frame(struct unwind_state *state) case ORC_REG_DI: if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg DI at ip %p\n", + orc_warn("missing regs for base reg DI at ip %pB\n", (void *)state->ip); goto done; } @@ -400,7 +400,7 @@ bool unwind_next_frame(struct unwind_state *state) case ORC_REG_DX: if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg DX at ip %p\n", + orc_warn("missing regs for base reg DX at ip %pB\n", (void *)state->ip); goto done; } @@ -408,7 +408,7 @@ bool unwind_next_frame(struct unwind_state *state) break; default: - orc_warn("unknown SP base reg %d for ip %p\n", + orc_warn("unknown SP base reg %d for ip %pB\n", orc->sp_reg, (void *)state->ip); goto done; } @@ -436,7 +436,7 @@ bool unwind_next_frame(struct unwind_state *state) case ORC_TYPE_REGS: if (!deref_stack_regs(state, sp, &state->ip, &state->sp, true)) { - orc_warn("can't dereference registers at %p for ip %p\n", + orc_warn("can't dereference registers at %p for ip %pB\n", (void *)sp, (void *)orig_ip); goto done; } @@ -448,7 +448,7 @@ bool unwind_next_frame(struct unwind_state *state) case ORC_TYPE_REGS_IRET: if (!deref_stack_regs(state, sp, &state->ip, &state->sp, false)) { - orc_warn("can't dereference iret registers at %p for ip %p\n", + orc_warn("can't dereference iret registers at %p for ip %pB\n", (void *)sp, (void *)orig_ip); goto done; } @@ -465,7 +465,8 @@ bool unwind_next_frame(struct unwind_state *state) break; default: - orc_warn("unknown .orc_unwind entry type %d\n", orc->type); + orc_warn("unknown .orc_unwind entry type %d for ip %pB\n", + orc->type, (void *)orig_ip); break; } @@ -487,7 +488,7 @@ bool unwind_next_frame(struct unwind_state *state) break; default: - orc_warn("unknown BP base reg %d for ip %p\n", + orc_warn("unknown BP base reg %d for ip %pB\n", orc->bp_reg, (void *)orig_ip); goto done; } @@ -496,7 +497,7 @@ bool unwind_next_frame(struct unwind_state *state) if (state->stack_info.type == prev_type && on_stack(&state->stack_info, (void *)state->sp, sizeof(long)) && state->sp <= prev_sp) { - orc_warn("stack going in the wrong direction? ip=%p\n", + orc_warn("stack going in the wrong direction? ip=%pB\n", (void *)orig_ip); goto done; } diff --git a/arch/x86/kernel/verify_cpu.S b/arch/x86/kernel/verify_cpu.S index 014ea59aa153..3d3c2f71f617 100644 --- a/arch/x86/kernel/verify_cpu.S +++ b/arch/x86/kernel/verify_cpu.S @@ -33,7 +33,7 @@ #include <asm/cpufeatures.h> #include <asm/msr-index.h> -verify_cpu: +ENTRY(verify_cpu) pushf # Save caller passed flags push $0 # Kill any dangerous flags popf @@ -139,3 +139,4 @@ verify_cpu: popf # Restore caller passed flags xorl %eax, %eax ret +ENDPROC(verify_cpu) diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 72bf8c01c6e3..e1f095884386 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -1,5 +1,12 @@ -# Kernel does not boot with instrumentation of tlb.c. -KCOV_INSTRUMENT_tlb.o := n +# Kernel does not boot with instrumentation of tlb.c and mem_encrypt.c +KCOV_INSTRUMENT_tlb.o := n +KCOV_INSTRUMENT_mem_encrypt.o := n + +KASAN_SANITIZE_mem_encrypt.o := n + +ifdef CONFIG_FUNCTION_TRACER +CFLAGS_REMOVE_mem_encrypt.o = -pg +endif obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \ pat.o pgtable.o physaddr.o setup_nx.o tlb.o diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index e2baeaa053a5..db71c73530bd 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -29,26 +29,6 @@ #include <asm/trace/exceptions.h> /* - * Page fault error code bits: - * - * bit 0 == 0: no page found 1: protection fault - * bit 1 == 0: read access 1: write access - * bit 2 == 0: kernel-mode access 1: user-mode access - * bit 3 == 1: use of reserved bit detected - * bit 4 == 1: fault was an instruction fetch - * bit 5 == 1: protection keys block access - */ -enum x86_pf_error_code { - - PF_PROT = 1 << 0, - PF_WRITE = 1 << 1, - PF_USER = 1 << 2, - PF_RSVD = 1 << 3, - PF_INSTR = 1 << 4, - PF_PK = 1 << 5, -}; - -/* * Returns 0 if mmiotrace is disabled, or if the fault is not * handled by mmiotrace: */ @@ -149,7 +129,7 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr) * If it was a exec (instruction fetch) fault on NX page, then * do not ignore the fault: */ - if (error_code & PF_INSTR) + if (error_code & X86_PF_INSTR) return 0; instr = (void *)convert_ip_to_linear(current, regs); @@ -179,7 +159,7 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr) * siginfo so userspace can discover which protection key was set * on the PTE. * - * If we get here, we know that the hardware signaled a PF_PK + * If we get here, we know that the hardware signaled a X86_PF_PK * fault and that there was a VMA once we got in the fault * handler. It does *not* guarantee that the VMA we find here * was the one that we faulted on. @@ -204,7 +184,7 @@ static void fill_sig_info_pkey(int si_code, siginfo_t *info, u32 *pkey) /* * force_sig_info_fault() is called from a number of * contexts, some of which have a VMA and some of which - * do not. The PF_PK handing happens after we have a + * do not. The X86_PF_PK handing happens after we have a * valid VMA, so we should never reach this without a * valid VMA. */ @@ -697,7 +677,7 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, if (!oops_may_print()) return; - if (error_code & PF_INSTR) { + if (error_code & X86_PF_INSTR) { unsigned int level; pgd_t *pgd; pte_t *pte; @@ -779,7 +759,7 @@ no_context(struct pt_regs *regs, unsigned long error_code, */ if (current->thread.sig_on_uaccess_err && signal) { tsk->thread.trap_nr = X86_TRAP_PF; - tsk->thread.error_code = error_code | PF_USER; + tsk->thread.error_code = error_code | X86_PF_USER; tsk->thread.cr2 = address; /* XXX: hwpoison faults will set the wrong code. */ @@ -897,7 +877,7 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, struct task_struct *tsk = current; /* User mode accesses just cause a SIGSEGV */ - if (error_code & PF_USER) { + if (error_code & X86_PF_USER) { /* * It's possible to have interrupts off here: */ @@ -918,7 +898,7 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, * Instruction fetch faults in the vsyscall page might need * emulation. */ - if (unlikely((error_code & PF_INSTR) && + if (unlikely((error_code & X86_PF_INSTR) && ((address & ~0xfff) == VSYSCALL_ADDR))) { if (emulate_vsyscall(regs, address)) return; @@ -931,7 +911,7 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, * are always protection faults. */ if (address >= TASK_SIZE_MAX) - error_code |= PF_PROT; + error_code |= X86_PF_PROT; if (likely(show_unhandled_signals)) show_signal_msg(regs, error_code, address, tsk); @@ -992,11 +972,11 @@ static inline bool bad_area_access_from_pkeys(unsigned long error_code, if (!boot_cpu_has(X86_FEATURE_OSPKE)) return false; - if (error_code & PF_PK) + if (error_code & X86_PF_PK) return true; /* this checks permission keys on the VMA: */ - if (!arch_vma_access_permitted(vma, (error_code & PF_WRITE), - (error_code & PF_INSTR), foreign)) + if (!arch_vma_access_permitted(vma, (error_code & X86_PF_WRITE), + (error_code & X86_PF_INSTR), foreign)) return true; return false; } @@ -1024,7 +1004,7 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address, int code = BUS_ADRERR; /* Kernel mode? Handle exceptions or die: */ - if (!(error_code & PF_USER)) { + if (!(error_code & X86_PF_USER)) { no_context(regs, error_code, address, SIGBUS, BUS_ADRERR); return; } @@ -1052,14 +1032,14 @@ static noinline void mm_fault_error(struct pt_regs *regs, unsigned long error_code, unsigned long address, u32 *pkey, unsigned int fault) { - if (fatal_signal_pending(current) && !(error_code & PF_USER)) { + if (fatal_signal_pending(current) && !(error_code & X86_PF_USER)) { no_context(regs, error_code, address, 0, 0); return; } if (fault & VM_FAULT_OOM) { /* Kernel mode? Handle exceptions or die: */ - if (!(error_code & PF_USER)) { + if (!(error_code & X86_PF_USER)) { no_context(regs, error_code, address, SIGSEGV, SEGV_MAPERR); return; @@ -1084,16 +1064,16 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, static int spurious_fault_check(unsigned long error_code, pte_t *pte) { - if ((error_code & PF_WRITE) && !pte_write(*pte)) + if ((error_code & X86_PF_WRITE) && !pte_write(*pte)) return 0; - if ((error_code & PF_INSTR) && !pte_exec(*pte)) + if ((error_code & X86_PF_INSTR) && !pte_exec(*pte)) return 0; /* * Note: We do not do lazy flushing on protection key - * changes, so no spurious fault will ever set PF_PK. + * changes, so no spurious fault will ever set X86_PF_PK. */ - if ((error_code & PF_PK)) + if ((error_code & X86_PF_PK)) return 1; return 1; @@ -1139,8 +1119,8 @@ spurious_fault(unsigned long error_code, unsigned long address) * change, so user accesses are not expected to cause spurious * faults. */ - if (error_code != (PF_WRITE | PF_PROT) - && error_code != (PF_INSTR | PF_PROT)) + if (error_code != (X86_PF_WRITE | X86_PF_PROT) && + error_code != (X86_PF_INSTR | X86_PF_PROT)) return 0; pgd = init_mm.pgd + pgd_index(address); @@ -1200,19 +1180,19 @@ access_error(unsigned long error_code, struct vm_area_struct *vma) * always an unconditional error and can never result in * a follow-up action to resolve the fault, like a COW. */ - if (error_code & PF_PK) + if (error_code & X86_PF_PK) return 1; /* * Make sure to check the VMA so that we do not perform - * faults just to hit a PF_PK as soon as we fill in a + * faults just to hit a X86_PF_PK as soon as we fill in a * page. */ - if (!arch_vma_access_permitted(vma, (error_code & PF_WRITE), - (error_code & PF_INSTR), foreign)) + if (!arch_vma_access_permitted(vma, (error_code & X86_PF_WRITE), + (error_code & X86_PF_INSTR), foreign)) return 1; - if (error_code & PF_WRITE) { + if (error_code & X86_PF_WRITE) { /* write, present and write, not present: */ if (unlikely(!(vma->vm_flags & VM_WRITE))) return 1; @@ -1220,7 +1200,7 @@ access_error(unsigned long error_code, struct vm_area_struct *vma) } /* read, present: */ - if (unlikely(error_code & PF_PROT)) + if (unlikely(error_code & X86_PF_PROT)) return 1; /* read, not present: */ @@ -1243,7 +1223,7 @@ static inline bool smap_violation(int error_code, struct pt_regs *regs) if (!static_cpu_has(X86_FEATURE_SMAP)) return false; - if (error_code & PF_USER) + if (error_code & X86_PF_USER) return false; if (!user_mode(regs) && (regs->flags & X86_EFLAGS_AC)) @@ -1296,7 +1276,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code, * protection error (error_code & 9) == 0. */ if (unlikely(fault_in_kernel_space(address))) { - if (!(error_code & (PF_RSVD | PF_USER | PF_PROT))) { + if (!(error_code & (X86_PF_RSVD | X86_PF_USER | X86_PF_PROT))) { if (vmalloc_fault(address) >= 0) return; @@ -1324,7 +1304,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code, if (unlikely(kprobes_fault(regs))) return; - if (unlikely(error_code & PF_RSVD)) + if (unlikely(error_code & X86_PF_RSVD)) pgtable_bad(regs, error_code, address); if (unlikely(smap_violation(error_code, regs))) { @@ -1350,7 +1330,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code, */ if (user_mode(regs)) { local_irq_enable(); - error_code |= PF_USER; + error_code |= X86_PF_USER; flags |= FAULT_FLAG_USER; } else { if (regs->flags & X86_EFLAGS_IF) @@ -1359,9 +1339,9 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code, perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); - if (error_code & PF_WRITE) + if (error_code & X86_PF_WRITE) flags |= FAULT_FLAG_WRITE; - if (error_code & PF_INSTR) + if (error_code & X86_PF_INSTR) flags |= FAULT_FLAG_INSTRUCTION; /* @@ -1381,7 +1361,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code, * space check, thus avoiding the deadlock: */ if (unlikely(!down_read_trylock(&mm->mmap_sem))) { - if ((error_code & PF_USER) == 0 && + if (!(error_code & X86_PF_USER) && !search_exception_tables(regs->ip)) { bad_area_nosemaphore(regs, error_code, address, NULL); return; @@ -1408,7 +1388,7 @@ retry: bad_area(regs, error_code, address); return; } - if (error_code & PF_USER) { + if (error_code & X86_PF_USER) { /* * Accessing the stack below %sp is always a bug. * The large cushion allows instructions like enter diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 49d9778376d7..0f3d0cea4d00 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -30,6 +30,7 @@ atomic64_t last_mm_ctx_id = ATOMIC64_INIT(1); + static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen, u16 *new_asid, bool *need_flush) { @@ -80,7 +81,7 @@ void leave_mm(int cpu) return; /* Warn if we're not lazy. */ - WARN_ON(cpumask_test_cpu(smp_processor_id(), mm_cpumask(loaded_mm))); + WARN_ON(!this_cpu_read(cpu_tlbstate.is_lazy)); switch_mm(NULL, &init_mm, NULL); } @@ -142,45 +143,24 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, __flush_tlb_all(); } #endif + this_cpu_write(cpu_tlbstate.is_lazy, false); if (real_prev == next) { - VM_BUG_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) != - next->context.ctx_id); - - if (cpumask_test_cpu(cpu, mm_cpumask(next))) { - /* - * There's nothing to do: we weren't lazy, and we - * aren't changing our mm. We don't need to flush - * anything, nor do we need to update CR3, CR4, or - * LDTR. - */ - return; - } - - /* Resume remote flushes and then read tlb_gen. */ - cpumask_set_cpu(cpu, mm_cpumask(next)); - next_tlb_gen = atomic64_read(&next->context.tlb_gen); - - if (this_cpu_read(cpu_tlbstate.ctxs[prev_asid].tlb_gen) < - next_tlb_gen) { - /* - * Ideally, we'd have a flush_tlb() variant that - * takes the known CR3 value as input. This would - * be faster on Xen PV and on hypothetical CPUs - * on which INVPCID is fast. - */ - this_cpu_write(cpu_tlbstate.ctxs[prev_asid].tlb_gen, - next_tlb_gen); - write_cr3(build_cr3(next, prev_asid)); - trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, - TLB_FLUSH_ALL); - } + VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) != + next->context.ctx_id); /* - * We just exited lazy mode, which means that CR4 and/or LDTR - * may be stale. (Changes to the required CR4 and LDTR states - * are not reflected in tlb_gen.) + * We don't currently support having a real mm loaded without + * our cpu set in mm_cpumask(). We have all the bookkeeping + * in place to figure out whether we would need to flush + * if our cpu were cleared in mm_cpumask(), but we don't + * currently use it. */ + if (WARN_ON_ONCE(real_prev != &init_mm && + !cpumask_test_cpu(cpu, mm_cpumask(next)))) + cpumask_set_cpu(cpu, mm_cpumask(next)); + + return; } else { u16 new_asid; bool need_flush; @@ -199,10 +179,9 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, } /* Stop remote flushes for the previous mm */ - if (cpumask_test_cpu(cpu, mm_cpumask(real_prev))) - cpumask_clear_cpu(cpu, mm_cpumask(real_prev)); - - VM_WARN_ON_ONCE(cpumask_test_cpu(cpu, mm_cpumask(next))); + VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(real_prev)) && + real_prev != &init_mm); + cpumask_clear_cpu(cpu, mm_cpumask(real_prev)); /* * Start remote flushes and then read tlb_gen. @@ -233,6 +212,40 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, } /* + * Please ignore the name of this function. It should be called + * switch_to_kernel_thread(). + * + * enter_lazy_tlb() is a hint from the scheduler that we are entering a + * kernel thread or other context without an mm. Acceptable implementations + * include doing nothing whatsoever, switching to init_mm, or various clever + * lazy tricks to try to minimize TLB flushes. + * + * The scheduler reserves the right to call enter_lazy_tlb() several times + * in a row. It will notify us that we're going back to a real mm by + * calling switch_mm_irqs_off(). + */ +void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) +{ + if (this_cpu_read(cpu_tlbstate.loaded_mm) == &init_mm) + return; + + if (tlb_defer_switch_to_init_mm()) { + /* + * There's a significant optimization that may be possible + * here. We have accurate enough TLB flush tracking that we + * don't need to maintain coherence of TLB per se when we're + * lazy. We do, however, need to maintain coherence of + * paging-structure caches. We could, in principle, leave our + * old mm loaded and only switch to init_mm when + * tlb_remove_page() happens. + */ + this_cpu_write(cpu_tlbstate.is_lazy, true); + } else { + switch_mm(NULL, &init_mm, NULL); + } +} + +/* * Call this when reinitializing a CPU. It fixes the following potential * problems: * @@ -303,16 +316,20 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f, /* This code cannot presently handle being reentered. */ VM_WARN_ON(!irqs_disabled()); + if (unlikely(loaded_mm == &init_mm)) + return; + VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].ctx_id) != loaded_mm->context.ctx_id); - if (!cpumask_test_cpu(smp_processor_id(), mm_cpumask(loaded_mm))) { + if (this_cpu_read(cpu_tlbstate.is_lazy)) { /* - * We're in lazy mode -- don't flush. We can get here on - * remote flushes due to races and on local flushes if a - * kernel thread coincidentally flushes the mm it's lazily - * still using. + * We're in lazy mode. We need to at least flush our + * paging-structure cache to avoid speculatively reading + * garbage into our TLB. Since switching to init_mm is barely + * slower than a minimal flush, just switch to init_mm. */ + switch_mm_irqs_off(NULL, &init_mm, NULL); return; } diff --git a/arch/x86/um/ldt.c b/arch/x86/um/ldt.c index 836a1eb5df43..3ee234b6234d 100644 --- a/arch/x86/um/ldt.c +++ b/arch/x86/um/ldt.c @@ -6,6 +6,7 @@ #include <linux/mm.h> #include <linux/sched.h> #include <linux/slab.h> +#include <linux/syscalls.h> #include <linux/uaccess.h> #include <asm/unistd.h> #include <os.h> @@ -369,7 +370,9 @@ void free_ldt(struct mm_context *mm) mm->arch.ldt.entry_count = 0; } -int sys_modify_ldt(int func, void __user *ptr, unsigned long bytecount) +SYSCALL_DEFINE3(modify_ldt, int , func , void __user * , ptr , + unsigned long , bytecount) { - return do_modify_ldt_skas(func, ptr, bytecount); + /* See non-um modify_ldt() for why we do this cast */ + return (unsigned int)do_modify_ldt_skas(func, ptr, bytecount); } diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 0e7ef69e8531..d669e9d89001 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -93,11 +93,11 @@ int xen_cpuhp_setup(int (*cpu_up_prepare_cb)(unsigned int), int rc; rc = cpuhp_setup_state_nocalls(CPUHP_XEN_PREPARE, - "x86/xen/hvm_guest:prepare", + "x86/xen/guest:prepare", cpu_up_prepare_cb, cpu_dead_cb); if (rc >= 0) { rc = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, - "x86/xen/hvm_guest:online", + "x86/xen/guest:online", xen_cpu_up_online, NULL); if (rc < 0) cpuhp_remove_state_nocalls(CPUHP_XEN_PREPARE); diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index a7525e95d53f..124941d09b2b 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -9,6 +9,7 @@ #include <asm/boot.h> #include <asm/asm.h> #include <asm/page_types.h> +#include <asm/unwind_hints.h> #include <xen/interface/elfnote.h> #include <xen/interface/features.h> @@ -19,6 +20,7 @@ #ifdef CONFIG_XEN_PV __INIT ENTRY(startup_xen) + UNWIND_HINT_EMPTY cld /* Clear .bss */ @@ -33,21 +35,24 @@ ENTRY(startup_xen) mov $init_thread_union+THREAD_SIZE, %_ASM_SP jmp xen_start_kernel - +END(startup_xen) __FINIT #endif .pushsection .text .balign PAGE_SIZE ENTRY(hypercall_page) - .skip PAGE_SIZE + .rept (PAGE_SIZE / 32) + UNWIND_HINT_EMPTY + .skip 32 + .endr #define HYPERCALL(n) \ .equ xen_hypercall_##n, hypercall_page + __HYPERVISOR_##n * 32; \ .type xen_hypercall_##n, @function; .size xen_hypercall_##n, 32 #include <asm/xen-hypercalls.h> #undef HYPERCALL - +END(hypercall_page) .popsection ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS, .asciz "linux") |