diff options
| author | Stefan Agner <stefan.agner@toradex.com> | 2016-06-02 10:02:34 -0700 |
|---|---|---|
| committer | Stefan Agner <stefan.agner@toradex.com> | 2016-06-02 10:02:34 -0700 |
| commit | 430c728373dac245d0ca55aac1d0fcc456872174 (patch) | |
| tree | 82b61d813ac0204316dd5a67c46fd40e41d63e01 /arch | |
| parent | 7a829b541431d70eb10d8471bc33a424da36820f (diff) | |
| parent | 351d2d4d3108a9a0f0e112dabbc36c2b1446e4f8 (diff) | |
Merge tag 'v4.4.12' into toradex_vf_4.4-next
This is the 4.4.12 stable release
Diffstat (limited to 'arch')
126 files changed, 1136 insertions, 645 deletions
diff --git a/arch/arc/include/asm/bitops.h b/arch/arc/include/asm/bitops.h index 57c1f33844d4..0352fb8d21b9 100644 --- a/arch/arc/include/asm/bitops.h +++ b/arch/arc/include/asm/bitops.h @@ -35,21 +35,6 @@ static inline void op##_bit(unsigned long nr, volatile unsigned long *m)\ \ m += nr >> 5; \ \ - /* \ - * ARC ISA micro-optimization: \ - * \ - * Instructions dealing with bitpos only consider lower 5 bits \ - * e.g (x << 33) is handled like (x << 1) by ASL instruction \ - * (mem pointer still needs adjustment to point to next word) \ - * \ - * Hence the masking to clamp @nr arg can be elided in general. \ - * \ - * However if @nr is a constant (above assumed in a register), \ - * and greater than 31, gcc can optimize away (x << 33) to 0, \ - * as overflow, given the 32-bit ISA. Thus masking needs to be \ - * done for const @nr, but no code is generated due to gcc \ - * const prop. \ - */ \ nr &= 0x1f; \ \ __asm__ __volatile__( \ diff --git a/arch/arc/include/asm/io.h b/arch/arc/include/asm/io.h index 694ece8a0243..cb69299a492e 100644 --- a/arch/arc/include/asm/io.h +++ b/arch/arc/include/asm/io.h @@ -13,6 +13,15 @@ #include <asm/byteorder.h> #include <asm/page.h> +#ifdef CONFIG_ISA_ARCV2 +#include <asm/barrier.h> +#define __iormb() rmb() +#define __iowmb() wmb() +#else +#define __iormb() do { } while (0) +#define __iowmb() do { } while (0) +#endif + extern void __iomem *ioremap(unsigned long physaddr, unsigned long size); extern void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size, unsigned long flags); @@ -22,6 +31,15 @@ extern void iounmap(const void __iomem *addr); #define ioremap_wc(phy, sz) ioremap(phy, sz) #define ioremap_wt(phy, sz) ioremap(phy, sz) +/* + * io{read,write}{16,32}be() macros + */ +#define ioread16be(p) ({ u16 __v = be16_to_cpu((__force __be16)__raw_readw(p)); __iormb(); __v; }) +#define ioread32be(p) ({ u32 __v = be32_to_cpu((__force __be32)__raw_readl(p)); __iormb(); __v; }) + +#define iowrite16be(v,p) ({ __iowmb(); __raw_writew((__force u16)cpu_to_be16(v), p); }) +#define iowrite32be(v,p) ({ __iowmb(); __raw_writel((__force u32)cpu_to_be32(v), p); }) + /* Change struct page to physical address */ #define page_to_phys(page) (page_to_pfn(page) << PAGE_SHIFT) @@ -99,15 +117,6 @@ static inline void __raw_writel(u32 w, volatile void __iomem *addr) } -#ifdef CONFIG_ISA_ARCV2 -#include <asm/barrier.h> -#define __iormb() rmb() -#define __iowmb() wmb() -#else -#define __iormb() do { } while (0) -#define __iowmb() do { } while (0) -#endif - /* * MMIO can also get buffered/optimized in micro-arch, so barriers needed * Based on ARM model for the typical use case @@ -129,15 +138,23 @@ static inline void __raw_writel(u32 w, volatile void __iomem *addr) #define writel(v,c) ({ __iowmb(); writel_relaxed(v,c); }) /* - * Relaxed API for drivers which can handle any ordering themselves + * Relaxed API for drivers which can handle barrier ordering themselves + * + * Also these are defined to perform little endian accesses. + * To provide the typical device register semantics of fixed endian, + * swap the byte order for Big Endian + * + * http://lkml.kernel.org/r/201603100845.30602.arnd@arndb.de */ #define readb_relaxed(c) __raw_readb(c) -#define readw_relaxed(c) __raw_readw(c) -#define readl_relaxed(c) __raw_readl(c) +#define readw_relaxed(c) ({ u16 __r = le16_to_cpu((__force __le16) \ + __raw_readw(c)); __r; }) +#define readl_relaxed(c) ({ u32 __r = le32_to_cpu((__force __le32) \ + __raw_readl(c)); __r; }) #define writeb_relaxed(v,c) __raw_writeb(v,c) -#define writew_relaxed(v,c) __raw_writew(v,c) -#define writel_relaxed(v,c) __raw_writel(v,c) +#define writew_relaxed(v,c) __raw_writew((__force u16) cpu_to_le16(v),c) +#define writel_relaxed(v,c) __raw_writel((__force u32) cpu_to_le32(v),c) #include <asm-generic/io.h> diff --git a/arch/arm/boot/dts/am43x-epos-evm.dts b/arch/arm/boot/dts/am43x-epos-evm.dts index 47954ed990f8..00707aac72fc 100644 --- a/arch/arm/boot/dts/am43x-epos-evm.dts +++ b/arch/arm/boot/dts/am43x-epos-evm.dts @@ -792,3 +792,8 @@ tx-num-evt = <32>; rx-num-evt = <32>; }; + +&synctimer_32kclk { + assigned-clocks = <&mux_synctimer32k_ck>; + assigned-clock-parents = <&clkdiv32k_ick>; +}; diff --git a/arch/arm/boot/dts/armada-375.dtsi b/arch/arm/boot/dts/armada-375.dtsi index 7ccce7529b0c..cc952cf8ec30 100644 --- a/arch/arm/boot/dts/armada-375.dtsi +++ b/arch/arm/boot/dts/armada-375.dtsi @@ -529,7 +529,7 @@ }; sata@a0000 { - compatible = "marvell,orion-sata"; + compatible = "marvell,armada-370-sata"; reg = <0xa0000 0x5000>; interrupts = <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gateclk 14>, <&gateclk 20>; diff --git a/arch/arm/boot/dts/armada-385-linksys.dtsi b/arch/arm/boot/dts/armada-385-linksys.dtsi index 3710755c6d76..85d2c377c332 100644 --- a/arch/arm/boot/dts/armada-385-linksys.dtsi +++ b/arch/arm/boot/dts/armada-385-linksys.dtsi @@ -117,7 +117,7 @@ }; /* USB part of the eSATA/USB 2.0 port */ - usb@50000 { + usb@58000 { status = "okay"; }; diff --git a/arch/arm/boot/dts/armada-xp-axpwifiap.dts b/arch/arm/boot/dts/armada-xp-axpwifiap.dts index 23fc670c0427..5c21b236721f 100644 --- a/arch/arm/boot/dts/armada-xp-axpwifiap.dts +++ b/arch/arm/boot/dts/armada-xp-axpwifiap.dts @@ -70,8 +70,8 @@ soc { ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xf1000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; pcie-controller { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-db.dts b/arch/arm/boot/dts/armada-xp-db.dts index f774101416a5..ebe1d267406d 100644 --- a/arch/arm/boot/dts/armada-xp-db.dts +++ b/arch/arm/boot/dts/armada-xp-db.dts @@ -76,8 +76,8 @@ ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xf1000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 MBUS_ID(0x01, 0x2f) 0 0 0xf0000000 0x1000000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; devbus-bootcs { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-gp.dts b/arch/arm/boot/dts/armada-xp-gp.dts index 4878d7353069..5730b875c4f5 100644 --- a/arch/arm/boot/dts/armada-xp-gp.dts +++ b/arch/arm/boot/dts/armada-xp-gp.dts @@ -95,8 +95,8 @@ ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xf1000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 MBUS_ID(0x01, 0x2f) 0 0 0xf0000000 0x1000000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; devbus-bootcs { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts b/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts index 58b500873bfd..d960fef77ca1 100644 --- a/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts +++ b/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts @@ -65,8 +65,8 @@ soc { ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xd0000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; pcie-controller { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-linksys-mamba.dts b/arch/arm/boot/dts/armada-xp-linksys-mamba.dts index 6e9820e141f8..b89e6cf1271a 100644 --- a/arch/arm/boot/dts/armada-xp-linksys-mamba.dts +++ b/arch/arm/boot/dts/armada-xp-linksys-mamba.dts @@ -70,8 +70,8 @@ soc { ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xf1000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; pcie-controller { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-matrix.dts b/arch/arm/boot/dts/armada-xp-matrix.dts index 6ab33837a2b6..6522b04f4a8e 100644 --- a/arch/arm/boot/dts/armada-xp-matrix.dts +++ b/arch/arm/boot/dts/armada-xp-matrix.dts @@ -68,8 +68,8 @@ soc { ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xf1000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; internal-regs { serial@12000 { diff --git a/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts b/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts index 6fe8972de0a2..db54c7158a36 100644 --- a/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts +++ b/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts @@ -64,8 +64,8 @@ soc { ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xd0000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; pcie-controller { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts index a5db17782e08..853bd392a4fe 100644 --- a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts +++ b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts @@ -65,9 +65,9 @@ soc { ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xd0000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 - MBUS_ID(0x01, 0x2f) 0 0 0xf0000000 0x8000000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x01, 0x2f) 0 0 0xe8000000 0x8000000 + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; devbus-bootcs { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-synology-ds414.dts b/arch/arm/boot/dts/armada-xp-synology-ds414.dts index 2391b11dc546..d17dab0a6f51 100644 --- a/arch/arm/boot/dts/armada-xp-synology-ds414.dts +++ b/arch/arm/boot/dts/armada-xp-synology-ds414.dts @@ -78,8 +78,8 @@ soc { ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xf1000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; pcie-controller { status = "okay"; diff --git a/arch/arm/boot/dts/at91-sama5d3_xplained.dts b/arch/arm/boot/dts/at91-sama5d3_xplained.dts index ff888d21c786..f3e2b96c06a3 100644 --- a/arch/arm/boot/dts/at91-sama5d3_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d3_xplained.dts @@ -303,6 +303,7 @@ regulator-name = "mmc0-card-supply"; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; + regulator-always-on; }; gpio_keys { diff --git a/arch/arm/boot/dts/at91-sama5d4_xplained.dts b/arch/arm/boot/dts/at91-sama5d4_xplained.dts index 569026e8f96c..da84e65b56ef 100644 --- a/arch/arm/boot/dts/at91-sama5d4_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d4_xplained.dts @@ -268,5 +268,6 @@ regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; vin-supply = <&vcc_3v3_reg>; + regulator-always-on; }; }; diff --git a/arch/arm/boot/dts/at91sam9x5.dtsi b/arch/arm/boot/dts/at91sam9x5.dtsi index 0827d594b1f0..cd0cd5fd09a3 100644 --- a/arch/arm/boot/dts/at91sam9x5.dtsi +++ b/arch/arm/boot/dts/at91sam9x5.dtsi @@ -106,7 +106,7 @@ pmc: pmc@fffffc00 { compatible = "atmel,at91sam9x5-pmc", "syscon"; - reg = <0xfffffc00 0x100>; + reg = <0xfffffc00 0x200>; interrupts = <1 IRQ_TYPE_LEVEL_HIGH 7>; interrupt-controller; #address-cells = <1>; diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi index fe99231cbde5..c2a03c740e79 100644 --- a/arch/arm/boot/dts/dra7.dtsi +++ b/arch/arm/boot/dts/dra7.dtsi @@ -1497,6 +1497,16 @@ 0x48485200 0x2E00>; #address-cells = <1>; #size-cells = <1>; + + /* + * Do not allow gating of cpsw clock as workaround + * for errata i877. Keeping internal clock disabled + * causes the device switching characteristics + * to degrade over time and eventually fail to meet + * the data manual delay time/skew specs. + */ + ti,no-idle; + /* * rx_thresh_pend * rx_pend diff --git a/arch/arm/boot/dts/pxa3xx.dtsi b/arch/arm/boot/dts/pxa3xx.dtsi index cf6998a0804d..564341af7e97 100644 --- a/arch/arm/boot/dts/pxa3xx.dtsi +++ b/arch/arm/boot/dts/pxa3xx.dtsi @@ -30,7 +30,7 @@ reg = <0x43100000 90>; interrupts = <45>; clocks = <&clks CLK_NAND>; - dmas = <&pdma 97>; + dmas = <&pdma 97 3>; dma-names = "data"; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 61d96a645ff3..12d727fae0a7 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -886,11 +886,14 @@ static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache VM_BUG_ON(pmd_present(*pmd) && pmd_pfn(*pmd) != pmd_pfn(*new_pmd)); old_pmd = *pmd; - kvm_set_pmd(pmd, *new_pmd); - if (pmd_present(old_pmd)) + if (pmd_present(old_pmd)) { + pmd_clear(pmd); kvm_tlb_flush_vmid_ipa(kvm, addr); - else + } else { get_page(virt_to_page(pmd)); + } + + kvm_set_pmd(pmd, *new_pmd); return 0; } @@ -939,12 +942,14 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, /* Create 2nd stage page table mapping - Level 3 */ old_pte = *pte; - kvm_set_pte(pte, *new_pte); - if (pte_present(old_pte)) + if (pte_present(old_pte)) { + kvm_set_pte(pte, __pte(0)); kvm_tlb_flush_vmid_ipa(kvm, addr); - else + } else { get_page(virt_to_page(pte)); + } + kvm_set_pte(pte, *new_pte); return 0; } diff --git a/arch/arm/mach-cns3xxx/pcie.c b/arch/arm/mach-cns3xxx/pcie.c index 47905a50e075..318394ed5c7a 100644 --- a/arch/arm/mach-cns3xxx/pcie.c +++ b/arch/arm/mach-cns3xxx/pcie.c @@ -220,13 +220,13 @@ static void cns3xxx_write_config(struct cns3xxx_pcie *cnspci, u32 mask = (0x1ull << (size * 8)) - 1; int shift = (where % 4) * 8; - v = readl_relaxed(base + (where & 0xffc)); + v = readl_relaxed(base); v &= ~(mask << shift); v |= (val & mask) << shift; - writel_relaxed(v, base + (where & 0xffc)); - readl_relaxed(base + (where & 0xffc)); + writel_relaxed(v, base); + readl_relaxed(base); } static void __init cns3xxx_pcie_hw_init(struct cns3xxx_pcie *cnspci) diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig index 3a10f1a8317a..bfd8bb371477 100644 --- a/arch/arm/mach-exynos/Kconfig +++ b/arch/arm/mach-exynos/Kconfig @@ -26,6 +26,7 @@ menuconfig ARCH_EXYNOS select S5P_DEV_MFC select SRAM select THERMAL + select THERMAL_OF select MFD_SYSCON help Support for SAMSUNG EXYNOS SoCs (EXYNOS4/5) diff --git a/arch/arm/mach-exynos/pm_domains.c b/arch/arm/mach-exynos/pm_domains.c index 7c21760f590f..875a2bab64f6 100644 --- a/arch/arm/mach-exynos/pm_domains.c +++ b/arch/arm/mach-exynos/pm_domains.c @@ -92,7 +92,7 @@ static int exynos_pd_power(struct generic_pm_domain *domain, bool power_on) if (IS_ERR(pd->clk[i])) break; - if (IS_ERR(pd->clk[i])) + if (IS_ERR(pd->pclk[i])) continue; /* Skip on first power up */ if (clk_set_parent(pd->clk[i], pd->pclk[i])) pr_err("%s: error setting parent to clock%d\n", diff --git a/arch/arm/mach-omap2/cpuidle34xx.c b/arch/arm/mach-omap2/cpuidle34xx.c index aa7b379e2661..2a3db0bd9e15 100644 --- a/arch/arm/mach-omap2/cpuidle34xx.c +++ b/arch/arm/mach-omap2/cpuidle34xx.c @@ -34,6 +34,7 @@ #include "pm.h" #include "control.h" #include "common.h" +#include "soc.h" /* Mach specific information to be recorded in the C-state driver_data */ struct omap3_idle_statedata { @@ -315,6 +316,69 @@ static struct cpuidle_driver omap3_idle_driver = { .safe_state_index = 0, }; +/* + * Numbers based on measurements made in October 2009 for PM optimized kernel + * with CPU freq enabled on device Nokia N900. Assumes OPP2 (main idle OPP, + * and worst case latencies). + */ +static struct cpuidle_driver omap3430_idle_driver = { + .name = "omap3430_idle", + .owner = THIS_MODULE, + .states = { + { + .enter = omap3_enter_idle_bm, + .exit_latency = 110 + 162, + .target_residency = 5, + .name = "C1", + .desc = "MPU ON + CORE ON", + }, + { + .enter = omap3_enter_idle_bm, + .exit_latency = 106 + 180, + .target_residency = 309, + .name = "C2", + .desc = "MPU ON + CORE ON", + }, + { + .enter = omap3_enter_idle_bm, + .exit_latency = 107 + 410, + .target_residency = 46057, + .name = "C3", + .desc = "MPU RET + CORE ON", + }, + { + .enter = omap3_enter_idle_bm, + .exit_latency = 121 + 3374, + .target_residency = 46057, + .name = "C4", + .desc = "MPU OFF + CORE ON", + }, + { + .enter = omap3_enter_idle_bm, + .exit_latency = 855 + 1146, + .target_residency = 46057, + .name = "C5", + .desc = "MPU RET + CORE RET", + }, + { + .enter = omap3_enter_idle_bm, + .exit_latency = 7580 + 4134, + .target_residency = 484329, + .name = "C6", + .desc = "MPU OFF + CORE RET", + }, + { + .enter = omap3_enter_idle_bm, + .exit_latency = 7505 + 15274, + .target_residency = 484329, + .name = "C7", + .desc = "MPU OFF + CORE OFF", + }, + }, + .state_count = ARRAY_SIZE(omap3_idle_data), + .safe_state_index = 0, +}; + /* Public functions */ /** @@ -333,5 +397,8 @@ int __init omap3_idle_init(void) if (!mpu_pd || !core_pd || !per_pd || !cam_pd) return -ENODEV; - return cpuidle_register(&omap3_idle_driver, NULL); + if (cpu_is_omap3430()) + return cpuidle_register(&omap3430_idle_driver, NULL); + else + return cpuidle_register(&omap3_idle_driver, NULL); } diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c index 3eaeaca5da05..3a911d8dea8b 100644 --- a/arch/arm/mach-omap2/io.c +++ b/arch/arm/mach-omap2/io.c @@ -368,6 +368,7 @@ void __init omap5_map_io(void) void __init dra7xx_map_io(void) { iotable_init(dra7xx_io_desc, ARRAY_SIZE(dra7xx_io_desc)); + omap_barriers_init(); } #endif /* diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index 48495ad82aba..147c90e70b2e 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -1416,9 +1416,7 @@ static void _enable_sysc(struct omap_hwmod *oh) (sf & SYSC_HAS_CLOCKACTIVITY)) _set_clockactivity(oh, oh->class->sysc->clockact, &v); - /* If the cached value is the same as the new value, skip the write */ - if (oh->_sysc_cache != v) - _write_sysconfig(v, oh); + _write_sysconfig(v, oh); /* * Set the autoidle bit only after setting the smartidle bit @@ -1481,7 +1479,9 @@ static void _idle_sysc(struct omap_hwmod *oh) _set_master_standbymode(oh, idlemode, &v); } - _write_sysconfig(v, oh); + /* If the cached value is the same as the new value, skip the write */ + if (oh->_sysc_cache != v) + _write_sysconfig(v, oh); } /** @@ -2200,6 +2200,11 @@ static int _enable(struct omap_hwmod *oh) */ static int _idle(struct omap_hwmod *oh) { + if (oh->flags & HWMOD_NO_IDLE) { + oh->_int_flags |= _HWMOD_SKIP_ENABLE; + return 0; + } + pr_debug("omap_hwmod: %s: idling\n", oh->name); if (oh->_state != _HWMOD_STATE_ENABLED) { @@ -2504,6 +2509,8 @@ static int __init _init(struct omap_hwmod *oh, void *data) oh->flags |= HWMOD_INIT_NO_RESET; if (of_find_property(np, "ti,no-idle-on-init", NULL)) oh->flags |= HWMOD_INIT_NO_IDLE; + if (of_find_property(np, "ti,no-idle", NULL)) + oh->flags |= HWMOD_NO_IDLE; } oh->_state = _HWMOD_STATE_INITIALIZED; @@ -2630,7 +2637,7 @@ static void __init _setup_postsetup(struct omap_hwmod *oh) * XXX HWMOD_INIT_NO_IDLE does not belong in hwmod data - * it should be set by the core code as a runtime flag during startup */ - if ((oh->flags & HWMOD_INIT_NO_IDLE) && + if ((oh->flags & (HWMOD_INIT_NO_IDLE | HWMOD_NO_IDLE)) && (postsetup_state == _HWMOD_STATE_IDLE)) { oh->_int_flags |= _HWMOD_SKIP_ENABLE; postsetup_state = _HWMOD_STATE_ENABLED; diff --git a/arch/arm/mach-omap2/omap_hwmod.h b/arch/arm/mach-omap2/omap_hwmod.h index 76bce11c85a4..7c7a31169475 100644 --- a/arch/arm/mach-omap2/omap_hwmod.h +++ b/arch/arm/mach-omap2/omap_hwmod.h @@ -525,6 +525,8 @@ struct omap_hwmod_omap4_prcm { * or idled. * HWMOD_OPT_CLKS_NEEDED: The optional clocks are needed for the module to * operate and they need to be handled at the same time as the main_clk. + * HWMOD_NO_IDLE: Do not idle the hwmod at all. Useful to handle certain + * IPs like CPSW on DRA7, where clocks to this module cannot be disabled. */ #define HWMOD_SWSUP_SIDLE (1 << 0) #define HWMOD_SWSUP_MSTANDBY (1 << 1) @@ -541,6 +543,7 @@ struct omap_hwmod_omap4_prcm { #define HWMOD_SWSUP_SIDLE_ACT (1 << 12) #define HWMOD_RECONFIG_IO_CHAIN (1 << 13) #define HWMOD_OPT_CLKS_NEEDED (1 << 14) +#define HWMOD_NO_IDLE (1 << 15) /* * omap_hwmod._int_flags definitions diff --git a/arch/arm/mach-prima2/Kconfig b/arch/arm/mach-prima2/Kconfig index 9ab8932403e5..56e55fd37d13 100644 --- a/arch/arm/mach-prima2/Kconfig +++ b/arch/arm/mach-prima2/Kconfig @@ -1,6 +1,7 @@ menuconfig ARCH_SIRF bool "CSR SiRF" if ARCH_MULTI_V7 select ARCH_HAS_RESET_CONTROLLER + select RESET_CONTROLLER select ARCH_REQUIRE_GPIOLIB select GENERIC_IRQ_CHIP select NO_IOPORT_MAP diff --git a/arch/arm/mach-s3c64xx/dev-audio.c b/arch/arm/mach-s3c64xx/dev-audio.c index ff780a8d8366..9a42736ef4ac 100644 --- a/arch/arm/mach-s3c64xx/dev-audio.c +++ b/arch/arm/mach-s3c64xx/dev-audio.c @@ -54,12 +54,12 @@ static int s3c64xx_i2s_cfg_gpio(struct platform_device *pdev) static struct resource s3c64xx_iis0_resource[] = { [0] = DEFINE_RES_MEM(S3C64XX_PA_IIS0, SZ_256), - [1] = DEFINE_RES_DMA(DMACH_I2S0_OUT), - [2] = DEFINE_RES_DMA(DMACH_I2S0_IN), }; -static struct s3c_audio_pdata i2sv3_pdata = { +static struct s3c_audio_pdata i2s0_pdata = { .cfg_gpio = s3c64xx_i2s_cfg_gpio, + .dma_playback = DMACH_I2S0_OUT, + .dma_capture = DMACH_I2S0_IN, }; struct platform_device s3c64xx_device_iis0 = { @@ -68,15 +68,19 @@ struct platform_device s3c64xx_device_iis0 = { .num_resources = ARRAY_SIZE(s3c64xx_iis0_resource), .resource = s3c64xx_iis0_resource, .dev = { - .platform_data = &i2sv3_pdata, + .platform_data = &i2s0_pdata, }, }; EXPORT_SYMBOL(s3c64xx_device_iis0); static struct resource s3c64xx_iis1_resource[] = { [0] = DEFINE_RES_MEM(S3C64XX_PA_IIS1, SZ_256), - [1] = DEFINE_RES_DMA(DMACH_I2S1_OUT), - [2] = DEFINE_RES_DMA(DMACH_I2S1_IN), +}; + +static struct s3c_audio_pdata i2s1_pdata = { + .cfg_gpio = s3c64xx_i2s_cfg_gpio, + .dma_playback = DMACH_I2S1_OUT, + .dma_capture = DMACH_I2S1_IN, }; struct platform_device s3c64xx_device_iis1 = { @@ -85,19 +89,19 @@ struct platform_device s3c64xx_device_iis1 = { .num_resources = ARRAY_SIZE(s3c64xx_iis1_resource), .resource = s3c64xx_iis1_resource, .dev = { - .platform_data = &i2sv3_pdata, + .platform_data = &i2s1_pdata, }, }; EXPORT_SYMBOL(s3c64xx_device_iis1); static struct resource s3c64xx_iisv4_resource[] = { [0] = DEFINE_RES_MEM(S3C64XX_PA_IISV4, SZ_256), - [1] = DEFINE_RES_DMA(DMACH_HSI_I2SV40_TX), - [2] = DEFINE_RES_DMA(DMACH_HSI_I2SV40_RX), }; static struct s3c_audio_pdata i2sv4_pdata = { .cfg_gpio = s3c64xx_i2s_cfg_gpio, + .dma_playback = DMACH_HSI_I2SV40_TX, + .dma_capture = DMACH_HSI_I2SV40_RX, .type = { .i2s = { .quirks = QUIRK_PRI_6CHAN, @@ -142,12 +146,12 @@ static int s3c64xx_pcm_cfg_gpio(struct platform_device *pdev) static struct resource s3c64xx_pcm0_resource[] = { [0] = DEFINE_RES_MEM(S3C64XX_PA_PCM0, SZ_256), - [1] = DEFINE_RES_DMA(DMACH_PCM0_TX), - [2] = DEFINE_RES_DMA(DMACH_PCM0_RX), }; static struct s3c_audio_pdata s3c_pcm0_pdata = { .cfg_gpio = s3c64xx_pcm_cfg_gpio, + .dma_capture = DMACH_PCM0_RX, + .dma_playback = DMACH_PCM0_TX, }; struct platform_device s3c64xx_device_pcm0 = { @@ -163,12 +167,12 @@ EXPORT_SYMBOL(s3c64xx_device_pcm0); static struct resource s3c64xx_pcm1_resource[] = { [0] = DEFINE_RES_MEM(S3C64XX_PA_PCM1, SZ_256), - [1] = DEFINE_RES_DMA(DMACH_PCM1_TX), - [2] = DEFINE_RES_DMA(DMACH_PCM1_RX), }; static struct s3c_audio_pdata s3c_pcm1_pdata = { .cfg_gpio = s3c64xx_pcm_cfg_gpio, + .dma_playback = DMACH_PCM1_TX, + .dma_capture = DMACH_PCM1_RX, }; struct platform_device s3c64xx_device_pcm1 = { @@ -196,13 +200,14 @@ static int s3c64xx_ac97_cfg_gpe(struct platform_device *pdev) static struct resource s3c64xx_ac97_resource[] = { [0] = DEFINE_RES_MEM(S3C64XX_PA_AC97, SZ_256), - [1] = DEFINE_RES_DMA(DMACH_AC97_PCMOUT), - [2] = DEFINE_RES_DMA(DMACH_AC97_PCMIN), - [3] = DEFINE_RES_DMA(DMACH_AC97_MICIN), - [4] = DEFINE_RES_IRQ(IRQ_AC97), + [1] = DEFINE_RES_IRQ(IRQ_AC97), }; -static struct s3c_audio_pdata s3c_ac97_pdata; +static struct s3c_audio_pdata s3c_ac97_pdata = { + .dma_playback = DMACH_AC97_PCMOUT, + .dma_capture = DMACH_AC97_PCMIN, + .dma_capture_mic = DMACH_AC97_MICIN, +}; static u64 s3c64xx_ac97_dmamask = DMA_BIT_MASK(32); diff --git a/arch/arm/mach-s3c64xx/include/mach/dma.h b/arch/arm/mach-s3c64xx/include/mach/dma.h index 096e14073bd9..9c739eafe95c 100644 --- a/arch/arm/mach-s3c64xx/include/mach/dma.h +++ b/arch/arm/mach-s3c64xx/include/mach/dma.h @@ -14,38 +14,38 @@ #define S3C64XX_DMA_CHAN(name) ((unsigned long)(name)) /* DMA0/SDMA0 */ -#define DMACH_UART0 S3C64XX_DMA_CHAN("uart0_tx") -#define DMACH_UART0_SRC2 S3C64XX_DMA_CHAN("uart0_rx") -#define DMACH_UART1 S3C64XX_DMA_CHAN("uart1_tx") -#define DMACH_UART1_SRC2 S3C64XX_DMA_CHAN("uart1_rx") -#define DMACH_UART2 S3C64XX_DMA_CHAN("uart2_tx") -#define DMACH_UART2_SRC2 S3C64XX_DMA_CHAN("uart2_rx") -#define DMACH_UART3 S3C64XX_DMA_CHAN("uart3_tx") -#define DMACH_UART3_SRC2 S3C64XX_DMA_CHAN("uart3_rx") -#define DMACH_PCM0_TX S3C64XX_DMA_CHAN("pcm0_tx") -#define DMACH_PCM0_RX S3C64XX_DMA_CHAN("pcm0_rx") -#define DMACH_I2S0_OUT S3C64XX_DMA_CHAN("i2s0_tx") -#define DMACH_I2S0_IN S3C64XX_DMA_CHAN("i2s0_rx") +#define DMACH_UART0 "uart0_tx" +#define DMACH_UART0_SRC2 "uart0_rx" +#define DMACH_UART1 "uart1_tx" +#define DMACH_UART1_SRC2 "uart1_rx" +#define DMACH_UART2 "uart2_tx" +#define DMACH_UART2_SRC2 "uart2_rx" +#define DMACH_UART3 "uart3_tx" +#define DMACH_UART3_SRC2 "uart3_rx" +#define DMACH_PCM0_TX "pcm0_tx" +#define DMACH_PCM0_RX "pcm0_rx" +#define DMACH_I2S0_OUT "i2s0_tx" +#define DMACH_I2S0_IN "i2s0_rx" #define DMACH_SPI0_TX S3C64XX_DMA_CHAN("spi0_tx") #define DMACH_SPI0_RX S3C64XX_DMA_CHAN("spi0_rx") -#define DMACH_HSI_I2SV40_TX S3C64XX_DMA_CHAN("i2s2_tx") -#define DMACH_HSI_I2SV40_RX S3C64XX_DMA_CHAN("i2s2_rx") +#define DMACH_HSI_I2SV40_TX "i2s2_tx" +#define DMACH_HSI_I2SV40_RX "i2s2_rx" /* DMA1/SDMA1 */ -#define DMACH_PCM1_TX S3C64XX_DMA_CHAN("pcm1_tx") -#define DMACH_PCM1_RX S3C64XX_DMA_CHAN("pcm1_rx") -#define DMACH_I2S1_OUT S3C64XX_DMA_CHAN("i2s1_tx") -#define DMACH_I2S1_IN S3C64XX_DMA_CHAN("i2s1_rx") +#define DMACH_PCM1_TX "pcm1_tx" +#define DMACH_PCM1_RX "pcm1_rx" +#define DMACH_I2S1_OUT "i2s1_tx" +#define DMACH_I2S1_IN "i2s1_rx" #define DMACH_SPI1_TX S3C64XX_DMA_CHAN("spi1_tx") #define DMACH_SPI1_RX S3C64XX_DMA_CHAN("spi1_rx") -#define DMACH_AC97_PCMOUT S3C64XX_DMA_CHAN("ac97_out") -#define DMACH_AC97_PCMIN S3C64XX_DMA_CHAN("ac97_in") -#define DMACH_AC97_MICIN S3C64XX_DMA_CHAN("ac97_mic") -#define DMACH_PWM S3C64XX_DMA_CHAN("pwm") -#define DMACH_IRDA S3C64XX_DMA_CHAN("irda") -#define DMACH_EXTERNAL S3C64XX_DMA_CHAN("external") -#define DMACH_SECURITY_RX S3C64XX_DMA_CHAN("sec_rx") -#define DMACH_SECURITY_TX S3C64XX_DMA_CHAN("sec_tx") +#define DMACH_AC97_PCMOUT "ac97_out" +#define DMACH_AC97_PCMIN "ac97_in" +#define DMACH_AC97_MICIN "ac97_mic" +#define DMACH_PWM "pwm" +#define DMACH_IRDA "irda" +#define DMACH_EXTERNAL "external" +#define DMACH_SECURITY_RX "sec_rx" +#define DMACH_SECURITY_TX "sec_tx" enum dma_ch { DMACH_MAX = 32 diff --git a/arch/arm/mach-socfpga/headsmp.S b/arch/arm/mach-socfpga/headsmp.S index 5d94b7a2fb10..c160fa3007e9 100644 --- a/arch/arm/mach-socfpga/headsmp.S +++ b/arch/arm/mach-socfpga/headsmp.S @@ -13,6 +13,7 @@ #include <asm/assembler.h> .arch armv7-a + .arm ENTRY(secondary_trampoline) /* CPU1 will always fetch from 0x0 when it is brought out of reset. diff --git a/arch/arm/plat-samsung/devs.c b/arch/arm/plat-samsung/devs.c index 82074625de5c..e212f9d804bd 100644 --- a/arch/arm/plat-samsung/devs.c +++ b/arch/arm/plat-samsung/devs.c @@ -65,6 +65,7 @@ #include <linux/platform_data/usb-ohci-s3c2410.h> #include <plat/usb-phy.h> #include <plat/regs-spi.h> +#include <linux/platform_data/asoc-s3c.h> #include <linux/platform_data/spi-s3c64xx.h> static u64 samsung_device_dma_mask = DMA_BIT_MASK(32); @@ -74,9 +75,12 @@ static u64 samsung_device_dma_mask = DMA_BIT_MASK(32); static struct resource s3c_ac97_resource[] = { [0] = DEFINE_RES_MEM(S3C2440_PA_AC97, S3C2440_SZ_AC97), [1] = DEFINE_RES_IRQ(IRQ_S3C244X_AC97), - [2] = DEFINE_RES_DMA_NAMED(DMACH_PCM_OUT, "PCM out"), - [3] = DEFINE_RES_DMA_NAMED(DMACH_PCM_IN, "PCM in"), - [4] = DEFINE_RES_DMA_NAMED(DMACH_MIC_IN, "Mic in"), +}; + +static struct s3c_audio_pdata s3c_ac97_pdata = { + .dma_playback = (void *)DMACH_PCM_OUT, + .dma_capture = (void *)DMACH_PCM_IN, + .dma_capture_mic = (void *)DMACH_MIC_IN, }; struct platform_device s3c_device_ac97 = { @@ -87,6 +91,7 @@ struct platform_device s3c_device_ac97 = { .dev = { .dma_mask = &samsung_device_dma_mask, .coherent_dma_mask = DMA_BIT_MASK(32), + .platform_data = &s3c_ac97_pdata, } }; #endif /* CONFIG_CPU_S3C2440 */ diff --git a/arch/arm64/include/asm/opcodes.h b/arch/arm64/include/asm/opcodes.h index 4e603ea36ad3..123f45d92cd1 100644 --- a/arch/arm64/include/asm/opcodes.h +++ b/arch/arm64/include/asm/opcodes.h @@ -1 +1,5 @@ +#ifdef CONFIG_CPU_BIG_ENDIAN +#define CONFIG_CPU_ENDIAN_BE8 CONFIG_CPU_BIG_ENDIAN +#endif + #include <../../arm/include/asm/opcodes.h> diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index d6739e836f7b..b9da9545b442 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -117,7 +117,6 @@ * Section */ #define PMD_SECT_VALID (_AT(pmdval_t, 1) << 0) -#define PMD_SECT_PROT_NONE (_AT(pmdval_t, 1) << 58) #define PMD_SECT_USER (_AT(pmdval_t, 1) << 6) /* AP[1] */ #define PMD_SECT_RDONLY (_AT(pmdval_t, 1) << 7) /* AP[2] */ #define PMD_SECT_S (_AT(pmdval_t, 3) << 8) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index fc9f7ef2f4ab..67c2ad6d33b7 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -40,7 +40,7 @@ * VMALLOC_END: extends to the available space below vmmemmap, PCI I/O space, * fixed mappings and modules */ -#define VMEMMAP_SIZE ALIGN((1UL << (VA_BITS - PAGE_SHIFT - 1)) * sizeof(struct page), PUD_SIZE) +#define VMEMMAP_SIZE ALIGN((1UL << (VA_BITS - PAGE_SHIFT)) * sizeof(struct page), PUD_SIZE) #ifndef CONFIG_KASAN #define VMALLOC_START (VA_START) @@ -52,7 +52,8 @@ #define VMALLOC_END (PAGE_OFFSET - PUD_SIZE - VMEMMAP_SIZE - SZ_64K) #define VMEMMAP_START (VMALLOC_END + SZ_64K) -#define vmemmap ((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT)) +#define vmemmap ((struct page *)VMEMMAP_START - \ + SECTION_ALIGN_DOWN(memstart_addr >> PAGE_SHIFT)) #define FIRST_USER_ADDRESS 0UL @@ -68,11 +69,11 @@ extern void __pgd_error(const char *file, int line, unsigned long val); #define PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED) #define PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S) -#define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRnE)) -#define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRE)) -#define PROT_NORMAL_NC (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL_NC)) -#define PROT_NORMAL_WT (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL_WT)) -#define PROT_NORMAL (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL)) +#define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE)) +#define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE)) +#define PROT_NORMAL_NC (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_NC)) +#define PROT_NORMAL_WT (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_WT)) +#define PROT_NORMAL (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL)) #define PROT_SECT_DEVICE_nGnRE (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE)) #define PROT_SECT_NORMAL (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL)) @@ -82,7 +83,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val); #define PAGE_KERNEL __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE) #define PAGE_KERNEL_RO __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_RDONLY) -#define PAGE_KERNEL_ROX __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY) +#define PAGE_KERNEL_ROX __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY) #define PAGE_KERNEL_EXEC __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE) #define PAGE_KERNEL_EXEC_CONT __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_CONT) @@ -154,6 +155,7 @@ extern struct page *empty_zero_page; #define pte_write(pte) (!!(pte_val(pte) & PTE_WRITE)) #define pte_exec(pte) (!(pte_val(pte) & PTE_UXN)) #define pte_cont(pte) (!!(pte_val(pte) & PTE_CONT)) +#define pte_user(pte) (!!(pte_val(pte) & PTE_USER)) #ifdef CONFIG_ARM64_HW_AFDBM #define pte_hw_dirty(pte) (pte_write(pte) && !(pte_val(pte) & PTE_RDONLY)) @@ -164,8 +166,6 @@ extern struct page *empty_zero_page; #define pte_dirty(pte) (pte_sw_dirty(pte) || pte_hw_dirty(pte)) #define pte_valid(pte) (!!(pte_val(pte) & PTE_VALID)) -#define pte_valid_user(pte) \ - ((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER)) #define pte_valid_not_user(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID) @@ -263,13 +263,13 @@ extern void __sync_icache_dcache(pte_t pteval, unsigned long addr); static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { - if (pte_valid_user(pte)) { - if (!pte_special(pte) && pte_exec(pte)) - __sync_icache_dcache(pte, addr); + if (pte_present(pte)) { if (pte_sw_dirty(pte) && pte_write(pte)) pte_val(pte) &= ~PTE_RDONLY; else pte_val(pte) |= PTE_RDONLY; + if (pte_user(pte) && pte_exec(pte) && !pte_special(pte)) + __sync_icache_dcache(pte, addr); } /* @@ -347,6 +347,7 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address, #endif /* CONFIG_HAVE_RCU_TABLE_FREE */ #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#define pmd_present(pmd) pte_present(pmd_pte(pmd)) #define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd)) #define pmd_young(pmd) pte_young(pmd_pte(pmd)) #define pmd_wrprotect(pmd) pte_pmd(pte_wrprotect(pmd_pte(pmd))) @@ -355,7 +356,7 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address, #define pmd_mkwrite(pmd) pte_pmd(pte_mkwrite(pmd_pte(pmd))) #define pmd_mkdirty(pmd) pte_pmd(pte_mkdirty(pmd_pte(pmd))) #define pmd_mkyoung(pmd) pte_pmd(pte_mkyoung(pmd_pte(pmd))) -#define pmd_mknotpresent(pmd) (__pmd(pmd_val(pmd) & ~PMD_TYPE_MASK)) +#define pmd_mknotpresent(pmd) (__pmd(pmd_val(pmd) & ~PMD_SECT_VALID)) #define __HAVE_ARCH_PMD_WRITE #define pmd_write(pmd) pte_write(pmd_pte(pmd)) @@ -394,7 +395,6 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot); #define pmd_none(pmd) (!pmd_val(pmd)) -#define pmd_present(pmd) (pmd_val(pmd)) #define pmd_bad(pmd) (!(pmd_val(pmd) & 2)) @@ -538,6 +538,21 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) } #ifdef CONFIG_ARM64_HW_AFDBM +#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS +extern int ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep, + pte_t entry, int dirty); + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS +static inline int pmdp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp, + pmd_t entry, int dirty) +{ + return ptep_set_access_flags(vma, address, (pte_t *)pmdp, pmd_pte(entry), dirty); +} +#endif + /* * Atomic pte/pmd modifications. */ @@ -590,9 +605,9 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, } #ifdef CONFIG_TRANSPARENT_HUGEPAGE -#define __HAVE_ARCH_PMDP_GET_AND_CLEAR -static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm, - unsigned long address, pmd_t *pmdp) +#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR +static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, + unsigned long address, pmd_t *pmdp) { return pte_pmd(ptep_get_and_clear(mm, address, (pte_t *)pmdp)); } @@ -640,6 +655,7 @@ extern pgd_t idmap_pg_dir[PTRS_PER_PGD]; * bits 0-1: present (must be zero) * bits 2-7: swap type * bits 8-57: swap offset + * bit 58: PTE_PROT_NONE (must be zero) */ #define __SWP_TYPE_SHIFT 2 #define __SWP_TYPE_BITS 6 diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 212ae6361d8b..a5f234039616 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -85,7 +85,8 @@ static const char *const compat_hwcap_str[] = { "idivt", "vfpd32", "lpae", - "evtstrm" + "evtstrm", + NULL }; static const char *const compat_hwcap2_str[] = { diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c index 8aee3aeec3e6..c1492ba1f6d1 100644 --- a/arch/arm64/kernel/debug-monitors.c +++ b/arch/arm64/kernel/debug-monitors.c @@ -186,20 +186,21 @@ static void clear_regs_spsr_ss(struct pt_regs *regs) /* EL1 Single Step Handler hooks */ static LIST_HEAD(step_hook); -static DEFINE_RWLOCK(step_hook_lock); +static DEFINE_SPINLOCK(step_hook_lock); void register_step_hook(struct step_hook *hook) { - write_lock(&step_hook_lock); - list_add(&hook->node, &step_hook); - write_unlock(&step_hook_lock); + spin_lock(&step_hook_lock); + list_add_rcu(&hook->node, &step_hook); + spin_unlock(&step_hook_lock); } void unregister_step_hook(struct step_hook *hook) { - write_lock(&step_hook_lock); - list_del(&hook->node); - write_unlock(&step_hook_lock); + spin_lock(&step_hook_lock); + list_del_rcu(&hook->node); + spin_unlock(&step_hook_lock); + synchronize_rcu(); } /* @@ -213,15 +214,15 @@ static int call_step_hook(struct pt_regs *regs, unsigned int esr) struct step_hook *hook; int retval = DBG_HOOK_ERROR; - read_lock(&step_hook_lock); + rcu_read_lock(); - list_for_each_entry(hook, &step_hook, node) { + list_for_each_entry_rcu(hook, &step_hook, node) { retval = hook->fn(regs, esr); if (retval == DBG_HOOK_HANDLED) break; } - read_unlock(&step_hook_lock); + rcu_read_unlock(); return retval; } diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c index 648112e90ed5..3972e65fbd5a 100644 --- a/arch/arm64/kvm/inject_fault.c +++ b/arch/arm64/kvm/inject_fault.c @@ -130,7 +130,7 @@ static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr esr |= (ESR_ELx_EC_IABT_CUR << ESR_ELx_EC_SHIFT); if (!is_iabt) - esr |= ESR_ELx_EC_DABT_LOW; + esr |= ESR_ELx_EC_DABT_LOW << ESR_ELx_EC_SHIFT; vcpu_sys_reg(vcpu, ESR_EL1) = esr | ESR_ELx_FSC_EXTABT; } diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 92ddac1e8ca2..40f5522245a2 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -81,6 +81,56 @@ void show_pte(struct mm_struct *mm, unsigned long addr) printk("\n"); } +#ifdef CONFIG_ARM64_HW_AFDBM +/* + * This function sets the access flags (dirty, accessed), as well as write + * permission, and only to a more permissive setting. + * + * It needs to cope with hardware update of the accessed/dirty state by other + * agents in the system and can safely skip the __sync_icache_dcache() call as, + * like set_pte_at(), the PTE is never changed from no-exec to exec here. + * + * Returns whether or not the PTE actually changed. + */ +int ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep, + pte_t entry, int dirty) +{ + pteval_t old_pteval; + unsigned int tmp; + + if (pte_same(*ptep, entry)) + return 0; + + /* only preserve the access flags and write permission */ + pte_val(entry) &= PTE_AF | PTE_WRITE | PTE_DIRTY; + + /* + * PTE_RDONLY is cleared by default in the asm below, so set it in + * back if necessary (read-only or clean PTE). + */ + if (!pte_write(entry) || !dirty) + pte_val(entry) |= PTE_RDONLY; + + /* + * Setting the flags must be done atomically to avoid racing with the + * hardware update of the access/dirty state. + */ + asm volatile("// ptep_set_access_flags\n" + " prfm pstl1strm, %2\n" + "1: ldxr %0, %2\n" + " and %0, %0, %3 // clear PTE_RDONLY\n" + " orr %0, %0, %4 // set flags\n" + " stxr %w1, %0, %2\n" + " cbnz %w1, 1b\n" + : "=&r" (old_pteval), "=&r" (tmp), "+Q" (pte_val(*ptep)) + : "L" (~PTE_RDONLY), "r" (pte_val(entry))); + + flush_tlb_fix_spurious_fault(vma, address); + return 1; +} +#endif + /* * The kernel tried to access some page that wasn't present. */ diff --git a/arch/ia64/include/asm/io.h b/arch/ia64/include/asm/io.h index 9041bbe2b7b4..8fdb9c7eeb66 100644 --- a/arch/ia64/include/asm/io.h +++ b/arch/ia64/include/asm/io.h @@ -436,6 +436,7 @@ static inline void __iomem * ioremap_cache (unsigned long phys_addr, unsigned lo return ioremap(phys_addr, size); } #define ioremap_cache ioremap_cache +#define ioremap_uc ioremap_nocache /* diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 71683a853372..db459612de44 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -2155,7 +2155,7 @@ config MIPS_MT_SMP select CPU_MIPSR2_IRQ_VI select CPU_MIPSR2_IRQ_EI select SYNC_R4K - select MIPS_GIC_IPI + select MIPS_GIC_IPI if MIPS_GIC select MIPS_MT select SMP select SMP_UP @@ -2253,7 +2253,7 @@ config MIPS_VPE_APSP_API_MT config MIPS_CMP bool "MIPS CMP framework support (DEPRECATED)" depends on SYS_SUPPORTS_MIPS_CMP && !CPU_MIPSR6 - select MIPS_GIC_IPI + select MIPS_GIC_IPI if MIPS_GIC select SMP select SYNC_R4K select SYS_SUPPORTS_SMP @@ -2273,7 +2273,7 @@ config MIPS_CPS select MIPS_CM select MIPS_CPC select MIPS_CPS_PM if HOTPLUG_CPU - select MIPS_GIC_IPI + select MIPS_GIC_IPI if MIPS_GIC select SMP select SYNC_R4K if (CEVT_R4K || CSRC_R4K) select SYS_SUPPORTS_HOTPLUG_CPU @@ -2292,6 +2292,7 @@ config MIPS_CPS_PM bool config MIPS_GIC_IPI + depends on MIPS_GIC bool config MIPS_CM diff --git a/arch/mips/alchemy/devboards/db1000.c b/arch/mips/alchemy/devboards/db1000.c index bdeed9d13c6f..433c4b9a9f0a 100644 --- a/arch/mips/alchemy/devboards/db1000.c +++ b/arch/mips/alchemy/devboards/db1000.c @@ -503,15 +503,15 @@ int __init db1000_dev_setup(void) if (board == BCSR_WHOAMI_DB1500) { c0 = AU1500_GPIO2_INT; c1 = AU1500_GPIO5_INT; - d0 = AU1500_GPIO0_INT; - d1 = AU1500_GPIO3_INT; + d0 = 0; /* GPIO number, NOT irq! */ + d1 = 3; /* GPIO number, NOT irq! */ s0 = AU1500_GPIO1_INT; s1 = AU1500_GPIO4_INT; } else if (board == BCSR_WHOAMI_DB1100) { c0 = AU1100_GPIO2_INT; c1 = AU1100_GPIO5_INT; - d0 = AU1100_GPIO0_INT; - d1 = AU1100_GPIO3_INT; + d0 = 0; /* GPIO number, NOT irq! */ + d1 = 3; /* GPIO number, NOT irq! */ s0 = AU1100_GPIO1_INT; s1 = AU1100_GPIO4_INT; @@ -545,15 +545,15 @@ int __init db1000_dev_setup(void) } else if (board == BCSR_WHOAMI_DB1000) { c0 = AU1000_GPIO2_INT; c1 = AU1000_GPIO5_INT; - d0 = AU1000_GPIO0_INT; - d1 = AU1000_GPIO3_INT; + d0 = 0; /* GPIO number, NOT irq! */ + d1 = 3; /* GPIO number, NOT irq! */ s0 = AU1000_GPIO1_INT; s1 = AU1000_GPIO4_INT; platform_add_devices(db1000_devs, ARRAY_SIZE(db1000_devs)); } else if ((board == BCSR_WHOAMI_PB1500) || (board == BCSR_WHOAMI_PB1500R2)) { c0 = AU1500_GPIO203_INT; - d0 = AU1500_GPIO201_INT; + d0 = 1; /* GPIO number, NOT irq! */ s0 = AU1500_GPIO202_INT; twosocks = 0; flashsize = 64; @@ -566,7 +566,7 @@ int __init db1000_dev_setup(void) */ } else if (board == BCSR_WHOAMI_PB1100) { c0 = AU1100_GPIO11_INT; - d0 = AU1100_GPIO9_INT; + d0 = 9; /* GPIO number, NOT irq! */ s0 = AU1100_GPIO10_INT; twosocks = 0; flashsize = 64; @@ -583,7 +583,6 @@ int __init db1000_dev_setup(void) } else return 0; /* unknown board, no further dev setup to do */ - irq_set_irq_type(d0, IRQ_TYPE_EDGE_BOTH); irq_set_irq_type(c0, IRQ_TYPE_LEVEL_LOW); irq_set_irq_type(s0, IRQ_TYPE_LEVEL_LOW); @@ -597,7 +596,6 @@ int __init db1000_dev_setup(void) c0, d0, /*s0*/0, 0, 0); if (twosocks) { - irq_set_irq_type(d1, IRQ_TYPE_EDGE_BOTH); irq_set_irq_type(c1, IRQ_TYPE_LEVEL_LOW); irq_set_irq_type(s1, IRQ_TYPE_LEVEL_LOW); diff --git a/arch/mips/alchemy/devboards/db1550.c b/arch/mips/alchemy/devboards/db1550.c index 5740bcfdfc7f..6c37b9326f41 100644 --- a/arch/mips/alchemy/devboards/db1550.c +++ b/arch/mips/alchemy/devboards/db1550.c @@ -514,7 +514,7 @@ static void __init db1550_devices(void) AU1000_PCMCIA_MEM_PHYS_ADDR + 0x000400000 - 1, AU1000_PCMCIA_IO_PHYS_ADDR, AU1000_PCMCIA_IO_PHYS_ADDR + 0x000010000 - 1, - AU1550_GPIO3_INT, AU1550_GPIO0_INT, + AU1550_GPIO3_INT, 0, /*AU1550_GPIO21_INT*/0, 0, 0); db1x_register_pcmcia_socket( @@ -524,7 +524,7 @@ static void __init db1550_devices(void) AU1000_PCMCIA_MEM_PHYS_ADDR + 0x004400000 - 1, AU1000_PCMCIA_IO_PHYS_ADDR + 0x004000000, AU1000_PCMCIA_IO_PHYS_ADDR + 0x004010000 - 1, - AU1550_GPIO5_INT, AU1550_GPIO1_INT, + AU1550_GPIO5_INT, 1, /*AU1550_GPIO22_INT*/0, 0, 1); platform_device_register(&db1550_nand_dev); diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index 6ded8d347af9..4e956b3e16f5 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -784,7 +784,7 @@ extern enum emulation_result kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu, uint32_t kvm_mips_read_count(struct kvm_vcpu *vcpu); void kvm_mips_write_count(struct kvm_vcpu *vcpu, uint32_t count); -void kvm_mips_write_compare(struct kvm_vcpu *vcpu, uint32_t compare); +void kvm_mips_write_compare(struct kvm_vcpu *vcpu, uint32_t compare, bool ack); void kvm_mips_init_count(struct kvm_vcpu *vcpu); int kvm_mips_set_count_ctl(struct kvm_vcpu *vcpu, s64 count_ctl); int kvm_mips_set_count_resume(struct kvm_vcpu *vcpu, s64 count_resume); diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index bd4385a8e6e8..2b521e07b860 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -121,6 +121,7 @@ static inline void calculate_cpu_foreign_map(void) cpumask_t temp_foreign_map; /* Re-calculate the mask */ + cpumask_clear(&temp_foreign_map); for_each_online_cpu(i) { core_present = 0; for_each_cpu(k, &temp_foreign_map) diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c index 490cea569d57..5c62065cbf22 100644 --- a/arch/mips/kernel/unaligned.c +++ b/arch/mips/kernel/unaligned.c @@ -885,7 +885,7 @@ static void emulate_load_store_insn(struct pt_regs *regs, { union mips_instruction insn; unsigned long value; - unsigned int res; + unsigned int res, preempted; unsigned long origpc; unsigned long orig31; void __user *fault_addr = NULL; @@ -1226,27 +1226,36 @@ static void emulate_load_store_insn(struct pt_regs *regs, if (!access_ok(VERIFY_READ, addr, sizeof(*fpr))) goto sigbus; - /* - * Disable preemption to avoid a race between copying - * state from userland, migrating to another CPU and - * updating the hardware vector register below. - */ - preempt_disable(); - - res = __copy_from_user_inatomic(fpr, addr, - sizeof(*fpr)); - if (res) - goto fault; - - /* - * Update the hardware register if it is in use by the - * task in this quantum, in order to avoid having to - * save & restore the whole vector context. - */ - if (test_thread_flag(TIF_USEDMSA)) - write_msa_wr(wd, fpr, df); + do { + /* + * If we have live MSA context keep track of + * whether we get preempted in order to avoid + * the register context we load being clobbered + * by the live context as it's saved during + * preemption. If we don't have live context + * then it can't be saved to clobber the value + * we load. + */ + preempted = test_thread_flag(TIF_USEDMSA); + + res = __copy_from_user_inatomic(fpr, addr, + sizeof(*fpr)); + if (res) + goto fault; - preempt_enable(); + /* + * Update the hardware register if it is in use + * by the task in this quantum, in order to + * avoid having to save & restore the whole + * vector context. + */ + preempt_disable(); + if (test_thread_flag(TIF_USEDMSA)) { + write_msa_wr(wd, fpr, df); + preempted = 0; + } + preempt_enable(); + } while (preempted); break; case msa_st_op: diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index 41b1b090f56f..dc10c77b7500 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -302,12 +302,31 @@ static inline ktime_t kvm_mips_count_time(struct kvm_vcpu *vcpu) */ static uint32_t kvm_mips_read_count_running(struct kvm_vcpu *vcpu, ktime_t now) { - ktime_t expires; + struct mips_coproc *cop0 = vcpu->arch.cop0; + ktime_t expires, threshold; + uint32_t count, compare; int running; - /* Is the hrtimer pending? */ + /* Calculate the biased and scaled guest CP0_Count */ + count = vcpu->arch.count_bias + kvm_mips_ktime_to_count(vcpu, now); + compare = kvm_read_c0_guest_compare(cop0); + + /* + * Find whether CP0_Count has reached the closest timer interrupt. If + * not, we shouldn't inject it. + */ + if ((int32_t)(count - compare) < 0) + return count; + + /* + * The CP0_Count we're going to return has already reached the closest + * timer interrupt. Quickly check if it really is a new interrupt by + * looking at whether the interval until the hrtimer expiry time is + * less than 1/4 of the timer period. + */ expires = hrtimer_get_expires(&vcpu->arch.comparecount_timer); - if (ktime_compare(now, expires) >= 0) { + threshold = ktime_add_ns(now, vcpu->arch.count_period / 4); + if (ktime_before(expires, threshold)) { /* * Cancel it while we handle it so there's no chance of * interference with the timeout handler. @@ -329,8 +348,7 @@ static uint32_t kvm_mips_read_count_running(struct kvm_vcpu *vcpu, ktime_t now) } } - /* Return the biased and scaled guest CP0_Count */ - return vcpu->arch.count_bias + kvm_mips_ktime_to_count(vcpu, now); + return count; } /** @@ -420,32 +438,6 @@ static void kvm_mips_resume_hrtimer(struct kvm_vcpu *vcpu, } /** - * kvm_mips_update_hrtimer() - Update next expiry time of hrtimer. - * @vcpu: Virtual CPU. - * - * Recalculates and updates the expiry time of the hrtimer. This can be used - * after timer parameters have been altered which do not depend on the time that - * the change occurs (in those cases kvm_mips_freeze_hrtimer() and - * kvm_mips_resume_hrtimer() are used directly). - * - * It is guaranteed that no timer interrupts will be lost in the process. - * - * Assumes !kvm_mips_count_disabled(@vcpu) (guest CP0_Count timer is running). - */ -static void kvm_mips_update_hrtimer(struct kvm_vcpu *vcpu) -{ - ktime_t now; - uint32_t count; - - /* - * freeze_hrtimer takes care of a timer interrupts <= count, and - * resume_hrtimer the hrtimer takes care of a timer interrupts > count. - */ - now = kvm_mips_freeze_hrtimer(vcpu, &count); - kvm_mips_resume_hrtimer(vcpu, now, count); -} - -/** * kvm_mips_write_count() - Modify the count and update timer. * @vcpu: Virtual CPU. * @count: Guest CP0_Count value to set. @@ -540,23 +532,42 @@ int kvm_mips_set_count_hz(struct kvm_vcpu *vcpu, s64 count_hz) * kvm_mips_write_compare() - Modify compare and update timer. * @vcpu: Virtual CPU. * @compare: New CP0_Compare value. + * @ack: Whether to acknowledge timer interrupt. * * Update CP0_Compare to a new value and update the timeout. + * If @ack, atomically acknowledge any pending timer interrupt, otherwise ensure + * any pending timer interrupt is preserved. */ -void kvm_mips_write_compare(struct kvm_vcpu *vcpu, uint32_t compare) +void kvm_mips_write_compare(struct kvm_vcpu *vcpu, uint32_t compare, bool ack) { struct mips_coproc *cop0 = vcpu->arch.cop0; + int dc; + u32 old_compare = kvm_read_c0_guest_compare(cop0); + ktime_t now; + uint32_t count; /* if unchanged, must just be an ack */ - if (kvm_read_c0_guest_compare(cop0) == compare) + if (old_compare == compare) { + if (!ack) + return; + kvm_mips_callbacks->dequeue_timer_int(vcpu); + kvm_write_c0_guest_compare(cop0, compare); return; + } + + /* freeze_hrtimer() takes care of timer interrupts <= count */ + dc = kvm_mips_count_disabled(vcpu); + if (!dc) + now = kvm_mips_freeze_hrtimer(vcpu, &count); + + if (ack) + kvm_mips_callbacks->dequeue_timer_int(vcpu); - /* Update compare */ kvm_write_c0_guest_compare(cop0, compare); - /* Update timeout if count enabled */ - if (!kvm_mips_count_disabled(vcpu)) - kvm_mips_update_hrtimer(vcpu); + /* resume_hrtimer() takes care of timer interrupts > count */ + if (!dc) + kvm_mips_resume_hrtimer(vcpu, now, count); } /** @@ -1095,9 +1106,9 @@ enum emulation_result kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc, /* If we are writing to COMPARE */ /* Clear pending timer interrupt, if any */ - kvm_mips_callbacks->dequeue_timer_int(vcpu); kvm_mips_write_compare(vcpu, - vcpu->arch.gprs[rt]); + vcpu->arch.gprs[rt], + true); } else if ((rd == MIPS_CP0_STATUS) && (sel == 0)) { unsigned int old_val, val, change; diff --git a/arch/mips/kvm/trap_emul.c b/arch/mips/kvm/trap_emul.c index d836ed5b0bc7..307cc4c98bdd 100644 --- a/arch/mips/kvm/trap_emul.c +++ b/arch/mips/kvm/trap_emul.c @@ -547,7 +547,7 @@ static int kvm_trap_emul_set_one_reg(struct kvm_vcpu *vcpu, kvm_mips_write_count(vcpu, v); break; case KVM_REG_MIPS_CP0_COMPARE: - kvm_mips_write_compare(vcpu, v); + kvm_mips_write_compare(vcpu, v, false); break; case KVM_REG_MIPS_CP0_CAUSE: /* diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h index 0abdd4c607ed..1960b87c1c8b 100644 --- a/arch/parisc/include/asm/uaccess.h +++ b/arch/parisc/include/asm/uaccess.h @@ -76,6 +76,7 @@ struct exception_table_entry { */ struct exception_data { unsigned long fault_ip; + unsigned long fault_gp; unsigned long fault_space; unsigned long fault_addr; }; diff --git a/arch/parisc/kernel/asm-offsets.c b/arch/parisc/kernel/asm-offsets.c index d2f62570a7b1..78d30d2ea2d8 100644 --- a/arch/parisc/kernel/asm-offsets.c +++ b/arch/parisc/kernel/asm-offsets.c @@ -299,6 +299,7 @@ int main(void) #endif BLANK(); DEFINE(EXCDATA_IP, offsetof(struct exception_data, fault_ip)); + DEFINE(EXCDATA_GP, offsetof(struct exception_data, fault_gp)); DEFINE(EXCDATA_SPACE, offsetof(struct exception_data, fault_space)); DEFINE(EXCDATA_ADDR, offsetof(struct exception_data, fault_addr)); BLANK(); diff --git a/arch/parisc/kernel/parisc_ksyms.c b/arch/parisc/kernel/parisc_ksyms.c index 568b2c61ea02..3cad8aadc69e 100644 --- a/arch/parisc/kernel/parisc_ksyms.c +++ b/arch/parisc/kernel/parisc_ksyms.c @@ -47,11 +47,11 @@ EXPORT_SYMBOL(__cmpxchg_u64); EXPORT_SYMBOL(lclear_user); EXPORT_SYMBOL(lstrnlen_user); -/* Global fixups */ -extern void fixup_get_user_skip_1(void); -extern void fixup_get_user_skip_2(void); -extern void fixup_put_user_skip_1(void); -extern void fixup_put_user_skip_2(void); +/* Global fixups - defined as int to avoid creation of function pointers */ +extern int fixup_get_user_skip_1; +extern int fixup_get_user_skip_2; +extern int fixup_put_user_skip_1; +extern int fixup_put_user_skip_2; EXPORT_SYMBOL(fixup_get_user_skip_1); EXPORT_SYMBOL(fixup_get_user_skip_2); EXPORT_SYMBOL(fixup_put_user_skip_1); diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index 553b09855cfd..77e2262c97f6 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -798,6 +798,9 @@ void notrace handle_interruption(int code, struct pt_regs *regs) if (fault_space == 0 && !faulthandler_disabled()) { + /* Clean up and return if in exception table. */ + if (fixup_exception(regs)) + return; pdc_chassis_send_status(PDC_CHASSIS_DIRECT_PANIC); parisc_terminate("Kernel Fault", regs, code, fault_address); } diff --git a/arch/parisc/lib/fixup.S b/arch/parisc/lib/fixup.S index 536ef66bb94b..1052b747e011 100644 --- a/arch/parisc/lib/fixup.S +++ b/arch/parisc/lib/fixup.S @@ -26,6 +26,7 @@ #ifdef CONFIG_SMP .macro get_fault_ip t1 t2 + loadgp addil LT%__per_cpu_offset,%r27 LDREG RT%__per_cpu_offset(%r1),\t1 /* t2 = smp_processor_id() */ @@ -40,14 +41,19 @@ LDREG RT%exception_data(%r1),\t1 /* t1 = this_cpu_ptr(&exception_data) */ add,l \t1,\t2,\t1 + /* %r27 = t1->fault_gp - restore gp */ + LDREG EXCDATA_GP(\t1), %r27 /* t1 = t1->fault_ip */ LDREG EXCDATA_IP(\t1), \t1 .endm #else .macro get_fault_ip t1 t2 + loadgp /* t1 = this_cpu_ptr(&exception_data) */ addil LT%exception_data,%r27 LDREG RT%exception_data(%r1),\t2 + /* %r27 = t2->fault_gp - restore gp */ + LDREG EXCDATA_GP(\t2), %r27 /* t1 = t2->fault_ip */ LDREG EXCDATA_IP(\t2), \t1 .endm diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index a762864ec92e..f9064449908a 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -151,6 +151,7 @@ int fixup_exception(struct pt_regs *regs) struct exception_data *d; d = this_cpu_ptr(&exception_data); d->fault_ip = regs->iaoq[0]; + d->fault_gp = regs->gr[27]; d->fault_space = regs->isr; d->fault_addr = regs->ior; diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h index 8374afed9d0a..f8faaaeeca1e 100644 --- a/arch/powerpc/include/asm/opal-api.h +++ b/arch/powerpc/include/asm/opal-api.h @@ -157,7 +157,8 @@ #define OPAL_LEDS_GET_INDICATOR 114 #define OPAL_LEDS_SET_INDICATOR 115 #define OPAL_CEC_REBOOT2 116 -#define OPAL_LAST 116 +#define OPAL_CONSOLE_FLUSH 117 +#define OPAL_LAST 117 /* Device tree flags */ diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 800115910e43..07a99e638449 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -35,6 +35,7 @@ int64_t opal_console_read(int64_t term_number, __be64 *length, uint8_t *buffer); int64_t opal_console_write_buffer_space(int64_t term_number, __be64 *length); +int64_t opal_console_flush(int64_t term_number); int64_t opal_rtc_read(__be32 *year_month_day, __be64 *hour_minute_second_millisecond); int64_t opal_rtc_write(uint32_t year_month_day, @@ -262,6 +263,8 @@ extern int opal_resync_timebase(void); extern void opal_lpc_init(void); +extern void opal_kmsg_init(void); + extern int opal_event_request(unsigned int opal_event_nr); struct opal_sg_list *opal_vmalloc_to_sg_list(void *vmalloc_addr, diff --git a/arch/powerpc/include/asm/word-at-a-time.h b/arch/powerpc/include/asm/word-at-a-time.h index e4396a7d0f7c..4afe66aa1400 100644 --- a/arch/powerpc/include/asm/word-at-a-time.h +++ b/arch/powerpc/include/asm/word-at-a-time.h @@ -82,7 +82,7 @@ static inline unsigned long create_zero_mask(unsigned long bits) "andc %1,%1,%2\n\t" "popcntd %0,%1" : "=r" (leading_zero_bits), "=&r" (trailing_zero_bit_mask) - : "r" (bits)); + : "b" (bits)); return leading_zero_bits; } diff --git a/arch/powerpc/include/uapi/asm/cputable.h b/arch/powerpc/include/uapi/asm/cputable.h index 43686043e297..2734c005da21 100644 --- a/arch/powerpc/include/uapi/asm/cputable.h +++ b/arch/powerpc/include/uapi/asm/cputable.h @@ -31,6 +31,7 @@ #define PPC_FEATURE_PSERIES_PERFMON_COMPAT \ 0x00000040 +/* Reserved - do not use 0x00000004 */ #define PPC_FEATURE_TRUE_LE 0x00000002 #define PPC_FEATURE_PPC_LE 0x00000001 diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 59663af9315f..e4f7d4eed20c 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -335,7 +335,7 @@ static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab) if (syms[i].st_shndx == SHN_UNDEF) { char *name = strtab + syms[i].st_name; if (name[0] == '.') - memmove(name, name+1, strlen(name)); + syms[i].st_name++; } } } diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index ef2ad2d682da..646bf4d222c1 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -569,24 +569,6 @@ static void tm_reclaim_thread(struct thread_struct *thr, if (!MSR_TM_SUSPENDED(mfmsr())) return; - /* - * Use the current MSR TM suspended bit to track if we have - * checkpointed state outstanding. - * On signal delivery, we'd normally reclaim the checkpointed - * state to obtain stack pointer (see:get_tm_stackpointer()). - * This will then directly return to userspace without going - * through __switch_to(). However, if the stack frame is bad, - * we need to exit this thread which calls __switch_to() which - * will again attempt to reclaim the already saved tm state. - * Hence we need to check that we've not already reclaimed - * this state. - * We do this using the current MSR, rather tracking it in - * some specific thread_struct bit, as it has the additional - * benifit of checking for a potential TM bad thing exception. - */ - if (!MSR_TM_SUSPENDED(mfmsr())) - return; - tm_reclaim(thr, thr->regs->msr, cause); /* Having done the reclaim, we now have the checkpointed diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 7030b035905d..a15fe1d4e84a 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -148,23 +148,25 @@ static struct ibm_pa_feature { unsigned long cpu_features; /* CPU_FTR_xxx bit */ unsigned long mmu_features; /* MMU_FTR_xxx bit */ unsigned int cpu_user_ftrs; /* PPC_FEATURE_xxx bit */ + unsigned int cpu_user_ftrs2; /* PPC_FEATURE2_xxx bit */ unsigned char pabyte; /* byte number in ibm,pa-features */ unsigned char pabit; /* bit number (big-endian) */ unsigned char invert; /* if 1, pa bit set => clear feature */ } ibm_pa_features[] __initdata = { - {0, 0, PPC_FEATURE_HAS_MMU, 0, 0, 0}, - {0, 0, PPC_FEATURE_HAS_FPU, 0, 1, 0}, - {CPU_FTR_CTRL, 0, 0, 0, 3, 0}, - {CPU_FTR_NOEXECUTE, 0, 0, 0, 6, 0}, - {CPU_FTR_NODSISRALIGN, 0, 0, 1, 1, 1}, - {0, MMU_FTR_CI_LARGE_PAGE, 0, 1, 2, 0}, - {CPU_FTR_REAL_LE, PPC_FEATURE_TRUE_LE, 5, 0, 0}, + {0, 0, PPC_FEATURE_HAS_MMU, 0, 0, 0, 0}, + {0, 0, PPC_FEATURE_HAS_FPU, 0, 0, 1, 0}, + {CPU_FTR_CTRL, 0, 0, 0, 0, 3, 0}, + {CPU_FTR_NOEXECUTE, 0, 0, 0, 0, 6, 0}, + {CPU_FTR_NODSISRALIGN, 0, 0, 0, 1, 1, 1}, + {0, MMU_FTR_CI_LARGE_PAGE, 0, 0, 1, 2, 0}, + {CPU_FTR_REAL_LE, 0, PPC_FEATURE_TRUE_LE, 0, 5, 0, 0}, /* - * If the kernel doesn't support TM (ie. CONFIG_PPC_TRANSACTIONAL_MEM=n), - * we don't want to turn on CPU_FTR_TM here, so we use CPU_FTR_TM_COMP - * which is 0 if the kernel doesn't support TM. + * If the kernel doesn't support TM (ie CONFIG_PPC_TRANSACTIONAL_MEM=n), + * we don't want to turn on TM here, so we use the *_COMP versions + * which are 0 if the kernel doesn't support TM. */ - {CPU_FTR_TM_COMP, 0, 0, 22, 0, 0}, + {CPU_FTR_TM_COMP, 0, 0, + PPC_FEATURE2_HTM_COMP|PPC_FEATURE2_HTM_NOSC_COMP, 22, 0, 0}, }; static void __init scan_features(unsigned long node, const unsigned char *ftrs, @@ -195,10 +197,12 @@ static void __init scan_features(unsigned long node, const unsigned char *ftrs, if (bit ^ fp->invert) { cur_cpu_spec->cpu_features |= fp->cpu_features; cur_cpu_spec->cpu_user_features |= fp->cpu_user_ftrs; + cur_cpu_spec->cpu_user_features2 |= fp->cpu_user_ftrs2; cur_cpu_spec->mmu_features |= fp->mmu_features; } else { cur_cpu_spec->cpu_features &= ~fp->cpu_features; cur_cpu_spec->cpu_user_features &= ~fp->cpu_user_ftrs; + cur_cpu_spec->cpu_user_features2 &= ~fp->cpu_user_ftrs2; cur_cpu_spec->mmu_features &= ~fp->mmu_features; } } diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index e57cc383e5da..463af88c95a2 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1370,6 +1370,20 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) std r6, VCPU_ACOP(r9) stw r7, VCPU_GUEST_PID(r9) std r8, VCPU_WORT(r9) + /* + * Restore various registers to 0, where non-zero values + * set by the guest could disrupt the host. + */ + li r0, 0 + mtspr SPRN_IAMR, r0 + mtspr SPRN_CIABR, r0 + mtspr SPRN_DAWRX, r0 + mtspr SPRN_TCSCR, r0 + mtspr SPRN_WORT, r0 + /* Set MMCRS to 1<<31 to freeze and disable the SPMC counters */ + li r0, 1 + sldi r0, r0, 31 + mtspr SPRN_MMCRS, r0 8: /* Save and reset AMR and UAMOR before turning on the MMU */ diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 9833fee493ec..807f1594701d 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -486,13 +486,13 @@ static void hugepd_free(struct mmu_gather *tlb, void *hugepte) { struct hugepd_freelist **batchp; - batchp = this_cpu_ptr(&hugepd_freelist_cur); + batchp = &get_cpu_var(hugepd_freelist_cur); if (atomic_read(&tlb->mm->mm_users) < 2 || cpumask_equal(mm_cpumask(tlb->mm), cpumask_of(smp_processor_id()))) { kmem_cache_free(hugepte_cache, hugepte); - put_cpu_var(hugepd_freelist_cur); + put_cpu_var(hugepd_freelist_cur); return; } diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile index 1c8cdb6250e7..b9de7ef48849 100644 --- a/arch/powerpc/platforms/powernv/Makefile +++ b/arch/powerpc/platforms/powernv/Makefile @@ -2,6 +2,7 @@ obj-y += setup.o opal-wrappers.o opal.o opal-async.o idle.o obj-y += opal-rtc.o opal-nvram.o opal-lpc.o opal-flash.o obj-y += rng.o opal-elog.o opal-dump.o opal-sysparam.o opal-sensor.o obj-y += opal-msglog.o opal-hmi.o opal-power.o opal-irqchip.o +obj-y += opal-kmsg.o obj-$(CONFIG_SMP) += smp.o subcore.o subcore-asm.o obj-$(CONFIG_PCI) += pci.o pci-p5ioc2.o pci-ioda.o diff --git a/arch/powerpc/platforms/powernv/opal-kmsg.c b/arch/powerpc/platforms/powernv/opal-kmsg.c new file mode 100644 index 000000000000..6f1214d4de92 --- /dev/null +++ b/arch/powerpc/platforms/powernv/opal-kmsg.c @@ -0,0 +1,75 @@ +/* + * kmsg dumper that ensures the OPAL console fully flushes panic messages + * + * Author: Russell Currey <ruscur@russell.cc> + * + * Copyright 2015 IBM Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include <linux/kmsg_dump.h> + +#include <asm/opal.h> +#include <asm/opal-api.h> + +/* + * Console output is controlled by OPAL firmware. The kernel regularly calls + * OPAL_POLL_EVENTS, which flushes some console output. In a panic state, + * however, the kernel no longer calls OPAL_POLL_EVENTS and the panic message + * may not be completely printed. This function does not actually dump the + * message, it just ensures that OPAL completely flushes the console buffer. + */ +static void force_opal_console_flush(struct kmsg_dumper *dumper, + enum kmsg_dump_reason reason) +{ + int i; + int64_t ret; + + /* + * Outside of a panic context the pollers will continue to run, + * so we don't need to do any special flushing. + */ + if (reason != KMSG_DUMP_PANIC) + return; + + if (opal_check_token(OPAL_CONSOLE_FLUSH)) { + ret = opal_console_flush(0); + + if (ret == OPAL_UNSUPPORTED || ret == OPAL_PARAMETER) + return; + + /* Incrementally flush until there's nothing left */ + while (opal_console_flush(0) != OPAL_SUCCESS); + } else { + /* + * If OPAL_CONSOLE_FLUSH is not implemented in the firmware, + * the console can still be flushed by calling the polling + * function enough times to flush the buffer. We don't know + * how much output still needs to be flushed, but we can be + * generous since the kernel is in panic and doesn't need + * to do much else. + */ + printk(KERN_NOTICE "opal: OPAL_CONSOLE_FLUSH missing.\n"); + for (i = 0; i < 1024; i++) { + opal_poll_events(NULL); + } + } +} + +static struct kmsg_dumper opal_kmsg_dumper = { + .dump = force_opal_console_flush +}; + +void __init opal_kmsg_init(void) +{ + int rc; + + /* Add our dumper to the list */ + rc = kmsg_dump_register(&opal_kmsg_dumper); + if (rc != 0) + pr_err("opal: kmsg_dump_register failed; returned %d\n", rc); +} diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index b7a464fef7a7..e45b88a5d7e0 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -301,3 +301,4 @@ OPAL_CALL(opal_flash_erase, OPAL_FLASH_ERASE); OPAL_CALL(opal_prd_msg, OPAL_PRD_MSG); OPAL_CALL(opal_leds_get_ind, OPAL_LEDS_GET_INDICATOR); OPAL_CALL(opal_leds_set_ind, OPAL_LEDS_SET_INDICATOR); +OPAL_CALL(opal_console_flush, OPAL_CONSOLE_FLUSH); diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 57cffb80bc36..ae29eaf85e9e 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -758,6 +758,9 @@ static int __init opal_init(void) opal_pdev_init(opal_node, "ibm,opal-flash"); opal_pdev_init(opal_node, "ibm,opal-prd"); + /* Initialise OPAL kmsg dumper for flushing console on panic */ + opal_kmsg_init(); + return 0; } machine_subsys_initcall(powernv, opal_init); diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h index d29ad9545b41..081b2ad99d73 100644 --- a/arch/s390/include/asm/mmu.h +++ b/arch/s390/include/asm/mmu.h @@ -11,7 +11,7 @@ typedef struct { spinlock_t list_lock; struct list_head pgtable_list; struct list_head gmap_list; - unsigned long asce_bits; + unsigned long asce; unsigned long asce_limit; unsigned long vdso_base; /* The mmu context allocates 4K page tables. */ diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index fb1b93ea3e3f..22877c9440ea 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -15,17 +15,41 @@ static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { + spin_lock_init(&mm->context.list_lock); + INIT_LIST_HEAD(&mm->context.pgtable_list); + INIT_LIST_HEAD(&mm->context.gmap_list); cpumask_clear(&mm->context.cpu_attach_mask); atomic_set(&mm->context.attach_count, 0); mm->context.flush_mm = 0; - mm->context.asce_bits = _ASCE_TABLE_LENGTH | _ASCE_USER_BITS; - mm->context.asce_bits |= _ASCE_TYPE_REGION3; #ifdef CONFIG_PGSTE mm->context.alloc_pgste = page_table_allocate_pgste; mm->context.has_pgste = 0; mm->context.use_skey = 0; #endif - mm->context.asce_limit = STACK_TOP_MAX; + switch (mm->context.asce_limit) { + case 1UL << 42: + /* + * forked 3-level task, fall through to set new asce with new + * mm->pgd + */ + case 0: + /* context created by exec, set asce limit to 4TB */ + mm->context.asce_limit = STACK_TOP_MAX; + mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_REGION3; + break; + case 1UL << 53: + /* forked 4-level task, set new asce with new mm->pgd */ + mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_REGION2; + break; + case 1UL << 31: + /* forked 2-level compat task, set new asce with new mm->pgd */ + mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_SEGMENT; + /* pgd_alloc() did not increase mm->nr_pmds */ + mm_inc_nr_pmds(mm); + } crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm)); return 0; } @@ -34,7 +58,7 @@ static inline int init_new_context(struct task_struct *tsk, static inline void set_user_asce(struct mm_struct *mm) { - S390_lowcore.user_asce = mm->context.asce_bits | __pa(mm->pgd); + S390_lowcore.user_asce = mm->context.asce; if (current->thread.mm_segment.ar4) __ctl_load(S390_lowcore.user_asce, 7, 7); set_cpu_flag(CIF_ASCE); @@ -63,7 +87,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, { int cpu = smp_processor_id(); - S390_lowcore.user_asce = next->context.asce_bits | __pa(next->pgd); + S390_lowcore.user_asce = next->context.asce; if (prev == next) return; if (MACHINE_HAS_TLB_LC) @@ -111,8 +135,6 @@ static inline void activate_mm(struct mm_struct *prev, static inline void arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { - if (oldmm->context.asce_limit < mm->context.asce_limit) - crst_table_downgrade(mm, oldmm->context.asce_limit); } static inline void arch_exit_mmap(struct mm_struct *mm) diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index c873e682b67f..6dafabb6ae1a 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -45,7 +45,8 @@ struct zpci_fmb { u64 rpcit_ops; u64 dma_rbytes; u64 dma_wbytes; -} __packed __aligned(16); + u64 pad[2]; +} __packed __aligned(128); enum zpci_state { ZPCI_FN_STATE_RESERVED, diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index 7b7858f158b4..5991cdcb5b40 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -56,8 +56,8 @@ static inline unsigned long pgd_entry_type(struct mm_struct *mm) return _REGION2_ENTRY_EMPTY; } -int crst_table_upgrade(struct mm_struct *, unsigned long limit); -void crst_table_downgrade(struct mm_struct *, unsigned long limit); +int crst_table_upgrade(struct mm_struct *); +void crst_table_downgrade(struct mm_struct *); static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address) { @@ -100,12 +100,26 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) static inline pgd_t *pgd_alloc(struct mm_struct *mm) { - spin_lock_init(&mm->context.list_lock); - INIT_LIST_HEAD(&mm->context.pgtable_list); - INIT_LIST_HEAD(&mm->context.gmap_list); - return (pgd_t *) crst_table_alloc(mm); + unsigned long *table = crst_table_alloc(mm); + + if (!table) + return NULL; + if (mm->context.asce_limit == (1UL << 31)) { + /* Forking a compat process with 2 page table levels */ + if (!pgtable_pmd_page_ctor(virt_to_page(table))) { + crst_table_free(mm, table); + return NULL; + } + } + return (pgd_t *) table; +} + +static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) +{ + if (mm->context.asce_limit == (1UL << 31)) + pgtable_pmd_page_dtor(virt_to_page(pgd)); + crst_table_free(mm, (unsigned long *) pgd); } -#define pgd_free(mm, pgd) crst_table_free(mm, (unsigned long *) pgd) static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, pgtable_t pte) diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index b16c3d0a1b9f..c1ea67db8404 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -163,7 +163,7 @@ extern __vector128 init_task_fpu_regs[__NUM_VXRS]; regs->psw.mask = PSW_USER_BITS | PSW_MASK_BA; \ regs->psw.addr = new_psw | PSW_ADDR_AMODE; \ regs->gprs[15] = new_stackp; \ - crst_table_downgrade(current->mm, 1UL << 31); \ + crst_table_downgrade(current->mm); \ execve_tail(); \ } while (0) diff --git a/arch/s390/include/asm/tlbflush.h b/arch/s390/include/asm/tlbflush.h index ca148f7c3eaa..a2e6ef32e054 100644 --- a/arch/s390/include/asm/tlbflush.h +++ b/arch/s390/include/asm/tlbflush.h @@ -110,8 +110,7 @@ static inline void __tlb_flush_asce(struct mm_struct *mm, unsigned long asce) static inline void __tlb_flush_kernel(void) { if (MACHINE_HAS_IDTE) - __tlb_flush_idte((unsigned long) init_mm.pgd | - init_mm.context.asce_bits); + __tlb_flush_idte(init_mm.context.asce); else __tlb_flush_global(); } @@ -133,8 +132,7 @@ static inline void __tlb_flush_asce(struct mm_struct *mm, unsigned long asce) static inline void __tlb_flush_kernel(void) { if (MACHINE_HAS_TLB_LC) - __tlb_flush_idte_local((unsigned long) init_mm.pgd | - init_mm.context.asce_bits); + __tlb_flush_idte_local(init_mm.context.asce); else __tlb_flush_local(); } @@ -148,8 +146,7 @@ static inline void __tlb_flush_mm(struct mm_struct * mm) * only ran on the local cpu. */ if (MACHINE_HAS_IDTE && list_empty(&mm->context.gmap_list)) - __tlb_flush_asce(mm, (unsigned long) mm->pgd | - mm->context.asce_bits); + __tlb_flush_asce(mm, mm->context.asce); else __tlb_flush_full(mm); } diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 857b6526d298..424e6809ad07 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -1197,114 +1197,12 @@ cleanup_critical: .quad .Lpsw_idle_lpsw .Lcleanup_save_fpu_regs: - TSTMSK __LC_CPU_FLAGS,_CIF_FPU - bor %r14 - clg %r9,BASED(.Lcleanup_save_fpu_regs_done) - jhe 5f - clg %r9,BASED(.Lcleanup_save_fpu_regs_fp) - jhe 4f - clg %r9,BASED(.Lcleanup_save_fpu_regs_vx_high) - jhe 3f - clg %r9,BASED(.Lcleanup_save_fpu_regs_vx_low) - jhe 2f - clg %r9,BASED(.Lcleanup_save_fpu_fpc_end) - jhe 1f - lg %r2,__LC_CURRENT - aghi %r2,__TASK_thread -0: # Store floating-point controls - stfpc __THREAD_FPU_fpc(%r2) -1: # Load register save area and check if VX is active - lg %r3,__THREAD_FPU_regs(%r2) - TSTMSK __LC_MACHINE_FLAGS,MACHINE_FLAG_VX - jz 4f # no VX -> store FP regs -2: # Store vector registers (V0-V15) - VSTM %v0,%v15,0,%r3 # vstm 0,15,0(3) -3: # Store vector registers (V16-V31) - VSTM %v16,%v31,256,%r3 # vstm 16,31,256(3) - j 5f # -> done, set CIF_FPU flag -4: # Store floating-point registers - std 0,0(%r3) - std 1,8(%r3) - std 2,16(%r3) - std 3,24(%r3) - std 4,32(%r3) - std 5,40(%r3) - std 6,48(%r3) - std 7,56(%r3) - std 8,64(%r3) - std 9,72(%r3) - std 10,80(%r3) - std 11,88(%r3) - std 12,96(%r3) - std 13,104(%r3) - std 14,112(%r3) - std 15,120(%r3) -5: # Set CIF_FPU flag - oi __LC_CPU_FLAGS+7,_CIF_FPU - lg %r9,48(%r11) # return from save_fpu_regs + larl %r9,save_fpu_regs br %r14 -.Lcleanup_save_fpu_fpc_end: - .quad .Lsave_fpu_regs_fpc_end -.Lcleanup_save_fpu_regs_vx_low: - .quad .Lsave_fpu_regs_vx_low -.Lcleanup_save_fpu_regs_vx_high: - .quad .Lsave_fpu_regs_vx_high -.Lcleanup_save_fpu_regs_fp: - .quad .Lsave_fpu_regs_fp -.Lcleanup_save_fpu_regs_done: - .quad .Lsave_fpu_regs_done .Lcleanup_load_fpu_regs: - TSTMSK __LC_CPU_FLAGS,_CIF_FPU - bnor %r14 - clg %r9,BASED(.Lcleanup_load_fpu_regs_done) - jhe 1f - clg %r9,BASED(.Lcleanup_load_fpu_regs_fp) - jhe 2f - clg %r9,BASED(.Lcleanup_load_fpu_regs_vx_high) - jhe 3f - clg %r9,BASED(.Lcleanup_load_fpu_regs_vx) - jhe 4f - lg %r4,__LC_CURRENT - aghi %r4,__TASK_thread - lfpc __THREAD_FPU_fpc(%r4) - TSTMSK __LC_MACHINE_FLAGS,MACHINE_FLAG_VX - lg %r4,__THREAD_FPU_regs(%r4) # %r4 <- reg save area - jz 2f # -> no VX, load FP regs -4: # Load V0 ..V15 registers - VLM %v0,%v15,0,%r4 -3: # Load V16..V31 registers - VLM %v16,%v31,256,%r4 - j 1f -2: # Load floating-point registers - ld 0,0(%r4) - ld 1,8(%r4) - ld 2,16(%r4) - ld 3,24(%r4) - ld 4,32(%r4) - ld 5,40(%r4) - ld 6,48(%r4) - ld 7,56(%r4) - ld 8,64(%r4) - ld 9,72(%r4) - ld 10,80(%r4) - ld 11,88(%r4) - ld 12,96(%r4) - ld 13,104(%r4) - ld 14,112(%r4) - ld 15,120(%r4) -1: # Clear CIF_FPU bit - ni __LC_CPU_FLAGS+7,255-_CIF_FPU - lg %r9,48(%r11) # return from load_fpu_regs + larl %r9,load_fpu_regs br %r14 -.Lcleanup_load_fpu_regs_vx: - .quad .Lload_fpu_regs_vx -.Lcleanup_load_fpu_regs_vx_high: - .quad .Lload_fpu_regs_vx_high -.Lcleanup_load_fpu_regs_fp: - .quad .Lload_fpu_regs_fp -.Lcleanup_load_fpu_regs_done: - .quad .Lload_fpu_regs_done /* * Integer constants diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S index 58b719fa8067..1ad2407c7f75 100644 --- a/arch/s390/kernel/head64.S +++ b/arch/s390/kernel/head64.S @@ -16,7 +16,7 @@ __HEAD ENTRY(startup_continue) - tm __LC_STFL_FAC_LIST+6,0x80 # LPP available ? + tm __LC_STFL_FAC_LIST+5,0x80 # LPP available ? jz 0f xc __LC_LPP+1(7,0),__LC_LPP+1 # clear lpp and current_pid mvi __LC_LPP,0x80 # and set LPP_MAGIC diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index c837bcacf218..1f581eb61bc2 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -329,6 +329,7 @@ static void __init setup_lowcore(void) + PAGE_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs); lc->current_task = (unsigned long) init_thread_union.thread_info.task; lc->thread_info = (unsigned long) &init_thread_union; + lc->lpp = LPP_MAGIC; lc->machine_flags = S390_lowcore.machine_flags; lc->stfl_fac_list = S390_lowcore.stfl_fac_list; memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list, diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index a08d0afd5ff6..575dc123bda2 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2249,7 +2249,7 @@ int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa) /* manually convert vector registers if necessary */ if (MACHINE_HAS_VX) { - convert_vx_to_fp(fprs, current->thread.fpu.vxrs); + convert_vx_to_fp(fprs, (__vector128 *) vcpu->run->s.regs.vrs); rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA, fprs, 128); } else { diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index c722400c7697..feff9caf89b5 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -89,7 +89,8 @@ void __init paging_init(void) asce_bits = _ASCE_TYPE_REGION3 | _ASCE_TABLE_LENGTH; pgd_type = _REGION3_ENTRY_EMPTY; } - S390_lowcore.kernel_asce = (__pa(init_mm.pgd) & PAGE_MASK) | asce_bits; + init_mm.context.asce = (__pa(init_mm.pgd) & PAGE_MASK) | asce_bits; + S390_lowcore.kernel_asce = init_mm.context.asce; clear_table((unsigned long *) init_mm.pgd, pgd_type, sizeof(unsigned long)*2048); vmem_map_init(); diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index ea01477b4aa6..f2b6b1d9c804 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -174,7 +174,7 @@ int s390_mmap_check(unsigned long addr, unsigned long len, unsigned long flags) if (!(flags & MAP_FIXED)) addr = 0; if ((addr + len) >= TASK_SIZE) - return crst_table_upgrade(current->mm, 1UL << 53); + return crst_table_upgrade(current->mm); return 0; } @@ -191,7 +191,7 @@ s390_get_unmapped_area(struct file *filp, unsigned long addr, return area; if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < (1UL << 53)) { /* Upgrade the page table to 4 levels and retry. */ - rc = crst_table_upgrade(mm, 1UL << 53); + rc = crst_table_upgrade(mm); if (rc) return (unsigned long) rc; area = arch_get_unmapped_area(filp, addr, len, pgoff, flags); @@ -213,7 +213,7 @@ s390_get_unmapped_area_topdown(struct file *filp, const unsigned long addr, return area; if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < (1UL << 53)) { /* Upgrade the page table to 4 levels and retry. */ - rc = crst_table_upgrade(mm, 1UL << 53); + rc = crst_table_upgrade(mm); if (rc) return (unsigned long) rc; area = arch_get_unmapped_area_topdown(filp, addr, len, diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 54ef3bc01b43..471a370a527b 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -49,81 +49,52 @@ static void __crst_table_upgrade(void *arg) __tlb_flush_local(); } -int crst_table_upgrade(struct mm_struct *mm, unsigned long limit) +int crst_table_upgrade(struct mm_struct *mm) { unsigned long *table, *pgd; - unsigned long entry; - int flush; - BUG_ON(limit > (1UL << 53)); - flush = 0; -repeat: + /* upgrade should only happen from 3 to 4 levels */ + BUG_ON(mm->context.asce_limit != (1UL << 42)); + table = crst_table_alloc(mm); if (!table) return -ENOMEM; + spin_lock_bh(&mm->page_table_lock); - if (mm->context.asce_limit < limit) { - pgd = (unsigned long *) mm->pgd; - if (mm->context.asce_limit <= (1UL << 31)) { - entry = _REGION3_ENTRY_EMPTY; - mm->context.asce_limit = 1UL << 42; - mm->context.asce_bits = _ASCE_TABLE_LENGTH | - _ASCE_USER_BITS | - _ASCE_TYPE_REGION3; - } else { - entry = _REGION2_ENTRY_EMPTY; - mm->context.asce_limit = 1UL << 53; - mm->context.asce_bits = _ASCE_TABLE_LENGTH | - _ASCE_USER_BITS | - _ASCE_TYPE_REGION2; - } - crst_table_init(table, entry); - pgd_populate(mm, (pgd_t *) table, (pud_t *) pgd); - mm->pgd = (pgd_t *) table; - mm->task_size = mm->context.asce_limit; - table = NULL; - flush = 1; - } + pgd = (unsigned long *) mm->pgd; + crst_table_init(table, _REGION2_ENTRY_EMPTY); + pgd_populate(mm, (pgd_t *) table, (pud_t *) pgd); + mm->pgd = (pgd_t *) table; + mm->context.asce_limit = 1UL << 53; + mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_REGION2; + mm->task_size = mm->context.asce_limit; spin_unlock_bh(&mm->page_table_lock); - if (table) - crst_table_free(mm, table); - if (mm->context.asce_limit < limit) - goto repeat; - if (flush) - on_each_cpu(__crst_table_upgrade, mm, 0); + + on_each_cpu(__crst_table_upgrade, mm, 0); return 0; } -void crst_table_downgrade(struct mm_struct *mm, unsigned long limit) +void crst_table_downgrade(struct mm_struct *mm) { pgd_t *pgd; + /* downgrade should only happen from 3 to 2 levels (compat only) */ + BUG_ON(mm->context.asce_limit != (1UL << 42)); + if (current->active_mm == mm) { clear_user_asce(); __tlb_flush_mm(mm); } - while (mm->context.asce_limit > limit) { - pgd = mm->pgd; - switch (pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) { - case _REGION_ENTRY_TYPE_R2: - mm->context.asce_limit = 1UL << 42; - mm->context.asce_bits = _ASCE_TABLE_LENGTH | - _ASCE_USER_BITS | - _ASCE_TYPE_REGION3; - break; - case _REGION_ENTRY_TYPE_R3: - mm->context.asce_limit = 1UL << 31; - mm->context.asce_bits = _ASCE_TABLE_LENGTH | - _ASCE_USER_BITS | - _ASCE_TYPE_SEGMENT; - break; - default: - BUG(); - } - mm->pgd = (pgd_t *) (pgd_val(*pgd) & _REGION_ENTRY_ORIGIN); - mm->task_size = mm->context.asce_limit; - crst_table_free(mm, (unsigned long *) pgd); - } + + pgd = mm->pgd; + mm->pgd = (pgd_t *) (pgd_val(*pgd) & _REGION_ENTRY_ORIGIN); + mm->context.asce_limit = 1UL << 31; + mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_SEGMENT; + mm->task_size = mm->context.asce_limit; + crst_table_free(mm, (unsigned long *) pgd); + if (current->active_mm == mm) set_user_asce(mm); } diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 7ef12a3ace3a..19442395f413 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -871,8 +871,11 @@ static inline int barsize(u8 size) static int zpci_mem_init(void) { + BUILD_BUG_ON(!is_power_of_2(__alignof__(struct zpci_fmb)) || + __alignof__(struct zpci_fmb) < sizeof(struct zpci_fmb)); + zdev_fmb_cache = kmem_cache_create("PCI_FMB_cache", sizeof(struct zpci_fmb), - 16, 0, NULL); + __alignof__(struct zpci_fmb), 0, NULL); if (!zdev_fmb_cache) goto error_zdev; diff --git a/arch/sh/mm/kmap.c b/arch/sh/mm/kmap.c index ec29e14ec5a8..bf25d7c79a2d 100644 --- a/arch/sh/mm/kmap.c +++ b/arch/sh/mm/kmap.c @@ -36,6 +36,7 @@ void *kmap_coherent(struct page *page, unsigned long addr) BUG_ON(!test_bit(PG_dcache_clean, &page->flags)); + preempt_disable(); pagefault_disable(); idx = FIX_CMAP_END - @@ -64,4 +65,5 @@ void kunmap_coherent(void *kvaddr) } pagefault_enable(); + preempt_enable(); } diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index 29880c9b324e..e22e57298522 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -133,7 +133,7 @@ void mconsole_proc(struct mc_request *req) ptr += strlen("proc"); ptr = skip_spaces(ptr); - file = file_open_root(mnt->mnt_root, mnt, ptr, O_RDONLY); + file = file_open_root(mnt->mnt_root, mnt, ptr, O_RDONLY, 0); if (IS_ERR(file)) { mconsole_reply(req, "Failed to open file", 1, 0); printk(KERN_ERR "open /proc/%s: %ld\n", ptr, PTR_ERR(file)); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index db3622f22b61..436639a31624 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1126,22 +1126,23 @@ config MICROCODE bool "CPU microcode loading support" default y depends on CPU_SUP_AMD || CPU_SUP_INTEL - depends on BLK_DEV_INITRD select FW_LOADER ---help--- - If you say Y here, you will be able to update the microcode on - certain Intel and AMD processors. The Intel support is for the - IA32 family, e.g. Pentium Pro, Pentium II, Pentium III, Pentium 4, - Xeon etc. The AMD support is for families 0x10 and later. You will - obviously need the actual microcode binary data itself which is not - shipped with the Linux kernel. - - This option selects the general module only, you need to select - at least one vendor specific module as well. - - To compile this driver as a module, choose M here: the module - will be called microcode. + Intel and AMD processors. The Intel support is for the IA32 family, + e.g. Pentium Pro, Pentium II, Pentium III, Pentium 4, Xeon etc. The + AMD support is for families 0x10 and later. You will obviously need + the actual microcode binary data itself which is not shipped with + the Linux kernel. + + The preferred method to load microcode from a detached initrd is described + in Documentation/x86/early-microcode.txt. For that you need to enable + CONFIG_BLK_DEV_INITRD in order for the loader to be able to scan the + initrd for microcode blobs. + + In addition, you can build-in the microcode into the kernel. For that you + need to enable FIRMWARE_IN_KERNEL and add the vendor-supplied microcode + to the CONFIG_EXTRA_FIRMWARE config option. config MICROCODE_INTEL bool "Intel microcode loading support" diff --git a/arch/x86/crypto/sha-mb/sha1_mb.c b/arch/x86/crypto/sha-mb/sha1_mb.c index a841e9765bd6..8381c09d2870 100644 --- a/arch/x86/crypto/sha-mb/sha1_mb.c +++ b/arch/x86/crypto/sha-mb/sha1_mb.c @@ -453,10 +453,10 @@ static int sha_complete_job(struct mcryptd_hash_request_ctx *rctx, req = cast_mcryptd_ctx_to_req(req_ctx); if (irqs_disabled()) - rctx->complete(&req->base, ret); + req_ctx->complete(&req->base, ret); else { local_bh_disable(); - rctx->complete(&req->base, ret); + req_ctx->complete(&req->base, ret); local_bh_enable(); } } diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 03663740c866..1a4477cedc49 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -268,6 +268,7 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags) /* Called with IRQs disabled. */ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs) { + struct thread_info *ti = pt_regs_to_thread_info(regs); u32 cached_flags; if (IS_ENABLED(CONFIG_PROVE_LOCKING) && WARN_ON(!irqs_disabled())) @@ -275,12 +276,22 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs) lockdep_sys_exit(); - cached_flags = - READ_ONCE(pt_regs_to_thread_info(regs)->flags); + cached_flags = READ_ONCE(ti->flags); if (unlikely(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS)) exit_to_usermode_loop(regs, cached_flags); +#ifdef CONFIG_COMPAT + /* + * Compat syscalls set TS_COMPAT. Make sure we clear it before + * returning to user mode. We need to clear it *after* signal + * handling, because syscall restart has a fixup for compat + * syscalls. The fixup is exercised by the ptrace_syscall_32 + * selftest. + */ + ti->status &= ~TS_COMPAT; +#endif + user_enter(); } @@ -332,14 +343,6 @@ __visible inline void syscall_return_slowpath(struct pt_regs *regs) if (unlikely(cached_flags & SYSCALL_EXIT_WORK_FLAGS)) syscall_slow_exit_work(regs, cached_flags); -#ifdef CONFIG_COMPAT - /* - * Compat syscalls set TS_COMPAT. Make sure we clear it before - * returning to user mode. - */ - ti->status &= ~TS_COMPAT; -#endif - local_irq_disable(); prepare_exit_to_usermode(regs); } diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index a30316bf801a..163769d82475 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -638,8 +638,8 @@ static inline void entering_irq(void) static inline void entering_ack_irq(void) { - ack_APIC_irq(); entering_irq(); + ack_APIC_irq(); } static inline void ipi_entering_ack_irq(void) diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h index f8a29d2c97b0..e6a8613fbfb0 100644 --- a/arch/x86/include/asm/hugetlb.h +++ b/arch/x86/include/asm/hugetlb.h @@ -4,6 +4,7 @@ #include <asm/page.h> #include <asm-generic/hugetlb.h> +#define hugepages_supported() cpu_has_pse static inline int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index 1e3408e88604..59caa55fb9b5 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -136,6 +136,7 @@ struct irq_alloc_info { struct irq_cfg { unsigned int dest_apicid; u8 vector; + u8 old_vector; }; extern struct irq_cfg *irq_cfg(unsigned int irq); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 30cfd64295a0..9d2abb2a41d2 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -41,7 +41,7 @@ #define KVM_PIO_PAGE_OFFSET 1 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2 -#define KVM_HALT_POLL_NS_DEFAULT 500000 +#define KVM_HALT_POLL_NS_DEFAULT 400000 #define KVM_IRQCHIP_NUM_PINS KVM_IOAPIC_NUM_PINS diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 34e62b1dcfce..712b24ed3a64 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -2,6 +2,7 @@ #define _ASM_X86_MICROCODE_H #include <linux/earlycpio.h> +#include <linux/initrd.h> #define native_rdmsr(msr, val1, val2) \ do { \ @@ -168,4 +169,29 @@ static inline void reload_early_microcode(void) { } static inline bool get_builtin_firmware(struct cpio_data *cd, const char *name) { return false; } #endif + +static inline unsigned long get_initrd_start(void) +{ +#ifdef CONFIG_BLK_DEV_INITRD + return initrd_start; +#else + return 0; +#endif +} + +static inline unsigned long get_initrd_start_addr(void) +{ +#ifdef CONFIG_BLK_DEV_INITRD +#ifdef CONFIG_X86_32 + unsigned long *initrd_start_p = (unsigned long *)__pa_nodebug(&initrd_start); + + return (unsigned long)__pa_nodebug(*initrd_start_p); +#else + return get_initrd_start(); +#endif +#else /* CONFIG_BLK_DEV_INITRD */ + return 0; +#endif +} + #endif /* _ASM_X86_MICROCODE_H */ diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index fa1195dae425..164e3f8d3c3d 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -93,6 +93,8 @@ extern raw_spinlock_t pci_config_lock; extern int (*pcibios_enable_irq)(struct pci_dev *dev); extern void (*pcibios_disable_irq)(struct pci_dev *dev); +extern bool mp_should_keep_irq(struct device *dev); + struct pci_raw_ops { int (*read)(unsigned int domain, unsigned int bus, unsigned int devfn, int reg, int len, u32 *val); diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 7bcb861a04e5..5a2ed3ed2f26 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -165,6 +165,7 @@ struct x86_pmu_capability { #define GLOBAL_STATUS_ASIF BIT_ULL(60) #define GLOBAL_STATUS_COUNTERS_FROZEN BIT_ULL(59) #define GLOBAL_STATUS_LBRS_FROZEN BIT_ULL(58) +#define GLOBAL_STATUS_TRACE_TOPAPMI BIT_ULL(55) /* * IBS cpuid feature detection diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h index 8b2d4bea9962..39171b3646bb 100644 --- a/arch/x86/include/asm/xen/hypervisor.h +++ b/arch/x86/include/asm/xen/hypervisor.h @@ -62,4 +62,6 @@ void xen_arch_register_cpu(int num); void xen_arch_unregister_cpu(int num); #endif +extern void xen_set_iopl_mask(unsigned mask); + #endif /* _ASM_X86_XEN_HYPERVISOR_H */ diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index a35f6b5473f4..df6b4eeac0bd 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -211,6 +211,7 @@ update: */ cpumask_and(d->old_domain, d->old_domain, cpu_online_mask); d->move_in_progress = !cpumask_empty(d->old_domain); + d->cfg.old_vector = d->move_in_progress ? d->cfg.vector : 0; d->cfg.vector = vector; cpumask_copy(d->domain, vector_cpumask); success: @@ -253,7 +254,8 @@ static void clear_irq_vector(int irq, struct apic_chip_data *data) struct irq_desc *desc; int cpu, vector; - BUG_ON(!data->cfg.vector); + if (!data->cfg.vector) + return; vector = data->cfg.vector; for_each_cpu_and(cpu, data->domain, cpu_online_mask) @@ -653,46 +655,97 @@ void irq_complete_move(struct irq_cfg *cfg) } /* - * Called with @desc->lock held and interrupts disabled. + * Called from fixup_irqs() with @desc->lock held and interrupts disabled. */ void irq_force_complete_move(struct irq_desc *desc) { struct irq_data *irqdata = irq_desc_get_irq_data(desc); struct apic_chip_data *data = apic_chip_data(irqdata); struct irq_cfg *cfg = data ? &data->cfg : NULL; + unsigned int cpu; if (!cfg) return; - __irq_complete_move(cfg, cfg->vector); - /* * This is tricky. If the cleanup of @data->old_domain has not been * done yet, then the following setaffinity call will fail with * -EBUSY. This can leave the interrupt in a stale state. * - * The cleanup cannot make progress because we hold @desc->lock. So in - * case @data->old_domain is not yet cleaned up, we need to drop the - * lock and acquire it again. @desc cannot go away, because the - * hotplug code holds the sparse irq lock. + * All CPUs are stuck in stop machine with interrupts disabled so + * calling __irq_complete_move() would be completely pointless. */ raw_spin_lock(&vector_lock); - /* Clean out all offline cpus (including ourself) first. */ + /* + * Clean out all offline cpus (including the outgoing one) from the + * old_domain mask. + */ cpumask_and(data->old_domain, data->old_domain, cpu_online_mask); - while (!cpumask_empty(data->old_domain)) { + + /* + * If move_in_progress is cleared and the old_domain mask is empty, + * then there is nothing to cleanup. fixup_irqs() will take care of + * the stale vectors on the outgoing cpu. + */ + if (!data->move_in_progress && cpumask_empty(data->old_domain)) { raw_spin_unlock(&vector_lock); - raw_spin_unlock(&desc->lock); - cpu_relax(); - raw_spin_lock(&desc->lock); + return; + } + + /* + * 1) The interrupt is in move_in_progress state. That means that we + * have not seen an interrupt since the io_apic was reprogrammed to + * the new vector. + * + * 2) The interrupt has fired on the new vector, but the cleanup IPIs + * have not been processed yet. + */ + if (data->move_in_progress) { /* - * Reevaluate apic_chip_data. It might have been cleared after - * we dropped @desc->lock. + * In theory there is a race: + * + * set_ioapic(new_vector) <-- Interrupt is raised before update + * is effective, i.e. it's raised on + * the old vector. + * + * So if the target cpu cannot handle that interrupt before + * the old vector is cleaned up, we get a spurious interrupt + * and in the worst case the ioapic irq line becomes stale. + * + * But in case of cpu hotplug this should be a non issue + * because if the affinity update happens right before all + * cpus rendevouz in stop machine, there is no way that the + * interrupt can be blocked on the target cpu because all cpus + * loops first with interrupts enabled in stop machine, so the + * old vector is not yet cleaned up when the interrupt fires. + * + * So the only way to run into this issue is if the delivery + * of the interrupt on the apic/system bus would be delayed + * beyond the point where the target cpu disables interrupts + * in stop machine. I doubt that it can happen, but at least + * there is a theroretical chance. Virtualization might be + * able to expose this, but AFAICT the IOAPIC emulation is not + * as stupid as the real hardware. + * + * Anyway, there is nothing we can do about that at this point + * w/o refactoring the whole fixup_irq() business completely. + * We print at least the irq number and the old vector number, + * so we have the necessary information when a problem in that + * area arises. */ - data = apic_chip_data(irqdata); - if (!data) - return; - raw_spin_lock(&vector_lock); + pr_warn("IRQ fixup: irq %d move in progress, old vector %d\n", + irqdata->irq, cfg->old_vector); } + /* + * If old_domain is not empty, then other cpus still have the irq + * descriptor set in their vector array. Clean it up. + */ + for_each_cpu(cpu, data->old_domain) + per_cpu(vector_irq, cpu)[cfg->old_vector] = VECTOR_UNUSED; + + /* Cleanup the left overs of the (half finished) move */ + cpumask_clear(data->old_domain); + data->move_in_progress = 0; raw_spin_unlock(&vector_lock); } #endif diff --git a/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/arch/x86/kernel/cpu/mcheck/mce-genpool.c index 0a850100c594..2658e2af74ec 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-genpool.c +++ b/arch/x86/kernel/cpu/mcheck/mce-genpool.c @@ -29,7 +29,7 @@ static char gen_pool_buf[MCE_POOLSZ]; void mce_gen_pool_process(void) { struct llist_node *head; - struct mce_evt_llist *node; + struct mce_evt_llist *node, *tmp; struct mce *mce; head = llist_del_all(&mce_event_llist); @@ -37,7 +37,7 @@ void mce_gen_pool_process(void) return; head = llist_reverse_order(head); - llist_for_each_entry(node, head, llnode) { + llist_for_each_entry_safe(node, tmp, head, llnode) { mce = &node->mce; atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, mce); gen_pool_free(mce_evt_pool, (unsigned long)node, sizeof(*node)); diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 2c5aaf8c2e2f..05538582a809 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -385,6 +385,9 @@ static void intel_thermal_interrupt(void) { __u64 msr_val; + if (static_cpu_has(X86_FEATURE_HWP)) + wrmsrl_safe(MSR_HWP_STATUS, 0); + rdmsrl(MSR_IA32_THERM_STATUS, msr_val); /* Check for violation of core thermal thresholds*/ diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index ce47402eb2f9..ac8975a65280 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -555,10 +555,14 @@ scan_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd, cd.data = NULL; cd.size = 0; - cd = find_cpio_data(p, (void *)start, size, &offset); - if (!cd.data) { + /* try built-in microcode if no initrd */ + if (!size) { if (!load_builtin_intel_microcode(&cd)) return UCODE_ERROR; + } else { + cd = find_cpio_data(p, (void *)start, size, &offset); + if (!cd.data) + return UCODE_ERROR; } return get_matching_model_microcode(0, start, cd.data, cd.size, @@ -694,7 +698,7 @@ int __init save_microcode_in_initrd_intel(void) if (count == 0) return ret; - copy_initrd_ptrs(mc_saved, mc_saved_in_initrd, initrd_start, count); + copy_initrd_ptrs(mc_saved, mc_saved_in_initrd, get_initrd_start(), count); ret = save_microcode(&mc_saved_data, mc_saved, count); if (ret) pr_err("Cannot save microcode patches from initrd.\n"); @@ -732,16 +736,20 @@ void __init load_ucode_intel_bsp(void) struct boot_params *p; p = (struct boot_params *)__pa_nodebug(&boot_params); - start = p->hdr.ramdisk_image; size = p->hdr.ramdisk_size; - _load_ucode_intel_bsp( - (struct mc_saved_data *)__pa_nodebug(&mc_saved_data), - (unsigned long *)__pa_nodebug(&mc_saved_in_initrd), - start, size); + /* + * Set start only if we have an initrd image. We cannot use initrd_start + * because it is not set that early yet. + */ + start = (size ? p->hdr.ramdisk_image : 0); + + _load_ucode_intel_bsp((struct mc_saved_data *)__pa_nodebug(&mc_saved_data), + (unsigned long *)__pa_nodebug(&mc_saved_in_initrd), + start, size); #else - start = boot_params.hdr.ramdisk_image + PAGE_OFFSET; size = boot_params.hdr.ramdisk_size; + start = (size ? boot_params.hdr.ramdisk_image + PAGE_OFFSET : 0); _load_ucode_intel_bsp(&mc_saved_data, mc_saved_in_initrd, start, size); #endif @@ -752,20 +760,14 @@ void load_ucode_intel_ap(void) struct mc_saved_data *mc_saved_data_p; struct ucode_cpu_info uci; unsigned long *mc_saved_in_initrd_p; - unsigned long initrd_start_addr; enum ucode_state ret; #ifdef CONFIG_X86_32 - unsigned long *initrd_start_p; - mc_saved_in_initrd_p = - (unsigned long *)__pa_nodebug(mc_saved_in_initrd); + mc_saved_in_initrd_p = (unsigned long *)__pa_nodebug(mc_saved_in_initrd); mc_saved_data_p = (struct mc_saved_data *)__pa_nodebug(&mc_saved_data); - initrd_start_p = (unsigned long *)__pa_nodebug(&initrd_start); - initrd_start_addr = (unsigned long)__pa_nodebug(*initrd_start_p); #else - mc_saved_data_p = &mc_saved_data; mc_saved_in_initrd_p = mc_saved_in_initrd; - initrd_start_addr = initrd_start; + mc_saved_data_p = &mc_saved_data; #endif /* @@ -777,7 +779,7 @@ void load_ucode_intel_ap(void) collect_cpu_info_early(&uci); ret = load_microcode(mc_saved_data_p, mc_saved_in_initrd_p, - initrd_start_addr, &uci); + get_initrd_start_addr(), &uci); if (ret != UCODE_OK) return; diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 2bf79d7c97df..a3aeb2cc361e 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -593,6 +593,19 @@ void x86_pmu_disable_all(void) } } +/* + * There may be PMI landing after enabled=0. The PMI hitting could be before or + * after disable_all. + * + * If PMI hits before disable_all, the PMU will be disabled in the NMI handler. + * It will not be re-enabled in the NMI handler again, because enabled=0. After + * handling the NMI, disable_all will be called, which will not change the + * state either. If PMI hits after disable_all, the PMU is already disabled + * before entering NMI handler. The NMI handler will not change the state + * either. + * + * So either situation is harmless. + */ static void x86_pmu_disable(struct pmu *pmu) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index d0e35ebb2adb..ee70445fbb1f 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -591,6 +591,7 @@ struct x86_pmu { pebs_active :1, pebs_broken :1; int pebs_record_size; + int pebs_buffer_size; void (*drain_pebs)(struct pt_regs *regs); struct event_constraint *pebs_constraints; void (*pebs_aliases)(struct perf_event *event); @@ -907,6 +908,8 @@ void intel_pmu_lbr_init_hsw(void); void intel_pmu_lbr_init_skl(void); +void intel_pmu_pebs_data_source_nhm(void); + int intel_pmu_setup_lbr_filter(struct perf_event *event); void intel_pt_interrupt(void); diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index e2a430021e46..078de2e86b7a 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1458,7 +1458,15 @@ static __initconst const u64 slm_hw_cache_event_ids }; /* - * Use from PMIs where the LBRs are already disabled. + * Used from PMIs where the LBRs are already disabled. + * + * This function could be called consecutively. It is required to remain in + * disabled state if called consecutively. + * + * During consecutive calls, the same disable value will be written to related + * registers, so the PMU state remains unchanged. hw.state in + * intel_bts_disable_local will remain PERF_HES_STOPPED too in consecutive + * calls. */ static void __intel_pmu_disable_all(void) { @@ -1840,6 +1848,16 @@ again: if (__test_and_clear_bit(62, (unsigned long *)&status)) { handled++; x86_pmu.drain_pebs(regs); + /* + * There are cases where, even though, the PEBS ovfl bit is set + * in GLOBAL_OVF_STATUS, the PEBS events may also have their + * overflow bits set for their counters. We must clear them + * here because they have been processed as exact samples in + * the drain_pebs() routine. They must not be processed again + * in the for_each_bit_set() loop for regular samples below. + */ + status &= ~cpuc->pebs_enabled; + status &= x86_pmu.intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI; } /* @@ -1885,7 +1903,10 @@ again: goto again; done: - __intel_pmu_enable_all(0, true); + /* Only restore PMU state when it's active. See x86_pmu_disable(). */ + if (cpuc->enabled) + __intel_pmu_enable_all(0, true); + /* * Only unmask the NMI after the overflow counters * have been reset. This avoids spurious NMIs on @@ -3315,6 +3336,7 @@ __init int intel_pmu_init(void) intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1); + intel_pmu_pebs_data_source_nhm(); x86_add_quirk(intel_nehalem_quirk); pr_cont("Nehalem events, "); @@ -3377,6 +3399,7 @@ __init int intel_pmu_init(void) intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1); + intel_pmu_pebs_data_source_nhm(); pr_cont("Westmere events, "); break; diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 5db1c7755548..7abb2b88572e 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -51,7 +51,8 @@ union intel_x86_pebs_dse { #define OP_LH (P(OP, LOAD) | P(LVL, HIT)) #define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS)) -static const u64 pebs_data_source[] = { +/* Version for Sandy Bridge and later */ +static u64 pebs_data_source[] = { P(OP, LOAD) | P(LVL, MISS) | P(LVL, L3) | P(SNOOP, NA),/* 0x00:ukn L3 */ OP_LH | P(LVL, L1) | P(SNOOP, NONE), /* 0x01: L1 local */ OP_LH | P(LVL, LFB) | P(SNOOP, NONE), /* 0x02: LFB hit */ @@ -70,6 +71,14 @@ static const u64 pebs_data_source[] = { OP_LH | P(LVL, UNC) | P(SNOOP, NONE), /* 0x0f: uncached */ }; +/* Patch up minor differences in the bits */ +void __init intel_pmu_pebs_data_source_nhm(void) +{ + pebs_data_source[0x05] = OP_LH | P(LVL, L3) | P(SNOOP, HIT); + pebs_data_source[0x06] = OP_LH | P(LVL, L3) | P(SNOOP, HITM); + pebs_data_source[0x07] = OP_LH | P(LVL, L3) | P(SNOOP, HITM); +} + static u64 precise_store_data(u64 status) { union intel_x86_pebs_dse dse; @@ -269,7 +278,7 @@ static int alloc_pebs_buffer(int cpu) if (!x86_pmu.pebs) return 0; - buffer = kzalloc_node(PEBS_BUFFER_SIZE, GFP_KERNEL, node); + buffer = kzalloc_node(x86_pmu.pebs_buffer_size, GFP_KERNEL, node); if (unlikely(!buffer)) return -ENOMEM; @@ -286,7 +295,7 @@ static int alloc_pebs_buffer(int cpu) per_cpu(insn_buffer, cpu) = ibuffer; } - max = PEBS_BUFFER_SIZE / x86_pmu.pebs_record_size; + max = x86_pmu.pebs_buffer_size / x86_pmu.pebs_record_size; ds->pebs_buffer_base = (u64)(unsigned long)buffer; ds->pebs_index = ds->pebs_buffer_base; @@ -1296,6 +1305,7 @@ void __init intel_ds_init(void) x86_pmu.bts = boot_cpu_has(X86_FEATURE_BTS); x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS); + x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE; if (x86_pmu.pebs) { char pebs_type = x86_pmu.intel_cap.pebs_trap ? '+' : '-'; int format = x86_pmu.intel_cap.pebs_format; @@ -1304,6 +1314,14 @@ void __init intel_ds_init(void) case 0: printk(KERN_CONT "PEBS fmt0%c, ", pebs_type); x86_pmu.pebs_record_size = sizeof(struct pebs_record_core); + /* + * Using >PAGE_SIZE buffers makes the WRMSR to + * PERF_GLOBAL_CTRL in intel_pmu_enable_all() + * mysteriously hang on Core2. + * + * As a workaround, we don't do this. + */ + x86_pmu.pebs_buffer_size = PAGE_SIZE; x86_pmu.drain_pebs = intel_pmu_drain_pebs_core; break; diff --git a/arch/x86/kernel/cpu/perf_event_intel_pt.c b/arch/x86/kernel/cpu/perf_event_intel_pt.c index 868e1194337f..49e35d003b74 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_pt.c +++ b/arch/x86/kernel/cpu/perf_event_intel_pt.c @@ -694,6 +694,7 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf, /* clear STOP and INT from current entry */ buf->topa_index[buf->stop_pos]->stop = 0; + buf->topa_index[buf->stop_pos]->intr = 0; buf->topa_index[buf->intr_pos]->intr = 0; /* how many pages till the STOP marker */ @@ -718,6 +719,7 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf, buf->intr_pos = idx; buf->topa_index[buf->stop_pos]->stop = 1; + buf->topa_index[buf->stop_pos]->intr = 1; buf->topa_index[buf->intr_pos]->intr = 1; return 0; diff --git a/arch/x86/kernel/cpu/perf_event_knc.c b/arch/x86/kernel/cpu/perf_event_knc.c index 5b0c232d1ee6..b931095e86d4 100644 --- a/arch/x86/kernel/cpu/perf_event_knc.c +++ b/arch/x86/kernel/cpu/perf_event_knc.c @@ -263,7 +263,9 @@ again: goto again; done: - knc_pmu_enable_all(0); + /* Only restore PMU state when it's active. See x86_pmu_disable(). */ + if (cpuc->enabled) + knc_pmu_enable_all(0); return handled; } diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c index 37dae792dbbe..589b3193f102 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -96,9 +96,14 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) SYSCALL_DEFINE1(iopl, unsigned int, level) { struct pt_regs *regs = current_pt_regs(); - unsigned int old = (regs->flags >> 12) & 3; struct thread_struct *t = ¤t->thread; + /* + * Careful: the IOPL bits in regs->flags are undefined under Xen PV + * and changing them has no effect. + */ + unsigned int old = t->iopl >> X86_EFLAGS_IOPL_BIT; + if (level > 3) return -EINVAL; /* Trying to gain more privileges? */ @@ -106,8 +111,9 @@ SYSCALL_DEFINE1(iopl, unsigned int, level) if (!capable(CAP_SYS_RAWIO)) return -EPERM; } - regs->flags = (regs->flags & ~X86_EFLAGS_IOPL) | (level << 12); - t->iopl = level << 12; + regs->flags = (regs->flags & ~X86_EFLAGS_IOPL) | + (level << X86_EFLAGS_IOPL_BIT); + t->iopl = level << X86_EFLAGS_IOPL_BIT; set_iopl_mask(t->iopl); return 0; diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index e835d263a33b..4cbb60fbff3e 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -48,6 +48,7 @@ #include <asm/syscalls.h> #include <asm/debugreg.h> #include <asm/switch_to.h> +#include <asm/xen/hypervisor.h> asmlinkage extern void ret_from_fork(void); @@ -411,6 +412,17 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV)) __switch_to_xtra(prev_p, next_p, tss); +#ifdef CONFIG_XEN + /* + * On Xen PV, IOPL bits in pt_regs->flags have no effect, and + * current_pt_regs()->flags may not match the current task's + * intended IOPL. We need to switch it manually. + */ + if (unlikely(static_cpu_has(X86_FEATURE_XENPV) && + prev->iopl != next->iopl)) + xen_set_iopl_mask(next->iopl); +#endif + if (static_cpu_has_bug(X86_BUG_SYSRET_SS_ATTRS)) { /* * AMD CPUs have a misfeature: SYSRET sets the SS selector but diff --git a/arch/x86/kernel/sysfb_efi.c b/arch/x86/kernel/sysfb_efi.c index b285d4e8c68e..5da924bbf0a0 100644 --- a/arch/x86/kernel/sysfb_efi.c +++ b/arch/x86/kernel/sysfb_efi.c @@ -106,14 +106,24 @@ static int __init efifb_set_system(const struct dmi_system_id *id) continue; for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) { resource_size_t start, end; + unsigned long flags; + + flags = pci_resource_flags(dev, i); + if (!(flags & IORESOURCE_MEM)) + continue; + + if (flags & IORESOURCE_UNSET) + continue; + + if (pci_resource_len(dev, i) == 0) + continue; start = pci_resource_start(dev, i); - if (start == 0) - break; end = pci_resource_end(dev, i); if (screen_info.lfb_base >= start && screen_info.lfb_base < end) { found_bar = 1; + break; } } } diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c index 92ae6acac8a7..6aa0f4d9eea6 100644 --- a/arch/x86/kernel/tsc_msr.c +++ b/arch/x86/kernel/tsc_msr.c @@ -92,7 +92,7 @@ unsigned long try_msr_calibrate_tsc(void) if (freq_desc_tables[cpu_index].msr_plat) { rdmsr(MSR_PLATFORM_INFO, lo, hi); - ratio = (lo >> 8) & 0x1f; + ratio = (lo >> 8) & 0xff; } else { rdmsr(MSR_IA32_PERF_STATUS, lo, hi); ratio = (hi >> 8) & 0x1f; diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 6525e926f566..2e1fd586b895 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -509,6 +509,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, do_cpuid_1_ent(&entry[i], function, idx); if (idx == 1) { entry[i].eax &= kvm_supported_word10_x86_features; + cpuid_mask(&entry[i].eax, 10); entry[i].ebx = 0; if (entry[i].eax & (F(XSAVES)|F(XSAVEC))) entry[i].ebx = diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index b0ea42b78ccd..ab5318727579 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -245,7 +245,7 @@ static void kvm_pit_ack_irq(struct kvm_irq_ack_notifier *kian) * PIC is being reset. Handle it gracefully here */ atomic_inc(&ps->pending); - else if (value > 0) + else if (value > 0 && ps->reinject) /* in this case, we had multiple outstanding pit interrupts * that we needed to inject. Reinject */ @@ -288,7 +288,9 @@ static void pit_do_work(struct kthread_work *work) * last one has been acked. */ spin_lock(&ps->inject_lock); - if (ps->irq_ack) { + if (!ps->reinject) + inject = 1; + else if (ps->irq_ack) { ps->irq_ack = 0; inject = 1; } @@ -317,10 +319,10 @@ static enum hrtimer_restart pit_timer_fn(struct hrtimer *data) struct kvm_kpit_state *ps = container_of(data, struct kvm_kpit_state, timer); struct kvm_pit *pt = ps->kvm->arch.vpit; - if (ps->reinject || !atomic_read(&ps->pending)) { + if (ps->reinject) atomic_inc(&ps->pending); - queue_kthread_work(&pt->worker, &pt->expired); - } + + queue_kthread_work(&pt->worker, &pt->expired); if (ps->is_periodic) { hrtimer_add_expires_ns(&ps->timer, ps->period); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index e7c2c1428a69..8eb8a934b531 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3754,13 +3754,15 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu, void reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) { + bool uses_nx = context->nx || context->base_role.smep_andnot_wp; + /* * Passing "true" to the last argument is okay; it adds a check * on bit 8 of the SPTEs which KVM doesn't use anyway. */ __reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check, boot_cpu_data.x86_phys_bits, - context->shadow_root_level, context->nx, + context->shadow_root_level, uses_nx, guest_cpuid_has_gbpages(vcpu), is_pse(vcpu), true); } diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index 3f8c732117ec..c146f3c262c3 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -44,8 +44,6 @@ static bool msr_mtrr_valid(unsigned msr) case MSR_MTRRdefType: case MSR_IA32_CR_PAT: return true; - case 0x2f8: - return true; } return false; } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 5fd846cd6e0e..f314e9b9660b 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1748,6 +1748,13 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, return; } break; + case MSR_IA32_PEBS_ENABLE: + /* PEBS needs a quiescent period after being disabled (to write + * a record). Disabling PEBS through VMX MSR swapping doesn't + * provide that period, so a CPU could write host's record into + * guest's memory. + */ + wrmsrl(MSR_IA32_PEBS_ENABLE, 0); } for (i = 0; i < m->nr; ++i) @@ -1785,26 +1792,31 @@ static void reload_tss(void) static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) { - u64 guest_efer; - u64 ignore_bits; + u64 guest_efer = vmx->vcpu.arch.efer; + u64 ignore_bits = 0; - guest_efer = vmx->vcpu.arch.efer; + if (!enable_ept) { + /* + * NX is needed to handle CR0.WP=1, CR4.SMEP=1. Testing + * host CPUID is more efficient than testing guest CPUID + * or CR4. Host SMEP is anyway a requirement for guest SMEP. + */ + if (boot_cpu_has(X86_FEATURE_SMEP)) + guest_efer |= EFER_NX; + else if (!(guest_efer & EFER_NX)) + ignore_bits |= EFER_NX; + } /* - * NX is emulated; LMA and LME handled by hardware; SCE meaningless - * outside long mode + * LMA and LME handled by hardware; SCE meaningless outside long mode. */ - ignore_bits = EFER_NX | EFER_SCE; + ignore_bits |= EFER_SCE; #ifdef CONFIG_X86_64 ignore_bits |= EFER_LMA | EFER_LME; /* SCE is meaningful only in long mode on Intel */ if (guest_efer & EFER_LMA) ignore_bits &= ~(u64)EFER_SCE; #endif - guest_efer &= ~ignore_bits; - guest_efer |= host_efer & ignore_bits; - vmx->guest_msrs[efer_offset].data = guest_efer; - vmx->guest_msrs[efer_offset].mask = ~ignore_bits; clear_atomic_switch_msr(vmx, MSR_EFER); @@ -1815,16 +1827,21 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) */ if (cpu_has_load_ia32_efer || (enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX))) { - guest_efer = vmx->vcpu.arch.efer; if (!(guest_efer & EFER_LMA)) guest_efer &= ~EFER_LME; if (guest_efer != host_efer) add_atomic_switch_msr(vmx, MSR_EFER, guest_efer, host_efer); return false; - } + } else { + guest_efer &= ~ignore_bits; + guest_efer |= host_efer & ignore_bits; - return true; + vmx->guest_msrs[efer_offset].data = guest_efer; + vmx->guest_msrs[efer_offset].mask = ~ignore_bits; + + return true; + } } static unsigned long segment_base(u16 selector) @@ -2620,8 +2637,15 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) } else vmx->nested.nested_vmx_ept_caps = 0; + /* + * Old versions of KVM use the single-context version without + * checking for support, so declare that it is supported even + * though it is treated as global context. The alternative is + * not failing the single-context invvpid, and it is worse. + */ if (enable_vpid) vmx->nested.nested_vmx_vpid_caps = VMX_VPID_INVVPID_BIT | + VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT | VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT; else vmx->nested.nested_vmx_vpid_caps = 0; @@ -4930,8 +4954,8 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET; - vmx_set_cr0(vcpu, cr0); /* enter rmode */ vmx->vcpu.arch.cr0 = cr0; + vmx_set_cr0(vcpu, cr0); /* enter rmode */ vmx_set_cr4(vcpu, 0); vmx_set_efer(vcpu, 0); vmx_fpu_activate(vcpu); @@ -7323,6 +7347,7 @@ static int handle_invept(struct kvm_vcpu *vcpu) if (!(types & (1UL << type))) { nested_vmx_failValid(vcpu, VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); + skip_emulated_instruction(vcpu); return 1; } @@ -7381,6 +7406,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) if (!(types & (1UL << type))) { nested_vmx_failValid(vcpu, VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); + skip_emulated_instruction(vcpu); return 1; } @@ -7397,12 +7423,17 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) } switch (type) { + case VMX_VPID_EXTENT_SINGLE_CONTEXT: + /* + * Old versions of KVM use the single-context version so we + * have to support it; just treat it the same as all-context. + */ case VMX_VPID_EXTENT_ALL_CONTEXT: __vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02); nested_vmx_succeed(vcpu); break; default: - /* Trap single context invalidation invvpid calls */ + /* Trap individual address invalidation invvpid calls */ BUG_ON(1); break; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index d2945024ed33..605cea75eb0d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -697,7 +697,6 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) if ((xcr0 & XFEATURE_MASK_AVX512) != XFEATURE_MASK_AVX512) return 1; } - kvm_put_guest_xcr0(vcpu); vcpu->arch.xcr0 = xcr0; if ((xcr0 ^ old_xcr0) & XFEATURE_MASK_EXTEND) @@ -2736,6 +2735,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) } kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); + vcpu->arch.switch_db_regs |= KVM_DEBUGREG_RELOAD; } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) @@ -6023,12 +6023,10 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) } /* try to inject new event if pending */ - if (vcpu->arch.nmi_pending) { - if (kvm_x86_ops->nmi_allowed(vcpu)) { - --vcpu->arch.nmi_pending; - vcpu->arch.nmi_injected = true; - kvm_x86_ops->set_nmi(vcpu); - } + if (vcpu->arch.nmi_pending && kvm_x86_ops->nmi_allowed(vcpu)) { + --vcpu->arch.nmi_pending; + vcpu->arch.nmi_injected = true; + kvm_x86_ops->set_nmi(vcpu); } else if (kvm_cpu_has_injectable_intr(vcpu)) { /* * Because interrupts can be injected asynchronously, we are @@ -6473,10 +6471,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (inject_pending_event(vcpu, req_int_win) != 0) req_immediate_exit = true; /* enable NMI/IRQ window open exits if needed */ - else if (vcpu->arch.nmi_pending) - kvm_x86_ops->enable_nmi_window(vcpu); - else if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win) - kvm_x86_ops->enable_irq_window(vcpu); + else { + if (vcpu->arch.nmi_pending) + kvm_x86_ops->enable_nmi_window(vcpu); + if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win) + kvm_x86_ops->enable_irq_window(vcpu); + } if (kvm_lapic_enabled(vcpu)) { update_cr8_intercept(vcpu); @@ -6494,8 +6494,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_x86_ops->prepare_guest_switch(vcpu); if (vcpu->fpu_active) kvm_load_guest_fpu(vcpu); - kvm_load_guest_xcr0(vcpu); - vcpu->mode = IN_GUEST_MODE; srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); @@ -6518,6 +6516,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) goto cancel_injection; } + kvm_load_guest_xcr0(vcpu); + if (req_immediate_exit) smp_send_reschedule(vcpu->cpu); @@ -6567,6 +6567,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); + kvm_put_guest_xcr0(vcpu); + /* Interrupt is enabled by handle_external_intr() */ kvm_x86_ops->handle_external_intr(vcpu); @@ -7214,7 +7216,6 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) * and assume host would use all available bits. * Guest xcr0 would be loaded later. */ - kvm_put_guest_xcr0(vcpu); vcpu->guest_fpu_loaded = 1; __kernel_fpu_begin(); __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state); @@ -7223,8 +7224,6 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) { - kvm_put_guest_xcr0(vcpu); - if (!vcpu->guest_fpu_loaded) { vcpu->fpu_counter = 0; return; diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c index 637ab34ed632..ddb2244b06a1 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -33,7 +33,7 @@ struct kmmio_fault_page { struct list_head list; struct kmmio_fault_page *release_next; - unsigned long page; /* location of the fault page */ + unsigned long addr; /* the requested address */ pteval_t old_presence; /* page presence prior to arming */ bool armed; @@ -70,9 +70,16 @@ unsigned int kmmio_count; static struct list_head kmmio_page_table[KMMIO_PAGE_TABLE_SIZE]; static LIST_HEAD(kmmio_probes); -static struct list_head *kmmio_page_list(unsigned long page) +static struct list_head *kmmio_page_list(unsigned long addr) { - return &kmmio_page_table[hash_long(page, KMMIO_PAGE_HASH_BITS)]; + unsigned int l; + pte_t *pte = lookup_address(addr, &l); + + if (!pte) + return NULL; + addr &= page_level_mask(l); + + return &kmmio_page_table[hash_long(addr, KMMIO_PAGE_HASH_BITS)]; } /* Accessed per-cpu */ @@ -98,15 +105,19 @@ static struct kmmio_probe *get_kmmio_probe(unsigned long addr) } /* You must be holding RCU read lock. */ -static struct kmmio_fault_page *get_kmmio_fault_page(unsigned long page) +static struct kmmio_fault_page *get_kmmio_fault_page(unsigned long addr) { struct list_head *head; struct kmmio_fault_page *f; + unsigned int l; + pte_t *pte = lookup_address(addr, &l); - page &= PAGE_MASK; - head = kmmio_page_list(page); + if (!pte) + return NULL; + addr &= page_level_mask(l); + head = kmmio_page_list(addr); list_for_each_entry_rcu(f, head, list) { - if (f->page == page) + if (f->addr == addr) return f; } return NULL; @@ -137,10 +148,10 @@ static void clear_pte_presence(pte_t *pte, bool clear, pteval_t *old) static int clear_page_presence(struct kmmio_fault_page *f, bool clear) { unsigned int level; - pte_t *pte = lookup_address(f->page, &level); + pte_t *pte = lookup_address(f->addr, &level); if (!pte) { - pr_err("no pte for page 0x%08lx\n", f->page); + pr_err("no pte for addr 0x%08lx\n", f->addr); return -1; } @@ -156,7 +167,7 @@ static int clear_page_presence(struct kmmio_fault_page *f, bool clear) return -1; } - __flush_tlb_one(f->page); + __flush_tlb_one(f->addr); return 0; } @@ -176,12 +187,12 @@ static int arm_kmmio_fault_page(struct kmmio_fault_page *f) int ret; WARN_ONCE(f->armed, KERN_ERR pr_fmt("kmmio page already armed.\n")); if (f->armed) { - pr_warning("double-arm: page 0x%08lx, ref %d, old %d\n", - f->page, f->count, !!f->old_presence); + pr_warning("double-arm: addr 0x%08lx, ref %d, old %d\n", + f->addr, f->count, !!f->old_presence); } ret = clear_page_presence(f, true); - WARN_ONCE(ret < 0, KERN_ERR pr_fmt("arming 0x%08lx failed.\n"), - f->page); + WARN_ONCE(ret < 0, KERN_ERR pr_fmt("arming at 0x%08lx failed.\n"), + f->addr); f->armed = true; return ret; } @@ -191,7 +202,7 @@ static void disarm_kmmio_fault_page(struct kmmio_fault_page *f) { int ret = clear_page_presence(f, false); WARN_ONCE(ret < 0, - KERN_ERR "kmmio disarming 0x%08lx failed.\n", f->page); + KERN_ERR "kmmio disarming at 0x%08lx failed.\n", f->addr); f->armed = false; } @@ -215,6 +226,12 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr) struct kmmio_context *ctx; struct kmmio_fault_page *faultpage; int ret = 0; /* default to fault not handled */ + unsigned long page_base = addr; + unsigned int l; + pte_t *pte = lookup_address(addr, &l); + if (!pte) + return -EINVAL; + page_base &= page_level_mask(l); /* * Preemption is now disabled to prevent process switch during @@ -227,7 +244,7 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr) preempt_disable(); rcu_read_lock(); - faultpage = get_kmmio_fault_page(addr); + faultpage = get_kmmio_fault_page(page_base); if (!faultpage) { /* * Either this page fault is not caused by kmmio, or @@ -239,7 +256,7 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr) ctx = &get_cpu_var(kmmio_ctx); if (ctx->active) { - if (addr == ctx->addr) { + if (page_base == ctx->addr) { /* * A second fault on the same page means some other * condition needs handling by do_page_fault(), the @@ -267,9 +284,9 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr) ctx->active++; ctx->fpage = faultpage; - ctx->probe = get_kmmio_probe(addr); + ctx->probe = get_kmmio_probe(page_base); ctx->saved_flags = (regs->flags & (X86_EFLAGS_TF | X86_EFLAGS_IF)); - ctx->addr = addr; + ctx->addr = page_base; if (ctx->probe && ctx->probe->pre_handler) ctx->probe->pre_handler(ctx->probe, regs, addr); @@ -354,12 +371,11 @@ out: } /* You must be holding kmmio_lock. */ -static int add_kmmio_fault_page(unsigned long page) +static int add_kmmio_fault_page(unsigned long addr) { struct kmmio_fault_page *f; - page &= PAGE_MASK; - f = get_kmmio_fault_page(page); + f = get_kmmio_fault_page(addr); if (f) { if (!f->count) arm_kmmio_fault_page(f); @@ -372,26 +388,25 @@ static int add_kmmio_fault_page(unsigned long page) return -1; f->count = 1; - f->page = page; + f->addr = addr; if (arm_kmmio_fault_page(f)) { kfree(f); return -1; } - list_add_rcu(&f->list, kmmio_page_list(f->page)); + list_add_rcu(&f->list, kmmio_page_list(f->addr)); return 0; } /* You must be holding kmmio_lock. */ -static void release_kmmio_fault_page(unsigned long page, +static void release_kmmio_fault_page(unsigned long addr, struct kmmio_fault_page **release_list) { struct kmmio_fault_page *f; - page &= PAGE_MASK; - f = get_kmmio_fault_page(page); + f = get_kmmio_fault_page(addr); if (!f) return; @@ -420,18 +435,27 @@ int register_kmmio_probe(struct kmmio_probe *p) int ret = 0; unsigned long size = 0; const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK); + unsigned int l; + pte_t *pte; spin_lock_irqsave(&kmmio_lock, flags); if (get_kmmio_probe(p->addr)) { ret = -EEXIST; goto out; } + + pte = lookup_address(p->addr, &l); + if (!pte) { + ret = -EINVAL; + goto out; + } + kmmio_count++; list_add_rcu(&p->list, &kmmio_probes); while (size < size_lim) { if (add_kmmio_fault_page(p->addr + size)) pr_err("Unable to set page fault.\n"); - size += PAGE_SIZE; + size += page_level_size(l); } out: spin_unlock_irqrestore(&kmmio_lock, flags); @@ -506,11 +530,17 @@ void unregister_kmmio_probe(struct kmmio_probe *p) const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK); struct kmmio_fault_page *release_list = NULL; struct kmmio_delayed_release *drelease; + unsigned int l; + pte_t *pte; + + pte = lookup_address(p->addr, &l); + if (!pte) + return; spin_lock_irqsave(&kmmio_lock, flags); while (size < size_lim) { release_kmmio_fault_page(p->addr + size, &release_list); - size += PAGE_SIZE; + size += page_level_size(l); } list_del_rcu(&p->list); kmmio_count--; diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index db20ee9a413a..b599a780a5a9 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -414,24 +414,30 @@ pmd_t *lookup_pmd_address(unsigned long address) phys_addr_t slow_virt_to_phys(void *__virt_addr) { unsigned long virt_addr = (unsigned long)__virt_addr; - unsigned long phys_addr, offset; + phys_addr_t phys_addr; + unsigned long offset; enum pg_level level; pte_t *pte; pte = lookup_address(virt_addr, &level); BUG_ON(!pte); + /* + * pXX_pfn() returns unsigned long, which must be cast to phys_addr_t + * before being left-shifted PAGE_SHIFT bits -- this trick is to + * make 32-PAE kernel work correctly. + */ switch (level) { case PG_LEVEL_1G: - phys_addr = pud_pfn(*(pud_t *)pte) << PAGE_SHIFT; + phys_addr = (phys_addr_t)pud_pfn(*(pud_t *)pte) << PAGE_SHIFT; offset = virt_addr & ~PUD_PAGE_MASK; break; case PG_LEVEL_2M: - phys_addr = pmd_pfn(*(pmd_t *)pte) << PAGE_SHIFT; + phys_addr = (phys_addr_t)pmd_pfn(*(pmd_t *)pte) << PAGE_SHIFT; offset = virt_addr & ~PMD_PAGE_MASK; break; default: - phys_addr = pte_pfn(*pte) << PAGE_SHIFT; + phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT; offset = virt_addr & ~PAGE_MASK; } diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 8f4cc3dfac32..5fb6adaaa796 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -106,8 +106,6 @@ static void flush_tlb_func(void *info) if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm)) return; - if (!f->flush_end) - f->flush_end = f->flush_start + PAGE_SIZE; count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) { @@ -135,12 +133,20 @@ void native_flush_tlb_others(const struct cpumask *cpumask, unsigned long end) { struct flush_tlb_info info; + + if (end == 0) + end = start + PAGE_SIZE; info.flush_mm = mm; info.flush_start = start; info.flush_end = end; count_vm_tlb_event(NR_TLB_REMOTE_FLUSH); - trace_tlb_flush(TLB_REMOTE_SEND_IPI, end - start); + if (end == TLB_FLUSH_ALL) + trace_tlb_flush(TLB_REMOTE_SEND_IPI, TLB_FLUSH_ALL); + else + trace_tlb_flush(TLB_REMOTE_SEND_IPI, + (end - start) >> PAGE_SHIFT); + if (is_uv_system()) { unsigned int cpu; diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index eccd4d99e6a4..8fd6f44aee83 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -673,28 +673,22 @@ int pcibios_add_device(struct pci_dev *dev) return 0; } -int pcibios_alloc_irq(struct pci_dev *dev) +int pcibios_enable_device(struct pci_dev *dev, int mask) { - /* - * If the PCI device was already claimed by core code and has - * MSI enabled, probing of the pcibios IRQ will overwrite - * dev->irq. So bail out if MSI is already enabled. - */ - if (pci_dev_msi_enabled(dev)) - return -EBUSY; + int err; - return pcibios_enable_irq(dev); -} + if ((err = pci_enable_resources(dev, mask)) < 0) + return err; -void pcibios_free_irq(struct pci_dev *dev) -{ - if (pcibios_disable_irq) - pcibios_disable_irq(dev); + if (!pci_dev_msi_enabled(dev)) + return pcibios_enable_irq(dev); + return 0; } -int pcibios_enable_device(struct pci_dev *dev, int mask) +void pcibios_disable_device (struct pci_dev *dev) { - return pci_enable_resources(dev, mask); + if (!pci_dev_msi_enabled(dev) && pcibios_disable_irq) + pcibios_disable_irq(dev); } int pci_ext_cfg_avail(void) diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index e58565556703..0ae7e9fa348d 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -540,3 +540,10 @@ static void twinhead_reserve_killing_zone(struct pci_dev *dev) } } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x27B9, twinhead_reserve_killing_zone); + +static void pci_bdwep_bar(struct pci_dev *dev) +{ + dev->non_compliant_bars = 1; +} +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fa0, pci_bdwep_bar); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, pci_bdwep_bar); diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c index 0d24e7c10145..8b93e634af84 100644 --- a/arch/x86/pci/intel_mid_pci.c +++ b/arch/x86/pci/intel_mid_pci.c @@ -215,7 +215,7 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) int polarity; int ret; - if (pci_has_managed_irq(dev)) + if (dev->irq_managed && dev->irq > 0) return 0; switch (intel_mid_identify_cpu()) { @@ -256,13 +256,10 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) static void intel_mid_pci_irq_disable(struct pci_dev *dev) { - if (pci_has_managed_irq(dev)) { + if (!mp_should_keep_irq(&dev->dev) && dev->irq_managed && + dev->irq > 0) { mp_unmap_irq(dev->irq); dev->irq_managed = 0; - /* - * Don't reset dev->irq here, otherwise - * intel_mid_pci_irq_enable() will fail on next call. - */ } } diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index 32e70343e6fd..9bd115484745 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -1202,7 +1202,7 @@ static int pirq_enable_irq(struct pci_dev *dev) struct pci_dev *temp_dev; int irq; - if (pci_has_managed_irq(dev)) + if (dev->irq_managed && dev->irq > 0) return 0; irq = IO_APIC_get_PCI_irq_vector(dev->bus->number, @@ -1230,7 +1230,8 @@ static int pirq_enable_irq(struct pci_dev *dev) } dev = temp_dev; if (irq >= 0) { - pci_set_managed_irq(dev, irq); + dev->irq_managed = 1; + dev->irq = irq; dev_info(&dev->dev, "PCI->APIC IRQ transform: " "INT %c -> IRQ %d\n", 'A' + pin - 1, irq); return 0; @@ -1256,10 +1257,24 @@ static int pirq_enable_irq(struct pci_dev *dev) return 0; } +bool mp_should_keep_irq(struct device *dev) +{ + if (dev->power.is_prepared) + return true; +#ifdef CONFIG_PM + if (dev->power.runtime_status == RPM_SUSPENDING) + return true; +#endif + + return false; +} + static void pirq_disable_irq(struct pci_dev *dev) { - if (io_apic_assign_pci_irqs && pci_has_managed_irq(dev)) { + if (io_apic_assign_pci_irqs && !mp_should_keep_irq(&dev->dev) && + dev->irq_managed && dev->irq) { mp_unmap_irq(dev->irq); - pci_reset_managed_irq(dev); + dev->irq = 0; + dev->irq_managed = 0; } } diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index ff31ab464213..c6d6efed392a 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -488,8 +488,11 @@ int __init pci_xen_initial_domain(void) #endif __acpi_register_gsi = acpi_register_gsi_xen; __acpi_unregister_gsi = NULL; - /* Pre-allocate legacy irqs */ - for (irq = 0; irq < nr_legacy_irqs(); irq++) { + /* + * Pre-allocate the legacy IRQs. Use NR_LEGACY_IRQS here + * because we don't have a PIC and thus nr_legacy_irqs() is zero. + */ + for (irq = 0; irq < NR_IRQS_LEGACY; irq++) { int trigger, polarity; if (acpi_get_override_irq(irq, &trigger, &polarity) == -1) diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index b7de78bdc09c..beab8c706ac9 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -961,7 +961,7 @@ static void xen_load_sp0(struct tss_struct *tss, tss->x86_tss.sp0 = thread->sp0; } -static void xen_set_iopl_mask(unsigned mask) +void xen_set_iopl_mask(unsigned mask) { struct physdev_set_iopl set_iopl; diff --git a/arch/xtensa/kernel/head.S b/arch/xtensa/kernel/head.S index 9ed55649ac8e..05e1df943856 100644 --- a/arch/xtensa/kernel/head.S +++ b/arch/xtensa/kernel/head.S @@ -128,7 +128,7 @@ ENTRY(_startup) wsr a0, icountlevel .set _index, 0 - .rept XCHAL_NUM_DBREAK - 1 + .rept XCHAL_NUM_DBREAK wsr a0, SREG_DBREAKC + _index .set _index, _index + 1 .endr diff --git a/arch/xtensa/mm/cache.c b/arch/xtensa/mm/cache.c index d75aa1476da7..1a804a2f9a5b 100644 --- a/arch/xtensa/mm/cache.c +++ b/arch/xtensa/mm/cache.c @@ -97,11 +97,11 @@ void clear_user_highpage(struct page *page, unsigned long vaddr) unsigned long paddr; void *kvaddr = coherent_kvaddr(page, TLBTEMP_BASE_1, vaddr, &paddr); - pagefault_disable(); + preempt_disable(); kmap_invalidate_coherent(page, vaddr); set_bit(PG_arch_1, &page->flags); clear_page_alias(kvaddr, paddr); - pagefault_enable(); + preempt_enable(); } void copy_user_highpage(struct page *dst, struct page *src, @@ -113,11 +113,11 @@ void copy_user_highpage(struct page *dst, struct page *src, void *src_vaddr = coherent_kvaddr(src, TLBTEMP_BASE_2, vaddr, &src_paddr); - pagefault_disable(); + preempt_disable(); kmap_invalidate_coherent(dst, vaddr); set_bit(PG_arch_1, &dst->flags); copy_page_alias(dst_vaddr, src_vaddr, dst_paddr, src_paddr); - pagefault_enable(); + preempt_enable(); } #endif /* DCACHE_WAY_SIZE > PAGE_SIZE */ diff --git a/arch/xtensa/platforms/iss/console.c b/arch/xtensa/platforms/iss/console.c index 70cb408bc20d..92d785fefb6d 100644 --- a/arch/xtensa/platforms/iss/console.c +++ b/arch/xtensa/platforms/iss/console.c @@ -100,21 +100,23 @@ static void rs_poll(unsigned long priv) { struct tty_port *port = (struct tty_port *)priv; int i = 0; + int rd = 1; unsigned char c; spin_lock(&timer_lock); while (simc_poll(0)) { - simc_read(0, &c, 1); + rd = simc_read(0, &c, 1); + if (rd <= 0) + break; tty_insert_flip_char(port, c, TTY_NORMAL); i++; } if (i) tty_flip_buffer_push(port); - - - mod_timer(&serial_timer, jiffies + SERIAL_TIMER_VALUE); + if (rd) + mod_timer(&serial_timer, jiffies + SERIAL_TIMER_VALUE); spin_unlock(&timer_lock); } |