diff options
Diffstat (limited to 'arch')
71 files changed, 902 insertions, 434 deletions
diff --git a/arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts b/arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts index b10dccd0958f..3b1baa8605a7 100644 --- a/arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts +++ b/arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts @@ -11,6 +11,7 @@ #include "sama5d2-pinfunc.h" #include <dt-bindings/mfd/atmel-flexcom.h> #include <dt-bindings/gpio/gpio.h> +#include <dt-bindings/pinctrl/at91.h> / { model = "Atmel SAMA5D2 PTC EK"; @@ -299,6 +300,7 @@ <PIN_PA30__NWE_NANDWE>, <PIN_PB2__NRD_NANDOE>; bias-pull-up; + atmel,drive-strength = <ATMEL_PIO_DRVSTR_ME>; }; ale_cle_rdy_cs { diff --git a/arch/arm/boot/dts/bcm63138.dtsi b/arch/arm/boot/dts/bcm63138.dtsi index 43ee992ccdcf..6df61518776f 100644 --- a/arch/arm/boot/dts/bcm63138.dtsi +++ b/arch/arm/boot/dts/bcm63138.dtsi @@ -106,21 +106,23 @@ global_timer: timer@1e200 { compatible = "arm,cortex-a9-global-timer"; reg = <0x1e200 0x20>; - interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_PPI 11 IRQ_TYPE_EDGE_RISING>; clocks = <&axi_clk>; }; local_timer: local-timer@1e600 { compatible = "arm,cortex-a9-twd-timer"; reg = <0x1e600 0x20>; - interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(2) | + IRQ_TYPE_EDGE_RISING)>; clocks = <&axi_clk>; }; twd_watchdog: watchdog@1e620 { compatible = "arm,cortex-a9-twd-wdt"; reg = <0x1e620 0x20>; - interrupts = <GIC_PPI 14 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(2) | + IRQ_TYPE_LEVEL_HIGH)>; }; armpll: armpll { @@ -158,7 +160,7 @@ serial0: serial@600 { compatible = "brcm,bcm6345-uart"; reg = <0x600 0x1b>; - interrupts = <GIC_SPI 32 0>; + interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>; clocks = <&periph_clk>; clock-names = "periph"; status = "disabled"; @@ -167,7 +169,7 @@ serial1: serial@620 { compatible = "brcm,bcm6345-uart"; reg = <0x620 0x1b>; - interrupts = <GIC_SPI 33 0>; + interrupts = <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>; clocks = <&periph_clk>; clock-names = "periph"; status = "disabled"; @@ -180,7 +182,7 @@ reg = <0x2000 0x600>, <0xf0 0x10>; reg-names = "nand", "nand-int-base"; status = "disabled"; - interrupts = <GIC_SPI 38 0>; + interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "nand"; }; diff --git a/arch/arm/boot/dts/sama5d3_emac.dtsi b/arch/arm/boot/dts/sama5d3_emac.dtsi index 7cb235ef0fb6..6e9e1c2f9def 100644 --- a/arch/arm/boot/dts/sama5d3_emac.dtsi +++ b/arch/arm/boot/dts/sama5d3_emac.dtsi @@ -41,7 +41,7 @@ }; macb1: ethernet@f802c000 { - compatible = "cdns,at91sam9260-macb", "cdns,macb"; + compatible = "atmel,sama5d3-macb", "cdns,at91sam9260-macb", "cdns,macb"; reg = <0xf802c000 0x100>; interrupts = <35 IRQ_TYPE_LEVEL_HIGH 3>; pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/stm32mp157c.dtsi b/arch/arm/boot/dts/stm32mp157c.dtsi index 661be948ab74..185541a5b69f 100644 --- a/arch/arm/boot/dts/stm32mp157c.dtsi +++ b/arch/arm/boot/dts/stm32mp157c.dtsi @@ -1078,8 +1078,8 @@ interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>; clocks = <&rcc SPI6_K>; resets = <&rcc SPI6_R>; - dmas = <&mdma1 34 0x0 0x40008 0x0 0x0 0>, - <&mdma1 35 0x0 0x40002 0x0 0x0 0>; + dmas = <&mdma1 34 0x0 0x40008 0x0 0x0>, + <&mdma1 35 0x0 0x40002 0x0 0x0>; dma-names = "rx", "tx"; status = "disabled"; }; diff --git a/arch/arm/boot/dts/sun8i-r40.dtsi b/arch/arm/boot/dts/sun8i-r40.dtsi index ffd9f00f74a4..5f547c161baf 100644 --- a/arch/arm/boot/dts/sun8i-r40.dtsi +++ b/arch/arm/boot/dts/sun8i-r40.dtsi @@ -800,8 +800,7 @@ }; hdmi_phy: hdmi-phy@1ef0000 { - compatible = "allwinner,sun8i-r40-hdmi-phy", - "allwinner,sun50i-a64-hdmi-phy"; + compatible = "allwinner,sun8i-r40-hdmi-phy"; reg = <0x01ef0000 0x10000>; clocks = <&ccu CLK_BUS_HDMI1>, <&ccu CLK_HDMI_SLOW>, <&ccu 7>, <&ccu 16>; diff --git a/arch/arm/mach-mmp/devices.c b/arch/arm/mach-mmp/devices.c index 671c7a09ab3d..0fca63c80e1a 100644 --- a/arch/arm/mach-mmp/devices.c +++ b/arch/arm/mach-mmp/devices.c @@ -277,21 +277,12 @@ struct platform_device pxa168_device_u2o = { #if IS_ENABLED(CONFIG_USB_EHCI_MV_U2O) struct resource pxa168_u2oehci_resources[] = { - /* regbase */ [0] = { - .start = PXA168_U2O_REGBASE + U2x_CAPREGS_OFFSET, + .start = PXA168_U2O_REGBASE, .end = PXA168_U2O_REGBASE + USB_REG_RANGE, .flags = IORESOURCE_MEM, - .name = "capregs", }, - /* phybase */ [1] = { - .start = PXA168_U2O_PHYBASE, - .end = PXA168_U2O_PHYBASE + USB_PHY_RANGE, - .flags = IORESOURCE_MEM, - .name = "phyregs", - }, - [2] = { .start = IRQ_PXA168_USB1, .end = IRQ_PXA168_USB1, .flags = IORESOURCE_IRQ, diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c index fc91205ff46c..5bf9443cfbaa 100644 --- a/arch/arm/mm/ioremap.c +++ b/arch/arm/mm/ioremap.c @@ -473,7 +473,7 @@ void pci_ioremap_set_mem_type(int mem_type) int pci_ioremap_io(unsigned int offset, phys_addr_t phys_addr) { - BUG_ON(offset + SZ_64K > IO_SPACE_LIMIT); + BUG_ON(offset + SZ_64K - 1 > IO_SPACE_LIMIT); return ioremap_page_range(PCI_IO_VIRT_BASE + offset, PCI_IO_VIRT_BASE + offset + SZ_64K, diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index fbc74b5fa3ed..8edf93b4490f 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -413,3 +413,4 @@ 396 common pkey_free sys_pkey_free 397 common statx sys_statx 398 common rseq sys_rseq +399 common io_pgetevents sys_io_pgetevents diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 07256b08226c..a6c9fbaeaefc 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -57,6 +57,45 @@ static u64 core_reg_offset_from_id(u64 id) return id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_CORE); } +static int validate_core_offset(const struct kvm_one_reg *reg) +{ + u64 off = core_reg_offset_from_id(reg->id); + int size; + + switch (off) { + case KVM_REG_ARM_CORE_REG(regs.regs[0]) ... + KVM_REG_ARM_CORE_REG(regs.regs[30]): + case KVM_REG_ARM_CORE_REG(regs.sp): + case KVM_REG_ARM_CORE_REG(regs.pc): + case KVM_REG_ARM_CORE_REG(regs.pstate): + case KVM_REG_ARM_CORE_REG(sp_el1): + case KVM_REG_ARM_CORE_REG(elr_el1): + case KVM_REG_ARM_CORE_REG(spsr[0]) ... + KVM_REG_ARM_CORE_REG(spsr[KVM_NR_SPSR - 1]): + size = sizeof(__u64); + break; + + case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ... + KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]): + size = sizeof(__uint128_t); + break; + + case KVM_REG_ARM_CORE_REG(fp_regs.fpsr): + case KVM_REG_ARM_CORE_REG(fp_regs.fpcr): + size = sizeof(__u32); + break; + + default: + return -EINVAL; + } + + if (KVM_REG_SIZE(reg->id) == size && + IS_ALIGNED(off, size / sizeof(__u32))) + return 0; + + return -EINVAL; +} + static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { /* @@ -76,6 +115,9 @@ static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) (off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs) return -ENOENT; + if (validate_core_offset(reg)) + return -EINVAL; + if (copy_to_user(uaddr, ((u32 *)regs) + off, KVM_REG_SIZE(reg->id))) return -EFAULT; @@ -98,6 +140,9 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) (off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs) return -ENOENT; + if (validate_core_offset(reg)) + return -EINVAL; + if (KVM_REG_SIZE(reg->id) > sizeof(tmp)) return -EINVAL; @@ -107,17 +152,25 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) } if (off == KVM_REG_ARM_CORE_REG(regs.pstate)) { - u32 mode = (*(u32 *)valp) & PSR_AA32_MODE_MASK; + u64 mode = (*(u64 *)valp) & PSR_AA32_MODE_MASK; switch (mode) { case PSR_AA32_MODE_USR: + if (!system_supports_32bit_el0()) + return -EINVAL; + break; case PSR_AA32_MODE_FIQ: case PSR_AA32_MODE_IRQ: case PSR_AA32_MODE_SVC: case PSR_AA32_MODE_ABT: case PSR_AA32_MODE_UND: + if (!vcpu_el1_is_32bit(vcpu)) + return -EINVAL; + break; case PSR_MODE_EL0t: case PSR_MODE_EL1t: case PSR_MODE_EL1h: + if (vcpu_el1_is_32bit(vcpu)) + return -EINVAL; break; default: err = -EINVAL; diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 192b3ba07075..f58ea503ad01 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -117,11 +117,14 @@ static pte_t get_clear_flush(struct mm_struct *mm, /* * If HW_AFDBM is enabled, then the HW could turn on - * the dirty bit for any page in the set, so check - * them all. All hugetlb entries are already young. + * the dirty or accessed bit for any page in the set, + * so check them all. */ if (pte_dirty(pte)) orig_pte = pte_mkdirty(orig_pte); + + if (pte_young(pte)) + orig_pte = pte_mkyoung(orig_pte); } if (valid) { @@ -320,11 +323,40 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm, return get_clear_flush(mm, addr, ptep, pgsize, ncontig); } +/* + * huge_ptep_set_access_flags will update access flags (dirty, accesssed) + * and write permission. + * + * For a contiguous huge pte range we need to check whether or not write + * permission has to change only on the first pte in the set. Then for + * all the contiguous ptes we need to check whether or not there is a + * discrepancy between dirty or young. + */ +static int __cont_access_flags_changed(pte_t *ptep, pte_t pte, int ncontig) +{ + int i; + + if (pte_write(pte) != pte_write(huge_ptep_get(ptep))) + return 1; + + for (i = 0; i < ncontig; i++) { + pte_t orig_pte = huge_ptep_get(ptep + i); + + if (pte_dirty(pte) != pte_dirty(orig_pte)) + return 1; + + if (pte_young(pte) != pte_young(orig_pte)) + return 1; + } + + return 0; +} + int huge_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte, int dirty) { - int ncontig, i, changed = 0; + int ncontig, i; size_t pgsize = 0; unsigned long pfn = pte_pfn(pte), dpfn; pgprot_t hugeprot; @@ -336,19 +368,23 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma, ncontig = find_num_contig(vma->vm_mm, addr, ptep, &pgsize); dpfn = pgsize >> PAGE_SHIFT; + if (!__cont_access_flags_changed(ptep, pte, ncontig)) + return 0; + orig_pte = get_clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig); - if (!pte_same(orig_pte, pte)) - changed = 1; - /* Make sure we don't lose the dirty state */ + /* Make sure we don't lose the dirty or young state */ if (pte_dirty(orig_pte)) pte = pte_mkdirty(pte); + if (pte_young(orig_pte)) + pte = pte_mkyoung(pte); + hugeprot = pte_pgprot(pte); for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) set_pte_at(vma->vm_mm, addr, ptep, pfn_pte(pfn, hugeprot)); - return changed; + return 1; } void huge_ptep_set_wrprotect(struct mm_struct *mm, diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 13a688fc8cd0..2fdc865ca374 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -1051,7 +1051,6 @@ static inline void vmemmap_remove_mapping(unsigned long start, return hash__vmemmap_remove_mapping(start, page_size); } #endif -struct page *realmode_pfn_to_page(unsigned long pfn); static inline pte_t pmd_pte(pmd_t pmd) { diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index ab3a4fba38e3..3d4b88cb8599 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -220,8 +220,6 @@ extern void iommu_del_device(struct device *dev); extern int __init tce_iommu_bus_notifier_init(void); extern long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry, unsigned long *hpa, enum dma_data_direction *direction); -extern long iommu_tce_xchg_rm(struct iommu_table *tbl, unsigned long entry, - unsigned long *hpa, enum dma_data_direction *direction); #else static inline void iommu_register_group(struct iommu_table_group *table_group, int pci_domain_number, diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index b2f89b621b15..b694d6af1150 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -38,6 +38,7 @@ extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem, unsigned long ua, unsigned int pageshift, unsigned long *hpa); extern long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem, unsigned long ua, unsigned int pageshift, unsigned long *hpa); +extern void mm_iommu_ua_mark_dirty_rm(struct mm_struct *mm, unsigned long ua); extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem); extern void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem); #endif diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index 1a951b00465d..1fffbba8d6a5 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -9,6 +9,7 @@ extern void ppc_printk_progress(char *s, unsigned short hex); extern unsigned int rtas_data; extern unsigned long long memory_limit; +extern bool init_mem_is_free; extern unsigned long klimit; extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask); diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index ea04dfb8c092..2d8fc8c9da7a 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1314,9 +1314,7 @@ EXC_REAL_BEGIN(denorm_exception_hv, 0x1500, 0x100) #ifdef CONFIG_PPC_DENORMALISATION mfspr r10,SPRN_HSRR1 - mfspr r11,SPRN_HSRR0 /* save HSRR0 */ andis. r10,r10,(HSRR1_DENORM)@h /* denorm? */ - addi r11,r11,-4 /* HSRR0 is next instruction */ bne+ denorm_assist #endif @@ -1382,6 +1380,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) */ XVCPSGNDP32(32) denorm_done: + mfspr r11,SPRN_HSRR0 + subi r11,r11,4 mtspr SPRN_HSRR0,r11 mtcrf 0x80,r9 ld r9,PACA_EXGEN+EX_R9(r13) diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index af7a20dc6e09..19b4c628f3be 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -1013,31 +1013,6 @@ long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry, } EXPORT_SYMBOL_GPL(iommu_tce_xchg); -#ifdef CONFIG_PPC_BOOK3S_64 -long iommu_tce_xchg_rm(struct iommu_table *tbl, unsigned long entry, - unsigned long *hpa, enum dma_data_direction *direction) -{ - long ret; - - ret = tbl->it_ops->exchange_rm(tbl, entry, hpa, direction); - - if (!ret && ((*direction == DMA_FROM_DEVICE) || - (*direction == DMA_BIDIRECTIONAL))) { - struct page *pg = realmode_pfn_to_page(*hpa >> PAGE_SHIFT); - - if (likely(pg)) { - SetPageDirty(pg); - } else { - tbl->it_ops->exchange_rm(tbl, entry, hpa, direction); - ret = -EFAULT; - } - } - - return ret; -} -EXPORT_SYMBOL_GPL(iommu_tce_xchg_rm); -#endif - int iommu_take_ownership(struct iommu_table *tbl) { unsigned long flags, i, sz = (tbl->it_size + 7) >> 3; diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 913c5725cdb2..bb6ac471a784 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1306,6 +1306,16 @@ void show_user_instructions(struct pt_regs *regs) pc = regs->nip - (instructions_to_print * 3 / 4 * sizeof(int)); + /* + * Make sure the NIP points at userspace, not kernel text/data or + * elsewhere. + */ + if (!__access_ok(pc, instructions_to_print * sizeof(int), USER_DS)) { + pr_info("%s[%d]: Bad NIP, not dumping instructions.\n", + current->comm, current->pid); + return; + } + pr_info("%s[%d]: code: ", current->comm, current->pid); for (i = 0; i < instructions_to_print; i++) { diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index 6bffbc5affe7..7716374786bd 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -176,13 +176,27 @@ _GLOBAL(tm_reclaim) std r1, PACATMSCRATCH(r13) ld r1, PACAR1(r13) - /* Store the PPR in r11 and reset to decent value */ std r11, GPR11(r1) /* Temporary stash */ + /* + * Move the saved user r1 to the kernel stack in case PACATMSCRATCH is + * clobbered by an exception once we turn on MSR_RI below. + */ + ld r11, PACATMSCRATCH(r13) + std r11, GPR1(r1) + + /* + * Store r13 away so we can free up the scratch SPR for the SLB fault + * handler (needed once we start accessing the thread_struct). + */ + GET_SCRATCH0(r11) + std r11, GPR13(r1) + /* Reset MSR RI so we can take SLB faults again */ li r11, MSR_RI mtmsrd r11, 1 + /* Store the PPR in r11 and reset to decent value */ mfspr r11, SPRN_PPR HMT_MEDIUM @@ -207,11 +221,11 @@ _GLOBAL(tm_reclaim) SAVE_GPR(8, r7) /* user r8 */ SAVE_GPR(9, r7) /* user r9 */ SAVE_GPR(10, r7) /* user r10 */ - ld r3, PACATMSCRATCH(r13) /* user r1 */ + ld r3, GPR1(r1) /* user r1 */ ld r4, GPR7(r1) /* user r7 */ ld r5, GPR11(r1) /* user r11 */ ld r6, GPR12(r1) /* user r12 */ - GET_SCRATCH0(8) /* user r13 */ + ld r8, GPR13(r1) /* user r13 */ std r3, GPR1(r7) std r4, GPR7(r7) std r5, GPR11(r7) diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index fd6e8c13685f..998f8d089ac7 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -525,8 +525,8 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned long ea, unsigned long dsisr) { struct kvm *kvm = vcpu->kvm; - unsigned long mmu_seq, pte_size; - unsigned long gpa, gfn, hva, pfn; + unsigned long mmu_seq; + unsigned long gpa, gfn, hva; struct kvm_memory_slot *memslot; struct page *page = NULL; long ret; @@ -623,9 +623,10 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, */ hva = gfn_to_hva_memslot(memslot, gfn); if (upgrade_p && __get_user_pages_fast(hva, 1, 1, &page) == 1) { - pfn = page_to_pfn(page); upgrade_write = true; } else { + unsigned long pfn; + /* Call KVM generic code to do the slow-path check */ pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL, writing, upgrade_p); @@ -639,63 +640,55 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, } } - /* See if we can insert a 1GB or 2MB large PTE here */ - level = 0; - if (page && PageCompound(page)) { - pte_size = PAGE_SIZE << compound_order(compound_head(page)); - if (pte_size >= PUD_SIZE && - (gpa & (PUD_SIZE - PAGE_SIZE)) == - (hva & (PUD_SIZE - PAGE_SIZE))) { - level = 2; - pfn &= ~((PUD_SIZE >> PAGE_SHIFT) - 1); - } else if (pte_size >= PMD_SIZE && - (gpa & (PMD_SIZE - PAGE_SIZE)) == - (hva & (PMD_SIZE - PAGE_SIZE))) { - level = 1; - pfn &= ~((PMD_SIZE >> PAGE_SHIFT) - 1); - } - } - /* - * Compute the PTE value that we need to insert. + * Read the PTE from the process' radix tree and use that + * so we get the shift and attribute bits. */ - if (page) { - pgflags = _PAGE_READ | _PAGE_EXEC | _PAGE_PRESENT | _PAGE_PTE | - _PAGE_ACCESSED; - if (writing || upgrade_write) - pgflags |= _PAGE_WRITE | _PAGE_DIRTY; - pte = pfn_pte(pfn, __pgprot(pgflags)); - } else { - /* - * Read the PTE from the process' radix tree and use that - * so we get the attribute bits. - */ - local_irq_disable(); - ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift); - pte = *ptep; + local_irq_disable(); + ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift); + /* + * If the PTE disappeared temporarily due to a THP + * collapse, just return and let the guest try again. + */ + if (!ptep) { local_irq_enable(); - if (shift == PUD_SHIFT && - (gpa & (PUD_SIZE - PAGE_SIZE)) == - (hva & (PUD_SIZE - PAGE_SIZE))) { - level = 2; - } else if (shift == PMD_SHIFT && - (gpa & (PMD_SIZE - PAGE_SIZE)) == - (hva & (PMD_SIZE - PAGE_SIZE))) { - level = 1; - } else if (shift && shift != PAGE_SHIFT) { - /* Adjust PFN */ - unsigned long mask = (1ul << shift) - PAGE_SIZE; - pte = __pte(pte_val(pte) | (hva & mask)); - } - pte = __pte(pte_val(pte) | _PAGE_EXEC | _PAGE_ACCESSED); - if (writing || upgrade_write) { - if (pte_val(pte) & _PAGE_WRITE) - pte = __pte(pte_val(pte) | _PAGE_DIRTY); - } else { - pte = __pte(pte_val(pte) & ~(_PAGE_WRITE | _PAGE_DIRTY)); + if (page) + put_page(page); + return RESUME_GUEST; + } + pte = *ptep; + local_irq_enable(); + + /* Get pte level from shift/size */ + if (shift == PUD_SHIFT && + (gpa & (PUD_SIZE - PAGE_SIZE)) == + (hva & (PUD_SIZE - PAGE_SIZE))) { + level = 2; + } else if (shift == PMD_SHIFT && + (gpa & (PMD_SIZE - PAGE_SIZE)) == + (hva & (PMD_SIZE - PAGE_SIZE))) { + level = 1; + } else { + level = 0; + if (shift > PAGE_SHIFT) { + /* + * If the pte maps more than one page, bring over + * bits from the virtual address to get the real + * address of the specific single page we want. + */ + unsigned long rpnmask = (1ul << shift) - PAGE_SIZE; + pte = __pte(pte_val(pte) | (hva & rpnmask)); } } + pte = __pte(pte_val(pte) | _PAGE_EXEC | _PAGE_ACCESSED); + if (writing || upgrade_write) { + if (pte_val(pte) & _PAGE_WRITE) + pte = __pte(pte_val(pte) | _PAGE_DIRTY); + } else { + pte = __pte(pte_val(pte) & ~(_PAGE_WRITE | _PAGE_DIRTY)); + } + /* Allocate space in the tree and write the PTE */ ret = kvmppc_create_pte(kvm, pte, gpa, level, mmu_seq); diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c index 506a4d400458..6821ead4b4eb 100644 --- a/arch/powerpc/kvm/book3s_64_vio_hv.c +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c @@ -187,12 +187,35 @@ long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa, EXPORT_SYMBOL_GPL(kvmppc_gpa_to_ua); #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE -static void kvmppc_rm_clear_tce(struct iommu_table *tbl, unsigned long entry) +static long iommu_tce_xchg_rm(struct mm_struct *mm, struct iommu_table *tbl, + unsigned long entry, unsigned long *hpa, + enum dma_data_direction *direction) +{ + long ret; + + ret = tbl->it_ops->exchange_rm(tbl, entry, hpa, direction); + + if (!ret && ((*direction == DMA_FROM_DEVICE) || + (*direction == DMA_BIDIRECTIONAL))) { + __be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RM(tbl, entry); + /* + * kvmppc_rm_tce_iommu_do_map() updates the UA cache after + * calling this so we still get here a valid UA. + */ + if (pua && *pua) + mm_iommu_ua_mark_dirty_rm(mm, be64_to_cpu(*pua)); + } + + return ret; +} + +static void kvmppc_rm_clear_tce(struct kvm *kvm, struct iommu_table *tbl, + unsigned long entry) { unsigned long hpa = 0; enum dma_data_direction dir = DMA_NONE; - iommu_tce_xchg_rm(tbl, entry, &hpa, &dir); + iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir); } static long kvmppc_rm_tce_iommu_mapped_dec(struct kvm *kvm, @@ -224,7 +247,7 @@ static long kvmppc_rm_tce_iommu_do_unmap(struct kvm *kvm, unsigned long hpa = 0; long ret; - if (iommu_tce_xchg_rm(tbl, entry, &hpa, &dir)) + if (iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir)) /* * real mode xchg can fail if struct page crosses * a page boundary @@ -236,7 +259,7 @@ static long kvmppc_rm_tce_iommu_do_unmap(struct kvm *kvm, ret = kvmppc_rm_tce_iommu_mapped_dec(kvm, tbl, entry); if (ret) - iommu_tce_xchg_rm(tbl, entry, &hpa, &dir); + iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir); return ret; } @@ -282,7 +305,7 @@ static long kvmppc_rm_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl, if (WARN_ON_ONCE_RM(mm_iommu_mapped_inc(mem))) return H_CLOSED; - ret = iommu_tce_xchg_rm(tbl, entry, &hpa, &dir); + ret = iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir); if (ret) { mm_iommu_mapped_dec(mem); /* @@ -371,7 +394,7 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, return ret; WARN_ON_ONCE_RM(1); - kvmppc_rm_clear_tce(stit->tbl, entry); + kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry); } kvmppc_tce_put(stt, entry, tce); @@ -520,7 +543,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu, goto unlock_exit; WARN_ON_ONCE_RM(1); - kvmppc_rm_clear_tce(stit->tbl, entry); + kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry); } kvmppc_tce_put(stt, entry + i, tce); @@ -571,7 +594,7 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu, return ret; WARN_ON_ONCE_RM(1); - kvmppc_rm_clear_tce(stit->tbl, entry); + kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry); } } diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S index 886ed94b9c13..d05c8af4ac51 100644 --- a/arch/powerpc/lib/checksum_64.S +++ b/arch/powerpc/lib/checksum_64.S @@ -443,6 +443,9 @@ _GLOBAL(csum_ipv6_magic) addc r0, r8, r9 ld r10, 0(r4) ld r11, 8(r4) +#ifdef CONFIG_CPU_LITTLE_ENDIAN + rotldi r5, r5, 8 +#endif adde r0, r0, r10 add r5, r5, r7 adde r0, r0, r11 diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c index 850f3b8f4da5..5ffee298745f 100644 --- a/arch/powerpc/lib/code-patching.c +++ b/arch/powerpc/lib/code-patching.c @@ -142,7 +142,7 @@ static inline int unmap_patch_area(unsigned long addr) return 0; } -int patch_instruction(unsigned int *addr, unsigned int instr) +static int do_patch_instruction(unsigned int *addr, unsigned int instr) { int err; unsigned int *patch_addr = NULL; @@ -182,12 +182,22 @@ out: } #else /* !CONFIG_STRICT_KERNEL_RWX */ -int patch_instruction(unsigned int *addr, unsigned int instr) +static int do_patch_instruction(unsigned int *addr, unsigned int instr) { return raw_patch_instruction(addr, instr); } #endif /* CONFIG_STRICT_KERNEL_RWX */ + +int patch_instruction(unsigned int *addr, unsigned int instr) +{ + /* Make sure we aren't patching a freed init section */ + if (init_mem_is_free && init_section_contains(addr, 4)) { + pr_debug("Skipping init section patching addr: 0x%px\n", addr); + return 0; + } + return do_patch_instruction(addr, instr); +} NOKPROBE_SYMBOL(patch_instruction); int patch_branch(unsigned int *addr, unsigned long target, int flags) diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 51ce091914f9..7a9886f98b0c 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -308,55 +308,6 @@ void register_page_bootmem_memmap(unsigned long section_nr, { } -/* - * We do not have access to the sparsemem vmemmap, so we fallback to - * walking the list of sparsemem blocks which we already maintain for - * the sake of crashdump. In the long run, we might want to maintain - * a tree if performance of that linear walk becomes a problem. - * - * realmode_pfn_to_page functions can fail due to: - * 1) As real sparsemem blocks do not lay in RAM continously (they - * are in virtual address space which is not available in the real mode), - * the requested page struct can be split between blocks so get_page/put_page - * may fail. - * 2) When huge pages are used, the get_page/put_page API will fail - * in real mode as the linked addresses in the page struct are virtual - * too. - */ -struct page *realmode_pfn_to_page(unsigned long pfn) -{ - struct vmemmap_backing *vmem_back; - struct page *page; - unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift; - unsigned long pg_va = (unsigned long) pfn_to_page(pfn); - - for (vmem_back = vmemmap_list; vmem_back; vmem_back = vmem_back->list) { - if (pg_va < vmem_back->virt_addr) - continue; - - /* After vmemmap_list entry free is possible, need check all */ - if ((pg_va + sizeof(struct page)) <= - (vmem_back->virt_addr + page_size)) { - page = (struct page *) (vmem_back->phys + pg_va - - vmem_back->virt_addr); - return page; - } - } - - /* Probably that page struct is split between real pages */ - return NULL; -} -EXPORT_SYMBOL_GPL(realmode_pfn_to_page); - -#else - -struct page *realmode_pfn_to_page(unsigned long pfn) -{ - struct page *page = pfn_to_page(pfn); - return page; -} -EXPORT_SYMBOL_GPL(realmode_pfn_to_page); - #endif /* CONFIG_SPARSEMEM_VMEMMAP */ #ifdef CONFIG_PPC_BOOK3S_64 diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 5c8530d0c611..04ccb274a620 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -63,6 +63,7 @@ #endif unsigned long long memory_limit; +bool init_mem_is_free; #ifdef CONFIG_HIGHMEM pte_t *kmap_pte; @@ -396,6 +397,7 @@ void free_initmem(void) { ppc_md.progress = ppc_printk_progress; mark_initmem_nx(); + init_mem_is_free = true; free_initmem_default(POISON_FREE_INITMEM); } diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c index c9ee9e23845f..56c2234cc6ae 100644 --- a/arch/powerpc/mm/mmu_context_iommu.c +++ b/arch/powerpc/mm/mmu_context_iommu.c @@ -18,11 +18,15 @@ #include <linux/migrate.h> #include <linux/hugetlb.h> #include <linux/swap.h> +#include <linux/sizes.h> #include <asm/mmu_context.h> #include <asm/pte-walk.h> static DEFINE_MUTEX(mem_list_mutex); +#define MM_IOMMU_TABLE_GROUP_PAGE_DIRTY 0x1 +#define MM_IOMMU_TABLE_GROUP_PAGE_MASK ~(SZ_4K - 1) + struct mm_iommu_table_group_mem_t { struct list_head next; struct rcu_head rcu; @@ -263,6 +267,9 @@ static void mm_iommu_unpin(struct mm_iommu_table_group_mem_t *mem) if (!page) continue; + if (mem->hpas[i] & MM_IOMMU_TABLE_GROUP_PAGE_DIRTY) + SetPageDirty(page); + put_page(page); mem->hpas[i] = 0; } @@ -360,7 +367,6 @@ struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(struct mm_struct *mm, return ret; } -EXPORT_SYMBOL_GPL(mm_iommu_lookup_rm); struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm, unsigned long ua, unsigned long entries) @@ -390,7 +396,7 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem, if (pageshift > mem->pageshift) return -EFAULT; - *hpa = *va | (ua & ~PAGE_MASK); + *hpa = (*va & MM_IOMMU_TABLE_GROUP_PAGE_MASK) | (ua & ~PAGE_MASK); return 0; } @@ -413,11 +419,31 @@ long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem, if (!pa) return -EFAULT; - *hpa = *pa | (ua & ~PAGE_MASK); + *hpa = (*pa & MM_IOMMU_TABLE_GROUP_PAGE_MASK) | (ua & ~PAGE_MASK); return 0; } -EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa_rm); + +extern void mm_iommu_ua_mark_dirty_rm(struct mm_struct *mm, unsigned long ua) +{ + struct mm_iommu_table_group_mem_t *mem; + long entry; + void *va; + unsigned long *pa; + + mem = mm_iommu_lookup_rm(mm, ua, PAGE_SIZE); + if (!mem) + return; + + entry = (ua - mem->ua) >> PAGE_SHIFT; + va = &mem->hpas[entry]; + + pa = (void *) vmalloc_to_phys(va); + if (!pa) + return; + + *pa |= MM_IOMMU_TABLE_GROUP_PAGE_DIRTY; +} long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem) { diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 35ac5422903a..055b211b7126 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1204,7 +1204,9 @@ int find_and_online_cpu_nid(int cpu) int new_nid; /* Use associativity from first thread for all siblings */ - vphn_get_associativity(cpu, associativity); + if (vphn_get_associativity(cpu, associativity)) + return cpu_to_node(cpu); + new_nid = associativity_to_nid(associativity); if (new_nid < 0 || !node_possible(new_nid)) new_nid = first_online_node; @@ -1215,9 +1217,10 @@ int find_and_online_cpu_nid(int cpu) * Need to ensure that NODE_DATA is initialized for a node from * available memory (see memblock_alloc_try_nid). If unable to * init the node, then default to nearest node that has memory - * installed. + * installed. Skip onlining a node if the subsystems are not + * yet initialized. */ - if (try_online_node(new_nid)) + if (!topology_inited || try_online_node(new_nid)) new_nid = first_online_node; #else /* @@ -1452,7 +1455,8 @@ static struct timer_list topology_timer; static void reset_topology_timer(void) { - mod_timer(&topology_timer, jiffies + topology_timer_secs * HZ); + if (vphn_enabled) + mod_timer(&topology_timer, jiffies + topology_timer_secs * HZ); } #ifdef CONFIG_SMP diff --git a/arch/powerpc/mm/pkeys.c b/arch/powerpc/mm/pkeys.c index 333b1f80c435..b271b283c785 100644 --- a/arch/powerpc/mm/pkeys.c +++ b/arch/powerpc/mm/pkeys.c @@ -45,7 +45,7 @@ static void scan_pkey_feature(void) * Since any pkey can be used for data or execute, we will just treat * all keys as equal and track them as one entity. */ - pkeys_total = be32_to_cpu(vals[0]); + pkeys_total = vals[0]; pkeys_devtree_defined = true; } diff --git a/arch/powerpc/platforms/powernv/pci-ioda-tce.c b/arch/powerpc/platforms/powernv/pci-ioda-tce.c index 6c5db1acbe8d..fe9691040f54 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda-tce.c +++ b/arch/powerpc/platforms/powernv/pci-ioda-tce.c @@ -276,7 +276,7 @@ long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset, level_shift = entries_shift + 3; level_shift = max_t(unsigned int, level_shift, PAGE_SHIFT); - if ((level_shift - 3) * levels + page_shift >= 60) + if ((level_shift - 3) * levels + page_shift >= 55) return -EINVAL; /* Allocate TCE table */ diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h new file mode 100644 index 000000000000..c9fecd120d18 --- /dev/null +++ b/arch/riscv/include/asm/asm-prototypes.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_PROTOTYPES_H + +#include <linux/ftrace.h> +#include <asm-generic/asm-prototypes.h> + +#endif /* _ASM_RISCV_PROTOTYPES_H */ diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index aee603123030..b2d26d9d8489 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -186,7 +186,7 @@ static void __init setup_bootmem(void) BUG_ON(mem_size == 0); set_max_mapnr(PFN_DOWN(mem_size)); - max_low_pfn = pfn_base + PFN_DOWN(mem_size); + max_low_pfn = memblock_end_of_DRAM(); #ifdef CONFIG_BLK_DEV_INITRD setup_initrd(); diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index f69333fd2fa3..ac5da6b0b862 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -481,7 +481,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) break; case KVM_CAP_S390_HPAGE_1M: r = 0; - if (hpage) + if (hpage && !kvm_is_ucontrol(kvm)) r = 1; break; case KVM_CAP_S390_MEM_OP: @@ -691,7 +691,7 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) mutex_lock(&kvm->lock); if (kvm->created_vcpus) r = -EBUSY; - else if (!hpage || kvm->arch.use_cmma) + else if (!hpage || kvm->arch.use_cmma || kvm_is_ucontrol(kvm)) r = -EINVAL; else { r = 0; diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index bb44990c8212..911c7ded35f1 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -708,11 +708,13 @@ void gmap_discard(struct gmap *gmap, unsigned long from, unsigned long to) vmaddr |= gaddr & ~PMD_MASK; /* Find vma in the parent mm */ vma = find_vma(gmap->mm, vmaddr); + if (!vma) + continue; /* * We do not discard pages that are backed by * hugetlbfs, so we don't have to refault them. */ - if (vma && is_vm_hugetlb_page(vma)) + if (is_vm_hugetlb_page(vma)) continue; size = min(to - gaddr, PMD_SIZE - (gaddr & ~PMD_MASK)); zap_page_range(vma, vmaddr, size); diff --git a/arch/x86/boot/compressed/mem_encrypt.S b/arch/x86/boot/compressed/mem_encrypt.S index eaa843a52907..a480356e0ed8 100644 --- a/arch/x86/boot/compressed/mem_encrypt.S +++ b/arch/x86/boot/compressed/mem_encrypt.S @@ -25,20 +25,6 @@ ENTRY(get_sev_encryption_bit) push %ebx push %ecx push %edx - push %edi - - /* - * RIP-relative addressing is needed to access the encryption bit - * variable. Since we are running in 32-bit mode we need this call/pop - * sequence to get the proper relative addressing. - */ - call 1f -1: popl %edi - subl $1b, %edi - - movl enc_bit(%edi), %eax - cmpl $0, %eax - jge .Lsev_exit /* Check if running under a hypervisor */ movl $1, %eax @@ -69,15 +55,12 @@ ENTRY(get_sev_encryption_bit) movl %ebx, %eax andl $0x3f, %eax /* Return the encryption bit location */ - movl %eax, enc_bit(%edi) jmp .Lsev_exit .Lno_sev: xor %eax, %eax - movl %eax, enc_bit(%edi) .Lsev_exit: - pop %edi pop %edx pop %ecx pop %ebx @@ -113,8 +96,6 @@ ENTRY(set_sev_encryption_mask) ENDPROC(set_sev_encryption_mask) .data -enc_bit: - .int 0xffffffff #ifdef CONFIG_AMD_MEM_ENCRYPT .balign 8 diff --git a/arch/x86/crypto/aegis128-aesni-glue.c b/arch/x86/crypto/aegis128-aesni-glue.c index acd11b3bf639..2a356b948720 100644 --- a/arch/x86/crypto/aegis128-aesni-glue.c +++ b/arch/x86/crypto/aegis128-aesni-glue.c @@ -379,7 +379,6 @@ static int __init crypto_aegis128_aesni_module_init(void) { if (!boot_cpu_has(X86_FEATURE_XMM2) || !boot_cpu_has(X86_FEATURE_AES) || - !boot_cpu_has(X86_FEATURE_OSXSAVE) || !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; diff --git a/arch/x86/crypto/aegis128l-aesni-glue.c b/arch/x86/crypto/aegis128l-aesni-glue.c index 2071c3d1ae07..dbe8bb980da1 100644 --- a/arch/x86/crypto/aegis128l-aesni-glue.c +++ b/arch/x86/crypto/aegis128l-aesni-glue.c @@ -379,7 +379,6 @@ static int __init crypto_aegis128l_aesni_module_init(void) { if (!boot_cpu_has(X86_FEATURE_XMM2) || !boot_cpu_has(X86_FEATURE_AES) || - !boot_cpu_has(X86_FEATURE_OSXSAVE) || !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; diff --git a/arch/x86/crypto/aegis256-aesni-glue.c b/arch/x86/crypto/aegis256-aesni-glue.c index b5f2a8fd5a71..8bebda2de92f 100644 --- a/arch/x86/crypto/aegis256-aesni-glue.c +++ b/arch/x86/crypto/aegis256-aesni-glue.c @@ -379,7 +379,6 @@ static int __init crypto_aegis256_aesni_module_init(void) { if (!boot_cpu_has(X86_FEATURE_XMM2) || !boot_cpu_has(X86_FEATURE_AES) || - !boot_cpu_has(X86_FEATURE_OSXSAVE) || !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; diff --git a/arch/x86/crypto/morus1280-sse2-glue.c b/arch/x86/crypto/morus1280-sse2-glue.c index 95cf857d2cbb..f40244eaf14d 100644 --- a/arch/x86/crypto/morus1280-sse2-glue.c +++ b/arch/x86/crypto/morus1280-sse2-glue.c @@ -40,7 +40,6 @@ MORUS1280_DECLARE_ALGS(sse2, "morus1280-sse2", 350); static int __init crypto_morus1280_sse2_module_init(void) { if (!boot_cpu_has(X86_FEATURE_XMM2) || - !boot_cpu_has(X86_FEATURE_OSXSAVE) || !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; diff --git a/arch/x86/crypto/morus640-sse2-glue.c b/arch/x86/crypto/morus640-sse2-glue.c index 615fb7bc9a32..9afaf8f8565a 100644 --- a/arch/x86/crypto/morus640-sse2-glue.c +++ b/arch/x86/crypto/morus640-sse2-glue.c @@ -40,7 +40,6 @@ MORUS640_DECLARE_ALGS(sse2, "morus640-sse2", 400); static int __init crypto_morus640_sse2_module_init(void) { if (!boot_cpu_has(X86_FEATURE_XMM2) || - !boot_cpu_has(X86_FEATURE_OSXSAVE) || !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index fa3f439f0a92..141d415a8c80 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -68,7 +68,13 @@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \ $(filter -g%,$(KBUILD_CFLAGS)) $(call cc-option, -fno-stack-protector) \ -fno-omit-frame-pointer -foptimize-sibling-calls \ - -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO $(RETPOLINE_VDSO_CFLAGS) + -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO + +ifdef CONFIG_RETPOLINE +ifneq ($(RETPOLINE_VDSO_CFLAGS),) + CFL += $(RETPOLINE_VDSO_CFLAGS) +endif +endif $(vobjs): KBUILD_CFLAGS := $(filter-out $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL) @@ -138,7 +144,13 @@ KBUILD_CFLAGS_32 += $(call cc-option, -fno-stack-protector) KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls) KBUILD_CFLAGS_32 += -fno-omit-frame-pointer KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING -KBUILD_CFLAGS_32 += $(RETPOLINE_VDSO_CFLAGS) + +ifdef CONFIG_RETPOLINE +ifneq ($(RETPOLINE_VDSO_CFLAGS),) + KBUILD_CFLAGS_32 += $(RETPOLINE_VDSO_CFLAGS) +endif +endif + $(obj)/vdso32.so.dbg: KBUILD_CFLAGS = $(KBUILD_CFLAGS_32) $(obj)/vdso32.so.dbg: FORCE \ diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c index f19856d95c60..e48ca3afa091 100644 --- a/arch/x86/entry/vdso/vclock_gettime.c +++ b/arch/x86/entry/vdso/vclock_gettime.c @@ -43,8 +43,9 @@ extern u8 hvclock_page notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) { long ret; - asm("syscall" : "=a" (ret) : - "0" (__NR_clock_gettime), "D" (clock), "S" (ts) : "memory"); + asm ("syscall" : "=a" (ret), "=m" (*ts) : + "0" (__NR_clock_gettime), "D" (clock), "S" (ts) : + "memory", "rcx", "r11"); return ret; } @@ -52,8 +53,9 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz) { long ret; - asm("syscall" : "=a" (ret) : - "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory"); + asm ("syscall" : "=a" (ret), "=m" (*tv), "=m" (*tz) : + "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : + "memory", "rcx", "r11"); return ret; } @@ -64,13 +66,13 @@ notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) { long ret; - asm( + asm ( "mov %%ebx, %%edx \n" - "mov %2, %%ebx \n" + "mov %[clock], %%ebx \n" "call __kernel_vsyscall \n" "mov %%edx, %%ebx \n" - : "=a" (ret) - : "0" (__NR_clock_gettime), "g" (clock), "c" (ts) + : "=a" (ret), "=m" (*ts) + : "0" (__NR_clock_gettime), [clock] "g" (clock), "c" (ts) : "memory", "edx"); return ret; } @@ -79,13 +81,13 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz) { long ret; - asm( + asm ( "mov %%ebx, %%edx \n" - "mov %2, %%ebx \n" + "mov %[tv], %%ebx \n" "call __kernel_vsyscall \n" "mov %%edx, %%ebx \n" - : "=a" (ret) - : "0" (__NR_gettimeofday), "g" (tv), "c" (tz) + : "=a" (ret), "=m" (*tv), "=m" (*tz) + : "0" (__NR_gettimeofday), [tv] "g" (tv), "c" (tz) : "memory", "edx"); return ret; } diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c index 981ba5e8241b..8671de126eac 100644 --- a/arch/x86/events/amd/uncore.c +++ b/arch/x86/events/amd/uncore.c @@ -36,6 +36,7 @@ static int num_counters_llc; static int num_counters_nb; +static bool l3_mask; static HLIST_HEAD(uncore_unused_list); @@ -209,6 +210,13 @@ static int amd_uncore_event_init(struct perf_event *event) hwc->config = event->attr.config & AMD64_RAW_EVENT_MASK_NB; hwc->idx = -1; + /* + * SliceMask and ThreadMask need to be set for certain L3 events in + * Family 17h. For other events, the two fields do not affect the count. + */ + if (l3_mask) + hwc->config |= (AMD64_L3_SLICE_MASK | AMD64_L3_THREAD_MASK); + if (event->cpu < 0) return -EINVAL; @@ -525,6 +533,7 @@ static int __init amd_uncore_init(void) amd_llc_pmu.name = "amd_l3"; format_attr_event_df.show = &event_show_df; format_attr_event_l3.show = &event_show_l3; + l3_mask = true; } else { num_counters_nb = NUM_COUNTERS_NB; num_counters_llc = NUM_COUNTERS_L2; @@ -532,6 +541,7 @@ static int __init amd_uncore_init(void) amd_llc_pmu.name = "amd_l2"; format_attr_event_df = format_attr_event; format_attr_event_l3 = format_attr_event; + l3_mask = false; } amd_nb_pmu.attr_groups = amd_uncore_attr_groups_df; diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 51d7c117e3c7..c07bee31abe8 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -3061,7 +3061,7 @@ static struct event_constraint bdx_uncore_pcu_constraints[] = { void bdx_uncore_cpu_init(void) { - int pkg = topology_phys_to_logical_pkg(0); + int pkg = topology_phys_to_logical_pkg(boot_cpu_data.phys_proc_id); if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; @@ -3931,16 +3931,16 @@ static const struct pci_device_id skx_uncore_pci_ids[] = { .driver_data = UNCORE_PCI_DEV_FULL_DATA(21, 5, SKX_PCI_UNCORE_M2PCIE, 3), }, { /* M3UPI0 Link 0 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204C), - .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 0, SKX_PCI_UNCORE_M3UPI, 0), + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 1, SKX_PCI_UNCORE_M3UPI, 0), }, { /* M3UPI0 Link 1 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D), - .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 1, SKX_PCI_UNCORE_M3UPI, 1), + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204E), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 2, SKX_PCI_UNCORE_M3UPI, 1), }, { /* M3UPI1 Link 2 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204C), - .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 4, SKX_PCI_UNCORE_M3UPI, 2), + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 5, SKX_PCI_UNCORE_M3UPI, 2), }, { /* end: all zeroes */ } }; diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c index 5b0f613428c2..2c43e3055948 100644 --- a/arch/x86/hyperv/hv_apic.c +++ b/arch/x86/hyperv/hv_apic.c @@ -95,8 +95,8 @@ static void hv_apic_eoi_write(u32 reg, u32 val) */ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector) { - struct ipi_arg_ex **arg; - struct ipi_arg_ex *ipi_arg; + struct hv_send_ipi_ex **arg; + struct hv_send_ipi_ex *ipi_arg; unsigned long flags; int nr_bank = 0; int ret = 1; @@ -105,7 +105,7 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector) return false; local_irq_save(flags); - arg = (struct ipi_arg_ex **)this_cpu_ptr(hyperv_pcpu_input_arg); + arg = (struct hv_send_ipi_ex **)this_cpu_ptr(hyperv_pcpu_input_arg); ipi_arg = *arg; if (unlikely(!ipi_arg)) @@ -135,7 +135,7 @@ ipi_mask_ex_done: static bool __send_ipi_mask(const struct cpumask *mask, int vector) { int cur_cpu, vcpu; - struct ipi_arg_non_ex ipi_arg; + struct hv_send_ipi ipi_arg; int ret = 1; trace_hyperv_send_ipi_mask(mask, vector); diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index e203169931c7..6390bd8c141b 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -14,6 +14,16 @@ #ifndef _ASM_X86_FIXMAP_H #define _ASM_X86_FIXMAP_H +/* + * Exposed to assembly code for setting up initial page tables. Cannot be + * calculated in assembly code (fixmap entries are an enum), but is sanity + * checked in the actual fixmap C code to make sure that the fixmap is + * covered fully. + */ +#define FIXMAP_PMD_NUM 2 +/* fixmap starts downwards from the 507th entry in level2_fixmap_pgt */ +#define FIXMAP_PMD_TOP 507 + #ifndef __ASSEMBLY__ #include <linux/kernel.h> #include <asm/acpi.h> diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index e977b6b3a538..00e01d215f74 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -726,19 +726,21 @@ struct hv_enlightened_vmcs { #define HV_STIMER_AUTOENABLE (1ULL << 3) #define HV_STIMER_SINT(config) (__u8)(((config) >> 16) & 0x0F) -struct ipi_arg_non_ex { - u32 vector; - u32 reserved; - u64 cpu_mask; -}; - struct hv_vpset { u64 format; u64 valid_bank_mask; u64 bank_contents[]; }; -struct ipi_arg_ex { +/* HvCallSendSyntheticClusterIpi hypercall */ +struct hv_send_ipi { + u32 vector; + u32 reserved; + u64 cpu_mask; +}; + +/* HvCallSendSyntheticClusterIpiEx hypercall */ +struct hv_send_ipi_ex { u32 vector; u32 reserved; struct hv_vpset vp_set; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 8e90488c3d56..09b2e3e2cf1b 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -869,6 +869,8 @@ struct kvm_arch { bool x2apic_format; bool x2apic_broadcast_quirk_disabled; + + bool guest_can_read_msr_platform_info; }; struct kvm_vm_stat { @@ -1022,6 +1024,7 @@ struct kvm_x86_ops { void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu); void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr); void (*hwapic_isr_update)(struct kvm_vcpu *vcpu, int isr); + bool (*guest_apic_has_interrupt)(struct kvm_vcpu *vcpu); void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu); void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa); @@ -1055,6 +1058,7 @@ struct kvm_x86_ops { bool (*umip_emulated)(void); int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr); + void (*request_immediate_exit)(struct kvm_vcpu *vcpu); void (*sched_in)(struct kvm_vcpu *kvm, int cpu); @@ -1482,6 +1486,7 @@ extern bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn); int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu); int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err); +void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu); int kvm_is_in_guest(void); diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index c0643831706e..616f8e637bc3 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -48,10 +48,13 @@ int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size); /* Architecture __weak replacement functions */ void __init mem_encrypt_init(void); +void __init mem_encrypt_free_decrypted_mem(void); bool sme_active(void); bool sev_active(void); +#define __bss_decrypted __attribute__((__section__(".bss..decrypted"))) + #else /* !CONFIG_AMD_MEM_ENCRYPT */ #define sme_me_mask 0ULL @@ -77,6 +80,8 @@ early_set_memory_decrypted(unsigned long vaddr, unsigned long size) { return 0; static inline int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size) { return 0; } +#define __bss_decrypted + #endif /* CONFIG_AMD_MEM_ENCRYPT */ /* @@ -88,6 +93,8 @@ early_set_memory_encrypted(unsigned long vaddr, unsigned long size) { return 0; #define __sme_pa(x) (__pa(x) | sme_me_mask) #define __sme_pa_nodebug(x) (__pa_nodebug(x) | sme_me_mask) +extern char __start_bss_decrypted[], __end_bss_decrypted[], __start_bss_decrypted_unused[]; + #endif /* __ASSEMBLY__ */ #endif /* __X86_MEM_ENCRYPT_H__ */ diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 12f54082f4c8..78241b736f2a 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -46,6 +46,14 @@ #define INTEL_ARCH_EVENT_MASK \ (ARCH_PERFMON_EVENTSEL_UMASK | ARCH_PERFMON_EVENTSEL_EVENT) +#define AMD64_L3_SLICE_SHIFT 48 +#define AMD64_L3_SLICE_MASK \ + ((0xFULL) << AMD64_L3_SLICE_SHIFT) + +#define AMD64_L3_THREAD_SHIFT 56 +#define AMD64_L3_THREAD_MASK \ + ((0xFFULL) << AMD64_L3_THREAD_SHIFT) + #define X86_RAW_EVENT_MASK \ (ARCH_PERFMON_EVENTSEL_EVENT | \ ARCH_PERFMON_EVENTSEL_UMASK | \ diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index ce2b59047cb8..9c85b54bf03c 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -14,6 +14,7 @@ #include <asm/processor.h> #include <linux/bitops.h> #include <linux/threads.h> +#include <asm/fixmap.h> extern p4d_t level4_kernel_pgt[512]; extern p4d_t level4_ident_pgt[512]; @@ -22,7 +23,7 @@ extern pud_t level3_ident_pgt[512]; extern pmd_t level2_kernel_pgt[512]; extern pmd_t level2_fixmap_pgt[512]; extern pmd_t level2_ident_pgt[512]; -extern pte_t level1_fixmap_pgt[512]; +extern pte_t level1_fixmap_pgt[512 * FIXMAP_PMD_NUM]; extern pgd_t init_top_pgt[]; #define swapper_pg_dir init_top_pgt diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h index a80c0673798f..e60c45fd3679 100644 --- a/arch/x86/include/asm/uv/uv.h +++ b/arch/x86/include/asm/uv/uv.h @@ -10,8 +10,13 @@ struct cpumask; struct mm_struct; #ifdef CONFIG_X86_UV +#include <linux/efi.h> extern enum uv_system_type get_uv_system_type(void); +static inline bool is_early_uv_system(void) +{ + return !((efi.uv_systab == EFI_INVALID_TABLE_ADDR) || !efi.uv_systab); +} extern int is_uv_system(void); extern int is_uv_hubless(void); extern void uv_cpu_init(void); @@ -23,6 +28,7 @@ extern const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, #else /* X86_UV */ static inline enum uv_system_type get_uv_system_type(void) { return UV_NONE; } +static inline bool is_early_uv_system(void) { return 0; } static inline int is_uv_system(void) { return 0; } static inline int is_uv_hubless(void) { return 0; } static inline void uv_cpu_init(void) { } diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 86299efa804a..fd23d5778ea1 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -377,6 +377,7 @@ struct kvm_sync_regs { #define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0) #define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1) +#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2) #define KVM_STATE_NESTED_GUEST_MODE 0x00000001 #define KVM_STATE_NESTED_RUN_PENDING 0x00000002 diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 22ab408177b2..eeea634bee0a 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -922,7 +922,7 @@ static void init_amd(struct cpuinfo_x86 *c) static unsigned int amd_size_cache(struct cpuinfo_x86 *c, unsigned int size) { /* AMD errata T13 (order #21922) */ - if ((c->x86 == 6)) { + if (c->x86 == 6) { /* Duron Rev A0 */ if (c->x86_model == 3 && c->x86_stepping == 0) size = 64; diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h index 4e588f36228f..285eb3ec4200 100644 --- a/arch/x86/kernel/cpu/intel_rdt.h +++ b/arch/x86/kernel/cpu/intel_rdt.h @@ -382,6 +382,11 @@ static inline bool is_mbm_event(int e) e <= QOS_L3_MBM_LOCAL_EVENT_ID); } +struct rdt_parse_data { + struct rdtgroup *rdtgrp; + char *buf; +}; + /** * struct rdt_resource - attributes of an RDT resource * @rid: The index of the resource @@ -423,16 +428,19 @@ struct rdt_resource { struct rdt_cache cache; struct rdt_membw membw; const char *format_str; - int (*parse_ctrlval) (void *data, struct rdt_resource *r, - struct rdt_domain *d); + int (*parse_ctrlval)(struct rdt_parse_data *data, + struct rdt_resource *r, + struct rdt_domain *d); struct list_head evt_list; int num_rmid; unsigned int mon_scale; unsigned long fflags; }; -int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d); -int parse_bw(void *_buf, struct rdt_resource *r, struct rdt_domain *d); +int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r, + struct rdt_domain *d); +int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r, + struct rdt_domain *d); extern struct mutex rdtgroup_mutex; @@ -536,6 +544,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp); void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp); struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r); int update_domains(struct rdt_resource *r, int closid); +int closids_supported(void); void closid_free(int closid); int alloc_rmid(void); void free_rmid(u32 rmid); diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c index af358ca05160..0f53049719cd 100644 --- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c +++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c @@ -64,19 +64,19 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r) return true; } -int parse_bw(void *_buf, struct rdt_resource *r, struct rdt_domain *d) +int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r, + struct rdt_domain *d) { - unsigned long data; - char *buf = _buf; + unsigned long bw_val; if (d->have_new_ctrl) { rdt_last_cmd_printf("duplicate domain %d\n", d->id); return -EINVAL; } - if (!bw_validate(buf, &data, r)) + if (!bw_validate(data->buf, &bw_val, r)) return -EINVAL; - d->new_ctrl = data; + d->new_ctrl = bw_val; d->have_new_ctrl = true; return 0; @@ -123,18 +123,13 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r) return true; } -struct rdt_cbm_parse_data { - struct rdtgroup *rdtgrp; - char *buf; -}; - /* * Read one cache bit mask (hex). Check that it is valid for the current * resource type. */ -int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d) +int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r, + struct rdt_domain *d) { - struct rdt_cbm_parse_data *data = _data; struct rdtgroup *rdtgrp = data->rdtgrp; u32 cbm_val; @@ -195,11 +190,17 @@ int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d) static int parse_line(char *line, struct rdt_resource *r, struct rdtgroup *rdtgrp) { - struct rdt_cbm_parse_data data; + struct rdt_parse_data data; char *dom = NULL, *id; struct rdt_domain *d; unsigned long dom_id; + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP && + r->rid == RDT_RESOURCE_MBA) { + rdt_last_cmd_puts("Cannot pseudo-lock MBA resource\n"); + return -EINVAL; + } + next: if (!line || line[0] == '\0') return 0; diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index b799c00bef09..1b8e86a5d5e1 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -97,6 +97,12 @@ void rdt_last_cmd_printf(const char *fmt, ...) * limited as the number of resources grows. */ static int closid_free_map; +static int closid_free_map_len; + +int closids_supported(void) +{ + return closid_free_map_len; +} static void closid_init(void) { @@ -111,6 +117,7 @@ static void closid_init(void) /* CLOSID 0 is always reserved for the default group */ closid_free_map &= ~1; + closid_free_map_len = rdt_min_closid; } static int closid_alloc(void) @@ -802,7 +809,7 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of, sw_shareable = 0; exclusive = 0; seq_printf(seq, "%d=", dom->id); - for (i = 0; i < r->num_closid; i++, ctrl++) { + for (i = 0; i < closids_supported(); i++, ctrl++) { if (!closid_allocated(i)) continue; mode = rdtgroup_mode_by_closid(i); @@ -989,7 +996,7 @@ bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, /* Check for overlap with other resource groups */ ctrl = d->ctrl_val; - for (i = 0; i < r->num_closid; i++, ctrl++) { + for (i = 0; i < closids_supported(); i++, ctrl++) { ctrl_b = (unsigned long *)ctrl; mode = rdtgroup_mode_by_closid(i); if (closid_allocated(i) && i != closid && @@ -1024,16 +1031,27 @@ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp) { int closid = rdtgrp->closid; struct rdt_resource *r; + bool has_cache = false; struct rdt_domain *d; for_each_alloc_enabled_rdt_resource(r) { + if (r->rid == RDT_RESOURCE_MBA) + continue; + has_cache = true; list_for_each_entry(d, &r->domains, list) { if (rdtgroup_cbm_overlaps(r, d, d->ctrl_val[closid], - rdtgrp->closid, false)) + rdtgrp->closid, false)) { + rdt_last_cmd_puts("schemata overlaps\n"); return false; + } } } + if (!has_cache) { + rdt_last_cmd_puts("cannot be exclusive without CAT/CDP\n"); + return false; + } + return true; } @@ -1085,7 +1103,6 @@ static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of, rdtgrp->mode = RDT_MODE_SHAREABLE; } else if (!strcmp(buf, "exclusive")) { if (!rdtgroup_mode_test_exclusive(rdtgrp)) { - rdt_last_cmd_printf("schemata overlaps\n"); ret = -EINVAL; goto out; } @@ -1155,8 +1172,8 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, struct rdt_resource *r; struct rdt_domain *d; unsigned int size; - bool sep = false; - u32 cbm; + bool sep; + u32 ctrl; rdtgrp = rdtgroup_kn_lock_live(of->kn); if (!rdtgrp) { @@ -1174,6 +1191,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, } for_each_alloc_enabled_rdt_resource(r) { + sep = false; seq_printf(s, "%*s:", max_name_width, r->name); list_for_each_entry(d, &r->domains, list) { if (sep) @@ -1181,8 +1199,13 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { size = 0; } else { - cbm = d->ctrl_val[rdtgrp->closid]; - size = rdtgroup_cbm_to_size(r, d, cbm); + ctrl = (!is_mba_sc(r) ? + d->ctrl_val[rdtgrp->closid] : + d->mbps_val[rdtgrp->closid]); + if (r->rid == RDT_RESOURCE_MBA) + size = ctrl; + else + size = rdtgroup_cbm_to_size(r, d, ctrl); } seq_printf(s, "%d=%u", d->id, size); sep = true; @@ -2336,12 +2359,18 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) u32 *ctrl; for_each_alloc_enabled_rdt_resource(r) { + /* + * Only initialize default allocations for CBM cache + * resources + */ + if (r->rid == RDT_RESOURCE_MBA) + continue; list_for_each_entry(d, &r->domains, list) { d->have_new_ctrl = false; d->new_ctrl = r->cache.shareable_bits; used_b = r->cache.shareable_bits; ctrl = d->ctrl_val; - for (i = 0; i < r->num_closid; i++, ctrl++) { + for (i = 0; i < closids_supported(); i++, ctrl++) { if (closid_allocated(i) && i != closid) { mode = rdtgroup_mode_by_closid(i); if (mode == RDT_MODE_PSEUDO_LOCKSETUP) @@ -2373,6 +2402,12 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) } for_each_alloc_enabled_rdt_resource(r) { + /* + * Only initialize default allocations for CBM cache + * resources + */ + if (r->rid == RDT_RESOURCE_MBA) + continue; ret = update_domains(r, rdtgrp->closid); if (ret < 0) { rdt_last_cmd_puts("failed to initialize allocations\n"); diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 8047379e575a..ddee1f0870c4 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -35,6 +35,7 @@ #include <asm/bootparam_utils.h> #include <asm/microcode.h> #include <asm/kasan.h> +#include <asm/fixmap.h> /* * Manage page tables very early on. @@ -112,6 +113,7 @@ static bool __head check_la57_support(unsigned long physaddr) unsigned long __head __startup_64(unsigned long physaddr, struct boot_params *bp) { + unsigned long vaddr, vaddr_end; unsigned long load_delta, *p; unsigned long pgtable_flags; pgdval_t *pgd; @@ -165,7 +167,8 @@ unsigned long __head __startup_64(unsigned long physaddr, pud[511] += load_delta; pmd = fixup_pointer(level2_fixmap_pgt, physaddr); - pmd[506] += load_delta; + for (i = FIXMAP_PMD_TOP; i > FIXMAP_PMD_TOP - FIXMAP_PMD_NUM; i--) + pmd[i] += load_delta; /* * Set up the identity mapping for the switchover. These @@ -235,6 +238,21 @@ unsigned long __head __startup_64(unsigned long physaddr, sme_encrypt_kernel(bp); /* + * Clear the memory encryption mask from the .bss..decrypted section. + * The bss section will be memset to zero later in the initialization so + * there is no need to zero it after changing the memory encryption + * attribute. + */ + if (mem_encrypt_active()) { + vaddr = (unsigned long)__start_bss_decrypted; + vaddr_end = (unsigned long)__end_bss_decrypted; + for (; vaddr < vaddr_end; vaddr += PMD_SIZE) { + i = pmd_index(vaddr); + pmd[i] -= sme_get_me_mask(); + } + } + + /* * Return the SME encryption mask (if SME is active) to be used as a * modifier for the initial pgdir entry programmed into CR3. */ diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 15ebc2fc166e..a3618cf04cf6 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -24,6 +24,7 @@ #include "../entry/calling.h" #include <asm/export.h> #include <asm/nospec-branch.h> +#include <asm/fixmap.h> #ifdef CONFIG_PARAVIRT #include <asm/asm-offsets.h> @@ -445,13 +446,20 @@ NEXT_PAGE(level2_kernel_pgt) KERNEL_IMAGE_SIZE/PMD_SIZE) NEXT_PAGE(level2_fixmap_pgt) - .fill 506,8,0 - .quad level1_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC - /* 8MB reserved for vsyscalls + a 2MB hole = 4 + 1 entries */ - .fill 5,8,0 + .fill (512 - 4 - FIXMAP_PMD_NUM),8,0 + pgtno = 0 + .rept (FIXMAP_PMD_NUM) + .quad level1_fixmap_pgt + (pgtno << PAGE_SHIFT) - __START_KERNEL_map \ + + _PAGE_TABLE_NOENC; + pgtno = pgtno + 1 + .endr + /* 6 MB reserved space + a 2MB hole */ + .fill 4,8,0 NEXT_PAGE(level1_fixmap_pgt) + .rept (FIXMAP_PMD_NUM) .fill 512,8,0 + .endr #undef PMDS diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 1e6764648af3..013fe3d21dbb 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -28,6 +28,7 @@ #include <linux/sched/clock.h> #include <linux/mm.h> #include <linux/slab.h> +#include <linux/set_memory.h> #include <asm/hypervisor.h> #include <asm/mem_encrypt.h> @@ -61,9 +62,10 @@ early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall); (PAGE_SIZE / sizeof(struct pvclock_vsyscall_time_info)) static struct pvclock_vsyscall_time_info - hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __aligned(PAGE_SIZE); -static struct pvclock_wall_clock wall_clock; + hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __bss_decrypted __aligned(PAGE_SIZE); +static struct pvclock_wall_clock wall_clock __bss_decrypted; static DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu); +static struct pvclock_vsyscall_time_info *hvclock_mem; static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void) { @@ -236,6 +238,45 @@ static void kvm_shutdown(void) native_machine_shutdown(); } +static void __init kvmclock_init_mem(void) +{ + unsigned long ncpus; + unsigned int order; + struct page *p; + int r; + + if (HVC_BOOT_ARRAY_SIZE >= num_possible_cpus()) + return; + + ncpus = num_possible_cpus() - HVC_BOOT_ARRAY_SIZE; + order = get_order(ncpus * sizeof(*hvclock_mem)); + + p = alloc_pages(GFP_KERNEL, order); + if (!p) { + pr_warn("%s: failed to alloc %d pages", __func__, (1U << order)); + return; + } + + hvclock_mem = page_address(p); + + /* + * hvclock is shared between the guest and the hypervisor, must + * be mapped decrypted. + */ + if (sev_active()) { + r = set_memory_decrypted((unsigned long) hvclock_mem, + 1UL << order); + if (r) { + __free_pages(p, order); + hvclock_mem = NULL; + pr_warn("kvmclock: set_memory_decrypted() failed. Disabling\n"); + return; + } + } + + memset(hvclock_mem, 0, PAGE_SIZE << order); +} + static int __init kvm_setup_vsyscall_timeinfo(void) { #ifdef CONFIG_X86_64 @@ -250,6 +291,9 @@ static int __init kvm_setup_vsyscall_timeinfo(void) kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK; #endif + + kvmclock_init_mem(); + return 0; } early_initcall(kvm_setup_vsyscall_timeinfo); @@ -269,8 +313,10 @@ static int kvmclock_setup_percpu(unsigned int cpu) /* Use the static page for the first CPUs, allocate otherwise */ if (cpu < HVC_BOOT_ARRAY_SIZE) p = &hv_clock_boot[cpu]; + else if (hvclock_mem) + p = hvclock_mem + cpu - HVC_BOOT_ARRAY_SIZE; else - p = kzalloc(sizeof(*p), GFP_KERNEL); + return -ENOMEM; per_cpu(hv_clock_per_cpu, cpu) = p; return p ? 0 : -ENOMEM; diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index afdb303285f8..8dc69d82567e 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -91,7 +91,7 @@ unsigned paravirt_patch_call(void *insnbuf, if (len < 5) { #ifdef CONFIG_RETPOLINE - WARN_ONCE("Failing to patch indirect CALL in %ps\n", (void *)addr); + WARN_ONCE(1, "Failing to patch indirect CALL in %ps\n", (void *)addr); #endif return len; /* call too long for patch site */ } @@ -111,7 +111,7 @@ unsigned paravirt_patch_jmp(void *insnbuf, const void *target, if (len < 5) { #ifdef CONFIG_RETPOLINE - WARN_ONCE("Failing to patch indirect JMP in %ps\n", (void *)addr); + WARN_ONCE(1, "Failing to patch indirect JMP in %ps\n", (void *)addr); #endif return len; /* call too long for patch site */ } diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 6490f618e096..b52bd2b6cdb4 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -26,6 +26,7 @@ #include <asm/apic.h> #include <asm/intel-family.h> #include <asm/i8259.h> +#include <asm/uv/uv.h> unsigned int __read_mostly cpu_khz; /* TSC clocks / usec, not used here */ EXPORT_SYMBOL(cpu_khz); @@ -1433,6 +1434,9 @@ void __init tsc_early_init(void) { if (!boot_cpu_has(X86_FEATURE_TSC)) return; + /* Don't change UV TSC multi-chassis synchronization */ + if (is_early_uv_system()) + return; if (!determine_cpu_tsc_frequencies(true)) return; loops_per_jiffy = get_loops_per_jiffy(); diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 8bde0a419f86..5dd3317d761f 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -65,6 +65,23 @@ jiffies_64 = jiffies; #define ALIGN_ENTRY_TEXT_BEGIN . = ALIGN(PMD_SIZE); #define ALIGN_ENTRY_TEXT_END . = ALIGN(PMD_SIZE); +/* + * This section contains data which will be mapped as decrypted. Memory + * encryption operates on a page basis. Make this section PMD-aligned + * to avoid splitting the pages while mapping the section early. + * + * Note: We use a separate section so that only this section gets + * decrypted to avoid exposing more than we wish. + */ +#define BSS_DECRYPTED \ + . = ALIGN(PMD_SIZE); \ + __start_bss_decrypted = .; \ + *(.bss..decrypted); \ + . = ALIGN(PAGE_SIZE); \ + __start_bss_decrypted_unused = .; \ + . = ALIGN(PMD_SIZE); \ + __end_bss_decrypted = .; \ + #else #define X86_ALIGN_RODATA_BEGIN @@ -74,6 +91,7 @@ jiffies_64 = jiffies; #define ALIGN_ENTRY_TEXT_BEGIN #define ALIGN_ENTRY_TEXT_END +#define BSS_DECRYPTED #endif @@ -355,6 +373,7 @@ SECTIONS __bss_start = .; *(.bss..page_aligned) *(.bss) + BSS_DECRYPTED . = ALIGN(PAGE_SIZE); __bss_stop = .; } diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 17c0472c5b34..fbb0e6df121b 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1344,9 +1344,8 @@ EXPORT_SYMBOL_GPL(kvm_lapic_reg_read); static int apic_mmio_in_range(struct kvm_lapic *apic, gpa_t addr) { - return kvm_apic_hw_enabled(apic) && - addr >= apic->base_address && - addr < apic->base_address + LAPIC_MMIO_LENGTH; + return addr >= apic->base_address && + addr < apic->base_address + LAPIC_MMIO_LENGTH; } static int apic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this, @@ -1358,6 +1357,15 @@ static int apic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this, if (!apic_mmio_in_range(apic, address)) return -EOPNOTSUPP; + if (!kvm_apic_hw_enabled(apic) || apic_x2apic_mode(apic)) { + if (!kvm_check_has_quirk(vcpu->kvm, + KVM_X86_QUIRK_LAPIC_MMIO_HOLE)) + return -EOPNOTSUPP; + + memset(data, 0xff, len); + return 0; + } + kvm_lapic_reg_read(apic, offset, len, data); return 0; @@ -1917,6 +1925,14 @@ static int apic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this, if (!apic_mmio_in_range(apic, address)) return -EOPNOTSUPP; + if (!kvm_apic_hw_enabled(apic) || apic_x2apic_mode(apic)) { + if (!kvm_check_has_quirk(vcpu->kvm, + KVM_X86_QUIRK_LAPIC_MMIO_HOLE)) + return -EOPNOTSUPP; + + return 0; + } + /* * APIC register must be aligned on 128-bits boundary. * 32/64/128 bits registers must be accessed thru 32 bits. diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index e24ea7067373..51b953ad9d4e 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -249,6 +249,17 @@ static u64 __read_mostly shadow_nonpresent_or_rsvd_mask; */ static const u64 shadow_nonpresent_or_rsvd_mask_len = 5; +/* + * In some cases, we need to preserve the GFN of a non-present or reserved + * SPTE when we usurp the upper five bits of the physical address space to + * defend against L1TF, e.g. for MMIO SPTEs. To preserve the GFN, we'll + * shift bits of the GFN that overlap with shadow_nonpresent_or_rsvd_mask + * left into the reserved bits, i.e. the GFN in the SPTE will be split into + * high and low parts. This mask covers the lower bits of the GFN. + */ +static u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask; + + static void mmu_spte_set(u64 *sptep, u64 spte); static union kvm_mmu_page_role kvm_mmu_calc_root_page_role(struct kvm_vcpu *vcpu); @@ -357,9 +368,7 @@ static bool is_mmio_spte(u64 spte) static gfn_t get_mmio_spte_gfn(u64 spte) { - u64 mask = generation_mmio_spte_mask(MMIO_GEN_MASK) | shadow_mmio_mask | - shadow_nonpresent_or_rsvd_mask; - u64 gpa = spte & ~mask; + u64 gpa = spte & shadow_nonpresent_or_rsvd_lower_gfn_mask; gpa |= (spte >> shadow_nonpresent_or_rsvd_mask_len) & shadow_nonpresent_or_rsvd_mask; @@ -423,6 +432,8 @@ EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes); static void kvm_mmu_reset_all_pte_masks(void) { + u8 low_phys_bits; + shadow_user_mask = 0; shadow_accessed_mask = 0; shadow_dirty_mask = 0; @@ -437,12 +448,17 @@ static void kvm_mmu_reset_all_pte_masks(void) * appropriate mask to guard against L1TF attacks. Otherwise, it is * assumed that the CPU is not vulnerable to L1TF. */ + low_phys_bits = boot_cpu_data.x86_phys_bits; if (boot_cpu_data.x86_phys_bits < - 52 - shadow_nonpresent_or_rsvd_mask_len) + 52 - shadow_nonpresent_or_rsvd_mask_len) { shadow_nonpresent_or_rsvd_mask = rsvd_bits(boot_cpu_data.x86_phys_bits - shadow_nonpresent_or_rsvd_mask_len, boot_cpu_data.x86_phys_bits - 1); + low_phys_bits -= shadow_nonpresent_or_rsvd_mask_len; + } + shadow_nonpresent_or_rsvd_lower_gfn_mask = + GENMASK_ULL(low_phys_bits - 1, PAGE_SHIFT); } static int is_cpuid_PSE36(void) @@ -899,7 +915,7 @@ static void walk_shadow_page_lockless_end(struct kvm_vcpu *vcpu) { /* * Make sure the write to vcpu->mode is not reordered in front of - * reads to sptes. If it does, kvm_commit_zap_page() can see us + * reads to sptes. If it does, kvm_mmu_commit_zap_page() can see us * OUTSIDE_GUEST_MODE and proceed to free the shadow page table. */ smp_store_release(&vcpu->mode, OUTSIDE_GUEST_MODE); @@ -5417,7 +5433,12 @@ void kvm_mmu_setup(struct kvm_vcpu *vcpu) { MMU_WARN_ON(VALID_PAGE(vcpu->arch.mmu.root_hpa)); - kvm_init_mmu(vcpu, true); + /* + * kvm_mmu_setup() is called only on vCPU initialization. + * Therefore, no need to reset mmu roots as they are not yet + * initialized. + */ + kvm_init_mmu(vcpu, false); } static void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm, diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 89c4c5aa15f1..d96092b35936 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1226,8 +1226,7 @@ static __init int sev_hardware_setup(void) min_sev_asid = cpuid_edx(0x8000001F); /* Initialize SEV ASID bitmap */ - sev_asid_bitmap = kcalloc(BITS_TO_LONGS(max_sev_asid), - sizeof(unsigned long), GFP_KERNEL); + sev_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL); if (!sev_asid_bitmap) return 1; @@ -1405,7 +1404,7 @@ static __exit void svm_hardware_unsetup(void) int cpu; if (svm_sev_enabled()) - kfree(sev_asid_bitmap); + bitmap_free(sev_asid_bitmap); for_each_possible_cpu(cpu) svm_cpu_uninit(cpu); @@ -7149,6 +7148,8 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .check_intercept = svm_check_intercept, .handle_external_intr = svm_handle_external_intr, + .request_immediate_exit = __kvm_request_immediate_exit, + .sched_in = svm_sched_in, .pmu_ops = &amd_pmu_ops, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 533a327372c8..612fd17be635 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -121,7 +121,6 @@ module_param_named(pml, enable_pml, bool, S_IRUGO); #define MSR_BITMAP_MODE_X2APIC 1 #define MSR_BITMAP_MODE_X2APIC_APICV 2 -#define MSR_BITMAP_MODE_LM 4 #define KVM_VMX_TSC_MULTIPLIER_MAX 0xffffffffffffffffULL @@ -397,6 +396,7 @@ struct loaded_vmcs { int cpu; bool launched; bool nmi_known_unmasked; + bool hv_timer_armed; /* Support for vnmi-less CPUs */ int soft_vnmi_blocked; ktime_t entry_time; @@ -856,6 +856,7 @@ struct nested_vmx { /* to migrate it to L2 if VM_ENTRY_LOAD_DEBUG_CONTROLS is off */ u64 vmcs01_debugctl; + u64 vmcs01_guest_bndcfgs; u16 vpid02; u16 last_vpid; @@ -1019,6 +1020,8 @@ struct vcpu_vmx { int ple_window; bool ple_window_dirty; + bool req_immediate_exit; + /* Support for PML */ #define PML_ENTITY_NUM 512 struct page *pml_pg; @@ -2864,6 +2867,8 @@ static void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) u16 fs_sel, gs_sel; int i; + vmx->req_immediate_exit = false; + if (vmx->loaded_cpu_state) return; @@ -2894,8 +2899,7 @@ static void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) vmx->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE); } - if (is_long_mode(&vmx->vcpu)) - wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); + wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); #else savesegment(fs, fs_sel); savesegment(gs, gs_sel); @@ -2946,8 +2950,7 @@ static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx) vmx->loaded_cpu_state = NULL; #ifdef CONFIG_X86_64 - if (is_long_mode(&vmx->vcpu)) - rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); + rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); #endif if (host_state->ldt_sel || (host_state->gs_sel & 7)) { kvm_load_ldt(host_state->ldt_sel); @@ -2975,24 +2978,19 @@ static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx) #ifdef CONFIG_X86_64 static u64 vmx_read_guest_kernel_gs_base(struct vcpu_vmx *vmx) { - if (is_long_mode(&vmx->vcpu)) { - preempt_disable(); - if (vmx->loaded_cpu_state) - rdmsrl(MSR_KERNEL_GS_BASE, - vmx->msr_guest_kernel_gs_base); - preempt_enable(); - } + preempt_disable(); + if (vmx->loaded_cpu_state) + rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); + preempt_enable(); return vmx->msr_guest_kernel_gs_base; } static void vmx_write_guest_kernel_gs_base(struct vcpu_vmx *vmx, u64 data) { - if (is_long_mode(&vmx->vcpu)) { - preempt_disable(); - if (vmx->loaded_cpu_state) - wrmsrl(MSR_KERNEL_GS_BASE, data); - preempt_enable(); - } + preempt_disable(); + if (vmx->loaded_cpu_state) + wrmsrl(MSR_KERNEL_GS_BASE, data); + preempt_enable(); vmx->msr_guest_kernel_gs_base = data; } #endif @@ -3528,9 +3526,6 @@ static void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, bool apicv) VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER | VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT; - if (kvm_mpx_supported()) - msrs->exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS; - /* We support free control of debug control saving. */ msrs->exit_ctls_low &= ~VM_EXIT_SAVE_DEBUG_CONTROLS; @@ -3547,8 +3542,6 @@ static void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, bool apicv) VM_ENTRY_LOAD_IA32_PAT; msrs->entry_ctls_high |= (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | VM_ENTRY_LOAD_IA32_EFER); - if (kvm_mpx_supported()) - msrs->entry_ctls_high |= VM_ENTRY_LOAD_BNDCFGS; /* We support free control of debug control loading. */ msrs->entry_ctls_low &= ~VM_ENTRY_LOAD_DEBUG_CONTROLS; @@ -3596,12 +3589,12 @@ static void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, bool apicv) msrs->secondary_ctls_high); msrs->secondary_ctls_low = 0; msrs->secondary_ctls_high &= - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | SECONDARY_EXEC_DESC | SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | SECONDARY_EXEC_WBINVD_EXITING; + /* * We can emulate "VMCS shadowing," even if the hardware * doesn't support it. @@ -3658,6 +3651,10 @@ static void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, bool apicv) msrs->secondary_ctls_high |= SECONDARY_EXEC_UNRESTRICTED_GUEST; + if (flexpriority_enabled) + msrs->secondary_ctls_high |= + SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; + /* miscellaneous data */ rdmsr(MSR_IA32_VMX_MISC, msrs->misc_low, @@ -5068,19 +5065,6 @@ static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer) if (!msr) return; - /* - * MSR_KERNEL_GS_BASE is not intercepted when the guest is in - * 64-bit mode as a 64-bit kernel may frequently access the - * MSR. This means we need to manually save/restore the MSR - * when switching between guest and host state, but only if - * the guest is in 64-bit mode. Sync our cached value if the - * guest is transitioning to 32-bit mode and the CPU contains - * guest state, i.e. the cache is stale. - */ -#ifdef CONFIG_X86_64 - if (!(efer & EFER_LMA)) - (void)vmx_read_guest_kernel_gs_base(vmx); -#endif vcpu->arch.efer = efer; if (efer & EFER_LMA) { vm_entry_controls_setbit(to_vmx(vcpu), VM_ENTRY_IA32E_MODE); @@ -5393,9 +5377,10 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) * To use VMXON (and later other VMX instructions), a guest * must first be able to turn on cr4.VMXE (see handle_vmon()). * So basically the check on whether to allow nested VMX - * is here. + * is here. We operate under the default treatment of SMM, + * so VMX cannot be enabled under SMM. */ - if (!nested_vmx_allowed(vcpu)) + if (!nested_vmx_allowed(vcpu) || is_smm(vcpu)) return 1; } @@ -6072,9 +6057,6 @@ static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu) mode |= MSR_BITMAP_MODE_X2APIC_APICV; } - if (is_long_mode(vcpu)) - mode |= MSR_BITMAP_MODE_LM; - return mode; } @@ -6115,9 +6097,6 @@ static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu) if (!changed) return; - vmx_set_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW, - !(mode & MSR_BITMAP_MODE_LM)); - if (changed & (MSR_BITMAP_MODE_X2APIC | MSR_BITMAP_MODE_X2APIC_APICV)) vmx_update_msr_bitmap_x2apic(msr_bitmap, mode); @@ -6183,6 +6162,32 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) nested_mark_vmcs12_pages_dirty(vcpu); } +static u8 vmx_get_rvi(void) +{ + return vmcs_read16(GUEST_INTR_STATUS) & 0xff; +} + +static bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + void *vapic_page; + u32 vppr; + int rvi; + + if (WARN_ON_ONCE(!is_guest_mode(vcpu)) || + !nested_cpu_has_vid(get_vmcs12(vcpu)) || + WARN_ON_ONCE(!vmx->nested.virtual_apic_page)) + return false; + + rvi = vmx_get_rvi(); + + vapic_page = kmap(vmx->nested.virtual_apic_page); + vppr = *((u32 *)(vapic_page + APIC_PROCPRI)); + kunmap(vmx->nested.virtual_apic_page); + + return ((rvi & 0xf0) > (vppr & 0xf0)); +} + static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu, bool nested) { @@ -7966,6 +7971,9 @@ static __init int hardware_setup(void) kvm_x86_ops->enable_log_dirty_pt_masked = NULL; } + if (!cpu_has_vmx_preemption_timer()) + kvm_x86_ops->request_immediate_exit = __kvm_request_immediate_exit; + if (cpu_has_vmx_preemption_timer() && enable_preemption_timer) { u64 vmx_msr; @@ -9208,7 +9216,8 @@ static int handle_pml_full(struct kvm_vcpu *vcpu) static int handle_preemption_timer(struct kvm_vcpu *vcpu) { - kvm_lapic_expired_hv_timer(vcpu); + if (!to_vmx(vcpu)->req_immediate_exit) + kvm_lapic_expired_hv_timer(vcpu); return 1; } @@ -10214,15 +10223,16 @@ static void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu) if (!lapic_in_kernel(vcpu)) return; + if (!flexpriority_enabled && + !cpu_has_vmx_virtualize_x2apic_mode()) + return; + /* Postpone execution until vmcs01 is the current VMCS. */ if (is_guest_mode(vcpu)) { to_vmx(vcpu)->nested.change_vmcs01_virtual_apic_mode = true; return; } - if (!cpu_need_tpr_shadow(vcpu)) - return; - sec_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); sec_exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE); @@ -10344,6 +10354,14 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) return max_irr; } +static u8 vmx_has_apicv_interrupt(struct kvm_vcpu *vcpu) +{ + u8 rvi = vmx_get_rvi(); + u8 vppr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_PROCPRI); + + return ((rvi & 0xf0) > (vppr & 0xf0)); +} + static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) { if (!kvm_vcpu_apicv_active(vcpu)) @@ -10595,24 +10613,43 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx) msrs[i].host, false); } -static void vmx_arm_hv_timer(struct kvm_vcpu *vcpu) +static void vmx_arm_hv_timer(struct vcpu_vmx *vmx, u32 val) +{ + vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, val); + if (!vmx->loaded_vmcs->hv_timer_armed) + vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL, + PIN_BASED_VMX_PREEMPTION_TIMER); + vmx->loaded_vmcs->hv_timer_armed = true; +} + +static void vmx_update_hv_timer(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); u64 tscl; u32 delta_tsc; - if (vmx->hv_deadline_tsc == -1) + if (vmx->req_immediate_exit) { + vmx_arm_hv_timer(vmx, 0); return; + } - tscl = rdtsc(); - if (vmx->hv_deadline_tsc > tscl) - /* sure to be 32 bit only because checked on set_hv_timer */ - delta_tsc = (u32)((vmx->hv_deadline_tsc - tscl) >> - cpu_preemption_timer_multi); - else - delta_tsc = 0; + if (vmx->hv_deadline_tsc != -1) { + tscl = rdtsc(); + if (vmx->hv_deadline_tsc > tscl) + /* set_hv_timer ensures the delta fits in 32-bits */ + delta_tsc = (u32)((vmx->hv_deadline_tsc - tscl) >> + cpu_preemption_timer_multi); + else + delta_tsc = 0; + + vmx_arm_hv_timer(vmx, delta_tsc); + return; + } - vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, delta_tsc); + if (vmx->loaded_vmcs->hv_timer_armed) + vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL, + PIN_BASED_VMX_PREEMPTION_TIMER); + vmx->loaded_vmcs->hv_timer_armed = false; } static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) @@ -10672,7 +10709,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) atomic_switch_perf_msrs(vmx); - vmx_arm_hv_timer(vcpu); + vmx_update_hv_timer(vcpu); /* * If this vCPU has touched SPEC_CTRL, restore the guest's value if @@ -11214,6 +11251,23 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu) #undef cr4_fixed1_update } +static void nested_vmx_entry_exit_ctls_update(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + if (kvm_mpx_supported()) { + bool mpx_enabled = guest_cpuid_has(vcpu, X86_FEATURE_MPX); + + if (mpx_enabled) { + vmx->nested.msrs.entry_ctls_high |= VM_ENTRY_LOAD_BNDCFGS; + vmx->nested.msrs.exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS; + } else { + vmx->nested.msrs.entry_ctls_high &= ~VM_ENTRY_LOAD_BNDCFGS; + vmx->nested.msrs.exit_ctls_high &= ~VM_EXIT_CLEAR_BNDCFGS; + } + } +} + static void vmx_cpuid_update(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -11230,8 +11284,10 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &= ~FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX; - if (nested_vmx_allowed(vcpu)) + if (nested_vmx_allowed(vcpu)) { nested_vmx_cr_fixed1_bits_update(vcpu); + nested_vmx_entry_exit_ctls_update(vcpu); + } } static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) @@ -11427,16 +11483,18 @@ static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu) u64 preemption_timeout = get_vmcs12(vcpu)->vmx_preemption_timer_value; struct vcpu_vmx *vmx = to_vmx(vcpu); - if (vcpu->arch.virtual_tsc_khz == 0) - return; - - /* Make sure short timeouts reliably trigger an immediate vmexit. - * hrtimer_start does not guarantee this. */ - if (preemption_timeout <= 1) { + /* + * A timer value of zero is architecturally guaranteed to cause + * a VMExit prior to executing any instructions in the guest. + */ + if (preemption_timeout == 0) { vmx_preemption_timer_fn(&vmx->nested.preemption_timer); return; } + if (vcpu->arch.virtual_tsc_khz == 0) + return; + preemption_timeout <<= VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE; preemption_timeout *= 1000000; do_div(preemption_timeout, vcpu->arch.virtual_tsc_khz); @@ -11646,11 +11704,15 @@ static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu, * bits 15:8 should be zero in posted_intr_nv, * the descriptor address has been already checked * in nested_get_vmcs12_pages. + * + * bits 5:0 of posted_intr_desc_addr should be zero. */ if (nested_cpu_has_posted_intr(vmcs12) && (!nested_cpu_has_vid(vmcs12) || !nested_exit_intr_ack_set(vcpu) || - vmcs12->posted_intr_nv & 0xff00)) + (vmcs12->posted_intr_nv & 0xff00) || + (vmcs12->posted_intr_desc_addr & 0x3f) || + (!page_address_valid(vcpu, vmcs12->posted_intr_desc_addr)))) return -EINVAL; /* tpr shadow is needed by all apicv features. */ @@ -11993,8 +12055,13 @@ static void prepare_vmcs02_full(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) set_cr4_guest_host_mask(vmx); - if (vmx_mpx_supported()) - vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs); + if (kvm_mpx_supported()) { + if (vmx->nested.nested_run_pending && + (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)) + vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs); + else + vmcs_write64(GUEST_BNDCFGS, vmx->nested.vmcs01_guest_bndcfgs); + } if (enable_vpid) { if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02) @@ -12076,11 +12143,10 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, exec_control = vmcs12->pin_based_vm_exec_control; - /* Preemption timer setting is only taken from vmcs01. */ - exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER; + /* Preemption timer setting is computed directly in vmx_vcpu_run. */ exec_control |= vmcs_config.pin_based_exec_ctrl; - if (vmx->hv_deadline_tsc == -1) - exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER; + exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER; + vmx->loaded_vmcs->hv_timer_armed = false; /* Posted interrupts setting is only taken from vmcs12. */ if (nested_cpu_has_posted_intr(vmcs12)) { @@ -12318,6 +12384,9 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT) return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + if (nested_cpu_has_vpid(vmcs12) && !vmcs12->virtual_processor_id) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + if (nested_vmx_check_io_bitmap_controls(vcpu, vmcs12)) return VMXERR_ENTRY_INVALID_CONTROL_FIELD; @@ -12537,15 +12606,21 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual) struct vmcs12 *vmcs12 = get_vmcs12(vcpu); bool from_vmentry = !!exit_qual; u32 dummy_exit_qual; - u32 vmcs01_cpu_exec_ctrl; + bool evaluate_pending_interrupts; int r = 0; - vmcs01_cpu_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); + evaluate_pending_interrupts = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL) & + (CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_VIRTUAL_NMI_PENDING); + if (likely(!evaluate_pending_interrupts) && kvm_vcpu_apicv_active(vcpu)) + evaluate_pending_interrupts |= vmx_has_apicv_interrupt(vcpu); enter_guest_mode(vcpu); if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) vmx->nested.vmcs01_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL); + if (kvm_mpx_supported() && + !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)) + vmx->nested.vmcs01_guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS); vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02); vmx_segment_cache_clear(vmx); @@ -12585,16 +12660,14 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual) * to L1 or delivered directly to L2 (e.g. In case L1 don't * intercept EXTERNAL_INTERRUPT). * - * Usually this would be handled by L0 requesting a - * IRQ/NMI window by setting VMCS accordingly. However, - * this setting was done on VMCS01 and now VMCS02 is active - * instead. Thus, we force L0 to perform pending event - * evaluation by requesting a KVM_REQ_EVENT. - */ - if (vmcs01_cpu_exec_ctrl & - (CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_VIRTUAL_NMI_PENDING)) { + * Usually this would be handled by the processor noticing an + * IRQ/NMI window request, or checking RVI during evaluation of + * pending virtual interrupts. However, this setting was done + * on VMCS01 and now VMCS02 is active instead. Thus, we force L0 + * to perform pending event evaluation by requesting a KVM_REQ_EVENT. + */ + if (unlikely(evaluate_pending_interrupts)) kvm_make_request(KVM_REQ_EVENT, vcpu); - } /* * Note no nested_vmx_succeed or nested_vmx_fail here. At this point @@ -12863,6 +12936,11 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) return 0; } +static void vmx_request_immediate_exit(struct kvm_vcpu *vcpu) +{ + to_vmx(vcpu)->req_immediate_exit = true; +} + static u32 vmx_get_preemption_timer_value(struct kvm_vcpu *vcpu) { ktime_t remaining = @@ -13253,12 +13331,7 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); - if (vmx->hv_deadline_tsc == -1) - vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL, - PIN_BASED_VMX_PREEMPTION_TIMER); - else - vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL, - PIN_BASED_VMX_PREEMPTION_TIMER); + if (kvm_has_tsc_control) decache_tsc_multiplier(vmx); @@ -13462,18 +13535,12 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc) return -ERANGE; vmx->hv_deadline_tsc = tscl + delta_tsc; - vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL, - PIN_BASED_VMX_PREEMPTION_TIMER); - return delta_tsc == 0; } static void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu) { - struct vcpu_vmx *vmx = to_vmx(vcpu); - vmx->hv_deadline_tsc = -1; - vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL, - PIN_BASED_VMX_PREEMPTION_TIMER); + to_vmx(vcpu)->hv_deadline_tsc = -1; } #endif @@ -13954,6 +14021,14 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, ~(KVM_STATE_NESTED_SMM_GUEST_MODE | KVM_STATE_NESTED_SMM_VMXON)) return -EINVAL; + /* + * SMM temporarily disables VMX, so we cannot be in guest mode, + * nor can VMLAUNCH/VMRESUME be pending. Outside SMM, SMM flags + * must be zero. + */ + if (is_smm(vcpu) ? kvm_state->flags : kvm_state->vmx.smm.flags) + return -EINVAL; + if ((kvm_state->vmx.smm.flags & KVM_STATE_NESTED_SMM_GUEST_MODE) && !(kvm_state->vmx.smm.flags & KVM_STATE_NESTED_SMM_VMXON)) return -EINVAL; @@ -14097,6 +14172,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .apicv_post_state_restore = vmx_apicv_post_state_restore, .hwapic_irr_update = vmx_hwapic_irr_update, .hwapic_isr_update = vmx_hwapic_isr_update, + .guest_apic_has_interrupt = vmx_guest_apic_has_interrupt, .sync_pir_to_irr = vmx_sync_pir_to_irr, .deliver_posted_interrupt = vmx_deliver_posted_interrupt, @@ -14130,6 +14206,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .umip_emulated = vmx_umip_emulated, .check_nested_events = vmx_check_nested_events, + .request_immediate_exit = vmx_request_immediate_exit, .sched_in = vmx_sched_in, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 542f6315444d..ca717737347e 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -628,7 +628,7 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu) gfn_t gfn; int r; - if (is_long_mode(vcpu) || !is_pae(vcpu)) + if (is_long_mode(vcpu) || !is_pae(vcpu) || !is_paging(vcpu)) return false; if (!test_bit(VCPU_EXREG_PDPTR, @@ -2537,7 +2537,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_PLATFORM_INFO: if (!msr_info->host_initiated || - data & ~MSR_PLATFORM_INFO_CPUID_FAULT || (!(data & MSR_PLATFORM_INFO_CPUID_FAULT) && cpuid_fault_enabled(vcpu))) return 1; @@ -2780,6 +2779,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vcpu->arch.osvw.status; break; case MSR_PLATFORM_INFO: + if (!msr_info->host_initiated && + !vcpu->kvm->arch.guest_can_read_msr_platform_info) + return 1; msr_info->data = vcpu->arch.msr_platform_info; break; case MSR_MISC_FEATURES_ENABLES: @@ -2927,6 +2929,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_SPLIT_IRQCHIP: case KVM_CAP_IMMEDIATE_EXIT: case KVM_CAP_GET_MSR_FEATURES: + case KVM_CAP_MSR_PLATFORM_INFO: r = 1; break; case KVM_CAP_SYNC_REGS: @@ -4007,19 +4010,23 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; BUILD_BUG_ON(sizeof(user_data_size) != sizeof(user_kvm_nested_state->size)); + r = -EFAULT; if (get_user(user_data_size, &user_kvm_nested_state->size)) - return -EFAULT; + break; r = kvm_x86_ops->get_nested_state(vcpu, user_kvm_nested_state, user_data_size); if (r < 0) - return r; + break; if (r > user_data_size) { if (put_user(r, &user_kvm_nested_state->size)) - return -EFAULT; - return -E2BIG; + r = -EFAULT; + else + r = -E2BIG; + break; } + r = 0; break; } @@ -4031,19 +4038,21 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (!kvm_x86_ops->set_nested_state) break; + r = -EFAULT; if (copy_from_user(&kvm_state, user_kvm_nested_state, sizeof(kvm_state))) - return -EFAULT; + break; + r = -EINVAL; if (kvm_state.size < sizeof(kvm_state)) - return -EINVAL; + break; if (kvm_state.flags & ~(KVM_STATE_NESTED_RUN_PENDING | KVM_STATE_NESTED_GUEST_MODE)) - return -EINVAL; + break; /* nested_run_pending implies guest_mode. */ if (kvm_state.flags == KVM_STATE_NESTED_RUN_PENDING) - return -EINVAL; + break; r = kvm_x86_ops->set_nested_state(vcpu, user_kvm_nested_state, &kvm_state); break; @@ -4350,6 +4359,10 @@ split_irqchip_unlock: kvm->arch.pause_in_guest = true; r = 0; break; + case KVM_CAP_MSR_PLATFORM_INFO: + kvm->arch.guest_can_read_msr_platform_info = cap->args[0]; + r = 0; + break; default: r = -EINVAL; break; @@ -4685,7 +4698,7 @@ static void kvm_init_msr_list(void) */ switch (msrs_to_save[i]) { case MSR_IA32_BNDCFGS: - if (!kvm_x86_ops->mpx_supported()) + if (!kvm_mpx_supported()) continue; break; case MSR_TSC_AUX: @@ -7361,6 +7374,12 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_vcpu_reload_apic_access_page); +void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu) +{ + smp_send_reschedule(vcpu->cpu); +} +EXPORT_SYMBOL_GPL(__kvm_request_immediate_exit); + /* * Returns 1 to let vcpu_run() continue the guest execution loop without * exiting to the userspace. Otherwise, the value will be returned to the @@ -7565,7 +7584,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (req_immediate_exit) { kvm_make_request(KVM_REQ_EVENT, vcpu); - smp_send_reschedule(vcpu->cpu); + kvm_x86_ops->request_immediate_exit(vcpu); } trace_kvm_entry(vcpu->vcpu_id); @@ -7829,6 +7848,29 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu) return 0; } +/* Swap (qemu) user FPU context for the guest FPU context. */ +static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) +{ + preempt_disable(); + copy_fpregs_to_fpstate(&vcpu->arch.user_fpu); + /* PKRU is separately restored in kvm_x86_ops->run. */ + __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state, + ~XFEATURE_MASK_PKRU); + preempt_enable(); + trace_kvm_fpu(1); +} + +/* When vcpu_run ends, restore user space FPU context. */ +static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) +{ + preempt_disable(); + copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu); + copy_kernel_to_fpregs(&vcpu->arch.user_fpu.state); + preempt_enable(); + ++vcpu->stat.fpu_reload; + trace_kvm_fpu(0); +} + int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { int r; @@ -8177,7 +8219,7 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) kvm_update_cpuid(vcpu); idx = srcu_read_lock(&vcpu->kvm->srcu); - if (!is_long_mode(vcpu) && is_pae(vcpu)) { + if (!is_long_mode(vcpu) && is_pae(vcpu) && is_paging(vcpu)) { load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); mmu_reset_needed = 1; } @@ -8406,29 +8448,6 @@ static void fx_init(struct kvm_vcpu *vcpu) vcpu->arch.cr0 |= X86_CR0_ET; } -/* Swap (qemu) user FPU context for the guest FPU context. */ -void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) -{ - preempt_disable(); - copy_fpregs_to_fpstate(&vcpu->arch.user_fpu); - /* PKRU is separately restored in kvm_x86_ops->run. */ - __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state, - ~XFEATURE_MASK_PKRU); - preempt_enable(); - trace_kvm_fpu(1); -} - -/* When vcpu_run ends, restore user space FPU context. */ -void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) -{ - preempt_disable(); - copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu); - copy_kernel_to_fpregs(&vcpu->arch.user_fpu.state); - preempt_enable(); - ++vcpu->stat.fpu_reload; - trace_kvm_fpu(0); -} - void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) { void *wbinvd_dirty_mask = vcpu->arch.wbinvd_dirty_mask; @@ -8852,6 +8871,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm->arch.kvmclock_offset = -ktime_get_boot_ns(); pvclock_update_vm_gtod_copy(kvm); + kvm->arch.guest_can_read_msr_platform_info = true; + INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn); INIT_DELAYED_WORK(&kvm->arch.kvmclock_sync_work, kvmclock_sync_fn); @@ -9200,6 +9221,13 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm, kvm_page_track_flush_slot(kvm, slot); } +static inline bool kvm_guest_apic_has_interrupt(struct kvm_vcpu *vcpu) +{ + return (is_guest_mode(vcpu) && + kvm_x86_ops->guest_apic_has_interrupt && + kvm_x86_ops->guest_apic_has_interrupt(vcpu)); +} + static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) { if (!list_empty_careful(&vcpu->async_pf.done)) @@ -9224,7 +9252,8 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) return true; if (kvm_arch_interrupt_allowed(vcpu) && - kvm_cpu_has_interrupt(vcpu)) + (kvm_cpu_has_interrupt(vcpu) || + kvm_guest_apic_has_interrupt(vcpu))) return true; if (kvm_hv_has_stimer_pending(vcpu)) diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 7a8fc26c1115..faca978ebf9d 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -815,10 +815,14 @@ void free_kernel_image_pages(void *begin, void *end) set_memory_np_noalias(begin_ul, len_pages); } +void __weak mem_encrypt_free_decrypted_mem(void) { } + void __ref free_initmem(void) { e820__reallocate_tables(); + mem_encrypt_free_decrypted_mem(); + free_kernel_image_pages(&__init_begin, &__init_end); } diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index b2de398d1fd3..006f373f54ab 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -348,6 +348,30 @@ bool sev_active(void) EXPORT_SYMBOL(sev_active); /* Architecture __weak replacement functions */ +void __init mem_encrypt_free_decrypted_mem(void) +{ + unsigned long vaddr, vaddr_end, npages; + int r; + + vaddr = (unsigned long)__start_bss_decrypted_unused; + vaddr_end = (unsigned long)__end_bss_decrypted; + npages = (vaddr_end - vaddr) >> PAGE_SHIFT; + + /* + * The unused memory range was mapped decrypted, change the encryption + * attribute from decrypted to encrypted before freeing it. + */ + if (mem_encrypt_active()) { + r = set_memory_encrypted(vaddr, npages); + if (r) { + pr_warn("failed to free unused decrypted pages\n"); + return; + } + } + + free_init_pages("unused decrypted", vaddr, vaddr_end); +} + void __init mem_encrypt_init(void) { if (!sme_me_mask) diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index ae394552fb94..089e78c4effd 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -637,6 +637,15 @@ void __native_set_fixmap(enum fixed_addresses idx, pte_t pte) { unsigned long address = __fix_to_virt(idx); +#ifdef CONFIG_X86_64 + /* + * Ensure that the static initial page tables are covering the + * fixmap completely. + */ + BUILD_BUG_ON(__end_of_permanent_fixed_addresses > + (FIXMAP_PMD_NUM * PTRS_PER_PTE)); +#endif + if (idx >= __end_of_fixed_addresses) { BUG(); return; diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 2fe5c9b1816b..dd461c0167ef 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1907,7 +1907,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) /* L3_k[511] -> level2_fixmap_pgt */ convert_pfn_mfn(level3_kernel_pgt); - /* L3_k[511][506] -> level1_fixmap_pgt */ + /* L3_k[511][508-FIXMAP_PMD_NUM ... 507] -> level1_fixmap_pgt */ convert_pfn_mfn(level2_fixmap_pgt); /* We get [511][511] and have Xen's version of level2_kernel_pgt */ @@ -1952,7 +1952,11 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO); set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO); set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO); - set_page_prot(level1_fixmap_pgt, PAGE_KERNEL_RO); + + for (i = 0; i < FIXMAP_PMD_NUM; i++) { + set_page_prot(level1_fixmap_pgt + i * PTRS_PER_PTE, + PAGE_KERNEL_RO); + } /* Pin down new L4 */ pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE, diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c index 7d00d4ad44d4..95997e6c0696 100644 --- a/arch/x86/xen/pmu.c +++ b/arch/x86/xen/pmu.c @@ -478,7 +478,7 @@ static void xen_convert_regs(const struct xen_pmu_regs *xen_regs, irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id) { int err, ret = IRQ_NONE; - struct pt_regs regs; + struct pt_regs regs = {0}; const struct xen_pmu_data *xenpmu_data = get_xenpmu_data(); uint8_t xenpmu_flags = get_xenpmu_flags(); |
